diff options
Diffstat (limited to 'net')
125 files changed, 2345 insertions, 1328 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9424f3718ea7..2fb2d88e8c2e 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -341,7 +341,7 @@ static void __vlan_device_event(struct net_device *dev, unsigned long event) static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vlan_group *grp; struct vlan_info *vlan_info; int i, flgs; diff --git a/net/Kconfig b/net/Kconfig index 2ddc9046868e..523e43e6da1b 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -218,6 +218,7 @@ source "net/batman-adv/Kconfig" source "net/openvswitch/Kconfig" source "net/vmw_vsock/Kconfig" source "net/netlink/Kconfig" +source "net/mpls/Kconfig" config RPS boolean @@ -259,6 +260,18 @@ config BPF_JIT packet sniffing (libpcap/tcpdump). Note : Admin should enable this feature changing /proc/sys/net/core/bpf_jit_enable +config NET_FLOW_LIMIT + boolean + depends on RPS + default y + ---help--- + The network stack has to drop packets when a receive processing CPU's + backlog reaches netdev_max_backlog. If a few out of many active flows + generate the vast majority of load, drop their traffic earlier to + maintain capacity for the other flows. This feature provides servers + with many clients some protection against DoS by a single (spoofed) + flow that greatly exceeds average workload. + menu "Network testing" config NET_PKTGEN diff --git a/net/Makefile b/net/Makefile index 091e7b04f301..9492e8cb64e9 100644 --- a/net/Makefile +++ b/net/Makefile @@ -70,3 +70,4 @@ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ obj-$(CONFIG_NFC) += nfc/ obj-$(CONFIG_OPENVSWITCH) += openvswitch/ obj-$(CONFIG_VSOCKETS) += vmw_vsock/ +obj-$(CONFIG_NET_MPLS_GSO) += mpls/ diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 173a2e82f486..690356fa52b9 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -332,7 +332,7 @@ static void aarp_expire_timeout(unsigned long unused) static int aarp_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); int ct; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index ef12839a7cfe..7fee50d637f9 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -644,7 +644,7 @@ static inline void atalk_dev_down(struct net_device *dev) static int ddp_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/atm/clip.c b/net/atm/clip.c index 8ae3a7879335..8215f7cb170b 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -539,9 +539,9 @@ static int clip_create(int number) } static int clip_device_event(struct notifier_block *this, unsigned long event, - void *arg) + void *ptr) { - struct net_device *dev = arg; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; @@ -575,6 +575,7 @@ static int clip_inet_event(struct notifier_block *this, unsigned long event, void *ifa) { struct in_device *in_dev; + struct netdev_notifier_info info; in_dev = ((struct in_ifaddr *)ifa)->ifa_dev; /* @@ -583,7 +584,8 @@ static int clip_inet_event(struct notifier_block *this, unsigned long event, */ if (event != NETDEV_UP) return NOTIFY_DONE; - return clip_device_event(this, NETDEV_CHANGE, in_dev->dev); + netdev_notifier_info_init(&info, in_dev->dev); + return clip_device_event(this, NETDEV_CHANGE, &info); } static struct notifier_block clip_dev_notifier = { diff --git a/net/atm/mpc.c b/net/atm/mpc.c index d4cc1be5c364..3af12755cd04 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -998,14 +998,12 @@ int msg_to_mpoad(struct k_message *mesg, struct mpoa_client *mpc) } static int mpoa_event_listener(struct notifier_block *mpoa_notifier, - unsigned long event, void *dev_ptr) + unsigned long event, void *ptr) { - struct net_device *dev; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct mpoa_client *mpc; struct lec_priv *priv; - dev = dev_ptr; - if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index e277e38f736b..4b4d2b779ec1 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -111,9 +111,9 @@ again: * Handle device status changes. */ static int ax25_device_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; @@ -1974,7 +1974,7 @@ static struct packet_type ax25_packet_type __read_mostly = { }; static struct notifier_block ax25_dev_notifier = { - .notifier_call =ax25_device_event, + .notifier_call = ax25_device_event, }; static int __init ax25_init(void) diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index acbac2a9c62f..489bb36f1b94 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -32,7 +32,6 @@ batman-adv-y += icmp_socket.o batman-adv-y += main.o batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o batman-adv-y += originator.o -batman-adv-y += ring_buffer.o batman-adv-y += routing.o batman-adv-y += send.o batman-adv-y += soft-interface.o diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 071f288b77a8..d07323b3e9b8 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -19,7 +19,6 @@ #include "main.h" #include "translation-table.h" -#include "ring_buffer.h" #include "originator.h" #include "routing.h" #include "gateway_common.h" @@ -29,16 +28,57 @@ #include "bat_algo.h" #include "network-coding.h" +/** + * batadv_ring_buffer_set - update the ring buffer with the given value + * @lq_recv: pointer to the ring buffer + * @lq_index: index to store the value at + * @value: value to store in the ring buffer + */ +static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, + uint8_t value) +{ + lq_recv[*lq_index] = value; + *lq_index = (*lq_index + 1) % BATADV_TQ_GLOBAL_WINDOW_SIZE; +} + +/** + * batadv_ring_buffer_set - compute the average of all non-zero values stored + * in the given ring buffer + * @lq_recv: pointer to the ring buffer + * + * Returns computed average value. + */ +static uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]) +{ + const uint8_t *ptr; + uint16_t count = 0, i = 0, sum = 0; + + ptr = lq_recv; + + while (i < BATADV_TQ_GLOBAL_WINDOW_SIZE) { + if (*ptr != 0) { + count++; + sum += *ptr; + } + + i++; + ptr++; + } + + if (count == 0) + return 0; + + return (uint8_t)(sum / count); +} static struct batadv_neigh_node * batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, const uint8_t *neigh_addr, struct batadv_orig_node *orig_node, - struct batadv_orig_node *orig_neigh, __be32 seqno) + struct batadv_orig_node *orig_neigh) { struct batadv_neigh_node *neigh_node; - neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, - ntohl(seqno)); + neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr); if (!neigh_node) goto out; @@ -413,18 +453,16 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, else skb_size = packet_len; - skb_size += ETH_HLEN + NET_IP_ALIGN; + skb_size += ETH_HLEN; - forw_packet_aggr->skb = dev_alloc_skb(skb_size); + forw_packet_aggr->skb = netdev_alloc_skb_ip_align(NULL, skb_size); if (!forw_packet_aggr->skb) { if (!own_packet) atomic_inc(&bat_priv->batman_queue_left); kfree(forw_packet_aggr); goto out; } - skb_reserve(forw_packet_aggr->skb, ETH_HLEN + NET_IP_ALIGN); - - INIT_HLIST_NODE(&forw_packet_aggr->list); + skb_reserve(forw_packet_aggr->skb, ETH_HLEN); skb_buff = skb_put(forw_packet_aggr->skb, packet_len); forw_packet_aggr->packet_len = packet_len; @@ -590,6 +628,41 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, if_incoming, 0, batadv_iv_ogm_fwd_send_time()); } +/** + * batadv_iv_ogm_slide_own_bcast_window - bitshift own OGM broadcast windows for + * the given interface + * @hard_iface: the interface for which the windows have to be shifted + */ +static void +batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) +{ + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct hlist_head *head; + struct batadv_orig_node *orig_node; + unsigned long *word; + uint32_t i; + size_t word_index; + uint8_t *w; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + spin_lock_bh(&orig_node->ogm_cnt_lock); + word_index = hard_iface->if_num * BATADV_NUM_WORDS; + word = &(orig_node->bcast_own[word_index]); + + batadv_bit_get_packet(bat_priv, word, 1, 0); + w = &orig_node->bcast_own_sum[hard_iface->if_num]; + *w = bitmap_weight(word, BATADV_TQ_LOCAL_WINDOW_SIZE); + spin_unlock_bh(&orig_node->ogm_cnt_lock); + } + rcu_read_unlock(); + } +} + static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); @@ -634,7 +707,7 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) batadv_ogm_packet->gw_flags = BATADV_NO_FLAGS; } - batadv_slide_own_bcast_window(hard_iface); + batadv_iv_ogm_slide_own_bcast_window(hard_iface); batadv_iv_ogm_queue_add(bat_priv, hard_iface->bat_iv.ogm_buff, hard_iface->bat_iv.ogm_buff_len, hard_iface, 1, batadv_iv_ogm_emit_send_time(bat_priv)); @@ -670,7 +743,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, if (batadv_compare_eth(neigh_addr, ethhdr->h_source) && tmp_neigh_node->if_incoming == if_incoming && atomic_inc_not_zero(&tmp_neigh_node->refcount)) { - if (neigh_node) + if (WARN(neigh_node, "too many matching neigh_nodes")) batadv_neigh_node_free_ref(neigh_node); neigh_node = tmp_neigh_node; continue; @@ -696,8 +769,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, neigh_node = batadv_iv_ogm_neigh_new(if_incoming, ethhdr->h_source, - orig_node, orig_tmp, - batadv_ogm_packet->seqno); + orig_node, orig_tmp); batadv_orig_node_free_ref(orig_tmp); if (!neigh_node) @@ -829,8 +901,7 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, neigh_node = batadv_iv_ogm_neigh_new(if_incoming, orig_neigh_node->orig, orig_neigh_node, - orig_neigh_node, - batadv_ogm_packet->seqno); + orig_neigh_node); if (!neigh_node) goto out; @@ -991,7 +1062,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, struct batadv_neigh_node *orig_neigh_router = NULL; int has_directlink_flag; int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; - int is_broadcast = 0, is_bidirect; + int is_bidirect; bool is_single_hop_neigh = false; bool is_from_best_next_hop = false; int is_duplicate, sameseq, simlar_ttl; @@ -1054,19 +1125,9 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, if (batadv_compare_eth(batadv_ogm_packet->prev_sender, hard_iface->net_dev->dev_addr)) is_my_oldorig = 1; - - if (is_broadcast_ether_addr(ethhdr->h_source)) - is_broadcast = 1; } rcu_read_unlock(); - if (batadv_ogm_packet->header.version != BATADV_COMPAT_VERSION) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: incompatible batman version (%i)\n", - batadv_ogm_packet->header.version); - return; - } - if (is_my_addr) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: received my own broadcast (sender: %pM)\n", @@ -1074,13 +1135,6 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, return; } - if (is_broadcast) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: ignoring all packets with broadcast source addr (sender: %pM)\n", - ethhdr->h_source); - return; - } - if (is_my_orig) { unsigned long *word; int offset; @@ -1288,7 +1342,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, skb->len + ETH_HLEN); packet_len = skb_headlen(skb); - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); packet_buff = skb->data; batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff; diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 379061c72549..e9d8e0b3c3d0 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -180,7 +180,7 @@ static struct batadv_bla_claim */ static struct batadv_bla_backbone_gw * batadv_backbone_hash_find(struct batadv_priv *bat_priv, - uint8_t *addr, short vid) + uint8_t *addr, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; @@ -257,7 +257,7 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...) */ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, - short vid, int claimtype) + unsigned short vid, int claimtype) { struct sk_buff *skb; struct ethhdr *ethhdr; @@ -307,7 +307,8 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, */ memcpy(ethhdr->h_source, mac, ETH_ALEN); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_send_claim(): CLAIM %pM on vid %d\n", mac, vid); + "bla_send_claim(): CLAIM %pM on vid %d\n", mac, + BATADV_PRINT_VID(vid)); break; case BATADV_CLAIM_TYPE_UNCLAIM: /* unclaim frame @@ -316,7 +317,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, memcpy(hw_src, mac, ETH_ALEN); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_send_claim(): UNCLAIM %pM on vid %d\n", mac, - vid); + BATADV_PRINT_VID(vid)); break; case BATADV_CLAIM_TYPE_ANNOUNCE: /* announcement frame @@ -325,7 +326,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, memcpy(hw_src, mac, ETH_ALEN); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_send_claim(): ANNOUNCE of %pM on vid %d\n", - ethhdr->h_source, vid); + ethhdr->h_source, BATADV_PRINT_VID(vid)); break; case BATADV_CLAIM_TYPE_REQUEST: /* request frame @@ -335,13 +336,15 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, memcpy(hw_src, mac, ETH_ALEN); memcpy(ethhdr->h_dest, mac, ETH_ALEN); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "bla_send_claim(): REQUEST of %pM to %pMon vid %d\n", - ethhdr->h_source, ethhdr->h_dest, vid); + "bla_send_claim(): REQUEST of %pM to %pM on vid %d\n", + ethhdr->h_source, ethhdr->h_dest, + BATADV_PRINT_VID(vid)); break; } - if (vid != -1) - skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), vid); + if (vid & BATADV_VLAN_HAS_TAG) + skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), + vid & VLAN_VID_MASK); skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, soft_iface); @@ -367,7 +370,7 @@ out: */ static struct batadv_bla_backbone_gw * batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, - short vid, bool own_backbone) + unsigned short vid, bool own_backbone) { struct batadv_bla_backbone_gw *entry; struct batadv_orig_node *orig_node; @@ -380,7 +383,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_get_backbone_gw(): not found (%pM, %d), creating new entry\n", - orig, vid); + orig, BATADV_PRINT_VID(vid)); entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) @@ -434,7 +437,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, static void batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, - short vid) + unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; @@ -456,7 +459,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, */ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, - short vid) + unsigned short vid) { struct hlist_head *head; struct batadv_hashtable *hash; @@ -547,7 +550,7 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, * @backbone_gw: the backbone gateway which claims it */ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, - const uint8_t *mac, const short vid, + const uint8_t *mac, const unsigned short vid, struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_bla_claim *claim; @@ -572,7 +575,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, atomic_set(&claim->refcount, 2); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_add_claim(): adding new entry %pM, vid %d to hash ...\n", - mac, vid); + mac, BATADV_PRINT_VID(vid)); hash_added = batadv_hash_add(bat_priv->bla.claim_hash, batadv_compare_claim, batadv_choose_claim, claim, @@ -591,7 +594,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_add_claim(): changing ownership for %pM, vid %d\n", - mac, vid); + mac, BATADV_PRINT_VID(vid)); claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); batadv_backbone_gw_free_ref(claim->backbone_gw); @@ -611,7 +614,7 @@ claim_free_ref: * given mac address and vid. */ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, - const uint8_t *mac, const short vid) + const uint8_t *mac, const unsigned short vid) { struct batadv_bla_claim search_claim, *claim; @@ -622,7 +625,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, return; batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n", - mac, vid); + mac, BATADV_PRINT_VID(vid)); batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim, batadv_choose_claim, claim); @@ -637,7 +640,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, /* check for ANNOUNCE frame, return 1 if handled */ static int batadv_handle_announce(struct batadv_priv *bat_priv, uint8_t *an_addr, uint8_t *backbone_addr, - short vid) + unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; uint16_t crc; @@ -658,12 +661,13 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_BLA, bat_priv, "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", - vid, backbone_gw->orig, crc); + BATADV_PRINT_VID(vid), backbone_gw->orig, crc); if (backbone_gw->crc != crc) { batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", - backbone_gw->orig, backbone_gw->vid, + backbone_gw->orig, + BATADV_PRINT_VID(backbone_gw->vid), backbone_gw->crc, crc); batadv_bla_send_request(backbone_gw); @@ -685,7 +689,7 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, static int batadv_handle_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, uint8_t *backbone_addr, - struct ethhdr *ethhdr, short vid) + struct ethhdr *ethhdr, unsigned short vid) { /* check for REQUEST frame */ if (!batadv_compare_eth(backbone_addr, ethhdr->h_dest)) @@ -699,7 +703,7 @@ static int batadv_handle_request(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_BLA, bat_priv, "handle_request(): REQUEST vid %d (sent by %pM)...\n", - vid, ethhdr->h_source); + BATADV_PRINT_VID(vid), ethhdr->h_source); batadv_bla_answer_request(bat_priv, primary_if, vid); return 1; @@ -709,7 +713,7 @@ static int batadv_handle_request(struct batadv_priv *bat_priv, static int batadv_handle_unclaim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, uint8_t *backbone_addr, - uint8_t *claim_addr, short vid) + uint8_t *claim_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; @@ -727,7 +731,7 @@ static int batadv_handle_unclaim(struct batadv_priv *bat_priv, /* this must be an UNCLAIM frame */ batadv_dbg(BATADV_DBG_BLA, bat_priv, "handle_unclaim(): UNCLAIM %pM on vid %d (sent by %pM)...\n", - claim_addr, vid, backbone_gw->orig); + claim_addr, BATADV_PRINT_VID(vid), backbone_gw->orig); batadv_bla_del_claim(bat_priv, claim_addr, vid); batadv_backbone_gw_free_ref(backbone_gw); @@ -738,7 +742,7 @@ static int batadv_handle_unclaim(struct batadv_priv *bat_priv, static int batadv_handle_claim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, uint8_t *backbone_addr, uint8_t *claim_addr, - short vid) + unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; @@ -861,14 +865,15 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, struct batadv_bla_claim_dst *bla_dst; uint16_t proto; int headlen; - short vid = -1; + unsigned short vid = BATADV_NO_FLAGS; int ret; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) { vhdr = (struct vlan_ethhdr *)ethhdr; vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + vid |= BATADV_VLAN_HAS_TAG; proto = ntohs(vhdr->h_vlan_encapsulated_proto); headlen = sizeof(*vhdr); } else { @@ -885,7 +890,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, return 0; /* pskb_may_pull() may have modified the pointers, get ethhdr again */ - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); arphdr = (struct arphdr *)((uint8_t *)ethhdr + headlen); /* Check whether the ARP frame carries a valid @@ -910,7 +915,8 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, if (ret == 1) batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_process_claim(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", - ethhdr->h_source, vid, hw_src, hw_dst); + ethhdr->h_source, BATADV_PRINT_VID(vid), hw_src, + hw_dst); if (ret < 2) return ret; @@ -945,7 +951,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_process_claim(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", - ethhdr->h_source, vid, hw_src, hw_dst); + ethhdr->h_source, BATADV_PRINT_VID(vid), hw_src, hw_dst); return 1; } @@ -1358,7 +1364,7 @@ int batadv_bla_is_backbone_gw(struct sk_buff *skb, struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; struct batadv_bla_backbone_gw *backbone_gw; - short vid = -1; + unsigned short vid = BATADV_NO_FLAGS; if (!atomic_read(&orig_node->bat_priv->bridge_loop_avoidance)) return 0; @@ -1375,6 +1381,7 @@ int batadv_bla_is_backbone_gw(struct sk_buff *skb, vhdr = (struct vlan_ethhdr *)(skb->data + hdr_size); vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + vid |= BATADV_VLAN_HAS_TAG; } /* see if this originator is a backbone gw for this VLAN */ @@ -1424,15 +1431,15 @@ void batadv_bla_free(struct batadv_priv *bat_priv) * returns 1, otherwise it returns 0 and the caller shall further * process the skb. */ -int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid, - bool is_bcast) +int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid, bool is_bcast) { struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; int ret; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) @@ -1519,7 +1526,8 @@ out: * returns 1, otherwise it returns 0 and the caller shall further * process the skb. */ -int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid) +int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid) { struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; @@ -1539,7 +1547,7 @@ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid) if (batadv_bla_process_claim(bat_priv, primary_if, skb)) goto handled; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); if (unlikely(atomic_read(&bat_priv->bla.num_requests))) /* don't allow broadcasts while requests are in flight */ @@ -1623,8 +1631,8 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) hlist_for_each_entry_rcu(claim, head, hash_entry) { is_own = batadv_compare_eth(claim->backbone_gw->orig, primary_addr); - seq_printf(seq, " * %pM on % 5d by %pM [%c] (%#.4x)\n", - claim->addr, claim->vid, + seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n", + claim->addr, BATADV_PRINT_VID(claim->vid), claim->backbone_gw->orig, (is_own ? 'x' : ' '), claim->backbone_gw->crc); @@ -1676,10 +1684,10 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) if (is_own) continue; - seq_printf(seq, - " * %pM on % 5d % 4i.%03is (%#.4x)\n", - backbone_gw->orig, backbone_gw->vid, - secs, msecs, backbone_gw->crc); + seq_printf(seq, " * %pM on %5d %4i.%03is (%#.4x)\n", + backbone_gw->orig, + BATADV_PRINT_VID(backbone_gw->vid), secs, + msecs, backbone_gw->crc); } rcu_read_unlock(); } diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index dea2fbc5d98d..4b102e71e5bd 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -21,9 +21,10 @@ #define _NET_BATMAN_ADV_BLA_H_ #ifdef CONFIG_BATMAN_ADV_BLA -int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid, - bool is_bcast); -int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid); +int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid, bool is_bcast); +int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid); int batadv_bla_is_backbone_gw(struct sk_buff *skb, struct batadv_orig_node *orig_node, int hdr_size); int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset); @@ -42,13 +43,14 @@ void batadv_bla_free(struct batadv_priv *bat_priv); #else /* ifdef CONFIG_BATMAN_ADV_BLA */ static inline int batadv_bla_rx(struct batadv_priv *bat_priv, - struct sk_buff *skb, short vid, bool is_bcast) + struct sk_buff *skb, unsigned short vid, + bool is_bcast) { return 0; } static inline int batadv_bla_tx(struct batadv_priv *bat_priv, - struct sk_buff *skb, short vid) + struct sk_buff *skb, unsigned short vid) { return 0; } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 239992021b1d..06345d401588 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -45,9 +45,9 @@ static void batadv_dat_start_timer(struct batadv_priv *bat_priv) } /** - * batadv_dat_entry_free_ref - decrements the dat_entry refcounter and possibly + * batadv_dat_entry_free_ref - decrement the dat_entry refcounter and possibly * free it - * @dat_entry: the oentry to free + * @dat_entry: the entry to free */ static void batadv_dat_entry_free_ref(struct batadv_dat_entry *dat_entry) { @@ -56,10 +56,10 @@ static void batadv_dat_entry_free_ref(struct batadv_dat_entry *dat_entry) } /** - * batadv_dat_to_purge - checks whether a dat_entry has to be purged or not + * batadv_dat_to_purge - check whether a dat_entry has to be purged or not * @dat_entry: the entry to check * - * Returns true if the entry has to be purged now, false otherwise + * Returns true if the entry has to be purged now, false otherwise. */ static bool batadv_dat_to_purge(struct batadv_dat_entry *dat_entry) { @@ -75,8 +75,8 @@ static bool batadv_dat_to_purge(struct batadv_dat_entry *dat_entry) * returns a boolean value: true is the entry has to be deleted, * false otherwise * - * Loops over each entry in the DAT local storage and delete it if and only if - * the to_purge function passed as argument returns true + * Loops over each entry in the DAT local storage and deletes it if and only if + * the to_purge function passed as argument returns true. */ static void __batadv_dat_purge(struct batadv_priv *bat_priv, bool (*to_purge)(struct batadv_dat_entry *)) @@ -97,7 +97,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv, spin_lock_bh(list_lock); hlist_for_each_entry_safe(dat_entry, node_tmp, head, hash_entry) { - /* if an helper function has been passed as parameter, + /* if a helper function has been passed as parameter, * ask it if the entry has to be purged or not */ if (to_purge && !to_purge(dat_entry)) @@ -134,7 +134,7 @@ static void batadv_dat_purge(struct work_struct *work) * @node: node in the local table * @data2: second object to compare the node to * - * Returns 1 if the two entry are the same, 0 otherwise + * Returns 1 if the two entries are the same, 0 otherwise. */ static int batadv_compare_dat(const struct hlist_node *node, const void *data2) { @@ -149,7 +149,7 @@ static int batadv_compare_dat(const struct hlist_node *node, const void *data2) * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * - * Returns the value of the hw_src field in the ARP packet + * Returns the value of the hw_src field in the ARP packet. */ static uint8_t *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size) { @@ -166,7 +166,7 @@ static uint8_t *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size) * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * - * Returns the value of the ip_src field in the ARP packet + * Returns the value of the ip_src field in the ARP packet. */ static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size) { @@ -178,7 +178,7 @@ static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size) * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * - * Returns the value of the hw_dst field in the ARP packet + * Returns the value of the hw_dst field in the ARP packet. */ static uint8_t *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size) { @@ -190,7 +190,7 @@ static uint8_t *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size) * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * - * Returns the value of the ip_dst field in the ARP packet + * Returns the value of the ip_dst field in the ARP packet. */ static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size) { @@ -202,7 +202,7 @@ static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size) * @data: data to hash * @size: size of the hash table * - * Returns the selected index in the hash table for the given data + * Returns the selected index in the hash table for the given data. */ static uint32_t batadv_hash_dat(const void *data, uint32_t size) { @@ -224,12 +224,12 @@ static uint32_t batadv_hash_dat(const void *data, uint32_t size) } /** - * batadv_dat_entry_hash_find - looks for a given dat_entry in the local hash + * batadv_dat_entry_hash_find - look for a given dat_entry in the local hash * table * @bat_priv: the bat priv with all the soft interface information * @ip: search key * - * Returns the dat_entry if found, NULL otherwise + * Returns the dat_entry if found, NULL otherwise. */ static struct batadv_dat_entry * batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip) @@ -343,9 +343,6 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, if (hdr_size == 0) return; - /* if the ARP packet is encapsulated in a batman packet, let's print - * some debug messages - */ unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; switch (unicast_4addr_packet->u.header.packet_type) { @@ -409,7 +406,8 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, * @candidate: orig_node under evaluation * @max_orig_node: last selected candidate * - * Returns true if the node has been elected as next candidate or false othrwise + * Returns true if the node has been elected as next candidate or false + * otherwise. */ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, int select, batadv_dat_addr_t tmp_max, @@ -472,7 +470,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, */ cands[select].type = BATADV_DAT_CANDIDATE_NOT_FOUND; - /* iterate over the originator list and find the node with closest + /* iterate over the originator list and find the node with the closest * dat_address which has not been selected yet */ for (i = 0; i < hash->size; i++) { @@ -480,7 +478,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - /* the dht space is a ring and addresses are unsigned */ + /* the dht space is a ring using unsigned addresses */ tmp_max = BATADV_DAT_ADDR_MAX - orig_node->dat_addr + ip_key; @@ -512,7 +510,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, } /** - * batadv_dat_select_candidates - selects the nodes which the DHT message has to + * batadv_dat_select_candidates - select the nodes which the DHT message has to * be sent to * @bat_priv: the bat priv with all the soft interface information * @ip_dst: ipv4 to look up in the DHT @@ -521,7 +519,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, * closest values (from the LEFT, with wrap around if needed) then the hash * value of the key. ip_dst is the key. * - * Returns the candidate array of size BATADV_DAT_CANDIDATE_NUM + * Returns the candidate array of size BATADV_DAT_CANDIDATE_NUM. */ static struct batadv_dat_candidate * batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) @@ -558,10 +556,11 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) * @ip: the DHT key * @packet_subtype: unicast4addr packet subtype to use * - * In this function the skb is copied by means of pskb_copy() and is sent as - * unicast packet to each of the selected candidates + * This function copies the skb with pskb_copy() and is sent as unicast packet + * to each of the selected candidates. * - * Returns true if the packet is sent to at least one candidate, false otherwise + * Returns true if the packet is sent to at least one candidate, false + * otherwise. */ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, struct sk_buff *skb, __be32 ip, @@ -727,7 +726,7 @@ out: * @skb: packet to analyse * @hdr_size: size of the possible header before the ARP packet in the skb * - * Returns the ARP type if the skb contains a valid ARP packet, 0 otherwise + * Returns the ARP type if the skb contains a valid ARP packet, 0 otherwise. */ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) @@ -754,9 +753,7 @@ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, arphdr = (struct arphdr *)(skb->data + hdr_size + ETH_HLEN); - /* Check whether the ARP packet carries a valid - * IP information - */ + /* check whether the ARP packet carries a valid IP information */ if (arphdr->ar_hrd != htons(ARPHRD_ETHER)) goto out; @@ -784,7 +781,7 @@ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, if (is_zero_ether_addr(hw_src) || is_multicast_ether_addr(hw_src)) goto out; - /* we don't care about the destination MAC address in ARP requests */ + /* don't care about the destination MAC address in ARP requests */ if (arphdr->ar_op != htons(ARPOP_REQUEST)) { hw_dst = batadv_arp_hw_dst(skb, hdr_size); if (is_zero_ether_addr(hw_dst) || @@ -804,8 +801,8 @@ out: * @skb: packet to check * * Returns true if the message has been sent to the dht candidates, false - * otherwise. In case of true the message has to be enqueued to permit the - * fallback + * otherwise. In case of a positive return value the message has to be enqueued + * to permit the fallback. */ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, struct sk_buff *skb) @@ -867,7 +864,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP request replied locally\n"); ret = true; } else { - /* Send the request on the DHT */ + /* Send the request to the DHT */ ret = batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_GET); } @@ -884,7 +881,7 @@ out: * @skb: packet to check * @hdr_size: size of the encapsulation header * - * Returns true if the request has been answered, false otherwise + * Returns true if the request has been answered, false otherwise. */ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) @@ -924,10 +921,9 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, if (!skb_new) goto out; - /* to preserve backwards compatibility, here the node has to answer - * using the same packet type it received for the request. This is due - * to that if a node is not using the 4addr packet format it may not - * support it. + /* To preserve backwards compatibility, the node has choose the outgoing + * format based on the incoming request packet type. The assumption is + * that a node not using the 4addr packet format doesn't support it. */ if (hdr_size == sizeof(struct batadv_unicast_4addr_packet)) err = batadv_unicast_4addr_send_skb(bat_priv, skb_new, @@ -977,7 +973,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, batadv_dat_entry_add(bat_priv, ip_dst, hw_dst); /* Send the ARP reply to the candidates for both the IP addresses that - * the node got within the ARP reply + * the node obtained from the ARP reply */ batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT); batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT); @@ -987,7 +983,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, * DAT storage only * @bat_priv: the bat priv with all the soft interface information * @skb: packet to check - * @hdr_size: siaze of the encapsulation header + * @hdr_size: size of the encapsulation header */ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) @@ -1031,11 +1027,11 @@ out: /** * batadv_dat_drop_broadcast_packet - check if an ARP request has to be dropped - * (because the node has already got the reply via DAT) or not + * (because the node has already obtained the reply via DAT) or not * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the broadcast packet * - * Returns true if the node can drop the packet, false otherwise + * Returns true if the node can drop the packet, false otherwise. */ bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 522243aff2f3..c478e6bcf89b 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -117,6 +117,58 @@ static int batadv_is_valid_iface(const struct net_device *net_dev) return 1; } +/** + * batadv_is_wifi_netdev - check if the given net_device struct is a wifi + * interface + * @net_device: the device to check + * + * Returns true if the net device is a 802.11 wireless device, false otherwise. + */ +static bool batadv_is_wifi_netdev(struct net_device *net_device) +{ +#ifdef CONFIG_WIRELESS_EXT + /* pre-cfg80211 drivers have to implement WEXT, so it is possible to + * check for wireless_handlers != NULL + */ + if (net_device->wireless_handlers) + return true; +#endif + + /* cfg80211 drivers have to set ieee80211_ptr */ + if (net_device->ieee80211_ptr) + return true; + + return false; +} + +/** + * batadv_is_wifi_iface - check if the given interface represented by ifindex + * is a wifi interface + * @ifindex: interface index to check + * + * Returns true if the interface represented by ifindex is a 802.11 wireless + * device, false otherwise. + */ +bool batadv_is_wifi_iface(int ifindex) +{ + struct net_device *net_device = NULL; + bool ret = false; + + if (ifindex == BATADV_NULL_IFINDEX) + goto out; + + net_device = dev_get_by_index(&init_net, ifindex); + if (!net_device) + goto out; + + ret = batadv_is_wifi_netdev(net_device); + +out: + if (net_device) + dev_put(net_device); + return ret; +} + static struct batadv_hard_iface * batadv_hardif_get_active(const struct net_device *soft_iface) { @@ -525,7 +577,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) dev_hold(net_dev); - hard_iface = kmalloc(sizeof(*hard_iface), GFP_ATOMIC); + hard_iface = kzalloc(sizeof(*hard_iface), GFP_ATOMIC); if (!hard_iface) goto release_dev; @@ -541,18 +593,16 @@ batadv_hardif_add_interface(struct net_device *net_dev) INIT_WORK(&hard_iface->cleanup_work, batadv_hardif_remove_interface_finish); + hard_iface->num_bcasts = BATADV_NUM_BCASTS_DEFAULT; + if (batadv_is_wifi_netdev(net_dev)) + hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; + /* extra reference for return */ atomic_set(&hard_iface->refcount, 2); batadv_check_known_mac_addr(hard_iface->net_dev); list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list); - /* This can't be called via a bat_priv callback because - * we have no bat_priv yet. - */ - atomic_set(&hard_iface->bat_iv.ogm_seqno, 1); - hard_iface->bat_iv.ogm_buff = NULL; - return hard_iface; free_if: @@ -595,7 +645,7 @@ void batadv_hardif_remove_interfaces(void) static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *net_dev = ptr; + struct net_device *net_dev = netdev_notifier_info_to_dev(ptr); struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv; @@ -657,38 +707,6 @@ out: return NOTIFY_DONE; } -/* This function returns true if the interface represented by ifindex is a - * 802.11 wireless device - */ -bool batadv_is_wifi_iface(int ifindex) -{ - struct net_device *net_device = NULL; - bool ret = false; - - if (ifindex == BATADV_NULL_IFINDEX) - goto out; - - net_device = dev_get_by_index(&init_net, ifindex); - if (!net_device) - goto out; - -#ifdef CONFIG_WIRELESS_EXT - /* pre-cfg80211 drivers have to implement WEXT, so it is possible to - * check for wireless_handlers != NULL - */ - if (net_device->wireless_handlers) - ret = true; - else -#endif - /* cfg80211 drivers have to set ieee80211_ptr */ - if (net_device->ieee80211_ptr) - ret = true; -out: - if (net_device) - dev_put(net_device); - return ret; -} - struct notifier_block batadv_hard_if_notifier = { .notifier_call = batadv_hard_if_event, }; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 0ba6c899b2d3..b27508b8085c 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -177,13 +177,13 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, if (len >= sizeof(struct batadv_icmp_packet_rr)) packet_len = sizeof(struct batadv_icmp_packet_rr); - skb = dev_alloc_skb(packet_len + ETH_HLEN + NET_IP_ALIGN); + skb = netdev_alloc_skb_ip_align(NULL, packet_len + ETH_HLEN); if (!skb) { len = -ENOMEM; goto out; } - skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); + skb_reserve(skb, ETH_HLEN); icmp_packet = (struct batadv_icmp_packet_rr *)skb_put(skb, packet_len); if (copy_from_user(icmp_packet, buff, packet_len)) { diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 59a0d6af15c8..5e9aebb7d56b 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -26,7 +26,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2013.2.0" +#define BATADV_SOURCE_VERSION "2013.3.0" #endif /* B.A.T.M.A.N. parameters */ @@ -76,6 +76,11 @@ #define BATADV_LOG_BUF_LEN 8192 /* has to be a power of 2 */ +/* number of packets to send for broadcasts on different interface types */ +#define BATADV_NUM_BCASTS_DEFAULT 1 +#define BATADV_NUM_BCASTS_WIRELESS 3 +#define BATADV_NUM_BCASTS_MAX 3 + /* msecs after which an ARP_REQUEST is sent in broadcast as fallback */ #define ARP_REQ_DELAY 250 /* numbers of originator to contact for any PUT/GET DHT operation */ @@ -157,6 +162,17 @@ enum batadv_uev_type { #include <linux/seq_file.h> #include "types.h" +/** + * batadv_vlan_flags - flags for the four MSB of any vlan ID field + * @BATADV_VLAN_HAS_TAG: whether the field contains a valid vlan tag or not + */ +enum batadv_vlan_flags { + BATADV_VLAN_HAS_TAG = BIT(15), +}; + +#define BATADV_PRINT_VID(vid) (vid & BATADV_VLAN_HAS_TAG ? \ + (int)(vid & VLAN_VID_MASK) : -1) + extern char batadv_routing_algo[]; extern struct list_head batadv_hardif_list; diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index e84629ece9b7..a487d46e0aec 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1245,7 +1245,7 @@ static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv, return; /* Set the mac header as if we actually sent the packet uncoded */ - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); memcpy(ethhdr->h_source, ethhdr->h_dest, ETH_ALEN); memcpy(ethhdr->h_dest, eth_dst_new, ETH_ALEN); @@ -1359,18 +1359,17 @@ static bool batadv_nc_skb_add_to_path(struct sk_buff *skb, * buffer * @skb: data skb to forward * @neigh_node: next hop to forward packet to - * @ethhdr: pointer to the ethernet header inside the skb * * Returns true if the skb was consumed (encoded packet sent) or false otherwise */ bool batadv_nc_skb_forward(struct sk_buff *skb, - struct batadv_neigh_node *neigh_node, - struct ethhdr *ethhdr) + struct batadv_neigh_node *neigh_node) { const struct net_device *netdev = neigh_node->if_incoming->soft_iface; struct batadv_priv *bat_priv = netdev_priv(netdev); struct batadv_unicast_packet *packet; struct batadv_nc_path *nc_path; + struct ethhdr *ethhdr = eth_hdr(skb); __be32 packet_id; u8 *payload; @@ -1423,7 +1422,7 @@ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv, { struct batadv_unicast_packet *packet; struct batadv_nc_path *nc_path; - struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + struct ethhdr *ethhdr = eth_hdr(skb); __be32 packet_id; u8 *payload; @@ -1482,7 +1481,7 @@ out: void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb) { - struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + struct ethhdr *ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return; @@ -1533,7 +1532,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, skb_reset_network_header(skb); /* Reconstruct original mac header */ - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); memcpy(ethhdr, ðhdr_tmp, sizeof(*ethhdr)); /* Select the correct unicast header information based on the location @@ -1677,7 +1676,7 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, return NET_RX_DROP; coded_packet = (struct batadv_coded_packet *)skb->data; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); /* Verify frame is destined for us */ if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest) && @@ -1763,6 +1762,13 @@ int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset) /* For each orig_node in this bin */ rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + /* no need to print the orig node if it does not have + * network coding neighbors + */ + if (list_empty(&orig_node->in_coding_list) && + list_empty(&orig_node->out_coding_list)) + continue; + seq_printf(seq, "Node: %pM\n", orig_node->orig); seq_puts(seq, " Ingoing: "); diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 4fa6d0caddbd..85a4ec81ad50 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -36,8 +36,7 @@ void batadv_nc_purge_orig(struct batadv_priv *bat_priv, void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv); void batadv_nc_init_orig(struct batadv_orig_node *orig_node); bool batadv_nc_skb_forward(struct sk_buff *skb, - struct batadv_neigh_node *neigh_node, - struct ethhdr *ethhdr); + struct batadv_neigh_node *neigh_node); void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv, struct sk_buff *skb); void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, @@ -87,8 +86,7 @@ static inline void batadv_nc_init_orig(struct batadv_orig_node *orig_node) } static inline bool batadv_nc_skb_forward(struct sk_buff *skb, - struct batadv_neigh_node *neigh_node, - struct ethhdr *ethhdr) + struct batadv_neigh_node *neigh_node) { return false; } diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index fad1a2093e15..f50553a7de62 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -92,7 +92,7 @@ batadv_orig_node_get_router(struct batadv_orig_node *orig_node) struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, - const uint8_t *neigh_addr, uint32_t seqno) + const uint8_t *neigh_addr) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_neigh_node *neigh_node; @@ -110,8 +110,8 @@ batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, atomic_set(&neigh_node->refcount, 2); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Creating new neighbor %pM, initial seqno %d\n", - neigh_addr, seqno); + "Creating new neighbor %pM on interface %s\n", neigh_addr, + hard_iface->net_dev->name); out: return neigh_node; diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 734e5a3d8a5b..7887b84a9af4 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -31,7 +31,7 @@ struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, - const uint8_t *neigh_addr, uint32_t seqno); + const uint8_t *neigh_addr); void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node); struct batadv_neigh_node * batadv_orig_node_get_router(struct batadv_orig_node *orig_node); diff --git a/net/batman-adv/ring_buffer.c b/net/batman-adv/ring_buffer.c deleted file mode 100644 index ccab0bbdbb59..000000000000 --- a/net/batman-adv/ring_buffer.c +++ /dev/null @@ -1,51 +0,0 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: - * - * Marek Lindner - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA - */ - -#include "main.h" -#include "ring_buffer.h" - -void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, - uint8_t value) -{ - lq_recv[*lq_index] = value; - *lq_index = (*lq_index + 1) % BATADV_TQ_GLOBAL_WINDOW_SIZE; -} - -uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]) -{ - const uint8_t *ptr; - uint16_t count = 0, i = 0, sum = 0; - - ptr = lq_recv; - - while (i < BATADV_TQ_GLOBAL_WINDOW_SIZE) { - if (*ptr != 0) { - count++; - sum += *ptr; - } - - i++; - ptr++; - } - - if (count == 0) - return 0; - - return (uint8_t)(sum / count); -} diff --git a/net/batman-adv/ring_buffer.h b/net/batman-adv/ring_buffer.h deleted file mode 100644 index 3f92ae248e83..000000000000 --- a/net/batman-adv/ring_buffer.h +++ /dev/null @@ -1,27 +0,0 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: - * - * Marek Lindner - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA - */ - -#ifndef _NET_BATMAN_ADV_RING_BUFFER_H_ -#define _NET_BATMAN_ADV_RING_BUFFER_H_ - -void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, - uint8_t value); -uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]); - -#endif /* _NET_BATMAN_ADV_RING_BUFFER_H_ */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index b27a4d792d15..2f0bd3ffe6e8 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -34,35 +34,6 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); -void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) -{ - struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_head *head; - struct batadv_orig_node *orig_node; - unsigned long *word; - uint32_t i; - size_t word_index; - uint8_t *w; - - for (i = 0; i < hash->size; i++) { - head = &hash->table[i]; - - rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - spin_lock_bh(&orig_node->ogm_cnt_lock); - word_index = hard_iface->if_num * BATADV_NUM_WORDS; - word = &(orig_node->bcast_own[word_index]); - - batadv_bit_get_packet(bat_priv, word, 1, 0); - w = &orig_node->bcast_own_sum[hard_iface->if_num]; - *w = bitmap_weight(word, BATADV_TQ_LOCAL_WINDOW_SIZE); - spin_unlock_bh(&orig_node->ogm_cnt_lock); - } - rcu_read_unlock(); - } -} - static void _batadv_update_route(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node) @@ -256,7 +227,7 @@ bool batadv_check_management_packet(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, header_len))) return false; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); /* packet with broadcast indication but unicast recipient */ if (!is_broadcast_ether_addr(ethhdr->h_dest)) @@ -314,7 +285,7 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv, icmp_packet->msg_type = BATADV_ECHO_REPLY; icmp_packet->header.ttl = BATADV_TTL; - if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP) ret = NET_RX_SUCCESS; out: @@ -362,7 +333,7 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv, icmp_packet->msg_type = BATADV_TTL_EXCEEDED; icmp_packet->header.ttl = BATADV_TTL; - if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP) ret = NET_RX_SUCCESS; out: @@ -392,7 +363,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, hdr_size))) goto out; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); /* packet with unicast indication but broadcast recipient */ if (is_broadcast_ether_addr(ethhdr->h_dest)) @@ -439,7 +410,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, icmp_packet->header.ttl--; /* route it */ - if (batadv_send_skb_to_orig(skb, orig_node, recv_if)) + if (batadv_send_skb_to_orig(skb, orig_node, recv_if) != NET_XMIT_DROP) ret = NET_RX_SUCCESS; out: @@ -569,7 +540,7 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, if (unlikely(!pskb_may_pull(skb, hdr_size))) return -ENODATA; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); /* packet with unicast indication but broadcast recipient */ if (is_broadcast_ether_addr(ethhdr->h_dest)) @@ -803,8 +774,8 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, struct batadv_orig_node *orig_node = NULL; struct batadv_neigh_node *neigh_node = NULL; struct batadv_unicast_packet *unicast_packet; - struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); - int ret = NET_RX_DROP; + struct ethhdr *ethhdr = eth_hdr(skb); + int res, ret = NET_RX_DROP; struct sk_buff *new_skb; unicast_packet = (struct batadv_unicast_packet *)skb->data; @@ -864,16 +835,19 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, /* decrement ttl */ unicast_packet->header.ttl--; - /* network code packet if possible */ - if (batadv_nc_skb_forward(skb, neigh_node, ethhdr)) { - ret = NET_RX_SUCCESS; - } else if (batadv_send_skb_to_orig(skb, orig_node, recv_if)) { - ret = NET_RX_SUCCESS; + res = batadv_send_skb_to_orig(skb, orig_node, recv_if); - /* Update stats counter */ + /* translate transmit result into receive result */ + if (res == NET_XMIT_SUCCESS) { + /* skb was transmitted and consumed */ batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD); batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES, skb->len + ETH_HLEN); + + ret = NET_RX_SUCCESS; + } else if (res == NET_XMIT_POLICED) { + /* skb was buffered and consumed */ + ret = NET_RX_SUCCESS; } out: @@ -1165,7 +1139,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, hdr_size))) goto out; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); /* packet with broadcast indication but unicast recipient */ if (!is_broadcast_ether_addr(ethhdr->h_dest)) @@ -1265,7 +1239,7 @@ int batadv_recv_vis_packet(struct sk_buff *skb, return NET_RX_DROP; vis_packet = (struct batadv_vis_packet *)skb->data; - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); /* not for me */ if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 99eeafaba407..72a29bde2010 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -20,7 +20,6 @@ #ifndef _NET_BATMAN_ADV_ROUTING_H_ #define _NET_BATMAN_ADV_ROUTING_H_ -void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface); bool batadv_check_management_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, int header_len); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 263cfd1ccee7..e9ff8d801201 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -61,7 +61,7 @@ int batadv_send_skb_packet(struct sk_buff *skb, skb_reset_mac_header(skb); - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); memcpy(ethhdr->h_source, hard_iface->net_dev->dev_addr, ETH_ALEN); memcpy(ethhdr->h_dest, dst_addr, ETH_ALEN); ethhdr->h_proto = __constant_htons(ETH_P_BATMAN); @@ -96,26 +96,37 @@ send_skb_err: * host, NULL can be passed as recv_if and no interface alternating is * attempted. * - * Returns TRUE on success; FALSE otherwise. + * Returns NET_XMIT_SUCCESS on success, NET_XMIT_DROP on failure, or + * NET_XMIT_POLICED if the skb is buffered for later transmit. */ -bool batadv_send_skb_to_orig(struct sk_buff *skb, - struct batadv_orig_node *orig_node, - struct batadv_hard_iface *recv_if) +int batadv_send_skb_to_orig(struct sk_buff *skb, + struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = orig_node->bat_priv; struct batadv_neigh_node *neigh_node; + int ret = NET_XMIT_DROP; /* batadv_find_router() increases neigh_nodes refcount if found. */ neigh_node = batadv_find_router(bat_priv, orig_node, recv_if); if (!neigh_node) - return false; + return ret; - /* route it */ - batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + /* try to network code the packet, if it is received on an interface + * (i.e. being forwarded). If the packet originates from this node or if + * network coding fails, then send the packet as usual. + */ + if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) { + ret = NET_XMIT_POLICED; + } else { + batadv_send_skb_packet(skb, neigh_node->if_incoming, + neigh_node->addr); + ret = NET_XMIT_SUCCESS; + } batadv_neigh_node_free_ref(neigh_node); - return true; + return ret; } void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface) @@ -152,8 +163,6 @@ _batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { - INIT_HLIST_NODE(&forw_packet->list); - /* add new packet to packet list */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); hlist_add_head(&forw_packet->list, &bat_priv->forw_bcast_list); @@ -260,6 +269,9 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) if (hard_iface->soft_iface != soft_iface) continue; + if (forw_packet->num_packets >= hard_iface->num_bcasts) + continue; + /* send a copy of the saved skb */ skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); if (skb1) @@ -271,7 +283,7 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) forw_packet->num_packets++; /* if we still have some more bcasts to send */ - if (forw_packet->num_packets < 3) { + if (forw_packet->num_packets < BATADV_NUM_BCASTS_MAX) { _batadv_add_bcast_packet_to_list(bat_priv, forw_packet, msecs_to_jiffies(5)); return; diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 38e662f619ac..e7b17880fca4 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -23,9 +23,9 @@ int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, const uint8_t *dst_addr); -bool batadv_send_skb_to_orig(struct sk_buff *skb, - struct batadv_orig_node *orig_node, - struct batadv_hard_iface *recv_if); +int batadv_send_skb_to_orig(struct sk_buff *skb, + struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if); void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface); int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, const struct sk_buff *skb, diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 819dfb006cdf..700d0b49742d 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -154,7 +154,7 @@ static int batadv_interface_tx(struct sk_buff *skb, 0x00, 0x00}; unsigned int header_len = 0; int data_len = skb->len, ret; - short vid __maybe_unused = -1; + unsigned short vid __maybe_unused = BATADV_NO_FLAGS; bool do_bcast = false; uint32_t seqno; unsigned long brd_delay = 1; @@ -303,7 +303,7 @@ void batadv_interface_rx(struct net_device *soft_iface, struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; struct batadv_header *batadv_header = (struct batadv_header *)skb->data; - short vid __maybe_unused = -1; + unsigned short vid __maybe_unused = BATADV_NO_FLAGS; __be16 ethertype = __constant_htons(ETH_P_BATMAN); bool is_bcast; @@ -316,7 +316,7 @@ void batadv_interface_rx(struct net_device *soft_iface, skb_pull_rcsum(skb, hdr_size); skb_reset_mac_header(skb); - ethhdr = (struct ethhdr *)skb_mac_header(skb); + ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 9e8748575845..429aeef3d8b2 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -163,10 +163,19 @@ batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry) call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); } +/** + * batadv_tt_local_event - store a local TT event (ADD/DEL) + * @bat_priv: the bat priv with all the soft interface information + * @tt_local_entry: the TT entry involved in the event + * @event_flags: flags to store in the event structure + */ static void batadv_tt_local_event(struct batadv_priv *bat_priv, - const uint8_t *addr, uint8_t flags) + struct batadv_tt_local_entry *tt_local_entry, + uint8_t event_flags) { struct batadv_tt_change_node *tt_change_node, *entry, *safe; + struct batadv_tt_common_entry *common = &tt_local_entry->common; + uint8_t flags = common->flags | event_flags; bool event_removed = false; bool del_op_requested, del_op_entry; @@ -176,7 +185,7 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, return; tt_change_node->change.flags = flags; - memcpy(tt_change_node->change.addr, addr, ETH_ALEN); + memcpy(tt_change_node->change.addr, common->addr, ETH_ALEN); del_op_requested = flags & BATADV_TT_CLIENT_DEL; @@ -184,7 +193,7 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->tt.changes_list_lock); list_for_each_entry_safe(entry, safe, &bat_priv->tt.changes_list, list) { - if (!batadv_compare_eth(entry->change.addr, addr)) + if (!batadv_compare_eth(entry->change.addr, common->addr)) continue; /* DEL+ADD in the same orig interval have no effect and can be @@ -332,7 +341,7 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, } add_event: - batadv_tt_local_event(bat_priv, addr, tt_local->common.flags); + batadv_tt_local_event(bat_priv, tt_local, BATADV_NO_FLAGS); check_roaming: /* Check whether it is a roaming, but don't do anything if the roaming @@ -529,8 +538,7 @@ batadv_tt_local_set_pending(struct batadv_priv *bat_priv, struct batadv_tt_local_entry *tt_local_entry, uint16_t flags, const char *message) { - batadv_tt_local_event(bat_priv, tt_local_entry->common.addr, - tt_local_entry->common.flags | flags); + batadv_tt_local_event(bat_priv, tt_local_entry, flags); /* The local client has to be marked as "pending to be removed" but has * to be kept in the table in order to send it in a full table @@ -584,8 +592,7 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, /* if this client has been added right now, it is possible to * immediately purge it */ - batadv_tt_local_event(bat_priv, tt_local_entry->common.addr, - curr_flags | BATADV_TT_CLIENT_DEL); + batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL); hlist_del_rcu(&tt_local_entry->common.hash_entry); batadv_tt_local_entry_free_ref(tt_local_entry); @@ -791,10 +798,25 @@ out: batadv_tt_orig_list_entry_free_ref(orig_entry); } -/* caller must hold orig_node refcount */ +/** + * batadv_tt_global_add - add a new TT global entry or update an existing one + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: the originator announcing the client + * @tt_addr: the mac address of the non-mesh client + * @flags: TT flags that have to be set for this non-mesh client + * @ttvn: the tt version number ever announcing this non-mesh client + * + * Add a new TT global entry for the given originator. If the entry already + * exists add a new reference to the given originator (a global entry can have + * references to multiple originators) and adjust the flags attribute to reflect + * the function argument. + * If a TT local entry exists for this non-mesh client remove it. + * + * The caller must hold orig_node refcount. + */ int batadv_tt_global_add(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - const unsigned char *tt_addr, uint8_t flags, + const unsigned char *tt_addr, uint16_t flags, uint8_t ttvn) { struct batadv_tt_global_entry *tt_global_entry; @@ -1600,11 +1622,11 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, tt_tot = tt_len / sizeof(struct batadv_tt_change); len = tt_query_size + tt_len; - skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN); + skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN); if (!skb) goto out; - skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); + skb_reserve(skb, ETH_HLEN); tt_response = (struct batadv_tt_query_packet *)skb_put(skb, len); tt_response->ttvn = ttvn; @@ -1665,11 +1687,11 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv, if (!tt_req_node) goto out; - skb = dev_alloc_skb(sizeof(*tt_request) + ETH_HLEN + NET_IP_ALIGN); + skb = netdev_alloc_skb_ip_align(NULL, sizeof(*tt_request) + ETH_HLEN); if (!skb) goto out; - skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); + skb_reserve(skb, ETH_HLEN); tt_req_len = sizeof(*tt_request); tt_request = (struct batadv_tt_query_packet *)skb_put(skb, tt_req_len); @@ -1691,7 +1713,7 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv, batadv_inc_counter(bat_priv, BATADV_CNT_TT_REQUEST_TX); - if (batadv_send_skb_to_orig(skb, dst_orig_node, NULL)) + if (batadv_send_skb_to_orig(skb, dst_orig_node, NULL) != NET_XMIT_DROP) ret = 0; out: @@ -1715,7 +1737,7 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv, struct batadv_orig_node *req_dst_orig_node; struct batadv_orig_node *res_dst_orig_node = NULL; uint8_t orig_ttvn, req_ttvn, ttvn; - int ret = false; + int res, ret = false; unsigned char *tt_buff; bool full_table; uint16_t tt_len, tt_tot; @@ -1762,11 +1784,11 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv, tt_tot = tt_len / sizeof(struct batadv_tt_change); len = sizeof(*tt_response) + tt_len; - skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN); + skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN); if (!skb) goto unlock; - skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); + skb_reserve(skb, ETH_HLEN); packet_pos = skb_put(skb, len); tt_response = (struct batadv_tt_query_packet *)packet_pos; tt_response->ttvn = req_ttvn; @@ -1810,8 +1832,10 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv, batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX); - if (batadv_send_skb_to_orig(skb, res_dst_orig_node, NULL)) + res = batadv_send_skb_to_orig(skb, res_dst_orig_node, NULL); + if (res != NET_XMIT_DROP) ret = true; + goto out; unlock: @@ -1878,11 +1902,11 @@ batadv_send_my_tt_response(struct batadv_priv *bat_priv, tt_tot = tt_len / sizeof(struct batadv_tt_change); len = sizeof(*tt_response) + tt_len; - skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN); + skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN); if (!skb) goto unlock; - skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); + skb_reserve(skb, ETH_HLEN); packet_pos = skb_put(skb, len); tt_response = (struct batadv_tt_query_packet *)packet_pos; tt_response->ttvn = req_ttvn; @@ -1925,7 +1949,7 @@ batadv_send_my_tt_response(struct batadv_priv *bat_priv, batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX); - if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP) ret = true; goto out; @@ -2212,11 +2236,11 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, if (!batadv_tt_check_roam_count(bat_priv, client)) goto out; - skb = dev_alloc_skb(sizeof(*roam_adv_packet) + ETH_HLEN + NET_IP_ALIGN); + skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN); if (!skb) goto out; - skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); + skb_reserve(skb, ETH_HLEN); roam_adv_packet = (struct batadv_roam_adv_packet *)skb_put(skb, len); @@ -2238,7 +2262,7 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_TX); - if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP) ret = 0; out: diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index ab8e683b402f..659a3bb759ce 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -33,7 +33,7 @@ void batadv_tt_global_add_orig(struct batadv_priv *bat_priv, const unsigned char *tt_buff, int tt_buff_len); int batadv_tt_global_add(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - const unsigned char *addr, uint8_t flags, + const unsigned char *addr, uint16_t flags, uint8_t ttvn); int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset); void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index aba8364c3689..b2c94e139319 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -61,6 +61,7 @@ struct batadv_hard_iface_bat_iv { * @if_status: status of the interface for batman-adv * @net_dev: pointer to the net_device * @frag_seqno: last fragment sequence number sent by this interface + * @num_bcasts: number of payload re-broadcasts on this interface (ARQ) * @hardif_obj: kobject of the per interface sysfs "mesh" directory * @refcount: number of contexts the object is used * @batman_adv_ptype: packet type describing packets that should be processed by @@ -76,6 +77,7 @@ struct batadv_hard_iface { char if_status; struct net_device *net_dev; atomic_t frag_seqno; + uint8_t num_bcasts; struct kobject *hardif_obj; atomic_t refcount; struct packet_type batman_adv_ptype; @@ -640,7 +642,7 @@ struct batadv_socket_packet { #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_bla_backbone_gw { uint8_t orig[ETH_ALEN]; - short vid; + unsigned short vid; struct hlist_node hash_entry; struct batadv_priv *bat_priv; unsigned long lasttime; @@ -663,7 +665,7 @@ struct batadv_bla_backbone_gw { */ struct batadv_bla_claim { uint8_t addr[ETH_ALEN]; - short vid; + unsigned short vid; struct batadv_bla_backbone_gw *backbone_gw; unsigned long lasttime; struct hlist_node hash_entry; diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 0bb3b5982f94..dc8b5d4dd636 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -464,7 +464,7 @@ find_router: goto out; } - if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP) ret = 0; out: diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index 1625e5793a89..4983340f1943 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -392,12 +392,12 @@ batadv_add_packet(struct batadv_priv *bat_priv, return NULL; len = sizeof(*packet) + vis_info_len; - info->skb_packet = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN); + info->skb_packet = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN); if (!info->skb_packet) { kfree(info); return NULL; } - skb_reserve(info->skb_packet, ETH_HLEN + NET_IP_ALIGN); + skb_reserve(info->skb_packet, ETH_HLEN); packet = (struct batadv_vis_packet *)skb_put(info->skb_packet, len); kref_init(&info->refcount); @@ -697,7 +697,7 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node; struct batadv_vis_packet *packet; struct sk_buff *skb; - uint32_t i; + uint32_t i, res; packet = (struct batadv_vis_packet *)info->skb_packet->data; @@ -724,7 +724,8 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, if (!skb) continue; - if (!batadv_send_skb_to_orig(skb, orig_node, NULL)) + res = batadv_send_skb_to_orig(skb, orig_node, NULL); + if (res == NET_XMIT_DROP) kfree_skb(skb); } rcu_read_unlock(); @@ -748,7 +749,7 @@ static void batadv_unicast_vis_packet(struct batadv_priv *bat_priv, if (!skb) goto out; - if (!batadv_send_skb_to_orig(skb, orig_node, NULL)) + if (batadv_send_skb_to_orig(skb, orig_node, NULL) == NET_XMIT_DROP) kfree_skb(skb); out: @@ -854,13 +855,13 @@ int batadv_vis_init(struct batadv_priv *bat_priv) if (!bat_priv->vis.my_info) goto err; - len = sizeof(*packet) + BATADV_MAX_VIS_PACKET_SIZE; - len += ETH_HLEN + NET_IP_ALIGN; - bat_priv->vis.my_info->skb_packet = dev_alloc_skb(len); + len = sizeof(*packet) + BATADV_MAX_VIS_PACKET_SIZE + ETH_HLEN; + bat_priv->vis.my_info->skb_packet = netdev_alloc_skb_ip_align(NULL, + len); if (!bat_priv->vis.my_info->skb_packet) goto free_info; - skb_reserve(bat_priv->vis.my_info->skb_packet, ETH_HLEN + NET_IP_ALIGN); + skb_reserve(bat_priv->vis.my_info->skb_packet, ETH_HLEN); tmp_skb = bat_priv->vis.my_info->skb_packet; packet = (struct batadv_vis_packet *)skb_put(tmp_skb, sizeof(*packet)); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 967312803e41..75f3239130f8 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -22,6 +22,9 @@ #include <asm/uaccess.h> #include "br_private.h" +#define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \ + NETIF_F_GSO_MASK | NETIF_F_HW_CSUM) + /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -346,12 +349,10 @@ void br_dev_setup(struct net_device *dev) dev->tx_queue_len = 0; dev->priv_flags = IFF_EBRIDGE; - dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | - NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_LLTX | - NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_CTAG_TX; - dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | - NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | - NETIF_F_HW_VLAN_CTAG_TX; + dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | + NETIF_F_HW_VLAN_CTAG_TX; + dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX; + dev->vlan_features = COMMON_FEATURES; br->dev = dev; spin_lock_init(&br->lock); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 81f2389f78eb..37a467697967 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -23,6 +23,7 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> +#include <linux/inetdevice.h> #include <net/ip.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -381,7 +382,8 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->protocol = IPPROTO_IGMP; - iph->saddr = 0; + iph->saddr = br->multicast_query_use_ifaddr ? + inet_select_addr(br->dev, 0, RT_SCOPE_LINK) : 0; iph->daddr = htonl(INADDR_ALLHOSTS_GROUP); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; @@ -615,8 +617,6 @@ 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++; @@ -654,7 +654,6 @@ static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; - unsigned long now = jiffies; int err; spin_lock(&br->multicast_lock); @@ -669,7 +668,6 @@ static int br_multicast_add_group(struct net_bridge *br, if (!port) { mp->mglist = true; - mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -677,7 +675,7 @@ static int br_multicast_add_group(struct net_bridge *br, (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->port == port) - goto found; + goto out; if ((unsigned long)p->port < (unsigned long)port) break; } @@ -688,8 +686,6 @@ static int br_multicast_add_group(struct net_bridge *br, rcu_assign_pointer(*pp, p); br_mdb_notify(br->dev, port, group, RTM_NEWMDB); -found: - mod_timer(&p->timer, now + br->multicast_membership_interval); out: err = 0; @@ -1129,6 +1125,10 @@ 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; + max_delay *= br->multicast_last_member_count; if (mp->mglist && @@ -1203,6 +1203,10 @@ 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; + max_delay *= br->multicast_last_member_count; if (mp->mglist && (timer_pending(&mp->timer) ? @@ -1246,6 +1250,32 @@ static void br_multicast_leave_group(struct net_bridge *br, if (!mp) goto out; + if (br->multicast_querier && + !timer_pending(&br->multicast_querier_timer)) { + __br_multicast_send_query(br, port, &mp->addr); + + time = jiffies + br->multicast_last_member_count * + br->multicast_last_member_interval; + mod_timer(port ? &port->multicast_query_timer : + &br->multicast_query_timer, time); + + for (p = mlock_dereference(mp->ports, br); + p != NULL; + p = mlock_dereference(p->next, br)) { + if (p->port != port) + continue; + + if (!hlist_unhashed(&p->mglist) && + (timer_pending(&p->timer) ? + time_after(p->timer.expires, time) : + try_to_del_timer_sync(&p->timer) >= 0)) { + mod_timer(&p->timer, time); + } + + break; + } + } + if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { struct net_bridge_port_group __rcu **pp; @@ -1261,7 +1291,7 @@ static void br_multicast_leave_group(struct net_bridge *br, call_rcu_bh(&p->rcu, br_multicast_free_pg); br_mdb_notify(br->dev, port, group, RTM_DELMDB); - if (!mp->ports && !mp->mglist && + if (!mp->ports && !mp->mglist && mp->timer_armed && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } @@ -1273,30 +1303,12 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval; if (!port) { - if (mp->mglist && + if (mp->mglist && mp->timer_armed && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); } - - goto out; - } - - for (p = mlock_dereference(mp->ports, br); - p != NULL; - p = mlock_dereference(p->next, br)) { - if (p->port != port) - continue; - - if (!hlist_unhashed(&p->mglist) && - (timer_pending(&p->timer) ? - time_after(p->timer.expires, time) : - try_to_del_timer_sync(&p->timer) >= 0)) { - mod_timer(&p->timer, time); - } - - break; } out: @@ -1618,6 +1630,7 @@ void br_multicast_init(struct net_bridge *br) br->multicast_router = 1; br->multicast_querier = 0; + br->multicast_query_use_ifaddr = 0; br->multicast_last_member_count = 2; br->multicast_startup_query_count = 2; @@ -1671,6 +1684,7 @@ void br_multicast_stop(struct net_bridge *br) hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); + mp->timer_armed = false; call_rcu_bh(&mp->rcu, br_multicast_free_group); } } diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 1644b3e1f947..3a3f371b2841 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -31,7 +31,7 @@ struct notifier_block br_device_notifier = { */ static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; bool changed_addr; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d2c043a857b6..1b0ac95a5c37 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -112,6 +112,7 @@ struct net_bridge_mdb_entry struct timer_list timer; struct br_ip addr; bool mglist; + bool timer_armed; }; struct net_bridge_mdb_htable @@ -249,6 +250,7 @@ struct net_bridge u8 multicast_disabled:1; u8 multicast_querier:1; + u8 multicast_query_use_ifaddr:1; u32 hash_elasticity; u32 hash_max; diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 8baa9c08e1a4..394bb96b6087 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -375,6 +375,31 @@ static ssize_t store_multicast_snooping(struct device *d, static DEVICE_ATTR(multicast_snooping, S_IRUGO | S_IWUSR, show_multicast_snooping, store_multicast_snooping); +static ssize_t show_multicast_query_use_ifaddr(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", br->multicast_query_use_ifaddr); +} + +static int set_query_use_ifaddr(struct net_bridge *br, unsigned long val) +{ + br->multicast_query_use_ifaddr = !!val; + return 0; +} + +static ssize_t +store_multicast_query_use_ifaddr(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_query_use_ifaddr); +} +static DEVICE_ATTR(multicast_query_use_ifaddr, S_IRUGO | S_IWUSR, + show_multicast_query_use_ifaddr, + store_multicast_query_use_ifaddr); + static ssize_t show_multicast_querier(struct device *d, struct device_attribute *attr, char *buf) @@ -734,6 +759,7 @@ static struct attribute *bridge_attrs[] = { &dev_attr_multicast_router.attr, &dev_attr_multicast_snooping.attr, &dev_attr_multicast_querier.attr, + &dev_attr_multicast_query_use_ifaddr.attr, &dev_attr_hash_elasticity.attr, &dev_attr_hash_max.attr, &dev_attr_multicast_last_member_count.attr, diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 1f9ece1a9c34..4dca159435cf 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -352,9 +352,9 @@ EXPORT_SYMBOL(caif_enroll_dev); /* notify Caif of device events */ static int caif_device_notify(struct notifier_block *me, unsigned long what, - void *arg) + void *ptr) { - struct net_device *dev = arg; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct caif_device_entry *caifd = NULL; struct caif_dev_common *caifdev; struct cfcnfg *cfg; diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index 942e00a425fd..75ed04b78fa4 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -121,9 +121,9 @@ static struct packet_type caif_usb_type __read_mostly = { }; static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, - void *arg) + void *ptr) { - struct net_device *dev = arg; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct caif_dev_common common; struct cflayer *layer, *link_support; struct usbnet *usbnet; diff --git a/net/can/af_can.c b/net/can/af_can.c index c4e50852c9f4..3ab8dd2e1282 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -794,9 +794,9 @@ EXPORT_SYMBOL(can_proto_unregister); * af_can notifier to create/remove CAN netdevice specific structs */ static int can_notifier(struct notifier_block *nb, unsigned long msg, - void *data) + void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dev_rcv_lists *d; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/can/bcm.c b/net/can/bcm.c index 8f113e6ff327..46f20bfafc0e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1350,9 +1350,9 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, * notification handler for netdevice status changes */ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *data) + void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; diff --git a/net/can/gw.c b/net/can/gw.c index 3ee690e8c7d3..2f291f961a17 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -445,9 +445,9 @@ static inline void cgw_unregister_filter(struct cgw_job *gwj) } static int cgw_notifier(struct notifier_block *nb, - unsigned long msg, void *data) + unsigned long msg, void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/can/raw.c b/net/can/raw.c index 1085e65f848e..641e1c895123 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -239,9 +239,9 @@ static int raw_enable_allfilters(struct net_device *dev, struct sock *sk) } static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *data) + unsigned long msg, void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; diff --git a/net/core/dev.c b/net/core/dev.c index fc1e289397f5..9c18557f93c6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1198,9 +1198,7 @@ static int __dev_open(struct net_device *dev) * If we don't do this there is a chance ndo_poll_controller * or ndo_poll may be running while we open the device */ - ret = netpoll_rx_disable(dev); - if (ret) - return ret; + netpoll_rx_disable(dev); ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); ret = notifier_to_errno(ret); @@ -1309,9 +1307,7 @@ static int __dev_close(struct net_device *dev) LIST_HEAD(single); /* Temporarily disable netpoll until the interface is down */ - retval = netpoll_rx_disable(dev); - if (retval) - return retval; + netpoll_rx_disable(dev); list_add(&dev->unreg_list, &single); retval = __dev_close_many(&single); @@ -1353,14 +1349,11 @@ static int dev_close_many(struct list_head *head) */ int dev_close(struct net_device *dev) { - int ret = 0; if (dev->flags & IFF_UP) { LIST_HEAD(single); /* Block netpoll rx while the interface is going down */ - ret = netpoll_rx_disable(dev); - if (ret) - return ret; + netpoll_rx_disable(dev); list_add(&dev->unreg_list, &single); dev_close_many(&single); @@ -1368,7 +1361,7 @@ int dev_close(struct net_device *dev) netpoll_rx_enable(dev); } - return ret; + return 0; } EXPORT_SYMBOL(dev_close); @@ -1398,6 +1391,14 @@ void dev_disable_lro(struct net_device *dev) } EXPORT_SYMBOL(dev_disable_lro); +static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, + struct net_device *dev) +{ + struct netdev_notifier_info info; + + netdev_notifier_info_init(&info, dev); + return nb->notifier_call(nb, val, &info); +} static int dev_boot_phase = 1; @@ -1430,7 +1431,7 @@ int register_netdevice_notifier(struct notifier_block *nb) goto unlock; for_each_net(net) { for_each_netdev(net, dev) { - err = nb->notifier_call(nb, NETDEV_REGISTER, dev); + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) goto rollback; @@ -1438,7 +1439,7 @@ int register_netdevice_notifier(struct notifier_block *nb) if (!(dev->flags & IFF_UP)) continue; - nb->notifier_call(nb, NETDEV_UP, dev); + call_netdevice_notifier(nb, NETDEV_UP, dev); } } @@ -1454,10 +1455,11 @@ rollback: goto outroll; if (dev->flags & IFF_UP) { - nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); - nb->notifier_call(nb, NETDEV_DOWN, dev); + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); } - nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } } @@ -1495,10 +1497,11 @@ int unregister_netdevice_notifier(struct notifier_block *nb) for_each_net(net) { for_each_netdev(net, dev) { if (dev->flags & IFF_UP) { - nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); - nb->notifier_call(nb, NETDEV_DOWN, dev); + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); } - nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } } unlock: @@ -1508,6 +1511,25 @@ unlock: EXPORT_SYMBOL(unregister_netdevice_notifier); /** + * call_netdevice_notifiers_info - call all network notifier blocks + * @val: value passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function + * @info: notifier information data + * + * Call all network notifier blocks. Parameters and return value + * are as for raw_notifier_call_chain(). + */ + +int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev, + struct netdev_notifier_info *info) +{ + ASSERT_RTNL(); + netdev_notifier_info_init(info, dev); + return raw_notifier_call_chain(&netdev_chain, val, info); +} +EXPORT_SYMBOL(call_netdevice_notifiers_info); + +/** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function @@ -1518,8 +1540,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - ASSERT_RTNL(); - return raw_notifier_call_chain(&netdev_chain, val, dev); + struct netdev_notifier_info info; + + return call_netdevice_notifiers_info(val, dev, &info); } EXPORT_SYMBOL(call_netdevice_notifiers); @@ -1629,7 +1652,6 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) return NET_RX_DROP; } skb->skb_iif = 0; - skb->dev = dev; skb_dst_drop(skb); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; @@ -1702,7 +1724,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb2); if (skb_network_header(skb2) < skb2->data || - skb2->network_header > skb2->tail) { + skb_network_header(skb2) > skb_tail_pointer(skb2)) { net_crit_ratelimited("protocol %04x is buggy, dev %s\n", ntohs(skb2->protocol), dev->name); @@ -3065,6 +3087,46 @@ static int rps_ipi_queued(struct softnet_data *sd) return 0; } +#ifdef CONFIG_NET_FLOW_LIMIT +int netdev_flow_limit_table_len __read_mostly = (1 << 12); +#endif + +static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) +{ +#ifdef CONFIG_NET_FLOW_LIMIT + struct sd_flow_limit *fl; + struct softnet_data *sd; + unsigned int old_flow, new_flow; + + if (qlen < (netdev_max_backlog >> 1)) + return false; + + sd = &__get_cpu_var(softnet_data); + + rcu_read_lock(); + fl = rcu_dereference(sd->flow_limit); + if (fl) { + new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1); + old_flow = fl->history[fl->history_head]; + fl->history[fl->history_head] = new_flow; + + fl->history_head++; + fl->history_head &= FLOW_LIMIT_HISTORY - 1; + + if (likely(fl->buckets[old_flow])) + fl->buckets[old_flow]--; + + if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { + fl->count++; + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); +#endif + return false; +} + /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). @@ -3074,13 +3136,15 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, { struct softnet_data *sd; unsigned long flags; + unsigned int qlen; sd = &per_cpu(softnet_data, cpu); local_irq_save(flags); rps_lock(sd); - if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) { + qlen = skb_queue_len(&sd->input_pkt_queue); + if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { if (skb_queue_len(&sd->input_pkt_queue)) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); @@ -3828,7 +3892,7 @@ static void skb_gro_reset_offset(struct sk_buff *skb) NAPI_GRO_CB(skb)->frag0 = NULL; NAPI_GRO_CB(skb)->frag0_len = 0; - if (skb->mac_header == skb->tail && + if (skb_mac_header(skb) == skb_tail_pointer(skb) && pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); @@ -4370,7 +4434,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, else list_add_tail_rcu(&upper->list, &dev->upper_dev_list); dev_hold(upper_dev); - + call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); return 0; } @@ -4430,6 +4494,7 @@ void netdev_upper_dev_unlink(struct net_device *dev, list_del_rcu(&upper->list); dev_put(upper_dev); kfree_rcu(upper, rcu); + call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -4700,8 +4765,13 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags) } if (dev->flags & IFF_UP && - (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) - call_netdevice_notifiers(NETDEV_CHANGE, dev); + (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = changes; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); + } } /** @@ -5235,6 +5305,10 @@ int register_netdevice(struct net_device *dev) */ dev->hw_enc_features |= NETIF_F_SG; + /* Make NETIF_F_SG inheritable to MPLS. + */ + dev->mpls_features |= NETIF_F_SG; + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) @@ -6014,7 +6088,7 @@ netdev_features_t netdev_increment_features(netdev_features_t all, } EXPORT_SYMBOL(netdev_increment_features); -static struct hlist_head *netdev_create_hash(void) +static struct hlist_head * __net_init netdev_create_hash(void) { int i; struct hlist_head *hash; @@ -6270,6 +6344,10 @@ static int __init net_dev_init(void) sd->backlog.weight = weight_p; sd->backlog.gro_list = NULL; sd->backlog.gro_count = 0; + +#ifdef CONFIG_NET_FLOW_LIMIT + sd->flow_limit = NULL; +#endif } dev_boot_phase = 0; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index d23b6682f4e9..5e78d44333b9 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -295,9 +295,9 @@ static int net_dm_cmd_trace(struct sk_buff *skb, } static int dropmon_net_event(struct notifier_block *ev_block, - unsigned long event, void *ptr) + unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dm_hw_stat_delta *new_stat = NULL; struct dm_hw_stat_delta *tmp; diff --git a/net/core/dst.c b/net/core/dst.c index df9cc810ec8e..ca4231ec7347 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -372,7 +372,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, static int dst_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dst_entry *dst, *last = NULL; switch (event) { diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 22efdaa76ebf..cd23d314d68a 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -82,6 +82,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", + [NETIF_F_GSO_MPLS_BIT] = "tx-mpls-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", @@ -1413,7 +1414,7 @@ static int ethtool_get_module_eeprom(struct net_device *dev, modinfo.eeprom_len); } -/* The main entry point in this file. Called from net/core/dev.c */ +/* The main entry point in this file. Called from net/core/dev_ioctl.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) { diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index d5a9f8ead0d8..21735440c44a 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -705,9 +705,9 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) static int fib_rules_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct fib_rules_ops *ops; diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 569d355fec3e..2bf83299600a 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -146,11 +146,23 @@ static void softnet_seq_stop(struct seq_file *seq, void *v) static int softnet_seq_show(struct seq_file *seq, void *v) { struct softnet_data *sd = v; + unsigned int flow_limit_count = 0; - seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", +#ifdef CONFIG_NET_FLOW_LIMIT + struct sd_flow_limit *fl; + + rcu_read_lock(); + fl = rcu_dereference(sd->flow_limit); + if (fl) + flow_limit_count = fl->count; + rcu_read_unlock(); +#endif + + seq_printf(seq, + "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ - sd->cpu_collision, sd->received_rps); + sd->cpu_collision, sd->received_rps, flow_limit_count); return 0; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index cec074be8c43..03c8ec3edc72 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -247,7 +247,7 @@ static void netpoll_poll_dev(struct net_device *dev) zap_completion_queue(); } -int netpoll_rx_disable(struct net_device *dev) +void netpoll_rx_disable(struct net_device *dev) { struct netpoll_info *ni; int idx; @@ -257,7 +257,6 @@ int netpoll_rx_disable(struct net_device *dev) if (ni) down(&ni->dev_lock); srcu_read_unlock(&netpoll_srcu, idx); - return 0; } EXPORT_SYMBOL(netpoll_rx_disable); @@ -690,25 +689,20 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo send_skb->dev = skb->dev; skb_reset_network_header(send_skb); - skb_put(send_skb, sizeof(struct ipv6hdr)); - hdr = ipv6_hdr(send_skb); - + hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr)); *(__be32*)hdr = htonl(0x60000000); - hdr->payload_len = htons(size); hdr->nexthdr = IPPROTO_ICMPV6; hdr->hop_limit = 255; hdr->saddr = *saddr; hdr->daddr = *daddr; - send_skb->transport_header = send_skb->tail; - skb_put(send_skb, size); - - icmp6h = (struct icmp6hdr *)skb_transport_header(skb); + icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr)); icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; icmp6h->icmp6_router = 0; icmp6h->icmp6_solicited = 1; - target = (struct in6_addr *)(skb_transport_header(send_skb) + sizeof(struct icmp6hdr)); + + target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr)); *target = msg->target; icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size, IPPROTO_ICMPV6, diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 0777d0aa18c3..e533259dce3c 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -261,7 +261,7 @@ struct cgroup_subsys net_prio_subsys = { static int netprio_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netprio_map *old; /* diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 11f2704c3810..303412d8332b 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1921,7 +1921,7 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id); if (pn->pktgen_exiting) @@ -2708,15 +2708,15 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, *vlan_encapsulated_proto = htons(ETH_P_IP); } - skb->network_header = skb->tail; - skb->transport_header = skb->network_header + sizeof(struct iphdr); - skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr)); + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, skb->len); + iph = (struct iphdr *) skb_put(skb, sizeof(struct iphdr)); + + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); skb_set_queue_mapping(skb, queue_map); skb->priority = pkt_dev->skb_priority; - iph = ip_hdr(skb); - udph = udp_hdr(skb); - memcpy(eth, pkt_dev->hh, 12); *(__be16 *) & eth[12] = protocol; @@ -2746,8 +2746,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->check = 0; iph->check = ip_fast_csum((void *)iph, iph->ihl); skb->protocol = protocol; - skb->mac_header = (skb->network_header - ETH_HLEN - - pkt_dev->pkt_overhead); skb->dev = odev; skb->pkt_type = PACKET_HOST; pktgen_finalize_skb(pkt_dev, skb, datalen); @@ -2822,13 +2820,14 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, *vlan_encapsulated_proto = htons(ETH_P_IPV6); } - skb->network_header = skb->tail; - skb->transport_header = skb->network_header + sizeof(struct ipv6hdr); - skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr)); + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, skb->len); + iph = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); + + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); skb_set_queue_mapping(skb, queue_map); skb->priority = pkt_dev->skb_priority; - iph = ipv6_hdr(skb); - udph = udp_hdr(skb); memcpy(eth, pkt_dev->hh, 12); *(__be16 *) ð[12] = protocol; @@ -2863,8 +2862,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, iph->daddr = pkt_dev->cur_in6_daddr; iph->saddr = pkt_dev->cur_in6_saddr; - skb->mac_header = (skb->network_header - ETH_HLEN - - pkt_dev->pkt_overhead); skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a08bd2b7fe3f..49c14451d8ab 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2667,7 +2667,7 @@ static void rtnetlink_rcv(struct sk_buff *skb) static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_UP: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index cfd777bd6bd0..73f57a0e1523 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -199,9 +199,7 @@ struct sk_buff *__alloc_skb_head(gfp_t gfp_mask, int node) skb->truesize = sizeof(struct sk_buff); atomic_set(&skb->users, 1); -#ifdef NET_SKBUFF_DATA_USES_OFFSET - skb->mac_header = ~0U; -#endif + skb->mac_header = (typeof(skb->mac_header))~0U; out: return skb; } @@ -275,10 +273,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - skb->mac_header = ~0U; - skb->transport_header = ~0U; -#endif + skb->mac_header = (typeof(skb->mac_header))~0U; + skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); @@ -344,10 +340,8 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - skb->mac_header = ~0U; - skb->transport_header = ~0U; -#endif + skb->mac_header = (typeof(skb->mac_header))~0U; + skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); @@ -2853,7 +2847,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) doffset + tnl_hlen); if (fskb != skb_shinfo(skb)->frag_list) - continue; + goto perform_csum_check; if (!sg) { nskb->ip_summed = CHECKSUM_NONE; @@ -2917,6 +2911,7 @@ skip_fraglist: nskb->len += nskb->data_len; nskb->truesize += nskb->data_len; +perform_csum_check: if (!csum) { nskb->csum = skb_checksum(nskb, doffset, nskb->len - doffset, 0); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cfdb46ab3a7f..741db5fc7806 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -87,6 +87,96 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write, } #endif /* CONFIG_RPS */ +#ifdef CONFIG_NET_FLOW_LIMIT +static DEFINE_MUTEX(flow_limit_update_mutex); + +static int flow_limit_cpu_sysctl(ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct sd_flow_limit *cur; + struct softnet_data *sd; + cpumask_var_t mask; + int i, len, ret = 0; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + if (write) { + ret = cpumask_parse_user(buffer, *lenp, mask); + if (ret) + goto done; + + mutex_lock(&flow_limit_update_mutex); + len = sizeof(*cur) + netdev_flow_limit_table_len; + for_each_possible_cpu(i) { + sd = &per_cpu(softnet_data, i); + cur = rcu_dereference_protected(sd->flow_limit, + lockdep_is_held(&flow_limit_update_mutex)); + if (cur && !cpumask_test_cpu(i, mask)) { + RCU_INIT_POINTER(sd->flow_limit, NULL); + synchronize_rcu(); + kfree(cur); + } else if (!cur && cpumask_test_cpu(i, mask)) { + cur = kzalloc(len, GFP_KERNEL); + if (!cur) { + /* not unwinding previous changes */ + ret = -ENOMEM; + goto write_unlock; + } + cur->num_buckets = netdev_flow_limit_table_len; + rcu_assign_pointer(sd->flow_limit, cur); + } + } +write_unlock: + mutex_unlock(&flow_limit_update_mutex); + } else { + if (*ppos || !*lenp) { + *lenp = 0; + goto done; + } + + cpumask_clear(mask); + rcu_read_lock(); + for_each_possible_cpu(i) { + sd = &per_cpu(softnet_data, i); + if (rcu_dereference(sd->flow_limit)) + cpumask_set_cpu(i, mask); + } + rcu_read_unlock(); + + len = cpumask_scnprintf(buffer, *lenp, mask); + *lenp = len + 1; + *ppos += len + 1; + } + +done: + free_cpumask_var(mask); + return ret; +} + +static int flow_limit_table_len_sysctl(ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + unsigned int old, *ptr; + int ret; + + mutex_lock(&flow_limit_update_mutex); + + ptr = table->data; + old = *ptr; + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (!ret && write && !is_power_of_2(*ptr)) { + *ptr = old; + ret = -EINVAL; + } + + mutex_unlock(&flow_limit_update_mutex); + return ret; +} +#endif /* CONFIG_NET_FLOW_LIMIT */ + static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { @@ -180,6 +270,20 @@ static struct ctl_table net_core_table[] = { .proc_handler = rps_sock_flow_sysctl }, #endif +#ifdef CONFIG_NET_FLOW_LIMIT + { + .procname = "flow_limit_cpu_bitmap", + .mode = 0644, + .proc_handler = flow_limit_cpu_sysctl + }, + { + .procname = "flow_limit_table_len", + .data = &netdev_flow_limit_table_len, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = flow_limit_table_len_sysctl + }, +#endif /* CONFIG_NET_FLOW_LIMIT */ #endif /* CONFIG_NET */ { .procname = "netdev_budget", diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index c21f200eed93..dd4d506ef923 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2078,9 +2078,9 @@ out_err: } static int dn_device_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 55e1fd5b3e56..3b9d5f20bd1c 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -1352,10 +1352,9 @@ static inline void lowpan_netlink_fini(void) } static int lowpan_device_event(struct notifier_block *unused, - unsigned long event, - void *ptr) + unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); LIST_HEAD(del_list); struct lowpan_dev_record *entry, *tmp; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 8603ca827104..37cf1a6ea3ad 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -9,10 +9,7 @@ config IP_MULTICAST intend to participate in the MBONE, a high bandwidth network on top of the Internet which carries audio and video broadcasts. More information about the MBONE is on the WWW at - <http://www.savetz.com/mbone/>. Information about the multicast - capabilities of the various network cards is contained in - <file:Documentation/networking/multicast.txt>. For most people, it's - safe to say N. + <http://www.savetz.com/mbone/>. For most people, it's safe to say N. config IP_ADVANCED_ROUTER bool "IP: advanced router" @@ -223,10 +220,8 @@ config IP_MROUTE packets that have several destination addresses. It is needed on the MBONE, a high bandwidth network on top of the Internet which carries audio and video broadcasts. In order to do that, you would most - likely run the program mrouted. Information about the multicast - capabilities of the various network cards is contained in - <file:Documentation/networking/multicast.txt>. If you haven't heard - about it, you don't need it. + likely run the program mrouted. If you haven't heard about it, you + don't need it. config IP_MROUTE_MULTIPLE_TABLES bool "IP: multicast policy routing" diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index d01be2a3ae53..9c090c7daea1 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1295,6 +1295,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_GRE | SKB_GSO_TCPV6 | SKB_GSO_UDP_TUNNEL | + SKB_GSO_MPLS | 0))) goto out; @@ -1384,7 +1385,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, goto out_unlock; id = ntohl(*(__be32 *)&iph->id); - flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF)); + flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); id >>= 16; for (p = *head; p; p = p->next) { @@ -1406,6 +1407,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | + ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) | ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); NAPI_GRO_CB(p)->flush |= flush; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 2e7f1948216f..717902669d2f 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -419,12 +419,9 @@ static void ah4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { - atomic_inc(&flow_cache_genid); - rt_genid_bump(net); - + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); - } else + else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 247ec1951c35..4429b013f269 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1234,13 +1234,19 @@ out: static int arp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_change_info *change_info; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&arp_tbl, dev); rt_cache_flush(dev_net(dev)); break; + case NETDEV_CHANGE: + change_info = ptr; + if (change_info->flags_changed & IFF_NOARP) + neigh_changeaddr(&arp_tbl, dev); + break; default: break; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index dfc39d4d48b7..b047e2d8a614 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1333,7 +1333,7 @@ static void inetdev_send_gratuitous_arp(struct net_device *dev, static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4cfe34d4cc96..ab3d814bc80a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -502,12 +502,9 @@ static void esp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { - atomic_inc(&flow_cache_genid); - rt_genid_bump(net); - + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); - } else + else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c7629a209f9d..05a4888dede9 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1038,7 +1038,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; struct net *net = dev_net(dev); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 76e10b47e053..5f7d11a45871 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -482,7 +482,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct iphdr *iph; int room; - struct icmp_bxm icmp_param; + struct icmp_bxm *icmp_param; struct rtable *rt = skb_rtable(skb_in); struct ipcm_cookie ipc; struct flowi4 fl4; @@ -503,7 +503,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) iph = ip_hdr(skb_in); if ((u8 *)iph < skb_in->head || - (skb_in->network_header + sizeof(*iph)) > skb_in->tail) + (skb_network_header(skb_in) + sizeof(*iph)) > + skb_tail_pointer(skb_in)) goto out; /* @@ -557,9 +558,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) } } + icmp_param = kmalloc(sizeof(*icmp_param), GFP_ATOMIC); + if (!icmp_param) + return; + sk = icmp_xmit_lock(net); if (sk == NULL) - return; + goto out_free; /* * Construct source address and options. @@ -585,7 +590,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) IPTOS_PREC_INTERNETCONTROL) : iph->tos; - if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in)) + if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in)) goto out_unlock; @@ -593,19 +598,19 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) * Prepare data for ICMP header. */ - icmp_param.data.icmph.type = type; - icmp_param.data.icmph.code = code; - icmp_param.data.icmph.un.gateway = info; - icmp_param.data.icmph.checksum = 0; - icmp_param.skb = skb_in; - icmp_param.offset = skb_network_offset(skb_in); + icmp_param->data.icmph.type = type; + icmp_param->data.icmph.code = code; + icmp_param->data.icmph.un.gateway = info; + icmp_param->data.icmph.checksum = 0; + icmp_param->skb = skb_in; + icmp_param->offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; ipc.addr = iph->saddr; - ipc.opt = &icmp_param.replyopts.opt; + ipc.opt = &icmp_param->replyopts.opt; ipc.tx_flags = 0; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, - type, code, &icmp_param); + type, code, icmp_param); if (IS_ERR(rt)) goto out_unlock; @@ -617,19 +622,21 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) room = dst_mtu(&rt->dst); if (room > 576) room = 576; - room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; + room -= sizeof(struct iphdr) + icmp_param->replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); - icmp_param.data_len = skb_in->len - icmp_param.offset; - if (icmp_param.data_len > room) - icmp_param.data_len = room; - icmp_param.head_len = sizeof(struct icmphdr); + icmp_param->data_len = skb_in->len - icmp_param->offset; + if (icmp_param->data_len > room) + icmp_param->data_len = room; + icmp_param->head_len = sizeof(struct icmphdr); - icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); + icmp_push_reply(icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); +out_free: + kfree(icmp_param); out:; } EXPORT_SYMBOL(icmp_send); @@ -657,7 +664,8 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info) } /* - * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, and ICMP_QUENCH. + * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and + * ICMP_PARAMETERPROB. */ static void icmp_unreach(struct sk_buff *skb) @@ -939,7 +947,8 @@ error: void icmp_err(struct sk_buff *skb, u32 info) { struct iphdr *iph = (struct iphdr *)skb->data; - struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); + int offset = iph->ihl<<2; + struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset); int type = icmp_hdr(skb)->type; int code = icmp_hdr(skb)->code; struct net *net = dev_net(skb->dev); @@ -949,7 +958,7 @@ void icmp_err(struct sk_buff *skb, u32 info) * triggered by ICMP_ECHOREPLY which sent from kernel. */ if (icmph->type != ICMP_ECHOREPLY) { - ping_err(skb, info); + ping_err(skb, offset, info); return; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d8c232794bcb..450f625361e4 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -363,7 +363,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); - const int igmplen = skb->tail - skb->transport_header; + const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2a83591492dd..a982657d05e7 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -429,7 +429,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, return; } - ip_tunnel_xmit(skb, dev, tnl_params); + ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } static netdev_tx_t ipgre_xmit(struct sk_buff *skb, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index be2f8da0ae8e..7c79cf8ad449 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -487,7 +487,7 @@ drop: EXPORT_SYMBOL_GPL(ip_tunnel_rcv); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, - const struct iphdr *tnl_params) + const struct iphdr *tnl_params, const u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *inner_iph; @@ -670,7 +670,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, iph->version = 4; iph->ihl = sizeof(struct iphdr) >> 2; iph->frag_off = df; - iph->protocol = tnl_params->protocol; + iph->protocol = protocol; iph->tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 59cb8c769056..826be4cb482a 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -47,12 +47,9 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { - atomic_inc(&flow_cache_genid); - rt_genid_bump(net); - + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); - } else + else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 77bfcce64fe5..9df7ecd393f2 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -222,7 +222,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb->encapsulation = 1; } - ip_tunnel_xmit(skb, dev, tiph); + ip_tunnel_xmit(skb, dev, tiph, tiph->protocol); return NETDEV_TX_OK; tx_error: diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9d9610ae7855..df97f0ac1a1c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -945,6 +945,7 @@ static int ipmr_cache_report(struct mr_table *mrt, struct igmpmsg *msg; struct sock *mroute_sk; int ret; + unsigned long tail_offset; #ifdef CONFIG_IP_PIMSM if (assert == IGMPMSG_WHOLEPKT) @@ -980,7 +981,12 @@ static int ipmr_cache_report(struct mr_table *mrt, /* Copy the IP header */ - skb->network_header = skb->tail; + tail_offset = skb_tail_offset(skb); + if (tail_offset > 0xffff) { + kfree_skb(skb); + return -EINVAL; + } + skb_set_network_header(skb, tail_offset); skb_put(skb, ihl); skb_copy_to_linear_data(skb, pkt->data, ihl); ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */ @@ -1609,7 +1615,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr_table *mrt; struct vif_device *v; diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 5d5d4d1be9c2..30e4de940567 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -108,7 +108,7 @@ static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - const struct net_device *dev = ptr; + const struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_DOWN) { @@ -129,7 +129,10 @@ static int masq_inet_event(struct notifier_block *this, void *ptr) { struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev; - return masq_device_event(this, event, dev); + struct netdev_notifier_info info; + + netdev_notifier_info_init(&info, dev); + return masq_device_event(this, event, &info); } static struct notifier_block masq_dev_notifier = { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 7d93d62cd5fd..1f1b2dd90277 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -33,7 +33,6 @@ #include <linux/netdevice.h> #include <net/snmp.h> #include <net/ip.h> -#include <net/ipv6.h> #include <net/icmp.h> #include <net/protocol.h> #include <linux/skbuff.h> @@ -46,8 +45,18 @@ #include <net/inet_common.h> #include <net/checksum.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <linux/in6.h> +#include <linux/icmpv6.h> +#include <net/addrconf.h> +#include <net/ipv6.h> +#include <net/transp_v6.h> +#endif -static struct ping_table ping_table; + +struct ping_table ping_table; +struct pingv6_ops pingv6_ops; +EXPORT_SYMBOL_GPL(pingv6_ops); static u16 ping_port_rover; @@ -58,6 +67,7 @@ static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int ma pr_debug("hash(%d) = %d\n", num, res); return res; } +EXPORT_SYMBOL_GPL(ping_hash); static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table, struct net *net, unsigned int num) @@ -65,7 +75,7 @@ static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table, return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)]; } -static int ping_v4_get_port(struct sock *sk, unsigned short ident) +int ping_get_port(struct sock *sk, unsigned short ident) { struct hlist_nulls_node *node; struct hlist_nulls_head *hlist; @@ -103,6 +113,10 @@ next_port: ping_portaddr_for_each_entry(sk2, node, hlist) { isk2 = inet_sk(sk2); + /* BUG? Why is this reuse and not reuseaddr? ping.c + * doesn't turn off SO_REUSEADDR, and it doesn't expect + * that other ping processes can steal its packets. + */ if ((isk2->inet_num == ident) && (sk2 != sk) && (!sk2->sk_reuse || !sk->sk_reuse)) @@ -125,17 +139,18 @@ fail: write_unlock_bh(&ping_table.lock); return 1; } +EXPORT_SYMBOL_GPL(ping_get_port); -static void ping_v4_hash(struct sock *sk) +void ping_hash(struct sock *sk) { - pr_debug("ping_v4_hash(sk->port=%u)\n", inet_sk(sk)->inet_num); + pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num); BUG(); /* "Please do not press this button again." */ } -static void ping_v4_unhash(struct sock *sk) +void ping_unhash(struct sock *sk) { struct inet_sock *isk = inet_sk(sk); - pr_debug("ping_v4_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); + pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); if (sk_hashed(sk)) { write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); @@ -146,31 +161,61 @@ static void ping_v4_unhash(struct sock *sk) write_unlock_bh(&ping_table.lock); } } +EXPORT_SYMBOL_GPL(ping_unhash); -static struct sock *ping_v4_lookup(struct net *net, __be32 saddr, __be32 daddr, - u16 ident, int dif) +static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) { struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident); struct sock *sk = NULL; struct inet_sock *isk; struct hlist_nulls_node *hnode; + int dif = skb->dev->ifindex; + + if (skb->protocol == htons(ETH_P_IP)) { + pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", + (int)ident, &ip_hdr(skb)->daddr, dif); +#if IS_ENABLED(CONFIG_IPV6) + } else if (skb->protocol == htons(ETH_P_IPV6)) { + pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n", + (int)ident, &ipv6_hdr(skb)->daddr, dif); +#endif + } - pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", - (int)ident, &daddr, dif); read_lock_bh(&ping_table.lock); ping_portaddr_for_each_entry(sk, hnode, hslot) { isk = inet_sk(sk); - pr_debug("found: %p: num = %d, daddr = %pI4, dif = %d\n", sk, - (int)isk->inet_num, &isk->inet_rcv_saddr, - sk->sk_bound_dev_if); - pr_debug("iterate\n"); if (isk->inet_num != ident) continue; - if (isk->inet_rcv_saddr && isk->inet_rcv_saddr != daddr) - continue; + + if (skb->protocol == htons(ETH_P_IP) && + sk->sk_family == AF_INET) { + pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk, + (int) isk->inet_num, &isk->inet_rcv_saddr, + sk->sk_bound_dev_if); + + if (isk->inet_rcv_saddr && + isk->inet_rcv_saddr != ip_hdr(skb)->daddr) + continue; +#if IS_ENABLED(CONFIG_IPV6) + } else if (skb->protocol == htons(ETH_P_IPV6) && + sk->sk_family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk, + (int) isk->inet_num, + &inet6_sk(sk)->rcv_saddr, + sk->sk_bound_dev_if); + + if (!ipv6_addr_any(&np->rcv_saddr) && + !ipv6_addr_equal(&np->rcv_saddr, + &ipv6_hdr(skb)->daddr)) + continue; +#endif + } + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) continue; @@ -200,7 +245,7 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, } -static int ping_init_sock(struct sock *sk) +int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); kgid_t group = current_egid(); @@ -225,8 +270,9 @@ static int ping_init_sock(struct sock *sk) return -EACCES; } +EXPORT_SYMBOL_GPL(ping_init_sock); -static void ping_close(struct sock *sk, long timeout) +void ping_close(struct sock *sk, long timeout) { pr_debug("ping_close(sk=%p,sk->num=%u)\n", inet_sk(sk), inet_sk(sk)->inet_num); @@ -234,36 +280,122 @@ static void ping_close(struct sock *sk, long timeout) sk_common_release(sk); } +EXPORT_SYMBOL_GPL(ping_close); + +/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ +int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, + struct sockaddr *uaddr, int addr_len) { + struct net *net = sock_net(sk); + if (sk->sk_family == AF_INET) { + struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; + int chk_addr_ret; + + if (addr_len < sizeof(*addr)) + return -EINVAL; + + pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", + sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); + + chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + + if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) + chk_addr_ret = RTN_LOCAL; + + if ((sysctl_ip_nonlocal_bind == 0 && + isk->freebind == 0 && isk->transparent == 0 && + chk_addr_ret != RTN_LOCAL) || + chk_addr_ret == RTN_MULTICAST || + chk_addr_ret == RTN_BROADCAST) + return -EADDRNOTAVAIL; + +#if IS_ENABLED(CONFIG_IPV6) + } else if (sk->sk_family == AF_INET6) { + struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; + int addr_type, scoped, has_addr; + struct net_device *dev = NULL; + + if (addr_len < sizeof(*addr)) + return -EINVAL; + + pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n", + sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port)); + + addr_type = ipv6_addr_type(&addr->sin6_addr); + scoped = __ipv6_addr_needs_scope_id(addr_type); + if ((addr_type != IPV6_ADDR_ANY && + !(addr_type & IPV6_ADDR_UNICAST)) || + (scoped && !addr->sin6_scope_id)) + return -EINVAL; + + rcu_read_lock(); + if (addr->sin6_scope_id) { + dev = dev_get_by_index_rcu(net, addr->sin6_scope_id); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + } + has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev, + scoped); + rcu_read_unlock(); + + if (!(isk->freebind || isk->transparent || has_addr || + addr_type == IPV6_ADDR_ANY)) + return -EADDRNOTAVAIL; + + if (scoped) + sk->sk_bound_dev_if = addr->sin6_scope_id; +#endif + } else { + return -EAFNOSUPPORT; + } + return 0; +} + +void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) +{ + if (saddr->sa_family == AF_INET) { + struct inet_sock *isk = inet_sk(sk); + struct sockaddr_in *addr = (struct sockaddr_in *) saddr; + isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (saddr->sa_family == AF_INET6) { + struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr; + struct ipv6_pinfo *np = inet6_sk(sk); + np->rcv_saddr = np->saddr = addr->sin6_addr; +#endif + } +} +void ping_clear_saddr(struct sock *sk, int dif) +{ + sk->sk_bound_dev_if = dif; + if (sk->sk_family == AF_INET) { + struct inet_sock *isk = inet_sk(sk); + isk->inet_rcv_saddr = isk->inet_saddr = 0; +#if IS_ENABLED(CONFIG_IPV6) + } else if (sk->sk_family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr)); + memset(&np->saddr, 0, sizeof(np->saddr)); +#endif + } +} /* * We need our own bind because there are no privileged id's == local ports. * Moreover, we don't allow binding to multi- and broadcast addresses. */ -static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct inet_sock *isk = inet_sk(sk); unsigned short snum; - int chk_addr_ret; int err; + int dif = sk->sk_bound_dev_if; - if (addr_len < sizeof(struct sockaddr_in)) - return -EINVAL; - - pr_debug("ping_v4_bind(sk=%p,sa_addr=%08x,sa_port=%d)\n", - sk, addr->sin_addr.s_addr, ntohs(addr->sin_port)); - - chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); - if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) - chk_addr_ret = RTN_LOCAL; - - if ((sysctl_ip_nonlocal_bind == 0 && - isk->freebind == 0 && isk->transparent == 0 && - chk_addr_ret != RTN_LOCAL) || - chk_addr_ret == RTN_MULTICAST || - chk_addr_ret == RTN_BROADCAST) - return -EADDRNOTAVAIL; + err = ping_check_bind_addr(sk, isk, uaddr, addr_len); + if (err) + return err; lock_sock(sk); @@ -272,42 +404,50 @@ static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto out; err = -EADDRINUSE; - isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr; - snum = ntohs(addr->sin_port); - if (ping_v4_get_port(sk, snum) != 0) { - isk->inet_saddr = isk->inet_rcv_saddr = 0; + ping_set_saddr(sk, uaddr); + snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port); + if (ping_get_port(sk, snum) != 0) { + ping_clear_saddr(sk, dif); goto out; } - pr_debug("after bind(): num = %d, daddr = %pI4, dif = %d\n", + pr_debug("after bind(): num = %d, dif = %d\n", (int)isk->inet_num, - &isk->inet_rcv_saddr, (int)sk->sk_bound_dev_if); err = 0; - if (isk->inet_rcv_saddr) + if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) || + (sk->sk_family == AF_INET6 && + !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr))) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; + if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; isk->inet_sport = htons(isk->inet_num); isk->inet_daddr = 0; isk->inet_dport = 0; + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr)); +#endif + sk_dst_reset(sk); out: release_sock(sk); pr_debug("ping_v4_bind -> %d\n", err); return err; } +EXPORT_SYMBOL_GPL(ping_bind); /* * Is this a supported type of ICMP message? */ -static inline int ping_supported(int type, int code) +static inline int ping_supported(int family, int type, int code) { - if (type == ICMP_ECHO && code == 0) - return 1; - return 0; + return (family == AF_INET && type == ICMP_ECHO && code == 0) || + (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0); } /* @@ -315,30 +455,42 @@ static inline int ping_supported(int type, int code) * sort of error condition. */ -static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); - -void ping_err(struct sk_buff *skb, u32 info) +void ping_err(struct sk_buff *skb, int offset, u32 info) { - struct iphdr *iph = (struct iphdr *)skb->data; - struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); + int family; + struct icmphdr *icmph; struct inet_sock *inet_sock; - int type = icmp_hdr(skb)->type; - int code = icmp_hdr(skb)->code; + int type; + int code; struct net *net = dev_net(skb->dev); struct sock *sk; int harderr; int err; + if (skb->protocol == htons(ETH_P_IP)) { + family = AF_INET; + type = icmp_hdr(skb)->type; + code = icmp_hdr(skb)->code; + icmph = (struct icmphdr *)(skb->data + offset); + } else if (skb->protocol == htons(ETH_P_IPV6)) { + family = AF_INET6; + type = icmp6_hdr(skb)->icmp6_type; + code = icmp6_hdr(skb)->icmp6_code; + icmph = (struct icmphdr *) (skb->data + offset); + } else { + BUG(); + } + /* We assume the packet has already been checked by icmp_unreach */ - if (!ping_supported(icmph->type, icmph->code)) + if (!ping_supported(family, icmph->type, icmph->code)) return; - pr_debug("ping_err(type=%04x,code=%04x,id=%04x,seq=%04x)\n", type, - code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); + pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n", + skb->protocol, type, code, ntohs(icmph->un.echo.id), + ntohs(icmph->un.echo.sequence)); - sk = ping_v4_lookup(net, iph->daddr, iph->saddr, - ntohs(icmph->un.echo.id), skb->dev->ifindex); + sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); if (sk == NULL) { pr_debug("no socket, dropping\n"); return; /* No socket for error */ @@ -349,72 +501,83 @@ void ping_err(struct sk_buff *skb, u32 info) harderr = 0; inet_sock = inet_sk(sk); - switch (type) { - default: - case ICMP_TIME_EXCEEDED: - err = EHOSTUNREACH; - break; - case ICMP_SOURCE_QUENCH: - /* This is not a real error but ping wants to see it. - * Report it with some fake errno. */ - err = EREMOTEIO; - break; - case ICMP_PARAMETERPROB: - err = EPROTO; - harderr = 1; - break; - case ICMP_DEST_UNREACH: - if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ - ipv4_sk_update_pmtu(skb, sk, info); - if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) { - err = EMSGSIZE; - harderr = 1; - break; + if (skb->protocol == htons(ETH_P_IP)) { + switch (type) { + default: + case ICMP_TIME_EXCEEDED: + err = EHOSTUNREACH; + break; + case ICMP_SOURCE_QUENCH: + /* This is not a real error but ping wants to see it. + * Report it with some fake errno. + */ + err = EREMOTEIO; + break; + case ICMP_PARAMETERPROB: + err = EPROTO; + harderr = 1; + break; + case ICMP_DEST_UNREACH: + if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ + ipv4_sk_update_pmtu(skb, sk, info); + if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) { + err = EMSGSIZE; + harderr = 1; + break; + } + goto out; } - goto out; - } - err = EHOSTUNREACH; - if (code <= NR_ICMP_UNREACH) { - harderr = icmp_err_convert[code].fatal; - err = icmp_err_convert[code].errno; + err = EHOSTUNREACH; + if (code <= NR_ICMP_UNREACH) { + harderr = icmp_err_convert[code].fatal; + err = icmp_err_convert[code].errno; + } + break; + case ICMP_REDIRECT: + /* See ICMP_SOURCE_QUENCH */ + ipv4_sk_redirect(skb, sk); + err = EREMOTEIO; + break; } - break; - case ICMP_REDIRECT: - /* See ICMP_SOURCE_QUENCH */ - ipv4_sk_redirect(skb, sk); - err = EREMOTEIO; - break; +#if IS_ENABLED(CONFIG_IPV6) + } else if (skb->protocol == htons(ETH_P_IPV6)) { + harderr = pingv6_ops.icmpv6_err_convert(type, code, &err); +#endif } /* * RFC1122: OK. Passes ICMP errors back to application, as per * 4.1.3.3. */ - if (!inet_sock->recverr) { + if ((family == AF_INET && !inet_sock->recverr) || + (family == AF_INET6 && !inet6_sk(sk)->recverr)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else { - ip_icmp_error(sk, skb, err, 0 /* no remote port */, - info, (u8 *)icmph); + if (family == AF_INET) { + ip_icmp_error(sk, skb, err, 0 /* no remote port */, + info, (u8 *)icmph); +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + pingv6_ops.ipv6_icmp_error(sk, skb, err, 0, + info, (u8 *)icmph); +#endif + } } sk->sk_err = err; sk->sk_error_report(sk); out: sock_put(sk); } +EXPORT_SYMBOL_GPL(ping_err); /* - * Copy and checksum an ICMP Echo packet from user space into a buffer. + * Copy and checksum an ICMP Echo packet from user space into a buffer + * starting from the payload. */ -struct pingfakehdr { - struct icmphdr icmph; - struct iovec *iov; - __wsum wcheck; -}; - -static int ping_getfrag(void *from, char *to, - int offset, int fraglen, int odd, struct sk_buff *skb) +int ping_getfrag(void *from, char *to, + int offset, int fraglen, int odd, struct sk_buff *skb) { struct pingfakehdr *pfh = (struct pingfakehdr *)from; @@ -425,20 +588,33 @@ static int ping_getfrag(void *from, char *to, pfh->iov, 0, fraglen - sizeof(struct icmphdr), &pfh->wcheck)) return -EFAULT; + } else if (offset < sizeof(struct icmphdr)) { + BUG(); + } else { + if (csum_partial_copy_fromiovecend + (to, pfh->iov, offset - sizeof(struct icmphdr), + fraglen, &pfh->wcheck)) + return -EFAULT; + } - return 0; +#if IS_ENABLED(CONFIG_IPV6) + /* For IPv6, checksum each skb as we go along, as expected by + * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in + * wcheck, it will be finalized in ping_v4_push_pending_frames. + */ + if (pfh->family == AF_INET6) { + skb->csum = pfh->wcheck; + skb->ip_summed = CHECKSUM_NONE; + pfh->wcheck = 0; } - if (offset < sizeof(struct icmphdr)) - BUG(); - if (csum_partial_copy_fromiovecend - (to, pfh->iov, offset - sizeof(struct icmphdr), - fraglen, &pfh->wcheck)) - return -EFAULT; +#endif + return 0; } +EXPORT_SYMBOL_GPL(ping_getfrag); -static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, - struct flowi4 *fl4) +static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, + struct flowi4 *fl4) { struct sk_buff *skb = skb_peek(&sk->sk_write_queue); @@ -450,24 +626,9 @@ static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, return ip_push_pending_frames(sk, fl4); } -static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) -{ - struct net *net = sock_net(sk); - struct flowi4 fl4; - struct inet_sock *inet = inet_sk(sk); - struct ipcm_cookie ipc; - struct icmphdr user_icmph; - struct pingfakehdr pfh; - struct rtable *rt = NULL; - struct ip_options_data opt_copy; - int free = 0; - __be32 saddr, daddr, faddr; - u8 tos; - int err; - - pr_debug("ping_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); - +int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, + void *user_icmph, size_t icmph_len) { + u8 type, code; if (len > 0xFFFF) return -EMSGSIZE; @@ -482,15 +643,53 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* * Fetch the ICMP header provided by the userland. - * iovec is modified! + * iovec is modified! The ICMP header is consumed. */ - - if (memcpy_fromiovec((u8 *)&user_icmph, msg->msg_iov, - sizeof(struct icmphdr))) + if (memcpy_fromiovec(user_icmph, msg->msg_iov, icmph_len)) return -EFAULT; - if (!ping_supported(user_icmph.type, user_icmph.code)) + + if (family == AF_INET) { + type = ((struct icmphdr *) user_icmph)->type; + code = ((struct icmphdr *) user_icmph)->code; +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + type = ((struct icmp6hdr *) user_icmph)->icmp6_type; + code = ((struct icmp6hdr *) user_icmph)->icmp6_code; +#endif + } else { + BUG(); + } + + if (!ping_supported(family, type, code)) return -EINVAL; + return 0; +} +EXPORT_SYMBOL_GPL(ping_common_sendmsg); + +int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len) +{ + struct net *net = sock_net(sk); + struct flowi4 fl4; + struct inet_sock *inet = inet_sk(sk); + struct ipcm_cookie ipc; + struct icmphdr user_icmph; + struct pingfakehdr pfh; + struct rtable *rt = NULL; + struct ip_options_data opt_copy; + int free = 0; + __be32 saddr, daddr, faddr; + u8 tos; + int err; + + pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); + + err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph, + sizeof(user_icmph)); + if (err) + return err; + /* * Get and verify the address. */ @@ -595,13 +794,14 @@ back_from_confirm: pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence; pfh.iov = msg->msg_iov; pfh.wcheck = 0; + pfh.family = AF_INET; err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len, 0, &ipc, &rt, msg->msg_flags); if (err) ip_flush_pending_frames(sk); else - err = ping_push_pending_frames(sk, &pfh, &fl4); + err = ping_v4_push_pending_frames(sk, &pfh, &fl4); release_sock(sk); out: @@ -622,11 +822,13 @@ do_confirm: goto out; } -static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len) +int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *isk = inet_sk(sk); - struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + int family = sk->sk_family; + struct sockaddr_in *sin; + struct sockaddr_in6 *sin6; struct sk_buff *skb; int copied, err; @@ -636,11 +838,22 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*sin); + if (addr_len) { + if (family == AF_INET) + *addr_len = sizeof(*sin); + else if (family == AF_INET6 && addr_len) + *addr_len = sizeof(*sin6); + } - if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + if (flags & MSG_ERRQUEUE) { + if (family == AF_INET) { + return ip_recv_error(sk, msg, len); +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + return pingv6_ops.ipv6_recv_error(sk, msg, len); +#endif + } + } skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -659,15 +872,40 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sock_recv_timestamp(msg, sk, skb); - /* Copy the address. */ - if (sin) { + /* Copy the address and add cmsg data. */ + if (family == AF_INET) { + sin = (struct sockaddr_in *) msg->msg_name; sin->sin_family = AF_INET; sin->sin_port = 0 /* skb->h.uh->source */; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + + if (isk->cmsg_flags) + ip_cmsg_recv(msg, skb); + +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6hdr *ip6 = ipv6_hdr(skb); + sin6 = (struct sockaddr_in6 *) msg->msg_name; + sin6->sin6_family = AF_INET6; + sin6->sin6_port = 0; + sin6->sin6_addr = ip6->saddr; + + sin6->sin6_flowinfo = 0; + if (np->sndflow) + sin6->sin6_flowinfo = ip6_flowinfo(ip6); + + sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, + IP6CB(skb)->iif); + + if (inet6_sk(sk)->rxopt.all) + pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb); +#endif + } else { + BUG(); } - if (isk->cmsg_flags) - ip_cmsg_recv(msg, skb); + err = copied; done: @@ -676,8 +914,9 @@ out: pr_debug("ping_recvmsg -> %d\n", err); return err; } +EXPORT_SYMBOL_GPL(ping_recvmsg); -static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); @@ -688,6 +927,7 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } return 0; } +EXPORT_SYMBOL_GPL(ping_queue_rcv_skb); /* @@ -698,10 +938,7 @@ void ping_rcv(struct sk_buff *skb) { struct sock *sk; struct net *net = dev_net(skb->dev); - struct iphdr *iph = ip_hdr(skb); struct icmphdr *icmph = icmp_hdr(skb); - __be32 saddr = iph->saddr; - __be32 daddr = iph->daddr; /* We assume the packet has already been checked by icmp_rcv */ @@ -711,8 +948,7 @@ void ping_rcv(struct sk_buff *skb) /* Push ICMP header back */ skb_push(skb, skb->data - (u8 *)icmph); - sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id), - skb->dev->ifindex); + sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); if (sk != NULL) { pr_debug("rcv on socket %p\n", sk); ping_queue_rcv_skb(sk, skb_get(skb)); @@ -723,6 +959,7 @@ void ping_rcv(struct sk_buff *skb) /* We're called from icmp_rcv(). kfree_skb() is done there. */ } +EXPORT_SYMBOL_GPL(ping_rcv); struct proto ping_prot = { .name = "PING", @@ -733,14 +970,14 @@ struct proto ping_prot = { .disconnect = udp_disconnect, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, - .sendmsg = ping_sendmsg, + .sendmsg = ping_v4_sendmsg, .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, .release_cb = ip4_datagram_release_cb, - .hash = ping_v4_hash, - .unhash = ping_v4_unhash, - .get_port = ping_v4_get_port, + .hash = ping_hash, + .unhash = ping_unhash, + .get_port = ping_get_port, .obj_size = sizeof(struct inet_sock), }; EXPORT_SYMBOL(ping_prot); @@ -764,7 +1001,8 @@ static struct sock *ping_get_first(struct seq_file *seq, int start) continue; sk_nulls_for_each(sk, node, hslot) { - if (net_eq(sock_net(sk), net)) + if (net_eq(sock_net(sk), net) && + sk->sk_family == state->family) goto found; } } @@ -797,17 +1035,24 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) return pos ? NULL : sk; } -static void *ping_seq_start(struct seq_file *seq, loff_t *pos) +void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) { struct ping_iter_state *state = seq->private; state->bucket = 0; + state->family = family; read_lock_bh(&ping_table.lock); return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } +EXPORT_SYMBOL_GPL(ping_seq_start); + +static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos) +{ + return ping_seq_start(seq, pos, AF_INET); +} -static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) +void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; @@ -819,13 +1064,15 @@ static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; return sk; } +EXPORT_SYMBOL_GPL(ping_seq_next); -static void ping_seq_stop(struct seq_file *seq, void *v) +void ping_seq_stop(struct seq_file *seq, void *v) { read_unlock_bh(&ping_table.lock); } +EXPORT_SYMBOL_GPL(ping_seq_stop); -static void ping_format_sock(struct sock *sp, struct seq_file *f, +static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, int bucket, int *len) { struct inet_sock *inet = inet_sk(sp); @@ -846,7 +1093,7 @@ static void ping_format_sock(struct sock *sp, struct seq_file *f, atomic_read(&sp->sk_drops), len); } -static int ping_seq_show(struct seq_file *seq, void *v) +static int ping_v4_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%-127s\n", @@ -857,72 +1104,86 @@ static int ping_seq_show(struct seq_file *seq, void *v) struct ping_iter_state *state = seq->private; int len; - ping_format_sock(v, seq, state->bucket, &len); + ping_v4_format_sock(v, seq, state->bucket, &len); seq_printf(seq, "%*s\n", 127 - len, ""); } return 0; } -static const struct seq_operations ping_seq_ops = { - .show = ping_seq_show, - .start = ping_seq_start, +static const struct seq_operations ping_v4_seq_ops = { + .show = ping_v4_seq_show, + .start = ping_v4_seq_start, .next = ping_seq_next, .stop = ping_seq_stop, }; static int ping_seq_open(struct inode *inode, struct file *file) { - return seq_open_net(inode, file, &ping_seq_ops, + struct ping_seq_afinfo *afinfo = PDE_DATA(inode); + return seq_open_net(inode, file, &afinfo->seq_ops, sizeof(struct ping_iter_state)); } -static const struct file_operations ping_seq_fops = { +const struct file_operations ping_seq_fops = { .open = ping_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_net, }; +EXPORT_SYMBOL_GPL(ping_seq_fops); + +static struct ping_seq_afinfo ping_v4_seq_afinfo = { + .name = "icmp", + .family = AF_INET, + .seq_fops = &ping_seq_fops, + .seq_ops = { + .start = ping_v4_seq_start, + .show = ping_v4_seq_show, + .next = ping_seq_next, + .stop = ping_seq_stop, + }, +}; -static int ping_proc_register(struct net *net) +int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo) { struct proc_dir_entry *p; - int rc = 0; - - p = proc_create("icmp", S_IRUGO, net->proc_net, &ping_seq_fops); + p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, + afinfo->seq_fops, afinfo); if (!p) - rc = -ENOMEM; - return rc; + return -ENOMEM; + return 0; } +EXPORT_SYMBOL_GPL(ping_proc_register); -static void ping_proc_unregister(struct net *net) +void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo) { - remove_proc_entry("icmp", net->proc_net); + remove_proc_entry(afinfo->name, net->proc_net); } +EXPORT_SYMBOL_GPL(ping_proc_unregister); - -static int __net_init ping_proc_init_net(struct net *net) +static int __net_init ping_v4_proc_init_net(struct net *net) { - return ping_proc_register(net); + return ping_proc_register(net, &ping_v4_seq_afinfo); } -static void __net_exit ping_proc_exit_net(struct net *net) +static void __net_exit ping_v4_proc_exit_net(struct net *net) { - ping_proc_unregister(net); + ping_proc_unregister(net, &ping_v4_seq_afinfo); } -static struct pernet_operations ping_net_ops = { - .init = ping_proc_init_net, - .exit = ping_proc_exit_net, +static struct pernet_operations ping_v4_net_ops = { + .init = ping_v4_proc_init_net, + .exit = ping_v4_proc_exit_net, }; int __init ping_proc_init(void) { - return register_pernet_subsys(&ping_net_ops); + return register_pernet_subsys(&ping_v4_net_ops); } void ping_proc_exit(void) { - unregister_pernet_subsys(&ping_net_ops); + unregister_pernet_subsys(&ping_v4_net_ops); } #endif diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d35bbf0cf404..198ea596f2d9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -594,11 +594,25 @@ static inline u32 fnhe_hashfun(__be32 daddr) return hval & (FNHE_HASH_SIZE - 1); } +static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) +{ + rt->rt_pmtu = fnhe->fnhe_pmtu; + rt->dst.expires = fnhe->fnhe_expires; + + if (fnhe->fnhe_gw) { + rt->rt_flags |= RTCF_REDIRECTED; + rt->rt_gateway = fnhe->fnhe_gw; + rt->rt_uses_gateway = 1; + } +} + static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, u32 pmtu, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; + struct rtable *rt; + unsigned int i; int depth; u32 hval = fnhe_hashfun(daddr); @@ -627,8 +641,12 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_gw = gw; if (pmtu) { fnhe->fnhe_pmtu = pmtu; - fnhe->fnhe_expires = expires; + fnhe->fnhe_expires = max(1UL, expires); } + /* Update all cached dsts too */ + rt = rcu_dereference(fnhe->fnhe_rth); + if (rt) + fill_route_from_fnhe(rt, fnhe); } else { if (depth > FNHE_RECLAIM_DEPTH) fnhe = fnhe_oldest(hash); @@ -640,10 +658,23 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_next = hash->chain; rcu_assign_pointer(hash->chain, fnhe); } + fnhe->fnhe_genid = fnhe_genid(dev_net(nh->nh_dev)); fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_expires = expires; + + /* Exception created; mark the cached routes for the nexthop + * stale, so anyone caching it rechecks if this exception + * applies to them. + */ + for_each_possible_cpu(i) { + struct rtable __rcu **prt; + prt = per_cpu_ptr(nh->nh_pcpu_rth_output, i); + rt = rcu_dereference(*prt); + if (rt) + rt->dst.obsolete = DST_OBSOLETE_KILL; + } } fnhe->fnhe_stamp = jiffies; @@ -922,12 +953,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; - if (!rt->rt_pmtu) { - dst->obsolete = DST_OBSOLETE_KILL; - } else { - rt->rt_pmtu = mtu; - dst->expires = max(1UL, jiffies + ip_rt_mtu_expires); - } + if (rt->rt_pmtu == mtu && + time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) + return; rcu_read_lock(); if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) { @@ -1068,11 +1096,11 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. * - * When a PMTU/redirect information update invalidates a - * route, this is indicated by setting obsolete to - * DST_OBSOLETE_KILL. + * When a PMTU/redirect information update invalidates a route, + * this is indicated by setting obsolete to DST_OBSOLETE_KILL or + * DST_OBSOLETE_DEAD by dst_free(). */ - if (dst->obsolete == DST_OBSOLETE_KILL || rt_is_expired(rt)) + if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) return NULL; return dst; } @@ -1214,26 +1242,17 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, spin_lock_bh(&fnhe_lock); if (daddr == fnhe->fnhe_daddr) { + int genid = fnhe_genid(dev_net(rt->dst.dev)); struct rtable *orig = rcu_dereference(fnhe->fnhe_rth); - if (orig && rt_is_expired(orig)) { + + if (fnhe->fnhe_genid != genid) { + fnhe->fnhe_genid = genid; fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; } - if (fnhe->fnhe_pmtu) { - unsigned long expires = fnhe->fnhe_expires; - unsigned long diff = expires - jiffies; - - if (time_before(jiffies, expires)) { - rt->rt_pmtu = fnhe->fnhe_pmtu; - dst_set_expires(&rt->dst, diff); - } - } - if (fnhe->fnhe_gw) { - rt->rt_flags |= RTCF_REDIRECTED; - rt->rt_gateway = fnhe->fnhe_gw; - rt->rt_uses_gateway = 1; - } else if (!rt->rt_gateway) + fill_route_from_fnhe(rt, fnhe); + if (!rt->rt_gateway) rt->rt_gateway = daddr; rcu_assign_pointer(fnhe->fnhe_rth, rt); @@ -2433,8 +2452,11 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = (struct net *)__ctl->extra1; + if (write) { - rt_cache_flush((struct net *)__ctl->extra1); + rt_cache_flush(net); + fnhe_genid_bump(net); return 0; } @@ -2609,6 +2631,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->rt_genid, 0); + atomic_set(&net->fnhe_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); return 0; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ab450c099aa4..b5d4ad988053 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -436,6 +436,8 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + sock_rps_record_flow(sk); + sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == TCP_LISTEN) return inet_csk_listen_poll(sk); @@ -2917,6 +2919,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | SKB_GSO_GRE | + SKB_GSO_MPLS | SKB_GSO_UDP_TUNNEL | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) @@ -2988,7 +2991,8 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, swap(gso_skb->truesize, skb->truesize); } - delta = htonl(oldlen + (skb->tail - skb->transport_header) + + delta = htonl(oldlen + (skb_tail_pointer(skb) - + skb_transport_header(skb)) + skb->data_len); th->check = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); @@ -3115,9 +3119,8 @@ int tcp_gro_complete(struct sk_buff *skb) EXPORT_SYMBOL(tcp_gro_complete); #ifdef CONFIG_TCP_MD5SIG -static unsigned long tcp_md5sig_users; -static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool; -static DEFINE_SPINLOCK(tcp_md5sig_pool_lock); +static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly; +static DEFINE_MUTEX(tcp_md5sig_mutex); static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool) { @@ -3132,30 +3135,14 @@ static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool) free_percpu(pool); } -void tcp_free_md5sig_pool(void) -{ - struct tcp_md5sig_pool __percpu *pool = NULL; - - spin_lock_bh(&tcp_md5sig_pool_lock); - if (--tcp_md5sig_users == 0) { - pool = tcp_md5sig_pool; - tcp_md5sig_pool = NULL; - } - spin_unlock_bh(&tcp_md5sig_pool_lock); - if (pool) - __tcp_free_md5sig_pool(pool); -} -EXPORT_SYMBOL(tcp_free_md5sig_pool); - -static struct tcp_md5sig_pool __percpu * -__tcp_alloc_md5sig_pool(struct sock *sk) +static void __tcp_alloc_md5sig_pool(void) { int cpu; struct tcp_md5sig_pool __percpu *pool; pool = alloc_percpu(struct tcp_md5sig_pool); if (!pool) - return NULL; + return; for_each_possible_cpu(cpu) { struct crypto_hash *hash; @@ -3166,53 +3153,27 @@ __tcp_alloc_md5sig_pool(struct sock *sk) per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; } - return pool; + /* before setting tcp_md5sig_pool, we must commit all writes + * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool() + */ + smp_wmb(); + tcp_md5sig_pool = pool; + return; out_free: __tcp_free_md5sig_pool(pool); - return NULL; } -struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk) +bool tcp_alloc_md5sig_pool(void) { - struct tcp_md5sig_pool __percpu *pool; - bool alloc = false; - -retry: - spin_lock_bh(&tcp_md5sig_pool_lock); - pool = tcp_md5sig_pool; - if (tcp_md5sig_users++ == 0) { - alloc = true; - spin_unlock_bh(&tcp_md5sig_pool_lock); - } else if (!pool) { - tcp_md5sig_users--; - spin_unlock_bh(&tcp_md5sig_pool_lock); - cpu_relax(); - goto retry; - } else - spin_unlock_bh(&tcp_md5sig_pool_lock); - - if (alloc) { - /* we cannot hold spinlock here because this may sleep. */ - struct tcp_md5sig_pool __percpu *p; - - p = __tcp_alloc_md5sig_pool(sk); - spin_lock_bh(&tcp_md5sig_pool_lock); - if (!p) { - tcp_md5sig_users--; - spin_unlock_bh(&tcp_md5sig_pool_lock); - return NULL; - } - pool = tcp_md5sig_pool; - if (pool) { - /* oops, it has already been assigned. */ - spin_unlock_bh(&tcp_md5sig_pool_lock); - __tcp_free_md5sig_pool(p); - } else { - tcp_md5sig_pool = pool = p; - spin_unlock_bh(&tcp_md5sig_pool_lock); - } + if (unlikely(!tcp_md5sig_pool)) { + mutex_lock(&tcp_md5sig_mutex); + + if (!tcp_md5sig_pool) + __tcp_alloc_md5sig_pool(); + + mutex_unlock(&tcp_md5sig_mutex); } - return pool; + return tcp_md5sig_pool != NULL; } EXPORT_SYMBOL(tcp_alloc_md5sig_pool); @@ -3229,28 +3190,15 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) struct tcp_md5sig_pool __percpu *p; local_bh_disable(); - - spin_lock(&tcp_md5sig_pool_lock); - p = tcp_md5sig_pool; + p = ACCESS_ONCE(tcp_md5sig_pool); if (p) - tcp_md5sig_users++; - spin_unlock(&tcp_md5sig_pool_lock); - - if (p) - return this_cpu_ptr(p); + return __this_cpu_ptr(p); local_bh_enable(); return NULL; } EXPORT_SYMBOL(tcp_get_md5sig_pool); -void tcp_put_md5sig_pool(void) -{ - local_bh_enable(); - tcp_free_md5sig_pool(); -} -EXPORT_SYMBOL(tcp_put_md5sig_pool); - int tcp_md5_hash_header(struct tcp_md5sig_pool *hp, const struct tcphdr *th) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9c6225780bd5..907311c9a012 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -360,9 +360,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk) if (mss > 1460) icwnd = max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2); - rcvmem = SKB_TRUESIZE(mss + MAX_TCP_HEADER); - while (tcp_win_from_space(rcvmem) < mss) - rcvmem += 128; + rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER); rcvmem *= icwnd; @@ -1257,8 +1255,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, if (skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = prev; - if (skb == tp->scoreboard_skb_hint) - tp->scoreboard_skb_hint = prev; if (skb == tp->lost_skb_hint) { tp->lost_skb_hint = prev; tp->lost_cnt_hint -= tcp_skb_pcount(prev); @@ -1966,20 +1962,6 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag) return true; } -static inline int tcp_skb_timedout(const struct sock *sk, - const struct sk_buff *skb) -{ - return tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto; -} - -static inline int tcp_head_timedout(const struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - - return tp->packets_out && - tcp_skb_timedout(sk, tcp_write_queue_head(sk)); -} - /* Linux NewReno/SACK/FACK/ECN state machine. * -------------------------------------- * @@ -2086,12 +2068,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) if (tcp_dupack_heuristics(tp) > tp->reordering) return true; - /* Trick#3 : when we use RFC2988 timer restart, fast - * retransmit can be triggered by timeout of queue head. - */ - if (tcp_is_fack(tp) && tcp_head_timedout(sk)) - return true; - /* Trick#4: It is still not OK... But will it be useful to delay * recovery more? */ @@ -2128,44 +2104,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) return false; } -/* New heuristics: it is possible only after we switched to restart timer - * each time when something is ACKed. Hence, we can detect timed out packets - * during fast retransmit without falling to slow start. - * - * Usefulness of this as is very questionable, since we should know which of - * the segments is the next to timeout which is relatively expensive to find - * in general case unless we add some data structure just for that. The - * current approach certainly won't find the right one too often and when it - * finally does find _something_ it usually marks large part of the window - * right away (because a retransmission with a larger timestamp blocks the - * loop from advancing). -ij - */ -static void tcp_timeout_skbs(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - - if (!tcp_is_fack(tp) || !tcp_head_timedout(sk)) - return; - - skb = tp->scoreboard_skb_hint; - if (tp->scoreboard_skb_hint == NULL) - skb = tcp_write_queue_head(sk); - - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - if (!tcp_skb_timedout(sk, skb)) - break; - - tcp_skb_mark_lost(tp, skb); - } - - tp->scoreboard_skb_hint = skb; - - tcp_verify_left_out(tp); -} - /* Detect loss in event "A" above by marking head of queue up as lost. * For FACK or non-SACK(Reno) senders, the first "packets" number of segments * are considered lost. For RFC3517 SACK, a segment is considered lost if it @@ -2251,8 +2189,6 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) else if (fast_rexmit) tcp_mark_head_lost(sk, 1, 1); } - - tcp_timeout_skbs(sk); } /* CWND moderation, preventing bursts due to too big ACKs @@ -2307,10 +2243,22 @@ static void DBGUNDO(struct sock *sk, const char *msg) #define DBGUNDO(x...) do { } while (0) #endif -static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh) +static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) { struct tcp_sock *tp = tcp_sk(sk); + if (unmark_loss) { + struct sk_buff *skb; + + tcp_for_write_queue(skb, sk) { + if (skb == tcp_send_head(sk)) + break; + TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; + } + tp->lost_out = 0; + tcp_clear_all_retrans_hints(tp); + } + if (tp->prior_ssthresh) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -2319,7 +2267,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh) else tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1); - if (undo_ssthresh && tp->prior_ssthresh > tp->snd_ssthresh) { + if (tp->prior_ssthresh > tp->snd_ssthresh) { tp->snd_ssthresh = tp->prior_ssthresh; TCP_ECN_withdraw_cwr(tp); } @@ -2327,6 +2275,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh) tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh); } tp->snd_cwnd_stamp = tcp_time_stamp; + tp->undo_marker = 0; } static inline bool tcp_may_undo(const struct tcp_sock *tp) @@ -2346,14 +2295,13 @@ static bool tcp_try_undo_recovery(struct sock *sk) * or our original transmission succeeded. */ DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans"); - tcp_undo_cwr(sk, true); + tcp_undo_cwnd_reduction(sk, false); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) mib_idx = LINUX_MIB_TCPLOSSUNDO; else mib_idx = LINUX_MIB_TCPFULLUNDO; NET_INC_STATS_BH(sock_net(sk), mib_idx); - tp->undo_marker = 0; } if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { /* Hold old state until something *above* high_seq @@ -2367,16 +2315,17 @@ static bool tcp_try_undo_recovery(struct sock *sk) } /* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */ -static void tcp_try_undo_dsack(struct sock *sk) +static bool tcp_try_undo_dsack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (tp->undo_marker && !tp->undo_retrans) { DBGUNDO(sk, "D-SACK"); - tcp_undo_cwr(sk, true); - tp->undo_marker = 0; + tcp_undo_cwnd_reduction(sk, false); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO); + return true; } + return false; } /* We can clear retrans_stamp when there are no retransmissions in the @@ -2408,60 +2357,20 @@ static bool tcp_any_retrans_done(const struct sock *sk) return false; } -/* Undo during fast recovery after partial ACK. */ - -static int tcp_try_undo_partial(struct sock *sk, int acked) -{ - struct tcp_sock *tp = tcp_sk(sk); - /* Partial ACK arrived. Force Hoe's retransmit. */ - int failed = tcp_is_reno(tp) || (tcp_fackets_out(tp) > tp->reordering); - - if (tcp_may_undo(tp)) { - /* Plain luck! Hole if filled with delayed - * packet, rather than with a retransmit. - */ - if (!tcp_any_retrans_done(sk)) - tp->retrans_stamp = 0; - - tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1); - - DBGUNDO(sk, "Hoe"); - tcp_undo_cwr(sk, false); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); - - /* So... Do not make Hoe's retransmit yet. - * If the first packet was delayed, the rest - * ones are most probably delayed as well. - */ - failed = 0; - } - return failed; -} - /* Undo during loss recovery after partial ACK or using F-RTO. */ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) { struct tcp_sock *tp = tcp_sk(sk); if (frto_undo || tcp_may_undo(tp)) { - struct sk_buff *skb; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; - } - - tcp_clear_all_retrans_hints(tp); + tcp_undo_cwnd_reduction(sk, true); DBGUNDO(sk, "partial loss"); - tp->lost_out = 0; - tcp_undo_cwr(sk, true); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO); if (frto_undo) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; - tp->undo_marker = 0; if (frto_undo || tcp_is_sack(tp)) tcp_set_ca_state(sk, TCP_CA_Open); return true; @@ -2494,12 +2403,14 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh) TCP_ECN_queue_cwr(tp); } -static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, +static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, int fast_rexmit) { struct tcp_sock *tp = tcp_sk(sk); int sndcnt = 0; int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp); + int newly_acked_sacked = prior_unsacked - + (tp->packets_out - tp->sacked_out); tp->prr_delivered += newly_acked_sacked; if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { @@ -2556,7 +2467,7 @@ static void tcp_try_keep_open(struct sock *sk) } } -static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked) +static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked) { struct tcp_sock *tp = tcp_sk(sk); @@ -2573,7 +2484,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked) if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open) tcp_moderate_cwnd(tp); } else { - tcp_cwnd_reduction(sk, newly_acked_sacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0); } } @@ -2731,6 +2642,40 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) tcp_xmit_retransmit_queue(sk); } +/* Undo during fast recovery after partial ACK. */ +static bool tcp_try_undo_partial(struct sock *sk, const int acked, + const int prior_unsacked) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (tp->undo_marker && tcp_packet_delayed(tp)) { + /* Plain luck! Hole if filled with delayed + * packet, rather than with a retransmit. + */ + tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1); + + /* We are getting evidence that the reordering degree is higher + * than we realized. If there are no retransmits out then we + * can undo. Otherwise we clock out new packets but do not + * mark more packets lost or retransmit more. + */ + if (tp->retrans_out) { + tcp_cwnd_reduction(sk, prior_unsacked, 0); + return true; + } + + if (!tcp_any_retrans_done(sk)) + tp->retrans_stamp = 0; + + DBGUNDO(sk, "partial recovery"); + tcp_undo_cwnd_reduction(sk, true); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); + tcp_try_keep_open(sk); + return true; + } + return false; +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2742,15 +2687,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) * It does _not_ decide what to send, it is made in function * tcp_xmit_retransmit_queue(). */ -static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, - int prior_sacked, int prior_packets, +static void tcp_fastretrans_alert(struct sock *sk, const int acked, + const int prior_unsacked, bool is_dupack, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && + bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); - int newly_acked_sacked = 0; int fast_rexmit = 0; if (WARN_ON(!tp->packets_out && tp->sacked_out)) @@ -2802,10 +2746,17 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (!(flag & FLAG_SND_UNA_ADVANCED)) { if (tcp_is_reno(tp) && is_dupack) tcp_add_reno_sack(sk); - } else - do_lost = tcp_try_undo_partial(sk, pkts_acked); - newly_acked_sacked = prior_packets - tp->packets_out + - tp->sacked_out - prior_sacked; + } else { + if (tcp_try_undo_partial(sk, acked, prior_unsacked)) + return; + /* Partial ACK arrived. Force fast retransmit. */ + do_lost = tcp_is_reno(tp) || + tcp_fackets_out(tp) > tp->reordering; + } + if (tcp_try_undo_dsack(sk)) { + tcp_try_keep_open(sk); + return; + } break; case TCP_CA_Loss: tcp_process_loss(sk, flag, is_dupack); @@ -2819,14 +2770,12 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (is_dupack) tcp_add_reno_sack(sk); } - newly_acked_sacked = prior_packets - tp->packets_out + - tp->sacked_out - prior_sacked; if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); if (!tcp_time_to_recover(sk, flag)) { - tcp_try_to_open(sk, flag, newly_acked_sacked); + tcp_try_to_open(sk, flag, prior_unsacked); return; } @@ -2846,9 +2795,9 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, fast_rexmit = 1; } - if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk))) + if (do_lost) tcp_update_scoreboard(sk, fast_rexmit); - tcp_cwnd_reduction(sk, newly_acked_sacked, fast_rexmit); + tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit); tcp_xmit_retransmit_queue(sk); } @@ -3079,7 +3028,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); - tp->scoreboard_skb_hint = NULL; if (skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = NULL; if (skb == tp->lost_skb_hint) @@ -3333,9 +3281,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 prior_in_flight; u32 prior_fackets; int prior_packets = tp->packets_out; - int prior_sacked = tp->sacked_out; - int pkts_acked = 0; - int previous_packets_out = 0; + const int prior_unsacked = tp->packets_out - tp->sacked_out; + int acked = 0; /* Number of packets newly acked */ /* If the ack is older than previous acks * then we can probably ignore it. @@ -3410,18 +3357,17 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) goto no_queue; /* See if we can take anything off of the retransmit queue. */ - previous_packets_out = tp->packets_out; + acked = tp->packets_out; flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); - - pkts_acked = previous_packets_out - tp->packets_out; + acked -= tp->packets_out; if (tcp_ack_is_dubious(sk, flag)) { /* Advance CWND, if state allows this. */ if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); - tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, - prior_packets, is_dupack, flag); + tcp_fastretrans_alert(sk, acked, prior_unsacked, + is_dupack, flag); } else { if (flag & FLAG_DATA_ACKED) tcp_cong_avoid(sk, ack, prior_in_flight); @@ -3443,8 +3389,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) no_queue: /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) - tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, - prior_packets, is_dupack, flag); + tcp_fastretrans_alert(sk, acked, prior_unsacked, + is_dupack, flag); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. @@ -3466,8 +3412,8 @@ old_ack: */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); - tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, - prior_packets, is_dupack, flag); + tcp_fastretrans_alert(sk, acked, prior_unsacked, + is_dupack, flag); } SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt); @@ -5601,6 +5547,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock *req; int queued = 0; + bool acceptable; tp->rx_opt.saw_tstamp = 0; @@ -5671,157 +5618,147 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, return 0; /* step 5: check the ACK field */ - if (true) { - int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | - FLAG_UPDATE_TS_RECENT) > 0; - - switch (sk->sk_state) { - case TCP_SYN_RECV: - if (acceptable) { - /* Once we leave TCP_SYN_RECV, we no longer - * need req so release it. - */ - if (req) { - tcp_synack_rtt_meas(sk, req); - tp->total_retrans = req->num_retrans; - - reqsk_fastopen_remove(sk, req, false); - } else { - /* Make sure socket is routed, for - * correct metrics. - */ - icsk->icsk_af_ops->rebuild_header(sk); - tcp_init_congestion_control(sk); + acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT) > 0; - tcp_mtup_init(sk); - tcp_init_buffer_space(sk); - tp->copied_seq = tp->rcv_nxt; - } - smp_mb(); - tcp_set_state(sk, TCP_ESTABLISHED); - sk->sk_state_change(sk); - - /* Note, that this wakeup is only for marginal - * crossed SYN case. Passively open sockets - * are not waked up, because sk->sk_sleep == - * NULL and sk->sk_socket == NULL. - */ - if (sk->sk_socket) - sk_wake_async(sk, - SOCK_WAKE_IO, POLL_OUT); - - tp->snd_una = TCP_SKB_CB(skb)->ack_seq; - tp->snd_wnd = ntohs(th->window) << - tp->rx_opt.snd_wscale; - tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - - if (tp->rx_opt.tstamp_ok) - tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - - if (req) { - /* Re-arm the timer because data may - * have been sent out. This is similar - * to the regular data transmission case - * when new data has just been ack'ed. - * - * (TFO) - we could try to be more - * aggressive and retranmitting any data - * sooner based on when they were sent - * out. - */ - tcp_rearm_rto(sk); - } else - tcp_init_metrics(sk); + switch (sk->sk_state) { + case TCP_SYN_RECV: + if (!acceptable) + return 1; - /* Prevent spurious tcp_cwnd_restart() on - * first data packet. - */ - tp->lsndtime = tcp_time_stamp; + /* Once we leave TCP_SYN_RECV, we no longer need req + * so release it. + */ + if (req) { + tcp_synack_rtt_meas(sk, req); + tp->total_retrans = req->num_retrans; - tcp_initialize_rcv_mss(sk); - tcp_fast_path_on(tp); - } else { - return 1; - } - break; + reqsk_fastopen_remove(sk, req, false); + } else { + /* Make sure socket is routed, for correct metrics. */ + icsk->icsk_af_ops->rebuild_header(sk); + tcp_init_congestion_control(sk); + + tcp_mtup_init(sk); + tcp_init_buffer_space(sk); + tp->copied_seq = tp->rcv_nxt; + } + smp_mb(); + tcp_set_state(sk, TCP_ESTABLISHED); + sk->sk_state_change(sk); + + /* Note, that this wakeup is only for marginal crossed SYN case. + * Passively open sockets are not waked up, because + * sk->sk_sleep == NULL and sk->sk_socket == NULL. + */ + if (sk->sk_socket) + sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); + + tp->snd_una = TCP_SKB_CB(skb)->ack_seq; + tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; + tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); + + if (tp->rx_opt.tstamp_ok) + tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - case TCP_FIN_WAIT1: - /* If we enter the TCP_FIN_WAIT1 state and we are a - * Fast Open socket and this is the first acceptable - * ACK we have received, this would have acknowledged - * our SYNACK so stop the SYNACK timer. + if (req) { + /* Re-arm the timer because data may have been sent out. + * This is similar to the regular data transmission case + * when new data has just been ack'ed. + * + * (TFO) - we could try to be more aggressive and + * retransmitting any data sooner based on when they + * are sent out. */ - if (req != NULL) { - /* Return RST if ack_seq is invalid. - * Note that RFC793 only says to generate a - * DUPACK for it but for TCP Fast Open it seems - * better to treat this case like TCP_SYN_RECV - * above. - */ - if (!acceptable) - return 1; - /* We no longer need the request sock. */ - reqsk_fastopen_remove(sk, req, false); - tcp_rearm_rto(sk); - } - if (tp->snd_una == tp->write_seq) { - struct dst_entry *dst; - - tcp_set_state(sk, TCP_FIN_WAIT2); - sk->sk_shutdown |= SEND_SHUTDOWN; - - dst = __sk_dst_get(sk); - if (dst) - dst_confirm(dst); - - if (!sock_flag(sk, SOCK_DEAD)) - /* Wake up lingering close() */ - sk->sk_state_change(sk); - else { - int tmo; - - if (tp->linger2 < 0 || - (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && - after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) { - tcp_done(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA); - return 1; - } + tcp_rearm_rto(sk); + } else + tcp_init_metrics(sk); - tmo = tcp_fin_time(sk); - if (tmo > TCP_TIMEWAIT_LEN) { - inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); - } else if (th->fin || sock_owned_by_user(sk)) { - /* Bad case. We could lose such FIN otherwise. - * It is not a big problem, but it looks confusing - * and not so rare event. We still can lose it now, - * if it spins in bh_lock_sock(), but it is really - * marginal case. - */ - inet_csk_reset_keepalive_timer(sk, tmo); - } else { - tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); - goto discard; - } - } - } - break; + /* Prevent spurious tcp_cwnd_restart() on first data packet */ + tp->lsndtime = tcp_time_stamp; - case TCP_CLOSING: - if (tp->snd_una == tp->write_seq) { - tcp_time_wait(sk, TCP_TIME_WAIT, 0); - goto discard; - } + tcp_initialize_rcv_mss(sk); + tcp_fast_path_on(tp); + break; + + case TCP_FIN_WAIT1: { + struct dst_entry *dst; + int tmo; + + /* If we enter the TCP_FIN_WAIT1 state and we are a + * Fast Open socket and this is the first acceptable + * ACK we have received, this would have acknowledged + * our SYNACK so stop the SYNACK timer. + */ + if (req != NULL) { + /* Return RST if ack_seq is invalid. + * Note that RFC793 only says to generate a + * DUPACK for it but for TCP Fast Open it seems + * better to treat this case like TCP_SYN_RECV + * above. + */ + if (!acceptable) + return 1; + /* We no longer need the request sock. */ + reqsk_fastopen_remove(sk, req, false); + tcp_rearm_rto(sk); + } + if (tp->snd_una != tp->write_seq) break; - case TCP_LAST_ACK: - if (tp->snd_una == tp->write_seq) { - tcp_update_metrics(sk); - tcp_done(sk); - goto discard; - } + tcp_set_state(sk, TCP_FIN_WAIT2); + sk->sk_shutdown |= SEND_SHUTDOWN; + + dst = __sk_dst_get(sk); + if (dst) + dst_confirm(dst); + + if (!sock_flag(sk, SOCK_DEAD)) { + /* Wake up lingering close() */ + sk->sk_state_change(sk); break; } + + if (tp->linger2 < 0 || + (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && + after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) { + tcp_done(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA); + return 1; + } + + tmo = tcp_fin_time(sk); + if (tmo > TCP_TIMEWAIT_LEN) { + inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); + } else if (th->fin || sock_owned_by_user(sk)) { + /* Bad case. We could lose such FIN otherwise. + * It is not a big problem, but it looks confusing + * and not so rare event. We still can lose it now, + * if it spins in bh_lock_sock(), but it is really + * marginal case. + */ + inet_csk_reset_keepalive_timer(sk, tmo); + } else { + tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); + goto discard; + } + break; + } + + case TCP_CLOSING: + if (tp->snd_una == tp->write_seq) { + tcp_time_wait(sk, TCP_TIME_WAIT, 0); + goto discard; + } + break; + + case TCP_LAST_ACK: + if (tp->snd_una == tp->write_seq) { + tcp_update_metrics(sk); + tcp_done(sk); + goto discard; + } + break; } /* step 6: check the URG bit */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 719652305a29..d20ede0c9593 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1026,7 +1026,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key = sock_kmalloc(sk, sizeof(*key), gfp); if (!key) return -ENOMEM; - if (hlist_empty(&md5sig->head) && !tcp_alloc_md5sig_pool(sk)) { + if (!tcp_alloc_md5sig_pool()) { sock_kfree_s(sk, key, sizeof(*key)); return -ENOMEM; } @@ -1044,9 +1044,7 @@ EXPORT_SYMBOL(tcp_md5_do_add); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) { - struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct tcp_md5sig_info *md5sig; key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET); if (!key) @@ -1054,10 +1052,6 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); - md5sig = rcu_dereference_protected(tp->md5sig_info, - sock_owned_by_user(sk)); - if (hlist_empty(&md5sig->head)) - tcp_free_md5sig_pool(); return 0; } EXPORT_SYMBOL(tcp_md5_do_del); @@ -1071,8 +1065,6 @@ static void tcp_clear_md5_list(struct sock *sk) md5sig = rcu_dereference_protected(tp->md5sig_info, 1); - if (!hlist_empty(&md5sig->head)) - tcp_free_md5sig_pool(); hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 0f0178827259..ab1c08658528 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -317,7 +317,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) key = tp->af_specific->md5_lookup(sk, sk); if (key != NULL) { tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); - if (tcptw->tw_md5_key && tcp_alloc_md5sig_pool(sk) == NULL) + if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()) BUG(); } } while (0); @@ -358,10 +358,8 @@ void tcp_twsk_destructor(struct sock *sk) #ifdef CONFIG_TCP_MD5SIG struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_key) { - tcp_free_md5sig_pool(); + if (twsk->tw_md5_key) kfree_rcu(twsk->tw_md5_key, rcu); - } #endif } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0bf5d399a03c..c7338ec79cc0 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1967,6 +1967,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) unsigned int mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; + sock_rps_record_flow(sk); + /* Check for false positives due to checksum errors */ if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk)) @@ -2381,7 +2383,7 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_UDP_TUNNEL | - SKB_GSO_GRE) || + SKB_GSO_GRE | SKB_GSO_MPLS) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 05a5df2febc9..06347dbd32c1 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -63,7 +63,7 @@ static int xfrm_tunnel_err(struct sk_buff *skb, u32 info) static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = { .handler = xfrm_tunnel_rcv, .err_handler = xfrm_tunnel_err, - .priority = 2, + .priority = 3, }; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 9af088d2cdaa..470a9c008e9b 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_IPV6) += ipv6.o ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ addrlabel.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ - raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ + raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1bbf744c2cc3..21010fddb203 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1126,8 +1126,7 @@ retry: ift = !max_addresses || ipv6_count_addresses(idev) < max_addresses ? - ipv6_add_addr(idev, &addr, tmp_plen, - ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, + ipv6_add_addr(idev, &addr, tmp_plen, ipv6_addr_scope(&addr), addr_flags) : NULL; if (IS_ERR_OR_NULL(ift)) { in6_ifa_put(ifp); @@ -2402,6 +2401,7 @@ err_exit: * Manual configuration of address on an interface */ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx, + const struct in6_addr *peer_pfx, unsigned int plen, __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft) { @@ -2457,6 +2457,8 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *p 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, @@ -2526,7 +2528,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) return -EFAULT; rtnl_lock(); - err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, + err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL, ireq.ifr6_prefixlen, IFA_F_PERMANENT, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); rtnl_unlock(); @@ -2826,9 +2828,9 @@ static void addrconf_ip6_tnl_config(struct net_device *dev) } static int addrconf_notify(struct notifier_block *this, unsigned long event, - void *data) + void *ptr) { - struct net_device *dev = (struct net_device *) data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); int run_pending = 0; int err; @@ -3612,18 +3614,20 @@ restart: rcu_read_unlock_bh(); } -static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local) +static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, + struct in6_addr **peer_pfx) { struct in6_addr *pfx = NULL; + *peer_pfx = NULL; + if (addr) pfx = nla_data(addr); if (local) { if (pfx && nla_memcmp(local, pfx, sizeof(*pfx))) - pfx = NULL; - else - pfx = nla_data(local); + *peer_pfx = pfx; + pfx = nla_data(local); } return pfx; @@ -3641,7 +3645,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; - struct in6_addr *pfx; + struct in6_addr *pfx, *peer_pfx; int err; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); @@ -3649,7 +3653,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) return err; ifm = nlmsg_data(nlh); - pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); + pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (pfx == NULL) return -EINVAL; @@ -3707,7 +3711,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; - struct in6_addr *pfx; + struct in6_addr *pfx, *peer_pfx; struct inet6_ifaddr *ifa; struct net_device *dev; u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME; @@ -3719,7 +3723,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) return err; ifm = nlmsg_data(nlh); - pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); + pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (pfx == NULL) return -EINVAL; @@ -3747,7 +3751,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) * It would be best to check for !NLM_F_CREATE here but * userspace alreay relies on not having to provide this. */ - return inet6_addr_add(net, ifm->ifa_index, pfx, + return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx, ifm->ifa_prefixlen, ifa_flags, preferred_lft, valid_lft); } @@ -3804,6 +3808,7 @@ static inline int rt_scope(int ifa_scope) static inline int inet6_ifaddr_msgsize(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(16) /* IFA_LOCAL */ + nla_total_size(16) /* IFA_ADDRESS */ + nla_total_size(sizeof(struct ifa_cacheinfo)); } @@ -3842,13 +3847,22 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, valid = INFINITY_LIFE_TIME; } - if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0 || - put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) { - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; - } + if (!ipv6_addr_any(&ifa->peer_addr)) { + if (nla_put(skb, IFA_LOCAL, 16, &ifa->addr) < 0 || + nla_put(skb, IFA_ADDRESS, 16, &ifa->peer_addr) < 0) + goto error; + } else + if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0) + goto error; + + if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) + goto error; return nlmsg_end(skb, nlh); + +error: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, @@ -4048,7 +4062,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh) struct net *net = sock_net(in_skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; - struct in6_addr *addr = NULL; + struct in6_addr *addr = NULL, *peer; struct net_device *dev = NULL; struct inet6_ifaddr *ifa; struct sk_buff *skb; @@ -4058,7 +4072,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); + addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); if (addr == NULL) { err = -EINVAL; goto errout; @@ -4566,11 +4580,26 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) ip6_ins_rt(ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); + if (!ipv6_addr_any(&ifp->peer_addr)) + addrconf_prefix_route(&ifp->peer_addr, 128, + ifp->idev->dev, 0, 0); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); + if (!ipv6_addr_any(&ifp->peer_addr)) { + struct rt6_info *rt; + struct net_device *dev = ifp->idev->dev; + + rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL, + dev->ifindex, 1); + if (rt) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } + } dst_hold(&ifp->rt->dst); if (ip6_del_rt(ifp->rt)) @@ -4618,13 +4647,16 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, static void dev_disable_change(struct inet6_dev *idev) { + struct netdev_notifier_info info; + if (!idev || !idev->dev) return; + netdev_notifier_info_init(&info, idev->dev); if (idev->cnf.disable_ipv6) - addrconf_notify(NULL, NETDEV_DOWN, idev->dev); + addrconf_notify(NULL, NETDEV_DOWN, &info); else - addrconf_notify(NULL, NETDEV_UP, idev->dev); + addrconf_notify(NULL, NETDEV_UP, &info); } static void addrconf_disable_change(struct net *net, __s32 newf) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index ab5c7ad482cd..a5ac969aeefe 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -49,6 +49,7 @@ #include <net/udp.h> #include <net/udplite.h> #include <net/tcp.h> +#include <net/ping.h> #include <net/protocol.h> #include <net/inet_common.h> #include <net/route.h> @@ -840,6 +841,9 @@ static int __init inet6_init(void) if (err) goto out_unregister_udplite_proto; + err = proto_register(&pingv6_prot, 1); + if (err) + goto out_unregister_ping_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. @@ -930,6 +934,10 @@ static int __init inet6_init(void) if (err) goto ipv6_packet_fail; + err = pingv6_init(); + if (err) + goto pingv6_fail; + #ifdef CONFIG_SYSCTL err = ipv6_sysctl_register(); if (err) @@ -942,6 +950,8 @@ out: sysctl_fail: ipv6_packet_cleanup(); #endif +pingv6_fail: + pingv6_exit(); ipv6_packet_fail: tcpv6_exit(); tcpv6_fail: @@ -985,6 +995,8 @@ register_pernet_fail: rtnl_unregister_all(PF_INET6); out_sock_register_fail: rawv6_exit(); +out_unregister_ping_proto: + proto_unregister(&pingv6_prot); out_unregister_raw_proto: proto_unregister(&rawv6_prot); out_unregister_udplite_proto: diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 4b56cbbc7890..197e6f4a2b74 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -879,3 +879,30 @@ exit_f: return err; } EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); + +void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, + __u16 srcp, __u16 destp, int bucket) +{ + struct ipv6_pinfo *np = inet6_sk(sp); + const struct in6_addr *dest, *src; + + dest = &np->daddr; + src = &np->rcv_saddr; + seq_printf(seq, + "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", + bucket, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp, + sp->sk_state, + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), + 0, 0L, 0, + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + 0, + sock_i_ino(sp), + atomic_read(&sp->sk_refcnt), sp, + atomic_read(&sp->sk_drops)); +} diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index c5e83fae4df4..140748debc4a 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -115,7 +115,7 @@ EXPORT_SYMBOL(ipv6_skip_exthdr); int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) { const unsigned char *nh = skb_network_header(skb); - int packet_len = skb->tail - skb->network_header; + int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); struct ipv6_opt_hdr *hdr; int len; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index b4ff0a42b8c7..4b4890bbe16d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -57,6 +57,7 @@ #include <net/ipv6.h> #include <net/ip6_checksum.h> +#include <net/ping.h> #include <net/protocol.h> #include <net/raw.h> #include <net/rawv6.h> @@ -84,12 +85,18 @@ static inline struct sock *icmpv6_sk(struct net *net) static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { + /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */ + struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset); struct net *net = dev_net(skb->dev); if (type == ICMPV6_PKT_TOOBIG) ip6_update_pmtu(skb, net, info, 0, 0); else if (type == NDISC_REDIRECT) ip6_redirect(skb, net, 0, 0); + + if (!(type & ICMPV6_INFOMSG_MASK)) + if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST) + ping_err(skb, offset, info); } static int icmpv6_rcv(struct sk_buff *skb); @@ -224,7 +231,8 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset) return (*op & 0xC0) == 0x80; } -static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len) +int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, + struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; @@ -307,8 +315,8 @@ static void mip6_addr_swap(struct sk_buff *skb) static inline void mip6_addr_swap(struct sk_buff *skb) {} #endif -static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, - struct sock *sk, struct flowi6 *fl6) +struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, + struct sock *sk, struct flowi6 *fl6) { struct dst_entry *dst, *dst2; struct flowi6 fl2; @@ -391,7 +399,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) int err = 0; if ((u8 *)hdr < skb->head || - (skb->network_header + sizeof(*hdr)) > skb->tail) + (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; /* @@ -697,7 +705,8 @@ static int icmpv6_rcv(struct sk_buff *skb) skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, 0)); if (__skb_checksum_complete(skb)) { - LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%pI6 > %pI6]\n", + LIMIT_NETDEBUG(KERN_DEBUG + "ICMPv6 checksum failed [%pI6c > %pI6c]\n", saddr, daddr); goto csum_error; } @@ -718,7 +727,7 @@ static int icmpv6_rcv(struct sk_buff *skb) break; case ICMPV6_ECHO_REPLY: - /* we couldn't care less */ + ping_rcv(skb); break; case ICMPV6_PKT_TOOBIG: diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 71b766ee821d..a263b990ee11 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -98,6 +98,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, SKB_GSO_TCP_ECN | SKB_GSO_GRE | SKB_GSO_UDP_TUNNEL | + SKB_GSO_MPLS | SKB_GSO_TCPV6 | 0))) goto out; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 241fb8ad9fcf..583e8d435f9a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1319,7 +1319,7 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, static int ip6mr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr6_table *mrt; struct mif_device *v; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index bfa6cc36ef2a..72c8bfe06bb4 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1409,8 +1409,9 @@ static void mld_sendpack(struct sk_buff *skb) idev = __in6_dev_get(skb->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - payload_len = (skb->tail - skb->network_header) - sizeof(*pip6); - mldlen = skb->tail - skb->transport_header; + payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - + sizeof(*pip6); + mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 0f9bdc5ee9f3..9ac01dc9402e 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -268,7 +268,8 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; @@ -404,7 +405,8 @@ static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb, struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2712ab22a174..781dd3c99680 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -693,7 +693,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; @@ -853,7 +853,7 @@ static void ndisc_recv_na(struct sk_buff *skb) const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; @@ -1069,7 +1069,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) __u8 * opt = (__u8 *)(ra_msg + 1); - optlen = (skb->tail - skb->transport_header) - sizeof(struct ra_msg); + optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - + sizeof(struct ra_msg); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); @@ -1346,7 +1347,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) u8 *hdr; struct ndisc_options ndopts; struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -1568,7 +1569,7 @@ int ndisc_rcv(struct sk_buff *skb) static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct inet6_dev *idev; diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 60e9053bab05..47bff6107519 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -71,7 +71,7 @@ static int device_cmp(struct nf_conn *ct, void *ifindex) static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - const struct net_device *dev = ptr; + const struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_DOWN) @@ -89,8 +89,10 @@ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; + struct netdev_notifier_info info; - return masq_device_event(this, event, ifa->idev->dev); + netdev_notifier_info_init(&info, ifa->idev->dev); + return masq_device_event(this, event, &info); } static struct notifier_block masq_inet_notifier = { diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index c2e73e647e44..ab92a3673fbb 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -40,7 +40,8 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) u16 offset = sizeof(struct ipv6hdr); struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c new file mode 100644 index 000000000000..a43110385918 --- /dev/null +++ b/net/ipv6/ping.c @@ -0,0 +1,272 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * "Ping" sockets + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Based on ipv4/ping.c code. + * + * Authors: Lorenzo Colitti (IPv6 support) + * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6), + * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32) + * + */ + +#include <net/addrconf.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/protocol.h> +#include <net/udp.h> +#include <net/transp_v6.h> +#include <net/ping.h> + +struct proto pingv6_prot = { + .name = "PINGv6", + .owner = THIS_MODULE, + .init = ping_init_sock, + .close = ping_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .sendmsg = ping_v6_sendmsg, + .recvmsg = ping_recvmsg, + .bind = ping_bind, + .backlog_rcv = ping_queue_rcv_skb, + .hash = ping_hash, + .unhash = ping_unhash, + .get_port = ping_get_port, + .obj_size = sizeof(struct raw6_sock), +}; +EXPORT_SYMBOL_GPL(pingv6_prot); + +static struct inet_protosw pingv6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_ICMPV6, + .prot = &pingv6_prot, + .ops = &inet6_dgram_ops, + .no_check = UDP_CSUM_DEFAULT, + .flags = INET_PROTOSW_REUSE, +}; + + +/* Compatibility glue so we can support IPv6 when it's compiled as a module */ +int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +{ + return -EAFNOSUPPORT; +} +int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + return -EAFNOSUPPORT; +} +int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) +{ + return -EAFNOSUPPORT; +} +void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) {} +int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict) +{ + return 0; +} + +int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len) +{ + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct icmp6hdr user_icmph; + int addr_type; + struct in6_addr *daddr; + int iif = 0; + struct flowi6 fl6; + int err; + int hlimit; + struct dst_entry *dst; + struct rt6_info *rt; + struct pingfakehdr pfh; + + pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); + + err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph, + sizeof(user_icmph)); + if (err) + return err; + + if (msg->msg_name) { + struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name; + if (msg->msg_namelen < sizeof(struct sockaddr_in6) || + u->sin6_family != AF_INET6) { + return -EINVAL; + } + if (sk->sk_bound_dev_if && + sk->sk_bound_dev_if != u->sin6_scope_id) { + return -EINVAL; + } + daddr = &(u->sin6_addr); + iif = u->sin6_scope_id; + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + daddr = &np->daddr; + } + + if (!iif) + iif = sk->sk_bound_dev_if; + + addr_type = ipv6_addr_type(daddr); + if (__ipv6_addr_needs_scope_id(addr_type) && !iif) + return -EINVAL; + if (addr_type & IPV6_ADDR_MAPPED) + return -EINVAL; + + /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ + + memset(&fl6, 0, sizeof(fl6)); + + fl6.flowi6_proto = IPPROTO_ICMPV6; + fl6.saddr = np->saddr; + fl6.daddr = *daddr; + fl6.fl6_icmp_type = user_icmph.icmp6_type; + fl6.fl6_icmp_code = user_icmph.icmp6_code; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + + dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, 1); + if (IS_ERR(dst)) + return PTR_ERR(dst); + rt = (struct rt6_info *) dst; + + np = inet6_sk(sk); + if (!np) + return -EBADF; + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + + pfh.icmph.type = user_icmph.icmp6_type; + pfh.icmph.code = user_icmph.icmp6_code; + pfh.icmph.checksum = 0; + pfh.icmph.un.echo.id = inet->inet_sport; + pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; + pfh.iov = msg->msg_iov; + pfh.wcheck = 0; + pfh.family = AF_INET6; + + if (ipv6_addr_is_multicast(&fl6.daddr)) + hlimit = np->mcast_hops; + else + hlimit = np->hop_limit; + if (hlimit < 0) + hlimit = ip6_dst_hoplimit(dst); + + err = ip6_append_data(sk, ping_getfrag, &pfh, len, + 0, hlimit, + np->tclass, NULL, &fl6, rt, + MSG_DONTWAIT, np->dontfrag); + + if (err) { + ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev, + ICMP6_MIB_OUTERRORS); + ip6_flush_pending_frames(sk); + } else { + err = icmpv6_push_pending_frames(sk, &fl6, + (struct icmp6hdr *) &pfh.icmph, + len); + } + + return err; +} + +#ifdef CONFIG_PROC_FS +static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos) +{ + return ping_seq_start(seq, pos, AF_INET6); +} + +int ping_v6_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + int bucket = ((struct ping_iter_state *) seq->private)->bucket; + struct inet_sock *inet = inet_sk(v); + __u16 srcp = ntohs(inet->inet_sport); + __u16 destp = ntohs(inet->inet_dport); + ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + } + return 0; +} + +static struct ping_seq_afinfo ping_v6_seq_afinfo = { + .name = "icmp6", + .family = AF_INET6, + .seq_fops = &ping_seq_fops, + .seq_ops = { + .start = ping_v6_seq_start, + .show = ping_v6_seq_show, + .next = ping_seq_next, + .stop = ping_seq_stop, + }, +}; + +static int __net_init ping_v6_proc_init_net(struct net *net) +{ + return ping_proc_register(net, &ping_v6_seq_afinfo); +} + +static void __net_init ping_v6_proc_exit_net(struct net *net) +{ + return ping_proc_unregister(net, &ping_v6_seq_afinfo); +} + +static struct pernet_operations ping_v6_net_ops = { + .init = ping_v6_proc_init_net, + .exit = ping_v6_proc_exit_net, +}; +#endif + +int __init pingv6_init(void) +{ +#ifdef CONFIG_PROC_FS + int ret = register_pernet_subsys(&ping_v6_net_ops); + if (ret) + return ret; +#endif + pingv6_ops.ipv6_recv_error = ipv6_recv_error; + pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl; + pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; + pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; + pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; + return inet6_register_protosw(&pingv6_protosw); +} + +/* This never gets called because it's not possible to unload the ipv6 module, + * but just in case. + */ +void pingv6_exit(void) +{ + pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; + pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; + pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; + pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; +#ifdef CONFIG_PROC_FS + unregister_pernet_subsys(&ping_v6_net_ops); +#endif + inet6_unregister_protosw(&pingv6_protosw); +} diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index eedff8ccded5..c45f7a5c36e9 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1132,7 +1132,8 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) - amount = skb->tail - skb->transport_header; + amount = skb_tail_pointer(skb) - + skb_transport_header(skb); spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } @@ -1226,45 +1227,16 @@ struct proto rawv6_prot = { }; #ifdef CONFIG_PROC_FS -static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) -{ - struct ipv6_pinfo *np = inet6_sk(sp); - const struct in6_addr *dest, *src; - __u16 destp, srcp; - - dest = &np->daddr; - src = &np->rcv_saddr; - destp = 0; - srcp = inet_sk(sp)->inet_num; - seq_printf(seq, - "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", - i, - src->s6_addr32[0], src->s6_addr32[1], - src->s6_addr32[2], src->s6_addr32[3], srcp, - dest->s6_addr32[0], dest->s6_addr32[1], - dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - sk_wmem_alloc_get(sp), - sk_rmem_alloc_get(sp), - 0, 0L, 0, - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), - 0, - sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); -} - static int raw6_seq_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) - seq_printf(seq, - " sl " - "local_address " - "remote_address " - "st tx_queue rx_queue tr tm->when retrnsmt" - " uid timeout inode ref pointer drops\n"); - else - raw6_sock_seq_show(seq, v, raw_seq_private(seq)->bucket); + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + struct sock *sp = v; + __u16 srcp = inet_sk(sp)->inet_num; + ip6_dgram_sock_seq_show(seq, v, srcp, 0, + raw_seq_private(seq)->bucket); + } return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ad0aa6b0b86a..2b874185ebb2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1649,7 +1649,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu int optlen, on_link; u8 *lladdr; - optlen = skb->tail - skb->transport_header; + optlen = skb_tail_pointer(skb) - skb_transport_header(skb); optlen -= sizeof(*msg); if (optlen < 0) { @@ -2681,9 +2681,9 @@ errout: } static int ip6_route_dev_notify(struct notifier_block *this, - unsigned long event, void *data) + unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 335363478bbf..6b9c1f128eaf 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -577,6 +577,10 @@ static int ipip6_rcv(struct sk_buff *skb) if (tunnel != NULL) { struct pcpu_tstats *tstats; + if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && + tunnel->parms.iph.protocol != 0) + goto out; + secpath_reset(skb); skb->mac_header = skb->network_header; skb_reset_network_header(skb); @@ -629,6 +633,35 @@ out: return 0; } +static const struct tnl_ptk_info tpi = { + /* no tunnel info required for ipip. */ + .proto = htons(ETH_P_IP), +}; + +static int ipip_rcv(struct sk_buff *skb) +{ + const struct iphdr *iph = ip_hdr(skb); + struct ip_tunnel *tunnel; + + tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, + iph->saddr, iph->daddr); + if (tunnel != NULL) { + if (tunnel->parms.iph.protocol != IPPROTO_IPIP && + tunnel->parms.iph.protocol != 0) + goto drop; + + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + } + + return 1; + +drop: + kfree_skb(skb); + return 0; +} + /* * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function * stores the embedded IPv4 address in v4dst and returns true. @@ -877,6 +910,43 @@ tx_error: return NETDEV_TX_OK; } +static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + const struct iphdr *tiph = &tunnel->parms.iph; + + if (likely(!skb->encapsulation)) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + + ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP); + return NETDEV_TX_OK; +} + +static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + switch (skb->protocol) { + case htons(ETH_P_IP): + ipip_tunnel_xmit(skb, dev); + break; + case htons(ETH_P_IPV6): + ipip6_tunnel_xmit(skb, dev); + break; + default: + goto tx_err; + } + + return NETDEV_TX_OK; + +tx_err: + dev->stats.tx_errors++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; + +} + static void ipip6_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; @@ -1027,7 +1097,11 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; err = -EINVAL; - if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPV6 || + if (p.iph.protocol != IPPROTO_IPV6 && + p.iph.protocol != IPPROTO_IPIP && + p.iph.protocol != 0) + goto done; + if (p.iph.version != 4 || p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF))) goto done; if (p.iph.ttl) @@ -1164,7 +1238,7 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ipip6_netdev_ops = { .ndo_uninit = ipip6_tunnel_uninit, - .ndo_start_xmit = ipip6_tunnel_xmit, + .ndo_start_xmit = sit_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, .ndo_change_mtu = ipip6_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, @@ -1232,6 +1306,22 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) return 0; } +static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + u8 proto; + + if (!data) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPV6 && + proto != IPPROTO_IPIP && + proto != 0) + return -EINVAL; + + return 0; +} + static void ipip6_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm *parms) { @@ -1268,6 +1358,10 @@ static void ipip6_netlink_parms(struct nlattr *data[], if (data[IFLA_IPTUN_FLAGS]) parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); + } #ifdef CONFIG_IPV6_SIT_6RD @@ -1391,6 +1485,8 @@ static size_t ipip6_get_size(const struct net_device *dev) nla_total_size(1) + /* IFLA_IPTUN_FLAGS */ nla_total_size(2) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + #ifdef CONFIG_IPV6_SIT_6RD /* IFLA_IPTUN_6RD_PREFIX */ nla_total_size(sizeof(struct in6_addr)) + @@ -1416,6 +1512,7 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags)) goto nla_put_failure; @@ -1445,6 +1542,7 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, #ifdef CONFIG_IPV6_SIT_6RD [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, @@ -1459,6 +1557,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = { .policy = ipip6_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipip6_tunnel_setup, + .validate = ipip6_validate, .newlink = ipip6_newlink, .changelink = ipip6_changelink, .get_size = ipip6_get_size, @@ -1471,6 +1570,12 @@ static struct xfrm_tunnel sit_handler __read_mostly = { .priority = 1, }; +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = ipip_rcv, + .err_handler = ipip6_err, + .priority = 2, +}; + static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) { int prio; @@ -1553,6 +1658,7 @@ static void __exit sit_cleanup(void) { rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); unregister_pernet_device(&sit_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ @@ -1569,9 +1675,14 @@ static int __init sit_init(void) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { - pr_info("%s: can't add protocol\n", __func__); + pr_info("%s: can't register ip6ip4\n", __func__); goto xfrm_tunnel_failed; } + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: can't register ip4ip4\n", __func__); + goto xfrm_tunnel4_failed; + } err = rtnl_link_register(&sit_link_ops); if (err < 0) goto rtnl_link_failed; @@ -1580,6 +1691,8 @@ out: return err; rtnl_link_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel4_failed: xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm_tunnel_failed: unregister_pernet_device(&sit_net_ops); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 42923b14dfa6..b5808539cd5c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1359,48 +1359,17 @@ static const struct inet6_protocol udpv6_protocol = { /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS - -static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket) -{ - struct inet_sock *inet = inet_sk(sp); - struct ipv6_pinfo *np = inet6_sk(sp); - const struct in6_addr *dest, *src; - __u16 destp, srcp; - - dest = &np->daddr; - src = &np->rcv_saddr; - destp = ntohs(inet->inet_dport); - srcp = ntohs(inet->inet_sport); - seq_printf(seq, - "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", - bucket, - src->s6_addr32[0], src->s6_addr32[1], - src->s6_addr32[2], src->s6_addr32[3], srcp, - dest->s6_addr32[0], dest->s6_addr32[1], - dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - sk_wmem_alloc_get(sp), - sk_rmem_alloc_get(sp), - 0, 0L, 0, - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), - 0, - sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, - atomic_read(&sp->sk_drops)); -} - int udp6_seq_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) - seq_printf(seq, - " sl " - "local_address " - "remote_address " - "st tx_queue rx_queue tr tm->when retrnsmt" - " uid timeout inode ref pointer drops\n"); - else - udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket); + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + int bucket = ((struct udp_iter_state *)seq->private)->bucket; + struct inet_sock *inet = inet_sk(v); + __u16 srcp = ntohs(inet->inet_sport); + __u16 destp = ntohs(inet->inet_dport); + ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + } return 0; } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index d3cfaf9c7a08..5d1b8d7ac993 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -64,7 +64,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_UDP_TUNNEL | - SKB_GSO_GRE) || + SKB_GSO_GRE | + SKB_GSO_MPLS) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index f547a47d381c..7a1e0fc1bd4d 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -330,7 +330,7 @@ static __inline__ void __ipxitf_put(struct ipx_interface *intrfc) static int ipxitf_device_event(struct notifier_block *notifier, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipx_interface *i, *tmp; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ae691651b721..168aff5e60de 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -2293,7 +2293,7 @@ out_unlock: static int afiucv_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *event_dev = (struct net_device *)ptr; + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); struct sock *sk; struct iucv_sock *iucv; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 98d20c0f6fed..7c3ba8628d4e 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1747,10 +1747,9 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) } static int netdev_notify(struct notifier_block *nb, - unsigned long state, - void *ndev) + unsigned long state, void *ptr) { - struct net_device *dev = ndev; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ieee80211_sub_if_data *sdata; if (state != NETDEV_CHANGENAME) diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig new file mode 100644 index 000000000000..37421db88965 --- /dev/null +++ b/net/mpls/Kconfig @@ -0,0 +1,9 @@ +# +# MPLS configuration +# +config NET_MPLS_GSO + tristate "MPLS: GSO support" + help + This is helper module to allow segmentation of non-MPLS GSO packets + that have had MPLS stack entries pushed onto them and thus + become MPLS GSO packets. diff --git a/net/mpls/Makefile b/net/mpls/Makefile new file mode 100644 index 000000000000..0a3c171be537 --- /dev/null +++ b/net/mpls/Makefile @@ -0,0 +1,4 @@ +# +# Makefile for MPLS. +# +obj-y += mpls_gso.o diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c new file mode 100644 index 000000000000..1bec1219ab81 --- /dev/null +++ b/net/mpls/mpls_gso.c @@ -0,0 +1,108 @@ +/* + * MPLS GSO Support + * + * Authors: Simon Horman (horms@verge.net.au) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Based on: GSO portions of net/ipv4/gre.c + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/err.h> +#include <linux/module.h> +#include <linux/netdev_features.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> + +static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + netdev_features_t mpls_features; + __be16 mpls_protocol; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_TCPV4 | + SKB_GSO_TCPV6 | + SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_GRE | + SKB_GSO_MPLS))) + goto out; + + /* Setup inner SKB. */ + mpls_protocol = skb->protocol; + skb->protocol = skb->inner_protocol; + + /* Push back the mac header that skb_mac_gso_segment() has pulled. + * It will be re-pulled by the call to skb_mac_gso_segment() below + */ + __skb_push(skb, skb->mac_len); + + /* Segment inner packet. */ + mpls_features = skb->dev->mpls_features & netif_skb_features(skb); + segs = skb_mac_gso_segment(skb, mpls_features); + + + /* Restore outer protocol. */ + skb->protocol = mpls_protocol; + + /* Re-pull the mac header that the call to skb_mac_gso_segment() + * above pulled. It will be re-pushed after returning + * skb_mac_gso_segment(), an indirect caller of this function. + */ + __skb_push(skb, skb->data - skb_mac_header(skb)); + +out: + return segs; +} + +static int mpls_gso_send_check(struct sk_buff *skb) +{ + return 0; +} + +static struct packet_offload mpls_mc_offload = { + .type = cpu_to_be16(ETH_P_MPLS_MC), + .callbacks = { + .gso_send_check = mpls_gso_send_check, + .gso_segment = mpls_gso_segment, + }, +}; + +static struct packet_offload mpls_uc_offload = { + .type = cpu_to_be16(ETH_P_MPLS_UC), + .callbacks = { + .gso_send_check = mpls_gso_send_check, + .gso_segment = mpls_gso_segment, + }, +}; + +static int __init mpls_gso_init(void) +{ + pr_info("MPLS GSO support\n"); + + dev_add_offload(&mpls_uc_offload); + dev_add_offload(&mpls_mc_offload); + + return 0; +} + +static void __exit mpls_gso_exit(void) +{ + dev_remove_offload(&mpls_uc_offload); + dev_remove_offload(&mpls_mc_offload); +} + +module_init(mpls_gso_init); +module_exit(mpls_gso_exit); + +MODULE_DESCRIPTION("MPLS GSO support"); +MODULE_AUTHOR("Simon Horman (horms@verge.net.au)"); +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5b142fb16480..7c3ed429789e 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1487,9 +1487,9 @@ ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev) * Currently only NETDEV_DOWN is handled to release refs to cached dsts */ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_service *svc; diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 5fea563afe30..85e20a919081 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -104,7 +104,7 @@ static void mangle_contents(struct sk_buff *skb, /* move post-replacement */ memmove(data + match_offset + rep_len, data + match_offset + match_len, - skb->tail - (skb->network_header + dataoff + + skb_tail_pointer(skb) - (skb_network_header(skb) + dataoff + match_offset + match_len)); /* insert data from buffer */ diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 4e27fa035814..0f2ac8f2e7b7 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -800,7 +800,7 @@ static int nfqnl_rcv_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* Drop any packets associated with the downed device */ if (event == NETDEV_DOWN) diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index bd93e51d30ac..292934d23482 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -200,7 +200,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) static int tee_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct xt_tee_priv *priv; priv = container_of(this, struct xt_tee_priv, notifier); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 8a6c6ea466d8..af3531926ee0 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -708,7 +708,7 @@ unlhsh_remove_return: * netlbl_unlhsh_netdev_handler - Network device notification handler * @this: notifier block * @event: the event - * @ptr: the network device (cast to void) + * @ptr: the netdevice notifier info (cast to void) * * Description: * Handle network device events, although at present all we care about is a @@ -717,10 +717,9 @@ unlhsh_remove_return: * */ static int netlbl_unlhsh_netdev_handler(struct notifier_block *this, - unsigned long event, - void *ptr) + unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netlbl_unlhsh_iface *iface = NULL; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ec0c80fde69f..698814bfa7ad 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -117,7 +117,7 @@ static void nr_kill_by_device(struct net_device *dev) */ static int nr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index ef4feec6cd84..c3235675f359 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -78,7 +78,7 @@ static int dp_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct ovs_net *ovs_net; - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vport *vport = NULL; if (!ovs_is_internal_dev(dev)) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8ec1bca7f859..79fe63246b27 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3331,10 +3331,11 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, } -static int packet_notifier(struct notifier_block *this, unsigned long msg, void *data) +static int packet_notifier(struct notifier_block *this, + unsigned long msg, void *ptr) { struct sock *sk; - struct net_device *dev = data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); rcu_read_lock(); diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 45a7df6575de..56a6146ac94b 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -292,9 +292,9 @@ static void phonet_route_autodel(struct net_device *dev) /* notify Phonet of device events */ static int phonet_device_notify(struct notifier_block *me, unsigned long what, - void *arg) + void *ptr) { - struct net_device *dev = arg; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (what) { case NETDEV_REGISTER: diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 9c8347451597..e98fcfbe6007 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -202,10 +202,10 @@ static void rose_kill_by_device(struct net_device *dev) /* * Handle device status changes. */ -static int rose_device_event(struct notifier_block *this, unsigned long event, - void *ptr) +static int rose_device_event(struct notifier_block *this, + unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 5d676edc22a6..977c10e0631b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -243,7 +243,7 @@ nla_put_failure: static int mirred_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tcf_mirred *m; if (event == NETDEV_UNREGISTER) diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index e478d316602b..1aaf1b6e51a2 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -116,14 +116,57 @@ struct tbf_sched_data { struct qdisc_watchdog watchdog; /* Watchdog timer */ }; + +/* GSO packet is too big, segment it so that tbf can transmit + * each segment in time + */ +static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) +{ + struct tbf_sched_data *q = qdisc_priv(sch); + struct sk_buff *segs, *nskb; + netdev_features_t features = netif_skb_features(skb); + int ret, nb; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + + if (IS_ERR_OR_NULL(segs)) + return qdisc_reshape_fail(skb, sch); + + nb = 0; + while (segs) { + nskb = segs->next; + segs->next = NULL; + if (likely(segs->len <= q->max_size)) { + qdisc_skb_cb(segs)->pkt_len = segs->len; + ret = qdisc_enqueue(segs, q->qdisc); + } else { + ret = qdisc_reshape_fail(skb, sch); + } + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) + sch->qstats.drops++; + } else { + nb++; + } + segs = nskb; + } + sch->q.qlen += nb; + if (nb > 1) + qdisc_tree_decrease_qlen(sch, 1 - nb); + consume_skb(skb); + return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; +} + static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); int ret; - if (qdisc_pkt_len(skb) > q->max_size) + if (qdisc_pkt_len(skb) > q->max_size) { + if (skb_is_gso(skb)) + return tbf_segment(skb, sch); return qdisc_reshape_fail(skb, sch); - + } ret = qdisc_enqueue(skb, q->qdisc); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) diff --git a/net/sctp/input.c b/net/sctp/input.c index 4b2c83146aa7..6533d81a638d 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -589,7 +589,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) struct sctp_association *asoc = NULL; struct sctp_transport *transport; struct inet_sock *inet; - sk_buff_data_t saveip, savesctp; + __u16 saveip, savesctp; int err; struct net *net = dev_net(skb->dev); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 391a245d5203..8ee553b499ce 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -153,7 +153,7 @@ SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct sctp_association *asoc; struct sctp_transport *transport; struct ipv6_pinfo *np; - sk_buff_data_t saveip, savesctp; + __be16 saveip, savesctp; int err; struct net *net = dev_net(skb->dev); diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 120a676a3360..fc60bea63169 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -251,9 +251,9 @@ static void disable_bearer(struct tipc_bearer *tb_ptr) * specified device. */ static int recv_notification(struct notifier_block *nb, unsigned long evt, - void *dv) + void *ptr) { - struct net_device *dev = (struct net_device *)dv; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct eth_bearer *eb_ptr = ð_bearers[0]; struct eth_bearer *stop = ð_bearers[MAX_ETH_BEARERS]; diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index 2a2864c25e15..baa9df4327d9 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -244,9 +244,9 @@ static void disable_bearer(struct tipc_bearer *tb_ptr) * specified device. */ static int recv_notification(struct notifier_block *nb, unsigned long evt, - void *dv) + void *ptr) { - struct net_device *dev = (struct net_device *)dv; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ib_bearer *ib_ptr = &ib_bearers[0]; struct ib_bearer *stop = &ib_bearers[MAX_IB_BEARERS]; diff --git a/net/wireless/core.c b/net/wireless/core.c index 73405e00c800..01e41191f1bf 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -886,10 +886,9 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, } static int cfg80211_netdev_notifier_call(struct notifier_block *nb, - unsigned long state, - void *ndev) + unsigned long state, void *ptr) { - struct net_device *dev = ndev; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; int ret; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 37ca9694aabe..1d964e23853f 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -224,7 +224,7 @@ static void x25_kill_by_device(struct net_device *dev) static int x25_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct x25_neigh *nb; if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 0cf003dfa8fc..eb4a84288648 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -89,7 +89,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) err = x->type->output(x, skb); if (err == -EINPROGRESS) - goto out_exit; + goto out; resume: if (err) { @@ -107,15 +107,14 @@ resume: x = dst->xfrm; } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); - err = 0; + return 0; -out_exit: - return err; error: spin_unlock_bh(&x->lock); error_nolock: kfree_skb(skb); - goto out_exit; +out: + return err; } int xfrm_output_resume(struct sk_buff *skb, int err) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ea970b8002a2..e52cab3591dd 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2785,7 +2785,7 @@ static void __net_init xfrm_dst_ops_init(struct net *net) static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_DOWN: |