diff options
Diffstat (limited to 'net')
319 files changed, 8234 insertions, 3800 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 59555f0f8fc8..d2cd9de4b724 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -618,6 +618,92 @@ out: return err; } +static struct sk_buff **vlan_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + struct sk_buff *p, **pp = NULL; + struct vlan_hdr *vhdr; + unsigned int hlen, off_vlan; + const struct packet_offload *ptype; + __be16 type; + int flush = 1; + + off_vlan = skb_gro_offset(skb); + hlen = off_vlan + sizeof(*vhdr); + vhdr = skb_gro_header_fast(skb, off_vlan); + if (skb_gro_header_hard(skb, hlen)) { + vhdr = skb_gro_header_slow(skb, hlen, off_vlan); + if (unlikely(!vhdr)) + goto out; + } + + type = vhdr->h_vlan_encapsulated_proto; + + rcu_read_lock(); + ptype = gro_find_receive_by_type(type); + if (!ptype) + goto out_unlock; + + flush = 0; + + for (p = *head; p; p = p->next) { + struct vlan_hdr *vhdr2; + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + vhdr2 = (struct vlan_hdr *)(p->data + off_vlan); + if (compare_vlan_header(vhdr, vhdr2)) + NAPI_GRO_CB(p)->same_flow = 0; + } + + skb_gro_pull(skb, sizeof(*vhdr)); + skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr)); + pp = ptype->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int vlan_gro_complete(struct sk_buff *skb, int nhoff) +{ + struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + nhoff); + __be16 type = vhdr->h_vlan_encapsulated_proto; + struct packet_offload *ptype; + int err = -ENOENT; + + rcu_read_lock(); + ptype = gro_find_complete_by_type(type); + if (ptype) + err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr)); + + rcu_read_unlock(); + return err; +} + +static struct packet_offload vlan_packet_offloads[] __read_mostly = { + { + .type = cpu_to_be16(ETH_P_8021Q), + .priority = 10, + .callbacks = { + .gro_receive = vlan_gro_receive, + .gro_complete = vlan_gro_complete, + }, + }, + { + .type = cpu_to_be16(ETH_P_8021AD), + .priority = 10, + .callbacks = { + .gro_receive = vlan_gro_receive, + .gro_complete = vlan_gro_complete, + }, + }, +}; + static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); @@ -645,6 +731,7 @@ static struct pernet_operations vlan_net_ops = { static int __init vlan_proto_init(void) { int err; + unsigned int i; pr_info("%s v%s\n", vlan_fullname, vlan_version); @@ -668,6 +755,9 @@ static int __init vlan_proto_init(void) if (err < 0) goto err5; + for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++) + dev_add_offload(&vlan_packet_offloads[i]); + vlan_ioctl_set(vlan_ioctl_handler); return 0; @@ -685,7 +775,13 @@ err0: static void __exit vlan_cleanup_module(void) { + unsigned int i; + vlan_ioctl_set(NULL); + + for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++) + dev_remove_offload(&vlan_packet_offloads[i]); + vlan_netlink_fini(); unregister_netdevice_notifier(&vlan_notifier_block); diff --git a/net/Kconfig b/net/Kconfig index 44dd5786ee91..57a7c5af3175 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -45,6 +45,9 @@ config COMPAT_NETLINK_MESSAGES Newly written code should NEVER need this option but do compat-independent messages instead! +config NET_INGRESS + bool + menu "Networking options" source "net/packet/Kconfig" diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 3b7ad43c7dad..d5871ac493eb 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1030,7 +1030,7 @@ static int atalk_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) goto out; rc = -ENOMEM; - sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto); + sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto, kern); if (!sk) goto out; rc = 0; diff --git a/net/atm/common.c b/net/atm/common.c index ed0466637e13..49a872db7e42 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -141,7 +141,7 @@ static struct proto vcc_proto = { .release_cb = vcc_release_cb, }; -int vcc_create(struct net *net, struct socket *sock, int protocol, int family) +int vcc_create(struct net *net, struct socket *sock, int protocol, int family, int kern) { struct sock *sk; struct atm_vcc *vcc; @@ -149,7 +149,7 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family) sock->sk = NULL; if (sock->type == SOCK_STREAM) return -EINVAL; - sk = sk_alloc(net, family, GFP_KERNEL, &vcc_proto); + sk = sk_alloc(net, family, GFP_KERNEL, &vcc_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); diff --git a/net/atm/common.h b/net/atm/common.h index 4d6f5b2068ac..959436b87182 100644 --- a/net/atm/common.h +++ b/net/atm/common.h @@ -10,7 +10,7 @@ #include <linux/poll.h> /* for poll_table */ -int vcc_create(struct net *net, struct socket *sock, int protocol, int family); +int vcc_create(struct net *net, struct socket *sock, int protocol, int family, int kern); int vcc_release(struct socket *sock); int vcc_connect(struct socket *sock, int itf, short vpi, int vci); int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/net/atm/pvc.c b/net/atm/pvc.c index ae0324021407..040207ec399f 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -136,7 +136,7 @@ static int pvc_create(struct net *net, struct socket *sock, int protocol, return -EAFNOSUPPORT; sock->ops = &pvc_proto_ops; - return vcc_create(net, sock, protocol, PF_ATMPVC); + return vcc_create(net, sock, protocol, PF_ATMPVC, kern); } static const struct net_proto_family pvc_family_ops = { diff --git a/net/atm/svc.c b/net/atm/svc.c index 1ba23f5018e7..3fa0a9ee98d1 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -660,7 +660,7 @@ static int svc_create(struct net *net, struct socket *sock, int protocol, return -EAFNOSUPPORT; sock->ops = &svc_proto_ops; - error = vcc_create(net, sock, protocol, AF_ATMSVC); + error = vcc_create(net, sock, protocol, AF_ATMSVC, kern); if (error) return error; ATM_SD(sock)->local.sas_family = AF_ATMSVC; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 330c1f4a5a0b..4273533d22b1 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -855,7 +855,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, return -ESOCKTNOSUPPORT; } - sk = sk_alloc(net, PF_AX25, GFP_ATOMIC, &ax25_proto); + sk = sk_alloc(net, PF_AX25, GFP_ATOMIC, &ax25_proto, kern); if (sk == NULL) return -ENOMEM; @@ -881,7 +881,7 @@ struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev) struct sock *sk; ax25_cb *ax25, *oax25; - sk = sk_alloc(sock_net(osk), PF_AX25, GFP_ATOMIC, osk->sk_prot); + sk = sk_alloc(sock_net(osk), PF_AX25, GFP_ATOMIC, osk->sk_prot, 0); if (sk == NULL) return NULL; diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index eb7d8c0388e4..21434ab79d2c 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # -# Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # @@ -20,7 +20,7 @@ obj-$(CONFIG_BATMAN_ADV) += batman-adv.o batman-adv-y += bat_iv_ogm.o batman-adv-y += bitarray.o batman-adv-$(CONFIG_BATMAN_ADV_BLA) += bridge_loop_avoidance.o -batman-adv-y += debugfs.o +batman-adv-$(CONFIG_DEBUG_FS) += debugfs.o batman-adv-$(CONFIG_BATMAN_ADV_DAT) += distributed-arp-table.o batman-adv-y += fragmentation.o batman-adv-y += gateway_client.o @@ -29,6 +29,7 @@ batman-adv-y += hard-interface.o batman-adv-y += hash.o batman-adv-y += icmp_socket.o batman-adv-y += main.o +batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o batman-adv-y += originator.o batman-adv-y += routing.o @@ -36,4 +37,3 @@ batman-adv-y += send.o batman-adv-y += soft-interface.o batman-adv-y += sysfs.o batman-adv-y += translation-table.o -batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 4e49666f8c65..4e59cf3eb079 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 00e00e09b000..4e93d2d3958b 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -28,7 +28,7 @@ /** * enum batadv_dup_status - duplicate status - * @BATADV_NO_DUP: the packet is a duplicate + * @BATADV_NO_DUP: the packet is no duplicate * @BATADV_ORIG_DUP: OGM is a duplicate in the originator (but not for the * neighbor) * @BATADV_NEIGH_DUP: OGM is a duplicate for the neighbor @@ -55,7 +55,7 @@ static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, } /** - * batadv_ring_buffer_set - compute the average of all non-zero values stored + * batadv_ring_buffer_avg - compute the average of all non-zero values stored * in the given ring buffer * @lq_recv: pointer to the ring buffer * @@ -64,7 +64,9 @@ static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, static uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]) { const uint8_t *ptr; - uint16_t count = 0, i = 0, sum = 0; + uint16_t count = 0; + uint16_t i = 0; + uint16_t sum = 0; ptr = lq_recv; @@ -308,7 +310,6 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) struct batadv_ogm_packet *batadv_ogm_packet; unsigned char *ogm_buff; uint32_t random_seqno; - int res = -ENOMEM; /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); @@ -317,7 +318,7 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN; ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC); if (!ogm_buff) - goto out; + return -ENOMEM; hard_iface->bat_iv.ogm_buff = ogm_buff; @@ -329,10 +330,7 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) batadv_ogm_packet->reserved = 0; batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE; - res = 0; - -out: - return res; + return 0; } static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) @@ -396,8 +394,8 @@ static uint8_t batadv_hop_penalty(uint8_t tq, } /* is there another aggregated packet here? */ -static int batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, - __be16 tvlv_len) +static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, + __be16 tvlv_len) { int next_buff_pos = 0; @@ -413,7 +411,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - char *fwd_str; + const char *fwd_str; uint8_t packet_num; int16_t buff_pos; struct batadv_ogm_packet *batadv_ogm_packet; @@ -548,58 +546,62 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, * - the send time is within our MAX_AGGREGATION_MS time * - the resulting packet wont be bigger than * MAX_AGGREGATION_BYTES + * otherwise aggregation is not possible */ - if (time_before(send_time, forw_packet->send_time) && - time_after_eq(aggregation_end_time, forw_packet->send_time) && - (aggregated_bytes <= BATADV_MAX_AGGREGATION_BYTES)) { - /* check aggregation compatibility - * -> direct link packets are broadcasted on - * their interface only - * -> aggregate packet if the current packet is - * a "global" packet as well as the base - * packet - */ - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; - - /* packet is not leaving on the same interface. */ - if (forw_packet->if_outgoing != if_outgoing) - goto out; + if (!time_before(send_time, forw_packet->send_time) || + !time_after_eq(aggregation_end_time, forw_packet->send_time)) + return false; + + if (aggregated_bytes > BATADV_MAX_AGGREGATION_BYTES) + return false; + + /* packet is not leaving on the same interface. */ + if (forw_packet->if_outgoing != if_outgoing) + return false; + + /* check aggregation compatibility + * -> direct link packets are broadcasted on + * their interface only + * -> aggregate packet if the current packet is + * a "global" packet as well as the base + * packet + */ + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + return false; - /* packets without direct link flag and high TTL - * are flooded through the net - */ - if ((!directlink) && - (!(batadv_ogm_packet->flags & BATADV_DIRECTLINK)) && - (batadv_ogm_packet->ttl != 1) && - - /* own packets originating non-primary - * interfaces leave only that interface - */ - ((!forw_packet->own) || - (forw_packet->if_incoming == primary_if))) { - res = true; - goto out; - } + /* packets without direct link flag and high TTL + * are flooded through the net + */ + if (!directlink && + !(batadv_ogm_packet->flags & BATADV_DIRECTLINK) && + batadv_ogm_packet->ttl != 1 && + + /* own packets originating non-primary + * interfaces leave only that interface + */ + (!forw_packet->own || + forw_packet->if_incoming == primary_if)) { + res = true; + goto out; + } - /* if the incoming packet is sent via this one - * interface only - we still can aggregate - */ - if ((directlink) && - (new_bat_ogm_packet->ttl == 1) && - (forw_packet->if_incoming == if_incoming) && - - /* packets from direct neighbors or - * own secondary interface packets - * (= secondary interface packets in general) - */ - (batadv_ogm_packet->flags & BATADV_DIRECTLINK || - (forw_packet->own && - forw_packet->if_incoming != primary_if))) { - res = true; - goto out; - } + /* if the incoming packet is sent via this one + * interface only - we still can aggregate + */ + if (directlink && + new_bat_ogm_packet->ttl == 1 && + forw_packet->if_incoming == if_incoming && + + /* packets from direct neighbors or + * own secondary interface packets + * (= secondary interface packets in general) + */ + (batadv_ogm_packet->flags & BATADV_DIRECTLINK || + (forw_packet->own && + forw_packet->if_incoming != primary_if))) { + res = true; + goto out; } out: @@ -642,19 +644,16 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, if (!batadv_atomic_dec_not_zero(&bat_priv->batman_queue_left)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "batman packet queue full\n"); - goto out; + goto out_free_outgoing; } } forw_packet_aggr = kmalloc(sizeof(*forw_packet_aggr), GFP_ATOMIC); - if (!forw_packet_aggr) { - if (!own_packet) - atomic_inc(&bat_priv->batman_queue_left); - goto out; - } + if (!forw_packet_aggr) + goto out_nomem; - if ((atomic_read(&bat_priv->aggregated_ogms)) && - (packet_len < BATADV_MAX_AGGREGATION_BYTES)) + if (atomic_read(&bat_priv->aggregated_ogms) && + packet_len < BATADV_MAX_AGGREGATION_BYTES) skb_size = BATADV_MAX_AGGREGATION_BYTES; else skb_size = packet_len; @@ -662,12 +661,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, skb_size += ETH_HLEN; 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; - } + if (!forw_packet_aggr->skb) + goto out_free_forw_packet; forw_packet_aggr->skb->priority = TC_PRIO_CONTROL; skb_reserve(forw_packet_aggr->skb, ETH_HLEN); @@ -699,7 +694,12 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, send_time - jiffies); return; -out: +out_free_forw_packet: + kfree(forw_packet_aggr); +out_nomem: + if (!own_packet) + atomic_inc(&bat_priv->batman_queue_left); +out_free_outgoing: batadv_hardif_free_ref(if_outgoing); out_free_incoming: batadv_hardif_free_ref(if_incoming); @@ -752,13 +752,13 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, unsigned long max_aggregation_jiffies; batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff; - direct_link = batadv_ogm_packet->flags & BATADV_DIRECTLINK ? 1 : 0; + direct_link = !!(batadv_ogm_packet->flags & BATADV_DIRECTLINK); max_aggregation_jiffies = msecs_to_jiffies(BATADV_MAX_AGGREGATION_MS); /* find position for the packet in the forward queue */ spin_lock_bh(&bat_priv->forw_bat_list_lock); /* own packets are not to be aggregated */ - if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) { + if (atomic_read(&bat_priv->aggregated_ogms) && !own_packet) { hlist_for_each_entry(forw_packet_pos, &bat_priv->forw_bat_list, list) { if (batadv_iv_ogm_can_aggregate(batadv_ogm_packet, @@ -1034,9 +1034,10 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, batadv_orig_node_free_ref(orig_tmp); if (!neigh_node) goto unlock; - } else + } else { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Updating existing last-hop neighbor of originator\n"); + } rcu_read_unlock(); neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); @@ -1081,7 +1082,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, * won't consider it either */ if (router_ifinfo && - (neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg)) { + neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg) { orig_node_tmp = router->orig_node; spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); if_num = router->if_incoming->if_num; @@ -1356,8 +1357,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, out: spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); batadv_orig_node_free_ref(orig_node); - if (orig_ifinfo) - batadv_orig_ifinfo_free_ref(orig_ifinfo); + batadv_orig_ifinfo_free_ref(orig_ifinfo); return ret; } diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index e3da07a64026..40e4a2a18e45 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 2acaafe60188..be497be696d1 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ac4b96eccade..fa941cd7d8ad 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 43c985d92c3e..1f506d34039e 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index a4972874c056..46118084221a 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -482,11 +482,7 @@ rem_attr: debugfs_remove_recursive(hard_iface->debug_dir); hard_iface->debug_dir = NULL; out: -#ifdef CONFIG_DEBUG_FS return -ENOMEM; -#else - return 0; -#endif /* CONFIG_DEBUG_FS */ } /** @@ -541,11 +537,7 @@ rem_attr: debugfs_remove_recursive(bat_priv->debug_dir); bat_priv->debug_dir = NULL; out: -#ifdef CONFIG_DEBUG_FS return -ENOMEM; -#else - return 0; -#endif /* CONFIG_DEBUG_FS */ } void batadv_debugfs_del_meshif(struct net_device *dev) diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 37c4d6ddd04d..ed25605ca732 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -20,6 +20,8 @@ #define BATADV_DEBUGFS_SUBDIR "batman_adv" +#if IS_ENABLED(CONFIG_DEBUG_FS) + void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); @@ -27,4 +29,36 @@ void batadv_debugfs_del_meshif(struct net_device *dev); int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); +#else + +static inline void batadv_debugfs_init(void) +{ +} + +static inline void batadv_debugfs_destroy(void) +{ +} + +static inline int batadv_debugfs_add_meshif(struct net_device *dev) +{ + return 0; +} + +static inline void batadv_debugfs_del_meshif(struct net_device *dev) +{ +} + +static inline +int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) +{ + return 0; +} + +static inline +void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) +{ +} + +#endif + #endif /* _NET_BATMAN_ADV_DEBUGFS_H_ */ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index aad022dd15df..da1742d9059f 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index 2fe0764c64be..ed41b8edba18 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 3d1dcaa3e8b5..6ce3c84a7e55 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2015 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * @@ -161,6 +161,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, hlist_add_head(&frag_entry_new->list, &chain->head); chain->size = skb->len - hdr_size; chain->timestamp = jiffies; + chain->total_size = ntohs(frag_packet->total_size); ret = true; goto out; } @@ -195,9 +196,11 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, out: if (chain->size > batadv_frag_size_limit() || - ntohs(frag_packet->total_size) > batadv_frag_size_limit()) { + chain->total_size != ntohs(frag_packet->total_size) || + chain->total_size > batadv_frag_size_limit()) { /* Clear chain if total size of either the list or the packet - * exceeds the maximum size of one merged packet. + * exceeds the maximum size of one merged packet. Don't allow + * packets to have different total_size. */ batadv_frag_clear_chain(&chain->head); chain->size = 0; @@ -228,19 +231,13 @@ err: * Returns the merged skb or NULL on error. */ static struct sk_buff * -batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb) +batadv_frag_merge_packets(struct hlist_head *chain) { struct batadv_frag_packet *packet; struct batadv_frag_list_entry *entry; struct sk_buff *skb_out = NULL; int size, hdr_size = sizeof(struct batadv_frag_packet); - /* Make sure incoming skb has non-bogus data. */ - packet = (struct batadv_frag_packet *)skb->data; - size = ntohs(packet->total_size); - if (size > batadv_frag_size_limit()) - goto free; - /* Remove first entry, as this is the destination for the rest of the * fragments. */ @@ -249,6 +246,9 @@ batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb) skb_out = entry->skb; kfree(entry); + packet = (struct batadv_frag_packet *)skb_out->data; + size = ntohs(packet->total_size); + /* Make room for the rest of the fragments. */ if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) { kfree_skb(skb_out); @@ -304,7 +304,7 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb, if (hlist_empty(&head)) goto out; - skb_out = batadv_frag_merge_packets(&head, *skb); + skb_out = batadv_frag_merge_packets(&head); if (!skb_out) goto out_err; diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index d848cf6676a2..ec1e86f899e8 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2015 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 090828cf1fa7..a85eaca344e8 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 7ee53bb7d50f..185fb0887654 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 88a1bc3804d1..0792e2f101e4 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index aa5116561947..df5434229675 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index baf1f9843f2c..bdb020e29272 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 1918cd50b62e..e8b6ffea703d 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 7c1c63080e20..3a0e1dcd1f29 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 539fc1266793..379e32acf2b4 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 161ef8f17d2e..6c3cfb57d132 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 0c33950aa4aa..4815824e2f61 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 12fc77bef23f..548e405d13c1 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -209,10 +209,13 @@ void batadv_mesh_free(struct net_device *soft_iface) * interfaces in the current mesh * @bat_priv: the bat priv with all the soft interface information * @addr: the address to check + * + * Returns 'true' if the mac address was found, false otherwise. */ -int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) +bool batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) { const struct batadv_hard_iface *hard_iface; + bool is_my_mac = false; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { @@ -223,12 +226,12 @@ int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) continue; if (batadv_compare_eth(hard_iface->net_dev->dev_addr, addr)) { - rcu_read_unlock(); - return 1; + is_my_mac = true; + break; } } rcu_read_unlock(); - return 0; + return is_my_mac; } /** @@ -510,14 +513,12 @@ static struct batadv_algo_ops *batadv_algo_get(char *name) int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) { struct batadv_algo_ops *bat_algo_ops_tmp; - int ret; bat_algo_ops_tmp = batadv_algo_get(bat_algo_ops->name); if (bat_algo_ops_tmp) { pr_info("Trying to register already registered routing algorithm: %s\n", bat_algo_ops->name); - ret = -EEXIST; - goto out; + return -EEXIST; } /* all algorithms must implement all ops (for now) */ @@ -531,32 +532,26 @@ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) !bat_algo_ops->bat_neigh_is_equiv_or_better) { pr_info("Routing algo '%s' does not implement required ops\n", bat_algo_ops->name); - ret = -EINVAL; - goto out; + return -EINVAL; } INIT_HLIST_NODE(&bat_algo_ops->list); hlist_add_head(&bat_algo_ops->list, &batadv_algo_list); - ret = 0; -out: - return ret; + return 0; } int batadv_algo_select(struct batadv_priv *bat_priv, char *name) { struct batadv_algo_ops *bat_algo_ops; - int ret = -EINVAL; bat_algo_ops = batadv_algo_get(name); if (!bat_algo_ops) - goto out; + return -EINVAL; bat_priv->bat_algo_ops = bat_algo_ops; - ret = 0; -out: - return ret; + return 0; } int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) @@ -819,15 +814,15 @@ static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff, new_buff = kmalloc(min_packet_len + additional_packet_len, GFP_ATOMIC); /* keep old buffer if kmalloc should fail */ - if (new_buff) { - memcpy(new_buff, *packet_buff, min_packet_len); - kfree(*packet_buff); - *packet_buff = new_buff; - *packet_buff_len = min_packet_len + additional_packet_len; - return true; - } + if (!new_buff) + return false; + + memcpy(new_buff, *packet_buff, min_packet_len); + kfree(*packet_buff); + *packet_buff = new_buff; + *packet_buff_len = min_packet_len + additional_packet_len; - return false; + return true; } /** diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 4d2318829a34..af0a3361d4b2 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2015.0" +#define BATADV_SOURCE_VERSION "2015.1" #endif /* B.A.T.M.A.N. parameters */ @@ -44,7 +44,7 @@ #define BATADV_TT_CLIENT_TEMP_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_WORK_PERIOD 5000 /* 5 seconds */ #define BATADV_ORIG_WORK_PERIOD 1000 /* 1 second */ -#define BATADV_DAT_ENTRY_TIMEOUT (5*60000) /* 5 mins in milliseconds */ +#define BATADV_DAT_ENTRY_TIMEOUT (5 * 60000) /* 5 mins in milliseconds */ /* sliding packet range of received originator messages in sequence numbers * (should be a multiple of our word size) */ @@ -195,7 +195,7 @@ extern struct workqueue_struct *batadv_event_workqueue; int batadv_mesh_init(struct net_device *soft_iface); void batadv_mesh_free(struct net_device *soft_iface); -int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr); +bool batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_hard_iface * batadv_seq_print_text_primary_if_get(struct seq_file *seq); int batadv_max_header_len(void); @@ -279,7 +279,7 @@ static inline void _batadv_dbg(int type __always_unused, * * note: can't use ether_addr_equal() as it requires aligned memory */ -static inline int batadv_compare_eth(const void *data1, const void *data2) +static inline bool batadv_compare_eth(const void *data1, const void *data2) { return ether_addr_equal_unaligned(data1, data2); } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index b24e4bb64fb5..09f2838dedf2 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2015 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 3a44ebdb43cb..033d80e84fdf 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2015 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 127cc4d7380a..b984bc49deaf 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2015 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * @@ -155,7 +155,7 @@ err: */ void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv) { - atomic_set(&bat_priv->network_coding, 1); + atomic_set(&bat_priv->network_coding, 0); bat_priv->nc.min_tq = 200; bat_priv->nc.max_fwd_delay = 10; bat_priv->nc.max_buffer_time = 200; @@ -275,7 +275,7 @@ static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv, * max_buffer time */ return batadv_has_timed_out(nc_path->last_valid, - bat_priv->nc.max_buffer_time*10); + bat_priv->nc.max_buffer_time * 10); } /** diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 358c0d686ab0..b5ab8ff544ee 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2015 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 90e805aba379..e3900e452616 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index aa4a43696295..91339143a2f7 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index b81fbbf21a63..9468bc09c7c4 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index da83982bf974..c5d90095bc3c 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 557d3d12a9ab..6573f12b3ddc 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 3d64ed20c393..23635bd63fec 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -255,8 +255,8 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, unsigned short vid) { - struct ethhdr *ethhdr; struct batadv_unicast_packet *unicast_packet; + struct ethhdr *ethhdr; int ret = NET_XMIT_DROP; if (!orig_node) diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 38d0ec1833ae..60c233eb35ed 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5ec31d7de24f..50cf722f4e1b 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -732,7 +732,7 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->aggregated_ogms, 1); atomic_set(&bat_priv->bonding, 0); #ifdef CONFIG_BATMAN_ADV_BLA - atomic_set(&bat_priv->bridge_loop_avoidance, 0); + atomic_set(&bat_priv->bridge_loop_avoidance, 1); #endif #ifdef CONFIG_BATMAN_ADV_DAT atomic_set(&bat_priv->distributed_arp_table, 1); @@ -818,7 +818,7 @@ static int batadv_softif_slave_add(struct net_device *dev, int ret = -EINVAL; hard_iface = batadv_hardif_get_by_netdev(slave_dev); - if (!hard_iface || hard_iface->soft_iface != NULL) + if (!hard_iface || hard_iface->soft_iface) goto out; ret = batadv_hardif_enable_interface(hard_iface, dev->name); diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index dbab22fd89a5..9ce08049ffd0 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index a75dc12f96f8..fa8c347bf057 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index b715b60db7cd..b9e79ad806ac 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 07b263a437d1..b098e53edded 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index ad84d7b89e39..5769037c7e2d 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 9398c3fb4174..c1000c0d6b0d 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -132,6 +132,7 @@ struct batadv_orig_ifinfo { * @timestamp: time (jiffie) of last received fragment * @seqno: sequence number of the fragments in the list * @size: accumulated size of packets in list + * @total_size: expected size of the assembled packet */ struct batadv_frag_table_entry { struct hlist_head head; @@ -139,6 +140,7 @@ struct batadv_frag_table_entry { unsigned long timestamp; uint16_t seqno; uint16_t size; + uint16_t total_size; }; /** @@ -181,9 +183,10 @@ struct batadv_orig_node_vlan { /** * struct batadv_orig_bat_iv - B.A.T.M.A.N. IV private orig_node members - * @bcast_own: bitfield containing the number of our OGMs this orig_node - * rebroadcasted "back" to us (relative to last_real_seqno) - * @bcast_own_sum: counted result of bcast_own + * @bcast_own: set of bitfields (one per hard interface) where each one counts + * the number of our OGMs this orig_node rebroadcasted "back" to us (relative + * to last_real_seqno). Every bitfield is BATADV_TQ_LOCAL_WINDOW_SIZE bits long. + * @bcast_own_sum: sum of bcast_own * @ogm_cnt_lock: lock protecting bcast_own, bcast_own_sum, * neigh_node->bat_iv.real_bits & neigh_node->bat_iv.real_packet_count */ diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 1742b849fcff..f3d6046c8ee7 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -192,7 +192,7 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_dev *dev, if (ipv6_addr_any(nexthop)) return NULL; } else { - nexthop = rt6_nexthop(rt); + nexthop = rt6_nexthop(rt, daddr); /* We need to remember the address because it is needed * by bt_xmit() when sending the packet. In bt_xmit(), the diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index bde2bdd9e929..b5116fa9835e 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -202,7 +202,7 @@ static int bnep_sock_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto); + sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto, kern); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c index d82787d417bd..ce86a7bae844 100644 --- a/net/bluetooth/cmtp/sock.c +++ b/net/bluetooth/cmtp/sock.c @@ -205,7 +205,7 @@ static int cmtp_sock_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &cmtp_proto); + sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &cmtp_proto, kern); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index c4802f3bd4c5..f6c99098959f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -94,7 +94,6 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf, char buf[32]; size_t buf_size = min(count, (sizeof(buf)-1)); bool enable; - int err; if (!test_bit(HCI_UP, &hdev->flags)) return -ENETDOWN; @@ -121,12 +120,8 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf, if (IS_ERR(skb)) return PTR_ERR(skb); - err = -bt_to_errno(skb->data[0]); kfree_skb(skb); - if (err < 0) - return err; - hci_dev_change_flag(hdev, HCI_DUT_MODE); return count; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 56f9edbf3d05..5b14dcafcd08 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1377,7 +1377,7 @@ static int hci_sock_create(struct net *net, struct socket *sock, int protocol, sock->ops = &hci_sock_ops; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto); + sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto, kern); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c index cb3fdde1968a..008ba439bd62 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -235,7 +235,7 @@ static int hidp_sock_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hidp_proto); + sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hidp_proto, kern); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index a7278f05eafb..244287706f91 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -43,7 +43,7 @@ static struct bt_sock_list l2cap_sk_list = { static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, - int proto, gfp_t prio); + int proto, gfp_t prio, int kern); bool l2cap_is_socket(struct socket *sock) { @@ -1193,7 +1193,7 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) } sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, - GFP_ATOMIC); + GFP_ATOMIC, 0); if (!sk) { release_sock(parent); return NULL; @@ -1523,12 +1523,12 @@ static struct proto l2cap_proto = { }; static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, - int proto, gfp_t prio) + int proto, gfp_t prio, int kern) { struct sock *sk; struct l2cap_chan *chan; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto); + sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto, kern); if (!sk) return NULL; @@ -1574,7 +1574,7 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, sock->ops = &l2cap_sock_ops; - sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC); + sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7fd87e7135b5..a6f21f8c2f98 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7577,7 +7577,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) memset(&ev, 0, sizeof(ev)); /* Devices using resolvable or non-resolvable random addresses - * without providing an indentity resolving key don't require + * without providing an identity resolving key don't require * to store long term keys. Their addresses will change the * next time around. * @@ -7617,7 +7617,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk) /* For identity resolving keys from devices that are already * using a public address or static random address, do not * ask for storing this key. The identity resolving key really - * is only mandatory for devices using resovlable random + * is only mandatory for devices using resolvable random * addresses. * * Storing all identity resolving keys has the downside that @@ -7646,7 +7646,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, memset(&ev, 0, sizeof(ev)); /* Devices using resolvable or non-resolvable random addresses - * without providing an indentity resolving key don't require + * without providing an identity resolving key don't require * to store signature resolving keys. Their addresses will change * the next time around. * diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 4fea24275b17..29709fbfd1f5 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -200,7 +200,7 @@ static int rfcomm_l2sock_create(struct socket **sock) BT_DBG(""); - err = sock_create_kern(PF_BLUETOOTH, SOCK_SEQPACKET, BTPROTO_L2CAP, sock); + err = sock_create_kern(&init_net, PF_BLUETOOTH, SOCK_SEQPACKET, BTPROTO_L2CAP, sock); if (!err) { struct sock *sk = (*sock)->sk; sk->sk_data_ready = rfcomm_l2data_ready; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 825e8fb5114b..b2338e971b33 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -269,12 +269,12 @@ static struct proto rfcomm_proto = { .obj_size = sizeof(struct rfcomm_pinfo) }; -static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio) +static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) { struct rfcomm_dlc *d; struct sock *sk; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &rfcomm_proto); + sk = sk_alloc(net, PF_BLUETOOTH, prio, &rfcomm_proto, kern); if (!sk) return NULL; @@ -324,7 +324,7 @@ static int rfcomm_sock_create(struct net *net, struct socket *sock, sock->ops = &rfcomm_sock_ops; - sk = rfcomm_sock_alloc(net, sock, protocol, GFP_ATOMIC); + sk = rfcomm_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; @@ -969,7 +969,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * goto done; } - sk = rfcomm_sock_alloc(sock_net(parent), NULL, BTPROTO_RFCOMM, GFP_ATOMIC); + sk = rfcomm_sock_alloc(sock_net(parent), NULL, BTPROTO_RFCOMM, GFP_ATOMIC, 0); if (!sk) goto done; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 4322c833e748..6b6e59dc54cf 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -460,11 +460,11 @@ static struct proto sco_proto = { .obj_size = sizeof(struct sco_pinfo) }; -static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio) +static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) { struct sock *sk; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &sco_proto); + sk = sk_alloc(net, PF_BLUETOOTH, prio, &sco_proto, kern); if (!sk) return NULL; @@ -501,7 +501,7 @@ static int sco_sock_create(struct net *net, struct socket *sock, int protocol, sock->ops = &sco_sock_ops; - sk = sco_sock_alloc(net, sock, protocol, GFP_ATOMIC); + sk = sco_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; @@ -1026,7 +1026,7 @@ static void sco_conn_ready(struct sco_conn *conn) bh_lock_sock(parent); sk = sco_sock_alloc(sock_net(parent), NULL, - BTPROTO_SCO, GFP_ATOMIC); + BTPROTO_SCO, GFP_ATOMIC, 0); if (!sk) { bh_unlock_sock(parent); sco_conn_unlock(conn); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1ab3dc9c8f99..659371af39e4 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -371,6 +371,8 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) uint8_t tmp[16], data[16]; int err; + SMP_DBG("k %16phN r %16phN", k, r); + if (!tfm) { BT_ERR("tfm %p", tfm); return -EINVAL; @@ -400,6 +402,8 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) /* Most significant octet of encryptedData corresponds to data[0] */ swap_buf(data, r, 16); + SMP_DBG("r %16phN", r); + return err; } @@ -410,6 +414,10 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16], u8 p1[16], p2[16]; int err; + SMP_DBG("k %16phN r %16phN", k, r); + SMP_DBG("iat %u ia %6phN rat %u ra %6phN", _iat, ia, _rat, ra); + SMP_DBG("preq %7phN pres %7phN", preq, pres); + memset(p1, 0, 16); /* p1 = pres || preq || _rat || _iat */ @@ -418,10 +426,7 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16], memcpy(p1 + 2, preq, 7); memcpy(p1 + 9, pres, 7); - /* p2 = padding || ia || ra */ - memcpy(p2, ra, 6); - memcpy(p2 + 6, ia, 6); - memset(p2 + 12, 0, 4); + SMP_DBG("p1 %16phN", p1); /* res = r XOR p1 */ u128_xor((u128 *) res, (u128 *) r, (u128 *) p1); @@ -433,6 +438,13 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16], return err; } + /* p2 = padding || ia || ra */ + memcpy(p2, ra, 6); + memcpy(p2 + 6, ia, 6); + memset(p2 + 12, 0, 4); + + SMP_DBG("p2 %16phN", p2); + /* res = res XOR p2 */ u128_xor((u128 *) res, (u128 *) res, (u128 *) p2); diff --git a/net/bridge/br.c b/net/bridge/br.c index 02c24cf63c34..a1abe4936fe1 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,13 +121,13 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; -static int br_netdev_switch_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int br_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) { - struct net_device *dev = netdev_switch_notifier_info_to_dev(ptr); + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; - struct netdev_switch_notifier_fdb_info *fdb_info; + struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; rtnl_lock(); @@ -138,14 +138,14 @@ static int br_netdev_switch_event(struct notifier_block *unused, br = p->br; switch (event) { - case NETDEV_SWITCH_FDB_ADD: + case SWITCHDEV_FDB_ADD: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid); if (err) err = notifier_from_errno(err); break; - case NETDEV_SWITCH_FDB_DEL: + case SWITCHDEV_FDB_DEL: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, fdb_info->vid); @@ -159,8 +159,8 @@ out: return err; } -static struct notifier_block br_netdev_switch_notifier = { - .notifier_call = br_netdev_switch_event, +static struct notifier_block br_switchdev_notifier = { + .notifier_call = br_switchdev_event, }; static void __net_exit br_net_exit(struct net *net) @@ -214,7 +214,7 @@ static int __init br_init(void) if (err) goto err_out3; - err = register_netdev_switch_notifier(&br_netdev_switch_notifier); + err = register_switchdev_notifier(&br_switchdev_notifier); if (err) goto err_out4; @@ -235,7 +235,7 @@ static int __init br_init(void) return 0; err_out5: - unregister_netdev_switch_notifier(&br_netdev_switch_notifier); + unregister_switchdev_notifier(&br_switchdev_notifier); err_out4: unregister_netdevice_notifier(&br_device_notifier); err_out3: @@ -253,7 +253,7 @@ static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); - unregister_netdev_switch_notifier(&br_netdev_switch_notifier); + unregister_switchdev_notifier(&br_switchdev_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); unregister_pernet_subsys(&br_net_ops); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 659fb96672e4..cecb482ed919 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -736,6 +736,12 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, struct net_bridge_fdb_entry *fdb; bool modified = false; + /* If the port cannot learn allow only local and static entries */ + if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) && + !(source->state == BR_STATE_LEARNING || + source->state == BR_STATE_FORWARDING)) + return -EPERM; + fdb = fdb_find(head, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 22fd0419b314..0b38ee98024b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -975,9 +975,6 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, int err = 0; __be32 group; - if (!pskb_may_pull(skb, sizeof(*ih))) - return -EINVAL; - ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); len = sizeof(*ih); @@ -1248,25 +1245,14 @@ static int br_ip4_multicast_query(struct net_bridge *br, max_delay = 10 * HZ; group = 0; } - } else { - if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) { - err = -EINVAL; - goto out; - } - + } else if (skb->len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) goto out; max_delay = ih3->code ? IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; - } - - /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer - * all-systems destination addresses (224.0.0.1) for general queries - */ - if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) { - err = -EINVAL; + } else { goto out; } @@ -1329,12 +1315,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ - if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) { - err = -EINVAL; - goto out; - } - if (skb->len == sizeof(*mld)) { if (!pskb_may_pull(skb, sizeof(*mld))) { err = -EINVAL; @@ -1358,14 +1338,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, is_general_query = group && ipv6_addr_any(group); - /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer - * all-nodes destination address (ff02::1) for general queries - */ - if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) { - err = -EINVAL; - goto out; - } - if (is_general_query) { saddr.proto = htons(ETH_P_IPV6); saddr.u.ip6 = ip6h->saddr; @@ -1557,74 +1529,22 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, struct sk_buff *skb, u16 vid) { - struct sk_buff *skb2 = skb; - const struct iphdr *iph; + struct sk_buff *skb_trimmed = NULL; struct igmphdr *ih; - unsigned int len; - unsigned int offset; int err; - /* We treat OOM as packet loss for now. */ - if (!pskb_may_pull(skb, sizeof(*iph))) - return -EINVAL; - - iph = ip_hdr(skb); - - if (iph->ihl < 5 || iph->version != 4) - return -EINVAL; - - if (!pskb_may_pull(skb, ip_hdrlen(skb))) - return -EINVAL; - - iph = ip_hdr(skb); + err = ip_mc_check_igmp(skb, &skb_trimmed); - if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) - return -EINVAL; - - if (iph->protocol != IPPROTO_IGMP) { - if (!ipv4_is_local_multicast(iph->daddr)) + if (err == -ENOMSG) { + if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr)) BR_INPUT_SKB_CB(skb)->mrouters_only = 1; return 0; + } else if (err < 0) { + return err; } - len = ntohs(iph->tot_len); - if (skb->len < len || len < ip_hdrlen(skb)) - return -EINVAL; - - if (skb->len > len) { - skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) - return -ENOMEM; - - err = pskb_trim_rcsum(skb2, len); - if (err) - goto err_out; - } - - len -= ip_hdrlen(skb2); - offset = skb_network_offset(skb2) + ip_hdrlen(skb2); - __skb_pull(skb2, offset); - skb_reset_transport_header(skb2); - - err = -EINVAL; - if (!pskb_may_pull(skb2, sizeof(*ih))) - goto out; - - switch (skb2->ip_summed) { - case CHECKSUM_COMPLETE: - if (!csum_fold(skb2->csum)) - break; - /* fall through */ - case CHECKSUM_NONE: - skb2->csum = 0; - if (skb_checksum_complete(skb2)) - goto out; - } - - err = 0; - BR_INPUT_SKB_CB(skb)->igmp = 1; - ih = igmp_hdr(skb2); + ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: @@ -1633,21 +1553,19 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = br_ip4_multicast_add_group(br, port, ih->group, vid); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: - err = br_ip4_multicast_igmp3_report(br, port, skb2, vid); + err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: - err = br_ip4_multicast_query(br, port, skb2, vid); + err = br_ip4_multicast_query(br, port, skb_trimmed, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(br, port, ih->group, vid); break; } -out: - __skb_push(skb2, offset); -err_out: - if (skb2 != skb) - kfree_skb(skb2); + if (skb_trimmed) + kfree_skb(skb_trimmed); + return err; } @@ -1657,138 +1575,42 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, struct sk_buff *skb, u16 vid) { - struct sk_buff *skb2; - const struct ipv6hdr *ip6h; - u8 icmp6_type; - u8 nexthdr; - __be16 frag_off; - unsigned int len; - int offset; + struct sk_buff *skb_trimmed = NULL; + struct mld_msg *mld; int err; - if (!pskb_may_pull(skb, sizeof(*ip6h))) - return -EINVAL; - - ip6h = ipv6_hdr(skb); - - /* - * We're interested in MLD messages only. - * - Version is 6 - * - MLD has always Router Alert hop-by-hop option - * - But we do not support jumbrograms. - */ - if (ip6h->version != 6) - return 0; - - /* Prevent flooding this packet if there is no listener present */ - if (!ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) - BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - - if (ip6h->nexthdr != IPPROTO_HOPOPTS || - ip6h->payload_len == 0) - return 0; - - len = ntohs(ip6h->payload_len) + sizeof(*ip6h); - if (skb->len < len) - return -EINVAL; - - nexthdr = ip6h->nexthdr; - offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off); + err = ipv6_mc_check_mld(skb, &skb_trimmed); - if (offset < 0 || nexthdr != IPPROTO_ICMPV6) + if (err == -ENOMSG) { + if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; return 0; - - /* Okay, we found ICMPv6 header */ - skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) - return -ENOMEM; - - err = -EINVAL; - if (!pskb_may_pull(skb2, offset + sizeof(struct icmp6hdr))) - goto out; - - len -= offset - skb_network_offset(skb2); - - __skb_pull(skb2, offset); - skb_reset_transport_header(skb2); - skb_postpull_rcsum(skb2, skb_network_header(skb2), - skb_network_header_len(skb2)); - - icmp6_type = icmp6_hdr(skb2)->icmp6_type; - - switch (icmp6_type) { - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - case ICMPV6_MLD2_REPORT: - break; - default: - err = 0; - goto out; - } - - /* Okay, we found MLD message. Check further. */ - if (skb2->len > len) { - err = pskb_trim_rcsum(skb2, len); - if (err) - goto out; - err = -EINVAL; - } - - ip6h = ipv6_hdr(skb2); - - switch (skb2->ip_summed) { - case CHECKSUM_COMPLETE: - if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb2->len, - IPPROTO_ICMPV6, skb2->csum)) - break; - /*FALLTHROUGH*/ - case CHECKSUM_NONE: - skb2->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, - &ip6h->daddr, - skb2->len, - IPPROTO_ICMPV6, 0)); - if (__skb_checksum_complete(skb2)) - goto out; + } else if (err < 0) { + return err; } - err = 0; - BR_INPUT_SKB_CB(skb)->igmp = 1; + mld = (struct mld_msg *)skb_transport_header(skb); - switch (icmp6_type) { + switch (mld->mld_type) { case ICMPV6_MGM_REPORT: - { - struct mld_msg *mld; - if (!pskb_may_pull(skb2, sizeof(*mld))) { - err = -EINVAL; - goto out; - } - mld = (struct mld_msg *)skb_transport_header(skb2); BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid); break; - } case ICMPV6_MLD2_REPORT: - err = br_ip6_multicast_mld2_report(br, port, skb2, vid); + err = br_ip6_multicast_mld2_report(br, port, skb_trimmed, vid); break; case ICMPV6_MGM_QUERY: - err = br_ip6_multicast_query(br, port, skb2, vid); + err = br_ip6_multicast_query(br, port, skb_trimmed, vid); break; case ICMPV6_MGM_REDUCTION: - { - struct mld_msg *mld; - if (!pskb_may_pull(skb2, sizeof(*mld))) { - err = -EINVAL; - goto out; - } - mld = (struct mld_msg *)skb_transport_header(skb2); br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid); - } + break; } -out: - kfree_skb(skb2); + if (skb_trimmed) + kfree_skb(skb_trimmed); + return err; } #endif @@ -1950,11 +1772,9 @@ out: int br_multicast_set_router(struct net_bridge *br, unsigned long val) { - int err = -ENOENT; + int err = -EINVAL; spin_lock_bh(&br->multicast_lock); - if (!netif_running(br->dev)) - goto unlock; switch (val) { case 0: @@ -1965,13 +1785,8 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) br->multicast_router = val; err = 0; break; - - default: - err = -EINVAL; - break; } -unlock: spin_unlock_bh(&br->multicast_lock); return err; @@ -1980,11 +1795,9 @@ unlock: int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) { struct net_bridge *br = p->br; - int err = -ENOENT; + int err = -EINVAL; spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED) - goto unlock; switch (val) { case 0: @@ -2006,13 +1819,8 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) br_multicast_add_router(br, p); break; - - default: - err = -EINVAL; - break; } -unlock: spin_unlock(&br->multicast_lock); return err; @@ -2117,15 +1925,11 @@ unlock: int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) { - int err = -ENOENT; + int err = -EINVAL; u32 old; struct net_bridge_mdb_htable *mdb; spin_lock_bh(&br->multicast_lock); - if (!netif_running(br->dev)) - goto unlock; - - err = -EINVAL; if (!is_power_of_2(val)) goto unlock; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 60ddfbeb47f5..46660a28feef 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -125,6 +125,14 @@ static struct nf_bridge_info *nf_bridge_info_get(const struct sk_buff *skb) return skb->nf_bridge; } +static void nf_bridge_info_free(struct sk_buff *skb) +{ + if (skb->nf_bridge) { + nf_bridge_put(skb->nf_bridge); + skb->nf_bridge = NULL; + } +} + static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) { struct net_bridge_port *port; @@ -832,17 +840,39 @@ static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb) skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size); __skb_push(skb, data->encap_size); + nf_bridge_info_free(skb); return br_dev_queue_push_xmit(sk, skb); } +static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)) +{ + unsigned int mtu = ip_skb_dst_mtu(skb); + struct iphdr *iph = ip_hdr(skb); + struct rtable *rt = skb_rtable(skb); + struct net_device *dev = rt->dst.dev; + + if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || + (IPCB(skb)->frag_max_size && + IPCB(skb)->frag_max_size > mtu))) { + IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + kfree_skb(skb); + return -EMSGSIZE; + } + + return ip_do_fragment(sk, skb, output); +} + static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) { int ret; int frag_max_size; unsigned int mtu_reserved; - if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP)) + if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP)) { + nf_bridge_info_free(skb); return br_dev_queue_push_xmit(sk, skb); + } mtu_reserved = nf_bridge_mtu_reduction(skb); /* This is wrong! We should preserve the original fragment @@ -866,8 +896,9 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - ret = ip_fragment(sk, skb, br_nf_push_frag_xmit); + ret = br_nf_ip_fragment(sk, skb, br_nf_push_frag_xmit); } else { + nf_bridge_info_free(skb); ret = br_dev_queue_push_xmit(sk, skb); } @@ -876,7 +907,8 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) #else static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) { - return br_dev_queue_push_xmit(sk, skb); + nf_bridge_info_free(skb); + return br_dev_queue_push_xmit(sk, skb); } #endif @@ -964,6 +996,8 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) nf_bridge->neigh_header, ETH_HLEN - ETH_ALEN); skb->dev = nf_bridge->physindev; + + nf_bridge->physoutdev = NULL; br_handle_frame_finish(NULL, skb); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4b5c236998ff..6b67ed3831de 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -586,7 +586,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) struct nlattr *afspec; struct net_bridge_port *p; struct nlattr *tb[IFLA_BRPORT_MAX + 1]; - int err = 0, ret_offload = 0; + int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); @@ -628,16 +628,6 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) afspec, RTM_SETLINK); } - if (p && !(flags & BRIDGE_FLAGS_SELF)) { - /* set bridge attributes in hardware if supported - */ - ret_offload = netdev_switch_port_bridge_setlink(dev, nlh, - flags); - if (ret_offload && ret_offload != -EOPNOTSUPP) - br_warn(p->br, "error setting attrs on port %u(%s)\n", - (unsigned int)p->port_no, p->dev->name); - } - if (err == 0) br_ifinfo_notify(RTM_NEWLINK, p); out: @@ -649,7 +639,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct nlattr *afspec; struct net_bridge_port *p; - int err = 0, ret_offload = 0; + int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) @@ -668,16 +658,6 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) */ br_ifinfo_notify(RTM_NEWLINK, p); - if (p && !(flags & BRIDGE_FLAGS_SELF)) { - /* del bridge attributes in hardware - */ - ret_offload = netdev_switch_port_bridge_dellink(dev, nlh, - flags); - if (ret_offload && ret_offload != -EOPNOTSUPP) - br_warn(p->br, "error deleting attrs on port %u (%s)\n", - (unsigned int)p->port_no, p->dev->name); - } - return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[]) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3362c29400f1..1f36fa70639b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -33,8 +33,8 @@ /* Control of forwarding link local multicast */ #define BR_GROUPFWD_DEFAULT 0 -/* Don't allow forwarding control protocols like STP and LLDP */ -#define BR_GROUPFWD_RESTRICTED 0x4007u +/* Don't allow forwarding of control protocols like STP, MAC PAUSE and LACP */ +#define BR_GROUPFWD_RESTRICTED 0x0007u /* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */ #define BR_GROUPFWD_8021AD 0xB801u diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index fb3ebe615513..45f1ff113af9 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -39,10 +39,14 @@ void br_log_state(const struct net_bridge_port *p) void br_set_state(struct net_bridge_port *p, unsigned int state) { + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_STP_STATE, + .u.stp_state = state, + }; int err; p->state = state; - err = netdev_switch_port_stp_update(p->dev, state); + err = switchdev_port_attr_set(p->dev, &attr); if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 071d87214dde..0c40570069ba 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -164,8 +164,10 @@ static int ebt_stp_mt_check(const struct xt_mtchk_param *par) !(info->bitmask & EBT_STP_MASK)) return -EINVAL; /* Make sure the match only receives stp frames */ - if (!ether_addr_equal(e->destmac, bridge_ula) || - !ether_addr_equal(e->destmsk, msk) || !(e->bitmask & EBT_DESTMAC)) + if (!par->nft_compat && + (!ether_addr_equal(e->destmac, bridge_ula) || + !ether_addr_equal(e->destmsk, msk) || + !(e->bitmask & EBT_DESTMAC))) return -EINVAL; return 0; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 91180a7fc943..5149d9e71114 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -139,7 +139,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, ethproto = h->h_proto; if (e->bitmask & EBT_802_3) { - if (FWINV2(ntohs(ethproto) >= ETH_P_802_3_MIN, EBT_IPROTO)) + if (FWINV2(eth_proto_is_802_3(ethproto), EBT_IPROTO)) return 1; } else if (!(e->bitmask & EBT_NOPROTO) && FWINV2(e->ethproto != ethproto, EBT_IPROTO)) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 112ad784838a..3cc71b9f5517 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -1055,7 +1055,7 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, * is really not used at all in the net/core or socket.c but the * initialization makes sure that sock->state is not uninitialized. */ - sk = sk_alloc(net, PF_CAIF, GFP_KERNEL, &prot); + sk = sk_alloc(net, PF_CAIF, GFP_KERNEL, &prot, kern); if (!sk) return -ENOMEM; diff --git a/net/can/af_can.c b/net/can/af_can.c index 32d710eaf1fc..d4d404bdfc9a 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -179,7 +179,7 @@ static int can_create(struct net *net, struct socket *sock, int protocol, sock->ops = cp->ops; - sk = sk_alloc(net, PF_CAN, GFP_KERNEL, cp->prot); + sk = sk_alloc(net, PF_CAN, GFP_KERNEL, cp->prot, kern); if (!sk) { err = -ENOMEM; goto errout; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 967080a9f043..073262fea6dd 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -480,8 +480,8 @@ static int ceph_tcp_connect(struct ceph_connection *con) int ret; BUG_ON(con->sock); - ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM, - IPPROTO_TCP, &sock); + ret = sock_create_kern(&init_net, con->peer_addr.in_addr.ss_family, + SOCK_STREAM, IPPROTO_TCP, &sock); if (ret) return ret; sock->sk->sk_allocation = GFP_NOFS; diff --git a/net/core/dev.c b/net/core/dev.c index aa82f9ab6a36..6778a9999d52 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -135,6 +135,7 @@ #include <linux/if_macvlan.h> #include <linux/errqueue.h> #include <linux/hrtimer.h> +#include <linux/netfilter_ingress.h> #include "net-sysfs.h" @@ -468,10 +469,14 @@ EXPORT_SYMBOL(dev_remove_pack); */ void dev_add_offload(struct packet_offload *po) { - struct list_head *head = &offload_base; + struct packet_offload *elem; spin_lock(&offload_lock); - list_add_rcu(&po->list, head); + list_for_each_entry(elem, &offload_base, list) { + if (po->priority < elem->priority) + break; + } + list_add_rcu(&po->list, elem->list.prev); spin_unlock(&offload_lock); } EXPORT_SYMBOL(dev_add_offload); @@ -1630,7 +1635,7 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) } EXPORT_SYMBOL(call_netdevice_notifiers); -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_INGRESS static struct static_key ingress_needed __read_mostly; void net_inc_ingress_queue(void) @@ -2343,6 +2348,34 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, + unsigned int num_tx_queues) +{ + u32 hash; + u16 qoffset = 0; + u16 qcount = num_tx_queues; + + if (skb_rx_queue_recorded(skb)) { + hash = skb_get_rx_queue(skb); + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; + return hash; + } + + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; + qcount = dev->tc_to_txq[tc].count; + } + + return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; +} +EXPORT_SYMBOL(__skb_tx_hash); + static void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features = 0; @@ -2901,6 +2934,84 @@ int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(dev_loopback_xmit); +static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[skb->sender_cpu - 1]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else + queue_index = map->queues[reciprocal_scale(skb_get_hash(skb), + map->len)]; + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); + + return queue_index; +#else + return -1; +#endif +} + +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + int queue_index = sk_tx_queue_get(sk); + + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int new_index = get_xps_queue(dev, skb); + if (new_index < 0) + new_index = skb_tx_hash(dev, skb); + + if (queue_index != new_index && sk && + rcu_access_pointer(sk->sk_dst_cache)) + sk_tx_queue_set(sk, new_index); + + queue_index = new_index; + } + + return queue_index; +} + +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb, + void *accel_priv) +{ + int queue_index = 0; + +#ifdef CONFIG_XPS + if (skb->sender_cpu == 0) + skb->sender_cpu = raw_smp_processor_id() + 1; +#endif + + if (dev->real_num_tx_queues != 1) { + const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); + else + queue_index = __netdev_pick_tx(dev, skb); + + if (!accel_priv) + queue_index = netdev_cap_txqueue(dev, queue_index); + } + + skb_set_queue_mapping(skb, queue_index); + return netdev_get_tx_queue(dev, queue_index); +} + /** * __dev_queue_xmit - transmit a buffer * @skb: buffer to transmit @@ -3513,66 +3624,47 @@ int (*br_fdb_test_addr_hook)(struct net_device *dev, EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif -#ifdef CONFIG_NET_CLS_ACT -/* TODO: Maybe we should just force sch_ingress to be compiled in - * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions - * a compare and 2 stores extra right now if we dont have it on - * but have CONFIG_NET_CLS_ACT - * NOTE: This doesn't stop any functionality; if you dont have - * the ingress scheduler, you just can't add policies on ingress. - * - */ -static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) -{ - struct net_device *dev = skb->dev; - u32 ttl = G_TC_RTTL(skb->tc_verd); - int result = TC_ACT_OK; - struct Qdisc *q; - - if (unlikely(MAX_RED_LOOP < ttl++)) { - net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n", - skb->skb_iif, dev->ifindex); - return TC_ACT_SHOT; - } - - skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl); - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); - - q = rcu_dereference(rxq->qdisc); - if (q != &noop_qdisc) { - spin_lock(qdisc_lock(q)); - if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) - result = qdisc_enqueue_root(skb, q); - spin_unlock(qdisc_lock(q)); - } - - return result; -} - static inline struct sk_buff *handle_ing(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { - struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue); +#ifdef CONFIG_NET_CLS_ACT + struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list); + struct tcf_result cl_res; - if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc) + /* If there's at least one ingress present somewhere (so + * we get here via enabled static key), remaining devices + * that are not configured with an ingress qdisc will bail + * out here. + */ + if (!cl) return skb; - if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } - switch (ing_filter(skb, rxq)) { + qdisc_skb_cb(skb)->pkt_len = skb->len; + skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); + qdisc_bstats_update_cpu(cl->q, skb); + + switch (tc_classify(skb, cl, &cl_res)) { + case TC_ACT_OK: + case TC_ACT_RECLASSIFY: + skb->tc_index = TC_H_MIN(cl_res.classid); + break; case TC_ACT_SHOT: + qdisc_qstats_drop_cpu(cl->q); case TC_ACT_STOLEN: + case TC_ACT_QUEUED: kfree_skb(skb); return NULL; + default: + break; } - +#endif /* CONFIG_NET_CLS_ACT */ return skb; } -#endif /** * netdev_rx_handler_register - register receive handler @@ -3645,6 +3737,22 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) } } +static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, + int *ret, struct net_device *orig_dev) +{ +#ifdef CONFIG_NETFILTER_INGRESS + if (nf_hook_ingress_active(skb)) { + if (*pt_prev) { + *ret = deliver_skb(skb, *pt_prev, orig_dev); + *pt_prev = NULL; + } + + return nf_hook_ingress(skb); + } +#endif /* CONFIG_NETFILTER_INGRESS */ + return 0; +} + static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) { struct packet_type *ptype, *pt_prev; @@ -3704,13 +3812,17 @@ another_round: } skip_taps: -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_INGRESS if (static_key_false(&ingress_needed)) { skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) goto unlock; - } + if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) + goto unlock; + } +#endif +#ifdef CONFIG_NET_CLS_ACT skb->tc_verd = 0; ncls: #endif @@ -6313,6 +6425,17 @@ static int netif_alloc_netdev_queues(struct net_device *dev) return 0; } +void netif_tx_stop_all_queues(struct net_device *dev) +{ + unsigned int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + netif_tx_stop_queue(txq); + } +} +EXPORT_SYMBOL(netif_tx_stop_all_queues); + /** * register_netdevice - register a network device * @dev: device to register @@ -6862,6 +6985,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; + + nf_hook_ingress_init(dev); + return dev; free_all: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 1d00b8922902..eb0c3ace7458 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -98,7 +98,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", [NETIF_F_BUSY_POLL_BIT] = "busy-poll", - [NETIF_F_HW_SWITCH_OFFLOAD_BIT] = "hw-switch-offload", }; static const char diff --git a/net/core/filter.c b/net/core/filter.c index bf831a85c315..d271c06bf01f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -36,6 +36,7 @@ #include <net/netlink.h> #include <linux/skbuff.h> #include <net/sock.h> +#include <net/flow_dissector.h> #include <linux/errno.h> #include <linux/timer.h> #include <asm/uaccess.h> @@ -45,6 +46,7 @@ #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> +#include <net/sch_generic.h> /** * sk_filter - run a packet through a socket filter @@ -355,8 +357,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * for socket filters: ctx == 'struct sk_buff *', for seccomp: * ctx == 'struct seccomp_data *'. */ -int bpf_convert_filter(struct sock_filter *prog, int len, - struct bpf_insn *new_prog, int *new_len) +static int bpf_convert_filter(struct sock_filter *prog, int len, + struct bpf_insn *new_prog, int *new_len) { int new_flen = 0, pass = 0, target, i; struct bpf_insn *new_insn; @@ -371,7 +373,8 @@ int bpf_convert_filter(struct sock_filter *prog, int len, return -EINVAL; if (new_prog) { - addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL); + addrs = kcalloc(len, sizeof(*addrs), + GFP_KERNEL | __GFP_NOWARN); if (!addrs) return -ENOMEM; } @@ -751,7 +754,8 @@ static bool chk_code_allowed(u16 code_to_probe) * * Returns 0 if the rule set is legal or -EINVAL if not. */ -int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) +static int bpf_check_classic(const struct sock_filter *filter, + unsigned int flen) { bool anc_found; int pc; @@ -825,7 +829,6 @@ int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) return -EINVAL; } -EXPORT_SYMBOL(bpf_check_classic); static int bpf_prog_store_orig_filter(struct bpf_prog *fp, const struct sock_fprog *fprog) @@ -839,7 +842,9 @@ static int bpf_prog_store_orig_filter(struct bpf_prog *fp, fkprog = fp->orig_prog; fkprog->len = fprog->len; - fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL); + + fkprog->filter = kmemdup(fp->insns, fsize, + GFP_KERNEL | __GFP_NOWARN); if (!fkprog->filter) { kfree(fp->orig_prog); return -ENOMEM; @@ -941,7 +946,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) * pass. At this time, the user BPF is stored in fp->insns. */ old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; @@ -988,7 +993,8 @@ out_err: return ERR_PTR(err); } -static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp) +static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, + bpf_aux_classic_check_t trans) { int err; @@ -1001,6 +1007,17 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp) return ERR_PTR(err); } + /* There might be additional checks and transformations + * needed on classic filters, f.e. in case of seccomp. + */ + if (trans) { + err = trans(fp->insns, fp->len); + if (err) { + __bpf_prog_release(fp); + return ERR_PTR(err); + } + } + /* Probe if we can JIT compile the filter and if so, do * the compilation of the filter. */ @@ -1050,7 +1067,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - fp = bpf_prepare_filter(fp); + fp = bpf_prepare_filter(fp, NULL); if (IS_ERR(fp)) return PTR_ERR(fp); @@ -1059,6 +1076,53 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) } EXPORT_SYMBOL_GPL(bpf_prog_create); +/** + * bpf_prog_create_from_user - create an unattached filter from user buffer + * @pfp: the unattached filter that is created + * @fprog: the filter program + * @trans: post-classic verifier transformation handler + * + * This function effectively does the same as bpf_prog_create(), only + * that it builds up its insns buffer from user space provided buffer. + * It also allows for passing a bpf_aux_classic_check_t handler. + */ +int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, + bpf_aux_classic_check_t trans) +{ + unsigned int fsize = bpf_classic_proglen(fprog); + struct bpf_prog *fp; + + /* Make sure new filter is there and in the right amounts. */ + if (fprog->filter == NULL) + return -EINVAL; + + fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); + if (!fp) + return -ENOMEM; + + if (copy_from_user(fp->insns, fprog->filter, fsize)) { + __bpf_prog_free(fp); + return -EFAULT; + } + + fp->len = fprog->len; + /* Since unattached filters are not copied back to user + * space through sk_get_filter(), we do not need to hold + * a copy here, and can spare us the work. + */ + fp->orig_prog = NULL; + + /* bpf_prepare_filter() already takes care of freeing + * memory in case something goes wrong. + */ + fp = bpf_prepare_filter(fp, trans); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + *pfp = fp; + return 0; +} + void bpf_prog_destroy(struct bpf_prog *fp) { __bpf_prog_release(fp); @@ -1135,7 +1199,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - prog = bpf_prepare_filter(prog); + prog = bpf_prepare_filter(prog, NULL); if (IS_ERR(prog)) return PTR_ERR(prog); @@ -1175,21 +1239,6 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) return 0; } -/** - * bpf_skb_clone_not_writable - is the header of a clone not writable - * @skb: buffer to check - * @len: length up to which to write, can be negative - * - * Returns true if modifying the header part of the cloned buffer - * does require the data to be copied. I.e. this version works with - * negative lengths needed for eBPF case! - */ -static bool bpf_skb_clone_unwritable(const struct sk_buff *skb, int len) -{ - return skb_header_cloned(skb) || - (int) skb_headroom(skb) + len > skb->hdr_len; -} - #define BPF_RECOMPUTE_CSUM(flags) ((flags) & 1) static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) @@ -1212,9 +1261,8 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) if (unlikely((u32) offset > 0xffff || len > sizeof(buf))) return -EFAULT; - offset -= skb->data - skb_mac_header(skb); if (unlikely(skb_cloned(skb) && - bpf_skb_clone_unwritable(skb, offset + len))) + !skb_clone_writable(skb, offset + len))) return -EFAULT; ptr = skb_header_pointer(skb, offset, len, buf); @@ -1258,9 +1306,8 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (unlikely((u32) offset > 0xffff)) return -EFAULT; - offset -= skb->data - skb_mac_header(skb); if (unlikely(skb_cloned(skb) && - bpf_skb_clone_unwritable(skb, offset + sizeof(sum)))) + !skb_clone_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1306,9 +1353,8 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (unlikely((u32) offset > 0xffff)) return -EFAULT; - offset -= skb->data - skb_mac_header(skb); if (unlikely(skb_cloned(skb) && - bpf_skb_clone_unwritable(skb, offset + sizeof(sum)))) + !skb_clone_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1344,6 +1390,40 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; +#define BPF_IS_REDIRECT_INGRESS(flags) ((flags) & 1) + +static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2; + struct net_device *dev; + + dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); + if (unlikely(!dev)) + return -EINVAL; + + if (unlikely(!(dev->flags & IFF_UP))) + return -EINVAL; + + skb2 = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!skb2)) + return -ENOMEM; + + if (BPF_IS_REDIRECT_INGRESS(flags)) + return dev_forward_skb(dev, skb2); + + skb2->dev = dev; + return dev_queue_xmit(skb2); +} + +const struct bpf_func_proto bpf_clone_redirect_proto = { + .func = bpf_clone_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id) { @@ -1358,6 +1438,10 @@ sk_filter_func_proto(enum bpf_func_id func_id) return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_tail_call: + return &bpf_tail_call_proto; + case BPF_FUNC_ktime_get_ns: + return &bpf_ktime_get_ns_proto; default: return NULL; } @@ -1373,18 +1457,15 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; + case BPF_FUNC_clone_redirect: + return &bpf_clone_redirect_proto; default: return sk_filter_func_proto(func_id); } } -static bool sk_filter_is_valid_access(int off, int size, - enum bpf_access_type type) +static bool __is_valid_access(int off, int size, enum bpf_access_type type) { - /* only read is allowed */ - if (type != BPF_READ) - return false; - /* check bounds */ if (off < 0 || off >= sizeof(struct __sk_buff)) return false; @@ -1400,8 +1481,42 @@ static bool sk_filter_is_valid_access(int off, int size, return true; } -static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, - struct bpf_insn *insn_buf) +static bool sk_filter_is_valid_access(int off, int size, + enum bpf_access_type type) +{ + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct __sk_buff, cb[0]) ... + offsetof(struct __sk_buff, cb[4]): + break; + default: + return false; + } + } + + return __is_valid_access(off, size, type); +} + +static bool tc_cls_act_is_valid_access(int off, int size, + enum bpf_access_type type) +{ + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct __sk_buff, mark): + case offsetof(struct __sk_buff, tc_index): + case offsetof(struct __sk_buff, cb[0]) ... + offsetof(struct __sk_buff, cb[4]): + break; + default: + return false; + } + } + return __is_valid_access(off, size, type); +} + +static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, + int src_reg, int ctx_off, + struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; @@ -1434,8 +1549,34 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, offsetof(struct sk_buff, priority)); break; + case offsetof(struct __sk_buff, ingress_ifindex): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, skb_iif) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, skb_iif)); + break; + + case offsetof(struct __sk_buff, ifindex): + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + dst_reg, src_reg, + offsetof(struct sk_buff, dev)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg, + offsetof(struct net_device, ifindex)); + break; + case offsetof(struct __sk_buff, mark): - return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn); + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, mark)); + else + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, mark)); + break; case offsetof(struct __sk_buff, pkt_type): return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn); @@ -1450,6 +1591,38 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, case offsetof(struct __sk_buff, vlan_tci): return convert_skb_access(SKF_AD_VLAN_TAG, dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, cb[0]) ... + offsetof(struct __sk_buff, cb[4]): + BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + + ctx_off -= offsetof(struct __sk_buff, cb[0]); + ctx_off += offsetof(struct sk_buff, cb); + ctx_off += offsetof(struct qdisc_skb_cb, data); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, ctx_off); + else + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off); + break; + + case offsetof(struct __sk_buff, tc_index): +#ifdef CONFIG_NET_SCHED + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2); + + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, tc_index)); + else + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, tc_index)); + break; +#else + if (type == BPF_WRITE) + *insn++ = BPF_MOV64_REG(dst_reg, dst_reg); + else + *insn++ = BPF_MOV64_IMM(dst_reg, 0); + break; +#endif } return insn - insn_buf; @@ -1458,13 +1631,13 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, static const struct bpf_verifier_ops sk_filter_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, - .convert_ctx_access = sk_filter_convert_ctx_access, + .convert_ctx_access = bpf_net_convert_ctx_access, }; static const struct bpf_verifier_ops tc_cls_act_ops = { .get_func_proto = tc_cls_act_func_proto, - .is_valid_access = sk_filter_is_valid_access, - .convert_ctx_access = sk_filter_convert_ctx_access, + .is_valid_access = tc_cls_act_is_valid_access, + .convert_ctx_access = bpf_net_convert_ctx_access, }; static struct bpf_prog_type_list sk_filter_type __read_mostly = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2c35c02a931e..77e22e4fc898 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1,3 +1,4 @@ +#include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/export.h> #include <linux/ip.h> @@ -12,19 +13,60 @@ #include <linux/if_tunnel.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> -#include <net/flow_keys.h> +#include <linux/stddef.h> +#include <linux/if_ether.h> +#include <linux/mpls.h> +#include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> -/* copy saddr & daddr, possibly using 64bit load/store - * Equivalent to : flow->src = iph->saddr; - * flow->dst = iph->daddr; - */ -static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph) +static bool skb_flow_dissector_uses_key(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) { - BUILD_BUG_ON(offsetof(typeof(*flow), dst) != - offsetof(typeof(*flow), src) + sizeof(flow->src)); - memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst)); + return flow_dissector->used_keys & (1 << key_id); +} + +static void skb_flow_dissector_set_key(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) +{ + flow_dissector->used_keys |= (1 << key_id); +} + +static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id, + void *target_container) +{ + return ((char *) target_container) + flow_dissector->offset[key_id]; +} + +void skb_flow_dissector_init(struct flow_dissector *flow_dissector, + const struct flow_dissector_key *key, + unsigned int key_count) +{ + unsigned int i; + + memset(flow_dissector, 0, sizeof(*flow_dissector)); + + for (i = 0; i < key_count; i++, key++) { + /* User should make sure that every key target offset is withing + * boundaries of unsigned short. + */ + BUG_ON(key->offset > USHRT_MAX); + BUG_ON(skb_flow_dissector_uses_key(flow_dissector, + key->key_id)); + + skb_flow_dissector_set_key(flow_dissector, key->key_id); + flow_dissector->offset[key->key_id] = key->offset; + } + + /* Ensure that the dissector always includes control and basic key. + * That way we are able to avoid handling lack of these in fast path. + */ + BUG_ON(!skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_CONTROL)); + BUG_ON(!skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_BASIC)); } +EXPORT_SYMBOL(skb_flow_dissector_init); /** * __skb_flow_get_ports - extract the upper layer ports and return them @@ -63,17 +105,30 @@ EXPORT_SYMBOL(__skb_flow_get_ports); /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified + * @flow_dissector: list of keys to dissect + * @target_container: target structure to put dissected values into * @data: raw buffer pointer to the packet, if NULL use skb->data * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb) * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * - * The function will try to retrieve the struct flow_keys from either the skbuff - * or a raw buffer specified by the rest parameters + * The function will try to retrieve individual keys into target specified + * by flow_dissector from either the skbuff or a raw buffer specified by the + * rest parameters. + * + * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, +bool __skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, __be16 proto, int nhoff, int hlen) { + struct flow_dissector_key_control *key_control; + struct flow_dissector_key_basic *key_basic; + struct flow_dissector_key_addrs *key_addrs; + struct flow_dissector_key_ports *key_ports; + struct flow_dissector_key_tags *key_tags; + struct flow_dissector_key_keyid *key_keyid; u8 ip_proto; if (!data) { @@ -83,7 +138,30 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, hlen = skb_headlen(skb); } - memset(flow, 0, sizeof(*flow)); + /* It is ensured by skb_flow_dissector_init() that control key will + * be always present. + */ + key_control = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_CONTROL, + target_container); + + /* It is ensured by skb_flow_dissector_init() that basic key will + * be always present. + */ + key_basic = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_BASIC, + target_container); + + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct ethhdr *eth = eth_hdr(skb); + struct flow_dissector_key_eth_addrs *key_eth_addrs; + + key_eth_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + target_container); + memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs)); + } again: switch (proto) { @@ -100,14 +178,15 @@ ip: if (ip_is_fragment(iph)) ip_proto = 0; - /* skip the address processing if skb is NULL. The assumption - * here is that if there is no skb we are not looking for flow - * info but lengths and protocols. - */ - if (!skb) + if (!skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS)) break; - iph_to_flow_copy_addrs(flow, iph); + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); + memcpy(&key_addrs->v4addrs, &iph->saddr, + sizeof(key_addrs->v4addrs)); + key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; break; } case htons(ETH_P_IPV6): { @@ -123,25 +202,27 @@ ipv6: ip_proto = iph->nexthdr; nhoff += sizeof(struct ipv6hdr); - /* see comment above in IPv4 section */ - if (!skb) - break; + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_dissector_key_ipv6_addrs *key_ipv6_addrs; - flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr); - flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); + key_ipv6_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + target_container); + + memcpy(key_ipv6_addrs, &iph->saddr, sizeof(*key_ipv6_addrs)); + key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + } flow_label = ip6_flowlabel(iph); if (flow_label) { - /* Awesome, IPv6 packet has a flow label so we can - * use that to represent the ports without any - * further dissection. - */ - flow->n_proto = proto; - flow->ip_proto = ip_proto; - flow->ports = flow_label; - flow->thoff = (u16)nhoff; - - return true; + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL)) { + key_tags = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL, + target_container); + key_tags->flow_label = ntohl(flow_label); + } } break; @@ -155,6 +236,15 @@ ipv6: if (!vlan) return false; + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_VLANID)) { + key_tags = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_VLANID, + target_container); + + key_tags->vlan_id = skb_vlan_tag_get_id(skb); + } + proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); goto again; @@ -186,14 +276,52 @@ ipv6: hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return false; - flow->src = hdr->srcnode; - flow->dst = 0; - flow->n_proto = proto; - flow->thoff = (u16)nhoff; + key_basic->n_proto = proto; + key_control->thoff = (u16)nhoff; + + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_TIPC_ADDRS)) { + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_TIPC_ADDRS, + target_container); + key_addrs->tipcaddrs.srcnode = hdr->srcnode; + key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC_ADDRS; + } return true; } + + case htons(ETH_P_MPLS_UC): + case htons(ETH_P_MPLS_MC): { + struct mpls_label *hdr, _hdr[2]; +mpls: + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, + hlen, &_hdr); + if (!hdr) + return false; + + if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) == + MPLS_LABEL_ENTROPY) { + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { + key_keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY, + target_container); + key_keyid->keyid = hdr[1].entry & + htonl(MPLS_LS_LABEL_MASK); + } + + key_basic->n_proto = proto; + key_basic->ip_proto = ip_proto; + key_control->thoff = (u16)nhoff; + + return true; + } + + return true; + } + case htons(ETH_P_FCOE): - flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN); + key_control->thoff = (u16)(nhoff + FCOE_HEADER_LEN); /* fall through */ default: return false; @@ -213,30 +341,47 @@ ipv6: * Only look inside GRE if version zero and no * routing */ - if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) { - proto = hdr->proto; + if (hdr->flags & (GRE_VERSION | GRE_ROUTING)) + break; + + proto = hdr->proto; + nhoff += 4; + if (hdr->flags & GRE_CSUM) nhoff += 4; - if (hdr->flags & GRE_CSUM) - nhoff += 4; - if (hdr->flags & GRE_KEY) - nhoff += 4; - if (hdr->flags & GRE_SEQ) - nhoff += 4; - if (proto == htons(ETH_P_TEB)) { - const struct ethhdr *eth; - struct ethhdr _eth; - - eth = __skb_header_pointer(skb, nhoff, - sizeof(_eth), - data, hlen, &_eth); - if (!eth) - return false; - proto = eth->h_proto; - nhoff += sizeof(*eth); + if (hdr->flags & GRE_KEY) { + const __be32 *keyid; + __be32 _keyid; + + keyid = __skb_header_pointer(skb, nhoff, sizeof(_keyid), + data, hlen, &_keyid); + + if (!keyid) + return false; + + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID)) { + key_keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID, + target_container); + key_keyid->keyid = *keyid; } - goto again; + nhoff += 4; } - break; + if (hdr->flags & GRE_SEQ) + nhoff += 4; + if (proto == htons(ETH_P_TEB)) { + const struct ethhdr *eth; + struct ethhdr _eth; + + eth = __skb_header_pointer(skb, nhoff, + sizeof(_eth), + data, hlen, &_eth); + if (!eth) + return false; + proto = eth->h_proto; + nhoff += sizeof(*eth); + } + goto again; } case IPPROTO_IPIP: proto = htons(ETH_P_IP); @@ -244,18 +389,25 @@ ipv6: case IPPROTO_IPV6: proto = htons(ETH_P_IPV6); goto ipv6; + case IPPROTO_MPLS: + proto = htons(ETH_P_MPLS_UC); + goto mpls; default: break; } - flow->n_proto = proto; - flow->ip_proto = ip_proto; - flow->thoff = (u16) nhoff; - - /* unless skb is set we don't need to record port info */ - if (skb) - flow->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); + key_basic->n_proto = proto; + key_basic->ip_proto = ip_proto; + key_control->thoff = (u16)nhoff; + + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS)) { + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); + key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, + data, hlen); + } return true; } @@ -267,27 +419,109 @@ static __always_inline void __flow_hash_secret_init(void) net_get_random_once(&hashrnd, sizeof(hashrnd)); } -static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c) +static __always_inline u32 __flow_hash_words(u32 *words, u32 length, u32 keyval) { - __flow_hash_secret_init(); - return jhash_3words(a, b, c, hashrnd); + return jhash2(words, length, keyval); } -static inline u32 __flow_hash_from_keys(struct flow_keys *keys) +static inline void *flow_keys_hash_start(struct flow_keys *flow) { - u32 hash; + BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32)); + return (void *)flow + FLOW_KEYS_HASH_OFFSET; +} - /* get a consistent hash (same value on both flow directions) */ - if (((__force u32)keys->dst < (__force u32)keys->src) || - (((__force u32)keys->dst == (__force u32)keys->src) && - ((__force u16)keys->port16[1] < (__force u16)keys->port16[0]))) { - swap(keys->dst, keys->src); - swap(keys->port16[0], keys->port16[1]); +static inline size_t flow_keys_hash_length(struct flow_keys *flow) +{ + size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); + BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); + BUILD_BUG_ON(offsetof(typeof(*flow), addrs) != + sizeof(*flow) - sizeof(flow->addrs)); + + switch (flow->control.addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + diff -= sizeof(flow->addrs.v4addrs); + break; + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + diff -= sizeof(flow->addrs.v6addrs); + break; + case FLOW_DISSECTOR_KEY_TIPC_ADDRS: + diff -= sizeof(flow->addrs.tipcaddrs); + break; } + return (sizeof(*flow) - diff) / sizeof(u32); +} - hash = __flow_hash_3words((__force u32)keys->dst, - (__force u32)keys->src, - (__force u32)keys->ports); +__be32 flow_get_u32_src(const struct flow_keys *flow) +{ + switch (flow->control.addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + return flow->addrs.v4addrs.src; + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + return (__force __be32)ipv6_addr_hash( + &flow->addrs.v6addrs.src); + case FLOW_DISSECTOR_KEY_TIPC_ADDRS: + return flow->addrs.tipcaddrs.srcnode; + default: + return 0; + } +} +EXPORT_SYMBOL(flow_get_u32_src); + +__be32 flow_get_u32_dst(const struct flow_keys *flow) +{ + switch (flow->control.addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + return flow->addrs.v4addrs.dst; + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + return (__force __be32)ipv6_addr_hash( + &flow->addrs.v6addrs.dst); + default: + return 0; + } +} +EXPORT_SYMBOL(flow_get_u32_dst); + +static inline void __flow_hash_consistentify(struct flow_keys *keys) +{ + int addr_diff, i; + + switch (keys->control.addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + addr_diff = (__force u32)keys->addrs.v4addrs.dst - + (__force u32)keys->addrs.v4addrs.src; + if ((addr_diff < 0) || + (addr_diff == 0 && + ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src))) { + swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); + swap(keys->ports.src, keys->ports.dst); + } + break; + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + addr_diff = memcmp(&keys->addrs.v6addrs.dst, + &keys->addrs.v6addrs.src, + sizeof(keys->addrs.v6addrs.dst)); + if ((addr_diff < 0) || + (addr_diff == 0 && + ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src))) { + for (i = 0; i < 4; i++) + swap(keys->addrs.v6addrs.src.s6_addr32[i], + keys->addrs.v6addrs.dst.s6_addr32[i]); + swap(keys->ports.src, keys->ports.dst); + } + break; + } +} + +static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) +{ + u32 hash; + + __flow_hash_consistentify(keys); + + hash = __flow_hash_words((u32 *)flow_keys_hash_start(keys), + flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; @@ -296,12 +530,52 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys) u32 flow_hash_from_keys(struct flow_keys *keys) { - return __flow_hash_from_keys(keys); + __flow_hash_secret_init(); + return __flow_hash_from_keys(keys, hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); -/* - * __skb_get_hash: calculate a flow hash based on src/dst addresses +static inline u32 ___skb_get_hash(const struct sk_buff *skb, + struct flow_keys *keys, u32 keyval) +{ + if (!skb_flow_dissect_flow_keys(skb, keys)) + return 0; + + return __flow_hash_from_keys(keys, keyval); +} + +struct _flow_keys_digest_data { + __be16 n_proto; + u8 ip_proto; + u8 padding; + __be32 ports; + __be32 src; + __be32 dst; +}; + +void make_flow_keys_digest(struct flow_keys_digest *digest, + const struct flow_keys *flow) +{ + struct _flow_keys_digest_data *data = + (struct _flow_keys_digest_data *)digest; + + BUILD_BUG_ON(sizeof(*data) > sizeof(*digest)); + + memset(digest, 0, sizeof(*digest)); + + data->n_proto = flow->basic.n_proto; + data->ip_proto = flow->basic.ip_proto; + data->ports = flow->ports.ports; + data->src = flow->addrs.v4addrs.src; + data->dst = flow->addrs.v4addrs.dst; +} +EXPORT_SYMBOL(make_flow_keys_digest); + +/** + * __skb_get_hash: calculate a flow hash + * @skb: sk_buff to calculate flow hash from + * + * This function calculates a flow hash based on src/dst addresses * and src/dst port numbers. Sets hash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. @@ -309,53 +583,34 @@ EXPORT_SYMBOL(flow_hash_from_keys); void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; + u32 hash; - if (!skb_flow_dissect(skb, &keys)) - return; + __flow_hash_secret_init(); - if (keys.ports) + hash = ___skb_get_hash(skb, &keys, hashrnd); + if (!hash) + return; + if (keys.ports.ports) skb->l4_hash = 1; - skb->sw_hash = 1; - - skb->hash = __flow_hash_from_keys(&keys); + skb->hash = hash; } EXPORT_SYMBOL(__skb_get_hash); -/* - * Returns a Tx hash based on the given packet descriptor a Tx queues' number - * to be used as a distribution range. - */ -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues) +__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) { - u32 hash; - u16 qoffset = 0; - u16 qcount = num_tx_queues; - - if (skb_rx_queue_recorded(skb)) { - hash = skb_get_rx_queue(skb); - while (unlikely(hash >= num_tx_queues)) - hash -= num_tx_queues; - return hash; - } - - if (dev->num_tc) { - u8 tc = netdev_get_prio_tc_map(dev, skb->priority); - qoffset = dev->tc_to_txq[tc].offset; - qcount = dev->tc_to_txq[tc].count; - } + struct flow_keys keys; - return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; + return ___skb_get_hash(skb, &keys, perturb); } -EXPORT_SYMBOL(__skb_tx_hash); +EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen) { - u32 poff = keys->thoff; + u32 poff = keys->control.thoff; - switch (keys->ip_proto) { + switch (keys->basic.ip_proto) { case IPPROTO_TCP: { /* access doff as u8 to avoid unaligned access */ const u8 *doff; @@ -396,8 +651,12 @@ u32 __skb_get_poff(const struct sk_buff *skb, void *data, return poff; } -/* skb_get_poff() returns the offset to the payload as far as it could - * be dissected. The main user is currently BPF, so that we can dynamically +/** + * skb_get_poff - get the offset to the payload + * @skb: sk_buff to get the payload offset from + * + * The function will get the offset to the payload as far as it could + * be dissected. The main user is currently BPF, so that we can dynamically * truncate packets without needing to push actual payload to the user * space and can analyze headers only, instead. */ @@ -405,86 +664,76 @@ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys keys; - if (!skb_flow_dissect(skb, &keys)) + if (!skb_flow_dissect_flow_keys(skb, &keys)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); } -static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +static const struct flow_dissector_key flow_keys_dissector_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_CONTROL, + .offset = offsetof(struct flow_keys, control), + }, + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v4addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v6addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_TIPC_ADDRS, + .offset = offsetof(struct flow_keys, addrs.tipcaddrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_PORTS, + .offset = offsetof(struct flow_keys, ports), + }, + { + .key_id = FLOW_DISSECTOR_KEY_VLANID, + .offset = offsetof(struct flow_keys, tags), + }, + { + .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, + .offset = offsetof(struct flow_keys, tags), + }, + { + .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, + .offset = offsetof(struct flow_keys, keyid), + }, +}; + +static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_CONTROL, + .offset = offsetof(struct flow_keys, control), + }, + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, +}; + +struct flow_dissector flow_keys_dissector __read_mostly; +EXPORT_SYMBOL(flow_keys_dissector); + +struct flow_dissector flow_keys_buf_dissector __read_mostly; + +static int __init init_default_flow_dissectors(void) { -#ifdef CONFIG_XPS - struct xps_dev_maps *dev_maps; - struct xps_map *map; - int queue_index = -1; - - rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); - if (dev_maps) { - map = rcu_dereference( - dev_maps->cpu_map[skb->sender_cpu - 1]); - if (map) { - if (map->len == 1) - queue_index = map->queues[0]; - else - queue_index = map->queues[reciprocal_scale(skb_get_hash(skb), - map->len)]; - if (unlikely(queue_index >= dev->real_num_tx_queues)) - queue_index = -1; - } - } - rcu_read_unlock(); - - return queue_index; -#else - return -1; -#endif -} - -static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - int queue_index = sk_tx_queue_get(sk); - - if (queue_index < 0 || skb->ooo_okay || - queue_index >= dev->real_num_tx_queues) { - int new_index = get_xps_queue(dev, skb); - if (new_index < 0) - new_index = skb_tx_hash(dev, skb); - - if (queue_index != new_index && sk && - rcu_access_pointer(sk->sk_dst_cache)) - sk_tx_queue_set(sk, new_index); - - queue_index = new_index; - } - - return queue_index; + skb_flow_dissector_init(&flow_keys_dissector, + flow_keys_dissector_keys, + ARRAY_SIZE(flow_keys_dissector_keys)); + skb_flow_dissector_init(&flow_keys_buf_dissector, + flow_keys_buf_dissector_keys, + ARRAY_SIZE(flow_keys_buf_dissector_keys)); + return 0; } -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb, - void *accel_priv) -{ - int queue_index = 0; - -#ifdef CONFIG_XPS - if (skb->sender_cpu == 0) - skb->sender_cpu = raw_smp_processor_id() + 1; -#endif - - if (dev->real_num_tx_queues != 1) { - const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, accel_priv, - __netdev_pick_tx); - else - queue_index = __netdev_pick_tx(dev, skb); - - if (!accel_priv) - queue_index = netdev_cap_txqueue(dev, queue_index); - } - - skb_set_queue_mapping(skb, queue_index); - return netdev_get_tx_queue(dev, queue_index); -} +late_initcall_sync(init_default_flow_dissectors); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 3de654256028..3a74df750af4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -913,6 +913,7 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_PROBE; neigh->updated = jiffies; atomic_set(&neigh->probes, 0); + notify = 1; next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } } else { @@ -1144,6 +1145,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (new != old) { neigh_del_timer(neigh); + if (new & NUD_PROBE) + atomic_set(&neigh->probes, 0); if (new & NUD_IN_TIMER) neigh_add_timer(neigh, (jiffies + ((new & NUD_REACHABLE) ? diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4238d6da5c60..18b34d771ed4 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -458,11 +458,15 @@ static ssize_t phys_switch_id_show(struct device *dev, return restart_syscall(); if (dev_isalive(netdev)) { - struct netdev_phys_item_id ppid; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; - ret = netdev_switch_parent_id_get(netdev, &ppid); + ret = switchdev_port_attr_get(netdev, &attr); if (!ret) - ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); + ret = sprintf(buf, "%*phN\n", attr.u.ppid.id_len, + attr.u.ppid.id); } rtnl_unlock(); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 572af0011997..2c2eb1b629b1 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -147,24 +147,17 @@ static void ops_free_list(const struct pernet_operations *ops, } } -static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd, - int id); +/* should be called with nsid_lock held */ static int alloc_netid(struct net *net, struct net *peer, int reqid) { - int min = 0, max = 0, id; - - ASSERT_RTNL(); + int min = 0, max = 0; if (reqid >= 0) { min = reqid; max = reqid + 1; } - id = idr_alloc(&net->netns_ids, peer, min, max, GFP_KERNEL); - if (id >= 0) - rtnl_net_notifyid(net, peer, RTM_NEWNSID, id); - - return id; + return idr_alloc(&net->netns_ids, peer, min, max, GFP_ATOMIC); } /* This function is used by idr_for_each(). If net is equal to peer, the @@ -180,11 +173,16 @@ static int net_eq_idr(int id, void *net, void *peer) return 0; } -static int __peernet2id(struct net *net, struct net *peer, bool alloc) +/* Should be called with nsid_lock held. If a new id is assigned, the bool alloc + * is set to true, thus the caller knows that the new id must be notified via + * rtnl. + */ +static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc) { int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); + bool alloc_it = *alloc; - ASSERT_RTNL(); + *alloc = false; /* Magic value for id 0. */ if (id == NET_ID_ZERO) @@ -192,36 +190,77 @@ static int __peernet2id(struct net *net, struct net *peer, bool alloc) if (id > 0) return id; - if (alloc) - return alloc_netid(net, peer, -1); + if (alloc_it) { + id = alloc_netid(net, peer, -1); + *alloc = true; + return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED; + } + + return NETNSA_NSID_NOT_ASSIGNED; +} + +/* should be called with nsid_lock held */ +static int __peernet2id(struct net *net, struct net *peer) +{ + bool no = false; - return -ENOENT; + return __peernet2id_alloc(net, peer, &no); } +static void rtnl_net_notifyid(struct net *net, int cmd, int id); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ +int peernet2id_alloc(struct net *net, struct net *peer) +{ + unsigned long flags; + bool alloc; + int id; + + spin_lock_irqsave(&net->nsid_lock, flags); + alloc = atomic_read(&peer->count) == 0 ? false : true; + id = __peernet2id_alloc(net, peer, &alloc); + spin_unlock_irqrestore(&net->nsid_lock, flags); + if (alloc && id >= 0) + rtnl_net_notifyid(net, RTM_NEWNSID, id); + return id; +} +EXPORT_SYMBOL(peernet2id_alloc); + +/* This function returns, if assigned, the id of a peer netns. */ int peernet2id(struct net *net, struct net *peer) { - bool alloc = atomic_read(&peer->count) == 0 ? false : true; + unsigned long flags; int id; - id = __peernet2id(net, peer, alloc); - return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED; + spin_lock_irqsave(&net->nsid_lock, flags); + id = __peernet2id(net, peer); + spin_unlock_irqrestore(&net->nsid_lock, flags); + return id; +} + +/* This function returns true is the peer netns has an id assigned into the + * current netns. + */ +bool peernet_has_id(struct net *net, struct net *peer) +{ + return peernet2id(net, peer) >= 0; } -EXPORT_SYMBOL(peernet2id); struct net *get_net_ns_by_id(struct net *net, int id) { + unsigned long flags; struct net *peer; if (id < 0) return NULL; rcu_read_lock(); + spin_lock_irqsave(&net->nsid_lock, flags); peer = idr_find(&net->netns_ids, id); if (peer) get_net(peer); + spin_unlock_irqrestore(&net->nsid_lock, flags); rcu_read_unlock(); return peer; @@ -242,6 +281,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); + spin_lock_init(&net->nsid_lock); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); @@ -362,14 +402,19 @@ static void cleanup_net(struct work_struct *work) list_del_rcu(&net->list); list_add_tail(&net->exit_list, &net_exit_list); for_each_net(tmp) { - int id = __peernet2id(tmp, net, false); + int id; - if (id >= 0) { - rtnl_net_notifyid(tmp, net, RTM_DELNSID, id); + spin_lock_irq(&tmp->nsid_lock); + id = __peernet2id(tmp, net); + if (id >= 0) idr_remove(&tmp->netns_ids, id); - } + spin_unlock_irq(&tmp->nsid_lock); + if (id >= 0) + rtnl_net_notifyid(tmp, RTM_DELNSID, id); } + spin_lock_irq(&net->nsid_lock); idr_destroy(&net->netns_ids); + spin_unlock_irq(&net->nsid_lock); } rtnl_unlock(); @@ -497,6 +542,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; + unsigned long flags; struct net *peer; int nsid, err; @@ -517,14 +563,19 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh) if (IS_ERR(peer)) return PTR_ERR(peer); - if (__peernet2id(net, peer, false) >= 0) { + spin_lock_irqsave(&net->nsid_lock, flags); + if (__peernet2id(net, peer) >= 0) { + spin_unlock_irqrestore(&net->nsid_lock, flags); err = -EEXIST; goto out; } err = alloc_netid(net, peer, nsid); - if (err > 0) + spin_unlock_irqrestore(&net->nsid_lock, flags); + if (err >= 0) { + rtnl_net_notifyid(net, RTM_NEWNSID, err); err = 0; + } out: put_net(peer); return err; @@ -538,14 +589,10 @@ static int rtnl_net_get_size(void) } static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags, - int cmd, struct net *net, struct net *peer, - int nsid) + int cmd, struct net *net, int nsid) { struct nlmsghdr *nlh; struct rtgenmsg *rth; - int id; - - ASSERT_RTNL(); nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rth), flags); if (!nlh) @@ -554,14 +601,7 @@ static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags, rth = nlmsg_data(nlh); rth->rtgen_family = AF_UNSPEC; - if (nsid >= 0) { - id = nsid; - } else { - id = __peernet2id(net, peer, false); - if (id < 0) - id = NETNSA_NSID_NOT_ASSIGNED; - } - if (nla_put_s32(skb, NETNSA_NSID, id)) + if (nla_put_s32(skb, NETNSA_NSID, nsid)) goto nla_put_failure; nlmsg_end(skb, nlh); @@ -578,7 +618,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *tb[NETNSA_MAX + 1]; struct sk_buff *msg; struct net *peer; - int err; + int err, id; err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy); @@ -600,8 +640,9 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh) goto out; } + id = peernet2id(net, peer); err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, - RTM_NEWNSID, net, peer, -1); + RTM_NEWNSID, net, id); if (err < 0) goto err_out; @@ -633,7 +674,7 @@ static int rtnl_net_dumpid_one(int id, void *peer, void *data) ret = rtnl_net_fill(net_cb->skb, NETLINK_CB(net_cb->cb->skb).portid, net_cb->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWNSID, net_cb->net, peer, id); + RTM_NEWNSID, net_cb->net, id); if (ret < 0) return ret; @@ -652,17 +693,17 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) .idx = 0, .s_idx = cb->args[0], }; + unsigned long flags; - ASSERT_RTNL(); - + spin_lock_irqsave(&net->nsid_lock, flags); idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb); + spin_unlock_irqrestore(&net->nsid_lock, flags); cb->args[0] = net_cb.idx; return skb->len; } -static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd, - int id) +static void rtnl_net_notifyid(struct net *net, int cmd, int id) { struct sk_buff *msg; int err = -ENOMEM; @@ -671,7 +712,7 @@ static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd, if (!msg) goto out; - err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, peer, id); + err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, id); if (err < 0) goto err_out; diff --git a/net/core/netevent.c b/net/core/netevent.c index f17ccd291d39..8b3bc4fac613 100644 --- a/net/core/netevent.c +++ b/net/core/netevent.c @@ -31,10 +31,7 @@ static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain); */ int register_netevent_notifier(struct notifier_block *nb) { - int err; - - err = atomic_notifier_chain_register(&netevent_notif_chain, nb); - return err; + return atomic_notifier_chain_register(&netevent_notif_chain, nb); } EXPORT_SYMBOL_GPL(register_netevent_notifier); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 508155b283dd..d93cbc5715f4 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -177,7 +177,7 @@ #include <asm/dma.h> #include <asm/div64.h> /* do_div */ -#define VERSION "2.74" +#define VERSION "2.75" #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ #define MPLS_STACK_BOTTOM htonl(0x00000100) @@ -210,6 +210,10 @@ #define T_REMDEVALL (1<<2) /* Remove all devs */ #define T_REMDEV (1<<3) /* Remove one dev */ +/* Xmit modes */ +#define M_START_XMIT 0 /* Default normal TX */ +#define M_NETIF_RECEIVE 1 /* Inject packets into stack */ + /* If lock -- protects updating of if_list */ #define if_lock(t) spin_lock(&(t->if_lock)); #define if_unlock(t) spin_unlock(&(t->if_lock)); @@ -251,13 +255,14 @@ struct pktgen_dev { * we will do a random selection from within the range. */ __u32 flags; - int removal_mark; /* non-zero => the device is marked for - * removal by worker thread */ - + int xmit_mode; int min_pkt_size; int max_pkt_size; int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */ int nfrags; + int removal_mark; /* non-zero => the device is marked for + * removal by worker thread */ + struct page *page; u64 delay; /* nano-seconds */ @@ -507,7 +512,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, pktgen_reset_all_threads(pn); else - pr_warn("Unknown command: %s\n", data); + return -EINVAL; return count; } @@ -567,7 +572,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) " dst_min: %s dst_max: %s\n", pkt_dev->dst_min, pkt_dev->dst_max); seq_printf(seq, - " src_min: %s src_max: %s\n", + " src_min: %s src_max: %s\n", pkt_dev->src_min, pkt_dev->src_max); } @@ -620,6 +625,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->node >= 0) seq_printf(seq, " node: %d\n", pkt_dev->node); + if (pkt_dev->xmit_mode == M_NETIF_RECEIVE) + seq_puts(seq, " xmit_mode: netif_receive\n"); + seq_puts(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) @@ -1081,7 +1089,8 @@ static ssize_t pktgen_if_write(struct file *file, if (len < 0) return len; if ((value > 0) && - (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) + ((pkt_dev->xmit_mode == M_NETIF_RECEIVE) || + !(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) return -ENOTSUPP; i += len; pkt_dev->clone_skb = value; @@ -1134,7 +1143,7 @@ static ssize_t pktgen_if_write(struct file *file, return len; i += len; - if ((value > 1) && + if ((value > 1) && (pkt_dev->xmit_mode == M_START_XMIT) && (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) return -ENOTSUPP; pkt_dev->burst = value < 1 ? 1 : value; @@ -1160,6 +1169,45 @@ static ssize_t pktgen_if_write(struct file *file, sprintf(pg_result, "ERROR: node not possible"); return count; } + if (!strcmp(name, "xmit_mode")) { + char f[32]; + + memset(f, 0, 32); + len = strn_len(&user_buffer[i], sizeof(f) - 1); + if (len < 0) + return len; + + if (copy_from_user(f, &user_buffer[i], len)) + return -EFAULT; + i += len; + + if (strcmp(f, "start_xmit") == 0) { + pkt_dev->xmit_mode = M_START_XMIT; + } else if (strcmp(f, "netif_receive") == 0) { + /* clone_skb set earlier, not supported in this mode */ + if (pkt_dev->clone_skb > 0) + return -ENOTSUPP; + + pkt_dev->xmit_mode = M_NETIF_RECEIVE; + + /* make sure new packet is allocated every time + * pktgen_xmit() is called + */ + pkt_dev->last_ok = 1; + + /* override clone_skb if user passed default value + * at module loading time + */ + pkt_dev->clone_skb = 0; + } else { + sprintf(pg_result, + "xmit_mode -:%s:- unknown\nAvailable modes: %s", + f, "start_xmit, netif_receive\n"); + return count; + } + sprintf(pg_result, "OK: xmit_mode=%s", f); + return count; + } if (!strcmp(name, "flag")) { char f[32]; memset(f, 0, 32); @@ -1267,6 +1315,9 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "NO_TIMESTAMP") == 0) pkt_dev->flags |= F_NO_TIMESTAMP; + else if (strcmp(f, "!NO_TIMESTAMP") == 0) + pkt_dev->flags &= ~F_NO_TIMESTAMP; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", @@ -2594,9 +2645,9 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; int nhead = 0; if (x) { - int ret; - __u8 *eth; + struct ethhdr *eth; struct iphdr *iph; + int ret; nhead = x->props.header_len - skb_headroom(skb); if (nhead > 0) { @@ -2616,9 +2667,9 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, goto err; } /* restore ll */ - eth = (__u8 *) skb_push(skb, ETH_HLEN); - memcpy(eth, pkt_dev->hh, 12); - *(u16 *) ð[12] = protocol; + eth = (struct ethhdr *)skb_push(skb, ETH_HLEN); + memcpy(eth, pkt_dev->hh, 2 * ETH_ALEN); + eth->h_proto = protocol; /* Update IPv4 header len as well as checksum value */ iph = ip_hdr(skb); @@ -3317,6 +3368,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) unsigned int burst = ACCESS_ONCE(pkt_dev->burst); struct net_device *odev = pkt_dev->odev; struct netdev_queue *txq; + struct sk_buff *skb; int ret; /* If device is offline, then don't send */ @@ -3354,6 +3406,37 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) if (pkt_dev->delay && pkt_dev->last_ok) spin(pkt_dev, pkt_dev->next_tx); + if (pkt_dev->xmit_mode == M_NETIF_RECEIVE) { + skb = pkt_dev->skb; + skb->protocol = eth_type_trans(skb, skb->dev); + atomic_add(burst, &skb->users); + local_bh_disable(); + do { + ret = netif_receive_skb(skb); + if (ret == NET_RX_DROP) + pkt_dev->errors++; + pkt_dev->sofar++; + pkt_dev->seq_num++; + if (atomic_read(&skb->users) != burst) { + /* skb was queued by rps/rfs or taps, + * so cannot reuse this skb + */ + atomic_sub(burst - 1, &skb->users); + /* get out of the loop and wait + * until skb is consumed + */ + break; + } + /* skb was 'freed' by stack, so clean few + * bits and reuse it + */ +#ifdef CONFIG_NET_CLS_ACT + skb->tc_verd = 0; /* reset reclass/redir ttl */ +#endif + } while (--burst > 0); + goto out; /* Skips xmit_mode M_START_XMIT */ + } + txq = skb_get_tx_queue(odev, pkt_dev->skb); local_bh_disable(); @@ -3401,6 +3484,7 @@ xmit_more: unlock: HARD_TX_UNLOCK(odev, txq); +out: local_bh_enable(); /* If pkt_dev->count is zero, then run forever */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8de36824018d..077b6d280371 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1004,16 +1004,20 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { int err; - struct netdev_phys_item_id psid; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; - err = netdev_switch_parent_id_get(dev, &psid); + err = switchdev_port_attr_get(dev, &attr); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } - if (nla_put(skb, IFLA_PHYS_SWITCH_ID, psid.id_len, psid.id)) + if (nla_put(skb, IFLA_PHYS_SWITCH_ID, attr.u.ppid.id_len, + attr.u.ppid.id)) return -EMSGSIZE; return 0; @@ -1204,7 +1208,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); if (!net_eq(dev_net(dev), link_net)) { - int id = peernet2id(dev_net(dev), link_net); + int id = peernet2id_alloc(dev_net(dev), link_net); if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) goto nla_put_failure; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 51dd3193a33e..fd3ce461fbe6 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -154,7 +154,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) - secret[i] = net_secret[i] + daddr[i]; + secret[i] = net_secret[i] + (__force u32)daddr[i]; secret[4] = net_secret[4] + (((__force u16)sport << 16) + (__force u16)dport); for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3cfff2a3d651..9bac0e6f8dfa 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -347,94 +347,18 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) } EXPORT_SYMBOL(build_skb); -struct netdev_alloc_cache { - struct page_frag frag; - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_count every time we allocate a fragment. - */ - unsigned int pagecnt_bias; -}; -static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); -static DEFINE_PER_CPU(struct netdev_alloc_cache, napi_alloc_cache); - -static struct page *__page_frag_refill(struct netdev_alloc_cache *nc, - gfp_t gfp_mask) -{ - const unsigned int order = NETDEV_FRAG_PAGE_MAX_ORDER; - struct page *page = NULL; - gfp_t gfp = gfp_mask; - - if (order) { - gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | - __GFP_NOMEMALLOC; - page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); - nc->frag.size = PAGE_SIZE << (page ? order : 0); - } - - if (unlikely(!page)) - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - - nc->frag.page = page; - - return page; -} - -static void *__alloc_page_frag(struct netdev_alloc_cache __percpu *cache, - unsigned int fragsz, gfp_t gfp_mask) -{ - struct netdev_alloc_cache *nc = this_cpu_ptr(cache); - struct page *page = nc->frag.page; - unsigned int size; - int offset; - - if (unlikely(!page)) { -refill: - page = __page_frag_refill(nc, gfp_mask); - if (!page) - return NULL; - - /* if size can vary use frag.size else just use PAGE_SIZE */ - size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE; - - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - atomic_add(size - 1, &page->_count); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = size; - nc->frag.offset = size; - } - - offset = nc->frag.offset - fragsz; - if (unlikely(offset < 0)) { - if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count)) - goto refill; - - /* if size can vary use frag.size else just use PAGE_SIZE */ - size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE; - - /* OK, page count is 0, we can safely set it */ - atomic_set(&page->_count, size); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = size; - offset = size - fragsz; - } - - nc->pagecnt_bias--; - nc->frag.offset = offset; - - return page_address(page) + offset; -} +static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); +static DEFINE_PER_CPU(struct page_frag_cache, napi_alloc_cache); static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { + struct page_frag_cache *nc; unsigned long flags; void *data; local_irq_save(flags); - data = __alloc_page_frag(&netdev_alloc_cache, fragsz, gfp_mask); + nc = this_cpu_ptr(&netdev_alloc_cache); + data = __alloc_page_frag(nc, fragsz, gfp_mask); local_irq_restore(flags); return data; } @@ -454,7 +378,9 @@ EXPORT_SYMBOL(netdev_alloc_frag); static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { - return __alloc_page_frag(&napi_alloc_cache, fragsz, gfp_mask); + struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); + + return __alloc_page_frag(nc, fragsz, gfp_mask); } void *napi_alloc_frag(unsigned int fragsz) @@ -464,76 +390,70 @@ void *napi_alloc_frag(unsigned int fragsz) EXPORT_SYMBOL(napi_alloc_frag); /** - * __alloc_rx_skb - allocate an skbuff for rx + * __netdev_alloc_skb - allocate an skbuff for rx on a specific device + * @dev: network device to receive on * @length: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb - * @flags: If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for - * allocations in case we have to fallback to __alloc_skb() - * If SKB_ALLOC_NAPI is set, page fragment will be allocated - * from napi_cache instead of netdev_cache. * * Allocate a new &sk_buff and assign it a usage count of one. The - * buffer has unspecified headroom built in. Users should allocate + * buffer has NET_SKB_PAD headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. */ -static struct sk_buff *__alloc_rx_skb(unsigned int length, gfp_t gfp_mask, - int flags) +struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, + gfp_t gfp_mask) { - struct sk_buff *skb = NULL; - unsigned int fragsz = SKB_DATA_ALIGN(length) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + struct page_frag_cache *nc; + unsigned long flags; + struct sk_buff *skb; + bool pfmemalloc; + void *data; - if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { - void *data; + len += NET_SKB_PAD; - if (sk_memalloc_socks()) - gfp_mask |= __GFP_MEMALLOC; + if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || + (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); + if (!skb) + goto skb_fail; + goto skb_success; + } - data = (flags & SKB_ALLOC_NAPI) ? - __napi_alloc_frag(fragsz, gfp_mask) : - __netdev_alloc_frag(fragsz, gfp_mask); + len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + len = SKB_DATA_ALIGN(len); - if (likely(data)) { - skb = build_skb(data, fragsz); - if (unlikely(!skb)) - put_page(virt_to_head_page(data)); - } - } else { - skb = __alloc_skb(length, gfp_mask, - SKB_ALLOC_RX, NUMA_NO_NODE); - } - return skb; -} + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; -/** - * __netdev_alloc_skb - allocate an skbuff for rx on a specific device - * @dev: network device to receive on - * @length: length to allocate - * @gfp_mask: get_free_pages mask, passed to alloc_skb - * - * Allocate a new &sk_buff and assign it a usage count of one. The - * buffer has NET_SKB_PAD headroom built in. Users should allocate - * the headroom they think they need without accounting for the - * built in space. The built in space is used for optimisations. - * - * %NULL is returned if there is no free memory. - */ -struct sk_buff *__netdev_alloc_skb(struct net_device *dev, - unsigned int length, gfp_t gfp_mask) -{ - struct sk_buff *skb; + local_irq_save(flags); + + nc = this_cpu_ptr(&netdev_alloc_cache); + data = __alloc_page_frag(nc, len, gfp_mask); + pfmemalloc = nc->pfmemalloc; - length += NET_SKB_PAD; - skb = __alloc_rx_skb(length, gfp_mask, 0); + local_irq_restore(flags); - if (likely(skb)) { - skb_reserve(skb, NET_SKB_PAD); - skb->dev = dev; + if (unlikely(!data)) + return NULL; + + skb = __build_skb(data, len); + if (unlikely(!skb)) { + skb_free_frag(data); + return NULL; } + /* use OR instead of assignment to avoid clearing of bits in mask */ + if (pfmemalloc) + skb->pfmemalloc = 1; + skb->head_frag = 1; + +skb_success: + skb_reserve(skb, NET_SKB_PAD); + skb->dev = dev; + +skb_fail: return skb; } EXPORT_SYMBOL(__netdev_alloc_skb); @@ -551,19 +471,49 @@ EXPORT_SYMBOL(__netdev_alloc_skb); * * %NULL is returned if there is no free memory. */ -struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, - unsigned int length, gfp_t gfp_mask) +struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, + gfp_t gfp_mask) { + struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; + void *data; - length += NET_SKB_PAD + NET_IP_ALIGN; - skb = __alloc_rx_skb(length, gfp_mask, SKB_ALLOC_NAPI); + len += NET_SKB_PAD + NET_IP_ALIGN; - if (likely(skb)) { - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - skb->dev = napi->dev; + if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || + (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); + if (!skb) + goto skb_fail; + goto skb_success; } + len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + len = SKB_DATA_ALIGN(len); + + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + + data = __alloc_page_frag(nc, len, gfp_mask); + if (unlikely(!data)) + return NULL; + + skb = __build_skb(data, len); + if (unlikely(!skb)) { + skb_free_frag(data); + return NULL; + } + + /* use OR instead of assignment to avoid clearing of bits in mask */ + if (nc->pfmemalloc) + skb->pfmemalloc = 1; + skb->head_frag = 1; + +skb_success: + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + skb->dev = napi->dev; + +skb_fail: return skb; } EXPORT_SYMBOL(__napi_alloc_skb); @@ -611,10 +561,12 @@ static void skb_clone_fraglist(struct sk_buff *skb) static void skb_free_head(struct sk_buff *skb) { + unsigned char *head = skb->head; + if (skb->head_frag) - put_page(virt_to_head_page(skb->head)); + skb_free_frag(head); else - kfree(skb->head); + kfree(head); } static void skb_release_data(struct sk_buff *skb) @@ -1918,15 +1870,39 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, return false; } +ssize_t skb_socket_splice(struct sock *sk, + struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd) +{ + int ret; + + /* Drop the socket lock, otherwise we have reverse + * locking dependencies between sk_lock and i_mutex + * here as compared to sendfile(). We enter here + * with the socket lock held, and splice_to_pipe() will + * grab the pipe inode lock. For sendfile() emulation, + * we call into ->sendpage() with the i_mutex lock held + * and networking will grab the socket lock. + */ + release_sock(sk); + ret = splice_to_pipe(pipe, spd); + lock_sock(sk); + + return ret; +} + /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. It does NOT handle frag lists within * the frag list, if such a thing exists. We'd probably need to recurse to * handle that cleanly. */ -int skb_splice_bits(struct sk_buff *skb, unsigned int offset, +int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, - unsigned int flags) + unsigned int flags, + ssize_t (*splice_cb)(struct sock *, + struct pipe_inode_info *, + struct splice_pipe_desc *)) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; @@ -1939,7 +1915,6 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .spd_release = sock_spd_release, }; struct sk_buff *frag_iter; - struct sock *sk = skb->sk; int ret = 0; /* @@ -1962,23 +1937,12 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, } done: - if (spd.nr_pages) { - /* - * Drop the socket lock, otherwise we have reverse - * locking dependencies between sk_lock and i_mutex - * here as compared to sendfile(). We enter here - * with the socket lock held, and splice_to_pipe() will - * grab the pipe inode lock. For sendfile() emulation, - * we call into ->sendpage() with the i_mutex lock held - * and networking will grab the socket lock. - */ - release_sock(sk); - ret = splice_to_pipe(pipe, &spd); - lock_sock(sk); - } + if (spd.nr_pages) + ret = splice_cb(sk, pipe, &spd); return ret; } +EXPORT_SYMBOL_GPL(skb_splice_bits); /** * skb_store_bits - store bits from kernel buffer to skb @@ -2963,6 +2927,24 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, } EXPORT_SYMBOL(skb_append_datato_frags); +int skb_append_pagefrags(struct sk_buff *skb, struct page *page, + int offset, size_t size) +{ + int i = skb_shinfo(skb)->nr_frags; + + if (skb_can_coalesce(skb, i, page, offset)) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); + } else if (i < MAX_SKB_FRAGS) { + get_page(page); + skb_fill_page_desc(skb, i, page, offset, size); + } else { + return -EMSGSIZE; + } + + return 0; +} +EXPORT_SYMBOL_GPL(skb_append_pagefrags); + /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update @@ -4030,6 +4012,93 @@ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) } EXPORT_SYMBOL(skb_checksum_setup); +/** + * skb_checksum_maybe_trim - maybe trims the given skb + * @skb: the skb to check + * @transport_len: the data length beyond the network header + * + * Checks whether the given skb has data beyond the given transport length. + * If so, returns a cloned skb trimmed to this transport length. + * Otherwise returns the provided skb. Returns NULL in error cases + * (e.g. transport_len exceeds skb length or out-of-memory). + * + * Caller needs to set the skb transport header and release the returned skb. + * Provided skb is consumed. + */ +static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, + unsigned int transport_len) +{ + struct sk_buff *skb_chk; + unsigned int len = skb_transport_offset(skb) + transport_len; + int ret; + + if (skb->len < len) { + kfree_skb(skb); + return NULL; + } else if (skb->len == len) { + return skb; + } + + skb_chk = skb_clone(skb, GFP_ATOMIC); + kfree_skb(skb); + + if (!skb_chk) + return NULL; + + ret = pskb_trim_rcsum(skb_chk, len); + if (ret) { + kfree_skb(skb_chk); + return NULL; + } + + return skb_chk; +} + +/** + * skb_checksum_trimmed - validate checksum of an skb + * @skb: the skb to check + * @transport_len: the data length beyond the network header + * @skb_chkf: checksum function to use + * + * Applies the given checksum function skb_chkf to the provided skb. + * Returns a checked and maybe trimmed skb. Returns NULL on error. + * + * If the skb has data beyond the given transport length, then a + * trimmed & cloned skb is checked and returned. + * + * Caller needs to set the skb transport header and release the returned skb. + * Provided skb is consumed. + */ +struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, + unsigned int transport_len, + __sum16(*skb_chkf)(struct sk_buff *skb)) +{ + struct sk_buff *skb_chk; + unsigned int offset = skb_transport_offset(skb); + __sum16 ret; + + skb_chk = skb_checksum_maybe_trim(skb, transport_len); + if (!skb_chk) + return NULL; + + if (!pskb_may_pull(skb_chk, offset)) { + kfree_skb(skb_chk); + return NULL; + } + + __skb_pull(skb_chk, offset); + ret = skb_chkf(skb_chk); + __skb_push(skb_chk, offset); + + if (ret) { + kfree_skb(skb_chk); + return NULL; + } + + return skb_chk; +} +EXPORT_SYMBOL(skb_checksum_trimmed); + void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", diff --git a/net/core/sock.c b/net/core/sock.c index 292f42228bfb..e72633c346b1 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1396,9 +1396,10 @@ EXPORT_SYMBOL_GPL(sock_update_netprioidx); * @family: protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @prot: struct proto associated with this new sock instance + * @kern: is this to be a kernel socket? */ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, - struct proto *prot) + struct proto *prot, int kern) { struct sock *sk; @@ -1411,7 +1412,10 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, */ sk->sk_prot = sk->sk_prot_creator = prot; sock_lock_init(sk); - sock_net_set(sk, get_net(net)); + sk->sk_net_refcnt = kern ? 0 : 1; + if (likely(sk->sk_net_refcnt)) + get_net(net); + sock_net_set(sk, net); atomic_set(&sk->sk_wmem_alloc, 1); sock_update_classid(sk); @@ -1445,7 +1449,8 @@ static void __sk_free(struct sock *sk) if (sk->sk_peer_cred) put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); - put_net(sock_net(sk)); + if (likely(sk->sk_net_refcnt)) + put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); } @@ -1461,25 +1466,6 @@ void sk_free(struct sock *sk) } EXPORT_SYMBOL(sk_free); -/* - * Last sock_put should drop reference to sk->sk_net. It has already - * been dropped in sk_change_net. Taking reference to stopping namespace - * is not an option. - * Take reference to a socket to remove it from hash _alive_ and after that - * destroy it in the context of init_net. - */ -void sk_release_kernel(struct sock *sk) -{ - if (sk == NULL || sk->sk_socket == NULL) - return; - - sock_hold(sk); - sock_release(sk->sk_socket); - sock_net_set(sk, get_net(&init_net)); - sock_put(sk); -} -EXPORT_SYMBOL(sk_release_kernel); - static void sk_update_clone(const struct sock *sk, struct sock *newsk) { if (mem_cgroup_sockets_enabled && sk->sk_cgrp) @@ -1595,6 +1581,8 @@ EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { + u32 max_segs = 1; + __sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; if (sk->sk_route_caps & NETIF_F_GSO) @@ -1606,9 +1594,10 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; - sk->sk_gso_max_segs = dst->dev->gso_max_segs; + max_segs = max_t(u32, dst->dev->gso_max_segs, 1); } } + sk->sk_gso_max_segs = max_segs; } EXPORT_SYMBOL_GPL(sk_setup_caps); @@ -2083,12 +2072,13 @@ EXPORT_SYMBOL(__sk_mem_schedule); /** * __sk_reclaim - reclaim memory_allocated * @sk: socket + * @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple) */ -void __sk_mem_reclaim(struct sock *sk) +void __sk_mem_reclaim(struct sock *sk, int amount) { - sk_memory_allocated_sub(sk, - sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); - sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; + amount >>= SK_MEM_QUANTUM_SHIFT; + sk_memory_allocated_sub(sk, amount); + sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; if (sk_under_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) diff --git a/net/core/stream.c b/net/core/stream.c index 301c05f26060..d70f77a0c889 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -119,6 +119,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) int err = 0; long vm_wait = 0; long current_timeo = *timeo_p; + bool noblock = (*timeo_p ? false : true); DEFINE_WAIT(wait); if (sk_stream_memory_free(sk)) @@ -131,8 +132,11 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; - if (!*timeo_p) + if (!*timeo_p) { + if (noblock) + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); goto do_nonblock; + } if (signal_pending(current)) goto do_interrupted; clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); diff --git a/net/core/utils.c b/net/core/utils.c index 7b803884c162..a7732a068043 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -304,13 +304,15 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, int pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { - *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from), - to)); + csum_replace4(sum, from, to); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) - skb->csum = ~csum_add(csum_sub(~(skb->csum), from), to); + skb->csum = ~csum_add(csum_sub(~(skb->csum), + (__force __wsum)from), + (__force __wsum)to); } else if (pseudohdr) - *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), from), - to)); + *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), + (__force __wsum)from), + (__force __wsum)to)); } EXPORT_SYMBOL(inet_proto_csum_replace4); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 754484b3cd0e..675cf94e04f8 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -468,10 +468,10 @@ static struct proto dn_proto = { .obj_size = sizeof(struct dn_sock), }; -static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gfp) +static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gfp, int kern) { struct dn_scp *scp; - struct sock *sk = sk_alloc(net, PF_DECnet, gfp, &dn_proto); + struct sock *sk = sk_alloc(net, PF_DECnet, gfp, &dn_proto, kern); if (!sk) goto out; @@ -693,7 +693,7 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, } - if ((sk = dn_alloc_sock(net, sock, GFP_KERNEL)) == NULL) + if ((sk = dn_alloc_sock(net, sock, GFP_KERNEL, kern)) == NULL) return -ENOBUFS; sk->sk_protocol = protocol; @@ -1096,7 +1096,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) cb = DN_SKB_CB(skb); sk->sk_ack_backlog--; - newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation); + newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0); if (newsk == NULL) { release_sock(sk); kfree_skb(skb); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 827cda560a55..04ffad311704 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -345,6 +345,24 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state) return ret; } +static int dsa_slave_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr) +{ + int ret = 0; + + switch (attr->id) { + case SWITCHDEV_ATTR_PORT_STP_STATE: + if (attr->trans == SWITCHDEV_TRANS_COMMIT) + ret = dsa_slave_stp_update(dev, attr->u.stp_state); + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + static int dsa_slave_bridge_port_join(struct net_device *dev, struct net_device *br) { @@ -382,14 +400,20 @@ static int dsa_slave_bridge_port_leave(struct net_device *dev) return ret; } -static int dsa_slave_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +static int dsa_slave_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - psid->id_len = sizeof(ds->index); - memcpy(&psid->id, &ds->index, psid->id_len); + switch (attr->id) { + case SWITCHDEV_ATTR_PORT_PARENT_ID: + attr->u.ppid.id_len = sizeof(ds->index); + memcpy(&attr->u.ppid.id, &ds->index, attr->u.ppid.id_len); + break; + default: + return -EOPNOTSUPP; + } return 0; } @@ -675,9 +699,9 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_get_iflink = dsa_slave_get_iflink, }; -static const struct swdev_ops dsa_slave_swdev_ops = { - .swdev_parent_id_get = dsa_slave_parent_id_get, - .swdev_port_stp_update = dsa_slave_stp_update, +static const struct switchdev_ops dsa_slave_switchdev_ops = { + .switchdev_port_attr_get = dsa_slave_port_attr_get, + .switchdev_port_attr_set = dsa_slave_port_attr_set, }; static void dsa_slave_adjust_link(struct net_device *dev) @@ -810,12 +834,19 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, return 0; } +static struct lock_class_key dsa_slave_netdev_xmit_lock_key; +static void dsa_slave_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *_unused) +{ + lockdep_set_class(&txq->_xmit_lock, + &dsa_slave_netdev_xmit_lock_key); +} + int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); - netif_device_detach(slave_dev); - if (p->phy) { phy_stop(p->phy); p->old_pause = -1; @@ -859,7 +890,10 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, eth_hw_addr_inherit(slave_dev, master); slave_dev->tx_queue_len = 0; slave_dev->netdev_ops = &dsa_slave_netdev_ops; - slave_dev->swdev_ops = &dsa_slave_swdev_ops; + slave_dev->switchdev_ops = &dsa_slave_switchdev_ops; + + netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, + NULL); SET_NETDEV_DEV(slave_dev, parent); slave_dev->dev.of_node = ds->pd->port_dn[port]; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index f3bad41d725f..77e0f0e7a88e 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -58,6 +58,7 @@ #include <net/ipv6.h> #include <net/ip.h> #include <net/dsa.h> +#include <net/flow_dissector.h> #include <linux/uaccess.h> __setup("ether=", netdev_boot_setup); @@ -130,9 +131,9 @@ u32 eth_get_headlen(void *data, unsigned int len) return len; /* parse any remaining L2/L3 headers, check for L4 */ - if (!__skb_flow_dissect(NULL, &keys, data, - eth->h_proto, sizeof(*eth), len)) - return max_t(u32, keys.thoff, sizeof(*eth)); + if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto, + sizeof(*eth), len)) + return max_t(u32, keys.control.thoff, sizeof(*eth)); /* parse for any L4 headers */ return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len); @@ -156,10 +157,11 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); + + eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); - eth = eth_hdr(skb); - if (unlikely(is_multicast_ether_addr(eth->h_dest))) { + if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else @@ -178,7 +180,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) if (unlikely(netdev_uses_dsa(dev))) return htons(ETH_P_XDSA); - if (likely(ntohs(eth->h_proto) >= ETH_P_802_3_MIN)) + if (likely(eth_proto_is_802_3(eth->h_proto))) return eth->h_proto; /* @@ -468,6 +470,7 @@ EXPORT_SYMBOL(eth_gro_complete); static struct packet_offload eth_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_TEB), + .priority = 10, .callbacks = { .gro_receive = eth_gro_receive, .gro_complete = eth_gro_complete, diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 0ae5822ef944..f20a387a1011 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -55,27 +55,6 @@ LIST_HEAD(lowpan_devices); static int lowpan_open_count; -static __le16 lowpan_get_pan_id(const struct net_device *dev) -{ - struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; - - return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev); -} - -static __le16 lowpan_get_short_addr(const struct net_device *dev) -{ - struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; - - return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev); -} - -static u8 lowpan_get_dsn(const struct net_device *dev) -{ - struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; - - return ieee802154_mlme_ops(real_dev)->get_dsn(real_dev); -} - static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; @@ -103,12 +82,6 @@ static const struct net_device_ops lowpan_netdev_ops = { .ndo_start_xmit = lowpan_xmit, }; -static struct ieee802154_mlme_ops lowpan_mlme = { - .get_pan_id = lowpan_get_pan_id, - .get_short_addr = lowpan_get_short_addr, - .get_dsn = lowpan_get_dsn, -}; - static void lowpan_setup(struct net_device *dev) { dev->addr_len = IEEE802154_ADDR_LEN; @@ -124,7 +97,6 @@ static void lowpan_setup(struct net_device *dev) dev->netdev_ops = &lowpan_netdev_ops; dev->header_ops = &lowpan_header_ops; - dev->ml_priv = &lowpan_mlme; dev->destructor = free_netdev; dev->features |= NETIF_F_NETNS_LOCAL; } diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index 2349070bd534..98acf7319754 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -207,7 +207,7 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *dev) /* prepare wpan address data */ sa.mode = IEEE802154_ADDR_LONG; - sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + sa.pan_id = lowpan_dev_info(dev)->real_dev->ieee802154_ptr->pan_id; sa.extended_addr = ieee802154_devaddr_from_raw(saddr); /* intra-PAN communications */ diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index 2ee00e8a0308..b0248e934230 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -121,8 +121,6 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) /* atomic_inc_return makes it start at 1, make it start at 0 */ rdev->wpan_phy_idx--; - mutex_init(&rdev->wpan_phy.pib_lock); - INIT_LIST_HEAD(&rdev->wpan_dev_list); device_initialize(&rdev->wpan_phy.dev); dev_set_name(&rdev->wpan_phy.dev, PHY_NAME "%d", rdev->wpan_phy_idx); diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 2b4955d7aae5..3503c38954f9 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -97,8 +97,10 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, BUG_ON(!phy); get_device(&phy->dev); - short_addr = ops->get_short_addr(dev); - pan_id = ops->get_pan_id(dev); + rtnl_lock(); + short_addr = dev->ieee802154_ptr->short_addr; + pan_id = dev->ieee802154_ptr->pan_id; + rtnl_unlock(); if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || @@ -117,12 +119,12 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, rtnl_unlock(); if (nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, - params.transmit_power) || + params.transmit_power / 100) || nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, params.lbt) || nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, params.cca.mode) || nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, - params.cca_ed_level) || + params.cca_ed_level / 100) || nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES, params.csma_retries) || nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE, @@ -166,10 +168,7 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) if (!dev) return NULL; - /* Check on mtu is currently a hacked solution because lowpan - * and wpan have the same ARPHRD type. - */ - if (dev->type != ARPHRD_IEEE802154 || dev->mtu != IEEE802154_MTU) { + if (dev->type != ARPHRD_IEEE802154) { dev_put(dev); return NULL; } @@ -244,7 +243,9 @@ int ieee802154_associate_resp(struct sk_buff *skb, struct genl_info *info) addr.mode = IEEE802154_ADDR_LONG; addr.extended_addr = nla_get_hwaddr( info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]); - addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + rtnl_lock(); + addr.pan_id = dev->ieee802154_ptr->pan_id; + rtnl_unlock(); ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr, nla_get_shortaddr(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), @@ -281,7 +282,9 @@ int ieee802154_disassociate_req(struct sk_buff *skb, struct genl_info *info) addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]); } - addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + rtnl_lock(); + addr.pan_id = dev->ieee802154_ptr->pan_id; + rtnl_unlock(); ret = ieee802154_mlme_ops(dev)->disassoc_req(dev, &addr, nla_get_u8(info->attrs[IEEE802154_ATTR_REASON])); @@ -449,11 +452,7 @@ int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; for_each_netdev(net, dev) { - /* Check on mtu is currently a hacked solution because lowpan - * and wpan have the same ARPHRD type. - */ - if (idx < s_idx || dev->type != ARPHRD_IEEE802154 || - dev->mtu != IEEE802154_MTU) + if (idx < s_idx || dev->type != ARPHRD_IEEE802154) goto cont; if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).portid, @@ -510,7 +509,7 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info) ops->get_mac_params(dev, ¶ms); if (info->attrs[IEEE802154_ATTR_TXPOWER]) - params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]); + params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]) * 100; if (info->attrs[IEEE802154_ATTR_LBT_ENABLED]) params.lbt = nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]); @@ -519,7 +518,7 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info) params.cca.mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]); if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) - params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]); + params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) * 100; if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES]) params.csma_retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]); @@ -783,11 +782,7 @@ ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb, int rc; for_each_netdev(net, dev) { - /* Check on mtu is currently a hacked solution because lowpan - * and wpan have the same ARPHRD type. - */ - if (idx < first_dev || dev->type != ARPHRD_IEEE802154 || - dev->mtu != IEEE802154_MTU) + if (idx < first_dev || dev->type != ARPHRD_IEEE802154) goto skip; data.ops = ieee802154_mlme_ops(dev); diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 346c6665d25e..77d73014bde3 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -50,26 +50,26 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, if (!hdr) goto out; - mutex_lock(&phy->pib_lock); + rtnl_lock(); if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) || nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel)) goto nla_put_failure; for (i = 0; i < 32; i++) { - if (phy->channels_supported[i]) - buf[pages++] = phy->channels_supported[i] | (i << 27); + if (phy->supported.channels[i]) + buf[pages++] = phy->supported.channels[i] | (i << 27); } if (pages && nla_put(msg, IEEE802154_ATTR_CHANNEL_PAGE_LIST, pages * sizeof(uint32_t), buf)) goto nla_put_failure; - mutex_unlock(&phy->pib_lock); + rtnl_unlock(); kfree(buf); genlmsg_end(msg, hdr); return 0; nla_put_failure: - mutex_unlock(&phy->pib_lock); + rtnl_unlock(); genlmsg_cancel(msg, hdr); out: kfree(buf); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index f3c12f6a4a39..7dbb1f4ce7df 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -207,10 +207,11 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_PAGE] = { .type = NLA_U8, }, [NL802154_ATTR_CHANNEL] = { .type = NLA_U8, }, - [NL802154_ATTR_TX_POWER] = { .type = NLA_S8, }, + [NL802154_ATTR_TX_POWER] = { .type = NLA_S32, }, [NL802154_ATTR_CCA_MODE] = { .type = NLA_U32, }, [NL802154_ATTR_CCA_OPT] = { .type = NLA_U32, }, + [NL802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, }, [NL802154_ATTR_SUPPORTED_CHANNEL] = { .type = NLA_U32, }, @@ -225,6 +226,8 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_MAX_FRAME_RETRIES] = { .type = NLA_S8, }, [NL802154_ATTR_LBT_MODE] = { .type = NLA_U8, }, + + [NL802154_ATTR_WPAN_PHY_CAPS] = { .type = NLA_NESTED }, }; /* message building helper */ @@ -236,6 +239,28 @@ static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq, } static int +nl802154_put_flags(struct sk_buff *msg, int attr, u32 mask) +{ + struct nlattr *nl_flags = nla_nest_start(msg, attr); + int i; + + if (!nl_flags) + return -ENOBUFS; + + i = 0; + while (mask) { + if ((mask & 1) && nla_put_flag(msg, i)) + return -ENOBUFS; + + mask >>= 1; + i++; + } + + nla_nest_end(msg, nl_flags); + return 0; +} + +static int nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, struct sk_buff *msg) { @@ -248,7 +273,7 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, for (page = 0; page <= IEEE802154_MAX_PAGE; page++) { if (nla_put_u32(msg, NL802154_ATTR_SUPPORTED_CHANNEL, - rdev->wpan_phy.channels_supported[page])) + rdev->wpan_phy.supported.channels[page])) return -ENOBUFS; } nla_nest_end(msg, nl_page); @@ -256,6 +281,92 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, return 0; } +static int +nl802154_put_capabilities(struct sk_buff *msg, + struct cfg802154_registered_device *rdev) +{ + const struct wpan_phy_supported *caps = &rdev->wpan_phy.supported; + struct nlattr *nl_caps, *nl_channels; + int i; + + nl_caps = nla_nest_start(msg, NL802154_ATTR_WPAN_PHY_CAPS); + if (!nl_caps) + return -ENOBUFS; + + nl_channels = nla_nest_start(msg, NL802154_CAP_ATTR_CHANNELS); + if (!nl_channels) + return -ENOBUFS; + + for (i = 0; i <= IEEE802154_MAX_PAGE; i++) { + if (caps->channels[i]) { + if (nl802154_put_flags(msg, i, caps->channels[i])) + return -ENOBUFS; + } + } + + nla_nest_end(msg, nl_channels); + + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { + struct nlattr *nl_ed_lvls; + + nl_ed_lvls = nla_nest_start(msg, + NL802154_CAP_ATTR_CCA_ED_LEVELS); + if (!nl_ed_lvls) + return -ENOBUFS; + + for (i = 0; i < caps->cca_ed_levels_size; i++) { + if (nla_put_s32(msg, i, caps->cca_ed_levels[i])) + return -ENOBUFS; + } + + nla_nest_end(msg, nl_ed_lvls); + } + + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { + struct nlattr *nl_tx_pwrs; + + nl_tx_pwrs = nla_nest_start(msg, NL802154_CAP_ATTR_TX_POWERS); + if (!nl_tx_pwrs) + return -ENOBUFS; + + for (i = 0; i < caps->tx_powers_size; i++) { + if (nla_put_s32(msg, i, caps->tx_powers[i])) + return -ENOBUFS; + } + + nla_nest_end(msg, nl_tx_pwrs); + } + + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) { + if (nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_MODES, + caps->cca_modes) || + nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_OPTS, + caps->cca_opts)) + return -ENOBUFS; + } + + if (nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MINBE, caps->min_minbe) || + nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MINBE, caps->max_minbe) || + nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MAXBE, caps->min_maxbe) || + nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MAXBE, caps->max_maxbe) || + nla_put_u8(msg, NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS, + caps->min_csma_backoffs) || + nla_put_u8(msg, NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS, + caps->max_csma_backoffs) || + nla_put_s8(msg, NL802154_CAP_ATTR_MIN_FRAME_RETRIES, + caps->min_frame_retries) || + nla_put_s8(msg, NL802154_CAP_ATTR_MAX_FRAME_RETRIES, + caps->max_frame_retries) || + nl802154_put_flags(msg, NL802154_CAP_ATTR_IFTYPES, + caps->iftypes) || + nla_put_u32(msg, NL802154_CAP_ATTR_LBT, caps->lbt)) + return -ENOBUFS; + + nla_nest_end(msg, nl_caps); + + return 0; +} + static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, enum nl802154_commands cmd, struct sk_buff *msg, u32 portid, u32 seq, @@ -286,23 +397,38 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, rdev->wpan_phy.current_channel)) goto nla_put_failure; - /* supported channels array */ + /* TODO remove this behaviour, we still keep support it for a while + * so users can change the behaviour to the new one. + */ if (nl802154_send_wpan_phy_channels(rdev, msg)) goto nla_put_failure; /* cca mode */ - if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE, - rdev->wpan_phy.cca.mode)) - goto nla_put_failure; + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) { + if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE, + rdev->wpan_phy.cca.mode)) + goto nla_put_failure; + + if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) { + if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT, + rdev->wpan_phy.cca.opt)) + goto nla_put_failure; + } + } - if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) { - if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT, - rdev->wpan_phy.cca.opt)) + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { + if (nla_put_s32(msg, NL802154_ATTR_TX_POWER, + rdev->wpan_phy.transmit_power)) goto nla_put_failure; } - if (nla_put_s8(msg, NL802154_ATTR_TX_POWER, - rdev->wpan_phy.transmit_power)) + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { + if (nla_put_s32(msg, NL802154_ATTR_CCA_ED_LEVEL, + rdev->wpan_phy.cca_ed_level)) + goto nla_put_failure; + } + + if (nl802154_put_capabilities(msg, rdev)) goto nla_put_failure; finish: @@ -575,7 +701,8 @@ static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL802154_ATTR_IFTYPE]) { type = nla_get_u32(info->attrs[NL802154_ATTR_IFTYPE]); - if (type > NL802154_IFTYPE_MAX) + if (type > NL802154_IFTYPE_MAX || + !(rdev->wpan_phy.supported.iftypes & BIT(type))) return -EINVAL; } @@ -625,7 +752,8 @@ static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info) channel = nla_get_u8(info->attrs[NL802154_ATTR_CHANNEL]); /* check 802.15.4 constraints */ - if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL) + if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL || + !(rdev->wpan_phy.supported.channels[page] & BIT(channel))) return -EINVAL; return rdev_set_channel(rdev, page, channel); @@ -636,12 +764,17 @@ static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info) struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct wpan_phy_cca cca; + if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE)) + return -EOPNOTSUPP; + if (!info->attrs[NL802154_ATTR_CCA_MODE]) return -EINVAL; cca.mode = nla_get_u32(info->attrs[NL802154_ATTR_CCA_MODE]); /* checking 802.15.4 constraints */ - if (cca.mode < NL802154_CCA_ENERGY || cca.mode > NL802154_CCA_ATTR_MAX) + if (cca.mode < NL802154_CCA_ENERGY || + cca.mode > NL802154_CCA_ATTR_MAX || + !(rdev->wpan_phy.supported.cca_modes & BIT(cca.mode))) return -EINVAL; if (cca.mode == NL802154_CCA_ENERGY_CARRIER) { @@ -649,13 +782,58 @@ static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info) return -EINVAL; cca.opt = nla_get_u32(info->attrs[NL802154_ATTR_CCA_OPT]); - if (cca.opt > NL802154_CCA_OPT_ATTR_MAX) + if (cca.opt > NL802154_CCA_OPT_ATTR_MAX || + !(rdev->wpan_phy.supported.cca_opts & BIT(cca.opt))) return -EINVAL; } return rdev_set_cca_mode(rdev, &cca); } +static int nl802154_set_cca_ed_level(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + s32 ed_level; + int i; + + if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL)) + return -EOPNOTSUPP; + + if (!info->attrs[NL802154_ATTR_CCA_ED_LEVEL]) + return -EINVAL; + + ed_level = nla_get_s32(info->attrs[NL802154_ATTR_CCA_ED_LEVEL]); + + for (i = 0; i < rdev->wpan_phy.supported.cca_ed_levels_size; i++) { + if (ed_level == rdev->wpan_phy.supported.cca_ed_levels[i]) + return rdev_set_cca_ed_level(rdev, ed_level); + } + + return -EINVAL; +} + +static int nl802154_set_tx_power(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + s32 power; + int i; + + if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER)) + return -EOPNOTSUPP; + + if (!info->attrs[NL802154_ATTR_TX_POWER]) + return -EINVAL; + + power = nla_get_s32(info->attrs[NL802154_ATTR_TX_POWER]); + + for (i = 0; i < rdev->wpan_phy.supported.tx_powers_size; i++) { + if (power == rdev->wpan_phy.supported.tx_powers[i]) + return rdev_set_tx_power(rdev, power); + } + + return -EINVAL; +} + static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; @@ -668,14 +846,22 @@ static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info) return -EBUSY; /* don't change address fields on monitor */ - if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) - return -EINVAL; - - if (!info->attrs[NL802154_ATTR_PAN_ID]) + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR || + !info->attrs[NL802154_ATTR_PAN_ID]) return -EINVAL; pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]); + /* TODO + * I am not sure about to check here on broadcast pan_id. + * Broadcast is a valid setting, comment from 802.15.4: + * If this value is 0xffff, the device is not associated. + * + * This could useful to simple deassociate an device. + */ + if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) + return -EINVAL; + return rdev_set_pan_id(rdev, wpan_dev, pan_id); } @@ -691,14 +877,27 @@ static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info) return -EBUSY; /* don't change address fields on monitor */ - if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) - return -EINVAL; - - if (!info->attrs[NL802154_ATTR_SHORT_ADDR]) + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR || + !info->attrs[NL802154_ATTR_SHORT_ADDR]) return -EINVAL; short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]); + /* TODO + * I am not sure about to check here on broadcast short_addr. + * Broadcast is a valid setting, comment from 802.15.4: + * A value of 0xfffe indicates that the device has + * associated but has not been allocated an address. A + * value of 0xffff indicates that the device does not + * have a short address. + * + * I think we should allow to set these settings but + * don't allow to allow socket communication with it. + */ + if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) || + short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST)) + return -EINVAL; + return rdev_set_short_addr(rdev, wpan_dev, short_addr); } @@ -722,7 +921,11 @@ nl802154_set_backoff_exponent(struct sk_buff *skb, struct genl_info *info) max_be = nla_get_u8(info->attrs[NL802154_ATTR_MAX_BE]); /* check 802.15.4 constraints */ - if (max_be < 3 || max_be > 8 || min_be > max_be) + if (min_be < rdev->wpan_phy.supported.min_minbe || + min_be > rdev->wpan_phy.supported.max_minbe || + max_be < rdev->wpan_phy.supported.min_maxbe || + max_be > rdev->wpan_phy.supported.max_maxbe || + min_be > max_be) return -EINVAL; return rdev_set_backoff_exponent(rdev, wpan_dev, min_be, max_be); @@ -747,7 +950,8 @@ nl802154_set_max_csma_backoffs(struct sk_buff *skb, struct genl_info *info) info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]); /* check 802.15.4 constraints */ - if (max_csma_backoffs > 5) + if (max_csma_backoffs < rdev->wpan_phy.supported.min_csma_backoffs || + max_csma_backoffs > rdev->wpan_phy.supported.max_csma_backoffs) return -EINVAL; return rdev_set_max_csma_backoffs(rdev, wpan_dev, max_csma_backoffs); @@ -771,7 +975,8 @@ nl802154_set_max_frame_retries(struct sk_buff *skb, struct genl_info *info) info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]); /* check 802.15.4 constraints */ - if (max_frame_retries < -1 || max_frame_retries > 7) + if (max_frame_retries < rdev->wpan_phy.supported.min_frame_retries || + max_frame_retries > rdev->wpan_phy.supported.max_frame_retries) return -EINVAL; return rdev_set_max_frame_retries(rdev, wpan_dev, max_frame_retries); @@ -791,6 +996,9 @@ static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info) return -EINVAL; mode = !!nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]); + if (!wpan_phy_supported_bool(mode, rdev->wpan_phy.supported.lbt)) + return -EINVAL; + return rdev_set_lbt_mode(rdev, wpan_dev, mode); } @@ -937,6 +1145,22 @@ static const struct genl_ops nl802154_ops[] = { NL802154_FLAG_NEED_RTNL, }, { + .cmd = NL802154_CMD_SET_CCA_ED_LEVEL, + .doit = nl802154_set_cca_ed_level, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_SET_TX_POWER, + .doit = nl802154_set_tx_power, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | + NL802154_FLAG_NEED_RTNL, + }, + { .cmd = NL802154_CMD_SET_PAN_ID, .doit = nl802154_set_pan_id, .policy = nl802154_policy, diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h index 7b5a9dd94fe5..b2155a123f6c 100644 --- a/net/ieee802154/rdev-ops.h +++ b/net/ieee802154/rdev-ops.h @@ -75,6 +75,29 @@ rdev_set_cca_mode(struct cfg802154_registered_device *rdev, } static inline int +rdev_set_cca_ed_level(struct cfg802154_registered_device *rdev, s32 ed_level) +{ + int ret; + + trace_802154_rdev_set_cca_ed_level(&rdev->wpan_phy, ed_level); + ret = rdev->ops->set_cca_ed_level(&rdev->wpan_phy, ed_level); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + +static inline int +rdev_set_tx_power(struct cfg802154_registered_device *rdev, + s32 power) +{ + int ret; + + trace_802154_rdev_set_tx_power(&rdev->wpan_phy, power); + ret = rdev->ops->set_tx_power(&rdev->wpan_phy, power); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + +static inline int rdev_set_pan_id(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le16 pan_id) { diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index b60c65f70346..02abef2c1621 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -64,10 +64,8 @@ ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr) if (tmp->type != ARPHRD_IEEE802154) continue; - pan_id = ieee802154_mlme_ops(tmp)->get_pan_id(tmp); - short_addr = - ieee802154_mlme_ops(tmp)->get_short_addr(tmp); - + pan_id = tmp->ieee802154_ptr->pan_id; + short_addr = tmp->ieee802154_ptr->short_addr; if (pan_id == addr->pan_id && short_addr == addr->short_addr) { dev = tmp; @@ -228,15 +226,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len) goto out; } - if (dev->type != ARPHRD_IEEE802154) { - err = -ENODEV; - goto out_put; - } - sk->sk_bound_dev_if = dev->ifindex; sk_dst_reset(sk); -out_put: dev_put(dev); out: release_sock(sk); @@ -286,7 +278,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) if (size > mtu) { pr_debug("size = %Zu, mtu = %u\n", size, mtu); - err = -EINVAL; + err = -EMSGSIZE; goto out_dev; } @@ -797,9 +789,9 @@ static int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) /* Data frame processing */ BUG_ON(dev->type != ARPHRD_IEEE802154); - pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev); - hw_addr = ieee802154_devaddr_from_raw(dev->dev_addr); + pan_id = dev->ieee802154_ptr->pan_id; + short_addr = dev->ieee802154_ptr->short_addr; + hw_addr = dev->ieee802154_ptr->extended_addr; read_lock(&dgram_lock); sk_for_each(sk, &dgram_head) { @@ -1014,7 +1006,7 @@ static int ieee802154_create(struct net *net, struct socket *sock, } rc = -ENOMEM; - sk = sk_alloc(net, PF_IEEE802154, GFP_KERNEL, proto); + sk = sk_alloc(net, PF_IEEE802154, GFP_KERNEL, proto, kern); if (!sk) goto out; rc = 0; diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h index 5ac25eb6ed17..73eb7605c1eb 100644 --- a/net/ieee802154/trace.h +++ b/net/ieee802154/trace.h @@ -1,4 +1,4 @@ -/* Based on net/wireless/tracing.h */ +/* Based on net/wireless/trace.h */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cfg802154 @@ -93,6 +93,21 @@ TRACE_EVENT(802154_rdev_set_channel, __entry->page, __entry->channel) ); +TRACE_EVENT(802154_rdev_set_tx_power, + TP_PROTO(struct wpan_phy *wpan_phy, s32 power), + TP_ARGS(wpan_phy, power), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + __field(s32, power) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + __entry->power = power; + ), + TP_printk(WPAN_PHY_PR_FMT ", power: %d", WPAN_PHY_PR_ARG, + __entry->power) +); + TRACE_EVENT(802154_rdev_set_cca_mode, TP_PROTO(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca), TP_ARGS(wpan_phy, cca), @@ -108,6 +123,21 @@ TRACE_EVENT(802154_rdev_set_cca_mode, WPAN_CCA_PR_ARG) ); +TRACE_EVENT(802154_rdev_set_cca_ed_level, + TP_PROTO(struct wpan_phy *wpan_phy, s32 ed_level), + TP_ARGS(wpan_phy, ed_level), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + __field(s32, ed_level) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + __entry->ed_level = ed_level; + ), + TP_printk(WPAN_PHY_PR_FMT ", ed_level: %d", WPAN_PHY_PR_ARG, + __entry->ed_level) +); + DECLARE_EVENT_CLASS(802154_le16_template, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 le16arg), diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index bd2901604842..d83071dccd74 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -331,8 +331,8 @@ config NET_FOU_IP_TUNNELS When this option is enabled IP tunnels can be configured to use FOU or GUE encapsulation. -config GENEVE - tristate "Generic Network Virtualization Encapsulation (Geneve)" +config GENEVE_CORE + tristate "Generic Network Virtualization Encapsulation library" depends on INET select NET_UDP_TUNNEL ---help--- diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 518c04ed666e..b36236dd6014 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -56,7 +56,7 @@ obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o -obj-$(CONFIG_GENEVE) += geneve.o +obj-$(CONFIG_GENEVE_CORE) += geneve_core.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8b47a4d79d04..cc858ef44451 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -317,7 +317,7 @@ lookup_protocol: WARN_ON(!answer_prot->slab); err = -ENOBUFS; - sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot); + sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; @@ -488,7 +488,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ - if (sk->sk_prot->get_port(sk, snum)) { + if ((snum || !inet->bind_address_no_port) && + sk->sk_prot->get_port(sk, snum)) { inet->inet_saddr = inet->inet_rcv_saddr = 0; err = -EADDRINUSE; goto out_release_sock; @@ -1430,7 +1431,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, struct net *net) { struct socket *sock; - int rc = sock_create_kern(family, type, protocol, &sock); + int rc = sock_create_kern(net, family, type, protocol, &sock); if (rc == 0) { *sk = sock->sk; @@ -1440,8 +1441,6 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, * we do not wish this socket to see incoming packets. */ (*sk)->sk_prot->unhash(*sk); - - sk_change_net(*sk, net); } return rc; } @@ -1597,7 +1596,7 @@ static __net_init int inet_init_net(struct net *net) */ seqlock_init(&net->ipv4.ip_local_ports.lock); net->ipv4.ip_local_ports.range[0] = 32768; - net->ipv4.ip_local_ports.range[1] = 61000; + net->ipv4.ip_local_ports.range[1] = 60999; seqlock_init(&net->ipv4.ping_group_range.lock); /* diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 8d695b6659c7..28ec3c1823bf 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -713,8 +713,6 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, struct hlist_head *dest; unsigned int new_hash; - hlist_del(&fi->fib_hash); - new_hash = fib_info_hashfn(fi); dest = &new_info_hash[new_hash]; hlist_add_head(&fi->fib_hash, dest); @@ -731,8 +729,6 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, struct hlist_head *ldest; unsigned int new_hash; - hlist_del(&fi->fib_lhash); - new_hash = fib_laddr_hashfn(fi->fib_prefsrc); ldest = &new_laddrhash[new_hash]; hlist_add_head(&fi->fib_lhash, ldest); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 09b62e17dd8c..3c699c4e90a4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -72,6 +72,7 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> @@ -324,13 +325,15 @@ static inline void empty_child_dec(struct key_vector *n) static struct key_vector *leaf_new(t_key key, struct fib_alias *fa) { - struct tnode *kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); - struct key_vector *l = kv->kv; + struct key_vector *l; + struct tnode *kv; + kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); if (!kv) return NULL; /* initialize key vector */ + l = kv->kv; l->key = key; l->pos = 0; l->bits = 0; @@ -345,24 +348,26 @@ static struct key_vector *leaf_new(t_key key, struct fib_alias *fa) static struct key_vector *tnode_new(t_key key, int pos, int bits) { - struct tnode *tnode = tnode_alloc(bits); unsigned int shift = pos + bits; - struct key_vector *tn = tnode->kv; + struct key_vector *tn; + struct tnode *tnode; /* verify bits and pos their msb bits clear and values are valid */ BUG_ON(!bits || (shift > KEYLENGTH)); - pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0), - sizeof(struct key_vector *) << bits); - + tnode = tnode_alloc(bits); if (!tnode) return NULL; + pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0), + sizeof(struct key_vector *) << bits); + if (bits == KEYLENGTH) tnode->full_children = 1; else tnode->empty_children = 1ul << bits; + tn = tnode->kv; tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0; tn->pos = pos; tn->bits = bits; @@ -1166,13 +1171,13 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; - err = netdev_switch_fib_ipv4_add(key, plen, fi, - new_fa->fa_tos, - cfg->fc_type, - cfg->fc_nlflags, - tb->tb_id); + err = switchdev_fib_ipv4_add(key, plen, fi, + new_fa->fa_tos, + cfg->fc_type, + cfg->fc_nlflags, + tb->tb_id); if (err) { - netdev_switch_fib_ipv4_abort(fi); + switchdev_fib_ipv4_abort(fi); kmem_cache_free(fn_alias_kmem, new_fa); goto out; } @@ -1216,12 +1221,10 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->tb_id = tb->tb_id; /* (Optionally) offload fib entry to switch hardware. */ - err = netdev_switch_fib_ipv4_add(key, plen, fi, tos, - cfg->fc_type, - cfg->fc_nlflags, - tb->tb_id); + err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type, + cfg->fc_nlflags, tb->tb_id); if (err) { - netdev_switch_fib_ipv4_abort(fi); + switchdev_fib_ipv4_abort(fi); goto out_free_new_fa; } @@ -1240,7 +1243,7 @@ succeeded: return 0; out_sw_fib_del: - netdev_switch_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id); + switchdev_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: @@ -1518,8 +1521,8 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if (!fa_to_delete) return -ESRCH; - netdev_switch_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos, - cfg->fc_type, tb->tb_id); + switchdev_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos, + cfg->fc_type, tb->tb_id); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -1768,10 +1771,9 @@ void fib_table_flush_external(struct fib_table *tb) if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD)) continue; - netdev_switch_fib_ipv4_del(n->key, - KEYLENGTH - fa->fa_slen, - fi, fa->fa_tos, - fa->fa_type, tb->tb_id); + switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen, + fi, fa->fa_tos, fa->fa_type, + tb->tb_id); } /* update leaf slen */ @@ -1836,10 +1838,9 @@ int fib_table_flush(struct fib_table *tb) continue; } - netdev_switch_fib_ipv4_del(n->key, - KEYLENGTH - fa->fa_slen, - fi, fa->fa_tos, - fa->fa_type, tb->tb_id); + switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen, + fi, fa->fa_tos, fa->fa_type, + tb->tb_id); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); @@ -2057,11 +2058,12 @@ static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter) static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { - struct key_vector *n, *pn = t->kv; + struct key_vector *n, *pn; if (!t) return NULL; + pn = t->kv; n = rcu_dereference(pn->tnode[0]); if (!n) return NULL; diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve_core.c index 8986e63f3bda..311a4ba6950a 100644 --- a/net/ipv4/geneve.c +++ b/net/ipv4/geneve_core.c @@ -60,11 +60,6 @@ struct geneve_net { static int geneve_net_id; -static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) -{ - return (struct genevehdr *)(udp_hdr(skb) + 1); -} - static struct geneve_sock *geneve_find_sock(struct net *net, sa_family_t family, __be16 port) { @@ -435,7 +430,7 @@ static int __init geneve_init_module(void) if (rc) return rc; - pr_info("Geneve driver\n"); + pr_info("Geneve core logic\n"); return 0; } @@ -449,5 +444,4 @@ module_exit(geneve_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jesse Gross <jesse@nicira.com>"); -MODULE_DESCRIPTION("Driver for GENEVE encapsulated traffic"); -MODULE_ALIAS_RTNL_LINK("geneve"); +MODULE_DESCRIPTION("Driver library for GENEVE encapsulated traffic"); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a3a697f5ffba..651cdf648ec4 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1339,6 +1339,168 @@ out: } EXPORT_SYMBOL(ip_mc_inc_group); +static int ip_mc_check_iphdr(struct sk_buff *skb) +{ + const struct iphdr *iph; + unsigned int len; + unsigned int offset = skb_network_offset(skb) + sizeof(*iph); + + if (!pskb_may_pull(skb, offset)) + return -EINVAL; + + iph = ip_hdr(skb); + + if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) + return -EINVAL; + + offset += ip_hdrlen(skb) - sizeof(*iph); + + if (!pskb_may_pull(skb, offset)) + return -EINVAL; + + iph = ip_hdr(skb); + + if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + return -EINVAL; + + len = skb_network_offset(skb) + ntohs(iph->tot_len); + if (skb->len < len || len < offset) + return -EINVAL; + + skb_set_transport_header(skb, offset); + + return 0; +} + +static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) +{ + unsigned int len = skb_transport_offset(skb); + + len += sizeof(struct igmpv3_report); + + return pskb_may_pull(skb, len) ? 0 : -EINVAL; +} + +static int ip_mc_check_igmp_query(struct sk_buff *skb) +{ + unsigned int len = skb_transport_offset(skb); + + len += sizeof(struct igmphdr); + if (skb->len < len) + return -EINVAL; + + /* IGMPv{1,2}? */ + if (skb->len != len) { + /* or IGMPv3? */ + len += sizeof(struct igmpv3_query) - sizeof(struct igmphdr); + if (skb->len < len || !pskb_may_pull(skb, len)) + return -EINVAL; + } + + /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer + * all-systems destination addresses (224.0.0.1) for general queries + */ + if (!igmp_hdr(skb)->group && + ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) + return -EINVAL; + + return 0; +} + +static int ip_mc_check_igmp_msg(struct sk_buff *skb) +{ + switch (igmp_hdr(skb)->type) { + case IGMP_HOST_LEAVE_MESSAGE: + case IGMP_HOST_MEMBERSHIP_REPORT: + case IGMPV2_HOST_MEMBERSHIP_REPORT: + /* fall through */ + return 0; + case IGMPV3_HOST_MEMBERSHIP_REPORT: + return ip_mc_check_igmp_reportv3(skb); + case IGMP_HOST_MEMBERSHIP_QUERY: + return ip_mc_check_igmp_query(skb); + default: + return -ENOMSG; + } +} + +static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb) +{ + return skb_checksum_simple_validate(skb); +} + +static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) + +{ + struct sk_buff *skb_chk; + unsigned int transport_len; + unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); + int ret; + + transport_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb); + + skb_get(skb); + skb_chk = skb_checksum_trimmed(skb, transport_len, + ip_mc_validate_checksum); + if (!skb_chk) + return -EINVAL; + + if (!pskb_may_pull(skb_chk, len)) { + kfree_skb(skb_chk); + return -EINVAL; + } + + ret = ip_mc_check_igmp_msg(skb_chk); + if (ret) { + kfree_skb(skb_chk); + return ret; + } + + if (skb_trimmed) + *skb_trimmed = skb_chk; + else + kfree_skb(skb_chk); + + return 0; +} + +/** + * ip_mc_check_igmp - checks whether this is a sane IGMP packet + * @skb: the skb to validate + * @skb_trimmed: to store an skb pointer trimmed to IPv4 packet tail (optional) + * + * Checks whether an IPv4 packet is a valid IGMP packet. If so sets + * skb network and transport headers accordingly and returns zero. + * + * -EINVAL: A broken packet was detected, i.e. it violates some internet + * standard + * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. + * -ENOMEM: A memory allocation failure happened. + * + * Optionally, an skb pointer might be provided via skb_trimmed (or set it + * to NULL): After parsing an IGMP packet successfully it will point to + * an skb which has its tail aligned to the IP packet end. This might + * either be the originally provided skb or a trimmed, cloned version if + * the skb frame had data beyond the IP packet. A cloned skb allows us + * to leave the original skb and its full frame unchanged (which might be + * desirable for layer 2 frame jugglers). + * + * The caller needs to release a reference count from any returned skb_trimmed. + */ +int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) +{ + int ret = ip_mc_check_iphdr(skb); + + if (ret < 0) + return ret; + + if (ip_hdr(skb)->protocol != IPPROTO_IGMP) + return -ENOMSG; + + return __ip_mc_check_igmp(skb, skb_trimmed); +} +EXPORT_SYMBOL(ip_mc_check_igmp); + /* * Resend IGMP JOIN report; used by netdev notifier. */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8976ca423a07..60021d0d9326 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -99,6 +99,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) struct net *net = sock_net(sk); int smallest_size = -1, smallest_rover; kuid_t uid = sock_i_uid(sk); + int attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0; local_bh_disable(); if (!snum) { @@ -106,6 +107,14 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) again: inet_get_local_port_range(net, &low, &high); + if (attempt_half) { + int half = low + ((high - low) >> 1); + + if (attempt_half == 1) + high = half; + else + low = half; + } remaining = (high - low) + 1; smallest_rover = rover = prandom_u32() % remaining + low; @@ -127,11 +136,6 @@ again: (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; - if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 && - !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) { - snum = smallest_rover; - goto tb_found; - } } if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) { snum = rover; @@ -159,6 +163,11 @@ again: snum = smallest_rover; goto have_snum; } + if (attempt_half == 1) { + /* OK we now try the upper half of the range */ + attempt_half = 2; + goto again; + } goto fail; } /* OK, here is the one we will use. HEAD is diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c6fb80bd5826..5f9b063bbe8a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/wait.h> +#include <linux/vmalloc.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> @@ -90,10 +91,6 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, const unsigned short snum) { - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - - atomic_inc(&hashinfo->bsockets); - inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &tb->owners); tb->num_owners++; @@ -111,8 +108,6 @@ static void __inet_put_port(struct sock *sk) struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash]; struct inet_bind_bucket *tb; - atomic_dec(&hashinfo->bsockets); - spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; __sk_del_bind_node(sk); @@ -399,9 +394,10 @@ not_unique: return -EADDRNOTAVAIL; } -static inline u32 inet_sk_port_offset(const struct sock *sk) +static u32 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); + return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr, inet->inet_daddr, inet->inet_dport); @@ -507,8 +503,14 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; + /* By starting with offset being an even number, + * we tend to leave about 50% of ports for other uses, + * like bind(0). + */ + offset &= ~1; + local_bh_disable(); - for (i = 1; i <= remaining; i++) { + for (i = 0; i < remaining; i++) { port = low + (i + offset) % remaining; if (inet_is_local_reserved_port(net, port)) continue; @@ -552,7 +554,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, return -EADDRNOTAVAIL; ok: - hint += i; + hint += (i + 2) & ~1; /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, port); @@ -599,7 +601,11 @@ out: int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk), + u32 port_offset = 0; + + if (!inet_sk(sk)->inet_num) + port_offset = inet_sk_port_offset(sk); + return __inet_hash_connect(death_row, sk, port_offset, __inet_check_established); } EXPORT_SYMBOL_GPL(inet_hash_connect); @@ -608,7 +614,6 @@ void inet_hashinfo_init(struct inet_hashinfo *h) { int i; - atomic_set(&h->bsockets, 0); for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].head, @@ -616,3 +621,33 @@ void inet_hashinfo_init(struct inet_hashinfo *h) } } EXPORT_SYMBOL_GPL(inet_hashinfo_init); + +int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) +{ + unsigned int i, nblocks = 1; + + if (sizeof(spinlock_t) != 0) { + /* allocate 2 cache lines or at least one spinlock per cpu */ + nblocks = max_t(unsigned int, + 2 * L1_CACHE_BYTES / sizeof(spinlock_t), + 1); + nblocks = roundup_pow_of_two(nblocks * num_possible_cpus()); + + /* no more locks than number of hash buckets */ + nblocks = min(nblocks, hashinfo->ehash_mask + 1); + + hashinfo->ehash_locks = kmalloc_array(nblocks, sizeof(spinlock_t), + GFP_KERNEL | __GFP_NOWARN); + if (!hashinfo->ehash_locks) + hashinfo->ehash_locks = vmalloc(nblocks * sizeof(spinlock_t)); + + if (!hashinfo->ehash_locks) + return -ENOMEM; + + for (i = 0; i < nblocks; i++) + spin_lock_init(&hashinfo->ehash_locks[i]); + } + hashinfo->ehash_locks_mask = nblocks - 1; + return 0; +} +EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 00ec8d5d7e7e..2ffbd16b79e0 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -170,7 +170,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); -void tw_timer_handler(unsigned long data) +static void tw_timer_handler(unsigned long data) { struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3674484946a5..2d3aa408fbdc 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,17 +39,21 @@ #include <net/route.h> #include <net/xfrm.h> -static bool ip_may_fragment(const struct sk_buff *skb) -{ - return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || - skb->ignore_df; -} - static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; + if (unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)) + return false; + + /* original fragment exceeds mtu and DF is set */ + if (unlikely(IPCB(skb)->frag_max_size > mtu)) + return true; + + if (skb->ignore_df) + return false; + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) return false; @@ -114,7 +118,7 @@ int ip_forward(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) { + if (ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index cc1da6d9cb35..a50dc6d408d1 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -75,6 +75,7 @@ struct ipq { __be16 id; u8 protocol; u8 ecn; /* RFC3168 support */ + u16 max_df_size; /* largest frag with DF set seen */ int iif; unsigned int rid; struct inet_peer *peer; @@ -173,6 +174,15 @@ static void ipq_kill(struct ipq *ipq) inet_frag_kill(&ipq->q, &ip4_frags); } +static bool frag_expire_skip_icmp(u32 user) +{ + return user == IP_DEFRAG_AF_PACKET || + ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN, + __IP_DEFRAG_CONNTRACK_IN_END) || + ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN, + __IP_DEFRAG_CONNTRACK_BRIDGE_IN); +} + /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ @@ -217,10 +227,8 @@ static void ip_expire(unsigned long arg) /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ - if (qp->user == IP_DEFRAG_AF_PACKET || - ((qp->user >= IP_DEFRAG_CONNTRACK_IN) && - (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) && - (skb_rtable(head)->rt_type != RTN_LOCAL))) + if (frag_expire_skip_icmp(qp->user) && + (skb_rtable(head)->rt_type != RTN_LOCAL)) goto out_rcu_unlock; /* Send an ICMP "Fragment Reassembly Timeout" message. */ @@ -319,6 +327,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct sk_buff *prev, *next; struct net_device *dev; + unsigned int fragsize; int flags, offset; int ihl, end; int err = -ENOENT; @@ -474,9 +483,14 @@ found: if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; + fragsize = skb->len + ihl; + + if (fragsize > qp->q.max_size) + qp->q.max_size = fragsize; + if (ip_hdr(skb)->frag_off & htons(IP_DF) && - skb->len + ihl > qp->q.max_size) - qp->q.max_size = skb->len + ihl; + fragsize > qp->max_df_size) + qp->max_df_size = fragsize; if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && qp->q.meat == qp->q.len) { @@ -606,13 +620,27 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->next = NULL; head->dev = dev; head->tstamp = qp->q.stamp; - IPCB(head)->frag_max_size = qp->q.max_size; + IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); iph = ip_hdr(head); - /* max_size != 0 implies at least one fragment had IP_DF set */ - iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0; iph->tot_len = htons(len); iph->tos |= ecn; + + /* When we set IP_DF on a refragmented skb we must also force a + * call to ip_fragment to avoid forwarding a DF-skb of size s while + * original sender only sent fragments of size f (where f < s). + * + * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest + * frag seen to avoid sending tiny DF-fragments in case skb was built + * from one very small df-fragment and one large non-df frag. + */ + if (qp->max_df_size == qp->q.max_size) { + IPCB(head)->flags |= IPSKB_FRAG_PMTU; + iph->frag_off = htons(IP_DF); + } else { + iph->frag_off = 0; + } + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS); qp->q.fragments = NULL; qp->q.fragments_tail = NULL; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c65b93a7b711..f5f5ef1cebd5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -83,6 +83,10 @@ int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; EXPORT_SYMBOL(sysctl_ip_default_ttl); +static int ip_fragment(struct sock *sk, struct sk_buff *skb, + unsigned int mtu, + int (*output)(struct sock *, struct sk_buff *)); + /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) { @@ -91,7 +95,7 @@ void ip_send_check(struct iphdr *iph) } EXPORT_SYMBOL(ip_send_check); -int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) +static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); @@ -216,7 +220,8 @@ static inline int ip_finish_output2(struct sock *sk, struct sk_buff *skb) return -EINVAL; } -static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) +static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, + unsigned int mtu) { netdev_features_t features; struct sk_buff *segs; @@ -224,7 +229,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) /* common case: locally created skb or seglen is <= mtu */ if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || - skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb)) + skb_gso_network_seglen(skb) <= mtu) return ip_finish_output2(sk, skb); /* Slowpath - GSO segment length is exceeding the dst MTU. @@ -248,7 +253,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) int err; segs->next = NULL; - err = ip_fragment(sk, segs, ip_finish_output2); + err = ip_fragment(sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; @@ -260,6 +265,8 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) static int ip_finish_output(struct sock *sk, struct sk_buff *skb) { + unsigned int mtu; + #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { @@ -267,11 +274,12 @@ static int ip_finish_output(struct sock *sk, struct sk_buff *skb) return dst_output_sk(sk, skb); } #endif + mtu = ip_skb_dst_mtu(skb); if (skb_is_gso(skb)) - return ip_finish_output_gso(sk, skb); + return ip_finish_output_gso(sk, skb, mtu); - if (skb->len > ip_skb_dst_mtu(skb)) - return ip_fragment(sk, skb, ip_finish_output2); + if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU)) + return ip_fragment(sk, skb, mtu, ip_finish_output2); return ip_finish_output2(sk, skb); } @@ -478,6 +486,31 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } +static int ip_fragment(struct sock *sk, struct sk_buff *skb, + unsigned int mtu, + int (*output)(struct sock *, struct sk_buff *)) +{ + struct iphdr *iph = ip_hdr(skb); + + if ((iph->frag_off & htons(IP_DF)) == 0) + return ip_do_fragment(sk, skb, output); + + if (unlikely(!skb->ignore_df || + (IPCB(skb)->frag_max_size && + IPCB(skb)->frag_max_size > mtu))) { + struct rtable *rt = skb_rtable(skb); + struct net_device *dev = rt->dst.dev; + + IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + kfree_skb(skb); + return -EMSGSIZE; + } + + return ip_do_fragment(sk, skb, output); +} + /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus @@ -485,8 +518,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) * single device frame, and queue such a frame for sending. */ -int ip_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)) +int ip_do_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)) { struct iphdr *iph; int ptr; @@ -507,15 +540,8 @@ int ip_fragment(struct sock *sk, struct sk_buff *skb, iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(skb); - if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || - (IPCB(skb)->frag_max_size && - IPCB(skb)->frag_max_size > mtu))) { - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); - kfree_skb(skb); - return -EMSGSIZE; - } + if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) + mtu = IPCB(skb)->frag_max_size; /* * Setup starting values. @@ -711,6 +737,9 @@ slow_path: iph = ip_hdr(skb2); iph->frag_off = htons((offset >> 3)); + if (IPCB(skb)->flags & IPSKB_FRAG_PMTU) + iph->frag_off |= htons(IP_DF); + /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE @@ -751,7 +780,7 @@ fail: IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); return err; } -EXPORT_SYMBOL(ip_fragment); +EXPORT_SYMBOL(ip_do_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) @@ -1217,11 +1246,9 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, } while (size > 0) { - int i; - - if (skb_is_gso(skb)) + if (skb_is_gso(skb)) { len = size; - else { + } else { /* Check if the remaining data fits into current packet. */ len = mtu - skb->len; @@ -1273,15 +1300,10 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, continue; } - i = skb_shinfo(skb)->nr_frags; if (len > size) len = size; - if (skb_can_coalesce(skb, i, page, offset)) { - skb_frag_size_add(&skb_shinfo(skb)->frags[i-1], len); - } else if (i < MAX_SKB_FRAGS) { - get_page(page); - skb_fill_page_desc(skb, i, page, offset, len); - } else { + + if (skb_append_pagefrags(skb, page, offset, len)) { err = -EMSGSIZE; goto error; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 7cfb0893f263..04ae2992a5cd 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -582,6 +582,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_TRANSPARENT: case IP_MINTTL: case IP_NODEFRAG: + case IP_BIND_ADDRESS_NO_PORT: case IP_UNICAST_IF: case IP_MULTICAST_TTL: case IP_MULTICAST_ALL: @@ -732,6 +733,9 @@ static int do_ip_setsockopt(struct sock *sk, int level, } inet->nodefrag = val ? 1 : 0; break; + case IP_BIND_ADDRESS_NO_PORT: + inet->bind_address_no_port = val ? 1 : 0; + break; case IP_MTU_DISCOVER: if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; @@ -1324,6 +1328,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_NODEFRAG: val = inet->nodefrag; break; + case IP_BIND_ADDRESS_NO_PORT: + val = inet->bind_address_no_port; + break; case IP_MTU_DISCOVER: val = inet->pmtudisc; break; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index ce63ab21b6cd..6a51a71a6c67 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -98,7 +98,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) return -ENOMEM; eh = (struct ethhdr *)skb->data; - if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN)) + if (likely(eth_proto_is_802_3(eh->h_proto))) skb->protocol = eh->h_proto; else skb->protocol = htons(ETH_P_802_2); @@ -165,6 +165,8 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, { int i; + netdev_stats_to_stats64(tot, &dev->stats); + for_each_possible_cpu(i) { const struct pcpu_sw_netstats *tstats = per_cpu_ptr(dev->tstats, i); @@ -185,22 +187,6 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, tot->tx_bytes += tx_bytes; } - tot->multicast = dev->stats.multicast; - - tot->rx_crc_errors = dev->stats.rx_crc_errors; - tot->rx_fifo_errors = dev->stats.rx_fifo_errors; - tot->rx_length_errors = dev->stats.rx_length_errors; - tot->rx_frame_errors = dev->stats.rx_frame_errors; - tot->rx_errors = dev->stats.rx_errors; - - tot->tx_fifo_errors = dev->stats.tx_fifo_errors; - tot->tx_carrier_errors = dev->stats.tx_carrier_errors; - tot->tx_dropped = dev->stats.tx_dropped; - tot->tx_aborted_errors = dev->stats.tx_aborted_errors; - tot->tx_errors = dev->stats.tx_errors; - - tot->collisions = dev->stats.collisions; - return tot; } EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index ff96396ebec5..254238daf58b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -251,7 +251,8 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EINVAL; } - p.i_key = p.o_key = p.i_flags = p.o_flags = 0; + p.i_key = p.o_key = 0; + p.i_flags = p.o_flags = 0; if (p.iph.ttl) p.iph.frag_off |= htons(IP_DF); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2d0e265fef6e..e7abf5145edc 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1444,7 +1444,6 @@ static int compat_find_calc_match(struct xt_entry_match *m, const char *name, const struct ipt_ip *ip, - unsigned int hookmask, int *size) { struct xt_match *match; @@ -1513,8 +1512,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { - ret = compat_find_calc_match(ematch, name, - &e->ip, e->comefrom, &off); + ret = compat_find_calc_match(ematch, name, &e->ip, &off); if (ret != 0) goto release_matches; ++j; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 771ab3d01ad3..45cb16a6a4a3 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -367,6 +367,11 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) struct clusterip_config *config; int ret; + if (par->nft_compat) { + pr_err("cannot use CLUSTERIP target from nftables compat\n"); + return -EOPNOTSUPP; + } + if (cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT_DPT) { diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index e9e67793055f..fe8cc183411e 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -18,7 +18,7 @@ #include <net/netfilter/nf_conntrack_synproxy.h> static struct iphdr * -synproxy_build_ip(struct sk_buff *skb, u32 saddr, u32 daddr) +synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct iphdr *iph; @@ -220,7 +220,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet, nth->ack_seq = th->ack_seq; tcp_flag_word(nth) = TCP_FLAG_ACK; nth->doff = tcp_hdr_size / 4; - nth->window = ntohs(htons(th->window) >> opts->wscale); + nth->window = htons(ntohs(th->window) >> opts->wscale); nth->check = 0; nth->urg_ptr = 0; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index e1f3b911dd1e..da5d483e236a 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -298,6 +298,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPACKSkippedFinWait2", LINUX_MIB_TCPACKSKIPPEDFINWAIT2), SNMP_MIB_ITEM("TCPACKSkippedTimeWait", LINUX_MIB_TCPACKSKIPPEDTIMEWAIT), SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE), + SNMP_MIB_ITEM("TCPWinProbe", LINUX_MIB_TCPWINPROBE), + SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f45f2a12f37b..f6055984c307 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -457,12 +457,9 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, } #define IP_IDENTS_SZ 2048u -struct ip_ident_bucket { - atomic_t id; - u32 stamp32; -}; -static struct ip_ident_bucket *ip_idents __read_mostly; +static atomic_t *ip_idents __read_mostly; +static u32 *ip_tstamps __read_mostly; /* In order to protect privacy, we add a perturbation to identifiers * if one generator is seldom used. This makes hard for an attacker @@ -470,15 +467,16 @@ static struct ip_ident_bucket *ip_idents __read_mostly; */ u32 ip_idents_reserve(u32 hash, int segs) { - struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ; - u32 old = ACCESS_ONCE(bucket->stamp32); + u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ; + atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; + u32 old = ACCESS_ONCE(*p_tstamp); u32 now = (u32)jiffies; u32 delta = 0; - if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) + if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); - return atomic_add_return(segs + delta, &bucket->id) - segs; + return atomic_add_return(segs + delta, p_id) - segs; } EXPORT_SYMBOL(ip_idents_reserve); @@ -2097,7 +2095,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) goto out; } if (ipv4_is_local_multicast(fl4->daddr) || - ipv4_is_lbcast(fl4->daddr)) { + ipv4_is_lbcast(fl4->daddr) || + fl4->flowi4_proto == IPPROTO_IGMP) { if (!fl4->saddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); @@ -2742,6 +2741,10 @@ int __init ip_rt_init(void) prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + ip_tstamps = kcalloc(IP_IDENTS_SZ, sizeof(*ip_tstamps), GFP_KERNEL); + if (!ip_tstamps) + panic("IP: failed to allocate ip_tstamps\n"); + for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index df849e5a10f1..d70b1f603692 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -219,9 +219,9 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, } EXPORT_SYMBOL_GPL(__cookie_v4_check); -static struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst) +struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); struct sock *child; @@ -235,7 +235,7 @@ static struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, } return child; } - +EXPORT_SYMBOL(tcp_get_cookie_sock); /* * when syncookies are in effect and tcp timestamps are enabled we stored @@ -391,7 +391,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst); - ret = get_cookie_sock(sk, skb, req, &rt->dst); + ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); /* ip_queue_xmit() depends on our flow being setup * Normal sockets get it right from inet_csk_route_child_sock() */ diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index c3852a7ff3c7..433231ccfb17 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -41,11 +41,19 @@ static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static int min_sndbuf = SOCK_MIN_SNDBUF; +static int min_rcvbuf = SOCK_MIN_RCVBUF; /* Update system visible IP port range */ static void set_local_port_range(struct net *net, int range[2]) { + bool same_parity = !((range[0] ^ range[1]) & 1); + write_seqlock(&net->ipv4.ip_local_ports.lock); + if (same_parity && !net->ipv4.ip_local_ports.warned) { + net->ipv4.ip_local_ports.warned = true; + pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n"); + } net->ipv4.ip_local_ports.range[0] = range[0]; net->ipv4.ip_local_ports.range[1] = range[1]; write_sequnlock(&net->ipv4.ip_local_ports.lock); @@ -522,7 +530,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_tcp_wmem), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "tcp_notsent_lowat", @@ -537,7 +545,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_tcp_rmem), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "tcp_app_win", @@ -702,7 +710,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = &one, .extra2 = &gso_max_segs, }, { @@ -750,7 +758,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one + .extra1 = &min_rcvbuf, }, { .procname = "udp_wmem_min", @@ -758,7 +766,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one + .extra1 = &min_sndbuf, }, { } }; @@ -821,6 +829,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { + .procname = "tcp_ecn_fallback", + .data = &init_net.ipv4.sysctl_tcp_ecn_fallback, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "ip_local_port_range", .maxlen = sizeof(init_net.ipv4.ip_local_ports.range), .data = &init_net.ipv4.ip_local_ports.range, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f1377f2a0472..65f791f74845 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -695,8 +695,9 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, struct tcp_splice_state *tss = rd_desc->arg.data; int ret; - ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len), - tss->flags); + ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, + min(rd_desc->count, len), tss->flags, + skb_socket_splice); if (ret > 0) rd_desc->count -= ret; return ret; @@ -809,16 +810,28 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, } EXPORT_SYMBOL(tcp_splice_read); -struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) +struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, + bool force_schedule) { struct sk_buff *skb; /* The TCP header must be at least 32-bit aligned. */ size = ALIGN(size, 4); + if (unlikely(tcp_under_memory_pressure(sk))) + sk_mem_reclaim_partial(sk); + skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp); - if (skb) { - if (sk_wmem_schedule(sk, skb->truesize)) { + if (likely(skb)) { + bool mem_scheduled; + + if (force_schedule) { + mem_scheduled = true; + sk_forced_mem_schedule(sk, skb->truesize); + } else { + mem_scheduled = sk_wmem_schedule(sk, skb->truesize); + } + if (likely(mem_scheduled)) { skb_reserve(skb, sk->sk_prot->max_header); /* * Make sure that we have exactly size bytes @@ -908,7 +921,8 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, + skb_queue_empty(&sk->sk_write_queue)); if (!skb) goto wait_for_memory; @@ -987,6 +1001,9 @@ do_error: if (copied) goto out; out_err: + /* make sure we wake any epoll edge trigger waiter */ + if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) + sk->sk_write_space(sk); return sk_stream_error(sk, flags, err); } @@ -1144,7 +1161,8 @@ new_segment: skb = sk_stream_alloc_skb(sk, select_size(sk, sg), - sk->sk_allocation); + sk->sk_allocation, + skb_queue_empty(&sk->sk_write_queue)); if (!skb) goto wait_for_memory; @@ -1275,6 +1293,9 @@ do_error: goto out; out_err: err = sk_stream_error(sk, flags, err); + /* make sure we wake any epoll edge trigger waiter */ + if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) + sk->sk_write_space(sk); release_sock(sk); return err; } @@ -2483,6 +2504,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level, icsk->icsk_syn_retries = val; break; + case TCP_SAVE_SYN: + if (val < 0 || val > 1) + err = -EINVAL; + else + tp->save_syn = val; + break; + case TCP_LINGER2: if (val < 0) tp->linger2 = -1; @@ -2672,6 +2700,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_bytes_acked = tp->bytes_acked; info->tcpi_bytes_received = tp->bytes_received; } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); + info->tcpi_segs_out = tp->segs_out; + info->tcpi_segs_in = tp->segs_in; } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -2821,6 +2851,42 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; break; + case TCP_SAVE_SYN: + val = tp->save_syn; + break; + case TCP_SAVED_SYN: { + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + if (tp->saved_syn) { + if (len < tp->saved_syn[0]) { + if (put_user(tp->saved_syn[0], optlen)) { + release_sock(sk); + return -EFAULT; + } + release_sock(sk); + return -EINVAL; + } + len = tp->saved_syn[0]; + if (put_user(len, optlen)) { + release_sock(sk); + return -EFAULT; + } + if (copy_to_user(optval, tp->saved_syn + 1, len)) { + release_sock(sk); + return -EFAULT; + } + tcp_saved_syn_free(tp); + release_sock(sk); + } else { + release_sock(sk); + len = 0; + if (put_user(len, optlen)) + return -EFAULT; + } + return 0; + } default: return -ENOPROTOOPT; } @@ -3025,11 +3091,12 @@ __setup("thash_entries=", set_thash_entries); static void __init tcp_init_mem(void) { - unsigned long limit = nr_free_buffer_pages() / 8; + unsigned long limit = nr_free_buffer_pages() / 16; + limit = max(limit, 128UL); - sysctl_tcp_mem[0] = limit / 4 * 3; - sysctl_tcp_mem[1] = limit; - sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; + sysctl_tcp_mem[0] = limit / 4 * 3; /* 4.68 % */ + sysctl_tcp_mem[1] = limit; /* 6.25 % */ + sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } void __init tcp_init(void) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c9ab964189a0..15c4536188a4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -359,7 +359,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) /* Check #1 */ if (tp->rcv_ssthresh < tp->window_clamp && (int)tp->rcv_ssthresh < tcp_space(sk) && - !sk_under_memory_pressure(sk)) { + !tcp_under_memory_pressure(sk)) { int incr; /* Check #2. Increase window, if skb with such overhead @@ -446,7 +446,7 @@ static void tcp_clamp_window(struct sock *sk) if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && - !sk_under_memory_pressure(sk) && + !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), sysctl_tcp_rmem[2]); @@ -1130,7 +1130,12 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, struct tcp_sacktag_state { int reord; int fack_count; - long rtt_us; /* RTT measured by SACKing never-retransmitted data */ + /* Timestamps for earliest and latest never-retransmitted segment + * that was SACKed. RTO needs the earliest RTT to stay conservative, + * but congestion control should still get an accurate delay signal. + */ + struct skb_mstamp first_sackt; + struct skb_mstamp last_sackt; int flag; }; @@ -1233,14 +1238,9 @@ static u8 tcp_sacktag_one(struct sock *sk, state->reord); if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; - /* Pick the earliest sequence sacked for RTT */ - if (state->rtt_us < 0) { - struct skb_mstamp now; - - skb_mstamp_get(&now); - state->rtt_us = skb_mstamp_us_delta(&now, - xmit_time); - } + if (state->first_sackt.v64 == 0) + state->first_sackt = *xmit_time; + state->last_sackt = *xmit_time; } if (sacked & TCPCB_LOST) { @@ -1634,7 +1634,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, - u32 prior_snd_una, long *sack_rtt_us) + u32 prior_snd_una, struct tcp_sacktag_state *state) { struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + @@ -1642,7 +1642,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2); struct tcp_sack_block sp[TCP_NUM_SACKS]; struct tcp_sack_block *cache; - struct tcp_sacktag_state state; struct sk_buff *skb; int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3); int used_sacks; @@ -1650,9 +1649,8 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, int i, j; int first_sack_index; - state.flag = 0; - state.reord = tp->packets_out; - state.rtt_us = -1L; + state->flag = 0; + state->reord = tp->packets_out; if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) @@ -1663,7 +1661,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire, num_sacks, prior_snd_una); if (found_dup_sack) - state.flag |= FLAG_DSACKING_ACK; + state->flag |= FLAG_DSACKING_ACK; /* Eliminate too old ACKs, but take into * account more or less fresh ones, they can @@ -1728,7 +1726,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } skb = tcp_write_queue_head(sk); - state.fack_count = 0; + state->fack_count = 0; i = 0; if (!tp->sacked_out) { @@ -1762,10 +1760,10 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, /* Head todo? */ if (before(start_seq, cache->start_seq)) { - skb = tcp_sacktag_skip(skb, sk, &state, + skb = tcp_sacktag_skip(skb, sk, state, start_seq); skb = tcp_sacktag_walk(skb, sk, next_dup, - &state, + state, start_seq, cache->start_seq, dup_sack); @@ -1776,7 +1774,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, goto advance_sp; skb = tcp_maybe_skipping_dsack(skb, sk, next_dup, - &state, + state, cache->end_seq); /* ...tail remains todo... */ @@ -1785,12 +1783,12 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, skb = tcp_highest_sack(sk); if (!skb) break; - state.fack_count = tp->fackets_out; + state->fack_count = tp->fackets_out; cache++; goto walk; } - skb = tcp_sacktag_skip(skb, sk, &state, cache->end_seq); + skb = tcp_sacktag_skip(skb, sk, state, cache->end_seq); /* Check overlap against next cached too (past this one already) */ cache++; continue; @@ -1800,12 +1798,12 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, skb = tcp_highest_sack(sk); if (!skb) break; - state.fack_count = tp->fackets_out; + state->fack_count = tp->fackets_out; } - skb = tcp_sacktag_skip(skb, sk, &state, start_seq); + skb = tcp_sacktag_skip(skb, sk, state, start_seq); walk: - skb = tcp_sacktag_walk(skb, sk, next_dup, &state, + skb = tcp_sacktag_walk(skb, sk, next_dup, state, start_seq, end_seq, dup_sack); advance_sp: @@ -1820,9 +1818,9 @@ advance_sp: for (j = 0; j < used_sacks; j++) tp->recv_sack_cache[i++] = sp[j]; - if ((state.reord < tp->fackets_out) && + if ((state->reord < tp->fackets_out) && ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) - tcp_update_reordering(sk, tp->fackets_out - state.reord, 0); + tcp_update_reordering(sk, tp->fackets_out - state->reord, 0); tcp_mark_lost_retrans(sk); tcp_verify_left_out(tp); @@ -1834,8 +1832,7 @@ out: WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif - *sack_rtt_us = state.rtt_us; - return state.flag; + return state->flag; } /* Limits sacked_out so that sum with lost_out isn't ever larger than @@ -3055,7 +3052,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, * arrived at the other end. */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, - u32 prior_snd_una, long sack_rtt_us) + u32 prior_snd_una, + struct tcp_sacktag_state *sack) { const struct inet_connection_sock *icsk = inet_csk(sk); struct skb_mstamp first_ackt, last_ackt, now; @@ -3063,8 +3061,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; bool fully_acked = true; - long ca_seq_rtt_us = -1L; + long sack_rtt_us = -1L; long seq_rtt_us = -1L; + long ca_rtt_us = -1L; struct sk_buff *skb; u32 pkts_acked = 0; bool rtt_update; @@ -3153,15 +3152,16 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, skb_mstamp_get(&now); if (likely(first_ackt.v64)) { seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); - ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + ca_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + } + if (sack->first_sackt.v64) { + sack_rtt_us = skb_mstamp_us_delta(&now, &sack->first_sackt); + ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt); } rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us); if (flag & FLAG_ACKED) { - const struct tcp_congestion_ops *ca_ops - = inet_csk(sk)->icsk_ca_ops; - tcp_rearm_rto(sk); if (unlikely(icsk->icsk_mtup.probe_size && !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) { @@ -3184,11 +3184,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); - if (ca_ops->pkts_acked) { - long rtt_us = min_t(ulong, ca_seq_rtt_us, sack_rtt_us); - ca_ops->pkts_acked(sk, pkts_acked, rtt_us); - } - } else if (skb && rtt_update && sack_rtt_us >= 0 && sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent @@ -3198,6 +3193,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tcp_rearm_rto(sk); } + if (icsk->icsk_ca_ops->pkts_acked) + icsk->icsk_ca_ops->pkts_acked(sk, pkts_acked, ca_rtt_us); + #if FASTRETRANS_DEBUG > 0 WARN_ON((int)tp->sacked_out < 0); WARN_ON((int)tp->lost_out < 0); @@ -3238,7 +3236,7 @@ static void tcp_ack_probe(struct sock *sk) * This function is not for random using! */ } else { - unsigned long when = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); + unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX); inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX); @@ -3466,6 +3464,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + struct tcp_sacktag_state sack_state; u32 prior_snd_una = tp->snd_una; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; @@ -3474,7 +3473,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; int acked = 0; /* Number of packets newly acked */ - long sack_rtt_us = -1L; + + sack_state.first_sackt.v64 = 0; /* We very likely will need to access write queue head. */ prefetchw(sk->sk_write_queue.next); @@ -3538,7 +3538,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (TCP_SKB_CB(skb)->sacked) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt_us); + &sack_state); if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) { flag |= FLAG_ECE; @@ -3563,7 +3563,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ acked = tp->packets_out; flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, - sack_rtt_us); + &sack_state); acked -= tp->packets_out; /* Advance cwnd if state allows */ @@ -3615,7 +3615,7 @@ old_ack: */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt_us); + &sack_state); tcp_fastretrans_alert(sk, acked, prior_unsacked, is_dupack, flag); } @@ -4514,10 +4514,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (eaten <= 0) { queue_and_out: - if (eaten < 0 && - tcp_try_rmem_schedule(sk, skb, skb->truesize)) - goto drop; - + if (eaten < 0) { + if (skb_queue_len(&sk->sk_receive_queue) == 0) + sk_forced_mem_schedule(sk, skb->truesize); + else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) + goto drop; + } eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); } tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); @@ -4788,7 +4790,7 @@ static int tcp_prune_queue(struct sock *sk) if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) tcp_clamp_window(sk); - else if (sk_under_memory_pressure(sk)) + else if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); tcp_collapse_ofo_queue(sk); @@ -4832,7 +4834,7 @@ static bool tcp_should_expand_sndbuf(const struct sock *sk) return false; /* If we are under global TCP memory pressure, do not expand. */ - if (sk_under_memory_pressure(sk)) + if (tcp_under_memory_pressure(sk)) return false; /* If we are under soft global TCP memory pressure, do not expand. */ @@ -6067,6 +6069,23 @@ static bool tcp_syn_flood_action(struct sock *sk, return want_cookie; } +static void tcp_reqsk_record_syn(const struct sock *sk, + struct request_sock *req, + const struct sk_buff *skb) +{ + if (tcp_sk(sk)->save_syn) { + u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb); + u32 *copy; + + copy = kmalloc(len + sizeof(u32), GFP_ATOMIC); + if (copy) { + copy[0] = len; + memcpy(©[1], skb_network_header(skb), len); + req->saved_syn = copy; + } + } +} + int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) @@ -6199,6 +6218,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->tfo_listener = false; af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT); } + tcp_reqsk_record_syn(sk, req, skb); return 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fc1c658ec6c1..d7d4c2b79cf2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1400,7 +1400,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } - if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb)) + if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { @@ -1626,6 +1626,7 @@ process: skb->dev = NULL; bh_lock_sock_nested(sk); + tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) @@ -1646,7 +1647,7 @@ no_tcp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; - if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) { + if (tcp_checksum_complete(skb)) { csum_error: TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS); bad_packet: @@ -1670,10 +1671,6 @@ do_time_wait: goto discard_it; } - if (skb->len < (th->doff << 2)) { - inet_twsk_put(inet_twsk(sk)); - goto bad_packet; - } if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; @@ -1802,6 +1799,7 @@ void tcp_v4_destroy_sock(struct sock *sk) /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); + tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); sock_release_memcg(sk); @@ -2410,12 +2408,15 @@ static int __net_init tcp_sk_init(struct net *net) goto fail; *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; } + net->ipv4.sysctl_tcp_ecn = 2; + net->ipv4.sysctl_tcp_ecn_fallback = 1; + net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; - return 0; + return 0; fail: tcp_sk_exit(net); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 17e7339ee5ca..4bc00cb79e60 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -451,6 +451,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; + newtp->segs_in = 0; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; @@ -539,6 +540,9 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; + newtp->saved_syn = req->saved_syn; + req->saved_syn = NULL; + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS); } return newsk; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a369e8a70b2c..eeb59befaf06 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -50,8 +50,8 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1; */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; -/* Default TSQ limit of two TSO segments */ -int sysctl_tcp_limit_output_bytes __read_mostly = 131072; +/* Default TSQ limit of four TSO segments */ +int sysctl_tcp_limit_output_bytes __read_mostly = 262144; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames @@ -350,6 +350,15 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) } } +static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) +{ + if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback) + /* tp->ecn_flags are cleared at a later point in time when + * SYN ACK is ultimatively being received. + */ + TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR); +} + static void tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th, struct sock *sk) @@ -1018,6 +1027,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); + tp->segs_out += tcp_skb_pcount(skb); /* OK, its time to fill skb_shinfo(skb)->gso_segs */ skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); @@ -1163,7 +1173,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, return -ENOMEM; /* Get a new skb... force flag on. */ - buff = sk_stream_alloc_skb(sk, nsize, gfp); + buff = sk_stream_alloc_skb(sk, nsize, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ @@ -1722,7 +1732,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, if (skb->len != skb->data_len) return tcp_fragment(sk, skb, len, mss_now, gfp); - buff = sk_stream_alloc_skb(sk, 0, gfp); + buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) return -ENOMEM; @@ -1941,7 +1951,7 @@ static int tcp_mtu_probe(struct sock *sk) } /* We're allowed to probe. Build it now. */ - nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC); + nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; sk->sk_wmem_queued += nskb->truesize; @@ -2078,7 +2088,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; - if (tso_segs == 1 || !max_segs) { + if (tso_segs == 1) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) @@ -2091,7 +2101,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } limit = mss_now; - if (tso_segs > 1 && max_segs && !tcp_urg_mode(tp)) + if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, @@ -2392,7 +2402,7 @@ u32 __tcp_select_window(struct sock *sk) if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; - if (sk_under_memory_pressure(sk)) + if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); @@ -2615,6 +2625,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) } } + /* RFC3168, section 6.1.1.1. ECN fallback */ + if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) + tcp_ecn_clear_syn(sk, skb); + tcp_retrans_try_collapse(sk, skb, cur_mss); /* Make a copy, if the first transmission SKB clone we made @@ -2816,8 +2830,10 @@ begin_fwd: * connection tear down and (memory) recovery. * Otherwise tcp_send_fin() could be tempted to either delay FIN * or even be forced to close flow without any FIN. + * In general, we want to allow one skb per socket to avoid hangs + * with edge trigger epoll() */ -static void sk_forced_wmem_schedule(struct sock *sk, int size) +void sk_forced_mem_schedule(struct sock *sk, int size) { int amt, status; @@ -2841,7 +2857,7 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ - if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) { + if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) { coalesce: TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; @@ -2864,7 +2880,7 @@ coalesce: return; } skb_reserve(skb, MAX_TCP_HEADER); - sk_forced_wmem_schedule(sk, skb->truesize); + sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); @@ -3175,7 +3191,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) /* limit to order-0 allocations */ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); - syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation); + syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation, false); if (!syn_data) goto fallback; syn_data->ip_summed = CHECKSUM_PARTIAL; @@ -3241,7 +3257,7 @@ int tcp_connect(struct sock *sk) return 0; } - buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); + buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, true); if (unlikely(!buff)) return -ENOBUFS; @@ -3382,7 +3398,7 @@ EXPORT_SYMBOL_GPL(tcp_send_ack); * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is * out-of-date with SND.UNA-1 to probe window. */ -static int tcp_xmit_probe_skb(struct sock *sk, int urgent) +static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -3400,6 +3416,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); skb_mstamp_get(&skb->skb_mstamp); + NET_INC_STATS_BH(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } @@ -3407,12 +3424,12 @@ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; - tcp_xmit_probe_skb(sk, 0); + tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } /* Initiate keepalive or window probe from timer. */ -int tcp_write_wakeup(struct sock *sk) +int tcp_write_wakeup(struct sock *sk, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -3449,8 +3466,8 @@ int tcp_write_wakeup(struct sock *sk) return err; } else { if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF)) - tcp_xmit_probe_skb(sk, 1); - return tcp_xmit_probe_skb(sk, 0); + tcp_xmit_probe_skb(sk, 1, mib); + return tcp_xmit_probe_skb(sk, 0, mib); } } @@ -3464,7 +3481,7 @@ void tcp_send_probe0(struct sock *sk) unsigned long probe_max; int err; - err = tcp_write_wakeup(sk); + err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); if (tp->packets_out || !tcp_send_head(sk)) { /* Cancel probe timer, if it is not required. */ @@ -3490,7 +3507,7 @@ void tcp_send_probe0(struct sock *sk) probe_max = TCP_RESOURCE_PROBE_INTERVAL; } inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - inet_csk_rto_backoff(icsk, probe_max), + tcp_probe0_when(sk, probe_max), TCP_RTO_MAX); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8c65dc147d8b..5b752f58a900 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -247,7 +247,7 @@ void tcp_delack_timer_handler(struct sock *sk) } out: - if (sk_under_memory_pressure(sk)) + if (tcp_under_memory_pressure(sk)) sk_mem_reclaim(sk); } @@ -616,7 +616,7 @@ static void tcp_keepalive_timer (unsigned long data) tcp_write_err(sk); goto out; } - if (tcp_write_wakeup(sk) <= 0) { + if (tcp_write_wakeup(sk, LINUX_MIB_TCPKEEPALIVE) <= 0) { icsk->icsk_probes_out++; elapsed = keepalive_intvl_when(tp); } else { diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 6bb98cc193c9..933ea903f7b8 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -15,12 +15,10 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket *sock = NULL; struct sockaddr_in udp_addr; - err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock); + err = sock_create_kern(net, AF_INET, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; - sk_change_net(sock->sk, net); - udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->local_ip; udp_addr.sin_port = cfg->local_udp_port; @@ -47,7 +45,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sock->sk); + sock_release(sock); } *sockp = NULL; return err; @@ -101,7 +99,7 @@ void udp_tunnel_sock_release(struct socket *sock) { rcu_assign_sk_user_data(sock->sk, NULL); kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sock->sk); + sock_release(sock); } EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 2e8c06108ab9..0f3f1999719a 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -48,4 +48,5 @@ obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o ifneq ($(CONFIG_IPV6),) obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o +obj-y += mcast_snoop.o endif diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 37b70e82bff8..21c2c818df3b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2121,6 +2121,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); if (!fn) goto out; + + noflags |= RTF_CACHE; for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { if (rt->dst.dev->ifindex != dev->ifindex) continue; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index eef63b394c5a..7de52b65173f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -167,7 +167,7 @@ lookup_protocol: WARN_ON(!answer_prot->slab); err = -ENOBUFS; - sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot); + sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; @@ -362,7 +362,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) np->saddr = addr->sin6_addr; /* Make sure we are allowed to bind here. */ - if (sk->sk_prot->get_port(sk, snum)) { + if ((snum || !inet->bind_address_no_port) && + sk->sk_prot->get_port(sk, snum)) { inet_reset_saddr(sk); err = -EADDRINUSE; goto out; @@ -768,6 +769,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.auto_flowlabels = 0; net->ipv6.sysctl.idgen_retries = 3; net->ipv6.sysctl.idgen_delay = 1 * HZ; + net->ipv6.sysctl.flowlabel_state_ranges = 1; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 2c2b5d51f15c..713d7434c911 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -207,7 +207,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, struct inet_peer *peer; peer = inet_getpeer_v6(net->ipv6.peers, - &rt->rt6i_dst.addr, 1); + &fl6->daddr, 1); res = inet_peer_xrlim_allow(peer, tmo); if (peer) inet_putpeer(peer); @@ -337,7 +337,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, * We won't send icmp if the destination is known * anycast. */ - if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) { + if (ipv6_anycast_destination(dst, &fl6->daddr)) { net_dbg_ratelimited("icmp6_send: acast source\n"); dst_release(dst); return ERR_PTR(-EINVAL); @@ -564,7 +564,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (!ipv6_unicast_destination(skb) && !(net->ipv6.sysctl.anycast_src_echo_reply && - ipv6_anycast_destination(skb))) + ipv6_anycast_destination(skb_dst(skb), saddr))) saddr = NULL; memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 871641bc1ed4..b4fd96de97e6 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -257,7 +257,7 @@ not_unique: return -EADDRNOTAVAIL; } -static inline u32 inet6_sk_port_offset(const struct sock *sk) +static u32 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -269,7 +269,11 @@ static inline u32 inet6_sk_port_offset(const struct sock *sk) int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk), + u32 port_offset = 0; + + if (!inet_sk(sk)->inet_num) + port_offset = inet6_sk_port_offset(sk); + return __inet_hash_connect(death_row, sk, port_offset, __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index bde57b113009..55d19861ab20 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -154,10 +154,32 @@ static void node_free(struct fib6_node *fn) kmem_cache_free(fib6_node_kmem, fn); } +static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) +{ + int cpu; + + if (!non_pcpu_rt->rt6i_pcpu) + return; + + for_each_possible_cpu(cpu) { + struct rt6_info **ppcpu_rt; + struct rt6_info *pcpu_rt; + + ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); + pcpu_rt = *ppcpu_rt; + if (pcpu_rt) { + dst_free(&pcpu_rt->dst); + *ppcpu_rt = NULL; + } + } +} + static void rt6_release(struct rt6_info *rt) { - if (atomic_dec_and_test(&rt->rt6i_ref)) + if (atomic_dec_and_test(&rt->rt6i_ref)) { + rt6_free_pcpu(rt); dst_free(&rt->dst); + } } static void fib6_link_table(struct net *net, struct fib6_table *tb) @@ -738,6 +760,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, rt6_clean_expires(iter); else rt6_set_expires(iter, rt->dst.expires); + iter->rt6i_pmtu = rt->rt6i_pmtu; return -EEXIST; } /* If we have the same destination and the same metric, diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index d491125011c4..1f9ebe3cbb4a 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -595,6 +595,10 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) if (freq.flr_label & ~IPV6_FLOWLABEL_MASK) return -EINVAL; + if (net->ipv6.sysctl.flowlabel_state_ranges && + (freq.flr_label & IPV6_FLOWLABEL_STATELESS_FLAG)) + return -ERANGE; + fl = fl_create(net, sk, &freq, optval, optlen, &err); if (!fl) return err; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index bc09cb97b840..d5f7716662db 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst); + nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -459,7 +459,7 @@ int ip6_forward(struct sk_buff *skb) else target = &hdr->daddr; - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) @@ -551,7 +551,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, struct frag_hdr *fh; unsigned int mtu, hlen, left, len; int hroom, troom; - __be32 frag_id = 0; + __be32 frag_id; int ptr, offset = 0, err = 0; u8 *prevhdr, nexthdr = 0; struct net *net = dev_net(skb_dst(skb)->dev); @@ -564,18 +564,17 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ - if (unlikely(!skb->ignore_df && skb->len > mtu) || - (IP6CB(skb)->frag_max_size && - IP6CB(skb)->frag_max_size > mtu)) { - if (skb->sk && dst_allfrag(skb_dst(skb))) - sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); + if (unlikely(!skb->ignore_df && skb->len > mtu)) + goto fail_toobig; - skb->dev = skb_dst(skb)->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_FRAGFAILS); - kfree_skb(skb); - return -EMSGSIZE; + if (IP6CB(skb)->frag_max_size) { + if (IP6CB(skb)->frag_max_size > mtu) + goto fail_toobig; + + /* don't send fragments larger than what we received */ + mtu = IP6CB(skb)->frag_max_size; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; } if (np && np->frag_size < mtu) { @@ -584,6 +583,9 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, } mtu -= hlen + sizeof(struct frag_hdr); + frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, + &ipv6_hdr(skb)->saddr); + if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); struct sk_buff *frag2; @@ -632,11 +634,10 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); - ipv6_select_ident(net, fh, rt); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); - frag_id = fh->identification; + fh->identification = frag_id; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); @@ -778,11 +779,7 @@ slow_path: */ fh->nexthdr = nexthdr; fh->reserved = 0; - if (!frag_id) { - ipv6_select_ident(net, fh, rt); - frag_id = fh->identification; - } else - fh->identification = frag_id; + fh->identification = frag_id; /* * Copy a block of the IP datagram. @@ -815,6 +812,14 @@ slow_path: consume_skb(skb); return err; +fail_toobig: + if (skb->sk && dst_allfrag(skb_dst(skb))) + sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); + + skb->dev = skb_dst(skb)->dev; + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + err = -EMSGSIZE; + fail: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); @@ -936,7 +941,8 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, + rt6_nexthop(rt, &fl6->daddr)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); @@ -1060,11 +1066,10 @@ static inline int ip6_ufo_append_data(struct sock *sk, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, int transhdrlen, int mtu, unsigned int flags, - struct rt6_info *rt) + const struct flowi6 *fl6) { struct sk_buff *skb; - struct frag_hdr fhdr; int err; /* There is support for UDP large send offload by network @@ -1106,8 +1111,9 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - sizeof(struct frag_hdr)) & ~7; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(sock_net(sk), &fhdr, rt); - skb_shinfo(skb)->ip6_frag_id = fhdr.identification; + skb_shinfo(skb)->ip6_frag_id = ipv6_select_ident(sock_net(sk), + &fl6->daddr, + &fl6->saddr); append: return skb_append_datato_frags(sk, skb, getfrag, from, @@ -1332,7 +1338,7 @@ emsgsize: (sk->sk_type == SOCK_DGRAM)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, - transhdrlen, mtu, flags, rt); + transhdrlen, mtu, flags, fl6); if (err) goto error; return 0; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5cafd92c2312..2e67b660118b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -151,7 +151,7 @@ EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *) dst; - t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + t->dst_cookie = rt6_get_cookie(rt); dst_release(t->dst_cache); t->dst_cache = dst; } diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index bba8903e871f..e1a1136bda7c 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -19,12 +19,10 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, int err; struct socket *sock = NULL; - err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock); + err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; - sk_change_net(sock->sk, net); - udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); @@ -55,7 +53,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sock->sk); + sock_release(sock); } *sockp = NULL; return err; diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c new file mode 100644 index 000000000000..df8afe5ab31e --- /dev/null +++ b/net/ipv6/mcast_snoop.c @@ -0,0 +1,213 @@ +/* Copyright (C) 2010: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> + * Copyright (C) 2015: Linus Lüssing <linus.luessing@c0d3.blue> + * + * 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, see <http://www.gnu.org/licenses/>. + * + * + * Based on the MLD support added to br_multicast.c by YOSHIFUJI Hideaki. + */ + +#include <linux/skbuff.h> +#include <net/ipv6.h> +#include <net/mld.h> +#include <net/addrconf.h> +#include <net/ip6_checksum.h> + +static int ipv6_mc_check_ip6hdr(struct sk_buff *skb) +{ + const struct ipv6hdr *ip6h; + unsigned int len; + unsigned int offset = skb_network_offset(skb) + sizeof(*ip6h); + + if (!pskb_may_pull(skb, offset)) + return -EINVAL; + + ip6h = ipv6_hdr(skb); + + if (ip6h->version != 6) + return -EINVAL; + + len = offset + ntohs(ip6h->payload_len); + if (skb->len < len || len <= offset) + return -EINVAL; + + return 0; +} + +static int ipv6_mc_check_exthdrs(struct sk_buff *skb) +{ + const struct ipv6hdr *ip6h; + int offset; + u8 nexthdr; + __be16 frag_off; + + ip6h = ipv6_hdr(skb); + + if (ip6h->nexthdr != IPPROTO_HOPOPTS) + return -ENOMSG; + + nexthdr = ip6h->nexthdr; + offset = skb_network_offset(skb) + sizeof(*ip6h); + offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); + + if (offset < 0) + return -EINVAL; + + if (nexthdr != IPPROTO_ICMPV6) + return -ENOMSG; + + skb_set_transport_header(skb, offset); + + return 0; +} + +static int ipv6_mc_check_mld_reportv2(struct sk_buff *skb) +{ + unsigned int len = skb_transport_offset(skb); + + len += sizeof(struct mld2_report); + + return pskb_may_pull(skb, len) ? 0 : -EINVAL; +} + +static int ipv6_mc_check_mld_query(struct sk_buff *skb) +{ + struct mld_msg *mld; + unsigned int len = skb_transport_offset(skb); + + /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ + if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) + return -EINVAL; + + len += sizeof(struct mld_msg); + if (skb->len < len) + return -EINVAL; + + /* MLDv1? */ + if (skb->len != len) { + /* or MLDv2? */ + len += sizeof(struct mld2_query) - sizeof(struct mld_msg); + if (skb->len < len || !pskb_may_pull(skb, len)) + return -EINVAL; + } + + mld = (struct mld_msg *)skb_transport_header(skb); + + /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer + * all-nodes destination address (ff02::1) for general queries + */ + if (ipv6_addr_any(&mld->mld_mca) && + !ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) + return -EINVAL; + + return 0; +} + +static int ipv6_mc_check_mld_msg(struct sk_buff *skb) +{ + struct mld_msg *mld = (struct mld_msg *)skb_transport_header(skb); + + switch (mld->mld_type) { + case ICMPV6_MGM_REDUCTION: + case ICMPV6_MGM_REPORT: + /* fall through */ + return 0; + case ICMPV6_MLD2_REPORT: + return ipv6_mc_check_mld_reportv2(skb); + case ICMPV6_MGM_QUERY: + return ipv6_mc_check_mld_query(skb); + default: + return -ENOMSG; + } +} + +static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb) +{ + return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo); +} + +static int __ipv6_mc_check_mld(struct sk_buff *skb, + struct sk_buff **skb_trimmed) + +{ + struct sk_buff *skb_chk = NULL; + unsigned int transport_len; + unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg); + int ret; + + transport_len = ntohs(ipv6_hdr(skb)->payload_len); + transport_len -= skb_transport_offset(skb) - sizeof(struct ipv6hdr); + + skb_get(skb); + skb_chk = skb_checksum_trimmed(skb, transport_len, + ipv6_mc_validate_checksum); + if (!skb_chk) + return -EINVAL; + + if (!pskb_may_pull(skb_chk, len)) { + kfree_skb(skb_chk); + return -EINVAL; + } + + ret = ipv6_mc_check_mld_msg(skb_chk); + if (ret) { + kfree_skb(skb_chk); + return ret; + } + + if (skb_trimmed) + *skb_trimmed = skb_chk; + else + kfree_skb(skb_chk); + + return 0; +} + +/** + * ipv6_mc_check_mld - checks whether this is a sane MLD packet + * @skb: the skb to validate + * @skb_trimmed: to store an skb pointer trimmed to IPv6 packet tail (optional) + * + * Checks whether an IPv6 packet is a valid MLD packet. If so sets + * skb network and transport headers accordingly and returns zero. + * + * -EINVAL: A broken packet was detected, i.e. it violates some internet + * standard + * -ENOMSG: IP header validation succeeded but it is not an MLD packet. + * -ENOMEM: A memory allocation failure happened. + * + * Optionally, an skb pointer might be provided via skb_trimmed (or set it + * to NULL): After parsing an MLD packet successfully it will point to + * an skb which has its tail aligned to the IP packet end. This might + * either be the originally provided skb or a trimmed, cloned version if + * the skb frame had data beyond the IP packet. A cloned skb allows us + * to leave the original skb and its full frame unchanged (which might be + * desirable for layer 2 frame jugglers). + * + * The caller needs to release a reference count from any returned skb_trimmed. + */ +int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed) +{ + int ret; + + ret = ipv6_mc_check_ip6hdr(skb); + if (ret < 0) + return ret; + + ret = ipv6_mc_check_exthdrs(skb); + if (ret < 0) + return ret; + + return __ipv6_mc_check_mld(skb, skb_trimmed); +} +EXPORT_SYMBOL(ipv6_mc_check_mld); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 96f153c0846b..0a05b35a90fc 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1506,7 +1506,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) "Redirect: destination is not a neighbour\n"); goto release; } - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1); ret = inet_peer_xrlim_allow(peer, 1*HZ); if (peer) inet_putpeer(peer); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 62f5b0d0bc9b..cdd085f8b770 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1459,7 +1459,6 @@ static int compat_find_calc_match(struct xt_entry_match *m, const char *name, const struct ip6t_ip6 *ipv6, - unsigned int hookmask, int *size) { struct xt_match *match; @@ -1528,8 +1527,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { - ret = compat_find_calc_match(ematch, name, - &e->ipv6, e->comefrom, &off); + ret = compat_find_calc_match(ematch, name, &e->ipv6, &off); if (ret != 0) goto release_matches; ++j; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 85892af57364..21678acd4521 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -10,7 +10,8 @@ #include <net/secure_seq.h> static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, - struct in6_addr *dst, struct in6_addr *src) + const struct in6_addr *dst, + const struct in6_addr *src) { u32 hash, id; @@ -60,17 +61,17 @@ void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); -void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr, - struct rt6_info *rt) +__be32 ipv6_select_ident(struct net *net, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { static u32 ip6_idents_hashrnd __read_mostly; u32 id; net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); - id = __ipv6_select_ident(net, ip6_idents_hashrnd, &rt->rt6i_dst.addr, - &rt->rt6i_src.addr); - fhdr->identification = htonl(id); + id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr); + return htonl(id); } EXPORT_SYMBOL(ipv6_select_ident); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8072bd4139b7..ca4700cb26c4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -865,6 +865,9 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + if (inet->hdrincl) + fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); @@ -1324,13 +1327,7 @@ static struct inet_protosw rawv6_protosw = { int __init rawv6_init(void) { - int ret; - - ret = inet6_register_protosw(&rawv6_protosw); - if (ret) - goto out; -out: - return ret; + return inet6_register_protosw(&rawv6_protosw); } void rawv6_exit(void) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c73ae5039e46..1a1122a6bbf5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -72,8 +72,7 @@ enum rt6_nud_state { RT6_NUD_SUCCEED = 1 }; -static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, - const struct in6_addr *dest); +static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); static unsigned int ip6_mtu(const struct dst_entry *dst); @@ -92,6 +91,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); +static void rt6_dst_from_metrics_check(struct rt6_info *rt); static int rt6_score_route(struct rt6_info *rt, int oif, int strict); #ifdef CONFIG_IPV6_ROUTE_INFO @@ -104,65 +104,82 @@ static struct rt6_info *rt6_get_route_info(struct net *net, const struct in6_addr *gwaddr, int ifindex); #endif -static void rt6_bind_peer(struct rt6_info *rt, int create) +struct uncached_list { + spinlock_t lock; + struct list_head head; +}; + +static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); + +static void rt6_uncached_list_add(struct rt6_info *rt) { - struct inet_peer_base *base; - struct inet_peer *peer; + struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); - base = inetpeer_base_ptr(rt->_rt6i_peer); - if (!base) - return; + rt->dst.flags |= DST_NOCACHE; + rt->rt6i_uncached_list = ul; + + spin_lock_bh(&ul->lock); + list_add_tail(&rt->rt6i_uncached, &ul->head); + spin_unlock_bh(&ul->lock); +} - peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); - if (peer) { - if (!rt6_set_peer(rt, peer)) - inet_putpeer(peer); +static void rt6_uncached_list_del(struct rt6_info *rt) +{ + if (!list_empty(&rt->rt6i_uncached)) { + struct uncached_list *ul = rt->rt6i_uncached_list; + + spin_lock_bh(&ul->lock); + list_del(&rt->rt6i_uncached); + spin_unlock_bh(&ul->lock); } } -static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create) +static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) { - if (rt6_has_peer(rt)) - return rt6_peer_ptr(rt); + struct net_device *loopback_dev = net->loopback_dev; + int cpu; + + for_each_possible_cpu(cpu) { + struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); + struct rt6_info *rt; + + spin_lock_bh(&ul->lock); + list_for_each_entry(rt, &ul->head, rt6i_uncached) { + struct inet6_dev *rt_idev = rt->rt6i_idev; + struct net_device *rt_dev = rt->dst.dev; + + if (rt_idev && (rt_idev->dev == dev || !dev) && + rt_idev->dev != loopback_dev) { + rt->rt6i_idev = in6_dev_get(loopback_dev); + in6_dev_put(rt_idev); + } - rt6_bind_peer(rt, create); - return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL); + if (rt_dev && (rt_dev == dev || !dev) && + rt_dev != loopback_dev) { + rt->dst.dev = loopback_dev; + dev_hold(rt->dst.dev); + dev_put(rt_dev); + } + } + spin_unlock_bh(&ul->lock); + } } -static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt) +static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt) { - return __rt6_get_peer(rt, 1); + return dst_metrics_write_ptr(rt->dst.from); } static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) { - struct rt6_info *rt = (struct rt6_info *) dst; - struct inet_peer *peer; - u32 *p = NULL; + struct rt6_info *rt = (struct rt6_info *)dst; - if (!(rt->dst.flags & DST_HOST)) + if (rt->rt6i_flags & RTF_PCPU) + return rt6_pcpu_cow_metrics(rt); + else if (rt->rt6i_flags & RTF_CACHE) + return NULL; + else return dst_cow_metrics_generic(dst, old); - - peer = rt6_get_peer_create(rt); - if (peer) { - u32 *old_p = __DST_METRICS_PTR(old); - unsigned long prev, new; - - p = peer->metrics; - if (inet_metrics_new(peer) || - (old & DST_METRICS_FORCE_OVERWRITE)) - memcpy(p, old_p, sizeof(u32) * RTAX_MAX); - - new = (unsigned long) p; - prev = cmpxchg(&dst->_metrics, old, new); - - if (prev != old) { - p = __DST_METRICS_PTR(prev); - if (prev & DST_METRICS_READ_ONLY) - p = NULL; - } - } - return p; } static inline const void *choose_neigh_daddr(struct rt6_info *rt, @@ -299,10 +316,10 @@ static const struct rt6_info ip6_blk_hole_entry_template = { #endif /* allocate dst with ip6_dst_ops */ -static inline struct rt6_info *ip6_dst_alloc(struct net *net, - struct net_device *dev, - int flags, - struct fib6_table *table) +static struct rt6_info *__ip6_dst_alloc(struct net *net, + struct net_device *dev, + int flags, + struct fib6_table *table) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0, DST_OBSOLETE_FORCE_CHK, flags); @@ -311,21 +328,54 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, struct dst_entry *dst = &rt->dst; memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); - rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); INIT_LIST_HEAD(&rt->rt6i_siblings); + INIT_LIST_HEAD(&rt->rt6i_uncached); + } + return rt; +} + +static struct rt6_info *ip6_dst_alloc(struct net *net, + struct net_device *dev, + int flags, + struct fib6_table *table) +{ + struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags, table); + + if (rt) { + rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC); + if (rt->rt6i_pcpu) { + int cpu; + + for_each_possible_cpu(cpu) { + struct rt6_info **p; + + p = per_cpu_ptr(rt->rt6i_pcpu, cpu); + /* no one shares rt */ + *p = NULL; + } + } else { + dst_destroy((struct dst_entry *)rt); + return NULL; + } } + return rt; } static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; - struct inet6_dev *idev = rt->rt6i_idev; struct dst_entry *from = dst->from; + struct inet6_dev *idev; + + dst_destroy_metrics_generic(dst); - if (!(rt->dst.flags & DST_HOST)) - dst_destroy_metrics_generic(dst); + if (rt->rt6i_pcpu) + free_percpu(rt->rt6i_pcpu); + rt6_uncached_list_del(rt); + + idev = rt->rt6i_idev; if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); @@ -333,11 +383,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) dst->from = NULL; dst_release(from); - - if (rt6_has_peer(rt)) { - struct inet_peer *peer = rt6_peer_ptr(rt); - inet_putpeer(peer); - } } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -652,15 +697,33 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, u32 metric, int oif, int strict, bool *do_rr) { - struct rt6_info *rt, *match; + struct rt6_info *rt, *match, *cont; int mpri = -1; match = NULL; - for (rt = rr_head; rt && rt->rt6i_metric == metric; - rt = rt->dst.rt6_next) + cont = NULL; + for (rt = rr_head; rt; rt = rt->dst.rt6_next) { + if (rt->rt6i_metric != metric) { + cont = rt; + break; + } + match = find_match(rt, oif, strict, &mpri, match, do_rr); - for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; - rt = rt->dst.rt6_next) + } + + for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) { + if (rt->rt6i_metric != metric) { + cont = rt; + break; + } + + match = find_match(rt, oif, strict, &mpri, match, do_rr); + } + + if (match || !cont) + return match; + + for (rt = cont; rt; rt = rt->dst.rt6_next) match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; @@ -694,6 +757,11 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) return match ? match : net->ipv6.ip6_null_entry; } +static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt) +{ + return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)); +} + #ifdef CONFIG_IPV6_ROUTE_INFO int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr) @@ -872,9 +940,9 @@ int ip6_ins_rt(struct rt6_info *rt) return __ip6_ins_rt(rt, &info, &mxc); } -static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, - const struct in6_addr *daddr, - const struct in6_addr *saddr) +static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct rt6_info *rt; @@ -882,15 +950,26 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, * Clone the route. */ - rt = ip6_rt_copy(ort, daddr); + if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) + ort = (struct rt6_info *)ort->dst.from; - if (rt) { + rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev, + 0, ort->rt6i_table); + + if (!rt) + return NULL; + + ip6_rt_copy_init(rt, ort); + rt->rt6i_flags |= RTF_CACHE; + rt->rt6i_metric = 0; + rt->dst.flags |= DST_HOST; + rt->rt6i_dst.addr = *daddr; + rt->rt6i_dst.plen = 128; + + if (!rt6_is_gw_or_nonexthop(ort)) { if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - - rt->rt6i_flags |= RTF_CACHE; - #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { rt->rt6i_src.addr = *saddr; @@ -902,30 +981,65 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, return rt; } -static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, - const struct in6_addr *daddr) +static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt) { - struct rt6_info *rt = ip6_rt_copy(ort, daddr); + struct rt6_info *pcpu_rt; - if (rt) - rt->rt6i_flags |= RTF_CACHE; - return rt; + pcpu_rt = __ip6_dst_alloc(dev_net(rt->dst.dev), + rt->dst.dev, rt->dst.flags, + rt->rt6i_table); + + if (!pcpu_rt) + return NULL; + ip6_rt_copy_init(pcpu_rt, rt); + pcpu_rt->rt6i_protocol = rt->rt6i_protocol; + pcpu_rt->rt6i_flags |= RTF_PCPU; + return pcpu_rt; +} + +/* It should be called with read_lock_bh(&tb6_lock) acquired */ +static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) +{ + struct rt6_info *pcpu_rt, *prev, **p; + + p = this_cpu_ptr(rt->rt6i_pcpu); + pcpu_rt = *p; + + if (pcpu_rt) + goto done; + + pcpu_rt = ip6_rt_pcpu_alloc(rt); + if (!pcpu_rt) { + struct net *net = dev_net(rt->dst.dev); + + pcpu_rt = net->ipv6.ip6_null_entry; + goto done; + } + + prev = cmpxchg(p, NULL, pcpu_rt); + if (prev) { + /* If someone did it before us, return prev instead */ + dst_destroy(&pcpu_rt->dst); + pcpu_rt = prev; + } + +done: + dst_hold(&pcpu_rt->dst); + rt6_dst_from_metrics_check(pcpu_rt); + return pcpu_rt; } static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { struct fib6_node *fn, *saved_fn; - struct rt6_info *rt, *nrt; + struct rt6_info *rt; int strict = 0; - int attempts = 3; - int err; strict |= flags & RT6_LOOKUP_F_IFACE; if (net->ipv6.devconf_all->forwarding == 0) strict |= RT6_LOOKUP_F_REACHABLE; -redo_fib6_lookup_lock: read_lock_bh(&table->tb6_lock); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); @@ -944,51 +1058,52 @@ redo_rt6_select: strict &= ~RT6_LOOKUP_F_REACHABLE; fn = saved_fn; goto redo_rt6_select; - } else { - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - goto out2; } } - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - if (rt->rt6i_flags & RTF_CACHE) - goto out2; + if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) { + dst_use(&rt->dst, jiffies); + read_unlock_bh(&table->tb6_lock); - if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) - nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); - else if (!(rt->dst.flags & DST_HOST)) - nrt = rt6_alloc_clone(rt, &fl6->daddr); - else - goto out2; + rt6_dst_from_metrics_check(rt); + return rt; + } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && + !(rt->rt6i_flags & RTF_GATEWAY))) { + /* Create a RTF_CACHE clone which will not be + * owned by the fib6 tree. It is for the special case where + * the daddr in the skb during the neighbor look-up is different + * from the fl6->daddr used to look-up route here. + */ - ip6_rt_put(rt); - rt = nrt ? : net->ipv6.ip6_null_entry; + struct rt6_info *uncached_rt; - dst_hold(&rt->dst); - if (nrt) { - err = ip6_ins_rt(nrt); - if (!err) - goto out2; - } + dst_use(&rt->dst, jiffies); + read_unlock_bh(&table->tb6_lock); - if (--attempts <= 0) - goto out2; + uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); + dst_release(&rt->dst); - /* - * Race condition! In the gap, when table->tb6_lock was - * released someone could insert this route. Relookup. - */ - ip6_rt_put(rt); - goto redo_fib6_lookup_lock; + if (uncached_rt) + rt6_uncached_list_add(uncached_rt); + else + uncached_rt = net->ipv6.ip6_null_entry; -out2: - rt->dst.lastuse = jiffies; - rt->dst.__use++; + dst_hold(&uncached_rt->dst); + return uncached_rt; - return rt; + } else { + /* Get a percpu copy */ + + struct rt6_info *pcpu_rt; + + rt->dst.lastuse = jiffies; + rt->dst.__use++; + pcpu_rt = rt6_get_pcpu_route(rt); + read_unlock_bh(&table->tb6_lock); + + return pcpu_rt; + } } static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, @@ -1059,7 +1174,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new = &rt->dst; memset(new + 1, 0, sizeof(*rt) - sizeof(*new)); - rt6_init_peer(rt, net->ipv6.peers); new->__use = 1; new->input = dst_discard; @@ -1093,6 +1207,33 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori * Destination cache support functions */ +static void rt6_dst_from_metrics_check(struct rt6_info *rt) +{ + if (rt->dst.from && + dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(rt->dst.from)) + dst_init_metrics(&rt->dst, dst_metrics_ptr(rt->dst.from), true); +} + +static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) +{ + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; + + if (rt6_check_expired(rt)) + return NULL; + + return &rt->dst; +} + +static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) +{ + if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + rt6_check((struct rt6_info *)(rt->dst.from), cookie)) + return &rt->dst; + else + return NULL; +} + static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { struct rt6_info *rt; @@ -1103,13 +1244,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) - return NULL; - if (rt6_check_expired(rt)) - return NULL; + rt6_dst_from_metrics_check(rt); - return dst; + if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE)) + return rt6_dst_from_check(rt, cookie); + else + return rt6_check(rt, cookie); } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -1148,24 +1289,63 @@ static void ip6_link_failure(struct sk_buff *skb) } } -static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) +static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) +{ + struct net *net = dev_net(rt->dst.dev); + + rt->rt6i_flags |= RTF_MODIFIED; + rt->rt6i_pmtu = mtu; + rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); +} + +static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, + const struct ipv6hdr *iph, u32 mtu) { struct rt6_info *rt6 = (struct rt6_info *)dst; - dst_confirm(dst); - if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) { - struct net *net = dev_net(dst->dev); + if (rt6->rt6i_flags & RTF_LOCAL) + return; - rt6->rt6i_flags |= RTF_MODIFIED; - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; + dst_confirm(dst); + mtu = max_t(u32, mtu, IPV6_MIN_MTU); + if (mtu >= dst_mtu(dst)) + return; - dst_metric_set(dst, RTAX_MTU, mtu); - rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); + if (rt6->rt6i_flags & RTF_CACHE) { + rt6_do_update_pmtu(rt6, mtu); + } else { + const struct in6_addr *daddr, *saddr; + struct rt6_info *nrt6; + + if (iph) { + daddr = &iph->daddr; + saddr = &iph->saddr; + } else if (sk) { + daddr = &sk->sk_v6_daddr; + saddr = &inet6_sk(sk)->saddr; + } else { + return; + } + nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr); + if (nrt6) { + rt6_do_update_pmtu(nrt6, mtu); + + /* ip6_ins_rt(nrt6) will bump the + * rt6->rt6i_node->fn_sernum + * which will fail the next rt6_check() and + * invalidate the sk->sk_dst_cache. + */ + ip6_ins_rt(nrt6); + } } } +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ + __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu); +} + void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark) { @@ -1182,7 +1362,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu)); + __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu)); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); @@ -1341,12 +1521,17 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) static unsigned int ip6_mtu(const struct dst_entry *dst) { + const struct rt6_info *rt = (const struct rt6_info *)dst; + unsigned int mtu = rt->rt6i_pmtu; struct inet6_dev *idev; - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + goto out; + mtu = IPV6_MIN_MTU; rcu_read_lock(); @@ -1590,10 +1775,8 @@ int ip6_route_add(struct fib6_config *cfg) ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; - if (rt->rt6i_dst.plen == 128) { + if (rt->rt6i_dst.plen == 128) rt->dst.flags |= DST_HOST; - dst_metrics_set_force_overwrite(&rt->dst); - } #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); @@ -1651,6 +1834,16 @@ int ip6_route_add(struct fib6_config *cfg) int gwa_type; gw_addr = &cfg->fc_gateway; + + /* if gw_addr is local we will fail to detect this in case + * address is still TENTATIVE (DAD in progress). rt6_lookup() + * will return already-added prefix route via interface that + * prefix route was assigned to, which might be non-loopback. + */ + err = -EINVAL; + if (ipv6_chk_addr_and_flags(net, gw_addr, NULL, 0, 0)) + goto out; + rt->rt6i_gateway = *gw_addr; gwa_type = ipv6_addr_type(gw_addr); @@ -1664,7 +1857,6 @@ int ip6_route_add(struct fib6_config *cfg) (SIT, PtP, NBMA NOARP links) it is handy to allow some exceptions. --ANK */ - err = -EINVAL; if (!(gwa_type & IPV6_ADDR_UNICAST)) goto out; @@ -1785,6 +1977,9 @@ static int ip6_route_del(struct fib6_config *cfg) if (fn) { for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if ((rt->rt6i_flags & RTF_CACHE) && + !(cfg->fc_flags & RTF_CACHE)) + continue; if (cfg->fc_ifindex && (!rt->dst.dev || rt->dst.dev->ifindex != cfg->fc_ifindex)) @@ -1894,7 +2089,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu NEIGH_UPDATE_F_ISROUTER)) ); - nrt = ip6_rt_copy(rt, &msg->dest); + nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL); if (!nrt) goto out; @@ -1926,42 +2121,35 @@ out: * Misc support functions */ -static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, - const struct in6_addr *dest) +static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) { - struct net *net = dev_net(ort->dst.dev); - struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0, - ort->rt6i_table); + BUG_ON(from->dst.from); - if (rt) { - rt->dst.input = ort->dst.input; - rt->dst.output = ort->dst.output; - rt->dst.flags |= DST_HOST; - - rt->rt6i_dst.addr = *dest; - rt->rt6i_dst.plen = 128; - dst_copy_metrics(&rt->dst, &ort->dst); - rt->dst.error = ort->dst.error; - rt->rt6i_idev = ort->rt6i_idev; - if (rt->rt6i_idev) - in6_dev_hold(rt->rt6i_idev); - rt->dst.lastuse = jiffies; - - if (ort->rt6i_flags & RTF_GATEWAY) - rt->rt6i_gateway = ort->rt6i_gateway; - else - rt->rt6i_gateway = *dest; - rt->rt6i_flags = ort->rt6i_flags; - rt6_set_from(rt, ort); - rt->rt6i_metric = 0; + rt->rt6i_flags &= ~RTF_EXPIRES; + dst_hold(&from->dst); + rt->dst.from = &from->dst; + dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true); +} +static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort) +{ + rt->dst.input = ort->dst.input; + rt->dst.output = ort->dst.output; + rt->rt6i_dst = ort->rt6i_dst; + rt->dst.error = ort->dst.error; + rt->rt6i_idev = ort->rt6i_idev; + if (rt->rt6i_idev) + in6_dev_hold(rt->rt6i_idev); + rt->dst.lastuse = jiffies; + rt->rt6i_gateway = ort->rt6i_gateway; + rt->rt6i_flags = ort->rt6i_flags; + rt6_set_from(rt, ort); + rt->rt6i_metric = ort->rt6i_metric; #ifdef CONFIG_IPV6_SUBTREES - memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); + rt->rt6i_src = ort->rt6i_src; #endif - memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key)); - rt->rt6i_table = ort->rt6i_table; - } - return rt; + rt->rt6i_prefsrc = ort->rt6i_prefsrc; + rt->rt6i_table = ort->rt6i_table; } #ifdef CONFIG_IPV6_ROUTE_INFO @@ -2336,6 +2524,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev) fib6_clean_all(net, fib6_ifdown, &adn); icmp6_clean_all(fib6_ifdown, &adn); + rt6_uncached_list_flush_dev(net, dev); } struct rt6_mtu_change_arg { @@ -2373,11 +2562,20 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) PMTU discouvery. */ if (rt->dst.dev == arg->dev && - !dst_metric_locked(&rt->dst, RTAX_MTU) && - (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6))) { - dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); + !dst_metric_locked(&rt->dst, RTAX_MTU)) { + if (rt->rt6i_flags & RTF_CACHE) { + /* For RTF_CACHE with rt6i_pmtu == 0 + * (i.e. a redirected route), + * the metrics of its rt->dst.from has already + * been updated. + */ + if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu) + rt->rt6i_pmtu = arg->mtu; + } else if (dst_mtu(&rt->dst) >= arg->mtu || + (dst_mtu(&rt->dst) < arg->mtu && + dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); + } } return 0; } @@ -2434,6 +2632,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; + if (rtm->rtm_flags & RTM_F_CLONED) + cfg->fc_flags |= RTF_CACHE; + cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = sock_net(skb->sk); @@ -2608,6 +2809,7 @@ static int rt6_fill_node(struct net *net, int iif, int type, u32 portid, u32 seq, int prefix, int nowait, unsigned int flags) { + u32 metrics[RTAX_MAX]; struct rtmsg *rtm; struct nlmsghdr *nlh; long expires; @@ -2721,7 +2923,10 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; } - if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) + memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); + if (rt->rt6i_pmtu) + metrics[RTAX_MTU - 1] = rt->rt6i_pmtu; + if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; if (rt->rt6i_flags & RTF_GATEWAY) { @@ -3216,6 +3421,7 @@ static struct notifier_block ip6_route_dev_notifier = { int __init ip6_route_init(void) { int ret; + int cpu; ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = @@ -3275,6 +3481,13 @@ int __init ip6_route_init(void) if (ret) goto out_register_late_subsys; + for_each_possible_cpu(cpu) { + struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); + + INIT_LIST_HEAD(&ul->head); + spin_lock_init(&ul->lock); + } + out: return ret; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 21bc2eb53c57..0909f4e0d53c 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -41,23 +41,6 @@ static __u16 const msstab[] = { 9000 - 60, }; -static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct sock *child; - - child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) { - atomic_set(&req->rsk_refcnt, 1); - inet_csk_reqsk_queue_add(sk, req, child); - } else { - reqsk_free(req); - } - return child; -} - static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch); @@ -264,7 +247,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst); - ret = get_cookie_sock(sk, skb, req, dst); + ret = tcp_get_cookie_sock(sk, skb, req, dst); out: return ret; out_free: diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index abcc79f649b3..4e705add4f18 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -68,6 +68,13 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "flowlabel_state_ranges", + .data = &init_net.ipv6.sysctl.flowlabel_state_ranges, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -109,6 +116,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect; ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries; ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; + ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3adffb300238..45a7176ed460 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -99,8 +99,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) dst_hold(dst); sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; - if (rt->rt6i_node) - inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; + inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); } } @@ -262,7 +261,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, rt = (struct rt6_info *) dst; if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr)) + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr)) tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; @@ -1251,7 +1250,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } - if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb)) + if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { @@ -1421,6 +1420,7 @@ process: skb->dev = NULL; bh_lock_sock_nested(sk); + tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) @@ -1442,7 +1442,7 @@ no_tcp_socket: tcp_v6_fill_cb(skb, hdr, th); - if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { + if (tcp_checksum_complete(skb)) { csum_error: TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS); bad_packet: @@ -1467,10 +1467,6 @@ do_time_wait: tcp_v6_fill_cb(skb, hdr, th); - if (skb->len < (th->doff<<2)) { - inet_twsk_put(inet_twsk(sk)); - goto bad_packet; - } if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f337a908a76a..ed0583c1b9fc 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -71,20 +71,12 @@ static int xfrm6_get_tos(const struct flowi *fl) return 0; } -static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst) -{ - struct rt6_info *rt = (struct rt6_info *)xdst; - - rt6_init_peer(rt, net->ipv6.peers); -} - static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { if (dst->ops->family == AF_INET6) { struct rt6_info *rt = (struct rt6_info *)dst; - if (rt->rt6i_node) - path->path_cookie = rt->rt6i_node->fn_sernum; + path->path_cookie = rt6_get_cookie(rt); } path->u.rt6.rt6i_nfheader_len = nfheader_len; @@ -106,16 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, return -ENODEV; } - rt6_transfer_peer(&xdst->u.rt6, rt); - /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | RTF_LOCAL); xdst->u.rt6.rt6i_metric = rt->rt6i_metric; xdst->u.rt6.rt6i_node = rt->rt6i_node; - if (rt->rt6i_node) - xdst->route_cookie = rt->rt6i_node->fn_sernum; + xdst->route_cookie = rt6_get_cookie(rt); xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; @@ -255,10 +244,6 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); - if (rt6_has_peer(&xdst->u.rt6)) { - struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6); - inet_putpeer(peer); - } xfrm_dst_destroy(xdst); } @@ -308,7 +293,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .get_saddr = xfrm6_get_saddr, .decode_session = _decode_session6, .get_tos = xfrm6_get_tos, - .init_dst = xfrm6_init_dst, .init_path = xfrm6_init_path, .fill_dst = xfrm6_fill_dst, .blackhole_route = ip6_blackhole_route, diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 4ea5d7497b5f..48d0dc89b58d 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1347,7 +1347,7 @@ static int ipx_create(struct net *net, struct socket *sock, int protocol, goto out; rc = -ENOMEM; - sk = sk_alloc(net, PF_IPX, GFP_KERNEL, &ipx_proto); + sk = sk_alloc(net, PF_IPX, GFP_KERNEL, &ipx_proto, kern); if (!sk) goto out; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index ee0ea25c8e7a..fae6822cc367 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1100,7 +1100,7 @@ static int irda_create(struct net *net, struct socket *sock, int protocol, } /* Allocate networking socket */ - sk = sk_alloc(net, PF_IRDA, GFP_KERNEL, &irda_proto); + sk = sk_alloc(net, PF_IRDA, GFP_KERNEL, &irda_proto, kern); if (sk == NULL) return -ENOMEM; diff --git a/net/irda/timer.c b/net/irda/timer.c index 0c4c115a5cab..f2280f73b057 100644 --- a/net/irda/timer.c +++ b/net/irda/timer.c @@ -60,8 +60,8 @@ void irlap_start_query_timer(struct irlap_cb *self, int S, int s) * to avoid messing with for incoming connections requests and * to accommodate devices that perform discovery slower than us. * Jean II */ - timeout = ((sysctl_slot_timeout * HZ / 1000) * (S - s) - + XIDEXTRA_TIMEOUT + SMALLBUSY_TIMEOUT); + timeout = msecs_to_jiffies(sysctl_slot_timeout) * (S - s) + + XIDEXTRA_TIMEOUT + SMALLBUSY_TIMEOUT; /* Set or re-set the timer. We reset the timer for each received * discovery query, which allow us to automatically adjust to diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 6daa52a18d40..918151c11348 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -535,12 +535,12 @@ static void iucv_sock_init(struct sock *sk, struct sock *parent) sk->sk_type = parent->sk_type; } -static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio) +static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio, int kern) { struct sock *sk; struct iucv_sock *iucv; - sk = sk_alloc(&init_net, PF_IUCV, prio, &iucv_proto); + sk = sk_alloc(&init_net, PF_IUCV, prio, &iucv_proto, kern); if (!sk) return NULL; iucv = iucv_sk(sk); @@ -602,7 +602,7 @@ static int iucv_sock_create(struct net *net, struct socket *sock, int protocol, return -ESOCKTNOSUPPORT; } - sk = iucv_sock_alloc(sock, protocol, GFP_KERNEL); + sk = iucv_sock_alloc(sock, protocol, GFP_KERNEL, kern); if (!sk) return -ENOMEM; @@ -1723,7 +1723,7 @@ static int iucv_callback_connreq(struct iucv_path *path, } /* Create the new socket */ - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC); + nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); if (!nsk) { err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); @@ -1933,7 +1933,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) goto out; } - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC); + nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); bh_lock_sock(sk); if ((sk->sk_state != IUCV_LISTEN) || sk_acceptq_is_full(sk) || diff --git a/net/key/af_key.c b/net/key/af_key.c index f0d52d721b3a..9e834ec475a9 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -149,7 +149,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, return -EPROTONOSUPPORT; err = -ENOMEM; - sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto); + sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto, kern); if (sk == NULL) goto out; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index a29a504492af..f6b090df3930 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1334,9 +1334,10 @@ static void l2tp_tunnel_del_work(struct work_struct *work) if (sock) inet_shutdown(sock, 2); } else { - if (sock) + if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sk); + sock_release(sock); + } } l2tp_tunnel_sock_put(sk); @@ -1399,13 +1400,11 @@ static int l2tp_tunnel_sock_create(struct net *net, if (cfg->local_ip6 && cfg->peer_ip6) { struct sockaddr_l2tpip6 ip6_addr = {0}; - err = sock_create_kern(AF_INET6, SOCK_DGRAM, + err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; - sk_change_net(sock->sk, net); - ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); @@ -1429,13 +1428,11 @@ static int l2tp_tunnel_sock_create(struct net *net, { struct sockaddr_l2tpip ip_addr = {0}; - err = sock_create_kern(AF_INET, SOCK_DGRAM, + err = sock_create_kern(net, AF_INET, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; - sk_change_net(sock->sk, net); - ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; @@ -1462,7 +1459,7 @@ out: *sockp = sock; if ((err < 0) && sock) { kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sock->sk); + sock_release(sock); *sockp = NULL; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index e9b0dec56b8e..f56c9f69e9f2 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -542,12 +542,12 @@ static int pppol2tp_backlog_recv(struct sock *sk, struct sk_buff *skb) /* socket() handler. Initialize a new struct sock. */ -static int pppol2tp_create(struct net *net, struct socket *sock) +static int pppol2tp_create(struct net *net, struct socket *sock, int kern) { int error = -ENOMEM; struct sock *sk; - sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppol2tp_sk_proto); + sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppol2tp_sk_proto, kern); if (!sk) goto out; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 17a8dff06090..8fd9febaa5ba 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -168,7 +168,7 @@ static int llc_ui_create(struct net *net, struct socket *sock, int protocol, if (likely(sock->type == SOCK_DGRAM || sock->type == SOCK_STREAM)) { rc = -ENOMEM; - sk = llc_sk_alloc(net, PF_LLC, GFP_KERNEL, &llc_proto); + sk = llc_sk_alloc(net, PF_LLC, GFP_KERNEL, &llc_proto, kern); if (sk) { rc = 0; llc_ui_sk_init(sock, sk); diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 81a61fce3afb..3e821daf9dd4 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -768,7 +768,7 @@ static struct sock *llc_create_incoming_sock(struct sock *sk, struct llc_addr *daddr) { struct sock *newsk = llc_sk_alloc(sock_net(sk), sk->sk_family, GFP_ATOMIC, - sk->sk_prot); + sk->sk_prot, 0); struct llc_sock *newllc, *llc = llc_sk(sk); if (!newsk) @@ -931,9 +931,9 @@ static void llc_sk_init(struct sock *sk) * Allocates a LLC sock and initializes it. Returns the new LLC sock * or %NULL if there's no memory available for one */ -struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot) +struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern) { - struct sock *sk = sk_alloc(net, family, priority, prot); + struct sock *sk = sk_alloc(net, family, priority, prot, kern); if (!sk) goto out; diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 64a012a0c6e5..086de496a4c1 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -302,6 +302,20 @@ config MAC80211_DEBUG_COUNTERS ---help--- Selecting this option causes mac80211 to keep additional and very verbose statistics about TX and RX handler use - and show them in debugfs. + as well as a few selected dot11 counters. These will be + exposed in debugfs. + + Note that some of the counters are not concurrency safe + and may thus not always be accurate. If unsure, say N. + +config MAC80211_STA_HASH_MAX_SIZE + int "Station hash table maximum size" if MAC80211_DEBUG_MENU + default 0 + ---help--- + Setting this option to a low value (e.g. 4) allows testing the + hash table with collisions relatively deterministically (just + connect more stations than the number selected here.) + + If unsure, leave the default of 0. diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index ff347a0eebd4..690b9f640b41 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -137,6 +137,9 @@ static int ieee80211_set_noack_map(struct wiphy *wiphy, struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); sdata->noack_map = noack_map; + + ieee80211_check_fast_xmit_iface(sdata); + return 0; } @@ -309,6 +312,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, u32 iv32; u16 iv16; int err = -ENOENT; + struct ieee80211_key_seq kseq = {}; sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -339,10 +343,12 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, iv32 = key->u.tkip.tx.iv32; iv16 = key->u.tkip.tx.iv16; - if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) - drv_get_tkip_seq(sdata->local, - key->conf.hw_key_idx, - &iv32, &iv16); + if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { + drv_get_key_seq(sdata->local, key, &kseq); + iv32 = kseq.tkip.iv32; + iv16 = kseq.tkip.iv16; + } seq[0] = iv16 & 0xff; seq[1] = (iv16 >> 8) & 0xff; @@ -355,52 +361,85 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: - pn64 = atomic64_read(&key->u.ccmp.tx_pn); - seq[0] = pn64; - seq[1] = pn64 >> 8; - seq[2] = pn64 >> 16; - seq[3] = pn64 >> 24; - seq[4] = pn64 >> 32; - seq[5] = pn64 >> 40; + if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { + drv_get_key_seq(sdata->local, key, &kseq); + memcpy(seq, kseq.ccmp.pn, 6); + } else { + pn64 = atomic64_read(&key->u.ccmp.tx_pn); + seq[0] = pn64; + seq[1] = pn64 >> 8; + seq[2] = pn64 >> 16; + seq[3] = pn64 >> 24; + seq[4] = pn64 >> 32; + seq[5] = pn64 >> 40; + } params.seq = seq; params.seq_len = 6; break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: - pn64 = atomic64_read(&key->u.aes_cmac.tx_pn); - seq[0] = pn64; - seq[1] = pn64 >> 8; - seq[2] = pn64 >> 16; - seq[3] = pn64 >> 24; - seq[4] = pn64 >> 32; - seq[5] = pn64 >> 40; + if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { + drv_get_key_seq(sdata->local, key, &kseq); + memcpy(seq, kseq.aes_cmac.pn, 6); + } else { + pn64 = atomic64_read(&key->u.aes_cmac.tx_pn); + seq[0] = pn64; + seq[1] = pn64 >> 8; + seq[2] = pn64 >> 16; + seq[3] = pn64 >> 24; + seq[4] = pn64 >> 32; + seq[5] = pn64 >> 40; + } params.seq = seq; params.seq_len = 6; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: - pn64 = atomic64_read(&key->u.aes_gmac.tx_pn); - seq[0] = pn64; - seq[1] = pn64 >> 8; - seq[2] = pn64 >> 16; - seq[3] = pn64 >> 24; - seq[4] = pn64 >> 32; - seq[5] = pn64 >> 40; + if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { + drv_get_key_seq(sdata->local, key, &kseq); + memcpy(seq, kseq.aes_gmac.pn, 6); + } else { + pn64 = atomic64_read(&key->u.aes_gmac.tx_pn); + seq[0] = pn64; + seq[1] = pn64 >> 8; + seq[2] = pn64 >> 16; + seq[3] = pn64 >> 24; + seq[4] = pn64 >> 32; + seq[5] = pn64 >> 40; + } params.seq = seq; params.seq_len = 6; break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: - pn64 = atomic64_read(&key->u.gcmp.tx_pn); - seq[0] = pn64; - seq[1] = pn64 >> 8; - seq[2] = pn64 >> 16; - seq[3] = pn64 >> 24; - seq[4] = pn64 >> 32; - seq[5] = pn64 >> 40; + if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { + drv_get_key_seq(sdata->local, key, &kseq); + memcpy(seq, kseq.gcmp.pn, 6); + } else { + pn64 = atomic64_read(&key->u.gcmp.tx_pn); + seq[0] = pn64; + seq[1] = pn64 >> 8; + seq[2] = pn64 >> 16; + seq[3] = pn64 >> 24; + seq[4] = pn64 >> 32; + seq[5] = pn64 >> 40; + } params.seq = seq; params.seq_len = 6; break; + default: + if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) + break; + if (WARN_ON(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) + break; + drv_get_key_seq(sdata->local, key, &kseq); + params.seq = kseq.hw.seq; + params.seq_len = kseq.hw.seq_len; + break; } params.key = key->conf.key; @@ -1372,6 +1411,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, } sta->sdata = vlansdata; + ieee80211_check_fast_xmit(sta); if (sta->sta_state == IEEE80211_STA_AUTHORIZED && prev_4addr != new_4addr) { @@ -2099,10 +2139,14 @@ static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed) int err; if (changed & WIPHY_PARAM_FRAG_THRESHOLD) { + ieee80211_check_fast_xmit_all(local); + err = drv_set_frag_threshold(local, wiphy->frag_threshold); - if (err) + if (err) { + ieee80211_check_fast_xmit_all(local); return err; + } } if ((changed & WIPHY_PARAM_COVERAGE_CLASS) || @@ -3299,8 +3343,14 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - if (!sdata->u.mgd.associated) + sdata_lock(sdata); + if (!sdata->u.mgd.associated || + (params->offchan && params->wait && + local->ops->remain_on_channel && + memcmp(sdata->u.mgd.associated->bssid, + mgmt->bssid, ETH_ALEN))) need_offchan = true; + sdata_unlock(sdata); break; case NL80211_IFTYPE_P2P_DEVICE: need_offchan = true; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 5bcd4e5589d3..f01c18a3160e 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -664,6 +664,8 @@ out: ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IDLE); + ieee80211_check_fast_xmit_iface(sdata); + return ret; } @@ -1008,6 +1010,8 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata) if (WARN_ON(!chandef)) return -EINVAL; + ieee80211_change_chanctx(local, new_ctx, chandef); + vif_chsw[0].vif = &sdata->vif; vif_chsw[0].old_ctx = &old_ctx->conf; vif_chsw[0].new_ctx = &new_ctx->conf; @@ -1030,6 +1034,8 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata) if (sdata->vif.type == NL80211_IFTYPE_AP) __ieee80211_vif_copy_chanctx_to_vlans(sdata, false); + ieee80211_check_fast_xmit_iface(sdata); + if (ieee80211_chanctx_refcount(local, old_ctx) == 0) ieee80211_free_chanctx(local, old_ctx); @@ -1079,6 +1085,8 @@ ieee80211_vif_use_reserved_assign(struct ieee80211_sub_if_data *sdata) if (WARN_ON(!chandef)) return -EINVAL; + ieee80211_change_chanctx(local, new_ctx, chandef); + list_del(&sdata->reserved_chanctx_list); sdata->reserved_chanctx = NULL; @@ -1376,6 +1384,8 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) __ieee80211_vif_copy_chanctx_to_vlans(sdata, false); + ieee80211_check_fast_xmit_iface(sdata); + sdata->radar_required = sdata->reserved_radar_required; if (sdata->vif.bss_conf.chandef.width != diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 23813ebb349c..b17206db49b4 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -219,8 +219,8 @@ static const struct file_operations stats_ ##name## _ops = { \ .llseek = generic_file_llseek, \ }; -#define DEBUGFS_STATS_ADD(name, field) \ - debugfs_create_u32(#name, 0400, statsd, (u32 *) &field); +#define DEBUGFS_STATS_ADD(name) \ + debugfs_create_u32(#name, 0400, statsd, &local->name); #define DEBUGFS_DEVSTATS_ADD(name) \ debugfs_create_file(#name, 0400, statsd, local, &stats_ ##name## _ops); @@ -255,53 +255,31 @@ void debugfs_hw_add(struct ieee80211_local *local) if (!statsd) return; - DEBUGFS_STATS_ADD(transmitted_fragment_count, - local->dot11TransmittedFragmentCount); - DEBUGFS_STATS_ADD(multicast_transmitted_frame_count, - local->dot11MulticastTransmittedFrameCount); - DEBUGFS_STATS_ADD(failed_count, local->dot11FailedCount); - DEBUGFS_STATS_ADD(retry_count, local->dot11RetryCount); - DEBUGFS_STATS_ADD(multiple_retry_count, - local->dot11MultipleRetryCount); - DEBUGFS_STATS_ADD(frame_duplicate_count, - local->dot11FrameDuplicateCount); - DEBUGFS_STATS_ADD(received_fragment_count, - local->dot11ReceivedFragmentCount); - DEBUGFS_STATS_ADD(multicast_received_frame_count, - local->dot11MulticastReceivedFrameCount); - DEBUGFS_STATS_ADD(transmitted_frame_count, - local->dot11TransmittedFrameCount); #ifdef CONFIG_MAC80211_DEBUG_COUNTERS - DEBUGFS_STATS_ADD(tx_handlers_drop, local->tx_handlers_drop); - DEBUGFS_STATS_ADD(tx_handlers_queued, local->tx_handlers_queued); - DEBUGFS_STATS_ADD(tx_handlers_drop_fragment, - local->tx_handlers_drop_fragment); - DEBUGFS_STATS_ADD(tx_handlers_drop_wep, - local->tx_handlers_drop_wep); - DEBUGFS_STATS_ADD(tx_handlers_drop_not_assoc, - local->tx_handlers_drop_not_assoc); - DEBUGFS_STATS_ADD(tx_handlers_drop_unauth_port, - local->tx_handlers_drop_unauth_port); - DEBUGFS_STATS_ADD(rx_handlers_drop, local->rx_handlers_drop); - DEBUGFS_STATS_ADD(rx_handlers_queued, local->rx_handlers_queued); - DEBUGFS_STATS_ADD(rx_handlers_drop_nullfunc, - local->rx_handlers_drop_nullfunc); - DEBUGFS_STATS_ADD(rx_handlers_drop_defrag, - local->rx_handlers_drop_defrag); - DEBUGFS_STATS_ADD(rx_handlers_drop_short, - local->rx_handlers_drop_short); - DEBUGFS_STATS_ADD(tx_expand_skb_head, - local->tx_expand_skb_head); - DEBUGFS_STATS_ADD(tx_expand_skb_head_cloned, - local->tx_expand_skb_head_cloned); - DEBUGFS_STATS_ADD(rx_expand_skb_head, - local->rx_expand_skb_head); - DEBUGFS_STATS_ADD(rx_expand_skb_head2, - local->rx_expand_skb_head2); - DEBUGFS_STATS_ADD(rx_handlers_fragments, - local->rx_handlers_fragments); - DEBUGFS_STATS_ADD(tx_status_drop, - local->tx_status_drop); + DEBUGFS_STATS_ADD(dot11TransmittedFragmentCount); + DEBUGFS_STATS_ADD(dot11MulticastTransmittedFrameCount); + DEBUGFS_STATS_ADD(dot11FailedCount); + DEBUGFS_STATS_ADD(dot11RetryCount); + DEBUGFS_STATS_ADD(dot11MultipleRetryCount); + DEBUGFS_STATS_ADD(dot11FrameDuplicateCount); + DEBUGFS_STATS_ADD(dot11ReceivedFragmentCount); + DEBUGFS_STATS_ADD(dot11MulticastReceivedFrameCount); + DEBUGFS_STATS_ADD(dot11TransmittedFrameCount); + DEBUGFS_STATS_ADD(tx_handlers_drop); + DEBUGFS_STATS_ADD(tx_handlers_queued); + DEBUGFS_STATS_ADD(tx_handlers_drop_wep); + DEBUGFS_STATS_ADD(tx_handlers_drop_not_assoc); + DEBUGFS_STATS_ADD(tx_handlers_drop_unauth_port); + DEBUGFS_STATS_ADD(rx_handlers_drop); + DEBUGFS_STATS_ADD(rx_handlers_queued); + DEBUGFS_STATS_ADD(rx_handlers_drop_nullfunc); + DEBUGFS_STATS_ADD(rx_handlers_drop_defrag); + DEBUGFS_STATS_ADD(rx_handlers_drop_short); + DEBUGFS_STATS_ADD(tx_expand_skb_head); + DEBUGFS_STATS_ADD(tx_expand_skb_head_cloned); + DEBUGFS_STATS_ADD(rx_expand_skb_head_defrag); + DEBUGFS_STATS_ADD(rx_handlers_fragments); + DEBUGFS_STATS_ADD(tx_status_drop); #endif DEBUGFS_DEVSTATS_ADD(dot11ACKFailureCount); DEBUGFS_DEVSTATS_ADD(dot11RTSFailureCount); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 252859e90e8a..06d52935036d 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -29,8 +29,6 @@ static ssize_t sta_ ##name## _read(struct file *file, \ format_string, sta->field); \ } #define STA_READ_D(name, field) STA_READ(name, field, "%d\n") -#define STA_READ_U(name, field) STA_READ(name, field, "%u\n") -#define STA_READ_S(name, field) STA_READ(name, field, "%s\n") #define STA_OPS(name) \ static const struct file_operations sta_ ##name## _ops = { \ @@ -52,10 +50,7 @@ static const struct file_operations sta_ ##name## _ops = { \ STA_OPS(name) STA_FILE(aid, sta.aid, D); -STA_FILE(dev, sdata->name, S); -STA_FILE(last_signal, last_signal, D); STA_FILE(last_ack_signal, last_ack_signal, D); -STA_FILE(beacon_loss_count, beacon_loss_count, D); static ssize_t sta_flags_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -101,40 +96,6 @@ static ssize_t sta_num_ps_buf_frames_read(struct file *file, } STA_OPS(num_ps_buf_frames); -static ssize_t sta_inactive_ms_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct sta_info *sta = file->private_data; - return mac80211_format_buffer(userbuf, count, ppos, "%d\n", - jiffies_to_msecs(jiffies - sta->last_rx)); -} -STA_OPS(inactive_ms); - - -static ssize_t sta_connected_time_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct sta_info *sta = file->private_data; - struct timespec uptime; - struct tm result; - long connected_time_secs; - char buf[100]; - int res; - ktime_get_ts(&uptime); - connected_time_secs = uptime.tv_sec - sta->last_connected; - time_to_tm(connected_time_secs, 0, &result); - result.tm_year -= 70; - result.tm_mday -= 1; - res = scnprintf(buf, sizeof(buf), - "years - %ld\nmonths - %d\ndays - %d\nclock - %d:%d:%d\n\n", - result.tm_year, result.tm_mon, result.tm_mday, - result.tm_hour, result.tm_min, result.tm_sec); - return simple_read_from_buffer(userbuf, count, ppos, buf, res); -} -STA_OPS(connected_time); - - - static ssize_t sta_last_seq_ctrl_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -359,37 +320,6 @@ static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, } STA_OPS(vht_capa); -static ssize_t sta_current_tx_rate_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct sta_info *sta = file->private_data; - struct rate_info rinfo; - u16 rate; - sta_set_rate_info_tx(sta, &sta->last_tx_rate, &rinfo); - rate = cfg80211_calculate_bitrate(&rinfo); - - return mac80211_format_buffer(userbuf, count, ppos, - "%d.%d MBit/s\n", - rate/10, rate%10); -} -STA_OPS(current_tx_rate); - -static ssize_t sta_last_rx_rate_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct sta_info *sta = file->private_data; - struct rate_info rinfo; - u16 rate; - - sta_set_rate_info_rx(sta, &rinfo); - - rate = cfg80211_calculate_bitrate(&rinfo); - - return mac80211_format_buffer(userbuf, count, ppos, - "%d.%d MBit/s\n", - rate/10, rate%10); -} -STA_OPS(last_rx_rate); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ @@ -432,30 +362,15 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(flags); DEBUGFS_ADD(num_ps_buf_frames); - DEBUGFS_ADD(inactive_ms); - DEBUGFS_ADD(connected_time); DEBUGFS_ADD(last_seq_ctrl); DEBUGFS_ADD(agg_status); - DEBUGFS_ADD(dev); - DEBUGFS_ADD(last_signal); - DEBUGFS_ADD(beacon_loss_count); DEBUGFS_ADD(ht_capa); DEBUGFS_ADD(vht_capa); DEBUGFS_ADD(last_ack_signal); - DEBUGFS_ADD(current_tx_rate); - DEBUGFS_ADD(last_rx_rate); - DEBUGFS_ADD_COUNTER(rx_packets, rx_packets); - DEBUGFS_ADD_COUNTER(tx_packets, tx_packets); - DEBUGFS_ADD_COUNTER(rx_bytes, rx_bytes); - DEBUGFS_ADD_COUNTER(tx_bytes, tx_bytes); DEBUGFS_ADD_COUNTER(rx_duplicates, num_duplicates); DEBUGFS_ADD_COUNTER(rx_fragments, rx_fragments); - DEBUGFS_ADD_COUNTER(rx_dropped, rx_dropped); - DEBUGFS_ADD_COUNTER(tx_fragments, tx_fragments); DEBUGFS_ADD_COUNTER(tx_filtered, tx_filtered_count); - DEBUGFS_ADD_COUNTER(tx_retry_failed, tx_retry_failed); - DEBUGFS_ADD_COUNTER(tx_retry_count, tx_retry_count); if (sizeof(sta->driver_buffered_tids) == sizeof(u32)) debugfs_create_x32("driver_buffered_tids", 0400, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 26e1ca8a474a..c01e681b90fb 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -417,12 +417,13 @@ static inline int drv_get_stats(struct ieee80211_local *local, return ret; } -static inline void drv_get_tkip_seq(struct ieee80211_local *local, - u8 hw_key_idx, u32 *iv32, u16 *iv16) +static inline void drv_get_key_seq(struct ieee80211_local *local, + struct ieee80211_key *key, + struct ieee80211_key_seq *seq) { - if (local->ops->get_tkip_seq) - local->ops->get_tkip_seq(&local->hw, hw_key_idx, iv32, iv16); - trace_drv_get_tkip_seq(local, hw_key_idx, iv32, iv16); + if (local->ops->get_key_seq) + local->ops->get_key_seq(&local->hw, &key->conf, seq); + trace_drv_get_key_seq(local, &key->conf); } static inline int drv_set_frag_threshold(struct ieee80211_local *local, diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c index 52bcea6ad9e8..188faab11c24 100644 --- a/net/mac80211/ethtool.c +++ b/net/mac80211/ethtool.c @@ -38,7 +38,7 @@ static void ieee80211_get_ringparam(struct net_device *dev, static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = { "rx_packets", "rx_bytes", "rx_duplicates", "rx_fragments", "rx_dropped", - "tx_packets", "tx_bytes", "tx_fragments", + "tx_packets", "tx_bytes", "tx_filtered", "tx_retry_failed", "tx_retries", "beacon_loss", "sta_state", "txrate", "rxrate", "signal", "channel", "noise", "ch_time", "ch_time_busy", @@ -87,7 +87,6 @@ static void ieee80211_get_stats(struct net_device *dev, \ data[i++] += sinfo.tx_packets; \ data[i++] += sinfo.tx_bytes; \ - data[i++] += sta->tx_fragments; \ data[i++] += sta->tx_filtered_count; \ data[i++] += sta->tx_retry_failed; \ data[i++] += sta->tx_retry_count; \ diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index bfef1b215050..21716af8bec3 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1031,8 +1031,11 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, } } - if (sta && elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) + if (sta && !sta->sta.wme && + elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) { sta->sta.wme = true; + ieee80211_check_fast_xmit(sta); + } if (sta && elems->ht_operation && elems->ht_cap_elem && sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT && diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c0a9187bc3a9..b12f61507f9f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -181,8 +181,6 @@ typedef unsigned __bitwise__ ieee80211_rx_result; /** * enum ieee80211_packet_rx_flags - packet RX flags - * @IEEE80211_RX_RA_MATCH: frame is destined to interface currently processed - * (incl. multicast frames) * @IEEE80211_RX_FRAGMENTED: fragmented frame * @IEEE80211_RX_AMSDU: a-MSDU packet * @IEEE80211_RX_MALFORMED_ACTION_FRM: action frame is malformed @@ -192,7 +190,6 @@ typedef unsigned __bitwise__ ieee80211_rx_result; * @rx_flags field of &struct ieee80211_rx_status. */ enum ieee80211_packet_rx_flags { - IEEE80211_RX_RA_MATCH = BIT(1), IEEE80211_RX_FRAGMENTED = BIT(2), IEEE80211_RX_AMSDU = BIT(3), IEEE80211_RX_MALFORMED_ACTION_FRM = BIT(4), @@ -722,7 +719,6 @@ struct ieee80211_if_mesh { * enum ieee80211_sub_if_data_flags - virtual interface flags * * @IEEE80211_SDATA_ALLMULTI: interface wants all multicast packets - * @IEEE80211_SDATA_PROMISC: interface is promisc * @IEEE80211_SDATA_OPERATING_GMODE: operating in G-only mode * @IEEE80211_SDATA_DONT_BRIDGE_PACKETS: bridge packets between * associated stations and deliver multicast frames both @@ -732,7 +728,6 @@ struct ieee80211_if_mesh { */ enum ieee80211_sub_if_data_flags { IEEE80211_SDATA_ALLMULTI = BIT(0), - IEEE80211_SDATA_PROMISC = BIT(1), IEEE80211_SDATA_OPERATING_GMODE = BIT(2), IEEE80211_SDATA_DONT_BRIDGE_PACKETS = BIT(3), IEEE80211_SDATA_DISCONNECT_RESUME = BIT(4), @@ -1040,7 +1035,6 @@ enum queue_stop_reason { #ifdef CONFIG_MAC80211_LEDS struct tpt_led_trigger { - struct led_trigger trig; char name[32]; const struct ieee80211_tpt_blink *blink_table; unsigned int blink_table_len; @@ -1208,8 +1202,8 @@ struct ieee80211_local { atomic_t agg_queue_stop[IEEE80211_MAX_QUEUES]; - /* number of interfaces with corresponding IFF_ flags */ - atomic_t iff_allmultis, iff_promiscs; + /* number of interfaces with allmulti RX */ + atomic_t iff_allmultis; struct rate_control_ref *rate_ctrl; @@ -1261,6 +1255,15 @@ struct ieee80211_local { struct list_head chanctx_list; struct mutex chanctx_mtx; +#ifdef CONFIG_MAC80211_LEDS + struct led_trigger tx_led, rx_led, assoc_led, radio_led; + struct led_trigger tpt_led; + atomic_t tx_led_active, rx_led_active, assoc_led_active; + atomic_t radio_led_active, tpt_led_active; + struct tpt_led_trigger *tpt_led_trigger; +#endif + +#ifdef CONFIG_MAC80211_DEBUG_COUNTERS /* SNMP counters */ /* dot11CountersTable */ u32 dot11TransmittedFragmentCount; @@ -1273,18 +1276,9 @@ struct ieee80211_local { u32 dot11MulticastReceivedFrameCount; u32 dot11TransmittedFrameCount; -#ifdef CONFIG_MAC80211_LEDS - struct led_trigger *tx_led, *rx_led, *assoc_led, *radio_led; - struct tpt_led_trigger *tpt_led_trigger; - char tx_led_name[32], rx_led_name[32], - assoc_led_name[32], radio_led_name[32]; -#endif - -#ifdef CONFIG_MAC80211_DEBUG_COUNTERS /* TX/RX handler statistics */ unsigned int tx_handlers_drop; unsigned int tx_handlers_queued; - unsigned int tx_handlers_drop_fragment; unsigned int tx_handlers_drop_wep; unsigned int tx_handlers_drop_not_assoc; unsigned int tx_handlers_drop_unauth_port; @@ -1295,8 +1289,7 @@ struct ieee80211_local { unsigned int rx_handlers_drop_short; unsigned int tx_expand_skb_head; unsigned int tx_expand_skb_head_cloned; - unsigned int rx_expand_skb_head; - unsigned int rx_expand_skb_head2; + unsigned int rx_expand_skb_head_defrag; unsigned int rx_handlers_fragments; unsigned int tx_status_drop; #define I802_DEBUG_INC(c) (c)++ @@ -1648,6 +1641,11 @@ struct sk_buff * ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 info_flags); +void ieee80211_check_fast_xmit(struct sta_info *sta); +void ieee80211_check_fast_xmit_all(struct ieee80211_local *local); +void ieee80211_check_fast_xmit_iface(struct ieee80211_sub_if_data *sdata); +void ieee80211_clear_fast_xmit(struct sta_info *sta); + /* HT */ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_ht_cap *ht_cap); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 84cef600c573..b2e85ffca7ed 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -703,9 +703,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) if (sdata->flags & IEEE80211_SDATA_ALLMULTI) atomic_inc(&local->iff_allmultis); - if (sdata->flags & IEEE80211_SDATA_PROMISC) - atomic_inc(&local->iff_promiscs); - if (coming_up) local->open_count++; @@ -835,13 +832,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) || (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1))); - /* don't count this interface for promisc/allmulti while it is down */ + /* don't count this interface for allmulti while it is down */ if (sdata->flags & IEEE80211_SDATA_ALLMULTI) atomic_dec(&local->iff_allmultis); - if (sdata->flags & IEEE80211_SDATA_PROMISC) - atomic_dec(&local->iff_promiscs); - if (sdata->vif.type == NL80211_IFTYPE_AP) { local->fif_pspoll--; local->fif_probe_req--; @@ -1055,12 +1049,10 @@ static void ieee80211_set_multicast_list(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; - int allmulti, promisc, sdata_allmulti, sdata_promisc; + int allmulti, sdata_allmulti; allmulti = !!(dev->flags & IFF_ALLMULTI); - promisc = !!(dev->flags & IFF_PROMISC); sdata_allmulti = !!(sdata->flags & IEEE80211_SDATA_ALLMULTI); - sdata_promisc = !!(sdata->flags & IEEE80211_SDATA_PROMISC); if (allmulti != sdata_allmulti) { if (dev->flags & IFF_ALLMULTI) @@ -1070,13 +1062,6 @@ static void ieee80211_set_multicast_list(struct net_device *dev) sdata->flags ^= IEEE80211_SDATA_ALLMULTI; } - if (promisc != sdata_promisc) { - if (dev->flags & IFF_PROMISC) - atomic_inc(&local->iff_promiscs); - else - atomic_dec(&local->iff_promiscs); - sdata->flags ^= IEEE80211_SDATA_PROMISC; - } spin_lock_bh(&local->filter_lock); __hw_addr_sync(&local->mc_list, &dev->mc, dev->addr_len); spin_unlock_bh(&local->filter_lock); @@ -1117,6 +1102,35 @@ static u16 ieee80211_netdev_select_queue(struct net_device *dev, return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } +static struct rtnl_link_stats64 * +ieee80211_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *tstats; + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + tstats = per_cpu_ptr(dev->tstats, i); + + do { + start = u64_stats_fetch_begin_irq(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); + + stats->rx_packets += rx_packets; + stats->tx_packets += tx_packets; + stats->rx_bytes += rx_bytes; + stats->tx_bytes += tx_bytes; + } + + return stats; +} + static const struct net_device_ops ieee80211_dataif_ops = { .ndo_open = ieee80211_open, .ndo_stop = ieee80211_stop, @@ -1126,6 +1140,7 @@ static const struct net_device_ops ieee80211_dataif_ops = { .ndo_change_mtu = ieee80211_change_mtu, .ndo_set_mac_address = ieee80211_change_mac, .ndo_select_queue = ieee80211_netdev_select_queue, + .ndo_get_stats64 = ieee80211_get_stats64, }; static u16 ieee80211_monitor_select_queue(struct net_device *dev, @@ -1159,14 +1174,21 @@ static const struct net_device_ops ieee80211_monitorif_ops = { .ndo_change_mtu = ieee80211_change_mtu, .ndo_set_mac_address = ieee80211_change_mac, .ndo_select_queue = ieee80211_monitor_select_queue, + .ndo_get_stats64 = ieee80211_get_stats64, }; +static void ieee80211_if_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + static void ieee80211_if_setup(struct net_device *dev) { ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->netdev_ops = &ieee80211_dataif_ops; - dev->destructor = free_netdev; + dev->destructor = ieee80211_if_free; } static void ieee80211_iface_work(struct work_struct *work) @@ -1707,6 +1729,12 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, return -ENOMEM; dev_net_set(ndev, wiphy_net(local->hw.wiphy)); + ndev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!ndev->tstats) { + free_netdev(ndev); + return -ENOMEM; + } + ndev->needed_headroom = local->tx_headroom + 4*6 /* four MAC addresses */ + 2 + 2 + 2 + 2 /* ctl, dur, seq, qos */ diff --git a/net/mac80211/key.c b/net/mac80211/key.c index a907f2d5c12d..577a11a13cdf 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -256,6 +256,7 @@ static void __ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, if (uni) { rcu_assign_pointer(sdata->default_unicast_key, key); + ieee80211_check_fast_xmit_iface(sdata); drv_set_default_unicast_key(sdata->local, sdata, idx); } @@ -325,6 +326,7 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, if (pairwise) { rcu_assign_pointer(sta->ptk[idx], new); sta->ptk_idx = idx; + ieee80211_check_fast_xmit(sta); } else { rcu_assign_pointer(sta->gtk[idx], new); sta->gtk_idx = idx; @@ -510,15 +512,17 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, break; default: if (cs) { - size_t len = (seq_len > MAX_PN_LEN) ? - MAX_PN_LEN : seq_len; + if (seq_len && seq_len != cs->pn_len) { + kfree(key); + return ERR_PTR(-EINVAL); + } key->conf.iv_len = cs->hdr_len; key->conf.icv_len = cs->mic_len; for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) - for (j = 0; j < len; j++) + for (j = 0; j < seq_len; j++) key->u.gen.rx_pn[i][j] = - seq[len - j - 1]; + seq[seq_len - j - 1]; key->flags |= KEY_FLAG_CIPHER_SCHEME; } } diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 96557dd1e77d..2119526db2f4 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -18,7 +18,6 @@ #define NUM_DEFAULT_KEYS 4 #define NUM_DEFAULT_MGMT_KEYS 2 -#define MAX_PN_LEN 16 struct ieee80211_local; struct ieee80211_sub_if_data; @@ -116,7 +115,7 @@ struct ieee80211_key { } gcmp; struct { /* generic cipher scheme */ - u8 rx_pn[IEEE80211_NUM_TIDS + 1][MAX_PN_LEN]; + u8 rx_pn[IEEE80211_NUM_TIDS + 1][IEEE80211_MAX_PN_LEN]; } gen; } u; diff --git a/net/mac80211/led.c b/net/mac80211/led.c index e2b836446af3..0505845b7ab8 100644 --- a/net/mac80211/led.c +++ b/net/mac80211/led.c @@ -12,96 +12,175 @@ #include <linux/export.h> #include "led.h" -#define MAC80211_BLINK_DELAY 50 /* ms */ - -void ieee80211_led_rx(struct ieee80211_local *local) -{ - unsigned long led_delay = MAC80211_BLINK_DELAY; - if (unlikely(!local->rx_led)) - return; - led_trigger_blink_oneshot(local->rx_led, &led_delay, &led_delay, 0); -} - -void ieee80211_led_tx(struct ieee80211_local *local) -{ - unsigned long led_delay = MAC80211_BLINK_DELAY; - if (unlikely(!local->tx_led)) - return; - led_trigger_blink_oneshot(local->tx_led, &led_delay, &led_delay, 0); -} - void ieee80211_led_assoc(struct ieee80211_local *local, bool associated) { - if (unlikely(!local->assoc_led)) + if (!atomic_read(&local->assoc_led_active)) return; if (associated) - led_trigger_event(local->assoc_led, LED_FULL); + led_trigger_event(&local->assoc_led, LED_FULL); else - led_trigger_event(local->assoc_led, LED_OFF); + led_trigger_event(&local->assoc_led, LED_OFF); } void ieee80211_led_radio(struct ieee80211_local *local, bool enabled) { - if (unlikely(!local->radio_led)) + if (!atomic_read(&local->radio_led_active)) return; if (enabled) - led_trigger_event(local->radio_led, LED_FULL); + led_trigger_event(&local->radio_led, LED_FULL); else - led_trigger_event(local->radio_led, LED_OFF); + led_trigger_event(&local->radio_led, LED_OFF); +} + +void ieee80211_alloc_led_names(struct ieee80211_local *local) +{ + local->rx_led.name = kasprintf(GFP_KERNEL, "%srx", + wiphy_name(local->hw.wiphy)); + local->tx_led.name = kasprintf(GFP_KERNEL, "%stx", + wiphy_name(local->hw.wiphy)); + local->assoc_led.name = kasprintf(GFP_KERNEL, "%sassoc", + wiphy_name(local->hw.wiphy)); + local->radio_led.name = kasprintf(GFP_KERNEL, "%sradio", + wiphy_name(local->hw.wiphy)); +} + +void ieee80211_free_led_names(struct ieee80211_local *local) +{ + kfree(local->rx_led.name); + kfree(local->tx_led.name); + kfree(local->assoc_led.name); + kfree(local->radio_led.name); +} + +static void ieee80211_tx_led_activate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + tx_led); + + atomic_inc(&local->tx_led_active); +} + +static void ieee80211_tx_led_deactivate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + tx_led); + + atomic_dec(&local->tx_led_active); +} + +static void ieee80211_rx_led_activate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + rx_led); + + atomic_inc(&local->rx_led_active); +} + +static void ieee80211_rx_led_deactivate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + rx_led); + + atomic_dec(&local->rx_led_active); +} + +static void ieee80211_assoc_led_activate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + assoc_led); + + atomic_inc(&local->assoc_led_active); +} + +static void ieee80211_assoc_led_deactivate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + assoc_led); + + atomic_dec(&local->assoc_led_active); +} + +static void ieee80211_radio_led_activate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + radio_led); + + atomic_inc(&local->radio_led_active); +} + +static void ieee80211_radio_led_deactivate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + radio_led); + + atomic_dec(&local->radio_led_active); +} + +static void ieee80211_tpt_led_activate(struct led_classdev *led_cdev) +{ + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + tpt_led); + + atomic_inc(&local->tpt_led_active); } -void ieee80211_led_names(struct ieee80211_local *local) +static void ieee80211_tpt_led_deactivate(struct led_classdev *led_cdev) { - snprintf(local->rx_led_name, sizeof(local->rx_led_name), - "%srx", wiphy_name(local->hw.wiphy)); - snprintf(local->tx_led_name, sizeof(local->tx_led_name), - "%stx", wiphy_name(local->hw.wiphy)); - snprintf(local->assoc_led_name, sizeof(local->assoc_led_name), - "%sassoc", wiphy_name(local->hw.wiphy)); - snprintf(local->radio_led_name, sizeof(local->radio_led_name), - "%sradio", wiphy_name(local->hw.wiphy)); + struct ieee80211_local *local = container_of(led_cdev->trigger, + struct ieee80211_local, + tpt_led); + + atomic_dec(&local->tpt_led_active); } void ieee80211_led_init(struct ieee80211_local *local) { - local->rx_led = kzalloc(sizeof(struct led_trigger), GFP_KERNEL); - if (local->rx_led) { - local->rx_led->name = local->rx_led_name; - if (led_trigger_register(local->rx_led)) { - kfree(local->rx_led); - local->rx_led = NULL; - } + atomic_set(&local->rx_led_active, 0); + local->rx_led.activate = ieee80211_rx_led_activate; + local->rx_led.deactivate = ieee80211_rx_led_deactivate; + if (local->rx_led.name && led_trigger_register(&local->rx_led)) { + kfree(local->rx_led.name); + local->rx_led.name = NULL; } - local->tx_led = kzalloc(sizeof(struct led_trigger), GFP_KERNEL); - if (local->tx_led) { - local->tx_led->name = local->tx_led_name; - if (led_trigger_register(local->tx_led)) { - kfree(local->tx_led); - local->tx_led = NULL; - } + atomic_set(&local->tx_led_active, 0); + local->tx_led.activate = ieee80211_tx_led_activate; + local->tx_led.deactivate = ieee80211_tx_led_deactivate; + if (local->tx_led.name && led_trigger_register(&local->tx_led)) { + kfree(local->tx_led.name); + local->tx_led.name = NULL; } - local->assoc_led = kzalloc(sizeof(struct led_trigger), GFP_KERNEL); - if (local->assoc_led) { - local->assoc_led->name = local->assoc_led_name; - if (led_trigger_register(local->assoc_led)) { - kfree(local->assoc_led); - local->assoc_led = NULL; - } + atomic_set(&local->assoc_led_active, 0); + local->assoc_led.activate = ieee80211_assoc_led_activate; + local->assoc_led.deactivate = ieee80211_assoc_led_deactivate; + if (local->assoc_led.name && led_trigger_register(&local->assoc_led)) { + kfree(local->assoc_led.name); + local->assoc_led.name = NULL; } - local->radio_led = kzalloc(sizeof(struct led_trigger), GFP_KERNEL); - if (local->radio_led) { - local->radio_led->name = local->radio_led_name; - if (led_trigger_register(local->radio_led)) { - kfree(local->radio_led); - local->radio_led = NULL; - } + atomic_set(&local->radio_led_active, 0); + local->radio_led.activate = ieee80211_radio_led_activate; + local->radio_led.deactivate = ieee80211_radio_led_deactivate; + if (local->radio_led.name && led_trigger_register(&local->radio_led)) { + kfree(local->radio_led.name); + local->radio_led.name = NULL; } + atomic_set(&local->tpt_led_active, 0); if (local->tpt_led_trigger) { - if (led_trigger_register(&local->tpt_led_trigger->trig)) { + local->tpt_led.activate = ieee80211_tpt_led_activate; + local->tpt_led.deactivate = ieee80211_tpt_led_deactivate; + if (led_trigger_register(&local->tpt_led)) { kfree(local->tpt_led_trigger); local->tpt_led_trigger = NULL; } @@ -110,58 +189,50 @@ void ieee80211_led_init(struct ieee80211_local *local) void ieee80211_led_exit(struct ieee80211_local *local) { - if (local->radio_led) { - led_trigger_unregister(local->radio_led); - kfree(local->radio_led); - } - if (local->assoc_led) { - led_trigger_unregister(local->assoc_led); - kfree(local->assoc_led); - } - if (local->tx_led) { - led_trigger_unregister(local->tx_led); - kfree(local->tx_led); - } - if (local->rx_led) { - led_trigger_unregister(local->rx_led); - kfree(local->rx_led); - } + if (local->radio_led.name) + led_trigger_unregister(&local->radio_led); + if (local->assoc_led.name) + led_trigger_unregister(&local->assoc_led); + if (local->tx_led.name) + led_trigger_unregister(&local->tx_led); + if (local->rx_led.name) + led_trigger_unregister(&local->rx_led); if (local->tpt_led_trigger) { - led_trigger_unregister(&local->tpt_led_trigger->trig); + led_trigger_unregister(&local->tpt_led); kfree(local->tpt_led_trigger); } } -char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw) +const char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); - return local->radio_led_name; + return local->radio_led.name; } EXPORT_SYMBOL(__ieee80211_get_radio_led_name); -char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw) +const char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); - return local->assoc_led_name; + return local->assoc_led.name; } EXPORT_SYMBOL(__ieee80211_get_assoc_led_name); -char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw) +const char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); - return local->tx_led_name; + return local->tx_led.name; } EXPORT_SYMBOL(__ieee80211_get_tx_led_name); -char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw) +const char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); - return local->rx_led_name; + return local->rx_led.name; } EXPORT_SYMBOL(__ieee80211_get_rx_led_name); @@ -205,16 +276,17 @@ static void tpt_trig_timer(unsigned long data) } } - read_lock(&tpt_trig->trig.leddev_list_lock); - list_for_each_entry(led_cdev, &tpt_trig->trig.led_cdevs, trig_list) + read_lock(&local->tpt_led.leddev_list_lock); + list_for_each_entry(led_cdev, &local->tpt_led.led_cdevs, trig_list) led_blink_set(led_cdev, &on, &off); - read_unlock(&tpt_trig->trig.leddev_list_lock); + read_unlock(&local->tpt_led.leddev_list_lock); } -char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, - unsigned int flags, - const struct ieee80211_tpt_blink *blink_table, - unsigned int blink_table_len) +const char * +__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, + unsigned int flags, + const struct ieee80211_tpt_blink *blink_table, + unsigned int blink_table_len) { struct ieee80211_local *local = hw_to_local(hw); struct tpt_led_trigger *tpt_trig; @@ -229,7 +301,7 @@ char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, snprintf(tpt_trig->name, sizeof(tpt_trig->name), "%stpt", wiphy_name(local->hw.wiphy)); - tpt_trig->trig.name = tpt_trig->name; + local->tpt_led.name = tpt_trig->name; tpt_trig->blink_table = blink_table; tpt_trig->blink_table_len = blink_table_len; @@ -269,10 +341,10 @@ static void ieee80211_stop_tpt_led_trig(struct ieee80211_local *local) tpt_trig->running = false; del_timer_sync(&tpt_trig->timer); - read_lock(&tpt_trig->trig.leddev_list_lock); - list_for_each_entry(led_cdev, &tpt_trig->trig.led_cdevs, trig_list) + read_lock(&local->tpt_led.leddev_list_lock); + list_for_each_entry(led_cdev, &local->tpt_led.led_cdevs, trig_list) led_set_brightness(led_cdev, LED_OFF); - read_unlock(&tpt_trig->trig.leddev_list_lock); + read_unlock(&local->tpt_led.leddev_list_lock); } void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local, diff --git a/net/mac80211/led.h b/net/mac80211/led.h index 89f4344f13b9..a7893a1ac98b 100644 --- a/net/mac80211/led.h +++ b/net/mac80211/led.h @@ -11,25 +11,42 @@ #include <linux/leds.h> #include "ieee80211_i.h" +#define MAC80211_BLINK_DELAY 50 /* ms */ + +static inline void ieee80211_led_rx(struct ieee80211_local *local) +{ +#ifdef CONFIG_MAC80211_LEDS + unsigned long led_delay = MAC80211_BLINK_DELAY; + + if (!atomic_read(&local->rx_led_active)) + return; + led_trigger_blink_oneshot(&local->rx_led, &led_delay, &led_delay, 0); +#endif +} + +static inline void ieee80211_led_tx(struct ieee80211_local *local) +{ +#ifdef CONFIG_MAC80211_LEDS + unsigned long led_delay = MAC80211_BLINK_DELAY; + + if (!atomic_read(&local->tx_led_active)) + return; + led_trigger_blink_oneshot(&local->tx_led, &led_delay, &led_delay, 0); +#endif +} + #ifdef CONFIG_MAC80211_LEDS -void ieee80211_led_rx(struct ieee80211_local *local); -void ieee80211_led_tx(struct ieee80211_local *local); void ieee80211_led_assoc(struct ieee80211_local *local, bool associated); void ieee80211_led_radio(struct ieee80211_local *local, bool enabled); -void ieee80211_led_names(struct ieee80211_local *local); +void ieee80211_alloc_led_names(struct ieee80211_local *local); +void ieee80211_free_led_names(struct ieee80211_local *local); void ieee80211_led_init(struct ieee80211_local *local); void ieee80211_led_exit(struct ieee80211_local *local); void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local, unsigned int types_on, unsigned int types_off); #else -static inline void ieee80211_led_rx(struct ieee80211_local *local) -{ -} -static inline void ieee80211_led_tx(struct ieee80211_local *local) -{ -} static inline void ieee80211_led_assoc(struct ieee80211_local *local, bool associated) { @@ -38,7 +55,10 @@ static inline void ieee80211_led_radio(struct ieee80211_local *local, bool enabled) { } -static inline void ieee80211_led_names(struct ieee80211_local *local) +static inline void ieee80211_alloc_led_names(struct ieee80211_local *local) +{ +} +static inline void ieee80211_free_led_names(struct ieee80211_local *local) { } static inline void ieee80211_led_init(struct ieee80211_local *local) @@ -58,7 +78,7 @@ static inline void ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, __le16 fc, int bytes) { #ifdef CONFIG_MAC80211_LEDS - if (local->tpt_led_trigger && ieee80211_is_data(fc)) + if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active)) local->tpt_led_trigger->tx_bytes += bytes; #endif } @@ -67,7 +87,7 @@ static inline void ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, __le16 fc, int bytes) { #ifdef CONFIG_MAC80211_LEDS - if (local->tpt_led_trigger && ieee80211_is_data(fc)) + if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active)) local->tpt_led_trigger->rx_bytes += bytes; #endif } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index df3051d96aff..674164fe5cdb 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -41,9 +41,6 @@ void ieee80211_configure_filter(struct ieee80211_local *local) unsigned int changed_flags; unsigned int new_flags = 0; - if (atomic_read(&local->iff_promiscs)) - new_flags |= FIF_PROMISC_IN_BSS; - if (atomic_read(&local->iff_allmultis)) new_flags |= FIF_ALLMULTI; @@ -249,6 +246,7 @@ static void ieee80211_restart_work(struct work_struct *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); + struct ieee80211_sub_if_data *sdata; /* wait for scan work complete */ flush_workqueue(local->workqueue); @@ -257,6 +255,8 @@ static void ieee80211_restart_work(struct work_struct *work) "%s called with hardware scan in progress\n", __func__); rtnl_lock(); + list_for_each_entry(sdata, &local->interfaces, list) + flush_delayed_work(&sdata->dec_tailroom_needed_wk); ieee80211_scan_cancel(local); ieee80211_reconfig(local); rtnl_unlock(); @@ -646,7 +646,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, skb_queue_head_init(&local->skb_queue); skb_queue_head_init(&local->skb_queue_unreliable); - ieee80211_led_names(local); + ieee80211_alloc_led_names(local); ieee80211_roc_setup(local); @@ -771,8 +771,13 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_256; } - for (r = 0; r < local->hw.n_cipher_schemes; r++) + for (r = 0; r < local->hw.n_cipher_schemes; r++) { suites[w++] = cs[r].cipher; + if (WARN_ON(cs[r].pn_len > IEEE80211_MAX_PN_LEN)) { + kfree(suites); + return -EINVAL; + } + } } local->hw.wiphy->cipher_suites = suites; @@ -840,7 +845,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) /* Only HW csum features are currently compatible with mac80211 */ feature_whitelist = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_HW_CSUM; + NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | + NETIF_F_GSO_SOFTWARE; if (WARN_ON(hw->netdev_features & ~feature_whitelist)) return -EINVAL; @@ -1209,6 +1215,8 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) sta_info_stop(local); + ieee80211_free_led_names(local); + wiphy_free(local->hw.wiphy); } EXPORT_SYMBOL(ieee80211_free_hw); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 60d737f144e3..ac843fc88745 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -72,10 +72,11 @@ static bool rssi_threshold_check(struct ieee80211_sub_if_data *sdata, * * @sta: mesh peer link to restart * - * Locking: this function must be called holding sta->lock + * Locking: this function must be called holding sta->plink_lock */ static inline void mesh_plink_fsm_restart(struct sta_info *sta) { + lockdep_assert_held(&sta->plink_lock); sta->plink_state = NL80211_PLINK_LISTEN; sta->llid = sta->plid = sta->reason = 0; sta->plink_retries = 0; @@ -213,13 +214,15 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) * All mesh paths with this peer as next hop will be flushed * Returns beacon changed flag if the beacon content changed. * - * Locking: the caller must hold sta->lock + * Locking: the caller must hold sta->plink_lock */ static u32 __mesh_plink_deactivate(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; u32 changed = 0; + lockdep_assert_held(&sta->plink_lock); + if (sta->plink_state == NL80211_PLINK_ESTAB) changed = mesh_plink_dec_estab_count(sdata); sta->plink_state = NL80211_PLINK_BLOCKED; @@ -244,13 +247,13 @@ u32 mesh_plink_deactivate(struct sta_info *sta) struct ieee80211_sub_if_data *sdata = sta->sdata; u32 changed; - spin_lock_bh(&sta->lock); + spin_lock_bh(&sta->plink_lock); changed = __mesh_plink_deactivate(sta); sta->reason = WLAN_REASON_MESH_PEER_CANCELED; mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, sta->sta.addr, sta->llid, sta->plid, sta->reason); - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); return changed; } @@ -387,7 +390,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, sband = local->hw.wiphy->bands[band]; rates = ieee80211_sta_get_rates(sdata, elems, band, &basic_rates); - spin_lock_bh(&sta->lock); + spin_lock_bh(&sta->plink_lock); sta->last_rx = jiffies; /* rates and capabilities don't change during peering */ @@ -419,7 +422,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, else rate_control_rate_update(local, sband, sta, changed); out: - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); } static struct sta_info * @@ -552,7 +555,7 @@ static void mesh_plink_timer(unsigned long data) if (sta->sdata->local->quiescing) return; - spin_lock_bh(&sta->lock); + spin_lock_bh(&sta->plink_lock); /* If a timer fires just before a state transition on another CPU, * we may have already extended the timeout and changed state by the @@ -563,7 +566,7 @@ static void mesh_plink_timer(unsigned long data) mpl_dbg(sta->sdata, "Ignoring timer for %pM in state %s (timer adjusted)", sta->sta.addr, mplstates[sta->plink_state]); - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); return; } @@ -573,7 +576,7 @@ static void mesh_plink_timer(unsigned long data) mpl_dbg(sta->sdata, "Ignoring timer for %pM in state %s (timer deleted)", sta->sta.addr, mplstates[sta->plink_state]); - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); return; } @@ -619,7 +622,7 @@ static void mesh_plink_timer(unsigned long data) default: break; } - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); if (action) mesh_plink_frame_tx(sdata, action, sta->sta.addr, sta->llid, sta->plid, reason); @@ -674,16 +677,16 @@ u32 mesh_plink_open(struct sta_info *sta) if (!test_sta_flag(sta, WLAN_STA_AUTH)) return 0; - spin_lock_bh(&sta->lock); + spin_lock_bh(&sta->plink_lock); sta->llid = mesh_get_new_llid(sdata); if (sta->plink_state != NL80211_PLINK_LISTEN && sta->plink_state != NL80211_PLINK_BLOCKED) { - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); return 0; } sta->plink_state = NL80211_PLINK_OPN_SNT; mesh_plink_timer_set(sta, sdata->u.mesh.mshcfg.dot11MeshRetryTimeout); - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); mpl_dbg(sdata, "Mesh plink: starting establishment with %pM\n", sta->sta.addr); @@ -700,10 +703,10 @@ u32 mesh_plink_block(struct sta_info *sta) { u32 changed; - spin_lock_bh(&sta->lock); + spin_lock_bh(&sta->plink_lock); changed = __mesh_plink_deactivate(sta); sta->plink_state = NL80211_PLINK_BLOCKED; - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); return changed; } @@ -758,7 +761,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, mpl_dbg(sdata, "peer %pM in state %s got event %s\n", sta->sta.addr, mplstates[sta->plink_state], mplevents[event]); - spin_lock_bh(&sta->lock); + spin_lock_bh(&sta->plink_lock); switch (sta->plink_state) { case NL80211_PLINK_LISTEN: switch (event) { @@ -872,7 +875,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, */ break; } - spin_unlock_bh(&sta->lock); + spin_unlock_bh(&sta->plink_lock); if (action) { mesh_plink_frame_tx(sdata, action, sta->sta.addr, sta->llid, sta->plid, sta->reason); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 26053bf2faa8..387fe70ab126 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1098,6 +1098,24 @@ static void ieee80211_chswitch_timer(unsigned long data) ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.chswitch_work); } +static void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) +{ + struct sta_info *sta; + u16 reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { + if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || + !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + continue; + + ieee80211_tdls_oper_request(&sdata->vif, sta->sta.addr, + NL80211_TDLS_TEARDOWN, reason, + GFP_ATOMIC); + } + rcu_read_unlock(); +} + static void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, u64 timestamp, u32 device_timestamp, @@ -1161,6 +1179,14 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, return; } + /* + * Drop all TDLS peers - either we disconnect or move to a different + * channel from this point on. There's no telling what our peer will do. + * The TDLS WIDER_BW scenario is also problematic, as peers might now + * have an incompatible wider chandef. + */ + ieee80211_teardown_tdls_peers(sdata); + mutex_lock(&local->mtx); mutex_lock(&local->chanctx_mtx); conf = rcu_dereference_protected(sdata->vif.chanctx_conf, @@ -4307,15 +4333,15 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, - struct cfg80211_bss *cbss, bool assoc) + struct cfg80211_bss *cbss, bool assoc, + bool override) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_bss *bss = (void *)cbss->priv; struct sta_info *new_sta = NULL; struct ieee80211_supported_band *sband; - struct ieee80211_sta_ht_cap sta_ht_cap; - bool have_sta = false, is_override = false; + bool have_sta = false; int err; sband = local->hw.wiphy->bands[cbss->channel->band]; @@ -4335,14 +4361,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, return -ENOMEM; } - memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap)); - ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap); - - is_override = (sta_ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) != - (sband->ht_cap.cap & - IEEE80211_HT_CAP_SUP_WIDTH_20_40); - - if (new_sta || is_override) { + if (new_sta || override) { err = ieee80211_prep_channel(sdata, cbss); if (err) { if (new_sta) @@ -4552,7 +4571,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid); - err = ieee80211_prep_connection(sdata, req->bss, false); + err = ieee80211_prep_connection(sdata, req->bss, false, false); if (err) goto err_clear; @@ -4624,6 +4643,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband; const u8 *ssidie, *ht_ie, *vht_ie; int i, err; + bool override = false; assoc_data = kzalloc(sizeof(*assoc_data) + req->ie_len, GFP_KERNEL); if (!assoc_data) @@ -4728,14 +4748,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, } } - if (req->flags & ASSOC_REQ_DISABLE_HT) { - ifmgd->flags |= IEEE80211_STA_DISABLE_HT; - ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; - } - - if (req->flags & ASSOC_REQ_DISABLE_VHT) - ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; - /* Also disable HT if we don't support it or the AP doesn't use WMM */ sband = local->hw.wiphy->bands[req->bss->channel->band]; if (!sband->ht_cap.ht_supported || @@ -4847,7 +4859,36 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, ifmgd->dtim_period = 0; ifmgd->have_beacon = false; - err = ieee80211_prep_connection(sdata, req->bss, true); + /* override HT/VHT configuration only if the AP and we support it */ + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) { + struct ieee80211_sta_ht_cap sta_ht_cap; + + if (req->flags & ASSOC_REQ_DISABLE_HT) + override = true; + + memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap)); + ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap); + + /* check for 40 MHz disable override */ + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_40MHZ) && + sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 && + !(sta_ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40)) + override = true; + + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) && + req->flags & ASSOC_REQ_DISABLE_VHT) + override = true; + } + + if (req->flags & ASSOC_REQ_DISABLE_HT) { + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + } + + if (req->flags & ASSOC_REQ_DISABLE_VHT) + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + + err = ieee80211_prep_connection(sdata, req->bss, true, override); if (err) goto err_clear; diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index d53355b011f5..de69adf24f53 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -683,7 +683,13 @@ void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, if (sdata->local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) return; - ref->ops->get_rate(ref->priv, ista, priv_sta, txrc); + if (ista) { + spin_lock_bh(&sta->rate_ctrl_lock); + ref->ops->get_rate(ref->priv, ista, priv_sta, txrc); + spin_unlock_bh(&sta->rate_ctrl_lock); + } else { + ref->ops->get_rate(ref->priv, NULL, NULL, txrc); + } if (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_RC_TABLE) return; diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 38652f09feaf..25c9be5dd7fd 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -42,10 +42,12 @@ static inline void rate_control_tx_status(struct ieee80211_local *local, if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) return; + spin_lock_bh(&sta->rate_ctrl_lock); if (ref->ops->tx_status) ref->ops->tx_status(ref->priv, sband, ista, priv_sta, skb); else ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info); + spin_unlock_bh(&sta->rate_ctrl_lock); } static inline void @@ -64,7 +66,9 @@ rate_control_tx_status_noskb(struct ieee80211_local *local, if (WARN_ON_ONCE(!ref->ops->tx_status_noskb)) return; + spin_lock_bh(&sta->rate_ctrl_lock); ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info); + spin_unlock_bh(&sta->rate_ctrl_lock); } static inline void rate_control_rate_init(struct sta_info *sta) @@ -91,8 +95,10 @@ static inline void rate_control_rate_init(struct sta_info *sta) sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band]; + spin_lock_bh(&sta->rate_ctrl_lock); ref->ops->rate_init(ref->priv, sband, &chanctx_conf->def, ista, priv_sta); + spin_unlock_bh(&sta->rate_ctrl_lock); rcu_read_unlock(); set_sta_flag(sta, WLAN_STA_RATE_CONTROL); } @@ -115,18 +121,20 @@ static inline void rate_control_rate_update(struct ieee80211_local *local, return; } + spin_lock_bh(&sta->rate_ctrl_lock); ref->ops->rate_update(ref->priv, sband, &chanctx_conf->def, ista, priv_sta, changed); + spin_unlock_bh(&sta->rate_ctrl_lock); rcu_read_unlock(); } drv_sta_rc_update(local, sta->sdata, &sta->sta, changed); } static inline void *rate_control_alloc_sta(struct rate_control_ref *ref, - struct ieee80211_sta *sta, - gfp_t gfp) + struct sta_info *sta, gfp_t gfp) { - return ref->ops->alloc_sta(ref->priv, sta, gfp); + spin_lock_init(&sta->rate_ctrl_lock); + return ref->ops->alloc_sta(ref->priv, &sta->sta, gfp); } static inline void rate_control_free_sta(struct sta_info *sta) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5793f75c5ffd..7d85f7516324 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -32,6 +32,16 @@ #include "wme.h" #include "rate.h" +static inline void ieee80211_rx_stats(struct net_device *dev, u32 len) +{ + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += len; + u64_stats_update_end(&tstats->syncp); +} + /* * monitor mode reception * @@ -529,8 +539,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, } prev_dev = sdata->dev; - sdata->dev->stats.rx_packets++; - sdata->dev->stats.rx_bytes += skb->len; + ieee80211_rx_stats(sdata->dev, skb->len); } if (prev_dev) { @@ -981,7 +990,6 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, struct sk_buff *skb = rx->skb; struct ieee80211_local *local = rx->local; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct sta_info *sta = rx->sta; struct tid_ampdu_rx *tid_agg_rx; u16 sc; @@ -1016,10 +1024,6 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_NORMAL) goto dont_reorder; - /* not actually part of this BA session */ - if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) - goto dont_reorder; - /* new, potentially un-ordered, ampdu frame - process it */ /* reset session timer */ @@ -1073,10 +1077,8 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) if (unlikely(ieee80211_has_retry(hdr->frame_control) && rx->sta->last_seq_ctrl[rx->seqno_idx] == hdr->seq_ctrl)) { - if (status->rx_flags & IEEE80211_RX_RA_MATCH) { - rx->local->dot11FrameDuplicateCount++; - rx->sta->num_duplicates++; - } + I802_DEBUG_INC(rx->local->dot11FrameDuplicateCount); + rx->sta->num_duplicates++; return RX_DROP_UNUSABLE; } else if (!(status->flag & RX_FLAG_AMSDU_MORE)) { rx->sta->last_seq_ctrl[rx->seqno_idx] = hdr->seq_ctrl; @@ -1200,6 +1202,8 @@ static void sta_ps_start(struct sta_info *sta) ps_dbg(sdata, "STA %pM aid %d enters power save mode\n", sta->sta.addr, sta->sta.aid); + ieee80211_clear_fast_xmit(sta); + if (!sta->sta.txq[0]) return; @@ -1265,7 +1269,7 @@ ieee80211_rx_h_uapsd_and_pspoll(struct ieee80211_rx_data *rx) struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); int tid, ac; - if (!rx->sta || !(status->rx_flags & IEEE80211_RX_RA_MATCH)) + if (!rx->sta) return RX_CONTINUE; if (sdata->vif.type != NL80211_IFTYPE_AP && @@ -1367,11 +1371,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) } } } else if (rx->sdata->vif.type == NL80211_IFTYPE_OCB) { - u8 *bssid = ieee80211_get_bssid(hdr, rx->skb->len, - NL80211_IFTYPE_OCB); - /* OCB uses wild-card BSSID */ - if (is_broadcast_ether_addr(bssid)) - sta->last_rx = jiffies; + sta->last_rx = jiffies; } else if (!is_multicast_ether_addr(hdr->addr1)) { /* * Mesh beacons will update last_rx when if they are found to @@ -1386,9 +1386,6 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) } } - if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) - return RX_CONTINUE; - if (rx->sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_sta_rx_notify(rx->sdata, hdr); @@ -1517,13 +1514,6 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) * possible. */ - /* - * No point in finding a key and decrypting if the frame is neither - * addressed to us nor a multicast frame. - */ - if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) - return RX_CONTINUE; - /* start without a key */ rx->key = NULL; fc = hdr->frame_control; @@ -1795,7 +1785,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) frag = sc & IEEE80211_SCTL_FRAG; if (is_multicast_ether_addr(hdr->addr1)) { - rx->local->dot11MulticastReceivedFrameCount++; + I802_DEBUG_INC(rx->local->dot11MulticastReceivedFrameCount); goto out_no_led; } @@ -1878,7 +1868,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) rx->skb = __skb_dequeue(&entry->skb_list); if (skb_tailroom(rx->skb) < entry->extra_len) { - I802_DEBUG_INC(rx->local->rx_expand_skb_head2); + I802_DEBUG_INC(rx->local->rx_expand_skb_head_defrag); if (unlikely(pskb_expand_head(rx->skb, 0, entry->extra_len, GFP_ATOMIC))) { I802_DEBUG_INC(rx->local->rx_handlers_drop_defrag); @@ -2054,18 +2044,15 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) struct sk_buff *skb, *xmit_skb; struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data; struct sta_info *dsta; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); - - dev->stats.rx_packets++; - dev->stats.rx_bytes += rx->skb->len; skb = rx->skb; xmit_skb = NULL; + ieee80211_rx_stats(dev, skb->len); + if ((sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && - (status->rx_flags & IEEE80211_RX_RA_MATCH) && (sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta)) { if (is_multicast_ether_addr(ehdr->h_dest)) { /* @@ -2207,7 +2194,6 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct sk_buff *skb = rx->skb, *fwd_skb; struct ieee80211_local *local = rx->local; struct ieee80211_sub_if_data *sdata = rx->sdata; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u16 q, hdrlen; @@ -2238,8 +2224,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) mesh_rmc_check(rx->sdata, hdr->addr3, mesh_hdr)) return RX_DROP_MONITOR; - if (!ieee80211_is_data(hdr->frame_control) || - !(status->rx_flags & IEEE80211_RX_RA_MATCH)) + if (!ieee80211_is_data(hdr->frame_control)) return RX_CONTINUE; if (!mesh_hdr->ttl) @@ -2330,11 +2315,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, fwded_frames); ieee80211_add_pending_skb(local, fwd_skb); out: - if (is_multicast_ether_addr(hdr->addr1) || - sdata->dev->flags & IFF_PROMISC) + if (is_multicast_ether_addr(hdr->addr1)) return RX_CONTINUE; - else - return RX_DROP_MONITOR; + return RX_DROP_MONITOR; } #endif @@ -2445,6 +2428,9 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx, struct sk_buff_head *frames) struct { __le16 control, start_seq_num; } __packed bar_data; + struct ieee80211_event event = { + .type = BAR_RX_EVENT, + }; if (!rx->sta) return RX_DROP_MONITOR; @@ -2460,6 +2446,9 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx, struct sk_buff_head *frames) return RX_DROP_MONITOR; start_seq_num = le16_to_cpu(bar_data.start_seq_num) >> 4; + event.u.ba.tid = tid; + event.u.ba.ssn = start_seq_num; + event.u.ba.sta = &rx->sta->sta; /* reset session timer */ if (tid_agg_rx->timeout) @@ -2472,6 +2461,8 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx, struct sk_buff_head *frames) start_seq_num, frames); spin_unlock(&tid_agg_rx->reorder_lock); + drv_event_callback(rx->local, rx->sdata, &event); + kfree_skb(skb); return RX_QUEUED; } @@ -2561,9 +2552,6 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx) rx->flags |= IEEE80211_RX_BEACON_REPORTED; } - if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) - return RX_DROP_MONITOR; - if (ieee80211_drop_unencrypted_mgmt(rx)) return RX_DROP_UNUSABLE; @@ -2591,9 +2579,6 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) mgmt->u.action.category != WLAN_CATEGORY_SPECTRUM_MGMT) return RX_DROP_UNUSABLE; - if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) - return RX_DROP_UNUSABLE; - switch (mgmt->u.action.category) { case WLAN_CATEGORY_HT: /* reject HT action frames from stations not supporting HT */ @@ -3077,8 +3062,7 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, } prev_dev = sdata->dev; - sdata->dev->stats.rx_packets++; - sdata->dev->stats.rx_bytes += skb->len; + ieee80211_rx_stats(sdata->dev, skb->len); } if (prev_dev) { @@ -3246,16 +3230,25 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) ieee80211_sta_reorder_release(sta->sdata, tid_agg_rx, &frames); spin_unlock(&tid_agg_rx->reorder_lock); + if (!skb_queue_empty(&frames)) { + struct ieee80211_event event = { + .type = BA_FRAME_TIMEOUT, + .u.ba.tid = tid, + .u.ba.sta = &sta->sta, + }; + drv_event_callback(rx.local, rx.sdata, &event); + } + ieee80211_rx_handlers(&rx, &frames); } /* main receive path */ -static bool prepare_for_handlers(struct ieee80211_rx_data *rx, - struct ieee80211_hdr *hdr) +static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) { struct ieee80211_sub_if_data *sdata = rx->sdata; struct sk_buff *skb = rx->skb; + struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); u8 *bssid = ieee80211_get_bssid(hdr, skb->len, sdata->vif.type); int multicast = is_multicast_ether_addr(hdr->addr1); @@ -3264,30 +3257,23 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx, case NL80211_IFTYPE_STATION: if (!bssid && !sdata->u.mgd.use_4addr) return false; - if (!multicast && - !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { - if (!(sdata->dev->flags & IFF_PROMISC) || - sdata->u.mgd.use_4addr) - return false; - status->rx_flags &= ~IEEE80211_RX_RA_MATCH; - } - break; + if (multicast) + return true; + return ether_addr_equal(sdata->vif.addr, hdr->addr1); case NL80211_IFTYPE_ADHOC: if (!bssid) return false; if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) return false; - if (ieee80211_is_beacon(hdr->frame_control)) { + if (ieee80211_is_beacon(hdr->frame_control)) return true; - } else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) { + if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) return false; - } else if (!multicast && - !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { - if (!(sdata->dev->flags & IFF_PROMISC)) - return false; - status->rx_flags &= ~IEEE80211_RX_RA_MATCH; - } else if (!rx->sta) { + if (!multicast && + !ether_addr_equal(sdata->vif.addr, hdr->addr1)) + return false; + if (!rx->sta) { int rate_idx; if (status->flag & (RX_FLAG_HT | RX_FLAG_VHT)) rate_idx = 0; /* TODO: HT/VHT rates */ @@ -3296,25 +3282,18 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx, ieee80211_ibss_rx_no_sta(sdata, bssid, hdr->addr2, BIT(rate_idx)); } - break; + return true; case NL80211_IFTYPE_OCB: if (!bssid) return false; - if (ieee80211_is_beacon(hdr->frame_control)) { + if (ieee80211_is_beacon(hdr->frame_control)) return false; - } else if (!is_broadcast_ether_addr(bssid)) { - ocb_dbg(sdata, "BSSID mismatch in OCB mode!\n"); + if (!is_broadcast_ether_addr(bssid)) return false; - } else if (!multicast && - !ether_addr_equal(sdata->dev->dev_addr, - hdr->addr1)) { - /* if we are in promisc mode we also accept - * packets not destined for us - */ - if (!(sdata->dev->flags & IFF_PROMISC)) - return false; - rx->flags &= ~IEEE80211_RX_RA_MATCH; - } else if (!rx->sta) { + if (!multicast && + !ether_addr_equal(sdata->dev->dev_addr, hdr->addr1)) + return false; + if (!rx->sta) { int rate_idx; if (status->flag & RX_FLAG_HT) rate_idx = 0; /* TODO: HT rates */ @@ -3323,22 +3302,17 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx, ieee80211_ocb_rx_no_sta(sdata, bssid, hdr->addr2, BIT(rate_idx)); } - break; + return true; case NL80211_IFTYPE_MESH_POINT: - if (!multicast && - !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { - if (!(sdata->dev->flags & IFF_PROMISC)) - return false; - - status->rx_flags &= ~IEEE80211_RX_RA_MATCH; - } - break; + if (multicast) + return true; + return ether_addr_equal(sdata->vif.addr, hdr->addr1); case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_AP: - if (!bssid) { - if (!ether_addr_equal(sdata->vif.addr, hdr->addr1)) - return false; - } else if (!ieee80211_bssid_match(bssid, sdata->vif.addr)) { + if (!bssid) + return ether_addr_equal(sdata->vif.addr, hdr->addr1); + + if (!ieee80211_bssid_match(bssid, sdata->vif.addr)) { /* * Accept public action frames even when the * BSSID doesn't match, this is used for P2P @@ -3350,10 +3324,10 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx, return false; if (ieee80211_is_public_action(hdr, skb->len)) return true; - if (!ieee80211_is_beacon(hdr->frame_control)) - return false; - status->rx_flags &= ~IEEE80211_RX_RA_MATCH; - } else if (!ieee80211_has_tods(hdr->frame_control)) { + return ieee80211_is_beacon(hdr->frame_control); + } + + if (!ieee80211_has_tods(hdr->frame_control)) { /* ignore data frames to TDLS-peers */ if (ieee80211_is_data(hdr->frame_control)) return false; @@ -3362,30 +3336,22 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx, !ether_addr_equal(bssid, hdr->addr1)) return false; } - break; + return true; case NL80211_IFTYPE_WDS: if (bssid || !ieee80211_is_data(hdr->frame_control)) return false; - if (!ether_addr_equal(sdata->u.wds.remote_addr, hdr->addr2)) - return false; - break; + return ether_addr_equal(sdata->u.wds.remote_addr, hdr->addr2); case NL80211_IFTYPE_P2P_DEVICE: - if (!ieee80211_is_public_action(hdr, skb->len) && - !ieee80211_is_probe_req(hdr->frame_control) && - !ieee80211_is_probe_resp(hdr->frame_control) && - !ieee80211_is_beacon(hdr->frame_control)) - return false; - if (!ether_addr_equal(sdata->vif.addr, hdr->addr1) && - !multicast) - status->rx_flags &= ~IEEE80211_RX_RA_MATCH; - break; + return ieee80211_is_public_action(hdr, skb->len) || + ieee80211_is_probe_req(hdr->frame_control) || + ieee80211_is_probe_resp(hdr->frame_control) || + ieee80211_is_beacon(hdr->frame_control); default: - /* should never get here */ - WARN_ON_ONCE(1); break; } - return true; + WARN_ON_ONCE(1); + return false; } /* @@ -3399,13 +3365,10 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, { struct ieee80211_local *local = rx->local; struct ieee80211_sub_if_data *sdata = rx->sdata; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - struct ieee80211_hdr *hdr = (void *)skb->data; rx->skb = skb; - status->rx_flags |= IEEE80211_RX_RA_MATCH; - if (!prepare_for_handlers(rx, hdr)) + if (!ieee80211_accept_frame(rx)) return false; if (!consume) { @@ -3448,7 +3411,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, rx.local = local; if (ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) - local->dot11ReceivedFragmentCount++; + I802_DEBUG_INC(local->dot11ReceivedFragmentCount); if (ieee80211_is_mgmt(fc)) { /* drop frame if too short for header */ diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2880f2ae99ab..ce0c1662de42 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -71,6 +71,7 @@ static const struct rhashtable_params sta_rht_params = { .key_offset = offsetof(struct sta_info, sta.addr), .key_len = ETH_ALEN, .hashfn = sta_addr_hash, + .max_size = CONFIG_MAC80211_STA_HASH_MAX_SIZE, }; /* Caller must hold local->sta_mtx */ @@ -286,7 +287,7 @@ static int sta_prepare_rate_control(struct ieee80211_local *local, sta->rate_ctrl = local->rate_ctrl; sta->rate_ctrl_priv = rate_control_alloc_sta(sta->rate_ctrl, - &sta->sta, gfp); + sta, gfp); if (!sta->rate_ctrl_priv) return -ENOMEM; @@ -312,6 +313,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); #ifdef CONFIG_MAC80211_MESH + spin_lock_init(&sta->plink_lock); if (ieee80211_vif_is_mesh(&sdata->vif) && !sdata->u.mesh.user_mpm) init_timer(&sta->plink_timer); @@ -1217,6 +1219,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) ps_dbg(sdata, "STA %pM aid %d sending %d filtered/%d PS frames since STA not sleeping anymore\n", sta->sta.addr, sta->sta.aid, filtered, buffered); + + ieee80211_check_fast_xmit(sta); } static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, @@ -1615,6 +1619,7 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, if (block) { set_sta_flag(sta, WLAN_STA_PS_DRIVER); + ieee80211_clear_fast_xmit(sta); return; } @@ -1632,6 +1637,7 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, ieee80211_queue_work(hw, &sta->drv_deliver_wk); } else { clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + ieee80211_check_fast_xmit(sta); } } EXPORT_SYMBOL(ieee80211_sta_block_awake); @@ -1736,6 +1742,7 @@ int sta_info_move_state(struct sta_info *sta, !sta->sdata->u.vlan.sta)) atomic_dec(&sta->sdata->bss->num_mcast_sta); clear_bit(WLAN_STA_AUTHORIZED, &sta->_flags); + ieee80211_clear_fast_xmit(sta); } break; case IEEE80211_STA_AUTHORIZED: @@ -1745,6 +1752,7 @@ int sta_info_move_state(struct sta_info *sta, !sta->sdata->u.vlan.sta)) atomic_inc(&sta->sdata->bss->num_mcast_sta); set_bit(WLAN_STA_AUTHORIZED, &sta->_flags); + ieee80211_check_fast_xmit(sta); } break; default: diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 5c164fb3f6c5..9bd1e97876bd 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -241,6 +241,34 @@ struct sta_ampdu_mlme { /* Value to indicate no TID reservation */ #define IEEE80211_TID_UNRESERVED 0xff +#define IEEE80211_FAST_XMIT_MAX_IV 18 + +/** + * struct ieee80211_fast_tx - TX fastpath information + * @key: key to use for hw crypto + * @hdr: the 802.11 header to put with the frame + * @hdr_len: actual 802.11 header length + * @sa_offs: offset of the SA + * @da_offs: offset of the DA + * @pn_offs: offset where to put PN for crypto (or 0 if not needed) + * @band: band this will be transmitted on, for tx_info + * @rcu_head: RCU head to free this struct + * + * This struct is small enough so that the common case (maximum crypto + * header length of 8 like for CCMP/GCMP) fits into a single 64-byte + * cache line. + */ +struct ieee80211_fast_tx { + struct ieee80211_key *key; + u8 hdr_len; + u8 sa_offs, da_offs, pn_offs; + u8 band; + u8 hdr[30 + 2 + IEEE80211_FAST_XMIT_MAX_IV + + sizeof(rfc1042_header)]; + + struct rcu_head rcu_head; +}; + /** * struct sta_info - STA information * @@ -257,6 +285,8 @@ struct sta_ampdu_mlme { * @gtk: group keys negotiated with this station, if any * @gtk_idx: last installed group key index * @rate_ctrl: rate control algorithm reference + * @rate_ctrl_lock: spinlock used to protect rate control data + * (data inside the algorithm, so serializes calls there) * @rate_ctrl_priv: rate control private per-STA pointer * @last_tx_rate: rate used for last transmit, to report to userspace as * "the" transmit rate @@ -295,10 +325,10 @@ struct sta_ampdu_mlme { * @fail_avg: moving percentage of failed MSDUs * @tx_packets: number of RX/TX MSDUs * @tx_bytes: number of bytes transmitted to this STA - * @tx_fragments: number of transmitted MPDUs * @tid_seq: per-TID sequence numbers for sending to this STA * @ampdu_mlme: A-MPDU state machine state * @timer_to_tid: identity mapping to ID timers + * @plink_lock: serialize access to plink fields * @llid: Local link ID * @plid: Peer link ID * @reason: Cancel reason on PLINK_HOLDING state @@ -338,6 +368,7 @@ struct sta_ampdu_mlme { * using IEEE80211_NUM_TID entry for non-QoS frames * @rx_msdu: MSDUs received from this station, using IEEE80211_NUM_TID * entry for non-QoS frames + * @fast_tx: TX fastpath information */ struct sta_info { /* General information, mostly static */ @@ -352,8 +383,11 @@ struct sta_info { u8 ptk_idx; struct rate_control_ref *rate_ctrl; void *rate_ctrl_priv; + spinlock_t rate_ctrl_lock; spinlock_t lock; + struct ieee80211_fast_tx __rcu *fast_tx; + struct work_struct drv_deliver_wk; u16 listen_interval; @@ -400,7 +434,6 @@ struct sta_info { unsigned int fail_avg; /* Updated from TX path only, no locking requirements */ - u32 tx_fragments; u64 tx_packets[IEEE80211_NUM_ACS]; u64 tx_bytes[IEEE80211_NUM_ACS]; struct ieee80211_tx_rate last_tx_rate; @@ -422,9 +455,10 @@ struct sta_info { #ifdef CONFIG_MAC80211_MESH /* - * Mesh peer link attributes + * Mesh peer link attributes, protected by plink_lock. * TODO: move to a sub-structure that is referenced with pointer? */ + spinlock_t plink_lock; u16 llid; u16 plid; u16 reason; @@ -432,6 +466,7 @@ struct sta_info { enum nl80211_plink_state plink_state; u32 plink_timeout; struct timer_list plink_timer; + s64 t_offset; s64 t_offset_setpoint; /* mesh power save */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 005fdbe39a8b..461594966b65 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -631,15 +631,15 @@ void ieee80211_tx_status_noskb(struct ieee80211_hw *hw, } if (acked || noack_success) { - local->dot11TransmittedFrameCount++; - if (!pubsta) - local->dot11MulticastTransmittedFrameCount++; - if (retry_count > 0) - local->dot11RetryCount++; - if (retry_count > 1) - local->dot11MultipleRetryCount++; + I802_DEBUG_INC(local->dot11TransmittedFrameCount); + if (!pubsta) + I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount); + if (retry_count > 0) + I802_DEBUG_INC(local->dot11RetryCount); + if (retry_count > 1) + I802_DEBUG_INC(local->dot11MultipleRetryCount); } else { - local->dot11FailedCount++; + I802_DEBUG_INC(local->dot11FailedCount); } } EXPORT_SYMBOL(ieee80211_tx_status_noskb); @@ -802,13 +802,13 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if ((info->flags & IEEE80211_TX_STAT_ACK) || (info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED)) { if (ieee80211_is_first_frag(hdr->seq_ctrl)) { - local->dot11TransmittedFrameCount++; + I802_DEBUG_INC(local->dot11TransmittedFrameCount); if (is_multicast_ether_addr(ieee80211_get_DA(hdr))) - local->dot11MulticastTransmittedFrameCount++; + I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount); if (retry_count > 0) - local->dot11RetryCount++; + I802_DEBUG_INC(local->dot11RetryCount); if (retry_count > 1) - local->dot11MultipleRetryCount++; + I802_DEBUG_INC(local->dot11MultipleRetryCount); } /* This counter shall be incremented for an acknowledged MPDU @@ -818,10 +818,10 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (!is_multicast_ether_addr(hdr->addr1) || ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) - local->dot11TransmittedFragmentCount++; + I802_DEBUG_INC(local->dot11TransmittedFragmentCount); } else { if (ieee80211_is_first_frag(hdr->seq_ctrl)) - local->dot11FailedCount++; + I802_DEBUG_INC(local->dot11FailedCount); } if (ieee80211_is_nullfunc(fc) && ieee80211_has_pm(fc) && diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index fff0d864adfa..75e8e3bba538 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -527,30 +527,19 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, /* if HT support is only added in TDLS, we need an HT-operation IE */ if (!ap_sta->sta.ht_cap.ht_supported && sta->sta.ht_cap.ht_supported) { - struct ieee80211_chanctx_conf *chanctx_conf = - rcu_dereference(sdata->vif.chanctx_conf); - if (!WARN_ON(!chanctx_conf)) { - pos = skb_put(skb, 2 + - sizeof(struct ieee80211_ht_operation)); - /* send an empty HT operation IE */ - ieee80211_ie_build_ht_oper(pos, &sta->sta.ht_cap, - &chanctx_conf->def, 0); - } + pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_operation)); + /* send an empty HT operation IE */ + ieee80211_ie_build_ht_oper(pos, &sta->sta.ht_cap, + &sdata->vif.bss_conf.chandef, 0); } ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); /* only include VHT-operation if not on the 2.4GHz band */ - if (band != IEEE80211_BAND_2GHZ && !ap_sta->sta.vht_cap.vht_supported && - sta->sta.vht_cap.vht_supported) { - struct ieee80211_chanctx_conf *chanctx_conf = - rcu_dereference(sdata->vif.chanctx_conf); - if (!WARN_ON(!chanctx_conf)) { - pos = skb_put(skb, 2 + - sizeof(struct ieee80211_vht_operation)); - ieee80211_ie_build_vht_oper(pos, &sta->sta.vht_cap, - &chanctx_conf->def); - } + if (band != IEEE80211_BAND_2GHZ && sta->sta.vht_cap.vht_supported) { + pos = skb_put(skb, 2 + sizeof(struct ieee80211_vht_operation)); + ieee80211_ie_build_vht_oper(pos, &sta->sta.vht_cap, + &sdata->vif.bss_conf.chandef); } rcu_read_unlock(); @@ -1194,6 +1183,12 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, switch (oper) { case NL80211_TDLS_ENABLE_LINK: + if (sdata->vif.csa_active) { + tdls_dbg(sdata, "TDLS: disallow link during CSA\n"); + ret = -EBUSY; + break; + } + rcu_read_lock(); sta = sta_info_get(sdata, peer); if (!sta) { diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 4c2e7690226a..6f14591d8ca9 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -69,6 +69,17 @@ #define CHANCTX_PR_ARG CHANDEF_PR_ARG, MIN_CHANDEF_PR_ARG, \ __entry->rx_chains_static, __entry->rx_chains_dynamic +#define KEY_ENTRY __field(u32, cipher) \ + __field(u8, hw_key_idx) \ + __field(u8, flags) \ + __field(s8, keyidx) +#define KEY_ASSIGN(k) __entry->cipher = (k)->cipher; \ + __entry->flags = (k)->flags; \ + __entry->keyidx = (k)->keyidx; \ + __entry->hw_key_idx = (k)->hw_key_idx; +#define KEY_PR_FMT " cipher:0x%x, flags=%#x, keyidx=%d, hw_key_idx=%d" +#define KEY_PR_ARG __entry->cipher, __entry->flags, __entry->keyidx, __entry->hw_key_idx + /* @@ -522,25 +533,19 @@ TRACE_EVENT(drv_set_key, LOCAL_ENTRY VIF_ENTRY STA_ENTRY - __field(u32, cipher) - __field(u8, hw_key_idx) - __field(u8, flags) - __field(s8, keyidx) + KEY_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; STA_ASSIGN; - __entry->cipher = key->cipher; - __entry->flags = key->flags; - __entry->keyidx = key->keyidx; - __entry->hw_key_idx = key->hw_key_idx; + KEY_ASSIGN(key); ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT, - LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT KEY_PR_FMT, + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, KEY_PR_ARG ) ); @@ -656,28 +661,25 @@ TRACE_EVENT(drv_get_stats, ) ); -TRACE_EVENT(drv_get_tkip_seq, +TRACE_EVENT(drv_get_key_seq, TP_PROTO(struct ieee80211_local *local, - u8 hw_key_idx, u32 *iv32, u16 *iv16), + struct ieee80211_key_conf *key), - TP_ARGS(local, hw_key_idx, iv32, iv16), + TP_ARGS(local, key), TP_STRUCT__entry( LOCAL_ENTRY - __field(u8, hw_key_idx) - __field(u32, iv32) - __field(u16, iv16) + KEY_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; - __entry->hw_key_idx = hw_key_idx; - __entry->iv32 = *iv32; - __entry->iv16 = *iv16; + KEY_ASSIGN(key); ), TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG + LOCAL_PR_FMT KEY_PR_FMT, + LOCAL_PR_ARG, KEY_PR_ARG ) ); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 667111ee6a20..8df134213adf 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -37,6 +37,16 @@ /* misc utils */ +static inline void ieee80211_tx_stats(struct net_device *dev, u32 len) +{ + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->tx_packets++; + tstats->tx_bytes += len; + u64_stats_update_end(&tstats->syncp); +} + static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, struct sk_buff *skb, int group_addr, int next_frag_len) @@ -987,7 +997,6 @@ ieee80211_tx_h_stats(struct ieee80211_tx_data *tx) skb_queue_walk(&tx->skbs, skb) { ac = skb_get_queue_mapping(skb); - tx->sta->tx_fragments++; tx->sta->tx_bytes[ac] += skb->len; } if (ac >= 0) @@ -1600,7 +1609,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, if (skb_cloned(skb) && (!(local->hw.flags & IEEE80211_HW_SUPPORTS_CLONED_SKBS) || !skb_clone_writable(skb, ETH_HLEN) || - sdata->crypto_tx_tailroom_needed_cnt)) + (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt))) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); @@ -2387,12 +2396,460 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, return ERR_PTR(ret); } +/* + * fast-xmit overview + * + * The core idea of this fast-xmit is to remove per-packet checks by checking + * them out of band. ieee80211_check_fast_xmit() implements the out-of-band + * checks that are needed to get the sta->fast_tx pointer assigned, after which + * much less work can be done per packet. For example, fragmentation must be + * disabled or the fast_tx pointer will not be set. All the conditions are seen + * in the code here. + * + * Once assigned, the fast_tx data structure also caches the per-packet 802.11 + * header and other data to aid packet processing in ieee80211_xmit_fast(). + * + * The most difficult part of this is that when any of these assumptions + * change, an external trigger (i.e. a call to ieee80211_clear_fast_xmit(), + * ieee80211_check_fast_xmit() or friends) is required to reset the data, + * since the per-packet code no longer checks the conditions. This is reflected + * by the calls to these functions throughout the rest of the code, and must be + * maintained if any of the TX path checks change. + */ + +void ieee80211_check_fast_xmit(struct sta_info *sta) +{ + struct ieee80211_fast_tx build = {}, *fast_tx = NULL, *old; + struct ieee80211_local *local = sta->local; + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_hdr *hdr = (void *)build.hdr; + struct ieee80211_chanctx_conf *chanctx_conf; + __le16 fc; + + if (!(local->hw.flags & IEEE80211_HW_SUPPORT_FAST_XMIT)) + return; + + /* Locking here protects both the pointer itself, and against concurrent + * invocations winning data access races to, e.g., the key pointer that + * is used. + * Without it, the invocation of this function right after the key + * pointer changes wouldn't be sufficient, as another CPU could access + * the pointer, then stall, and then do the cache update after the CPU + * that invalidated the key. + * With the locking, such scenarios cannot happen as the check for the + * key and the fast-tx assignment are done atomically, so the CPU that + * modifies the key will either wait or other one will see the key + * cleared/changed already. + */ + spin_lock_bh(&sta->lock); + if (local->hw.flags & IEEE80211_HW_SUPPORTS_PS && + !(local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS) && + sdata->vif.type == NL80211_IFTYPE_STATION) + goto out; + + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + goto out; + + if (test_sta_flag(sta, WLAN_STA_PS_STA) || + test_sta_flag(sta, WLAN_STA_PS_DRIVER) || + test_sta_flag(sta, WLAN_STA_PS_DELIVER)) + goto out; + + if (sdata->noack_map) + goto out; + + /* fast-xmit doesn't handle fragmentation at all */ + if (local->hw.wiphy->frag_threshold != (u32)-1 && + !local->ops->set_frag_threshold) + goto out; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) { + rcu_read_unlock(); + goto out; + } + build.band = chanctx_conf->def.chan->band; + rcu_read_unlock(); + + fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); + + switch (sdata->vif.type) { + case NL80211_IFTYPE_ADHOC: + /* DA SA BSSID */ + build.da_offs = offsetof(struct ieee80211_hdr, addr1); + build.sa_offs = offsetof(struct ieee80211_hdr, addr2); + memcpy(hdr->addr3, sdata->u.ibss.bssid, ETH_ALEN); + build.hdr_len = 24; + break; + case NL80211_IFTYPE_STATION: + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { + /* DA SA BSSID */ + build.da_offs = offsetof(struct ieee80211_hdr, addr1); + build.sa_offs = offsetof(struct ieee80211_hdr, addr2); + memcpy(hdr->addr3, sdata->u.mgd.bssid, ETH_ALEN); + build.hdr_len = 24; + break; + } + + if (sdata->u.mgd.use_4addr) { + /* non-regular ethertype cannot use the fastpath */ + fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | + IEEE80211_FCTL_TODS); + /* RA TA DA SA */ + memcpy(hdr->addr1, sdata->u.mgd.bssid, ETH_ALEN); + memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); + build.da_offs = offsetof(struct ieee80211_hdr, addr3); + build.sa_offs = offsetof(struct ieee80211_hdr, addr4); + build.hdr_len = 30; + break; + } + fc |= cpu_to_le16(IEEE80211_FCTL_TODS); + /* BSSID SA DA */ + memcpy(hdr->addr1, sdata->u.mgd.bssid, ETH_ALEN); + build.da_offs = offsetof(struct ieee80211_hdr, addr3); + build.sa_offs = offsetof(struct ieee80211_hdr, addr2); + build.hdr_len = 24; + break; + case NL80211_IFTYPE_AP_VLAN: + if (sdata->wdev.use_4addr) { + fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | + IEEE80211_FCTL_TODS); + /* RA TA DA SA */ + memcpy(hdr->addr1, sta->sta.addr, ETH_ALEN); + memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); + build.da_offs = offsetof(struct ieee80211_hdr, addr3); + build.sa_offs = offsetof(struct ieee80211_hdr, addr4); + build.hdr_len = 30; + break; + } + /* fall through */ + case NL80211_IFTYPE_AP: + fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); + /* DA BSSID SA */ + build.da_offs = offsetof(struct ieee80211_hdr, addr1); + memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); + build.sa_offs = offsetof(struct ieee80211_hdr, addr3); + build.hdr_len = 24; + break; + default: + /* not handled on fast-xmit */ + goto out; + } + + if (sta->sta.wme) { + build.hdr_len += 2; + fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA); + } + + /* We store the key here so there's no point in using rcu_dereference() + * but that's fine because the code that changes the pointers will call + * this function after doing so. For a single CPU that would be enough, + * for multiple see the comment above. + */ + build.key = rcu_access_pointer(sta->ptk[sta->ptk_idx]); + if (!build.key) + build.key = rcu_access_pointer(sdata->default_unicast_key); + if (build.key) { + bool gen_iv, iv_spc, mmic; + + gen_iv = build.key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV; + iv_spc = build.key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE; + mmic = build.key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC; + + /* don't handle software crypto */ + if (!(build.key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) + goto out; + + switch (build.key->conf.cipher) { + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: + /* add fixed key ID */ + if (gen_iv) { + (build.hdr + build.hdr_len)[3] = + 0x20 | (build.key->conf.keyidx << 6); + build.pn_offs = build.hdr_len; + } + if (gen_iv || iv_spc) + build.hdr_len += IEEE80211_CCMP_HDR_LEN; + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + /* add fixed key ID */ + if (gen_iv) { + (build.hdr + build.hdr_len)[3] = + 0x20 | (build.key->conf.keyidx << 6); + build.pn_offs = build.hdr_len; + } + if (gen_iv || iv_spc) + build.hdr_len += IEEE80211_GCMP_HDR_LEN; + break; + case WLAN_CIPHER_SUITE_TKIP: + /* cannot handle MMIC or IV generation in xmit-fast */ + if (mmic || gen_iv) + goto out; + if (iv_spc) + build.hdr_len += IEEE80211_TKIP_IV_LEN; + break; + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + /* cannot handle IV generation in fast-xmit */ + if (gen_iv) + goto out; + if (iv_spc) + build.hdr_len += IEEE80211_WEP_IV_LEN; + break; + case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + WARN(1, + "management cipher suite 0x%x enabled for data\n", + build.key->conf.cipher); + goto out; + default: + /* we don't know how to generate IVs for this at all */ + if (WARN_ON(gen_iv)) + goto out; + /* pure hardware keys are OK, of course */ + if (!(build.key->flags & KEY_FLAG_CIPHER_SCHEME)) + break; + /* cipher scheme might require space allocation */ + if (iv_spc && + build.key->conf.iv_len > IEEE80211_FAST_XMIT_MAX_IV) + goto out; + if (iv_spc) + build.hdr_len += build.key->conf.iv_len; + } + + fc |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); + } + + hdr->frame_control = fc; + + memcpy(build.hdr + build.hdr_len, + rfc1042_header, sizeof(rfc1042_header)); + build.hdr_len += sizeof(rfc1042_header); + + fast_tx = kmemdup(&build, sizeof(build), GFP_ATOMIC); + /* if the kmemdup fails, continue w/o fast_tx */ + if (!fast_tx) + goto out; + + out: + /* we might have raced against another call to this function */ + old = rcu_dereference_protected(sta->fast_tx, + lockdep_is_held(&sta->lock)); + rcu_assign_pointer(sta->fast_tx, fast_tx); + if (old) + kfree_rcu(old, rcu_head); + spin_unlock_bh(&sta->lock); +} + +void ieee80211_check_fast_xmit_all(struct ieee80211_local *local) +{ + struct sta_info *sta; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &local->sta_list, list) + ieee80211_check_fast_xmit(sta); + rcu_read_unlock(); +} + +void ieee80211_check_fast_xmit_iface(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + rcu_read_lock(); + + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata != sta->sdata && + (!sta->sdata->bss || sta->sdata->bss != sdata->bss)) + continue; + ieee80211_check_fast_xmit(sta); + } + + rcu_read_unlock(); +} + +void ieee80211_clear_fast_xmit(struct sta_info *sta) +{ + struct ieee80211_fast_tx *fast_tx; + + spin_lock_bh(&sta->lock); + fast_tx = rcu_dereference_protected(sta->fast_tx, + lockdep_is_held(&sta->lock)); + RCU_INIT_POINTER(sta->fast_tx, NULL); + spin_unlock_bh(&sta->lock); + + if (fast_tx) + kfree_rcu(fast_tx, rcu_head); +} + +static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, + struct net_device *dev, struct sta_info *sta, + struct ieee80211_fast_tx *fast_tx, + struct sk_buff *skb) +{ + struct ieee80211_local *local = sdata->local; + u16 ethertype = (skb->data[12] << 8) | skb->data[13]; + int extra_head = fast_tx->hdr_len - (ETH_HLEN - 2); + int hw_headroom = sdata->local->hw.extra_tx_headroom; + struct ethhdr eth; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (void *)fast_tx->hdr; + struct ieee80211_tx_data tx; + ieee80211_tx_result r; + struct tid_ampdu_tx *tid_tx = NULL; + u8 tid = IEEE80211_NUM_TIDS; + + /* control port protocol needs a lot of special handling */ + if (cpu_to_be16(ethertype) == sdata->control_port_protocol) + return false; + + /* only RFC 1042 SNAP */ + if (ethertype < ETH_P_802_3_MIN) + return false; + + /* don't handle TX status request here either */ + if (skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS) + return false; + + if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; + tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); + if (tid_tx && + !test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) + return false; + } + + /* after this point (skb is modified) we cannot return false */ + + if (skb_shared(skb)) { + struct sk_buff *tmp_skb = skb; + + skb = skb_clone(skb, GFP_ATOMIC); + kfree_skb(tmp_skb); + + if (!skb) + return true; + } + + ieee80211_tx_stats(dev, skb->len + extra_head); + + /* will not be crypto-handled beyond what we do here, so use false + * as the may-encrypt argument for the resize to not account for + * more room than we already have in 'extra_head' + */ + if (unlikely(ieee80211_skb_resize(sdata, skb, + max_t(int, extra_head + hw_headroom - + skb_headroom(skb), 0), + false))) { + kfree_skb(skb); + return true; + } + + memcpy(ð, skb->data, ETH_HLEN - 2); + hdr = (void *)skb_push(skb, extra_head); + memcpy(skb->data, fast_tx->hdr, fast_tx->hdr_len); + memcpy(skb->data + fast_tx->da_offs, eth.h_dest, ETH_ALEN); + memcpy(skb->data + fast_tx->sa_offs, eth.h_source, ETH_ALEN); + + memset(info, 0, sizeof(*info)); + info->band = fast_tx->band; + info->control.vif = &sdata->vif; + info->flags = IEEE80211_TX_CTL_FIRST_FRAGMENT | + IEEE80211_TX_CTL_DONTFRAG | + (tid_tx ? IEEE80211_TX_CTL_AMPDU : 0); + + if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { + *ieee80211_get_qos_ctl(hdr) = tid; + hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid); + } else { + info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; + hdr->seq_ctrl = cpu_to_le16(sdata->sequence_number); + sdata->sequence_number += 0x10; + } + + sta->tx_msdu[tid]++; + + info->hw_queue = sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; + + __skb_queue_head_init(&tx.skbs); + + tx.flags = IEEE80211_TX_UNICAST; + tx.local = local; + tx.sdata = sdata; + tx.sta = sta; + tx.key = fast_tx->key; + + if (fast_tx->key) + info->control.hw_key = &fast_tx->key->conf; + + if (!(local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL)) { + tx.skb = skb; + r = ieee80211_tx_h_rate_ctrl(&tx); + skb = tx.skb; + tx.skb = NULL; + + if (r != TX_CONTINUE) { + if (r != TX_QUEUED) + kfree_skb(skb); + return true; + } + } + + /* statistics normally done by ieee80211_tx_h_stats (but that + * has to consider fragmentation, so is more complex) + */ + sta->tx_bytes[skb_get_queue_mapping(skb)] += skb->len; + sta->tx_packets[skb_get_queue_mapping(skb)]++; + + if (fast_tx->pn_offs) { + u64 pn; + u8 *crypto_hdr = skb->data + fast_tx->pn_offs; + + switch (fast_tx->key->conf.cipher) { + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: + pn = atomic64_inc_return(&fast_tx->key->u.ccmp.tx_pn); + crypto_hdr[0] = pn; + crypto_hdr[1] = pn >> 8; + crypto_hdr[4] = pn >> 16; + crypto_hdr[5] = pn >> 24; + crypto_hdr[6] = pn >> 32; + crypto_hdr[7] = pn >> 40; + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + pn = atomic64_inc_return(&fast_tx->key->u.gcmp.tx_pn); + crypto_hdr[0] = pn; + crypto_hdr[1] = pn >> 8; + crypto_hdr[4] = pn >> 16; + crypto_hdr[5] = pn >> 24; + crypto_hdr[6] = pn >> 32; + crypto_hdr[7] = pn >> 40; + break; + } + } + + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + sdata = container_of(sdata->bss, + struct ieee80211_sub_if_data, u.ap); + + __skb_queue_tail(&tx.skbs, skb); + ieee80211_tx_frags(local, &sdata->vif, &sta->sta, &tx.skbs, false); + return true; +} + void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sta_info *sta; + struct sk_buff *next; if (unlikely(skb->len < ETH_HLEN)) { kfree_skb(skb); @@ -2401,20 +2858,67 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, rcu_read_lock(); - if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) { - kfree_skb(skb); - goto out; + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) + goto out_free; + + if (!IS_ERR_OR_NULL(sta)) { + struct ieee80211_fast_tx *fast_tx; + + fast_tx = rcu_dereference(sta->fast_tx); + + if (fast_tx && + ieee80211_xmit_fast(sdata, dev, sta, fast_tx, skb)) + goto out; } - skb = ieee80211_build_hdr(sdata, skb, info_flags, sta); - if (IS_ERR(skb)) - goto out; + if (skb_is_gso(skb)) { + struct sk_buff *segs; + + segs = skb_gso_segment(skb, 0); + if (IS_ERR(segs)) { + goto out_free; + } else if (segs) { + consume_skb(skb); + skb = segs; + } + } else { + /* we cannot process non-linear frames on this path */ + if (skb_linearize(skb)) { + kfree_skb(skb); + goto out; + } + + /* the frame could be fragmented, software-encrypted, and other + * things so we cannot really handle checksum offload with it - + * fix it up in software before we handle anything else. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); + if (skb_checksum_help(skb)) + goto out_free; + } + } + + next = skb; + while (next) { + skb = next; + next = skb->next; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - dev->trans_start = jiffies; + skb->prev = NULL; + skb->next = NULL; + + skb = ieee80211_build_hdr(sdata, skb, info_flags, sta); + if (IS_ERR(skb)) + goto out; - ieee80211_xmit(sdata, sta, skb); + ieee80211_tx_stats(dev, skb->len); + + ieee80211_xmit(sdata, sta, skb); + } + goto out; + out_free: + kfree_skb(skb); out: rcu_read_unlock(); } diff --git a/net/mac802154/Kconfig b/net/mac802154/Kconfig index aa462b480a39..fb45287ebac3 100644 --- a/net/mac802154/Kconfig +++ b/net/mac802154/Kconfig @@ -2,6 +2,7 @@ config MAC802154 tristate "Generic IEEE 802.15.4 Soft Networking Stack (mac802154)" depends on IEEE802154 select CRC_CCITT + select CRYPTO select CRYPTO_AUTHENC select CRYPTO_CCM select CRYPTO_CTR diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index 70be9c799f8a..317c4662e544 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -73,9 +73,9 @@ ieee802154_set_channel(struct wpan_phy *wpan_phy, u8 page, u8 channel) ASSERT_RTNL(); - /* check if phy support this setting */ - if (!(wpan_phy->channels_supported[page] & BIT(channel))) - return -EINVAL; + if (wpan_phy->current_page == page && + wpan_phy->current_channel == channel) + return 0; ret = drv_set_channel(local, page, channel); if (!ret) { @@ -95,9 +95,8 @@ ieee802154_set_cca_mode(struct wpan_phy *wpan_phy, ASSERT_RTNL(); - /* check if phy support this setting */ - if (!(local->hw.flags & IEEE802154_HW_CCA_MODE)) - return -EOPNOTSUPP; + if (wpan_phy_cca_cmp(&wpan_phy->cca, cca)) + return 0; ret = drv_set_cca_mode(local, cca); if (!ret) @@ -107,20 +106,49 @@ ieee802154_set_cca_mode(struct wpan_phy *wpan_phy, } static int +ieee802154_set_cca_ed_level(struct wpan_phy *wpan_phy, s32 ed_level) +{ + struct ieee802154_local *local = wpan_phy_priv(wpan_phy); + int ret; + + ASSERT_RTNL(); + + if (wpan_phy->cca_ed_level == ed_level) + return 0; + + ret = drv_set_cca_ed_level(local, ed_level); + if (!ret) + wpan_phy->cca_ed_level = ed_level; + + return ret; +} + +static int +ieee802154_set_tx_power(struct wpan_phy *wpan_phy, s32 power) +{ + struct ieee802154_local *local = wpan_phy_priv(wpan_phy); + int ret; + + ASSERT_RTNL(); + + if (wpan_phy->transmit_power == power) + return 0; + + ret = drv_set_tx_power(local, power); + if (!ret) + wpan_phy->transmit_power = power; + + return ret; +} + +static int ieee802154_set_pan_id(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 pan_id) { ASSERT_RTNL(); - /* TODO - * I am not sure about to check here on broadcast pan_id. - * Broadcast is a valid setting, comment from 802.15.4: - * If this value is 0xffff, the device is not associated. - * - * This could useful to simple deassociate an device. - */ - if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) - return -EINVAL; + if (wpan_dev->pan_id == pan_id) + return 0; wpan_dev->pan_id = pan_id; return 0; @@ -131,12 +159,11 @@ ieee802154_set_backoff_exponent(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, u8 min_be, u8 max_be) { - struct ieee802154_local *local = wpan_phy_priv(wpan_phy); - ASSERT_RTNL(); - if (!(local->hw.flags & IEEE802154_HW_CSMA_PARAMS)) - return -EOPNOTSUPP; + if (wpan_dev->min_be == min_be && + wpan_dev->max_be == max_be) + return 0; wpan_dev->min_be = min_be; wpan_dev->max_be = max_be; @@ -149,20 +176,8 @@ ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, { ASSERT_RTNL(); - /* TODO - * I am not sure about to check here on broadcast short_addr. - * Broadcast is a valid setting, comment from 802.15.4: - * A value of 0xfffe indicates that the device has - * associated but has not been allocated an address. A - * value of 0xffff indicates that the device does not - * have a short address. - * - * I think we should allow to set these settings but - * don't allow to allow socket communication with it. - */ - if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) || - short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST)) - return -EINVAL; + if (wpan_dev->short_addr == short_addr) + return 0; wpan_dev->short_addr = short_addr; return 0; @@ -173,12 +188,10 @@ ieee802154_set_max_csma_backoffs(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, u8 max_csma_backoffs) { - struct ieee802154_local *local = wpan_phy_priv(wpan_phy); - ASSERT_RTNL(); - if (!(local->hw.flags & IEEE802154_HW_CSMA_PARAMS)) - return -EOPNOTSUPP; + if (wpan_dev->csma_retries == max_csma_backoffs) + return 0; wpan_dev->csma_retries = max_csma_backoffs; return 0; @@ -189,12 +202,10 @@ ieee802154_set_max_frame_retries(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, s8 max_frame_retries) { - struct ieee802154_local *local = wpan_phy_priv(wpan_phy); - ASSERT_RTNL(); - if (!(local->hw.flags & IEEE802154_HW_FRAME_RETRIES)) - return -EOPNOTSUPP; + if (wpan_dev->frame_retries == max_frame_retries) + return 0; wpan_dev->frame_retries = max_frame_retries; return 0; @@ -204,12 +215,10 @@ static int ieee802154_set_lbt_mode(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, bool mode) { - struct ieee802154_local *local = wpan_phy_priv(wpan_phy); - ASSERT_RTNL(); - if (!(local->hw.flags & IEEE802154_HW_LBT)) - return -EOPNOTSUPP; + if (wpan_dev->lbt == mode) + return 0; wpan_dev->lbt = mode; return 0; @@ -222,6 +231,8 @@ const struct cfg802154_ops mac802154_config_ops = { .del_virtual_intf = ieee802154_del_iface, .set_channel = ieee802154_set_channel, .set_cca_mode = ieee802154_set_cca_mode, + .set_cca_ed_level = ieee802154_set_cca_ed_level, + .set_tx_power = ieee802154_set_tx_power, .set_pan_id = ieee802154_set_pan_id, .set_short_addr = ieee802154_set_short_addr, .set_backoff_exponent = ieee802154_set_backoff_exponent, diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h index a0533357b9ea..caecd5f43aa7 100644 --- a/net/mac802154/driver-ops.h +++ b/net/mac802154/driver-ops.h @@ -58,7 +58,7 @@ drv_set_channel(struct ieee802154_local *local, u8 page, u8 channel) return local->ops->set_channel(&local->hw, page, channel); } -static inline int drv_set_tx_power(struct ieee802154_local *local, s8 dbm) +static inline int drv_set_tx_power(struct ieee802154_local *local, s32 mbm) { might_sleep(); @@ -67,7 +67,7 @@ static inline int drv_set_tx_power(struct ieee802154_local *local, s8 dbm) return -EOPNOTSUPP; } - return local->ops->set_txpower(&local->hw, dbm); + return local->ops->set_txpower(&local->hw, mbm); } static inline int drv_set_cca_mode(struct ieee802154_local *local, @@ -96,7 +96,7 @@ static inline int drv_set_lbt_mode(struct ieee802154_local *local, bool mode) } static inline int -drv_set_cca_ed_level(struct ieee802154_local *local, s32 ed_level) +drv_set_cca_ed_level(struct ieee802154_local *local, s32 mbm) { might_sleep(); @@ -105,7 +105,7 @@ drv_set_cca_ed_level(struct ieee802154_local *local, s32 ed_level) return -EOPNOTSUPP; } - return local->ops->set_cca_ed_level(&local->hw, ed_level); + return local->ops->set_cca_ed_level(&local->hw, mbm); } static inline int drv_set_pan_id(struct ieee802154_local *local, __le16 pan_id) diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 127ba18386fc..eec668f3637f 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -86,8 +86,6 @@ struct ieee802154_sub_if_data { unsigned long state; char name[IFNAMSIZ]; - spinlock_t mib_lock; - /* protects sec from concurrent access by netlink. access by * encrypt/decrypt/header_create safe without additional protection. */ @@ -136,12 +134,7 @@ ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer); /* MIB callbacks */ -void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val); -__le16 mac802154_dev_get_short_addr(const struct net_device *dev); -__le16 mac802154_dev_get_pan_id(const struct net_device *dev); -void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val); void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan); -u8 mac802154_dev_get_dsn(const struct net_device *dev); int mac802154_get_params(struct net_device *dev, struct ieee802154_llsec_params *params); diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 91b75abbd1a1..b544b5dc4bfb 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -62,9 +62,10 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) (struct sockaddr_ieee802154 *)&ifr->ifr_addr; int err = -ENOIOCTLCMD; - ASSERT_RTNL(); + if (cmd != SIOCGIFADDR && cmd != SIOCSIFADDR) + return err; - spin_lock_bh(&sdata->mib_lock); + rtnl_lock(); switch (cmd) { case SIOCGIFADDR: @@ -89,7 +90,7 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } case SIOCSIFADDR: if (netif_running(dev)) { - spin_unlock_bh(&sdata->mib_lock); + rtnl_unlock(); return -EBUSY; } @@ -111,7 +112,7 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - spin_unlock_bh(&sdata->mib_lock); + rtnl_unlock(); return err; } @@ -241,7 +242,6 @@ static int mac802154_wpan_open(struct net_device *dev) struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; - struct wpan_phy *phy = sdata->local->phy; rc = ieee802154_check_concurrent_iface(sdata, sdata->vif.type); if (rc < 0) @@ -251,8 +251,6 @@ static int mac802154_wpan_open(struct net_device *dev) if (rc < 0) return rc; - mutex_lock(&phy->pib_lock); - if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { rc = drv_set_promiscuous_mode(local, wpan_dev->promiscuous_mode); @@ -294,11 +292,7 @@ static int mac802154_wpan_open(struct net_device *dev) goto out; } - mutex_unlock(&phy->pib_lock); - return 0; - out: - mutex_unlock(&phy->pib_lock); return rc; } @@ -374,14 +368,12 @@ static int mac802154_header_create(struct sk_buff *skb, hdr.fc.type = cb->type; hdr.fc.security_enabled = cb->secen; hdr.fc.ack_request = cb->ackreq; - hdr.seq = ieee802154_mlme_ops(dev)->get_dsn(dev); + hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; if (mac802154_set_header_security(sdata, &hdr, cb) < 0) return -EINVAL; if (!saddr) { - spin_lock_bh(&sdata->mib_lock); - if (wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) || wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || wpan_dev->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) { @@ -393,8 +385,6 @@ static int mac802154_header_create(struct sk_buff *skb, } hdr.source.pan_id = wpan_dev->pan_id; - - spin_unlock_bh(&sdata->mib_lock); } else { hdr.source = *(const struct ieee802154_addr *)saddr; } @@ -474,13 +464,16 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype type) { struct wpan_dev *wpan_dev = &sdata->wpan_dev; + u8 tmp; /* set some type-dependent values */ sdata->vif.type = type; sdata->wpan_dev.iftype = type; - get_random_bytes(&wpan_dev->bsn, 1); - get_random_bytes(&wpan_dev->dsn, 1); + get_random_bytes(&tmp, sizeof(tmp)); + atomic_set(&wpan_dev->bsn, tmp); + get_random_bytes(&tmp, sizeof(tmp)); + atomic_set(&wpan_dev->dsn, tmp); /* defaults per 802.15.4-2011 */ wpan_dev->min_be = 3; @@ -503,7 +496,6 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, sdata->dev->ml_priv = &mac802154_mlme_wpan; wpan_dev->promiscuous_mode = false; - spin_lock_init(&sdata->mib_lock); mutex_init(&sdata->sec_mtx); mac802154_llsec_init(&sdata->sec); diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c index bdccb4ecd30f..8606da459ff3 100644 --- a/net/mac802154/mac_cmd.c +++ b/net/mac802154/mac_cmd.c @@ -36,37 +36,30 @@ static int mac802154_mlme_start_req(struct net_device *dev, u8 pan_coord, u8 blx, u8 coord_realign) { - struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); - int rc = 0; + struct ieee802154_llsec_params params; + int changed = 0; ASSERT_RTNL(); BUG_ON(addr->mode != IEEE802154_ADDR_SHORT); - mac802154_dev_set_pan_id(dev, addr->pan_id); - mac802154_dev_set_short_addr(dev, addr->short_addr); + dev->ieee802154_ptr->pan_id = addr->pan_id; + dev->ieee802154_ptr->short_addr = addr->short_addr; mac802154_dev_set_page_channel(dev, page, channel); - if (ops->llsec) { - struct ieee802154_llsec_params params; - int changed = 0; + params.pan_id = addr->pan_id; + changed |= IEEE802154_LLSEC_PARAM_PAN_ID; - params.coord_shortaddr = addr->short_addr; - changed |= IEEE802154_LLSEC_PARAM_COORD_SHORTADDR; + params.hwaddr = ieee802154_devaddr_from_raw(dev->dev_addr); + changed |= IEEE802154_LLSEC_PARAM_HWADDR; - params.pan_id = addr->pan_id; - changed |= IEEE802154_LLSEC_PARAM_PAN_ID; + params.coord_hwaddr = params.hwaddr; + changed |= IEEE802154_LLSEC_PARAM_COORD_HWADDR; - params.hwaddr = ieee802154_devaddr_from_raw(dev->dev_addr); - changed |= IEEE802154_LLSEC_PARAM_HWADDR; + params.coord_shortaddr = addr->short_addr; + changed |= IEEE802154_LLSEC_PARAM_COORD_SHORTADDR; - params.coord_hwaddr = params.hwaddr; - changed |= IEEE802154_LLSEC_PARAM_COORD_HWADDR; - - rc = ops->llsec->set_params(dev, ¶ms, changed); - } - - return rc; + return mac802154_set_params(dev, ¶ms, changed); } static int mac802154_set_mac_params(struct net_device *dev, @@ -91,19 +84,19 @@ static int mac802154_set_mac_params(struct net_device *dev, wpan_dev->frame_retries = params->frame_retries; wpan_dev->lbt = params->lbt; - if (local->hw.flags & IEEE802154_HW_TXPOWER) { + if (local->hw.phy->flags & WPAN_PHY_FLAG_TXPOWER) { ret = drv_set_tx_power(local, params->transmit_power); if (ret < 0) return ret; } - if (local->hw.flags & IEEE802154_HW_CCA_MODE) { + if (local->hw.phy->flags & WPAN_PHY_FLAG_CCA_MODE) { ret = drv_set_cca_mode(local, ¶ms->cca); if (ret < 0) return ret; } - if (local->hw.flags & IEEE802154_HW_CCA_ED_LEVEL) { + if (local->hw.phy->flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { ret = drv_set_cca_ed_level(local, params->cca_ed_level); if (ret < 0) return ret; @@ -151,9 +144,6 @@ static struct ieee802154_llsec_ops mac802154_llsec_ops = { struct ieee802154_mlme_ops mac802154_mlme_wpan = { .start_req = mac802154_mlme_start_req, - .get_pan_id = mac802154_dev_get_pan_id, - .get_short_addr = mac802154_dev_get_short_addr, - .get_dsn = mac802154_dev_get_dsn, .llsec = &mac802154_llsec_ops, diff --git a/net/mac802154/main.c b/net/mac802154/main.c index 08cb32dc8fd3..356b346e1ee8 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -107,6 +107,18 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) skb_queue_head_init(&local->skb_queue); + /* init supported flags with 802.15.4 default ranges */ + phy->supported.max_minbe = 8; + phy->supported.min_maxbe = 3; + phy->supported.max_maxbe = 8; + phy->supported.min_frame_retries = -1; + phy->supported.max_frame_retries = 7; + phy->supported.max_csma_backoffs = 5; + phy->supported.lbt = NL802154_SUPPORTED_BOOL_FALSE; + + /* always supported */ + phy->supported.iftypes = BIT(NL802154_IFTYPE_NODE); + return &local->hw; } EXPORT_SYMBOL(ieee802154_alloc_hw); @@ -155,6 +167,26 @@ int ieee802154_register_hw(struct ieee802154_hw *hw) ieee802154_setup_wpan_phy_pib(local->phy); + if (!(hw->flags & IEEE802154_HW_CSMA_PARAMS)) { + local->phy->supported.min_csma_backoffs = 4; + local->phy->supported.max_csma_backoffs = 4; + local->phy->supported.min_maxbe = 5; + local->phy->supported.max_maxbe = 5; + local->phy->supported.min_minbe = 3; + local->phy->supported.max_minbe = 3; + } + + if (!(hw->flags & IEEE802154_HW_FRAME_RETRIES)) { + /* TODO should be 3, but our default value is -1 which means + * no ARET handling. + */ + local->phy->supported.min_frame_retries = -1; + local->phy->supported.max_frame_retries = -1; + } + + if (hw->flags & IEEE802154_HW_PROMISCUOUS) + local->phy->supported.iftypes |= BIT(NL802154_IFTYPE_MONITOR); + rc = wpan_phy_register(local->phy); if (rc < 0) goto out_wq; diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index 5cf019a57fd7..73f94fbf8785 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -26,81 +26,22 @@ #include "ieee802154_i.h" #include "driver-ops.h" -void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - spin_lock_bh(&sdata->mib_lock); - sdata->wpan_dev.short_addr = val; - spin_unlock_bh(&sdata->mib_lock); -} - -__le16 mac802154_dev_get_short_addr(const struct net_device *dev) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - __le16 ret; - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - spin_lock_bh(&sdata->mib_lock); - ret = sdata->wpan_dev.short_addr; - spin_unlock_bh(&sdata->mib_lock); - - return ret; -} - -__le16 mac802154_dev_get_pan_id(const struct net_device *dev) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - __le16 ret; - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - spin_lock_bh(&sdata->mib_lock); - ret = sdata->wpan_dev.pan_id; - spin_unlock_bh(&sdata->mib_lock); - - return ret; -} - -void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - spin_lock_bh(&sdata->mib_lock); - sdata->wpan_dev.pan_id = val; - spin_unlock_bh(&sdata->mib_lock); -} - -u8 mac802154_dev_get_dsn(const struct net_device *dev) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - return sdata->wpan_dev.dsn++; -} - void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; int res; + ASSERT_RTNL(); + BUG_ON(dev->type != ARPHRD_IEEE802154); res = drv_set_channel(local, page, chan); if (res) { pr_debug("set_channel failed\n"); } else { - mutex_lock(&local->phy->pib_lock); local->phy->current_channel = chan; local->phy->current_page = page; - mutex_unlock(&local->phy->pib_lock); } } diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index c0d67b2b4132..e0f10063cac3 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -47,8 +47,6 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, pr_debug("getting packet via slave interface %s\n", sdata->dev->name); - spin_lock_bh(&sdata->mib_lock); - span = wpan_dev->pan_id; sshort = wpan_dev->short_addr; @@ -83,13 +81,10 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, skb->pkt_type = PACKET_OTHERHOST; break; default: - spin_unlock_bh(&sdata->mib_lock); pr_debug("invalid dest mode\n"); goto fail; } - spin_unlock_bh(&sdata->mib_lock); - skb->dev = sdata->dev; rc = mac802154_llsec_decrypt(&sdata->sec, skb); diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 150bf807e572..583435f38930 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -85,11 +85,10 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, hrtimer_start(&local->ifs_timer, ktime_set(0, hw->phy->sifs_period * NSEC_PER_USEC), HRTIMER_MODE_REL); - - consume_skb(skb); } else { ieee802154_wake_queue(hw); - consume_skb(skb); } + + dev_consume_skb_any(skb); } EXPORT_SYMBOL(ieee802154_xmit_complete); diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 809df534a720..0183b32da942 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -62,6 +62,7 @@ out: static struct packet_offload mpls_mc_offload __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_MC), + .priority = 15, .callbacks = { .gso_segment = mpls_gso_segment, }, @@ -69,6 +70,7 @@ static struct packet_offload mpls_mc_offload __read_mostly = { static struct packet_offload mpls_uc_offload __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_UC), + .priority = 15, .callbacks = { .gso_segment = mpls_gso_segment, }, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index a0f3e6a3c7d1..fbc8d15c7fda 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1,6 +1,14 @@ menu "Core Netfilter Configuration" depends on NET && INET && NETFILTER +config NETFILTER_INGRESS + bool "Netfilter ingress support" + default y + select NET_INGRESS + help + This allows you to classify packets from ingress using the Netfilter + infrastructure. + config NETFILTER_NETLINK tristate @@ -448,6 +456,11 @@ config NF_TABLES_INET help This option enables support for a mixed IPv4/IPv6 "inet" table. +config NF_TABLES_NETDEV + tristate "Netfilter nf_tables netdev tables support" + help + This option enables support for the "netdev" table. + config NFT_EXTHDR tristate "Netfilter nf_tables IPv6 exthdr module" help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a87d8b8ec730..70d026d46fe7 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -75,6 +75,7 @@ nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o +obj-$(CONFIG_NF_TABLES_NETDEV) += nf_tables_netdev.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o obj-$(CONFIG_NFT_META) += nft_meta.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index e6163017c42d..653e32eac08c 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -64,10 +64,27 @@ static DEFINE_MUTEX(nf_hook_mutex); int nf_register_hook(struct nf_hook_ops *reg) { + struct list_head *nf_hook_list; struct nf_hook_ops *elem; mutex_lock(&nf_hook_mutex); - list_for_each_entry(elem, &nf_hooks[reg->pf][reg->hooknum], list) { + switch (reg->pf) { + case NFPROTO_NETDEV: +#ifdef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) { + BUG_ON(reg->dev == NULL); + nf_hook_list = ®->dev->nf_hooks_ingress; + net_inc_ingress_queue(); + break; + } +#endif + /* Fall through. */ + default: + nf_hook_list = &nf_hooks[reg->pf][reg->hooknum]; + break; + } + + list_for_each_entry(elem, nf_hook_list, list) { if (reg->priority < elem->priority) break; } @@ -85,6 +102,18 @@ void nf_unregister_hook(struct nf_hook_ops *reg) mutex_lock(&nf_hook_mutex); list_del_rcu(®->list); mutex_unlock(&nf_hook_mutex); + switch (reg->pf) { + case NFPROTO_NETDEV: +#ifdef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) { + net_dec_ingress_queue(); + break; + } + break; +#endif + default: + break; + } #ifdef HAVE_JUMP_LABEL static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif @@ -166,11 +195,9 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state) /* We may already have this, but read-locks nest anyway */ rcu_read_lock(); - elem = list_entry_rcu(&nf_hooks[state->pf][state->hook], - struct nf_hook_ops, list); + elem = list_entry_rcu(state->hook_list, struct nf_hook_ops, list); next_hook: - verdict = nf_iterate(&nf_hooks[state->pf][state->hook], skb, state, - &elem); + verdict = nf_iterate(state->hook_list, skb, state, &elem); if (verdict == NF_ACCEPT || verdict == NF_STOP) { ret = 1; } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 55b083ec587a..2fe6de46f6d0 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -36,6 +36,7 @@ IP_SET_MODULE_DESC("bitmap:ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_bitmap:ip"); #define MTYPE bitmap_ip +#define HOST_MASK 32 /* Type structure */ struct bitmap_ip { @@ -149,8 +150,11 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -174,7 +178,7 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } else @@ -277,7 +281,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr >= 32) + if (cidr >= HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(first_ip, last_ip, cidr); } else @@ -286,7 +290,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_NETMASK]) { netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]); - if (netmask > 32) + if (netmask > HOST_MASK) return -IPSET_ERR_INVALID_NETMASK; first_ip &= ip_set_hostmask(netmask); @@ -360,7 +364,8 @@ static struct ip_set_type bitmap_ip_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 86104744b00f..eb188561d65f 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -36,6 +36,7 @@ IP_SET_MODULE_DESC("bitmap:ip,mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_bitmap:ip,mac"); #define MTYPE bitmap_ipmac +#define HOST_MASK 32 #define IP_SET_BITMAP_STORED_TIMEOUT enum { @@ -250,8 +251,11 @@ bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -343,7 +347,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr >= 32) + if (cidr >= HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(first_ip, last_ip, cidr); } else @@ -397,7 +401,8 @@ static struct ip_set_type bitmap_ipmac_type = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 005dd36444c3..898edb693b3f 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -294,7 +294,8 @@ static struct ip_set_type bitmap_port_type = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index d259da3ce67a..475e4960a164 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -42,7 +42,7 @@ static inline struct ip_set_net *ip_set_pernet(struct net *net) } #define IP_SET_INC 64 -#define STREQ(a, b) (strncmp(a, b, IPSET_MAXNAMELEN) == 0) +#define STRNCMP(a, b) (strncmp(a, b, IPSET_MAXNAMELEN) == 0) static unsigned int max_sets; @@ -85,7 +85,7 @@ find_set_type(const char *name, u8 family, u8 revision) struct ip_set_type *type; list_for_each_entry_rcu(type, &ip_set_type_list, list) - if (STREQ(type->name, name) && + if (STRNCMP(type->name, name) && (type->family == family || type->family == NFPROTO_UNSPEC) && revision >= type->revision_min && @@ -132,7 +132,7 @@ __find_set_type_get(const char *name, u8 family, u8 revision, /* Make sure the type is already loaded * but we don't support the revision */ list_for_each_entry_rcu(type, &ip_set_type_list, list) - if (STREQ(type->name, name)) { + if (STRNCMP(type->name, name)) { err = -IPSET_ERR_FIND_TYPE; goto unlock; } @@ -166,7 +166,7 @@ __find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max, *min = 255; *max = 0; rcu_read_lock(); list_for_each_entry_rcu(type, &ip_set_type_list, list) - if (STREQ(type->name, name) && + if (STRNCMP(type->name, name) && (type->family == family || type->family == NFPROTO_UNSPEC)) { found = true; @@ -365,7 +365,7 @@ size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len) { enum ip_set_ext_id id; - size_t offset = 0; + size_t offset = len; u32 cadt_flags = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) @@ -375,12 +375,12 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len) for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; - offset += ALIGN(len + offset, ip_set_extensions[id].align); + offset = ALIGN(offset, ip_set_extensions[id].align); set->offset[id] = offset; set->extensions |= ip_set_extensions[id].type; offset += ip_set_extensions[id].len; } - return len + offset; + return offset; } EXPORT_SYMBOL_GPL(ip_set_elem_len); @@ -432,6 +432,31 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], } EXPORT_SYMBOL_GPL(ip_set_get_extensions); +int +ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, + const void *e, bool active) +{ + if (SET_WITH_TIMEOUT(set)) { + unsigned long *timeout = ext_timeout(e, set); + + if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(active ? ip_set_timeout_get(timeout) + : *timeout))) + return -EMSGSIZE; + } + if (SET_WITH_COUNTER(set) && + ip_set_put_counter(skb, ext_counter(e, set))) + return -EMSGSIZE; + if (SET_WITH_COMMENT(set) && + ip_set_put_comment(skb, ext_comment(e, set))) + return -EMSGSIZE; + if (SET_WITH_SKBINFO(set) && + ip_set_put_skbinfo(skb, ext_skbinfo(e, set))) + return -EMSGSIZE; + return 0; +} +EXPORT_SYMBOL_GPL(ip_set_put_extensions); + /* * Creating/destroying/renaming/swapping affect the existence and * the properties of a set. All of these can be executed from userspace @@ -581,7 +606,7 @@ ip_set_get_byname(struct net *net, const char *name, struct ip_set **set) rcu_read_lock(); for (i = 0; i < inst->ip_set_max; i++) { s = rcu_dereference(inst->ip_set_list)[i]; - if (s != NULL && STREQ(s->name, name)) { + if (s != NULL && STRNCMP(s->name, name)) { __ip_set_get(s); index = i; *set = s; @@ -758,7 +783,7 @@ find_set_and_id(struct ip_set_net *inst, const char *name, ip_set_id_t *id) *id = IPSET_INVALID_ID; for (i = 0; i < inst->ip_set_max; i++) { set = ip_set(inst, i); - if (set != NULL && STREQ(set->name, name)) { + if (set != NULL && STRNCMP(set->name, name)) { *id = i; break; } @@ -787,7 +812,7 @@ find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index, if (s == NULL) { if (*index == IPSET_INVALID_ID) *index = i; - } else if (STREQ(name, s->name)) { + } else if (STRNCMP(name, s->name)) { /* Name clash */ *set = s; return -EEXIST; @@ -887,7 +912,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, if (ret == -EEXIST) { /* If this is the same set and requested, ignore error */ if ((flags & IPSET_FLAG_EXIST) && - STREQ(set->type->name, clash->type->name) && + STRNCMP(set->type->name, clash->type->name) && set->type->family == clash->type->family && set->type->revision_min == clash->type->revision_min && set->type->revision_max == clash->type->revision_max && @@ -1098,7 +1123,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); - if (s != NULL && STREQ(s->name, name2)) { + if (s != NULL && STRNCMP(s->name, name2)) { ret = -IPSET_ERR_EXIST_SETNAME2; goto out; } diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 29fb01ddff93..1981f021cc60 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -98,7 +98,7 @@ ip_set_get_ip4_port(const struct sk_buff *skb, bool src, __be16 *port, u8 *proto) { const struct iphdr *iph = ip_hdr(skb); - unsigned int protooff = ip_hdrlen(skb); + unsigned int protooff = skb_network_offset(skb) + ip_hdrlen(skb); int protocol = iph->protocol; /* See comments at tcp_match in ip_tables.c */ @@ -135,7 +135,9 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src, __be16 frag_off = 0; nexthdr = ipv6_hdr(skb)->nexthdr; - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + protoff = ipv6_skip_exthdr(skb, + skb_network_offset(skb) + + sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (protoff < 0 || (frag_off & htons(~0x7)) != 0) return false; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 974ff386db0f..7952869c8023 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -180,6 +180,7 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #undef mtype_data_equal #undef mtype_do_data_match #undef mtype_data_set_flags +#undef mtype_data_reset_elem #undef mtype_data_reset_flags #undef mtype_data_netmask #undef mtype_data_list @@ -193,7 +194,6 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #undef mtype_ahash_memsize #undef mtype_flush #undef mtype_destroy -#undef mtype_gc_init #undef mtype_same_set #undef mtype_kadt #undef mtype_uadt @@ -227,6 +227,7 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #define mtype_data_list IPSET_TOKEN(MTYPE, _data_list) #define mtype_data_next IPSET_TOKEN(MTYPE, _data_next) #define mtype_elem IPSET_TOKEN(MTYPE, _elem) + #define mtype_ahash_destroy IPSET_TOKEN(MTYPE, _ahash_destroy) #define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup) #define mtype_add_cidr IPSET_TOKEN(MTYPE, _add_cidr) @@ -234,7 +235,6 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #define mtype_ahash_memsize IPSET_TOKEN(MTYPE, _ahash_memsize) #define mtype_flush IPSET_TOKEN(MTYPE, _flush) #define mtype_destroy IPSET_TOKEN(MTYPE, _destroy) -#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_same_set IPSET_TOKEN(MTYPE, _same_set) #define mtype_kadt IPSET_TOKEN(MTYPE, _kadt) #define mtype_uadt IPSET_TOKEN(MTYPE, _uadt) @@ -249,9 +249,18 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) +#ifndef MTYPE +#error "MTYPE is not defined!" +#endif + +#ifndef HOST_MASK +#error "HOST_MASK is not defined!" +#endif + #ifndef HKEY_DATALEN #define HKEY_DATALEN sizeof(struct mtype_elem) #endif @@ -261,6 +270,9 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) & jhash_mask(htable_bits)) #ifndef htype +#ifndef HTYPE +#error "HTYPE is not defined!" +#endif /* HTYPE */ #define htype HTYPE /* The generic hash structure */ @@ -287,7 +299,7 @@ struct htype { struct net_prefixes nets[0]; /* book-keeping of prefixes */ #endif }; -#endif +#endif /* htype */ #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different @@ -1045,7 +1057,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, u8 netmask; #endif size_t hsize; - struct HTYPE *h; + struct htype *h; struct htable *t; #ifndef IP_SET_PROTO_UNDEF @@ -1165,3 +1177,5 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, return 0; } #endif /* IP_SET_EMIT_CREATE */ + +#undef HKEY_DATALEN diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 76959d79e9d1..54df48b5c455 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -56,15 +56,15 @@ hash_ip4_data_equal(const struct hash_ip4_elem *e1, return e1->ip == e2->ip; } -static inline bool +static bool hash_ip4_data_list(struct sk_buff *skb, const struct hash_ip4_elem *e) { if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, e->ip)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -74,7 +74,6 @@ hash_ip4_data_next(struct hash_ip4_elem *next, const struct hash_ip4_elem *e) } #define MTYPE hash_ip4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -121,8 +120,11 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -145,7 +147,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -196,10 +198,10 @@ hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *e) { if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -208,12 +210,9 @@ hash_ip6_data_next(struct hash_ip4_elem *next, const struct hash_ip6_elem *e) } #undef MTYPE -#undef PF #undef HOST_MASK -#undef HKEY_DATALEN #define MTYPE hash_ip6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE @@ -261,8 +260,11 @@ hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -301,7 +303,8 @@ static struct ip_set_type hash_ip_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 7abf9788cfa8..d231248eb3e2 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -63,10 +63,10 @@ hash_ipmark4_data_list(struct sk_buff *skb, if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -76,10 +76,8 @@ hash_ipmark4_data_next(struct hash_ipmark4_elem *next, next->ip = d->ip; } -#define MTYPE hash_ipmark4 -#define PF 4 -#define HOST_MASK 32 -#define HKEY_DATALEN sizeof(struct hash_ipmark4_elem) +#define MTYPE hash_ipmark4 +#define HOST_MASK 32 #include "ip_set_hash_gen.h" static int @@ -123,12 +121,15 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; - e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK])); + ret = ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; if (adt == IPSET_TEST || @@ -147,7 +148,7 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -191,10 +192,10 @@ hash_ipmark6_data_list(struct sk_buff *skb, if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -204,15 +205,11 @@ hash_ipmark6_data_next(struct hash_ipmark4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK -#undef HKEY_DATALEN #define MTYPE hash_ipmark6 -#define PF 6 #define HOST_MASK 128 -#define HKEY_DATALEN sizeof(struct hash_ipmark6_elem) -#define IP_SET_EMIT_CREATE +#define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -258,12 +255,15 @@ hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; - e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK])); + e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; if (adt == IPSET_TEST) { @@ -307,7 +307,8 @@ static struct ip_set_type hash_ipmark_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index dcbcceb9a52f..a47c29f12090 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -69,10 +69,10 @@ hash_ipport4_data_list(struct sk_buff *skb, nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -83,10 +83,8 @@ hash_ipport4_data_next(struct hash_ipport4_elem *next, next->port = d->port; } -#define MTYPE hash_ipport4 -#define PF 4 -#define HOST_MASK 32 -#define HKEY_DATALEN sizeof(struct hash_ipport4_elem) +#define MTYPE hash_ipport4 +#define HOST_MASK 32 #include "ip_set_hash_gen.h" static int @@ -132,15 +130,15 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + ret = ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -171,7 +169,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -231,10 +229,10 @@ hash_ipport6_data_list(struct sk_buff *skb, nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -245,15 +243,11 @@ hash_ipport6_data_next(struct hash_ipport4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK -#undef HKEY_DATALEN #define MTYPE hash_ipport6 -#define PF 6 #define HOST_MASK 128 -#define HKEY_DATALEN sizeof(struct hash_ipport6_elem) -#define IP_SET_EMIT_CREATE +#define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int @@ -301,15 +295,15 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + ret = ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -376,7 +370,8 @@ static struct ip_set_type hash_ipport_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 7ef93fc887a1..89615f134845 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -70,10 +70,10 @@ hash_ipportip4_data_list(struct sk_buff *skb, nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -86,7 +86,6 @@ hash_ipportip4_data_next(struct hash_ipportip4_elem *next, /* Common functions */ #define MTYPE hash_ipportip4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -134,8 +133,11 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -143,10 +145,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -177,7 +176,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -240,10 +239,10 @@ hash_ipportip6_data_list(struct sk_buff *skb, nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -254,11 +253,9 @@ hash_ipportip6_data_next(struct hash_ipportip4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_ipportip6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -309,8 +306,11 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -318,10 +318,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -388,7 +385,8 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index b6012ad92781..6ba7a7e083f9 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -114,10 +114,10 @@ hash_ipportnet4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -130,7 +130,6 @@ hash_ipportnet4_data_next(struct hash_ipportnet4_elem *next, } #define MTYPE hash_ipportnet4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -189,8 +188,11 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -205,10 +207,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.cidr = cidr - 1; } - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -249,7 +248,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -367,10 +366,10 @@ hash_ipportnet6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -381,11 +380,9 @@ hash_ipportnet6_data_next(struct hash_ipportnet4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_ipportnet6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -448,8 +445,11 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -466,10 +466,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], ip6_netmask(&e.ip2, e.cidr + 1); - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -547,7 +544,8 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c index 65690b52a4d5..1f8668d7a538 100644 --- a/net/netfilter/ipset/ip_set_hash_mac.c +++ b/net/netfilter/ipset/ip_set_hash_mac.c @@ -52,7 +52,12 @@ hash_mac4_data_equal(const struct hash_mac4_elem *e1, static inline bool hash_mac4_data_list(struct sk_buff *skb, const struct hash_mac4_elem *e) { - return nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether); + if (nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether)) + goto nla_put_failure; + return false; + +nla_put_failure: + return true; } static inline void @@ -62,7 +67,6 @@ hash_mac4_data_next(struct hash_mac4_elem *next, } #define MTYPE hash_mac4 -#define PF 4 #define HOST_MASK 32 #define IP_SET_EMIT_CREATE #define IP_SET_PROTO_UNDEF @@ -149,7 +153,8 @@ static struct ip_set_type hash_mac_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 6b3ac10ac2f1..2e63dad8644d 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -95,10 +95,10 @@ hash_net4_data_list(struct sk_buff *skb, const struct hash_net4_elem *data) (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -109,7 +109,6 @@ hash_net4_data_next(struct hash_net4_elem *next, } #define MTYPE hash_net4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -160,8 +159,11 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -264,10 +266,10 @@ hash_net6_data_list(struct sk_buff *skb, const struct hash_net6_elem *data) (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -277,11 +279,9 @@ hash_net6_data_next(struct hash_net4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_net6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -333,8 +333,11 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -383,7 +386,8 @@ static struct ip_set_type hash_net_type __read_mostly = { [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 380ef5148ea1..fe481f677f56 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -193,10 +193,10 @@ hash_netiface4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -207,7 +207,6 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next, } #define MTYPE hash_netiface4 -#define PF 4 #define HOST_MASK 32 #define HKEY_DATALEN sizeof(struct hash_netiface4_elem_hashed) #include "ip_set_hash_gen.h" @@ -308,8 +307,11 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -444,10 +446,10 @@ hash_netiface6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -457,12 +459,9 @@ hash_netiface6_data_next(struct hash_netiface4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK -#undef HKEY_DATALEN #define MTYPE hash_netiface6 -#define PF 6 #define HOST_MASK 128 #define HKEY_DATALEN sizeof(struct hash_netiface6_elem_hashed) #define IP_SET_EMIT_CREATE @@ -546,8 +545,11 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -613,7 +615,8 @@ static struct ip_set_type hash_netiface_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index ea8772afb6e7..847047483560 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -128,7 +128,6 @@ hash_netnet4_data_next(struct hash_netnet4_elem *next, } #define MTYPE hash_netnet4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -182,9 +181,15 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -354,11 +359,9 @@ hash_netnet6_data_next(struct hash_netnet4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_netnet6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -411,9 +414,15 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]) || - ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]); + if (ret) + return ret; + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -470,7 +479,8 @@ static struct ip_set_type hash_netnet_type __read_mostly = { [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index c0ddb58d19dc..8273819c1a2f 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -110,10 +110,10 @@ hash_netport4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -125,7 +125,6 @@ hash_netport4_data_next(struct hash_netport4_elem *next, } #define MTYPE hash_netport4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -182,8 +181,11 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -194,10 +196,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], e.cidr = cidr - 1; } - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -326,10 +325,10 @@ hash_netport6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -340,11 +339,9 @@ hash_netport6_data_next(struct hash_netport4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_netport6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -404,8 +401,11 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -417,10 +417,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], } ip6_netmask(&e.ip, e.cidr + 1); - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -495,7 +492,8 @@ static struct ip_set_type hash_netport_type __read_mostly = { [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index bfaa94c7baa7..1451a8ac938f 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -54,7 +54,7 @@ struct hash_netportnet4_elem { u16 ccmp; }; u16 padding; - u8 nomatch:1; + u8 nomatch; u8 proto; }; @@ -124,10 +124,10 @@ hash_netportnet4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -139,7 +139,6 @@ hash_netportnet4_data_next(struct hash_netportnet4_elem *next, } #define MTYPE hash_netportnet4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -200,9 +199,15 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -220,10 +225,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.cidr[1] = cidr; } - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -326,7 +328,7 @@ struct hash_netportnet6_elem { u16 ccmp; }; u16 padding; - u8 nomatch:1; + u8 nomatch; u8 proto; }; @@ -397,10 +399,10 @@ hash_netportnet6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -411,11 +413,9 @@ hash_netportnet6_data_next(struct hash_netportnet4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_netportnet6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -477,9 +477,15 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]) || - ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]); + if (ret) + return ret; + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -496,10 +502,7 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -577,7 +580,8 @@ static struct ip_set_type hash_netportnet_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index f8f682806e36..5bd3b1eae3fa 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -678,7 +678,8 @@ static struct ip_set_type list_set_type __read_mostly = { [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 19b9cce6c210..b08ba9538d12 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1457,18 +1457,12 @@ static struct socket *make_send_sock(struct net *net, int id) struct socket *sock; int result; - /* First create a socket move it to right name space later */ - result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + /* First create a socket */ + result = sock_create_kern(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - /* - * Kernel sockets that are a part of a namespace, should not - * hold a reference to a namespace in order to allow to stop it. - * After sk_change_net should be released using sk_release_kernel. - */ - sk_change_net(sock->sk, net); result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); @@ -1497,7 +1491,7 @@ static struct socket *make_send_sock(struct net *net, int id) return sock; error: - sk_release_kernel(sock->sk); + sock_release(sock); return ERR_PTR(result); } @@ -1518,17 +1512,11 @@ static struct socket *make_receive_sock(struct net *net, int id) int result; /* First create a socket */ - result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + result = sock_create_kern(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - /* - * Kernel sockets that are a part of a namespace, should not - * hold a reference to a namespace in order to allow to stop it. - * After sk_change_net should be released using sk_release_kernel. - */ - sk_change_net(sock->sk, net); /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = SK_CAN_REUSE; result = sysctl_sync_sock_size(ipvs); @@ -1554,7 +1542,7 @@ static struct socket *make_receive_sock(struct net *net, int id) return sock; error: - sk_release_kernel(sock->sk); + sock_release(sock); return ERR_PTR(result); } @@ -1692,7 +1680,7 @@ done: ip_vs_sync_buff_release(sb); /* release the sending multicast socket */ - sk_release_kernel(tinfo->sock->sk); + sock_release(tinfo->sock); kfree(tinfo); return 0; @@ -1729,7 +1717,7 @@ static int sync_thread_backup(void *data) } /* release the sending multicast socket */ - sk_release_kernel(tinfo->sock->sk); + sock_release(tinfo->sock); kfree(tinfo->buf); kfree(tinfo); @@ -1854,11 +1842,11 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) return 0; outsocket: - sk_release_kernel(sock->sk); + sock_release(sock); outtinfo: if (tinfo) { - sk_release_kernel(tinfo->sock->sk); + sock_release(tinfo->sock); kfree(tinfo->buf); kfree(tinfo); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 19986ec5f21a..bf66a8657a5f 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -364,13 +364,16 @@ err_unreach: #ifdef CONFIG_IP_VS_IPV6 static struct dst_entry * __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr, - struct in6_addr *ret_saddr, int do_xfrm) + struct in6_addr *ret_saddr, int do_xfrm, int rt_mode) { struct dst_entry *dst; struct flowi6 fl6 = { .daddr = *daddr, }; + if (rt_mode & IP_VS_RT_MODE_KNOWN_NH) + fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; + dst = ip6_route_output(net, NULL, &fl6); if (dst->error) goto out_err; @@ -427,7 +430,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, } dst = __ip_vs_route_output_v6(net, &dest->addr.in6, &dest_dst->dst_saddr.in6, - do_xfrm); + do_xfrm, rt_mode); if (!dst) { __ip_vs_dst_set(dest, NULL, NULL, 0); spin_unlock_bh(&dest->dst_lock); @@ -435,7 +438,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, goto err_unreach; } rt = (struct rt6_info *) dst; - cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + cookie = rt6_get_cookie(rt); __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", @@ -446,7 +449,8 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, *ret_saddr = dest_dst->dst_saddr.in6; } else { noref = 0; - dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); + dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm, + rt_mode); if (!dst) goto err_unreach; rt = (struct rt6_info *) dst; @@ -781,7 +785,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && - ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { + ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) { IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): " "stopping DNAT to loopback address"); @@ -1164,7 +1168,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6, NULL, ipvsh, 0, IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL); + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_KNOWN_NH); if (local < 0) goto tx_error; if (local) { @@ -1346,7 +1351,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && - ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { + ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI6\n", __func__, &cp->daddr.in6); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 1d69f5b9748f..9511af04dc81 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -779,8 +779,8 @@ static int callforward_do_filter(struct net *net, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2), false)) { - if (ipv6_addr_equal(rt6_nexthop(rt1), - rt6_nexthop(rt2)) && + if (ipv6_addr_equal(rt6_nexthop(rt1, &fl1.daddr), + rt6_nexthop(rt2, &fl2.daddr)) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 34ded09317e7..4528f122bcd2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -399,6 +399,8 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { [NFTA_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_TABLE_FLAGS] = { .type = NLA_U32 }, + [NFTA_TABLE_DEV] = { .type = NLA_STRING, + .len = IFNAMSIZ - 1 }, }; static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, @@ -423,6 +425,10 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use))) goto nla_put_failure; + if (table->dev && + nla_put_string(skb, NFTA_TABLE_DEV, table->dev->name)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -608,6 +614,11 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags == ctx->table->flags) return 0; + if ((ctx->afi->flags & NFT_AF_NEEDS_DEV) && + ctx->nla[NFTA_TABLE_DEV] && + nla_strcmp(ctx->nla[NFTA_TABLE_DEV], ctx->table->dev->name)) + return -EOPNOTSUPP; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) @@ -645,6 +656,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, struct nft_table *table; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct net_device *dev = NULL; u32 flags = 0; struct nft_ctx ctx; int err; @@ -679,30 +691,50 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, return -EINVAL; } + if (afi->flags & NFT_AF_NEEDS_DEV) { + char ifname[IFNAMSIZ]; + + if (!nla[NFTA_TABLE_DEV]) + return -EOPNOTSUPP; + + nla_strlcpy(ifname, nla[NFTA_TABLE_DEV], IFNAMSIZ); + dev = dev_get_by_name(net, ifname); + if (!dev) + return -ENOENT; + } else if (nla[NFTA_TABLE_DEV]) { + return -EOPNOTSUPP; + } + + err = -EAFNOSUPPORT; if (!try_module_get(afi->owner)) - return -EAFNOSUPPORT; + goto err1; err = -ENOMEM; table = kzalloc(sizeof(*table), GFP_KERNEL); if (table == NULL) - goto err1; + goto err2; nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN); INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); table->flags = flags; + table->dev = dev; nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) - goto err2; + goto err3; list_add_tail_rcu(&table->list, &afi->tables); return 0; -err2: +err3: kfree(table); -err1: +err2: module_put(afi->owner); +err1: + if (dev != NULL) + dev_put(dev); + return err; } @@ -806,6 +838,9 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) { BUG_ON(ctx->table->use > 0); + if (ctx->table->dev) + dev_put(ctx->table->dev); + kfree(ctx->table); module_put(ctx->afi->owner); } @@ -1361,6 +1396,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, ops->priority = priority; ops->priv = chain; ops->hook = afi->hooks[ops->hooknum]; + ops->dev = table->dev; if (hookfn) ops->hook = hookfn; if (afi->hook_ops_init) diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c new file mode 100644 index 000000000000..04cb17057f46 --- /dev/null +++ b/net/netfilter/nf_tables_netdev.c @@ -0,0 +1,183 @@ +/* + * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <net/netfilter/nf_tables.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <net/netfilter/nf_tables_ipv4.h> +#include <net/netfilter/nf_tables_ipv6.h> + +static inline void +nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct iphdr *iph, _iph; + u32 len, thoff; + + nft_set_pktinfo(pkt, ops, skb, state); + + iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), + &_iph); + if (!iph) + return; + + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + return; + + len = ntohs(iph->tot_len); + thoff = iph->ihl * 4; + if (skb->len < len) + return; + else if (len < thoff) + return; + + pkt->tprot = iph->protocol; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; +} + +static inline void +__nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6hdr *ip6h, _ip6h; + unsigned int thoff = 0; + unsigned short frag_off; + int protohdr; + u32 pkt_len; + + ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), + &_ip6h); + if (!ip6h) + return; + + if (ip6h->version != 6) + return; + + pkt_len = ntohs(ip6h->payload_len); + if (pkt_len + sizeof(*ip6h) > skb->len) + return; + + protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); + if (protohdr < 0) + return; + + pkt->tprot = protohdr; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = frag_off; +#endif +} + +static inline void nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + nft_set_pktinfo(pkt, ops, skb, state); + __nft_netdev_set_pktinfo_ipv6(pkt, ops, skb, state); +} + +static unsigned int +nft_do_chain_netdev(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nft_pktinfo pkt; + + switch (eth_hdr(skb)->h_proto) { + case htons(ETH_P_IP): + nft_netdev_set_pktinfo_ipv4(&pkt, ops, skb, state); + break; + case htons(ETH_P_IPV6): + nft_netdev_set_pktinfo_ipv6(&pkt, ops, skb, state); + break; + default: + nft_set_pktinfo(&pkt, ops, skb, state); + break; + } + + return nft_do_chain(&pkt, ops); +} + +static struct nft_af_info nft_af_netdev __read_mostly = { + .family = NFPROTO_NETDEV, + .nhooks = NF_NETDEV_NUMHOOKS, + .owner = THIS_MODULE, + .flags = NFT_AF_NEEDS_DEV, + .nops = 1, + .hooks = { + [NF_NETDEV_INGRESS] = nft_do_chain_netdev, + }, +}; + +static int nf_tables_netdev_init_net(struct net *net) +{ + net->nft.netdev = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL); + if (net->nft.netdev == NULL) + return -ENOMEM; + + memcpy(net->nft.netdev, &nft_af_netdev, sizeof(nft_af_netdev)); + + if (nft_register_afinfo(net, net->nft.netdev) < 0) + goto err; + + return 0; +err: + kfree(net->nft.netdev); + return -ENOMEM; +} + +static void nf_tables_netdev_exit_net(struct net *net) +{ + nft_unregister_afinfo(net->nft.netdev); + kfree(net->nft.netdev); +} + +static struct pernet_operations nf_tables_netdev_net_ops = { + .init = nf_tables_netdev_init_net, + .exit = nf_tables_netdev_exit_net, +}; + +static const struct nf_chain_type nft_filter_chain_netdev = { + .name = "filter", + .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_NETDEV, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_NETDEV_INGRESS), +}; + +static int __init nf_tables_netdev_init(void) +{ + int ret; + + nft_register_chain_type(&nft_filter_chain_netdev); + ret = register_pernet_subsys(&nf_tables_netdev_net_ops); + if (ret < 0) + nft_unregister_chain_type(&nft_filter_chain_netdev); + + return ret; +} + +static void __exit nf_tables_netdev_exit(void) +{ + unregister_pernet_subsys(&nf_tables_netdev_net_ops); + nft_unregister_chain_type(&nft_filter_chain_netdev); +} + +module_init(nf_tables_netdev_init); +module_exit(nf_tables_netdev_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_FAMILY(5); /* NFPROTO_NETDEV */ diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 11c7682fa0ea..22a5ac76683e 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -1257,7 +1257,7 @@ static int seq_show(struct seq_file *s, void *v) inst->copy_mode, inst->copy_range, inst->queue_dropped, inst->queue_user_dropped, inst->id_sequence, 1); - return seq_has_overflowed(s); + return 0; } static const struct seq_operations nfqnl_seq_ops = { diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 7f29cfc76349..66def315eb56 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -161,6 +161,7 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, par->hook_mask = 0; } par->family = ctx->afi->family; + par->nft_compat = true; } static void target_compat_from_user(struct xt_target *t, void *in, void *out) @@ -377,6 +378,7 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, par->hook_mask = 0; } par->family = ctx->afi->family; + par->nft_compat = true; } static void match_compat_from_user(struct xt_match *m, void *in, void *out) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 51a459c3c649..83032464a4bd 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -947,11 +947,9 @@ static int xt_table_seq_show(struct seq_file *seq, void *v) { struct xt_table *table = list_entry(v, struct xt_table, list); - if (strlen(table->name)) { + if (*table->name) seq_printf(seq, "%s\n", table->name); - return seq_has_overflowed(seq); - } else - return 0; + return 0; } static const struct seq_operations xt_table_seq_ops = { @@ -1087,10 +1085,8 @@ static int xt_match_seq_show(struct seq_file *seq, void *v) if (trav->curr == trav->head) return 0; match = list_entry(trav->curr, struct xt_match, list); - if (*match->name == '\0') - return 0; - seq_printf(seq, "%s\n", match->name); - return seq_has_overflowed(seq); + if (*match->name) + seq_printf(seq, "%s\n", match->name); } return 0; } @@ -1142,10 +1138,8 @@ static int xt_target_seq_show(struct seq_file *seq, void *v) if (trav->curr == trav->head) return 0; target = list_entry(trav->curr, struct xt_target, list); - if (*target->name == '\0') - return 0; - seq_printf(seq, "%s\n", target->name); - return seq_has_overflowed(seq); + if (*target->name) + seq_printf(seq, "%s\n", target->name); } return 0; } diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index e762de5ee89b..8c3190e2fc6a 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -277,6 +277,9 @@ static int tcpmss_tg4_check(const struct xt_tgchk_param *par) "FORWARD, OUTPUT and POSTROUTING hooks\n"); return -EINVAL; } + if (par->nft_compat) + return 0; + xt_ematch_foreach(ematch, e) if (find_syn_match(ematch)) return 0; @@ -299,6 +302,9 @@ static int tcpmss_tg6_check(const struct xt_tgchk_param *par) "FORWARD, OUTPUT and POSTROUTING hooks\n"); return -EINVAL; } + if (par->nft_compat) + return 0; + xt_ematch_foreach(ematch, e) if (find_syn_match(ematch)) return 0; diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 292934d23482..a747eb475b68 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -152,6 +152,7 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl6.daddr = info->gw.in6; fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) | (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]; + fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index fab6eea1bf38..5b4743cc0436 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -73,7 +73,7 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, if (dev == NULL && rt->rt6i_flags & RTF_LOCAL) ret |= XT_ADDRTYPE_LOCAL; - if (rt->rt6i_flags & RTF_ANYCAST) + if (ipv6_anycast_destination((struct dst_entry *)rt, addr)) ret |= XT_ADDRTYPE_ANYCAST; dst_release(&rt->dst); diff --git a/net/netfilter/xt_mark.c b/net/netfilter/xt_mark.c index 23345238711b..ebd41dc501e5 100644 --- a/net/netfilter/xt_mark.c +++ b/net/netfilter/xt_mark.c @@ -23,6 +23,7 @@ MODULE_ALIAS("ipt_mark"); MODULE_ALIAS("ip6t_mark"); MODULE_ALIAS("ipt_MARK"); MODULE_ALIAS("ip6t_MARK"); +MODULE_ALIAS("arpt_MARK"); static unsigned int mark_tg(struct sk_buff *skb, const struct xt_action_param *par) diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 89045982ec94..b103e9627716 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -15,8 +15,9 @@ #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> -#include <linux/netfilter/xt_set.h> +#include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_timeout.h> +#include <uapi/linux/netfilter/xt_set.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index bf6e76643f78..69d67c300b80 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -76,17 +76,18 @@ struct listeners { }; /* state bits */ -#define NETLINK_CONGESTED 0x0 +#define NETLINK_S_CONGESTED 0x0 /* flags */ -#define NETLINK_KERNEL_SOCKET 0x1 -#define NETLINK_RECV_PKTINFO 0x2 -#define NETLINK_BROADCAST_SEND_ERROR 0x4 -#define NETLINK_RECV_NO_ENOBUFS 0x8 +#define NETLINK_F_KERNEL_SOCKET 0x1 +#define NETLINK_F_RECV_PKTINFO 0x2 +#define NETLINK_F_BROADCAST_SEND_ERROR 0x4 +#define NETLINK_F_RECV_NO_ENOBUFS 0x8 +#define NETLINK_F_LISTEN_ALL_NSID 0x10 static inline int netlink_is_kernel(struct sock *sk) { - return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET; + return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET; } struct netlink_table *nl_table __read_mostly; @@ -256,8 +257,9 @@ static void netlink_overrun(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); - if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) { - if (!test_and_set_bit(NETLINK_CONGESTED, &nlk_sk(sk)->state)) { + if (!(nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)) { + if (!test_and_set_bit(NETLINK_S_CONGESTED, + &nlk_sk(sk)->state)) { sk->sk_err = ENOBUFS; sk->sk_error_report(sk); } @@ -270,8 +272,8 @@ static void netlink_rcv_wake(struct sock *sk) struct netlink_sock *nlk = nlk_sk(sk); if (skb_queue_empty(&sk->sk_receive_queue)) - clear_bit(NETLINK_CONGESTED, &nlk->state); - if (!test_bit(NETLINK_CONGESTED, &nlk->state)) + clear_bit(NETLINK_S_CONGESTED, &nlk->state); + if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); } @@ -1118,14 +1120,15 @@ static struct proto netlink_proto = { }; static int __netlink_create(struct net *net, struct socket *sock, - struct mutex *cb_mutex, int protocol) + struct mutex *cb_mutex, int protocol, + int kern) { struct sock *sk; struct netlink_sock *nlk; sock->ops = &netlink_ops; - sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto); + sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern); if (!sk) return -ENOMEM; @@ -1187,7 +1190,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, if (err < 0) goto out; - err = __netlink_create(net, sock, cb_mutex, protocol); + err = __netlink_create(net, sock, cb_mutex, protocol, kern); if (err < 0) goto out_module; @@ -1297,20 +1300,24 @@ static int netlink_autobind(struct socket *sock) struct netlink_table *table = &nl_table[sk->sk_protocol]; s32 portid = task_tgid_vnr(current); int err; - static s32 rover = -4097; + s32 rover = -4096; + bool ok; retry: cond_resched(); rcu_read_lock(); - if (__netlink_lookup(table, portid, net)) { + ok = !__netlink_lookup(table, portid, net); + rcu_read_unlock(); + if (!ok) { /* Bind collision, search negative portid values. */ - portid = rover--; - if (rover > -4097) + if (rover == -4096) + /* rover will be in range [S32_MIN, -4097] */ + rover = S32_MIN + prandom_u32_max(-4096 - S32_MIN); + else if (rover >= -4096) rover = -4097; - rcu_read_unlock(); + portid = rover--; goto retry; } - rcu_read_unlock(); err = netlink_insert(sk, portid); if (err == -EADDRINUSE) @@ -1657,7 +1664,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, nlk = nlk_sk(sk); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_CONGESTED, &nlk->state)) && + test_bit(NETLINK_S_CONGESTED, &nlk->state)) && !netlink_skb_is_mmaped(skb)) { DECLARE_WAITQUEUE(wait, current); if (!*timeo) { @@ -1672,7 +1679,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, add_wait_queue(&nlk->wait, &wait); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_CONGESTED, &nlk->state)) && + test_bit(NETLINK_S_CONGESTED, &nlk->state)) && !sock_flag(sk, SOCK_DEAD)) *timeo = schedule_timeout(*timeo); @@ -1896,7 +1903,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) struct netlink_sock *nlk = nlk_sk(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && - !test_bit(NETLINK_CONGESTED, &nlk->state)) { + !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); @@ -1932,8 +1939,17 @@ static void do_one_broadcast(struct sock *sk, !test_bit(p->group - 1, nlk->groups)) return; - if (!net_eq(sock_net(sk), p->net)) - return; + if (!net_eq(sock_net(sk), p->net)) { + if (!(nlk->flags & NETLINK_F_LISTEN_ALL_NSID)) + return; + + if (!peernet_has_id(sock_net(sk), p->net)) + return; + + if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns, + CAP_NET_BROADCAST)) + return; + } if (p->failure) { netlink_overrun(sk); @@ -1957,23 +1973,33 @@ static void do_one_broadcast(struct sock *sk, netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; - if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR) + if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) p->delivery_failure = 1; - } else if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { + goto out; + } + if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { kfree_skb(p->skb2); p->skb2 = NULL; - } else if (sk_filter(sk, p->skb2)) { + goto out; + } + if (sk_filter(sk, p->skb2)) { kfree_skb(p->skb2); p->skb2 = NULL; - } else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) { + goto out; + } + NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net); + NETLINK_CB(p->skb2).nsid_is_set = true; + val = netlink_broadcast_deliver(sk, p->skb2); + if (val < 0) { netlink_overrun(sk); - if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR) + if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) p->delivery_failure = 1; } else { p->congested |= val; p->delivered = 1; p->skb2 = NULL; } +out: sock_put(sk); } @@ -2058,7 +2084,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) !test_bit(p->group - 1, nlk->groups)) goto out; - if (p->code == ENOBUFS && nlk->flags & NETLINK_RECV_NO_ENOBUFS) { + if (p->code == ENOBUFS && nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) { ret = 1; goto out; } @@ -2077,7 +2103,7 @@ out: * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the - * NETLINK_RECV_NO_ENOBUFS socket option. + * NETLINK_NO_ENOBUFS socket option. */ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { @@ -2137,9 +2163,9 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case NETLINK_PKTINFO: if (val) - nlk->flags |= NETLINK_RECV_PKTINFO; + nlk->flags |= NETLINK_F_RECV_PKTINFO; else - nlk->flags &= ~NETLINK_RECV_PKTINFO; + nlk->flags &= ~NETLINK_F_RECV_PKTINFO; err = 0; break; case NETLINK_ADD_MEMBERSHIP: @@ -2168,18 +2194,18 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, } case NETLINK_BROADCAST_ERROR: if (val) - nlk->flags |= NETLINK_BROADCAST_SEND_ERROR; + nlk->flags |= NETLINK_F_BROADCAST_SEND_ERROR; else - nlk->flags &= ~NETLINK_BROADCAST_SEND_ERROR; + nlk->flags &= ~NETLINK_F_BROADCAST_SEND_ERROR; err = 0; break; case NETLINK_NO_ENOBUFS: if (val) { - nlk->flags |= NETLINK_RECV_NO_ENOBUFS; - clear_bit(NETLINK_CONGESTED, &nlk->state); + nlk->flags |= NETLINK_F_RECV_NO_ENOBUFS; + clear_bit(NETLINK_S_CONGESTED, &nlk->state); wake_up_interruptible(&nlk->wait); } else { - nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS; + nlk->flags &= ~NETLINK_F_RECV_NO_ENOBUFS; } err = 0; break; @@ -2202,6 +2228,16 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, break; } #endif /* CONFIG_NETLINK_MMAP */ + case NETLINK_LISTEN_ALL_NSID: + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) + return -EPERM; + + if (val) + nlk->flags |= NETLINK_F_LISTEN_ALL_NSID; + else + nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -2228,7 +2264,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, if (len < sizeof(int)) return -EINVAL; len = sizeof(int); - val = nlk->flags & NETLINK_RECV_PKTINFO ? 1 : 0; + val = nlk->flags & NETLINK_F_RECV_PKTINFO ? 1 : 0; if (put_user(len, optlen) || put_user(val, optval)) return -EFAULT; @@ -2238,7 +2274,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, if (len < sizeof(int)) return -EINVAL; len = sizeof(int); - val = nlk->flags & NETLINK_BROADCAST_SEND_ERROR ? 1 : 0; + val = nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR ? 1 : 0; if (put_user(len, optlen) || put_user(val, optval)) return -EFAULT; @@ -2248,7 +2284,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, if (len < sizeof(int)) return -EINVAL; len = sizeof(int); - val = nlk->flags & NETLINK_RECV_NO_ENOBUFS ? 1 : 0; + val = nlk->flags & NETLINK_F_RECV_NO_ENOBUFS ? 1 : 0; if (put_user(len, optlen) || put_user(val, optval)) return -EFAULT; @@ -2268,6 +2304,16 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); } +static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + if (!NETLINK_CB(skb).nsid_is_set) + return; + + put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int), + &NETLINK_CB(skb).nsid); +} + static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; @@ -2419,8 +2465,10 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, msg->msg_namelen = sizeof(*addr); } - if (nlk->flags & NETLINK_RECV_PKTINFO) + if (nlk->flags & NETLINK_F_RECV_PKTINFO) netlink_cmsg_recv_pktinfo(msg, skb); + if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID) + netlink_cmsg_listen_all_nsid(sk, msg, skb); memset(&scm, 0, sizeof(scm)); scm.creds = *NETLINK_CREDS(skb); @@ -2474,17 +2522,10 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) return NULL; - /* - * We have to just have a reference on the net from sk, but don't - * get_net it. Besides, we cannot get and then put the net here. - * So we create one inside init_net and the move it to net. - */ - - if (__netlink_create(&init_net, sock, cb_mutex, unit) < 0) + if (__netlink_create(net, sock, cb_mutex, unit, 1) < 0) goto out_sock_release_nosk; sk = sock->sk; - sk_change_net(sk, net); if (!cfg || cfg->groups < 32) groups = 32; @@ -2503,7 +2544,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, goto out_sock_release; nlk = nlk_sk(sk); - nlk->flags |= NETLINK_KERNEL_SOCKET; + nlk->flags |= NETLINK_F_KERNEL_SOCKET; netlink_table_grab(); if (!nl_table[unit].registered) { @@ -2540,7 +2581,10 @@ EXPORT_SYMBOL(__netlink_kernel_create); void netlink_kernel_release(struct sock *sk) { - sk_release_kernel(sk); + if (sk == NULL || sk->sk_socket == NULL) + return; + + sock_release(sk->sk_socket); } EXPORT_SYMBOL(netlink_kernel_release); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index b987fd56c3c5..ed212ffc1d9d 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -433,7 +433,7 @@ static int nr_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_SEQPACKET || protocol != 0) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, PF_NETROM, GFP_ATOMIC, &nr_proto); + sk = sk_alloc(net, PF_NETROM, GFP_ATOMIC, &nr_proto, kern); if (sk == NULL) return -ENOMEM; @@ -476,7 +476,7 @@ static struct sock *nr_make_new(struct sock *osk) if (osk->sk_type != SOCK_SEQPACKET) return NULL; - sk = sk_alloc(sock_net(osk), PF_NETROM, GFP_ATOMIC, osk->sk_prot); + sk = sk_alloc(sock_net(osk), PF_NETROM, GFP_ATOMIC, osk->sk_prot, 0); if (sk == NULL) return NULL; diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c index 2277276f52bc..54e40fa47822 100644 --- a/net/nfc/af_nfc.c +++ b/net/nfc/af_nfc.c @@ -40,7 +40,7 @@ static int nfc_sock_create(struct net *net, struct socket *sock, int proto, read_lock(&proto_tab_lock); if (proto_tab[proto] && try_module_get(proto_tab[proto]->owner)) { - rc = proto_tab[proto]->create(net, sock, proto_tab[proto]); + rc = proto_tab[proto]->create(net, sock, proto_tab[proto], kern); module_put(proto_tab[proto]->owner); } read_unlock(&proto_tab_lock); diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index de1789e3cc82..1f68724d44d3 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -225,7 +225,7 @@ void nfc_llcp_send_to_raw_sock(struct nfc_llcp_local *local, struct sk_buff *skb, u8 direction); /* Sock API */ -struct sock *nfc_llcp_sock_alloc(struct socket *sock, int type, gfp_t gfp); +struct sock *nfc_llcp_sock_alloc(struct socket *sock, int type, gfp_t gfp, int kern); void nfc_llcp_sock_free(struct nfc_llcp_sock *sock); void nfc_llcp_accept_unlink(struct sock *sk); void nfc_llcp_accept_enqueue(struct sock *parent, struct sock *sk); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index b18f07ccb504..98876274a1ee 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -934,7 +934,7 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, sock->ssap = ssap; } - new_sk = nfc_llcp_sock_alloc(NULL, parent->sk_type, GFP_ATOMIC); + new_sk = nfc_llcp_sock_alloc(NULL, parent->sk_type, GFP_ATOMIC, 0); if (new_sk == NULL) { reason = LLCP_DM_REJ; release_sock(&sock->sk); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 9578bd6a4f3e..b7de0da46acd 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -942,12 +942,12 @@ static void llcp_sock_destruct(struct sock *sk) } } -struct sock *nfc_llcp_sock_alloc(struct socket *sock, int type, gfp_t gfp) +struct sock *nfc_llcp_sock_alloc(struct socket *sock, int type, gfp_t gfp, int kern) { struct sock *sk; struct nfc_llcp_sock *llcp_sock; - sk = sk_alloc(&init_net, PF_NFC, gfp, &llcp_sock_proto); + sk = sk_alloc(&init_net, PF_NFC, gfp, &llcp_sock_proto, kern); if (!sk) return NULL; @@ -993,7 +993,7 @@ void nfc_llcp_sock_free(struct nfc_llcp_sock *sock) } static int llcp_sock_create(struct net *net, struct socket *sock, - const struct nfc_protocol *nfc_proto) + const struct nfc_protocol *nfc_proto, int kern) { struct sock *sk; @@ -1009,7 +1009,7 @@ static int llcp_sock_create(struct net *net, struct socket *sock, else sock->ops = &llcp_sock_ops; - sk = nfc_llcp_sock_alloc(sock, sock->type, GFP_ATOMIC); + sk = nfc_llcp_sock_alloc(sock, sock->type, GFP_ATOMIC, kern); if (sk == NULL) return -ENOMEM; diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index a8ce80b47720..5c93e8412a26 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -30,7 +30,7 @@ struct nfc_protocol { struct proto *proto; struct module *owner; int (*create)(struct net *net, struct socket *sock, - const struct nfc_protocol *nfc_proto); + const struct nfc_protocol *nfc_proto, int kern); }; struct nfc_rawsock { diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 82b4e8024778..e9a91488fe3d 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -334,7 +334,7 @@ static void rawsock_destruct(struct sock *sk) } static int rawsock_create(struct net *net, struct socket *sock, - const struct nfc_protocol *nfc_proto) + const struct nfc_protocol *nfc_proto, int kern) { struct sock *sk; @@ -348,7 +348,7 @@ static int rawsock_create(struct net *net, struct socket *sock, else sock->ops = &rawsock_ops; - sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto); + sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern); if (!sk) return -ENOMEM; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index ed6b0f8dd1bb..15840401a2ce 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -59,7 +59,7 @@ config OPENVSWITCH_VXLAN config OPENVSWITCH_GENEVE tristate "Open vSwitch Geneve tunneling support" depends on OPENVSWITCH - depends on GENEVE + depends on GENEVE_CORE default OPENVSWITCH ---help--- If you say Y here, then the Open vSwitch will be able create geneve vport. diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b491c1c296fe..8a8c0b8b4f63 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -608,17 +608,16 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port) } static int output_userspace(struct datapath *dp, struct sk_buff *skb, - struct sw_flow_key *key, const struct nlattr *attr) + struct sw_flow_key *key, const struct nlattr *attr, + const struct nlattr *actions, int actions_len) { struct ovs_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; + memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_ACTION; - upcall.userdata = NULL; - upcall.portid = 0; - upcall.egress_tun_info = NULL; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { @@ -647,6 +646,13 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, break; } + case OVS_USERSPACE_ATTR_ACTIONS: { + /* Include actions. */ + upcall.actions = actions; + upcall.actions_len = actions_len; + break; + } + } /* End of switch. */ } @@ -654,7 +660,8 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, } static int sample(struct datapath *dp, struct sk_buff *skb, - struct sw_flow_key *key, const struct nlattr *attr) + struct sw_flow_key *key, const struct nlattr *attr, + const struct nlattr *actions, int actions_len) { const struct nlattr *acts_list = NULL; const struct nlattr *a; @@ -688,7 +695,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, */ if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE && nla_is_last(a, rem))) - return output_userspace(dp, skb, key, a); + return output_userspace(dp, skb, key, a, actions, actions_len); skb = skb_clone(skb, GFP_ATOMIC); if (!skb) @@ -872,7 +879,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_USERSPACE: - output_userspace(dp, skb, key, a); + output_userspace(dp, skb, key, a, attr, len); break; case OVS_ACTION_ATTR_HASH: @@ -916,7 +923,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_SAMPLE: - err = sample(dp, skb, key, a); + err = sample(dp, skb, key, a, attr, len); break; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 096c6276e6b9..ff8c4a4c1609 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -272,10 +272,9 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) struct dp_upcall_info upcall; int error; + memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; - upcall.userdata = NULL; upcall.portid = ovs_vport_find_upcall_portid(p, skb); - upcall.egress_tun_info = NULL; error = ovs_dp_upcall(dp, skb, key, &upcall); if (unlikely(error)) kfree_skb(skb); @@ -397,6 +396,10 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info, if (upcall_info->egress_tun_info) size += nla_total_size(ovs_tun_key_attr_size()); + /* OVS_PACKET_ATTR_ACTIONS */ + if (upcall_info->actions_len) + size += nla_total_size(upcall_info->actions_len); + return size; } @@ -478,6 +481,17 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, nla_nest_end(user_skb, nla); } + if (upcall_info->actions_len) { + nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_ACTIONS); + err = ovs_nla_put_actions(upcall_info->actions, + upcall_info->actions_len, + user_skb); + if (!err) + nla_nest_end(user_skb, nla); + else + nla_nest_cancel(user_skb, nla); + } + /* Only reserve room for attribute header, packet data is added * in skb_zerocopy() */ if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) { @@ -545,7 +559,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) /* Normally, setting the skb 'protocol' field would be handled by a * call to eth_type_trans(), but it assumes there's a sending * device, which we may not have. */ - if (ntohs(eth->h_proto) >= ETH_P_802_3_MIN) + if (eth_proto_is_802_3(eth->h_proto)) packet->protocol = eth->h_proto; else packet->protocol = htons(ETH_P_802_2); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 4ec4a480b147..cd691e935e08 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -116,6 +116,8 @@ struct ovs_skb_cb { struct dp_upcall_info { const struct ovs_tunnel_info *egress_tun_info; const struct nlattr *userdata; + const struct nlattr *actions; + int actions_len; u32 portid; u8 cmd; }; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 2dacc7b5af23..bc7b0aba994a 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -332,7 +332,7 @@ static __be16 parse_ethertype(struct sk_buff *skb) proto = *(__be16 *) skb->data; __skb_pull(skb, sizeof(__be16)); - if (ntohs(proto) >= ETH_P_802_3_MIN) + if (eth_proto_is_802_3(proto)) return proto; if (skb->len < sizeof(struct llc_snap_hdr)) @@ -349,7 +349,7 @@ static __be16 parse_ethertype(struct sk_buff *skb) __skb_pull(skb, sizeof(struct llc_snap_hdr)); - if (ntohs(llc->ethertype) >= ETH_P_802_3_MIN) + if (eth_proto_is_802_3(llc->ethertype)) return llc->ethertype; return htons(ETH_P_802_2); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c691b1a1eee0..624e41c4267f 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -816,7 +816,7 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, if (is_mask) { /* Always exact match EtherType. */ eth_type = htons(0xffff); - } else if (ntohs(eth_type) < ETH_P_802_3_MIN) { + } else if (!eth_proto_is_802_3(eth_type)) { OVS_NLERR(log, "EtherType %x is less than min %x", ntohs(eth_type), ETH_P_802_3_MIN); return -EINVAL; diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index bf02fd5808c9..208c576bd1b6 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -46,11 +46,6 @@ static inline struct geneve_port *geneve_vport(const struct vport *vport) return vport_priv(vport); } -static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) -{ - return (struct genevehdr *)(udp_hdr(skb) + 1); -} - /* Convert 64 bit tunnel ID to 24 bit VNI. */ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b5989c6ee551..fd5164139bf0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1234,27 +1234,81 @@ static void packet_free_pending(struct packet_sock *po) free_percpu(po->tx_ring.pending_refcnt); } -static bool packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) +#define ROOM_POW_OFF 2 +#define ROOM_NONE 0x0 +#define ROOM_LOW 0x1 +#define ROOM_NORMAL 0x2 + +static bool __tpacket_has_room(struct packet_sock *po, int pow_off) +{ + int idx, len; + + len = po->rx_ring.frame_max + 1; + idx = po->rx_ring.head; + if (pow_off) + idx += len >> pow_off; + if (idx >= len) + idx -= len; + return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); +} + +static bool __tpacket_v3_has_room(struct packet_sock *po, int pow_off) +{ + int idx, len; + + len = po->rx_ring.prb_bdqc.knum_blocks; + idx = po->rx_ring.prb_bdqc.kactive_blk_num; + if (pow_off) + idx += len >> pow_off; + if (idx >= len) + idx -= len; + return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); +} + +static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { struct sock *sk = &po->sk; - bool has_room; + int ret = ROOM_NONE; + + if (po->prot_hook.func != tpacket_rcv) { + int avail = sk->sk_rcvbuf - atomic_read(&sk->sk_rmem_alloc) + - (skb ? skb->truesize : 0); + if (avail > (sk->sk_rcvbuf >> ROOM_POW_OFF)) + return ROOM_NORMAL; + else if (avail > 0) + return ROOM_LOW; + else + return ROOM_NONE; + } + + if (po->tp_version == TPACKET_V3) { + if (__tpacket_v3_has_room(po, ROOM_POW_OFF)) + ret = ROOM_NORMAL; + else if (__tpacket_v3_has_room(po, 0)) + ret = ROOM_LOW; + } else { + if (__tpacket_has_room(po, ROOM_POW_OFF)) + ret = ROOM_NORMAL; + else if (__tpacket_has_room(po, 0)) + ret = ROOM_LOW; + } - if (po->prot_hook.func != tpacket_rcv) - return (atomic_read(&sk->sk_rmem_alloc) + skb->truesize) - <= sk->sk_rcvbuf; + return ret; +} - spin_lock(&sk->sk_receive_queue.lock); - if (po->tp_version == TPACKET_V3) - has_room = prb_lookup_block(po, &po->rx_ring, - po->rx_ring.prb_bdqc.kactive_blk_num, - TP_STATUS_KERNEL); - else - has_room = packet_lookup_frame(po, &po->rx_ring, - po->rx_ring.head, - TP_STATUS_KERNEL); - spin_unlock(&sk->sk_receive_queue.lock); +static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) +{ + int ret; + bool has_room; + + spin_lock_bh(&po->sk.sk_receive_queue.lock); + ret = __packet_rcv_has_room(po, skb); + has_room = ret == ROOM_NORMAL; + if (po->pressure == has_room) + po->pressure = !has_room; + spin_unlock_bh(&po->sk.sk_receive_queue.lock); - return has_room; + return ret; } static void packet_sock_destruct(struct sock *sk) @@ -1282,6 +1336,20 @@ static int fanout_rr_next(struct packet_fanout *f, unsigned int num) return x; } +static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) +{ + u32 rxhash; + int i, count = 0; + + rxhash = skb_get_hash(skb); + for (i = 0; i < ROLLOVER_HLEN; i++) + if (po->rollover->history[i] == rxhash) + count++; + + po->rollover->history[prandom_u32() % ROLLOVER_HLEN] = rxhash; + return count > (ROLLOVER_HLEN >> 1); +} + static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) @@ -1318,22 +1386,40 @@ static unsigned int fanout_demux_rnd(struct packet_fanout *f, static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct sk_buff *skb, - unsigned int idx, unsigned int skip, + unsigned int idx, bool try_self, unsigned int num) { - unsigned int i, j; + struct packet_sock *po, *po_next, *po_skip = NULL; + unsigned int i, j, room = ROOM_NONE; - i = j = min_t(int, f->next[idx], num - 1); + po = pkt_sk(f->arr[idx]); + + if (try_self) { + room = packet_rcv_has_room(po, skb); + if (room == ROOM_NORMAL || + (room == ROOM_LOW && !fanout_flow_is_huge(po, skb))) + return idx; + po_skip = po; + } + + i = j = min_t(int, po->rollover->sock, num - 1); do { - if (i != skip && packet_rcv_has_room(pkt_sk(f->arr[i]), skb)) { + po_next = pkt_sk(f->arr[i]); + if (po_next != po_skip && !po_next->pressure && + packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) - f->next[idx] = i; + po->rollover->sock = i; + atomic_long_inc(&po->rollover->num); + if (room == ROOM_LOW) + atomic_long_inc(&po->rollover->num_huge); return i; } + if (++i == num) i = 0; } while (i != j); + atomic_long_inc(&po->rollover->num_failed); return idx; } @@ -1386,17 +1472,14 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, idx = fanout_demux_qm(f, skb, num); break; case PACKET_FANOUT_ROLLOVER: - idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num); + idx = fanout_demux_rollover(f, skb, 0, false, num); break; } - po = pkt_sk(f->arr[idx]); - if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER) && - unlikely(!packet_rcv_has_room(po, skb))) { - idx = fanout_demux_rollover(f, skb, idx, idx, num); - po = pkt_sk(f->arr[idx]); - } + if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) + idx = fanout_demux_rollover(f, skb, idx, true, num); + po = pkt_sk(f->arr[idx]); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } @@ -1467,6 +1550,16 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) if (po->fanout) return -EALREADY; + if (type == PACKET_FANOUT_ROLLOVER || + (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { + po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL); + if (!po->rollover) + return -ENOMEM; + atomic_long_set(&po->rollover->num, 0); + atomic_long_set(&po->rollover->num_huge, 0); + atomic_long_set(&po->rollover->num_failed, 0); + } + mutex_lock(&fanout_mutex); match = NULL; list_for_each_entry(f, &fanout_list, list) { @@ -1515,6 +1608,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) } out: mutex_unlock(&fanout_mutex); + if (err) { + kfree(po->rollover); + po->rollover = NULL; + } return err; } @@ -1536,6 +1633,8 @@ static void fanout_release(struct sock *sk) kfree(f); } mutex_unlock(&fanout_mutex); + + kfree(po->rollover); } static const struct proto_ops packet_ops; @@ -2835,7 +2934,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, sock->state = SS_UNCONNECTED; err = -ENOBUFS; - sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto); + sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern); if (sk == NULL) goto out; @@ -2865,6 +2964,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, spin_lock_init(&po->bind_lock); mutex_init(&po->pg_vec_lock); + po->rollover = NULL; po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) @@ -2942,6 +3042,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (skb == NULL) goto out; + if (pkt_sk(sk)->pressure) + packet_rcv_has_room(pkt_sk(sk), NULL); + if (pkt_sk(sk)->has_vnet_hdr) { struct virtio_net_hdr vnet_hdr = { 0 }; @@ -3485,6 +3588,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, struct packet_sock *po = pkt_sk(sk); void *data = &val; union tpacket_stats_u st; + struct tpacket_rollover_stats rstats; if (level != SOL_PACKET) return -ENOPROTOOPT; @@ -3560,6 +3664,15 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, ((u32)po->fanout->flags << 24)) : 0); break; + case PACKET_ROLLOVER_STATS: + if (!po->rollover) + return -EINVAL; + rstats.tp_all = atomic_long_read(&po->rollover->num); + rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); + rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); + data = &rstats; + lv = sizeof(rstats); + break; case PACKET_TX_HAS_OFF: val = po->tp_tx_has_off; break; @@ -3697,6 +3810,8 @@ static unsigned int packet_poll(struct file *file, struct socket *sock, TP_STATUS_KERNEL)) mask |= POLLIN | POLLRDNORM; } + if (po->pressure && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) + po->pressure = 0; spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { diff --git a/net/packet/internal.h b/net/packet/internal.h index fe6e20caea1d..c035d263c1e8 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -82,12 +82,20 @@ struct packet_fanout { atomic_t rr_cur; struct list_head list; struct sock *arr[PACKET_FANOUT_MAX]; - int next[PACKET_FANOUT_MAX]; spinlock_t lock; atomic_t sk_ref; struct packet_type prot_hook ____cacheline_aligned_in_smp; }; +struct packet_rollover { + int sock; + atomic_long_t num; + atomic_long_t num_huge; + atomic_long_t num_failed; +#define ROLLOVER_HLEN (L1_CACHE_BYTES / sizeof(u32)) + u32 history[ROLLOVER_HLEN] ____cacheline_aligned; +} ____cacheline_aligned_in_smp; + struct packet_sock { /* struct sock has to be the first member of packet_sock */ struct sock sk; @@ -102,8 +110,10 @@ struct packet_sock { auxdata:1, origdev:1, has_vnet_hdr:1; + int pressure; int ifindex; /* bound device */ __be16 num; + struct packet_rollover *rollover; struct packet_mclist *mclist; atomic_t mapped; enum tpacket_versions tp_version; diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 32ab87d34828..10d42f3220ab 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -97,7 +97,7 @@ static int pn_socket_create(struct net *net, struct socket *sock, int protocol, goto out; } - sk = sk_alloc(net, PF_PHONET, GFP_KERNEL, pnp->prot); + sk = sk_alloc(net, PF_PHONET, GFP_KERNEL, pnp->prot, kern); if (sk == NULL) { err = -ENOMEM; goto out; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 6de2aeb98a1f..850a86cde0b3 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -845,7 +845,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) } /* Create a new to-be-accepted sock */ - newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot); + newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0); if (!newsk) { pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL); err = -ENOBUFS; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 10443377fb9d..2ad9032372b2 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -270,6 +270,28 @@ static int rds_cong_monitor(struct rds_sock *rs, char __user *optval, return ret; } +static int rds_set_transport(struct rds_sock *rs, char __user *optval, + int optlen) +{ + int t_type; + + if (rs->rs_transport) + return -EOPNOTSUPP; /* previously attached to transport */ + + if (optlen != sizeof(int)) + return -EINVAL; + + if (copy_from_user(&t_type, (int __user *)optval, sizeof(t_type))) + return -EFAULT; + + if (t_type < 0 || t_type >= RDS_TRANS_COUNT) + return -EINVAL; + + rs->rs_transport = rds_trans_get(t_type); + + return rs->rs_transport ? 0 : -ENOPROTOOPT; +} + static int rds_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { @@ -300,6 +322,11 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, case RDS_CONG_MONITOR: ret = rds_cong_monitor(rs, optval, optlen); break; + case SO_RDS_TRANSPORT: + lock_sock(sock->sk); + ret = rds_set_transport(rs, optval, optlen); + release_sock(sock->sk); + break; default: ret = -ENOPROTOOPT; } @@ -312,6 +339,7 @@ static int rds_getsockopt(struct socket *sock, int level, int optname, { struct rds_sock *rs = rds_sk_to_rs(sock->sk); int ret = -ENOPROTOOPT, len; + int trans; if (level != SOL_RDS) goto out; @@ -337,6 +365,19 @@ static int rds_getsockopt(struct socket *sock, int level, int optname, else ret = 0; break; + case SO_RDS_TRANSPORT: + if (len < sizeof(int)) { + ret = -EINVAL; + break; + } + trans = (rs->rs_transport ? rs->rs_transport->t_type : + RDS_TRANS_NONE); /* unbound */ + if (put_user(trans, (int __user *)optval) || + put_user(sizeof(int), optlen)) + ret = -EFAULT; + else + ret = 0; + break; default: break; } @@ -440,7 +481,7 @@ static int rds_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_SEQPACKET || protocol) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, AF_RDS, GFP_ATOMIC, &rds_proto); + sk = sk_alloc(net, AF_RDS, GFP_ATOMIC, &rds_proto, kern); if (!sk) return -ENOMEM; diff --git a/net/rds/bind.c b/net/rds/bind.c index a2e6562da751..4ebd29c128b6 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -181,6 +181,10 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (ret) goto out; + if (rs->rs_transport) { /* previously bound */ + ret = 0; + goto out; + } trans = rds_trans_get_preferred(sin->sin_addr.s_addr); if (!trans) { ret = -EADDRNOTAVAIL; diff --git a/net/rds/rds.h b/net/rds/rds.h index 0d41155a2258..a33fb4ad3535 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -408,11 +408,6 @@ struct rds_notifier { * should try hard not to block. */ -#define RDS_TRANS_IB 0 -#define RDS_TRANS_IWARP 1 -#define RDS_TRANS_TCP 2 -#define RDS_TRANS_COUNT 3 - struct rds_transport { char t_name[TRANSNAMSIZ]; struct list_head t_item; @@ -803,6 +798,7 @@ struct rds_transport *rds_trans_get_preferred(__be32 addr); void rds_trans_put(struct rds_transport *trans); unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, unsigned int avail); +struct rds_transport *rds_trans_get(int t_type); int rds_trans_init(void); void rds_trans_exit(void); diff --git a/net/rds/transport.c b/net/rds/transport.c index 7f2ac4fec367..8b4a6cd2c3a7 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -101,6 +101,27 @@ struct rds_transport *rds_trans_get_preferred(__be32 addr) return ret; } +struct rds_transport *rds_trans_get(int t_type) +{ + struct rds_transport *ret = NULL; + struct rds_transport *trans; + unsigned int i; + + down_read(&rds_trans_sem); + for (i = 0; i < RDS_TRANS_COUNT; i++) { + trans = transports[i]; + + if (trans && trans->t_type == t_type && + (!trans->t_owner || try_module_get(trans->t_owner))) { + ret = trans; + break; + } + } + up_read(&rds_trans_sem); + + return ret; +} + /* * This returns the number of stats entries in the snapshot and only * copies them using the iter if there is enough space for them. The diff --git a/net/rfkill/core.c b/net/rfkill/core.c index fa7cd792791c..f12149a29cb1 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -794,7 +794,8 @@ void rfkill_resume_polling(struct rfkill *rfkill) } EXPORT_SYMBOL(rfkill_resume_polling); -static int rfkill_suspend(struct device *dev, pm_message_t state) +#ifdef CONFIG_PM_SLEEP +static int rfkill_suspend(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); @@ -818,13 +819,18 @@ static int rfkill_resume(struct device *dev) return 0; } +static SIMPLE_DEV_PM_OPS(rfkill_pm_ops, rfkill_suspend, rfkill_resume); +#define RFKILL_PM_OPS (&rfkill_pm_ops) +#else +#define RFKILL_PM_OPS NULL +#endif + static struct class rfkill_class = { .name = "rfkill", .dev_release = rfkill_release, .dev_groups = rfkill_dev_groups, .dev_uevent = rfkill_dev_uevent, - .suspend = rfkill_suspend, - .resume = rfkill_resume, + .pm = RFKILL_PM_OPS, }; bool rfkill_blocked(struct rfkill *rfkill) diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index d978f2f46ff3..d5d58d919552 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -112,21 +112,17 @@ static int rfkill_gpio_probe(struct platform_device *pdev) rfkill->clk = devm_clk_get(&pdev->dev, NULL); - gpio = devm_gpiod_get(&pdev->dev, "reset"); - if (!IS_ERR(gpio)) { - ret = gpiod_direction_output(gpio, 0); - if (ret) - return ret; - rfkill->reset_gpio = gpio; - } + gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(gpio)) + return PTR_ERR(gpio); - gpio = devm_gpiod_get(&pdev->dev, "shutdown"); - if (!IS_ERR(gpio)) { - ret = gpiod_direction_output(gpio, 0); - if (ret) - return ret; - rfkill->shutdown_gpio = gpio; - } + rfkill->reset_gpio = gpio; + + gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW); + if (IS_ERR(gpio)) + return PTR_ERR(gpio); + + rfkill->shutdown_gpio = gpio; /* Make sure at-least one of the GPIO is defined and that * a name is specified for this instance diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 8ae603069a1a..36dbc2da3661 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -520,7 +520,7 @@ static int rose_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_SEQPACKET || protocol != 0) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, PF_ROSE, GFP_ATOMIC, &rose_proto); + sk = sk_alloc(net, PF_ROSE, GFP_ATOMIC, &rose_proto, kern); if (sk == NULL) return -ENOMEM; @@ -559,7 +559,7 @@ static struct sock *rose_make_new(struct sock *osk) if (osk->sk_type != SOCK_SEQPACKET) return NULL; - sk = sk_alloc(sock_net(osk), PF_ROSE, GFP_ATOMIC, &rose_proto); + sk = sk_alloc(sock_net(osk), PF_ROSE, GFP_ATOMIC, &rose_proto, 0); if (sk == NULL) return NULL; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 0095b9a0b779..25d60ed15284 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -632,7 +632,7 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, sock->ops = &rxrpc_rpc_ops; sock->state = SS_UNCONNECTED; - sk = sk_alloc(net, PF_RXRPC, GFP_KERNEL, &rxrpc_proto); + sk = sk_alloc(net, PF_RXRPC, GFP_KERNEL, &rxrpc_proto, kern); if (!sk) return -ENOMEM; diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c index ca904ed5400a..78483b4602bf 100644 --- a/net/rxrpc/ar-local.c +++ b/net/rxrpc/ar-local.c @@ -73,8 +73,8 @@ static int rxrpc_create_local(struct rxrpc_local *local) _enter("%p{%d}", local, local->srx.transport_type); /* create a socket to represent the local endpoint */ - ret = sock_create_kern(PF_INET, local->srx.transport_type, IPPROTO_UDP, - &local->socket); + ret = sock_create_kern(&init_net, PF_INET, local->srx.transport_type, + IPPROTO_UDP, &local->socket); if (ret < 0) { _leave(" = %d [socket]", ret); return ret; diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 2274e723a3df..daa33432b716 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -312,6 +312,7 @@ config NET_SCH_PIE config NET_SCH_INGRESS tristate "Ingress Qdisc" depends on NET_CLS_ACT + select NET_INGRESS ---help--- Say Y here if you want to use classifiers for incoming packets. If unsure, say Y. @@ -477,6 +478,16 @@ config NET_CLS_BPF To compile this code as a module, choose M here: the module will be called cls_bpf. +config NET_CLS_FLOWER + tristate "Flower classifier" + select NET_CLS + ---help--- + If you say Y here, you will be able to classify packets based on + a configurable combination of packet keys and masks. + + To compile this code as a module, choose M here: the module will + be called cls_flower. + config NET_EMATCH bool "Extended Matches" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index 7ca7f4c1b8c2..690c1689e090 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o obj-$(CONFIG_NET_CLS_BPF) += cls_bpf.o +obj-$(CONFIG_NET_CLS_FLOWER) += cls_flower.o obj-$(CONFIG_NET_EMATCH) += ematch.o obj-$(CONFIG_NET_EMATCH_CMP) += em_cmp.o obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 3d43e4979f27..af427a3dbcba 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -392,11 +392,6 @@ int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, list_for_each_entry(a, actions, list) { repeat: ret = a->ops->act(skb, a, res); - if (TC_MUNGED & skb->tc_verd) { - /* copied already, allow trampling */ - skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); - skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd); - } if (ret == TC_ACT_REPEAT) goto repeat; /* we need a ttl - JHS */ if (ret != TC_ACT_PIPE) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index dc6a2d324bd8..1d56903fd4c7 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -37,6 +37,7 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, { struct tcf_bpf *prog = act->priv; int action, filter_res; + bool at_ingress = G_TC_AT(skb->tc_verd) & AT_INGRESS; if (unlikely(!skb_mac_header_was_set(skb))) return TC_ACT_UNSPEC; @@ -48,7 +49,13 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, /* Needed here for accessing maps. */ rcu_read_lock(); - filter_res = BPF_PROG_RUN(prog->filter, skb); + if (at_ingress) { + __skb_push(skb, skb->mac_len); + filter_res = BPF_PROG_RUN(prog->filter, skb); + __skb_pull(skb, skb->mac_len); + } else { + filter_res = BPF_PROG_RUN(prog->filter, skb); + } rcu_read_unlock(); /* A BPF program may overwrite the default action opcode. diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 3f63ceac8e01..a42a3b257226 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -151,7 +151,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, } at = G_TC_AT(skb->tc_verd); - skb2 = skb_act_clone(skb, GFP_ATOMIC, m->tcf_action); + skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2 == NULL) goto out; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 59649d588d79..17e6d6669c7f 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -108,7 +108,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_pedit *p = a->priv; - int i, munged = 0; + int i; unsigned int off; if (skb_unclone(skb, GFP_ATOMIC)) @@ -156,11 +156,8 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, *ptr = ((*ptr & tkey->mask) ^ tkey->val); if (ptr == &_data) skb_store_bits(skb, off + offset, ptr, 4); - munged++; } - if (munged) - skb->tc_verd = SET_TC_MUNGED(skb->tc_verd); goto done; } else WARN(1, "pedit BUG: index %d\n", p->tcf_index); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 91bd9c19471d..c79ecfd36e0f 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -64,6 +64,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, { struct cls_bpf_head *head = rcu_dereference_bh(tp->root); struct cls_bpf_prog *prog; +#ifdef CONFIG_NET_CLS_ACT + bool at_ingress = G_TC_AT(skb->tc_verd) & AT_INGRESS; +#else + bool at_ingress = false; +#endif int ret = -1; if (unlikely(!skb_mac_header_was_set(skb))) @@ -72,7 +77,16 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* Needed here for accessing maps. */ rcu_read_lock(); list_for_each_entry_rcu(prog, &head->plist, link) { - int filter_res = BPF_PROG_RUN(prog->filter, skb); + int filter_res; + + if (at_ingress) { + /* It is safe to push/pull even if skb_shared() */ + __skb_push(skb, skb->mac_len); + filter_res = BPF_PROG_RUN(prog->filter, skb); + __skb_pull(skb, skb->mac_len); + } else { + filter_res = BPF_PROG_RUN(prog->filter, skb); + } if (filter_res == 0) continue; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index a620c4e288a5..76bc3a20ffdb 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -26,7 +26,7 @@ #include <net/pkt_cls.h> #include <net/ip.h> #include <net/route.h> -#include <net/flow_keys.h> +#include <net/flow_dissector.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netfilter/nf_conntrack.h> @@ -68,35 +68,41 @@ static inline u32 addr_fold(void *addr) static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow) { - if (flow->src) - return ntohl(flow->src); + __be32 src = flow_get_u32_src(flow); + + if (src) + return ntohl(src); + return addr_fold(skb->sk); } static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - if (flow->dst) - return ntohl(flow->dst); + __be32 dst = flow_get_u32_dst(flow); + + if (dst) + return ntohl(dst); + return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); } static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow) { - return flow->ip_proto; + return flow->basic.ip_proto; } static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow) { - if (flow->ports) - return ntohs(flow->port16[0]); + if (flow->ports.ports) + return ntohs(flow->ports.src); return addr_fold(skb->sk); } static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - if (flow->ports) - return ntohs(flow->port16[1]); + if (flow->ports.ports) + return ntohs(flow->ports.dst); return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); } @@ -295,7 +301,7 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, keymask = f->keymask; if (keymask & FLOW_KEYS_NEEDED) - skb_flow_dissect(skb, &flow_keys); + skb_flow_dissect_flow_keys(skb, &flow_keys); for (n = 0; n < f->nkeys; n++) { key = ffs(keymask) - 1; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c new file mode 100644 index 000000000000..b92d3f49c23e --- /dev/null +++ b/net/sched/cls_flower.c @@ -0,0 +1,691 @@ +/* + * net/sched/cls_flower.c Flower classifier + * + * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/rhashtable.h> + +#include <linux/if_ether.h> +#include <linux/in6.h> +#include <linux/ip.h> + +#include <net/sch_generic.h> +#include <net/pkt_cls.h> +#include <net/ip.h> +#include <net/flow_dissector.h> + +struct fl_flow_key { + int indev_ifindex; + struct flow_dissector_key_control control; + struct flow_dissector_key_basic basic; + struct flow_dissector_key_eth_addrs eth; + struct flow_dissector_key_addrs ipaddrs; + union { + struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; + }; + struct flow_dissector_key_ports tp; +} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ + +struct fl_flow_mask_range { + unsigned short int start; + unsigned short int end; +}; + +struct fl_flow_mask { + struct fl_flow_key key; + struct fl_flow_mask_range range; + struct rcu_head rcu; +}; + +struct cls_fl_head { + struct rhashtable ht; + struct fl_flow_mask mask; + struct flow_dissector dissector; + u32 hgen; + bool mask_assigned; + struct list_head filters; + struct rhashtable_params ht_params; + struct rcu_head rcu; +}; + +struct cls_fl_filter { + struct rhash_head ht_node; + struct fl_flow_key mkey; + struct tcf_exts exts; + struct tcf_result res; + struct fl_flow_key key; + struct list_head list; + u32 handle; + struct rcu_head rcu; +}; + +static unsigned short int fl_mask_range(const struct fl_flow_mask *mask) +{ + return mask->range.end - mask->range.start; +} + +static void fl_mask_update_range(struct fl_flow_mask *mask) +{ + const u8 *bytes = (const u8 *) &mask->key; + size_t size = sizeof(mask->key); + size_t i, first = 0, last = size - 1; + + for (i = 0; i < sizeof(mask->key); i++) { + if (bytes[i]) { + if (!first && i) + first = i; + last = i; + } + } + mask->range.start = rounddown(first, sizeof(long)); + mask->range.end = roundup(last + 1, sizeof(long)); +} + +static void *fl_key_get_start(struct fl_flow_key *key, + const struct fl_flow_mask *mask) +{ + return (u8 *) key + mask->range.start; +} + +static void fl_set_masked_key(struct fl_flow_key *mkey, struct fl_flow_key *key, + struct fl_flow_mask *mask) +{ + const long *lkey = fl_key_get_start(key, mask); + const long *lmask = fl_key_get_start(&mask->key, mask); + long *lmkey = fl_key_get_start(mkey, mask); + int i; + + for (i = 0; i < fl_mask_range(mask); i += sizeof(long)) + *lmkey++ = *lkey++ & *lmask++; +} + +static void fl_clear_masked_range(struct fl_flow_key *key, + struct fl_flow_mask *mask) +{ + memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask)); +} + +static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res) +{ + struct cls_fl_head *head = rcu_dereference_bh(tp->root); + struct cls_fl_filter *f; + struct fl_flow_key skb_key; + struct fl_flow_key skb_mkey; + + fl_clear_masked_range(&skb_key, &head->mask); + skb_key.indev_ifindex = skb->skb_iif; + /* skb_flow_dissect() does not set n_proto in case an unknown protocol, + * so do it rather here. + */ + skb_key.basic.n_proto = skb->protocol; + skb_flow_dissect(skb, &head->dissector, &skb_key); + + fl_set_masked_key(&skb_mkey, &skb_key, &head->mask); + + f = rhashtable_lookup_fast(&head->ht, + fl_key_get_start(&skb_mkey, &head->mask), + head->ht_params); + if (f) { + *res = f->res; + return tcf_exts_exec(skb, &f->exts, res); + } + return -1; +} + +static int fl_init(struct tcf_proto *tp) +{ + struct cls_fl_head *head; + + head = kzalloc(sizeof(*head), GFP_KERNEL); + if (!head) + return -ENOBUFS; + + INIT_LIST_HEAD_RCU(&head->filters); + rcu_assign_pointer(tp->root, head); + + return 0; +} + +static void fl_destroy_filter(struct rcu_head *head) +{ + struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu); + + tcf_exts_destroy(&f->exts); + kfree(f); +} + +static bool fl_destroy(struct tcf_proto *tp, bool force) +{ + struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_filter *f, *next; + + if (!force && !list_empty(&head->filters)) + return false; + + list_for_each_entry_safe(f, next, &head->filters, list) { + list_del_rcu(&f->list); + call_rcu(&f->rcu, fl_destroy_filter); + } + RCU_INIT_POINTER(tp->root, NULL); + if (head->mask_assigned) + rhashtable_destroy(&head->ht); + kfree_rcu(head, rcu); + return true; +} + +static unsigned long fl_get(struct tcf_proto *tp, u32 handle) +{ + struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_filter *f; + + list_for_each_entry(f, &head->filters, list) + if (f->handle == handle) + return (unsigned long) f; + return 0; +} + +static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { + [TCA_FLOWER_UNSPEC] = { .type = NLA_UNSPEC }, + [TCA_FLOWER_CLASSID] = { .type = NLA_U32 }, + [TCA_FLOWER_INDEV] = { .type = NLA_STRING, + .len = IFNAMSIZ }, + [TCA_FLOWER_KEY_ETH_DST] = { .len = ETH_ALEN }, + [TCA_FLOWER_KEY_ETH_DST_MASK] = { .len = ETH_ALEN }, + [TCA_FLOWER_KEY_ETH_SRC] = { .len = ETH_ALEN }, + [TCA_FLOWER_KEY_ETH_SRC_MASK] = { .len = ETH_ALEN }, + [TCA_FLOWER_KEY_ETH_TYPE] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_IP_PROTO] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_IPV4_SRC] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_IPV4_SRC_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_IPV4_DST] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_IPV4_DST_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_TCP_SRC] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_TCP_SRC] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 }, +}; + +static void fl_set_key_val(struct nlattr **tb, + void *val, int val_type, + void *mask, int mask_type, int len) +{ + if (!tb[val_type]) + return; + memcpy(val, nla_data(tb[val_type]), len); + if (mask_type == TCA_FLOWER_UNSPEC || !tb[mask_type]) + memset(mask, 0xff, len); + else + memcpy(mask, nla_data(tb[mask_type]), len); +} + +static int fl_set_key(struct net *net, struct nlattr **tb, + struct fl_flow_key *key, struct fl_flow_key *mask) +{ +#ifdef CONFIG_NET_CLS_IND + if (tb[TCA_FLOWER_INDEV]) { + int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]); + if (err < 0) + return err; + key->indev_ifindex = err; + mask->indev_ifindex = 0xffffffff; + } +#endif + + fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, + mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, + sizeof(key->eth.dst)); + fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC, + mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, + sizeof(key->eth.src)); + fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE, + &mask->basic.n_proto, TCA_FLOWER_UNSPEC, + sizeof(key->basic.n_proto)); + if (key->basic.n_proto == htons(ETH_P_IP) || + key->basic.n_proto == htons(ETH_P_IPV6)) { + fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, + &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, + sizeof(key->basic.ip_proto)); + } + if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, + &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, + sizeof(key->ipv4.src)); + fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST, + &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK, + sizeof(key->ipv4.dst)); + } else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC, + &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK, + sizeof(key->ipv6.src)); + fl_set_key_val(tb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST, + &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK, + sizeof(key->ipv6.dst)); + } + if (key->basic.ip_proto == IPPROTO_TCP) { + fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, + &mask->tp.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp.src)); + fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST, + &mask->tp.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp.dst)); + } else if (key->basic.ip_proto == IPPROTO_UDP) { + fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC, + &mask->tp.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp.src)); + fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST, + &mask->tp.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp.dst)); + } + + return 0; +} + +static bool fl_mask_eq(struct fl_flow_mask *mask1, + struct fl_flow_mask *mask2) +{ + const long *lmask1 = fl_key_get_start(&mask1->key, mask1); + const long *lmask2 = fl_key_get_start(&mask2->key, mask2); + + return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) && + !memcmp(lmask1, lmask2, fl_mask_range(mask1)); +} + +static const struct rhashtable_params fl_ht_params = { + .key_offset = offsetof(struct cls_fl_filter, mkey), /* base offset */ + .head_offset = offsetof(struct cls_fl_filter, ht_node), + .automatic_shrinking = true, +}; + +static int fl_init_hashtable(struct cls_fl_head *head, + struct fl_flow_mask *mask) +{ + head->ht_params = fl_ht_params; + head->ht_params.key_len = fl_mask_range(mask); + head->ht_params.key_offset += mask->range.start; + + return rhashtable_init(&head->ht, &head->ht_params); +} + +#define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) +#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member)) +#define FL_KEY_MEMBER_END_OFFSET(member) \ + (FL_KEY_MEMBER_OFFSET(member) + FL_KEY_MEMBER_SIZE(member)) + +#define FL_KEY_IN_RANGE(mask, member) \ + (FL_KEY_MEMBER_OFFSET(member) <= (mask)->range.end && \ + FL_KEY_MEMBER_END_OFFSET(member) >= (mask)->range.start) + +#define FL_KEY_SET(keys, cnt, id, member) \ + do { \ + keys[cnt].key_id = id; \ + keys[cnt].offset = FL_KEY_MEMBER_OFFSET(member); \ + cnt++; \ + } while(0); + +#define FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, id, member) \ + do { \ + if (FL_KEY_IN_RANGE(mask, member)) \ + FL_KEY_SET(keys, cnt, id, member); \ + } while(0); + +static void fl_init_dissector(struct cls_fl_head *head, + struct fl_flow_mask *mask) +{ + struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX]; + size_t cnt = 0; + + FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control); + FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic); + FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, + FLOW_DISSECTOR_KEY_ETH_ADDRS, eth); + FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); + FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); + FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS, tp); + + skb_flow_dissector_init(&head->dissector, keys, cnt); +} + +static int fl_check_assign_mask(struct cls_fl_head *head, + struct fl_flow_mask *mask) +{ + int err; + + if (head->mask_assigned) { + if (!fl_mask_eq(&head->mask, mask)) + return -EINVAL; + else + return 0; + } + + /* Mask is not assigned yet. So assign it and init hashtable + * according to that. + */ + err = fl_init_hashtable(head, mask); + if (err) + return err; + memcpy(&head->mask, mask, sizeof(head->mask)); + head->mask_assigned = true; + + fl_init_dissector(head, mask); + + return 0; +} + +static int fl_set_parms(struct net *net, struct tcf_proto *tp, + struct cls_fl_filter *f, struct fl_flow_mask *mask, + unsigned long base, struct nlattr **tb, + struct nlattr *est, bool ovr) +{ + struct tcf_exts e; + int err; + + tcf_exts_init(&e, TCA_FLOWER_ACT, 0); + err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + if (err < 0) + return err; + + if (tb[TCA_FLOWER_CLASSID]) { + f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); + tcf_bind_filter(tp, &f->res, base); + } + + err = fl_set_key(net, tb, &f->key, &mask->key); + if (err) + goto errout; + + fl_mask_update_range(mask); + fl_set_masked_key(&f->mkey, &f->key, mask); + + tcf_exts_change(tp, &f->exts, &e); + + return 0; +errout: + tcf_exts_destroy(&e); + return err; +} + +static u32 fl_grab_new_handle(struct tcf_proto *tp, + struct cls_fl_head *head) +{ + unsigned int i = 0x80000000; + u32 handle; + + do { + if (++head->hgen == 0x7FFFFFFF) + head->hgen = 1; + } while (--i > 0 && fl_get(tp, head->hgen)); + + if (unlikely(i == 0)) { + pr_err("Insufficient number of handles\n"); + handle = 0; + } else { + handle = head->hgen; + } + + return handle; +} + +static int fl_change(struct net *net, struct sk_buff *in_skb, + struct tcf_proto *tp, unsigned long base, + u32 handle, struct nlattr **tca, + unsigned long *arg, bool ovr) +{ + struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_filter *fold = (struct cls_fl_filter *) *arg; + struct cls_fl_filter *fnew; + struct nlattr *tb[TCA_FLOWER_MAX + 1]; + struct fl_flow_mask mask = {}; + int err; + + if (!tca[TCA_OPTIONS]) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy); + if (err < 0) + return err; + + if (fold && handle && fold->handle != handle) + return -EINVAL; + + fnew = kzalloc(sizeof(*fnew), GFP_KERNEL); + if (!fnew) + return -ENOBUFS; + + tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0); + + if (!handle) { + handle = fl_grab_new_handle(tp, head); + if (!handle) { + err = -EINVAL; + goto errout; + } + } + fnew->handle = handle; + + err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr); + if (err) + goto errout; + + err = fl_check_assign_mask(head, &mask); + if (err) + goto errout; + + err = rhashtable_insert_fast(&head->ht, &fnew->ht_node, + head->ht_params); + if (err) + goto errout; + if (fold) + rhashtable_remove_fast(&head->ht, &fold->ht_node, + head->ht_params); + + *arg = (unsigned long) fnew; + + if (fold) { + list_replace_rcu(&fnew->list, &fold->list); + tcf_unbind_filter(tp, &fold->res); + call_rcu(&fold->rcu, fl_destroy_filter); + } else { + list_add_tail_rcu(&fnew->list, &head->filters); + } + + return 0; + +errout: + kfree(fnew); + return err; +} + +static int fl_delete(struct tcf_proto *tp, unsigned long arg) +{ + struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_filter *f = (struct cls_fl_filter *) arg; + + rhashtable_remove_fast(&head->ht, &f->ht_node, + head->ht_params); + list_del_rcu(&f->list); + tcf_unbind_filter(tp, &f->res); + call_rcu(&f->rcu, fl_destroy_filter); + return 0; +} + +static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg) +{ + struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_filter *f; + + list_for_each_entry_rcu(f, &head->filters, list) { + if (arg->count < arg->skip) + goto skip; + if (arg->fn(tp, (unsigned long) f, arg) < 0) { + arg->stop = 1; + break; + } +skip: + arg->count++; + } +} + +static int fl_dump_key_val(struct sk_buff *skb, + void *val, int val_type, + void *mask, int mask_type, int len) +{ + int err; + + if (!memchr_inv(mask, 0, len)) + return 0; + err = nla_put(skb, val_type, len, val); + if (err) + return err; + if (mask_type != TCA_FLOWER_UNSPEC) { + err = nla_put(skb, mask_type, len, mask); + if (err) + return err; + } + return 0; +} + +static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, + struct sk_buff *skb, struct tcmsg *t) +{ + struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_filter *f = (struct cls_fl_filter *) fh; + struct nlattr *nest; + struct fl_flow_key *key, *mask; + + if (!f) + return skb->len; + + t->tcm_handle = f->handle; + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + if (f->res.classid && + nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid)) + goto nla_put_failure; + + key = &f->key; + mask = &head->mask.key; + + if (mask->indev_ifindex) { + struct net_device *dev; + + dev = __dev_get_by_index(net, key->indev_ifindex); + if (dev && nla_put_string(skb, TCA_FLOWER_INDEV, dev->name)) + goto nla_put_failure; + } + + if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, + mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, + sizeof(key->eth.dst)) || + fl_dump_key_val(skb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC, + mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, + sizeof(key->eth.src)) || + fl_dump_key_val(skb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE, + &mask->basic.n_proto, TCA_FLOWER_UNSPEC, + sizeof(key->basic.n_proto))) + goto nla_put_failure; + if ((key->basic.n_proto == htons(ETH_P_IP) || + key->basic.n_proto == htons(ETH_P_IPV6)) && + fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, + &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, + sizeof(key->basic.ip_proto))) + goto nla_put_failure; + + if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && + (fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, + &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, + sizeof(key->ipv4.src)) || + fl_dump_key_val(skb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST, + &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK, + sizeof(key->ipv4.dst)))) + goto nla_put_failure; + else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS && + (fl_dump_key_val(skb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC, + &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK, + sizeof(key->ipv6.src)) || + fl_dump_key_val(skb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST, + &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK, + sizeof(key->ipv6.dst)))) + goto nla_put_failure; + + if (key->basic.ip_proto == IPPROTO_TCP && + (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, + &mask->tp.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp.src)) || + fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST, + &mask->tp.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp.dst)))) + goto nla_put_failure; + else if (key->basic.ip_proto == IPPROTO_UDP && + (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC, + &mask->tp.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp.src)) || + fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST, + &mask->tp.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp.dst)))) + goto nla_put_failure; + + if (tcf_exts_dump(skb, &f->exts)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + + if (tcf_exts_dump_stats(skb, &f->exts) < 0) + goto nla_put_failure; + + return skb->len; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct tcf_proto_ops cls_fl_ops __read_mostly = { + .kind = "flower", + .classify = fl_classify, + .init = fl_init, + .destroy = fl_destroy, + .get = fl_get, + .change = fl_change, + .delete = fl_delete, + .walk = fl_walk, + .dump = fl_dump, + .owner = THIS_MODULE, +}; + +static int __init cls_fl_init(void) +{ + return register_tcf_proto_ops(&cls_fl_ops); +} + +static void __exit cls_fl_exit(void) +{ + unregister_tcf_proto_ops(&cls_fl_ops); +} + +module_init(cls_fl_init); +module_exit(cls_fl_exit); + +MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>"); +MODULE_DESCRIPTION("Flower classifier"); +MODULE_LICENSE("GPL v2"); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1e1c89e51a11..c5b9db84d069 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1818,13 +1818,8 @@ int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp, continue; err = tp->classify(skb, tp, res); - if (err >= 0) { -#ifdef CONFIG_NET_CLS_ACT - if (err != TC_ACT_RECLASSIFY && skb->tc_verd) - skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0); -#endif + if (err >= 0) return err; - } } return -1; } @@ -1836,23 +1831,22 @@ int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, int err = 0; #ifdef CONFIG_NET_CLS_ACT const struct tcf_proto *otp = tp; + int limit = 0; reclassify: #endif err = tc_classify_compat(skb, tp, res); #ifdef CONFIG_NET_CLS_ACT if (err == TC_ACT_RECLASSIFY) { - u32 verd = G_TC_VERD(skb->tc_verd); tp = otp; - if (verd++ >= MAX_REC_LOOP) { + if (unlikely(limit++ >= MAX_REC_LOOP)) { net_notice_ratelimited("%s: packet reclassify loop rule prio %u protocol %02x\n", tp->q->ops->id, tp->prio & 0xffff, ntohs(tp->protocol)); return TC_ACT_SHOT; } - skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd); goto reclassify; } #endif diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index c009eb9045ce..93d5742dc7e0 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -18,7 +18,7 @@ #include <net/pkt_sched.h> #include <net/inet_ecn.h> #include <net/red.h> -#include <net/flow_keys.h> +#include <net/flow_dissector.h> /* CHOKe stateless AQM for fair bandwidth allocation @@ -133,16 +133,10 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx) --sch->q.qlen; } -/* private part of skb->cb[] that a qdisc is allowed to use - * is limited to QDISC_CB_PRIV_LEN bytes. - * As a flow key might be too large, we store a part of it only. - */ -#define CHOKE_K_LEN min_t(u32, sizeof(struct flow_keys), QDISC_CB_PRIV_LEN - 3) - struct choke_skb_cb { u16 classid; u8 keys_valid; - u8 keys[QDISC_CB_PRIV_LEN - 3]; + struct flow_keys_digest keys; }; static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) @@ -176,19 +170,19 @@ static bool choke_match_flow(struct sk_buff *skb1, if (!choke_skb_cb(skb1)->keys_valid) { choke_skb_cb(skb1)->keys_valid = 1; - skb_flow_dissect(skb1, &temp); - memcpy(&choke_skb_cb(skb1)->keys, &temp, CHOKE_K_LEN); + skb_flow_dissect_flow_keys(skb1, &temp); + make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp); } if (!choke_skb_cb(skb2)->keys_valid) { choke_skb_cb(skb2)->keys_valid = 1; - skb_flow_dissect(skb2, &temp); - memcpy(&choke_skb_cb(skb2)->keys, &temp, CHOKE_K_LEN); + skb_flow_dissect_flow_keys(skb2, &temp); + make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp); } return !memcmp(&choke_skb_cb(skb1)->keys, &choke_skb_cb(skb2)->keys, - CHOKE_K_LEN); + sizeof(choke_skb_cb(skb1)->keys)); } /* diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 7a0bdb16ac92..535007d5f0b5 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -6,7 +6,7 @@ * * Implemented on linux by : * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> - * Copyright (C) 2012 Eric Dumazet <edumazet@google.com> + * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -109,6 +109,7 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { [TCA_CODEL_LIMIT] = { .type = NLA_U32 }, [TCA_CODEL_INTERVAL] = { .type = NLA_U32 }, [TCA_CODEL_ECN] = { .type = NLA_U32 }, + [TCA_CODEL_CE_THRESHOLD]= { .type = NLA_U32 }, }; static int codel_change(struct Qdisc *sch, struct nlattr *opt) @@ -133,6 +134,12 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt) q->params.target = ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT; } + if (tb[TCA_CODEL_CE_THRESHOLD]) { + u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]); + + q->params.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; + } + if (tb[TCA_CODEL_INTERVAL]) { u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]); @@ -201,7 +208,10 @@ static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_CODEL_ECN, q->params.ecn)) goto nla_put_failure; - + if (q->params.ce_threshold != CODEL_DISABLED_THRESHOLD && + nla_put_u32(skb, TCA_CODEL_CE_THRESHOLD, + codel_time_to_us(q->params.ce_threshold))) + goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: @@ -220,6 +230,7 @@ static int codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .ldelay = codel_time_to_us(q->vars.ldelay), .dropping = q->vars.dropping, .ecn_mark = q->stats.ecn_mark, + .ce_mark = q->stats.ce_mark, }; if (q->vars.dropping) { diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index c244c45b78d7..d75993f89fac 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -6,7 +6,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Copyright (C) 2012 Eric Dumazet <edumazet@google.com> + * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> */ #include <linux/module.h> @@ -23,7 +23,6 @@ #include <linux/vmalloc.h> #include <net/netlink.h> #include <net/pkt_sched.h> -#include <net/flow_keys.h> #include <net/codel.h> /* Fair Queue CoDel. @@ -68,15 +67,9 @@ struct fq_codel_sched_data { }; static unsigned int fq_codel_hash(const struct fq_codel_sched_data *q, - const struct sk_buff *skb) + struct sk_buff *skb) { - struct flow_keys keys; - unsigned int hash; - - skb_flow_dissect(skb, &keys); - hash = jhash_3words((__force u32)keys.dst, - (__force u32)keys.src ^ keys.ip_proto, - (__force u32)keys.ports, q->perturbation); + u32 hash = skb_get_hash_perturb(skb, q->perturbation); return reciprocal_scale(hash, q->flows_cnt); } @@ -299,6 +292,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_ECN] = { .type = NLA_U32 }, [TCA_FQ_CODEL_FLOWS] = { .type = NLA_U32 }, [TCA_FQ_CODEL_QUANTUM] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, }; static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) @@ -329,6 +323,12 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) q->cparams.target = (target * NSEC_PER_USEC) >> CODEL_SHIFT; } + if (tb[TCA_FQ_CODEL_CE_THRESHOLD]) { + u64 val = nla_get_u32(tb[TCA_FQ_CODEL_CE_THRESHOLD]); + + q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; + } + if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); @@ -448,6 +448,11 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) q->flows_cnt)) goto nla_put_failure; + if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD && + nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, + codel_time_to_us(q->cparams.ce_threshold))) + goto nla_put_failure; + return nla_nest_end(skb, opts); nla_put_failure: @@ -466,6 +471,7 @@ static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.qdisc_stats.drop_overlimit = q->drop_overlimit; st.qdisc_stats.ecn_mark = q->cstats.ecn_mark; st.qdisc_stats.new_flow_count = q->new_flow_count; + st.qdisc_stats.ce_mark = q->cstats.ce_mark; list_for_each(pos, &q->new_flows) st.qdisc_stats.new_flows_len++; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 634529e0ce6b..abb9f2fec28f 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -165,7 +165,8 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch) * if no default DP has been configured. This * allows for DP flows to be left untouched. */ - if (skb_queue_len(&sch->q) < qdisc_dev(sch)->tx_queue_len) + if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= + sch->limit)) return qdisc_enqueue_tail(skb, sch); else goto drop; @@ -397,7 +398,10 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, q->DP = dp; q->prio = prio; - q->limit = ctl->limit; + if (ctl->limit > sch->limit) + q->limit = sch->limit; + else + q->limit = ctl->limit; if (q->backlog == 0) red_end_of_idle_period(&q->vars); @@ -414,6 +418,7 @@ static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = { [TCA_GRED_STAB] = { .len = 256 }, [TCA_GRED_DPS] = { .len = sizeof(struct tc_gred_sopt) }, [TCA_GRED_MAX_P] = { .type = NLA_U32 }, + [TCA_GRED_LIMIT] = { .type = NLA_U32 }, }; static int gred_change(struct Qdisc *sch, struct nlattr *opt) @@ -433,11 +438,15 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt) if (err < 0) return err; - if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) + if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) { + if (tb[TCA_GRED_LIMIT] != NULL) + sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); return gred_change_table_def(sch, opt); + } if (tb[TCA_GRED_PARMS] == NULL || - tb[TCA_GRED_STAB] == NULL) + tb[TCA_GRED_STAB] == NULL || + tb[TCA_GRED_LIMIT] != NULL) return -EINVAL; max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0; @@ -501,6 +510,14 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB]) return -EINVAL; + if (tb[TCA_GRED_LIMIT]) + sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); + else { + u32 qlen = qdisc_dev(sch)->tx_queue_len ? : 1; + + sch->limit = qlen * psched_mtu(qdisc_dev(sch)); + } + return gred_change_table_def(sch, tb[TCA_GRED_DPS]); } @@ -531,6 +548,9 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_GRED_MAX_P, sizeof(max_p), max_p)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_LIMIT, sch->limit)) + goto nla_put_failure; + parms = nla_nest_start(skb, TCA_GRED_PARMS); if (parms == NULL) goto nla_put_failure; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 15d3aabfe250..9d15cb6b8cb1 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -9,7 +9,6 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> -#include <net/flow_keys.h> #include <net/pkt_sched.h> #include <net/sock.h> @@ -176,22 +175,6 @@ static u32 hhf_time_stamp(void) return jiffies; } -static unsigned int skb_hash(const struct hhf_sched_data *q, - const struct sk_buff *skb) -{ - struct flow_keys keys; - unsigned int hash; - - if (skb->sk && skb->sk->sk_hash) - return skb->sk->sk_hash; - - skb_flow_dissect(skb, &keys); - hash = jhash_3words((__force u32)keys.dst, - (__force u32)keys.src ^ keys.ip_proto, - (__force u32)keys.ports, q->perturbation); - return hash; -} - /* Looks up a heavy-hitter flow in a chaining list of table T. */ static struct hh_flow_state *seek_list(const u32 hash, struct list_head *head, @@ -280,7 +263,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch) } /* Get hashed flow-id of the skb. */ - hash = skb_hash(q, skb); + hash = skb_get_hash_perturb(skb, q->perturbation); /* Check if this packet belongs to an already established HH flow. */ flow_pos = hash & HHF_BIT_MASK; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 4cdbfb85686a..e7c648fa9dc3 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -12,16 +12,10 @@ #include <linux/list.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> + #include <net/netlink.h> #include <net/pkt_sched.h> - -struct ingress_qdisc_data { - struct tcf_proto __rcu *filter_list; -}; - -/* ------------------------- Class/flow operations ------------------------- */ - static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; @@ -49,57 +43,24 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker) static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch, unsigned long cl) { - struct ingress_qdisc_data *p = qdisc_priv(sch); - - return &p->filter_list; -} - -/* --------------------------- Qdisc operations ---------------------------- */ + struct net_device *dev = qdisc_dev(sch); -static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch) -{ - struct ingress_qdisc_data *p = qdisc_priv(sch); - struct tcf_result res; - struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result; - - result = tc_classify(skb, fl, &res); - - qdisc_bstats_update(sch, skb); - switch (result) { - case TC_ACT_SHOT: - result = TC_ACT_SHOT; - qdisc_qstats_drop(sch); - break; - case TC_ACT_STOLEN: - case TC_ACT_QUEUED: - result = TC_ACT_STOLEN; - break; - case TC_ACT_RECLASSIFY: - case TC_ACT_OK: - skb->tc_index = TC_H_MIN(res.classid); - default: - result = TC_ACT_OK; - break; - } - - return result; + return &dev->ingress_cl_list; } -/* ------------------------------------------------------------- */ - static int ingress_init(struct Qdisc *sch, struct nlattr *opt) { net_inc_ingress_queue(); + sch->flags |= TCQ_F_CPUSTATS; return 0; } static void ingress_destroy(struct Qdisc *sch) { - struct ingress_qdisc_data *p = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); - tcf_destroy_chain(&p->filter_list); + tcf_destroy_chain(&dev->ingress_cl_list); net_dec_ingress_queue(); } @@ -110,6 +71,7 @@ static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb) nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; + return nla_nest_end(skb, nest); nla_put_failure: @@ -130,8 +92,6 @@ static const struct Qdisc_class_ops ingress_class_ops = { static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", - .priv_size = sizeof(struct ingress_qdisc_data), - .enqueue = ingress_enqueue, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -148,6 +108,7 @@ static void __exit ingress_module_exit(void) unregister_qdisc(&ingress_qdisc_ops); } -module_init(ingress_module_init) -module_exit(ingress_module_exit) +module_init(ingress_module_init); +module_exit(ingress_module_exit); + MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 956ead2cab9a..5abd1d9de989 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -440,9 +440,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { struct Qdisc *rootq = qdisc_root(sch); u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - q->duplicate = 0; - qdisc_enqueue_root(skb2, rootq); + q->duplicate = 0; + rootq->enqueue(skb2, rootq); q->duplicate = dupsave; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 5819dd82630d..4b815193326c 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -26,7 +26,6 @@ #include <net/ip.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> -#include <net/flow_keys.h> /* * SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level) @@ -285,9 +284,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) int i; u32 p_min = ~0; u32 minqlen = ~0; - u32 r, slot, salt, sfbhash; + u32 r, sfbhash; + u32 slot = q->slot; int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - struct flow_keys keys; if (unlikely(sch->q.qlen >= q->limit)) { qdisc_qstats_overlimit(sch); @@ -309,22 +308,17 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) fl = rcu_dereference_bh(q->filter_list); if (fl) { + u32 salt; + /* If using external classifiers, get result and record it. */ if (!sfb_classify(skb, fl, &ret, &salt)) goto other_drop; - keys.src = salt; - keys.dst = 0; - keys.ports = 0; + sfbhash = jhash_1word(salt, q->bins[slot].perturbation); } else { - skb_flow_dissect(skb, &keys); + sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation); } - slot = q->slot; - sfbhash = jhash_3words((__force u32)keys.dst, - (__force u32)keys.src, - (__force u32)keys.ports, - q->bins[slot].perturbation); if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; @@ -356,10 +350,8 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (unlikely(p_min >= SFB_MAX_PROB)) { /* Inelastic flow */ if (q->double_buffering) { - sfbhash = jhash_3words((__force u32)keys.dst, - (__force u32)keys.src, - (__force u32)keys.ports, - q->bins[slot].perturbation); + sfbhash = skb_get_hash_perturb(skb, + q->bins[slot].perturbation); if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b877140beda5..7d1492663360 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -23,7 +23,6 @@ #include <linux/vmalloc.h> #include <net/netlink.h> #include <net/pkt_sched.h> -#include <net/flow_keys.h> #include <net/red.h> @@ -156,30 +155,10 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index return &q->dep[val - SFQ_MAX_FLOWS]; } -/* - * In order to be able to quickly rehash our queue when timer changes - * q->perturbation, we store flow_keys in skb->cb[] - */ -struct sfq_skb_cb { - struct flow_keys keys; -}; - -static inline struct sfq_skb_cb *sfq_skb_cb(const struct sk_buff *skb) -{ - qdisc_cb_private_validate(skb, sizeof(struct sfq_skb_cb)); - return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data; -} - static unsigned int sfq_hash(const struct sfq_sched_data *q, const struct sk_buff *skb) { - const struct flow_keys *keys = &sfq_skb_cb(skb)->keys; - unsigned int hash; - - hash = jhash_3words((__force u32)keys->dst, - (__force u32)keys->src ^ keys->ip_proto, - (__force u32)keys->ports, q->perturbation); - return hash & (q->divisor - 1); + return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1); } static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, @@ -196,10 +175,8 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return TC_H_MIN(skb->priority); fl = rcu_dereference_bh(q->filter_list); - if (!fl) { - skb_flow_dissect(skb, &sfq_skb_cb(skb)->keys); + if (!fl) return sfq_hash(q, skb) + 1; - } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; result = tc_classify(skb, fl, &res); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 0e4198ee2370..e917d27328ea 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -331,8 +331,9 @@ out: rt = (struct rt6_info *)dst; t->dst = dst; - t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; - pr_debug("rt6_dst:%pI6 rt6_src:%pI6\n", &rt->rt6i_dst.addr, + t->dst_cookie = rt6_get_cookie(rt); + pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n", + &rt->rt6i_dst.addr, rt->rt6i_dst.plen, &fl6->saddr); } else { t->dst = NULL; @@ -635,7 +636,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; - newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot); + newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0); if (!newsk) goto out; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 53b7acde9aa3..59e80356672b 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -550,7 +550,7 @@ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, struct sctp_association *asoc) { struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, - sk->sk_prot); + sk->sk_prot, 0); struct inet_sock *newinet; if (!newsk) diff --git a/net/socket.c b/net/socket.c index 884e32997698..9963a0b53a64 100644 --- a/net/socket.c +++ b/net/socket.c @@ -576,9 +576,6 @@ void sock_release(struct socket *sock) if (rcu_dereference_protected(sock->wq, 1)->fasync_list) pr_err("%s: fasync list not empty!\n", __func__); - if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags)) - return; - this_cpu_sub(sockets_in_use, 1); if (!sock->file) { iput(SOCK_INODE(sock)); @@ -1213,9 +1210,9 @@ int sock_create(int family, int type, int protocol, struct socket **res) } EXPORT_SYMBOL(sock_create); -int sock_create_kern(int family, int type, int protocol, struct socket **res) +int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res) { - return __sock_create(&init_net, family, type, protocol, res, 1); + return __sock_create(net, family, type, protocol, res, 1); } EXPORT_SYMBOL(sock_create_kern); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 055453d48668..e008057dab46 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -15,97 +15,359 @@ #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/netdevice.h> +#include <linux/if_bridge.h> #include <net/ip_fib.h> #include <net/switchdev.h> /** - * netdev_switch_parent_id_get - Get ID of a switch + * switchdev_port_attr_get - Get port attribute + * + * @dev: port device + * @attr: attribute to get + */ +int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) +{ + const struct switchdev_ops *ops = dev->switchdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + struct switchdev_attr first = { + .id = SWITCHDEV_ATTR_UNDEFINED + }; + int err = -EOPNOTSUPP; + + if (ops && ops->switchdev_port_attr_get) + return ops->switchdev_port_attr_get(dev, attr); + + if (attr->flags & SWITCHDEV_F_NO_RECURSE) + return err; + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to get attr on + * each port. Return -ENODATA if attr values don't + * compare across ports. + */ + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = switchdev_port_attr_get(lower_dev, attr); + if (err) + break; + if (first.id == SWITCHDEV_ATTR_UNDEFINED) + first = *attr; + else if (memcmp(&first, attr, sizeof(*attr))) + return -ENODATA; + } + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_port_attr_get); + +static int __switchdev_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr) +{ + const struct switchdev_ops *ops = dev->switchdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops && ops->switchdev_port_attr_set) + return ops->switchdev_port_attr_set(dev, attr); + + if (attr->flags & SWITCHDEV_F_NO_RECURSE) + return err; + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to set attr on + * each port. + */ + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = __switchdev_port_attr_set(lower_dev, attr); + if (err) + break; + } + + return err; +} + +struct switchdev_attr_set_work { + struct work_struct work; + struct net_device *dev; + struct switchdev_attr attr; +}; + +static void switchdev_port_attr_set_work(struct work_struct *work) +{ + struct switchdev_attr_set_work *asw = + container_of(work, struct switchdev_attr_set_work, work); + int err; + + rtnl_lock(); + err = switchdev_port_attr_set(asw->dev, &asw->attr); + BUG_ON(err); + rtnl_unlock(); + + dev_put(asw->dev); + kfree(work); +} + +static int switchdev_port_attr_set_defer(struct net_device *dev, + struct switchdev_attr *attr) +{ + struct switchdev_attr_set_work *asw; + + asw = kmalloc(sizeof(*asw), GFP_ATOMIC); + if (!asw) + return -ENOMEM; + + INIT_WORK(&asw->work, switchdev_port_attr_set_work); + + dev_hold(dev); + asw->dev = dev; + memcpy(&asw->attr, attr, sizeof(asw->attr)); + + schedule_work(&asw->work); + + return 0; +} + +/** + * switchdev_port_attr_set - Set port attribute + * * @dev: port device - * @psid: switch ID + * @attr: attribute to set * - * Get ID of a switch this port is part of. + * Use a 2-phase prepare-commit transaction model to ensure + * system is not left in a partially updated state due to + * failure from driver/device. */ -int netdev_switch_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) { - const struct swdev_ops *ops = dev->swdev_ops; + int err; + + if (!rtnl_is_locked()) { + /* Running prepare-commit transaction across stacked + * devices requires nothing moves, so if rtnl_lock is + * not held, schedule a worker thread to hold rtnl_lock + * while setting attr. + */ + + return switchdev_port_attr_set_defer(dev, attr); + } + + /* Phase I: prepare for attr set. Driver/device should fail + * here if there are going to be issues in the commit phase, + * such as lack of resources or support. The driver/device + * should reserve resources needed for the commit phase here, + * but should not commit the attr. + */ + + attr->trans = SWITCHDEV_TRANS_PREPARE; + err = __switchdev_port_attr_set(dev, attr); + if (err) { + /* Prepare phase failed: abort the transaction. Any + * resources reserved in the prepare phase are + * released. + */ + + attr->trans = SWITCHDEV_TRANS_ABORT; + __switchdev_port_attr_set(dev, attr); + + return err; + } + + /* Phase II: commit attr set. This cannot fail as a fault + * of driver/device. If it does, it's a bug in the driver/device + * because the driver said everythings was OK in phase I. + */ + + attr->trans = SWITCHDEV_TRANS_COMMIT; + err = __switchdev_port_attr_set(dev, attr); + BUG_ON(err); + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_port_attr_set); + +static int __switchdev_port_obj_add(struct net_device *dev, + struct switchdev_obj *obj) +{ + const struct switchdev_ops *ops = dev->switchdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops && ops->switchdev_port_obj_add) + return ops->switchdev_port_obj_add(dev, obj); + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to add object on + * each port. + */ + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = __switchdev_port_obj_add(lower_dev, obj); + if (err) + break; + } + + return err; +} + +/** + * switchdev_port_obj_add - Add port object + * + * @dev: port device + * @obj: object to add + * + * Use a 2-phase prepare-commit transaction model to ensure + * system is not left in a partially updated state due to + * failure from driver/device. + * + * rtnl_lock must be held. + */ +int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) +{ + int err; - if (!ops || !ops->swdev_parent_id_get) - return -EOPNOTSUPP; - return ops->swdev_parent_id_get(dev, psid); + ASSERT_RTNL(); + + /* Phase I: prepare for obj add. Driver/device should fail + * here if there are going to be issues in the commit phase, + * such as lack of resources or support. The driver/device + * should reserve resources needed for the commit phase here, + * but should not commit the obj. + */ + + obj->trans = SWITCHDEV_TRANS_PREPARE; + err = __switchdev_port_obj_add(dev, obj); + if (err) { + /* Prepare phase failed: abort the transaction. Any + * resources reserved in the prepare phase are + * released. + */ + + obj->trans = SWITCHDEV_TRANS_ABORT; + __switchdev_port_obj_add(dev, obj); + + return err; + } + + /* Phase II: commit obj add. This cannot fail as a fault + * of driver/device. If it does, it's a bug in the driver/device + * because the driver said everythings was OK in phase I. + */ + + obj->trans = SWITCHDEV_TRANS_COMMIT; + err = __switchdev_port_obj_add(dev, obj); + WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); + + return err; } -EXPORT_SYMBOL_GPL(netdev_switch_parent_id_get); +EXPORT_SYMBOL_GPL(switchdev_port_obj_add); /** - * netdev_switch_port_stp_update - Notify switch device port of STP - * state change + * switchdev_port_obj_del - Delete port object + * * @dev: port device - * @state: port STP state + * @obj: object to delete + */ +int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) +{ + const struct switchdev_ops *ops = dev->switchdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops && ops->switchdev_port_obj_del) + return ops->switchdev_port_obj_del(dev, obj); + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to delete object on + * each port. + */ + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = switchdev_port_obj_del(lower_dev, obj); + if (err) + break; + } + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_del); + +/** + * switchdev_port_obj_dump - Dump port objects * - * Notify switch device port of bridge port STP state change. + * @dev: port device + * @obj: object to dump */ -int netdev_switch_port_stp_update(struct net_device *dev, u8 state) +int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj) { - const struct swdev_ops *ops = dev->swdev_ops; + const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; - if (ops && ops->swdev_port_stp_update) - return ops->swdev_port_stp_update(dev, state); + if (ops && ops->switchdev_port_obj_dump) + return ops->switchdev_port_obj_dump(dev, obj); + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to dump objects on + * first port at bottom of stack. + */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = netdev_switch_port_stp_update(lower_dev, state); - if (err && err != -EOPNOTSUPP) - return err; + err = switchdev_port_obj_dump(lower_dev, obj); + break; } return err; } -EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update); +EXPORT_SYMBOL_GPL(switchdev_port_obj_dump); -static DEFINE_MUTEX(netdev_switch_mutex); -static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain); +static DEFINE_MUTEX(switchdev_mutex); +static RAW_NOTIFIER_HEAD(switchdev_notif_chain); /** - * register_netdev_switch_notifier - Register notifier + * register_switchdev_notifier - Register notifier * @nb: notifier_block * * Register switch device notifier. This should be used by code * which needs to monitor events happening in particular device. * Return values are same as for atomic_notifier_chain_register(). */ -int register_netdev_switch_notifier(struct notifier_block *nb) +int register_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&netdev_switch_mutex); - err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb); - mutex_unlock(&netdev_switch_mutex); + mutex_lock(&switchdev_mutex); + err = raw_notifier_chain_register(&switchdev_notif_chain, nb); + mutex_unlock(&switchdev_mutex); return err; } -EXPORT_SYMBOL_GPL(register_netdev_switch_notifier); +EXPORT_SYMBOL_GPL(register_switchdev_notifier); /** - * unregister_netdev_switch_notifier - Unregister notifier + * unregister_switchdev_notifier - Unregister notifier * @nb: notifier_block * * Unregister switch device notifier. * Return values are same as for atomic_notifier_chain_unregister(). */ -int unregister_netdev_switch_notifier(struct notifier_block *nb) +int unregister_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&netdev_switch_mutex); - err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb); - mutex_unlock(&netdev_switch_mutex); + mutex_lock(&switchdev_mutex); + err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb); + mutex_unlock(&switchdev_mutex); return err; } -EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); +EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); /** - * call_netdev_switch_notifiers - Call notifiers + * call_switchdev_notifiers - Call notifiers * @val: value passed unmodified to notifier function * @dev: port device * @info: notifier information data @@ -114,146 +376,387 @@ EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); * when it needs to propagate hardware event. * Return values are same as for atomic_notifier_call_chain(). */ -int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, - struct netdev_switch_notifier_info *info) +int call_switchdev_notifiers(unsigned long val, struct net_device *dev, + struct switchdev_notifier_info *info) { int err; info->dev = dev; - mutex_lock(&netdev_switch_mutex); - err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info); - mutex_unlock(&netdev_switch_mutex); + mutex_lock(&switchdev_mutex); + err = raw_notifier_call_chain(&switchdev_notif_chain, val, info); + mutex_unlock(&switchdev_mutex); return err; } -EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers); +EXPORT_SYMBOL_GPL(call_switchdev_notifiers); /** - * netdev_switch_port_bridge_setlink - Notify switch device port of bridge - * port attributes + * switchdev_port_bridge_getlink - Get bridge port attributes * * @dev: port device - * @nlh: netlink msg with bridge port attributes - * @flags: bridge setlink flags * - * Notify switch device port of bridge port attributes + * Called for SELF on rtnl_bridge_getlink to get bridge port + * attributes. */ -int netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) +int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, + int nlflags) { - const struct net_device_ops *ops = dev->netdev_ops; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + }; + u16 mode = BRIDGE_MODE_UNDEF; + u32 mask = BR_LEARNING | BR_LEARNING_SYNC; + int err; - if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) - return 0; + err = switchdev_port_attr_get(dev, &attr); + if (err) + return err; + + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, + attr.u.brport_flags, mask, nlflags); +} +EXPORT_SYMBOL_GPL(switchdev_port_bridge_getlink); + +static int switchdev_port_br_setflag(struct net_device *dev, + struct nlattr *nlattr, + unsigned long brport_flag) +{ + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + }; + u8 flag = nla_get_u8(nlattr); + int err; + + err = switchdev_port_attr_get(dev, &attr); + if (err) + return err; + + if (flag) + attr.u.brport_flags |= brport_flag; + else + attr.u.brport_flags &= ~brport_flag; + + return switchdev_port_attr_set(dev, &attr); +} + +static const struct nla_policy +switchdev_port_bridge_policy[IFLA_BRPORT_MAX + 1] = { + [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, + [IFLA_BRPORT_COST] = { .type = NLA_U32 }, + [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, + [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, + [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, + [IFLA_BRPORT_FAST_LEAVE] = { .type = NLA_U8 }, + [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, + [IFLA_BRPORT_LEARNING_SYNC] = { .type = NLA_U8 }, + [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, +}; + +static int switchdev_port_br_setlink_protinfo(struct net_device *dev, + struct nlattr *protinfo) +{ + struct nlattr *attr; + int rem; + int err; + + err = nla_validate_nested(protinfo, IFLA_BRPORT_MAX, + switchdev_port_bridge_policy); + if (err) + return err; + + nla_for_each_nested(attr, protinfo, rem) { + switch (nla_type(attr)) { + case IFLA_BRPORT_LEARNING: + err = switchdev_port_br_setflag(dev, attr, + BR_LEARNING); + break; + case IFLA_BRPORT_LEARNING_SYNC: + err = switchdev_port_br_setflag(dev, attr, + BR_LEARNING_SYNC); + break; + default: + err = -EOPNOTSUPP; + break; + } + if (err) + return err; + } + + return 0; +} + +static int switchdev_port_br_afspec(struct net_device *dev, + struct nlattr *afspec, + int (*f)(struct net_device *dev, + struct switchdev_obj *obj)) +{ + struct nlattr *attr; + struct bridge_vlan_info *vinfo; + struct switchdev_obj obj = { + .id = SWITCHDEV_OBJ_PORT_VLAN, + }; + struct switchdev_obj_vlan *vlan = &obj.u.vlan; + int rem; + int err; - if (!ops->ndo_bridge_setlink) - return -EOPNOTSUPP; + nla_for_each_nested(attr, afspec, rem) { + if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO) + continue; + if (nla_len(attr) != sizeof(struct bridge_vlan_info)) + return -EINVAL; + vinfo = nla_data(attr); + vlan->flags = vinfo->flags; + if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { + if (vlan->vid_start) + return -EINVAL; + vlan->vid_start = vinfo->vid; + } else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) { + if (!vlan->vid_start) + return -EINVAL; + vlan->vid_end = vinfo->vid; + if (vlan->vid_end <= vlan->vid_start) + return -EINVAL; + err = f(dev, &obj); + if (err) + return err; + memset(vlan, 0, sizeof(*vlan)); + } else { + if (vlan->vid_start) + return -EINVAL; + vlan->vid_start = vinfo->vid; + vlan->vid_end = vinfo->vid; + err = f(dev, &obj); + if (err) + return err; + memset(vlan, 0, sizeof(*vlan)); + } + } - return ops->ndo_bridge_setlink(dev, nlh, flags); + return 0; } -EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_setlink); /** - * netdev_switch_port_bridge_dellink - Notify switch device port of bridge - * port attribute delete + * switchdev_port_bridge_setlink - Set bridge port attributes * * @dev: port device - * @nlh: netlink msg with bridge port attributes - * @flags: bridge setlink flags + * @nlh: netlink header + * @flags: netlink flags * - * Notify switch device port of bridge port attribute delete + * Called for SELF on rtnl_bridge_setlink to set bridge port + * attributes. */ -int netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) +int switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) { - const struct net_device_ops *ops = dev->netdev_ops; + struct nlattr *protinfo; + struct nlattr *afspec; + int err = 0; - if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) - return 0; + protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), + IFLA_PROTINFO); + if (protinfo) { + err = switchdev_port_br_setlink_protinfo(dev, protinfo); + if (err) + return err; + } - if (!ops->ndo_bridge_dellink) - return -EOPNOTSUPP; + afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), + IFLA_AF_SPEC); + if (afspec) + err = switchdev_port_br_afspec(dev, afspec, + switchdev_port_obj_add); - return ops->ndo_bridge_dellink(dev, nlh, flags); + return err; } -EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_dellink); +EXPORT_SYMBOL_GPL(switchdev_port_bridge_setlink); /** - * ndo_dflt_netdev_switch_port_bridge_setlink - default ndo bridge setlink - * op for master devices + * switchdev_port_bridge_dellink - Set bridge port attributes * * @dev: port device - * @nlh: netlink msg with bridge port attributes - * @flags: bridge setlink flags + * @nlh: netlink header + * @flags: netlink flags * - * Notify master device slaves of bridge port attributes + * Called for SELF on rtnl_bridge_dellink to set bridge port + * attributes. */ -int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) +int switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) { - struct net_device *lower_dev; - struct list_head *iter; - int ret = 0, err = 0; + struct nlattr *afspec; - if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) - return ret; + afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), + IFLA_AF_SPEC); + if (afspec) + return switchdev_port_br_afspec(dev, afspec, + switchdev_port_obj_del); - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = netdev_switch_port_bridge_setlink(lower_dev, nlh, flags); - if (err && err != -EOPNOTSUPP) - ret = err; - } + return 0; +} +EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink); - return ret; +/** + * switchdev_port_fdb_add - Add FDB (MAC/VLAN) entry to port + * + * @ndmsg: netlink hdr + * @nlattr: netlink attributes + * @dev: port device + * @addr: MAC address to add + * @vid: VLAN to add + * + * Add FDB entry to switch device. + */ +int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr, + u16 vid, u16 nlm_flags) +{ + struct switchdev_obj obj = { + .id = SWITCHDEV_OBJ_PORT_FDB, + .u.fdb = { + .addr = addr, + .vid = vid, + }, + }; + + return switchdev_port_obj_add(dev, &obj); } -EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_setlink); +EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); /** - * ndo_dflt_netdev_switch_port_bridge_dellink - default ndo bridge dellink - * op for master devices + * switchdev_port_fdb_del - Delete FDB (MAC/VLAN) entry from port * + * @ndmsg: netlink hdr + * @nlattr: netlink attributes * @dev: port device - * @nlh: netlink msg with bridge port attributes - * @flags: bridge dellink flags + * @addr: MAC address to delete + * @vid: VLAN to delete * - * Notify master device slaves of bridge port attribute deletes + * Delete FDB entry from switch device. */ -int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) +int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr, + u16 vid) { - struct net_device *lower_dev; - struct list_head *iter; - int ret = 0, err = 0; + struct switchdev_obj obj = { + .id = SWITCHDEV_OBJ_PORT_FDB, + .u.fdb = { + .addr = addr, + .vid = vid, + }, + }; + + return switchdev_port_obj_del(dev, &obj); +} +EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); + +struct switchdev_fdb_dump { + struct switchdev_obj obj; + struct sk_buff *skb; + struct netlink_callback *cb; + struct net_device *filter_dev; + int idx; +}; + +static int switchdev_port_fdb_dump_cb(struct net_device *dev, + struct switchdev_obj *obj) +{ + struct switchdev_fdb_dump *dump = + container_of(obj, struct switchdev_fdb_dump, obj); + u32 portid = NETLINK_CB(dump->cb->skb).portid; + u32 seq = dump->cb->nlh->nlmsg_seq; + struct nlmsghdr *nlh; + struct ndmsg *ndm; + struct net_device *master = netdev_master_upper_dev_get(dev); + + if (dump->idx < dump->cb->args[0]) + goto skip; + + if (master && dump->filter_dev != master) + goto skip; + + nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, + sizeof(*ndm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = NTF_SELF; + ndm->ndm_type = 0; + ndm->ndm_ifindex = dev->ifindex; + ndm->ndm_state = NUD_REACHABLE; + + if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, obj->u.fdb.addr)) + goto nla_put_failure; + + if (obj->u.fdb.vid && nla_put_u16(dump->skb, NDA_VLAN, obj->u.fdb.vid)) + goto nla_put_failure; + + nlmsg_end(dump->skb, nlh); + +skip: + dump->idx++; + return 0; + +nla_put_failure: + nlmsg_cancel(dump->skb, nlh); + return -EMSGSIZE; +} - if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) - return ret; +/** + * switchdev_port_fdb_dump - Dump port FDB (MAC/VLAN) entries + * + * @skb: netlink skb + * @cb: netlink callback + * @dev: port device + * @filter_dev: filter device + * @idx: + * + * Delete FDB entry from switch device. + */ +int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, + struct net_device *filter_dev, int idx) +{ + struct switchdev_fdb_dump dump = { + .obj = { + .id = SWITCHDEV_OBJ_PORT_FDB, + .cb = switchdev_port_fdb_dump_cb, + }, + .skb = skb, + .cb = cb, + .filter_dev = filter_dev, + .idx = idx, + }; + int err; - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = netdev_switch_port_bridge_dellink(lower_dev, nlh, flags); - if (err && err != -EOPNOTSUPP) - ret = err; - } + err = switchdev_port_obj_dump(dev, &dump.obj); + if (err) + return err; - return ret; + return dump.idx; } -EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_dellink); +EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); -static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev) +static struct net_device *switchdev_get_lowest_dev(struct net_device *dev) { - const struct swdev_ops *ops = dev->swdev_ops; + const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct net_device *port_dev; struct list_head *iter; /* Recusively search down until we find a sw port dev. - * (A sw port dev supports swdev_parent_id_get). + * (A sw port dev supports switchdev_port_attr_get). */ - if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD && - ops && ops->swdev_parent_id_get) + if (ops && ops->switchdev_port_attr_get) return dev; netdev_for_each_lower_dev(dev, lower_dev, iter) { - port_dev = netdev_switch_get_lowest_dev(lower_dev); + port_dev = switchdev_get_lowest_dev(lower_dev); if (port_dev) return port_dev; } @@ -261,10 +764,12 @@ static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev) return NULL; } -static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) +static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) { - struct netdev_phys_item_id psid; - struct netdev_phys_item_id prev_psid; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + }; + struct switchdev_attr prev_attr; struct net_device *dev = NULL; int nhsel; @@ -276,28 +781,29 @@ static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) if (!nh->nh_dev) return NULL; - dev = netdev_switch_get_lowest_dev(nh->nh_dev); + dev = switchdev_get_lowest_dev(nh->nh_dev); if (!dev) return NULL; - if (netdev_switch_parent_id_get(dev, &psid)) + if (switchdev_port_attr_get(dev, &attr)) return NULL; if (nhsel > 0) { - if (prev_psid.id_len != psid.id_len) + if (prev_attr.u.ppid.id_len != attr.u.ppid.id_len) return NULL; - if (memcmp(prev_psid.id, psid.id, psid.id_len)) + if (memcmp(prev_attr.u.ppid.id, attr.u.ppid.id, + attr.u.ppid.id_len)) return NULL; } - prev_psid = psid; + prev_attr = attr; } return dev; } /** - * netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch + * switchdev_fib_ipv4_add - Add/modify switch IPv4 route entry * * @dst: route's IPv4 destination address * @dst_len: destination address length (prefix length) @@ -307,13 +813,24 @@ static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) * @nlflags: netlink flags passed in (NLM_F_*) * @tb_id: route table ID * - * Add IPv4 route entry to switch device. + * Add/modify switch IPv4 route entry. */ -int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 nlflags, u32 tb_id) +int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, u32 tb_id) { + struct switchdev_obj fib_obj = { + .id = SWITCHDEV_OBJ_IPV4_FIB, + .u.ipv4_fib = { + .dst = dst, + .dst_len = dst_len, + .fi = fi, + .tos = tos, + .type = type, + .nlflags = nlflags, + .tb_id = tb_id, + }, + }; struct net_device *dev; - const struct swdev_ops *ops; int err = 0; /* Don't offload route if using custom ip rules or if @@ -328,25 +845,20 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (fi->fib_net->ipv4.fib_offload_disabled) return 0; - dev = netdev_switch_get_dev_by_nhs(fi); + dev = switchdev_get_dev_by_nhs(fi); if (!dev) return 0; - ops = dev->swdev_ops; - - if (ops->swdev_fib_ipv4_add) { - err = ops->swdev_fib_ipv4_add(dev, htonl(dst), dst_len, - fi, tos, type, nlflags, - tb_id); - if (!err) - fi->fib_flags |= RTNH_F_OFFLOAD; - } + + err = switchdev_port_obj_add(dev, &fib_obj); + if (!err) + fi->fib_flags |= RTNH_F_OFFLOAD; return err; } -EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_add); +EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_add); /** - * netdev_switch_fib_ipv4_del - Delete IPv4 route entry from switch + * switchdev_fib_ipv4_del - Delete IPv4 route entry from switch * * @dst: route's IPv4 destination address * @dst_len: destination address length (prefix length) @@ -357,38 +869,45 @@ EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_add); * * Delete IPv4 route entry from switch device. */ -int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) +int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) { + struct switchdev_obj fib_obj = { + .id = SWITCHDEV_OBJ_IPV4_FIB, + .u.ipv4_fib = { + .dst = dst, + .dst_len = dst_len, + .fi = fi, + .tos = tos, + .type = type, + .nlflags = 0, + .tb_id = tb_id, + }, + }; struct net_device *dev; - const struct swdev_ops *ops; int err = 0; if (!(fi->fib_flags & RTNH_F_OFFLOAD)) return 0; - dev = netdev_switch_get_dev_by_nhs(fi); + dev = switchdev_get_dev_by_nhs(fi); if (!dev) return 0; - ops = dev->swdev_ops; - if (ops->swdev_fib_ipv4_del) { - err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len, - fi, tos, type, tb_id); - if (!err) - fi->fib_flags &= ~RTNH_F_OFFLOAD; - } + err = switchdev_port_obj_del(dev, &fib_obj); + if (!err) + fi->fib_flags &= ~RTNH_F_OFFLOAD; return err; } -EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_del); +EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_del); /** - * netdev_switch_fib_ipv4_abort - Abort an IPv4 FIB operation + * switchdev_fib_ipv4_abort - Abort an IPv4 FIB operation * * @fi: route FIB info structure */ -void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +void switchdev_fib_ipv4_abort(struct fib_info *fi) { /* There was a problem installing this route to the offload * device. For now, until we come up with more refined @@ -401,4 +920,4 @@ void netdev_switch_fib_ipv4_abort(struct fib_info *fi) fib_flush_external(fi->fib_net); fi->fib_net->ipv4.fib_offload_disabled = true; } -EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_abort); +EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_abort); diff --git a/net/tipc/addr.c b/net/tipc/addr.c index ba7daa864d44..48fd3b5a73fb 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -38,13 +38,6 @@ #include "addr.h" #include "core.h" -u32 tipc_own_addr(struct net *net) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - - return tn->own_addr; -} - /** * in_own_cluster - test for cluster inclusion; <0.0.0> always matches */ diff --git a/net/tipc/addr.h b/net/tipc/addr.h index 7ba6d5c8ae40..93f7c983be33 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -41,10 +41,18 @@ #include <linux/tipc.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include "core.h" #define TIPC_ZONE_MASK 0xff000000u #define TIPC_CLUSTER_MASK 0xfffff000u +static inline u32 tipc_own_addr(struct net *net) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + + return tn->own_addr; +} + static inline u32 tipc_zone_mask(u32 addr) { return addr & TIPC_ZONE_MASK; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index c5cbdcb1f0b5..4906ca3c0f3a 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -115,19 +115,15 @@ static void bclink_set_last_sent(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_link *bcl = tn->bcl; - struct sk_buff *skb = skb_peek(&bcl->backlogq); - if (skb) - bcl->fsm_msg_cnt = mod(buf_seqno(skb) - 1); - else - bcl->fsm_msg_cnt = mod(bcl->next_out_no - 1); + bcl->silent_intv_cnt = mod(bcl->snd_nxt - 1); } u32 tipc_bclink_get_last_sent(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); - return tn->bcl->fsm_msg_cnt; + return tn->bcl->silent_intv_cnt; } static void bclink_update_last_sent(struct tipc_node *node, u32 seqno) @@ -212,16 +208,16 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) * or both sent and unsent messages (otherwise) */ if (tn->bclink->bcast_nodes.count) - acked = tn->bcl->fsm_msg_cnt; + acked = tn->bcl->silent_intv_cnt; else - acked = tn->bcl->next_out_no; + acked = tn->bcl->snd_nxt; } else { /* * Bail out if specified sequence number does not correspond * to a message that has been sent and not yet acknowledged */ if (less(acked, buf_seqno(skb)) || - less(tn->bcl->fsm_msg_cnt, acked) || + less(tn->bcl->silent_intv_cnt, acked) || less_eq(acked, n_ptr->bclink.acked)) goto exit; } @@ -803,9 +799,9 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) goto attr_msg_full; if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, bcl->next_in_no)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, bcl->rcv_nxt)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, bcl->next_out_no)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, bcl->snd_nxt)) goto attr_msg_full; prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); @@ -866,6 +862,27 @@ int tipc_bclink_set_queue_limits(struct net *net, u32 limit) return 0; } +int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]) +{ + int err; + u32 win; + struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; + + if (!attrs[TIPC_NLA_LINK_PROP]) + return -EINVAL; + + err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP], props); + if (err) + return err; + + if (!props[TIPC_NLA_PROP_WIN]) + return -EOPNOTSUPP; + + win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + + return tipc_bclink_set_queue_limits(net, win); +} + int tipc_bclink_init(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); @@ -893,7 +910,7 @@ int tipc_bclink_init(struct net *net) __skb_queue_head_init(&bcl->backlogq); __skb_queue_head_init(&bcl->deferdq); skb_queue_head_init(&bcl->wakeupq); - bcl->next_out_no = 1; + bcl->snd_nxt = 1; spin_lock_init(&bclink->node.lock); __skb_queue_head_init(&bclink->arrvq); skb_queue_head_init(&bclink->inputq); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 4bdc12277d33..3c290a48f720 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -131,6 +131,7 @@ uint tipc_bclink_get_mtu(void); int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list); void tipc_bclink_wakeup_users(struct net *net); int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg); +int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]); void tipc_bclink_input(struct net *net); #endif diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 70e3dacbf84a..00bc0e620532 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -71,8 +71,7 @@ static const struct nla_policy tipc_nl_media_policy[TIPC_NLA_MEDIA_MAX + 1] = { [TIPC_NLA_MEDIA_PROP] = { .type = NLA_NESTED } }; -static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr, - bool shutting_down); +static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr); /** * tipc_media_find - locates specified media object by name @@ -324,7 +323,7 @@ restart: res = tipc_disc_create(net, b_ptr, &b_ptr->bcast_addr); if (res) { - bearer_disable(net, b_ptr, false); + bearer_disable(net, b_ptr); pr_warn("Bearer <%s> rejected, discovery object creation failed\n", name); return -EINVAL; @@ -344,7 +343,7 @@ restart: static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b_ptr) { pr_info("Resetting bearer <%s>\n", b_ptr->name); - tipc_link_reset_list(net, b_ptr->identity); + tipc_link_delete_list(net, b_ptr->identity); tipc_disc_reset(net, b_ptr); return 0; } @@ -354,8 +353,7 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b_ptr) * * Note: This routine assumes caller holds RTNL lock. */ -static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr, - bool shutting_down) +static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr) { struct tipc_net *tn = net_generic(net, tipc_net_id); u32 i; @@ -363,7 +361,7 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr, pr_info("Disabling bearer <%s>\n", b_ptr->name); b_ptr->media->disable_media(b_ptr); - tipc_link_delete_list(net, b_ptr->identity, shutting_down); + tipc_link_delete_list(net, b_ptr->identity); if (b_ptr->link_req) tipc_disc_delete(b_ptr->link_req); @@ -541,7 +539,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, break; case NETDEV_UNREGISTER: case NETDEV_CHANGENAME: - bearer_disable(dev_net(dev), b_ptr, false); + bearer_disable(dev_net(dev), b_ptr); break; } return NOTIFY_OK; @@ -583,7 +581,7 @@ void tipc_bearer_stop(struct net *net) for (i = 0; i < MAX_BEARERS; i++) { b_ptr = rtnl_dereference(tn->bearer_list[i]); if (b_ptr) { - bearer_disable(net, b_ptr, true); + bearer_disable(net, b_ptr); tn->bearer_list[i] = NULL; } } @@ -747,7 +745,7 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - bearer_disable(net, bearer, false); + bearer_disable(net, bearer); rtnl_unlock(); return 0; @@ -812,7 +810,7 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) char *name; struct tipc_bearer *b; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; - struct net *net = genl_info_net(info); + struct net *net = sock_net(skb->sk); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 5cad243ee8fc..dc714d977768 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -38,9 +38,9 @@ #define _TIPC_BEARER_H #include "netlink.h" +#include "core.h" #include <net/genetlink.h> -#define MAX_BEARERS 2 #define MAX_MEDIA 3 #define MAX_NODES 4096 #define WSIZE 32 diff --git a/net/tipc/core.c b/net/tipc/core.c index be1c9fa60b09..005ba5eb0ea4 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -68,7 +68,7 @@ static int __net_init tipc_init_net(struct net *net) if (err) goto out_nametbl; - err = tipc_subscr_start(net); + err = tipc_topsrv_start(net); if (err) goto out_subscr; return 0; @@ -83,7 +83,7 @@ out_sk_rht: static void __net_exit tipc_exit_net(struct net *net) { - tipc_subscr_stop(net); + tipc_topsrv_stop(net); tipc_net_stop(net); tipc_nametbl_stop(net); tipc_sk_rht_destroy(net); diff --git a/net/tipc/core.h b/net/tipc/core.h index 3dc68c7a966d..0fcf133d5cb7 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -60,16 +60,19 @@ #include <net/netns/generic.h> #include <linux/rhashtable.h> -#include "node.h" -#include "bearer.h" -#include "bcast.h" -#include "netlink.h" -#include "link.h" -#include "node.h" -#include "msg.h" +struct tipc_node; +struct tipc_bearer; +struct tipc_bcbearer; +struct tipc_bclink; +struct tipc_link; +struct tipc_name_table; +struct tipc_server; #define TIPC_MOD_VER "2.0.0" +#define NODE_HTABLE_SIZE 512 +#define MAX_BEARERS 3 + extern int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; @@ -106,6 +109,26 @@ struct tipc_net { atomic_t subscription_count; }; +static inline u16 mod(u16 x) +{ + return x & 0xffffu; +} + +static inline int less_eq(u16 left, u16 right) +{ + return mod(right - left) < 32768u; +} + +static inline int more(u16 left, u16 right) +{ + return !less_eq(left, right); +} + +static inline int less(u16 left, u16 right) +{ + return less_eq(left, right) && (mod(right) != mod(left)); +} + #ifdef CONFIG_SYSCTL int tipc_register_sysctl(void); void tipc_unregister_sysctl(void); diff --git a/net/tipc/link.c b/net/tipc/link.c index 43a515dc97b0..ca8b8e0f49b5 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -86,7 +86,7 @@ static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { */ #define STARTING_EVT 856384768 /* link processing trigger */ #define TRAFFIC_MSG_EVT 560815u /* rx'd ??? */ -#define TIMEOUT_EVT 560817u /* link timer expired */ +#define SILENCE_EVT 560817u /* timer dicovered silence from peer */ /* * State value stored in 'failover_pkts' @@ -106,6 +106,7 @@ static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); static void tipc_link_input(struct tipc_link *l, struct sk_buff *skb); static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb); static bool tipc_link_failover_rcv(struct tipc_link *l, struct sk_buff **skb); +static void link_set_timer(struct tipc_link *link, unsigned long time); /* * Simple link routines */ @@ -197,11 +198,12 @@ static void link_timeout(unsigned long data) } /* do all other link processing performed on a periodic basis */ - link_state_event(l_ptr, TIMEOUT_EVT); - + if (l_ptr->silent_intv_cnt || tipc_bclink_acks_missing(l_ptr->owner)) + link_state_event(l_ptr, SILENCE_EVT); + l_ptr->silent_intv_cnt++; if (skb_queue_len(&l_ptr->backlogq)) tipc_link_push_packets(l_ptr); - + link_set_timer(l_ptr, l_ptr->keepalive_intv); tipc_node_unlock(l_ptr->owner); tipc_link_put(l_ptr); } @@ -233,8 +235,8 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, if (n_ptr->link_cnt >= MAX_BEARERS) { tipc_addr_string_fill(addr_string, n_ptr->addr); - pr_err("Attempt to establish %uth link to %s. Max %u allowed.\n", - n_ptr->link_cnt, addr_string, MAX_BEARERS); + pr_err("Cannot establish %uth link to %s. Max %u allowed.\n", + n_ptr->link_cnt, addr_string, MAX_BEARERS); return NULL; } @@ -261,7 +263,6 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, /* note: peer i/f name is updated by reset/activate message */ memcpy(&l_ptr->media_addr, media_addr, sizeof(*media_addr)); l_ptr->owner = n_ptr; - l_ptr->checkpoint = 1; l_ptr->peer_session = INVALID_SESSION; l_ptr->bearer_id = b_ptr->identity; link_set_supervision_props(l_ptr, b_ptr->tolerance); @@ -280,7 +281,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, l_ptr->mtu = l_ptr->advertised_mtu; l_ptr->priority = b_ptr->priority; tipc_link_set_queue_limits(l_ptr, b_ptr->window); - l_ptr->next_out_no = 1; + l_ptr->snd_nxt = 1; __skb_queue_head_init(&l_ptr->transmq); __skb_queue_head_init(&l_ptr->backlogq); __skb_queue_head_init(&l_ptr->deferdq); @@ -311,8 +312,7 @@ void tipc_link_delete(struct tipc_link *l) tipc_link_put(l); } -void tipc_link_delete_list(struct net *net, unsigned int bearer_id, - bool shutting_down) +void tipc_link_delete_list(struct net *net, unsigned int bearer_id) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_link *link; @@ -451,9 +451,9 @@ void tipc_link_reset(struct tipc_link *l_ptr) if (was_active_link && tipc_node_is_up(l_ptr->owner) && (pl != l_ptr)) { l_ptr->flags |= LINK_FAILINGOVER; - l_ptr->failover_checkpt = l_ptr->next_in_no; + l_ptr->failover_checkpt = l_ptr->rcv_nxt; pl->failover_pkts = FIRST_FAILOVER; - pl->failover_checkpt = l_ptr->next_in_no; + pl->failover_checkpt = l_ptr->rcv_nxt; pl->failover_skb = l_ptr->reasm_buf; } else { kfree_skb(l_ptr->reasm_buf); @@ -469,36 +469,19 @@ void tipc_link_reset(struct tipc_link *l_ptr) tipc_link_purge_backlog(l_ptr); l_ptr->reasm_buf = NULL; l_ptr->rcv_unacked = 0; - l_ptr->checkpoint = 1; - l_ptr->next_out_no = 1; - l_ptr->fsm_msg_cnt = 0; + l_ptr->snd_nxt = 1; + l_ptr->silent_intv_cnt = 0; l_ptr->stale_count = 0; link_reset_statistics(l_ptr); } -void tipc_link_reset_list(struct net *net, unsigned int bearer_id) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_link *l_ptr; - struct tipc_node *n_ptr; - - rcu_read_lock(); - list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { - tipc_node_lock(n_ptr); - l_ptr = n_ptr->links[bearer_id]; - if (l_ptr) - tipc_link_reset(l_ptr); - tipc_node_unlock(n_ptr); - } - rcu_read_unlock(); -} - static void link_activate(struct tipc_link *link) { struct tipc_node *node = link->owner; - link->next_in_no = 1; + link->rcv_nxt = 1; link->stats.recv_info = 1; + link->silent_intv_cnt = 0; tipc_node_link_up(node, link); tipc_bearer_add_dest(node->net, link->bearer_id, link->addr); } @@ -511,7 +494,7 @@ static void link_activate(struct tipc_link *link) static void link_state_event(struct tipc_link *l_ptr, unsigned int event) { struct tipc_link *other; - unsigned long cont_intv = l_ptr->cont_intv; + unsigned long timer_intv = l_ptr->keepalive_intv; if (l_ptr->flags & LINK_STOPPED) return; @@ -519,45 +502,33 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT)) return; /* Not yet. */ - if (l_ptr->flags & LINK_FAILINGOVER) { - if (event == TIMEOUT_EVT) - link_set_timer(l_ptr, cont_intv); + if (l_ptr->flags & LINK_FAILINGOVER) return; - } switch (l_ptr->state) { case WORKING_WORKING: switch (event) { case TRAFFIC_MSG_EVT: case ACTIVATE_MSG: + l_ptr->silent_intv_cnt = 0; break; - case TIMEOUT_EVT: - if (l_ptr->next_in_no != l_ptr->checkpoint) { - l_ptr->checkpoint = l_ptr->next_in_no; - if (tipc_bclink_acks_missing(l_ptr->owner)) { + case SILENCE_EVT: + if (!l_ptr->silent_intv_cnt) { + if (tipc_bclink_acks_missing(l_ptr->owner)) tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - } - link_set_timer(l_ptr, cont_intv); break; } l_ptr->state = WORKING_UNKNOWN; - l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv / 4); break; case RESET_MSG: pr_debug("%s<%s>, requested by peer\n", link_rst_msg, l_ptr->name); tipc_link_reset(l_ptr); l_ptr->state = RESET_RESET; - l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv); break; default: pr_debug("%s%u in WW state\n", link_unk_evt, event); @@ -568,46 +539,33 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) case TRAFFIC_MSG_EVT: case ACTIVATE_MSG: l_ptr->state = WORKING_WORKING; - l_ptr->fsm_msg_cnt = 0; - link_set_timer(l_ptr, cont_intv); + l_ptr->silent_intv_cnt = 0; break; case RESET_MSG: pr_debug("%s<%s>, requested by peer while probing\n", link_rst_msg, l_ptr->name); tipc_link_reset(l_ptr); l_ptr->state = RESET_RESET; - l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv); break; - case TIMEOUT_EVT: - if (l_ptr->next_in_no != l_ptr->checkpoint) { + case SILENCE_EVT: + if (!l_ptr->silent_intv_cnt) { l_ptr->state = WORKING_WORKING; - l_ptr->fsm_msg_cnt = 0; - l_ptr->checkpoint = l_ptr->next_in_no; - if (tipc_bclink_acks_missing(l_ptr->owner)) { + if (tipc_bclink_acks_missing(l_ptr->owner)) tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - } - link_set_timer(l_ptr, cont_intv); - } else if (l_ptr->fsm_msg_cnt < l_ptr->abort_limit) { + } else if (l_ptr->silent_intv_cnt < + l_ptr->abort_limit) { tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv / 4); } else { /* Link has failed */ pr_debug("%s<%s>, peer not responding\n", link_rst_msg, l_ptr->name); tipc_link_reset(l_ptr); l_ptr->state = RESET_UNKNOWN; - l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv); } break; default: @@ -623,31 +581,22 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) if (other && link_working_unknown(other)) break; l_ptr->state = WORKING_WORKING; - l_ptr->fsm_msg_cnt = 0; link_activate(l_ptr); tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - l_ptr->fsm_msg_cnt++; if (l_ptr->owner->working_links == 1) tipc_link_sync_xmit(l_ptr); - link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: l_ptr->state = RESET_RESET; - l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, 1, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv); break; case STARTING_EVT: l_ptr->flags |= LINK_STARTED; - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv); + link_set_timer(l_ptr, timer_intv); break; - case TIMEOUT_EVT: + case SILENCE_EVT: tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv); break; default: pr_err("%s%u in RU state\n", link_unk_evt, event); @@ -661,21 +610,16 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) if (other && link_working_unknown(other)) break; l_ptr->state = WORKING_WORKING; - l_ptr->fsm_msg_cnt = 0; link_activate(l_ptr); tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - l_ptr->fsm_msg_cnt++; if (l_ptr->owner->working_links == 1) tipc_link_sync_xmit(l_ptr); - link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: break; - case TIMEOUT_EVT: + case SILENCE_EVT: tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - link_set_timer(l_ptr, cont_intv); break; default: pr_err("%s%u in RR state\n", link_unk_evt, event); @@ -701,53 +645,58 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, { struct tipc_msg *msg = buf_msg(skb_peek(list)); unsigned int maxwin = link->window; - unsigned int imp = msg_importance(msg); + unsigned int i, imp = msg_importance(msg); uint mtu = link->mtu; - uint ack = mod(link->next_in_no - 1); - uint seqno = link->next_out_no; - uint bc_last_in = link->owner->bclink.last_in; + u16 ack = mod(link->rcv_nxt - 1); + u16 seqno = link->snd_nxt; + u16 bc_last_in = link->owner->bclink.last_in; struct tipc_media_addr *addr = &link->media_addr; struct sk_buff_head *transmq = &link->transmq; struct sk_buff_head *backlogq = &link->backlogq; - struct sk_buff *skb, *tmp; - - /* Match backlog limit against msg importance: */ - if (unlikely(link->backlog[imp].len >= link->backlog[imp].limit)) - return link_schedule_user(link, list); + struct sk_buff *skb, *bskb; + /* Match msg importance against this and all higher backlog limits: */ + for (i = imp; i <= TIPC_SYSTEM_IMPORTANCE; i++) { + if (unlikely(link->backlog[i].len >= link->backlog[i].limit)) + return link_schedule_user(link, list); + } if (unlikely(msg_size(msg) > mtu)) { __skb_queue_purge(list); return -EMSGSIZE; } /* Prepare each packet for sending, and add to relevant queue: */ - skb_queue_walk_safe(list, skb, tmp) { - __skb_unlink(skb, list); + while (skb_queue_len(list)) { + skb = skb_peek(list); msg = buf_msg(skb); msg_set_seqno(msg, seqno); msg_set_ack(msg, ack); msg_set_bcast_ack(msg, bc_last_in); if (likely(skb_queue_len(transmq) < maxwin)) { + __skb_dequeue(list); __skb_queue_tail(transmq, skb); tipc_bearer_send(net, link->bearer_id, skb, addr); link->rcv_unacked = 0; seqno++; continue; } - if (tipc_msg_bundle(skb_peek_tail(backlogq), skb, mtu)) { + if (tipc_msg_bundle(skb_peek_tail(backlogq), msg, mtu)) { + kfree_skb(__skb_dequeue(list)); link->stats.sent_bundled++; continue; } - if (tipc_msg_make_bundle(&skb, mtu, link->addr)) { + if (tipc_msg_make_bundle(&bskb, msg, mtu, link->addr)) { + kfree_skb(__skb_dequeue(list)); + __skb_queue_tail(backlogq, bskb); + link->backlog[msg_importance(buf_msg(bskb))].len++; link->stats.sent_bundled++; link->stats.sent_bundles++; - imp = msg_importance(buf_msg(skb)); + continue; } - __skb_queue_tail(backlogq, skb); - link->backlog[imp].len++; - seqno++; + link->backlog[imp].len += skb_queue_len(list); + skb_queue_splice_tail_init(list, backlogq); } - link->next_out_no = seqno; + link->snd_nxt = seqno; return 0; } @@ -877,7 +826,8 @@ void tipc_link_push_packets(struct tipc_link *link) { struct sk_buff *skb; struct tipc_msg *msg; - unsigned int ack = mod(link->next_in_no - 1); + u16 seqno = link->snd_nxt; + u16 ack = mod(link->rcv_nxt - 1); while (skb_queue_len(&link->transmq) < link->window) { skb = __skb_dequeue(&link->backlogq); @@ -886,12 +836,15 @@ void tipc_link_push_packets(struct tipc_link *link) msg = buf_msg(skb); link->backlog[msg_importance(msg)].len--; msg_set_ack(msg, ack); + msg_set_seqno(msg, seqno); + seqno = mod(seqno + 1); msg_set_bcast_ack(msg, link->owner->bclink.last_in); link->rcv_unacked = 0; __skb_queue_tail(&link->transmq, skb); tipc_bearer_send(link->owner->net, link->bearer_id, skb, &link->media_addr); } + link->snd_nxt = seqno; } void tipc_link_reset_all(struct tipc_node *node) @@ -964,13 +917,13 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, msg = buf_msg(skb); /* Detect repeated retransmit failures */ - if (l_ptr->last_retransmitted == msg_seqno(msg)) { + if (l_ptr->last_retransm == msg_seqno(msg)) { if (++l_ptr->stale_count > 100) { link_retransmit_failure(l_ptr, skb); return; } } else { - l_ptr->last_retransmitted = msg_seqno(msg); + l_ptr->last_retransm = msg_seqno(msg); l_ptr->stale_count = 1; } @@ -978,7 +931,7 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, if (!retransmits) break; msg = buf_msg(skb); - msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); + msg_set_ack(msg, mod(l_ptr->rcv_nxt - 1)); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, skb, &l_ptr->media_addr); @@ -1001,11 +954,11 @@ static bool link_synch(struct tipc_link *l) goto synched; /* Was last pre-synch packet added to input queue ? */ - if (less_eq(pl->next_in_no, l->synch_point)) + if (less_eq(pl->rcv_nxt, l->synch_point)) return false; /* Is it still in the input queue ? */ - post_synch = mod(pl->next_in_no - l->synch_point) - 1; + post_synch = mod(pl->rcv_nxt - l->synch_point) - 1; if (skb_queue_len(&pl->inputq) > post_synch) return false; synched: @@ -1016,13 +969,13 @@ synched: static void link_retrieve_defq(struct tipc_link *link, struct sk_buff_head *list) { - u32 seq_no; + u16 seq_no; if (skb_queue_empty(&link->deferdq)) return; seq_no = buf_seqno(skb_peek(&link->deferdq)); - if (seq_no == mod(link->next_in_no)) + if (seq_no == link->rcv_nxt) skb_queue_splice_tail_init(&link->deferdq, list); } @@ -1043,8 +996,8 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) struct tipc_link *l_ptr; struct sk_buff *skb1, *tmp; struct tipc_msg *msg; - u32 seq_no; - u32 ackd; + u16 seq_no; + u16 ackd; u32 released; skb2list(skb, &head); @@ -1137,18 +1090,20 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) } /* Link is now in state WORKING_WORKING */ - if (unlikely(seq_no != mod(l_ptr->next_in_no))) { + if (unlikely(seq_no != l_ptr->rcv_nxt)) { link_handle_out_of_seq_msg(l_ptr, skb); link_retrieve_defq(l_ptr, &head); skb = NULL; goto unlock; } + l_ptr->silent_intv_cnt = 0; + /* Synchronize with parallel link if applicable */ if (unlikely((l_ptr->flags & LINK_SYNCHING) && !msg_dup(msg))) { if (!link_synch(l_ptr)) goto unlock; } - l_ptr->next_in_no++; + l_ptr->rcv_nxt++; if (unlikely(!skb_queue_empty(&l_ptr->deferdq))) link_retrieve_defq(l_ptr, &head); if (unlikely(++l_ptr->rcv_unacked >= TIPC_MIN_LINK_WIN)) { @@ -1268,7 +1223,7 @@ static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb) u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *skb) { struct sk_buff *skb1; - u32 seq_no = buf_seqno(skb); + u16 seq_no = buf_seqno(skb); /* Empty queue ? */ if (skb_queue_empty(list)) { @@ -1284,7 +1239,7 @@ u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *skb) /* Locate insertion point in queue, then insert; discard if duplicate */ skb_queue_walk(list, skb1) { - u32 curr_seqno = buf_seqno(skb1); + u16 curr_seqno = buf_seqno(skb1); if (seq_no == curr_seqno) { kfree_skb(skb); @@ -1312,14 +1267,14 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, return; } - /* Record OOS packet arrival (force mismatch on next timeout) */ - l_ptr->checkpoint--; + /* Record OOS packet arrival */ + l_ptr->silent_intv_cnt = 0; /* * Discard packet if a duplicate; otherwise add it to deferred queue * and notify peer of gap as per protocol specification */ - if (less(seq_no, mod(l_ptr->next_in_no))) { + if (less(seq_no, l_ptr->rcv_nxt)) { l_ptr->stats.duplicates++; kfree_skb(buf); return; @@ -1344,6 +1299,7 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, struct tipc_msg *msg = l_ptr->pmsg; u32 msg_size = sizeof(l_ptr->proto_msg); int r_flag; + u16 last_rcv; /* Don't send protocol message during link failover */ if (l_ptr->flags & LINK_FAILINGOVER) @@ -1360,16 +1316,14 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, msg_set_last_bcast(msg, tipc_bclink_get_last_sent(l_ptr->owner->net)); if (msg_typ == STATE_MSG) { - u32 next_sent = mod(l_ptr->next_out_no); + u16 next_sent = l_ptr->snd_nxt; if (!tipc_link_is_up(l_ptr)) return; - if (skb_queue_len(&l_ptr->backlogq)) - next_sent = buf_seqno(skb_peek(&l_ptr->backlogq)); msg_set_next_sent(msg, next_sent); if (!skb_queue_empty(&l_ptr->deferdq)) { - u32 rec = buf_seqno(skb_peek(&l_ptr->deferdq)); - gap = mod(rec - mod(l_ptr->next_in_no)); + last_rcv = buf_seqno(skb_peek(&l_ptr->deferdq)); + gap = mod(last_rcv - l_ptr->rcv_nxt); } msg_set_seq_gap(msg, gap); if (gap) @@ -1377,7 +1331,7 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, msg_set_link_tolerance(msg, tolerance); msg_set_linkprio(msg, priority); msg_set_max_pkt(msg, l_ptr->mtu); - msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); + msg_set_ack(msg, mod(l_ptr->rcv_nxt - 1)); msg_set_probe(msg, probe_msg != 0); if (probe_msg) l_ptr->stats.sent_probes++; @@ -1397,7 +1351,7 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, msg_set_linkprio(msg, l_ptr->priority); msg_set_size(msg, msg_size); - msg_set_seqno(msg, mod(l_ptr->next_out_no + (0xffff/2))); + msg_set_seqno(msg, mod(l_ptr->snd_nxt + (0xffff / 2))); buf = tipc_buf_acquire(msg_size); if (!buf) @@ -1496,17 +1450,15 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, } /* Record reception; force mismatch at next timeout: */ - l_ptr->checkpoint--; + l_ptr->silent_intv_cnt = 0; link_state_event(l_ptr, TRAFFIC_MSG_EVT); l_ptr->stats.recv_states++; if (link_reset_unknown(l_ptr)) break; - if (less_eq(mod(l_ptr->next_in_no), msg_next_sent(msg))) { - rec_gap = mod(msg_next_sent(msg) - - mod(l_ptr->next_in_no)); - } + if (less_eq(l_ptr->rcv_nxt, msg_next_sent(msg))) + rec_gap = mod(msg_next_sent(msg) - l_ptr->rcv_nxt); if (msg_probe(msg)) l_ptr->stats.recv_probes++; @@ -1580,6 +1532,11 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, TUNNEL_PROTOCOL, FAILOVER_MSG, INT_H_SIZE, l_ptr->addr); + + skb_queue_walk(&l_ptr->backlogq, skb) { + msg_set_seqno(buf_msg(skb), l_ptr->snd_nxt); + l_ptr->snd_nxt = mod(l_ptr->snd_nxt + 1); + } skb_queue_splice_tail_init(&l_ptr->backlogq, &l_ptr->transmq); tipc_link_purge_backlog(l_ptr); msgcount = skb_queue_len(&l_ptr->transmq); @@ -1640,6 +1597,7 @@ void tipc_link_dup_queue_xmit(struct tipc_link *link, struct tipc_msg tnl_hdr; struct sk_buff_head *queue = &link->transmq; int mcnt; + u16 seqno; tipc_msg_init(link_own_addr(link), &tnl_hdr, TUNNEL_PROTOCOL, SYNCH_MSG, INT_H_SIZE, link->addr); @@ -1653,7 +1611,7 @@ tunnel_queue: struct tipc_msg *msg = buf_msg(skb); u32 len = msg_size(msg); - msg_set_ack(msg, mod(link->next_in_no - 1)); + msg_set_ack(msg, mod(link->rcv_nxt - 1)); msg_set_bcast_ack(msg, link->owner->bclink.last_in); msg_set_size(&tnl_hdr, len + INT_H_SIZE); outskb = tipc_buf_acquire(len + INT_H_SIZE); @@ -1671,6 +1629,11 @@ tunnel_queue: } if (queue == &link->backlogq) return; + seqno = link->snd_nxt; + skb_queue_walk(&link->backlogq, skb) { + msg_set_seqno(buf_msg(skb), seqno); + seqno = mod(seqno + 1); + } queue = &link->backlogq; goto tunnel_queue; } @@ -1742,8 +1705,8 @@ static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol) return; l_ptr->tolerance = tol; - l_ptr->cont_intv = msecs_to_jiffies(intv); - l_ptr->abort_limit = tol / (jiffies_to_msecs(l_ptr->cont_intv) / 4); + l_ptr->keepalive_intv = msecs_to_jiffies(intv); + l_ptr->abort_limit = tol / (jiffies_to_msecs(l_ptr->keepalive_intv)); } void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) @@ -1803,8 +1766,8 @@ static struct tipc_node *tipc_link_find_owner(struct net *net, static void link_reset_statistics(struct tipc_link *l_ptr) { memset(&l_ptr->stats, 0, sizeof(l_ptr->stats)); - l_ptr->stats.sent_info = l_ptr->next_out_no; - l_ptr->stats.recv_info = l_ptr->next_in_no; + l_ptr->stats.sent_info = l_ptr->snd_nxt; + l_ptr->stats.recv_info = l_ptr->rcv_nxt; } static void link_print(struct tipc_link *l_ptr, const char *str) @@ -1893,6 +1856,9 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_LINK_NAME]); + if (strcmp(name, tipc_bclink_name) == 0) + return tipc_nl_bc_link_set(net, attrs); + node = tipc_link_find_owner(net, name, &bearer_id); if (!node) return -EINVAL; @@ -2034,9 +2000,9 @@ static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->next_in_no)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->rcv_nxt)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->next_out_no)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->snd_nxt)) goto attr_msg_full; if (tipc_link_is_up(link)) @@ -2175,50 +2141,53 @@ out: int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); - struct sk_buff *ans_skb; struct tipc_nl_msg msg; - struct tipc_link *link; - struct tipc_node *node; char *name; - int bearer_id; int err; + msg.portid = info->snd_portid; + msg.seq = info->snd_seq; + if (!info->attrs[TIPC_NLA_LINK_NAME]) return -EINVAL; - name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]); - node = tipc_link_find_owner(net, name, &bearer_id); - if (!node) - return -EINVAL; - ans_skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); - if (!ans_skb) + msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg.skb) return -ENOMEM; - msg.skb = ans_skb; - msg.portid = info->snd_portid; - msg.seq = info->snd_seq; - - tipc_node_lock(node); - link = node->links[bearer_id]; - if (!link) { - err = -EINVAL; - goto err_out; - } - - err = __tipc_nl_add_link(net, &msg, link, 0); - if (err) - goto err_out; + if (strcmp(name, tipc_bclink_name) == 0) { + err = tipc_nl_add_bc_link(net, &msg); + if (err) { + nlmsg_free(msg.skb); + return err; + } + } else { + int bearer_id; + struct tipc_node *node; + struct tipc_link *link; - tipc_node_unlock(node); + node = tipc_link_find_owner(net, name, &bearer_id); + if (!node) + return -EINVAL; - return genlmsg_reply(ans_skb, info); + tipc_node_lock(node); + link = node->links[bearer_id]; + if (!link) { + tipc_node_unlock(node); + nlmsg_free(msg.skb); + return -EINVAL; + } -err_out: - tipc_node_unlock(node); - nlmsg_free(ans_skb); + err = __tipc_nl_add_link(net, &msg, link, 0); + tipc_node_unlock(node); + if (err) { + nlmsg_free(msg.skb); + return err; + } + } - return err; + return genlmsg_reply(msg.skb, info); } int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info) diff --git a/net/tipc/link.h b/net/tipc/link.h index b5b4e3554d4e..0c02c973e985 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -107,30 +107,29 @@ struct tipc_stats { * @owner: pointer to peer node * @refcnt: reference counter for permanent references (owner node & timer) * @flags: execution state flags for link endpoint instance - * @checkpoint: reference point for triggering link continuity checking * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link * @tolerance: minimum link continuity loss needed to reset link [in ms] - * @cont_intv: link continuity testing interval + * @keepalive_intv: link keepalive timer interval * @abort_limit: # of unacknowledged continuity probes needed to reset link * @state: current state of link FSM - * @fsm_msg_cnt: # of protocol messages link FSM has sent in current state + * @silent_intv_cnt: # of timer intervals without any reception from peer * @proto_msg: template for control messages generated by link * @pmsg: convenience pointer to "proto_msg" field * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') * @backlog_limit: backlog queue congestion thresholds (indexed by importance) * @exp_msg_count: # of tunnelled messages expected during link changeover - * @reset_checkpoint: seq # of last acknowledged message at time of link reset + * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset * @mtu: current maximum packet size for this link * @advertised_mtu: advertised own mtu when link is being established * @transmitq: queue for sent, non-acked messages * @backlogq: queue for messages waiting to be sent - * @next_out_no: next sequence number to use for outbound messages + * @snt_nxt: next sequence number to use for outbound messages * @last_retransmitted: sequence number of most recently retransmitted message * @stale_count: # of identical retransmit requests made by peer - * @next_in_no: next sequence number to expect for inbound messages + * @rcv_nxt: next sequence number to expect for inbound messages * @deferred_queue: deferred queue saved OOS b'cast message received from node * @unacked_window: # of inbound messages rx'd without ack'ing back to peer * @inputq: buffer queue for messages to be delivered upwards @@ -151,15 +150,14 @@ struct tipc_link { /* Management and link supervision data */ unsigned int flags; - u32 checkpoint; u32 peer_session; u32 peer_bearer_id; u32 bearer_id; u32 tolerance; - unsigned long cont_intv; + unsigned long keepalive_intv; u32 abort_limit; int state; - u32 fsm_msg_cnt; + u32 silent_intv_cnt; struct { unchar hdr[INT_H_SIZE]; unchar body[TIPC_MAX_IF_NAME]; @@ -185,13 +183,13 @@ struct tipc_link { u16 len; u16 limit; } backlog[5]; - u32 next_out_no; + u16 snd_nxt; + u16 last_retransm; u32 window; - u32 last_retransmitted; u32 stale_count; /* Reception */ - u32 next_in_no; + u16 rcv_nxt; u32 rcv_unacked; struct sk_buff_head deferdq; struct sk_buff_head inputq; @@ -213,8 +211,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, const struct tipc_media_addr *media_addr); void tipc_link_delete(struct tipc_link *link); -void tipc_link_delete_list(struct net *net, unsigned int bearer_id, - bool shutting_down); +void tipc_link_delete_list(struct net *net, unsigned int bearer_id); void tipc_link_failover_send_queue(struct tipc_link *l_ptr); void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest); void tipc_link_reset_fragments(struct tipc_link *l_ptr); @@ -223,7 +220,6 @@ int tipc_link_is_active(struct tipc_link *l_ptr); void tipc_link_purge_queues(struct tipc_link *l_ptr); void tipc_link_reset_all(struct tipc_node *node); void tipc_link_reset(struct tipc_link *l_ptr); -void tipc_link_reset_list(struct net *net, unsigned int bearer_id); int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, u32 selector); int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest, @@ -247,39 +243,6 @@ int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info); int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]); void link_prepare_wakeup(struct tipc_link *l); -/* - * Link sequence number manipulation routines (uses modulo 2**16 arithmetic) - */ -static inline u32 buf_seqno(struct sk_buff *buf) -{ - return msg_seqno(buf_msg(buf)); -} - -static inline u32 mod(u32 x) -{ - return x & 0xffffu; -} - -static inline int less_eq(u32 left, u32 right) -{ - return mod(right - left) < 32768u; -} - -static inline int more(u32 left, u32 right) -{ - return !less_eq(left, right); -} - -static inline int less(u32 left, u32 right) -{ - return less_eq(left, right) && (mod(right) != mod(left)); -} - -static inline u32 lesser(u32 left, u32 right) -{ - return less_eq(left, right) ? left : right; -} - static inline u32 link_own_addr(struct tipc_link *l) { return msg_prevnode(l->pmsg); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index c3e96e815418..08b4cc7d496d 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -331,16 +331,15 @@ error: /** * tipc_msg_bundle(): Append contents of a buffer to tail of an existing one - * @bskb: the buffer to append to ("bundle") - * @skb: buffer to be appended + * @skb: the buffer to append to ("bundle") + * @msg: message to be appended * @mtu: max allowable size for the bundle buffer * Consumes buffer if successful * Returns true if bundling could be performed, otherwise false */ -bool tipc_msg_bundle(struct sk_buff *bskb, struct sk_buff *skb, u32 mtu) +bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu) { struct tipc_msg *bmsg; - struct tipc_msg *msg = buf_msg(skb); unsigned int bsz; unsigned int msz = msg_size(msg); u32 start, pad; @@ -348,9 +347,9 @@ bool tipc_msg_bundle(struct sk_buff *bskb, struct sk_buff *skb, u32 mtu) if (likely(msg_user(msg) == MSG_FRAGMENTER)) return false; - if (!bskb) + if (!skb) return false; - bmsg = buf_msg(bskb); + bmsg = buf_msg(skb); bsz = msg_size(bmsg); start = align(bsz); pad = start - bsz; @@ -359,18 +358,20 @@ bool tipc_msg_bundle(struct sk_buff *bskb, struct sk_buff *skb, u32 mtu) return false; if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) return false; - if (likely(msg_user(bmsg) != MSG_BUNDLER)) + if (unlikely(msg_user(bmsg) != MSG_BUNDLER)) return false; - if (unlikely(skb_tailroom(bskb) < (pad + msz))) + if (unlikely(skb_tailroom(skb) < (pad + msz))) return false; if (unlikely(max < (start + msz))) return false; + if ((msg_importance(msg) < TIPC_SYSTEM_IMPORTANCE) && + (msg_importance(bmsg) == TIPC_SYSTEM_IMPORTANCE)) + return false; - skb_put(bskb, pad + msz); - skb_copy_to_linear_data_offset(bskb, start, skb->data, msz); + skb_put(skb, pad + msz); + skb_copy_to_linear_data_offset(skb, start, msg, msz); msg_set_size(bmsg, start + msz); msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1); - kfree_skb(skb); return true; } @@ -416,18 +417,18 @@ none: /** * tipc_msg_make_bundle(): Create bundle buf and append message to its tail - * @list: the buffer chain - * @skb: buffer to be appended and replaced + * @list: the buffer chain, where head is the buffer to replace/append + * @skb: buffer to be created, appended to and returned in case of success + * @msg: message to be appended * @mtu: max allowable size for the bundle buffer, inclusive header * @dnode: destination node for message. (Not always present in header) - * Replaces buffer if successful * Returns true if success, otherwise false */ -bool tipc_msg_make_bundle(struct sk_buff **skb, u32 mtu, u32 dnode) +bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, + u32 mtu, u32 dnode) { - struct sk_buff *bskb; + struct sk_buff *_skb; struct tipc_msg *bmsg; - struct tipc_msg *msg = buf_msg(*skb); u32 msz = msg_size(msg); u32 max = mtu - INT_H_SIZE; @@ -440,19 +441,23 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, u32 mtu, u32 dnode) if (msz > (max / 2)) return false; - bskb = tipc_buf_acquire(max); - if (!bskb) + _skb = tipc_buf_acquire(max); + if (!_skb) return false; - skb_trim(bskb, INT_H_SIZE); - bmsg = buf_msg(bskb); + skb_trim(_skb, INT_H_SIZE); + bmsg = buf_msg(_skb); tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0, INT_H_SIZE, dnode); + if (msg_isdata(msg)) + msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE); + else + msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE); msg_set_seqno(bmsg, msg_seqno(msg)); msg_set_ack(bmsg, msg_ack(msg)); msg_set_bcast_ack(bmsg, msg_bcast_ack(msg)); - tipc_msg_bundle(bskb, *skb, mtu); - *skb = bskb; + tipc_msg_bundle(_skb, msg, mtu); + *skb = _skb; return true; } diff --git a/net/tipc/msg.h b/net/tipc/msg.h index e1d3595e2ee9..19c45fb66238 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -313,12 +313,12 @@ static inline void msg_set_lookup_scope(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 19, 0x3, n); } -static inline u32 msg_bcast_ack(struct tipc_msg *m) +static inline u16 msg_bcast_ack(struct tipc_msg *m) { return msg_bits(m, 1, 0, 0xffff); } -static inline void msg_set_bcast_ack(struct tipc_msg *m, u32 n) +static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n) { msg_set_bits(m, 1, 0, 0xffff, n); } @@ -327,22 +327,22 @@ static inline void msg_set_bcast_ack(struct tipc_msg *m, u32 n) /* * Word 2 */ -static inline u32 msg_ack(struct tipc_msg *m) +static inline u16 msg_ack(struct tipc_msg *m) { return msg_bits(m, 2, 16, 0xffff); } -static inline void msg_set_ack(struct tipc_msg *m, u32 n) +static inline void msg_set_ack(struct tipc_msg *m, u16 n) { msg_set_bits(m, 2, 16, 0xffff, n); } -static inline u32 msg_seqno(struct tipc_msg *m) +static inline u16 msg_seqno(struct tipc_msg *m) { return msg_bits(m, 2, 0, 0xffff); } -static inline void msg_set_seqno(struct tipc_msg *m, u32 n) +static inline void msg_set_seqno(struct tipc_msg *m, u16 n) { msg_set_bits(m, 2, 0, 0xffff, n); } @@ -352,18 +352,22 @@ static inline void msg_set_seqno(struct tipc_msg *m, u32 n) */ static inline u32 msg_importance(struct tipc_msg *m) { - if (unlikely(msg_user(m) == MSG_FRAGMENTER)) + int usr = msg_user(m); + + if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m))) + return usr; + if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)) return msg_bits(m, 5, 13, 0x7); - if (likely(msg_isdata(m) && !msg_errcode(m))) - return msg_user(m); return TIPC_SYSTEM_IMPORTANCE; } static inline void msg_set_importance(struct tipc_msg *m, u32 i) { - if (unlikely(msg_user(m) == MSG_FRAGMENTER)) + int usr = msg_user(m); + + if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))) msg_set_bits(m, 5, 13, 0x7, i); - else if (likely(i < TIPC_SYSTEM_IMPORTANCE)) + else if (i < TIPC_SYSTEM_IMPORTANCE) msg_set_user(m, i); else pr_warn("Trying to set illegal importance in message\n"); @@ -772,9 +776,9 @@ struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, uint data_sz, u32 dnode, u32 onode, u32 dport, u32 oport, int errcode); int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf); -bool tipc_msg_bundle(struct sk_buff *bskb, struct sk_buff *skb, u32 mtu); - -bool tipc_msg_make_bundle(struct sk_buff **skb, u32 mtu, u32 dnode); +bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu); +bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, + u32 mtu, u32 dnode); bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); @@ -782,6 +786,11 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, u32 *dnode, int *err); struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list); +static inline u16 buf_seqno(struct sk_buff *skb) +{ + return msg_seqno(buf_msg(skb)); +} + /* tipc_skb_peek(): peek and reserve first buffer in list * @list: list to be peeked in * Returns pointer to first buffer in list, if any diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index ab0ac62a1287..0f47f08bf38f 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -330,13 +330,9 @@ static struct publication *tipc_nameseq_insert_publ(struct net *net, /* Any subscriptions waiting for notification? */ list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { - tipc_subscr_report_overlap(s, - publ->lower, - publ->upper, - TIPC_PUBLISHED, - publ->ref, - publ->node, - created_subseq); + tipc_subscrp_report_overlap(s, publ->lower, publ->upper, + TIPC_PUBLISHED, publ->ref, + publ->node, created_subseq); } return publ; } @@ -404,13 +400,9 @@ found: /* Notify any waiting subscriptions */ list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { - tipc_subscr_report_overlap(s, - publ->lower, - publ->upper, - TIPC_WITHDRAWN, - publ->ref, - publ->node, - removed_subseq); + tipc_subscrp_report_overlap(s, publ->lower, publ->upper, + TIPC_WITHDRAWN, publ->ref, + publ->node, removed_subseq); } return publ; @@ -432,19 +424,17 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq, return; while (sseq != &nseq->sseqs[nseq->first_free]) { - if (tipc_subscr_overlap(s, sseq->lower, sseq->upper)) { + if (tipc_subscrp_check_overlap(s, sseq->lower, sseq->upper)) { struct publication *crs; struct name_info *info = sseq->info; int must_report = 1; list_for_each_entry(crs, &info->zone_list, zone_list) { - tipc_subscr_report_overlap(s, - sseq->lower, - sseq->upper, - TIPC_PUBLISHED, - crs->ref, - crs->node, - must_report); + tipc_subscrp_report_overlap(s, sseq->lower, + sseq->upper, + TIPC_PUBLISHED, + crs->ref, crs->node, + must_report); must_report = 0; } } diff --git a/net/tipc/net.c b/net/tipc/net.c index a54f3cbe2246..d6d1399ae229 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -40,6 +40,7 @@ #include "subscr.h" #include "socket.h" #include "node.h" +#include "bcast.h" static const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { [TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC }, diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index ce9121e8e990..53e0fee80086 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -55,6 +55,7 @@ struct tipc_nl_compat_msg { int rep_type; int rep_size; int req_type; + struct net *net; struct sk_buff *rep; struct tlv_desc *req; struct sock *dst_sk; @@ -68,7 +69,8 @@ struct tipc_nl_compat_cmd_dump { struct tipc_nl_compat_cmd_doit { int (*doit)(struct sk_buff *skb, struct genl_info *info); - int (*transcode)(struct sk_buff *skb, struct tipc_nl_compat_msg *msg); + int (*transcode)(struct tipc_nl_compat_cmd_doit *cmd, + struct sk_buff *skb, struct tipc_nl_compat_msg *msg); }; static int tipc_skb_tailroom(struct sk_buff *skb) @@ -281,7 +283,7 @@ static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd, if (!trans_buf) return -ENOMEM; - err = (*cmd->transcode)(trans_buf, msg); + err = (*cmd->transcode)(cmd, trans_buf, msg); if (err) goto trans_out; @@ -353,7 +355,8 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg, nla_len(bearer[TIPC_NLA_BEARER_NAME])); } -static int tipc_nl_compat_bearer_enable(struct sk_buff *skb, +static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, + struct sk_buff *skb, struct tipc_nl_compat_msg *msg) { struct nlattr *prop; @@ -385,7 +388,8 @@ static int tipc_nl_compat_bearer_enable(struct sk_buff *skb, return 0; } -static int tipc_nl_compat_bearer_disable(struct sk_buff *skb, +static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, + struct sk_buff *skb, struct tipc_nl_compat_msg *msg) { char *name; @@ -576,11 +580,81 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg, &link_info, sizeof(link_info)); } -static int tipc_nl_compat_link_set(struct sk_buff *skb, - struct tipc_nl_compat_msg *msg) +static int __tipc_add_link_prop(struct sk_buff *skb, + struct tipc_nl_compat_msg *msg, + struct tipc_link_config *lc) +{ + switch (msg->cmd) { + case TIPC_CMD_SET_LINK_PRI: + return nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(lc->value)); + case TIPC_CMD_SET_LINK_TOL: + return nla_put_u32(skb, TIPC_NLA_PROP_TOL, ntohl(lc->value)); + case TIPC_CMD_SET_LINK_WINDOW: + return nla_put_u32(skb, TIPC_NLA_PROP_WIN, ntohl(lc->value)); + } + + return -EINVAL; +} + +static int tipc_nl_compat_media_set(struct sk_buff *skb, + struct tipc_nl_compat_msg *msg) { - struct nlattr *link; struct nlattr *prop; + struct nlattr *media; + struct tipc_link_config *lc; + + lc = (struct tipc_link_config *)TLV_DATA(msg->req); + + media = nla_nest_start(skb, TIPC_NLA_MEDIA); + if (!media) + return -EMSGSIZE; + + if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name)) + return -EMSGSIZE; + + prop = nla_nest_start(skb, TIPC_NLA_MEDIA_PROP); + if (!prop) + return -EMSGSIZE; + + __tipc_add_link_prop(skb, msg, lc); + nla_nest_end(skb, prop); + nla_nest_end(skb, media); + + return 0; +} + +static int tipc_nl_compat_bearer_set(struct sk_buff *skb, + struct tipc_nl_compat_msg *msg) +{ + struct nlattr *prop; + struct nlattr *bearer; + struct tipc_link_config *lc; + + lc = (struct tipc_link_config *)TLV_DATA(msg->req); + + bearer = nla_nest_start(skb, TIPC_NLA_BEARER); + if (!bearer) + return -EMSGSIZE; + + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name)) + return -EMSGSIZE; + + prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP); + if (!prop) + return -EMSGSIZE; + + __tipc_add_link_prop(skb, msg, lc); + nla_nest_end(skb, prop); + nla_nest_end(skb, bearer); + + return 0; +} + +static int __tipc_nl_compat_link_set(struct sk_buff *skb, + struct tipc_nl_compat_msg *msg) +{ + struct nlattr *prop; + struct nlattr *link; struct tipc_link_config *lc; lc = (struct tipc_link_config *)TLV_DATA(msg->req); @@ -596,24 +670,40 @@ static int tipc_nl_compat_link_set(struct sk_buff *skb, if (!prop) return -EMSGSIZE; - if (msg->cmd == TIPC_CMD_SET_LINK_PRI) { - if (nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(lc->value))) - return -EMSGSIZE; - } else if (msg->cmd == TIPC_CMD_SET_LINK_TOL) { - if (nla_put_u32(skb, TIPC_NLA_PROP_TOL, ntohl(lc->value))) - return -EMSGSIZE; - } else if (msg->cmd == TIPC_CMD_SET_LINK_WINDOW) { - if (nla_put_u32(skb, TIPC_NLA_PROP_WIN, ntohl(lc->value))) - return -EMSGSIZE; - } - + __tipc_add_link_prop(skb, msg, lc); nla_nest_end(skb, prop); nla_nest_end(skb, link); return 0; } -static int tipc_nl_compat_link_reset_stats(struct sk_buff *skb, +static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, + struct sk_buff *skb, + struct tipc_nl_compat_msg *msg) +{ + struct tipc_link_config *lc; + struct tipc_bearer *bearer; + struct tipc_media *media; + + lc = (struct tipc_link_config *)TLV_DATA(msg->req); + + media = tipc_media_find(lc->name); + if (media) { + cmd->doit = &tipc_nl_media_set; + return tipc_nl_compat_media_set(skb, msg); + } + + bearer = tipc_bearer_find(msg->net, lc->name); + if (bearer) { + cmd->doit = &tipc_nl_bearer_set; + return tipc_nl_compat_bearer_set(skb, msg); + } + + return __tipc_nl_compat_link_set(skb, msg); +} + +static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, + struct sk_buff *skb, struct tipc_nl_compat_msg *msg) { char *name; @@ -851,7 +941,8 @@ static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg, sizeof(node_info)); } -static int tipc_nl_compat_net_set(struct sk_buff *skb, +static int tipc_nl_compat_net_set(struct tipc_nl_compat_cmd_doit *cmd, + struct sk_buff *skb, struct tipc_nl_compat_msg *msg) { u32 val; @@ -1007,7 +1098,6 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) struct nlmsghdr *req_nlh; struct nlmsghdr *rep_nlh; struct tipc_genlmsghdr *req_userhdr = info->userhdr; - struct net *net = genl_info_net(info); memset(&msg, 0, sizeof(msg)); @@ -1015,6 +1105,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) msg.req = nlmsg_data(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN; msg.cmd = req_userhdr->cmd; msg.dst_sk = info->dst_sk; + msg.net = genl_info_net(info); if ((msg.cmd & 0xC000) && (!netlink_net_capable(skb, CAP_NET_ADMIN))) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_NET_ADMIN); @@ -1030,7 +1121,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) } err = tipc_nl_compat_handle(&msg); - if (err == -EOPNOTSUPP) + if ((err == -EOPNOTSUPP) || (err == -EPERM)) msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); else if (err == -EINVAL) msg.rep = tipc_get_err_tlv(TIPC_CFG_TLV_ERROR); @@ -1043,7 +1134,7 @@ send: rep_nlh = nlmsg_hdr(msg.rep); memcpy(rep_nlh, info->nlhdr, len); rep_nlh->nlmsg_len = msg.rep->len; - genlmsg_unicast(net, msg.rep, NETLINK_CB(skb).portid); + genlmsg_unicast(msg.net, msg.rep, NETLINK_CB(skb).portid); return err; } diff --git a/net/tipc/node.c b/net/tipc/node.c index 22c059ad2999..0b1d61a5f853 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1,7 +1,7 @@ /* * net/tipc/node.c: TIPC node management routines * - * Copyright (c) 2000-2006, 2012-2014, Ericsson AB + * Copyright (c) 2000-2006, 2012-2015, Ericsson AB * Copyright (c) 2005-2006, 2010-2014, Wind River Systems * All rights reserved. * @@ -39,6 +39,7 @@ #include "node.h" #include "name_distr.h" #include "socket.h" +#include "bcast.h" static void node_lost_contact(struct tipc_node *n_ptr); static void node_established_contact(struct tipc_node *n_ptr); diff --git a/net/tipc/node.h b/net/tipc/node.h index 02d5c20dc551..5a834cf142c8 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -45,8 +45,6 @@ /* Out-of-range value for node signature */ #define INVALID_NODE_SIG 0x10000 -#define NODE_HTABLE_SIZE 512 - /* Flags used to take different actions according to flag type * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down * TIPC_WAIT_OWN_LINKS_DOWN: wait until peer node is declared down diff --git a/net/tipc/server.c b/net/tipc/server.c index 77ff03ed1e18..922e04a43396 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -309,6 +309,10 @@ static int tipc_accept_from_sock(struct tipc_conn *con) /* Notify that new connection is incoming */ newcon->usr_data = s->tipc_conn_new(newcon->conid); + if (!newcon->usr_data) { + sock_release(newsock); + return -ENOMEM; + } /* Wake up receive process in case of 'SYN+' message */ newsock->sk->sk_data_ready(newsock->sk); @@ -321,7 +325,7 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) struct socket *sock = NULL; int ret; - ret = __sock_create(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock, 1); + ret = sock_create_kern(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock); if (ret < 0) return NULL; ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 9074b5cede38..30ea82a9b0f1 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -41,6 +41,7 @@ #include "link.h" #include "name_distr.h" #include "socket.h" +#include "bcast.h" #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ @@ -342,7 +343,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, } /* Allocate socket's protocol area */ - sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto); + sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto, kern); if (sk == NULL) return -ENOMEM; @@ -409,7 +410,7 @@ static int tipc_release(struct socket *sock) struct net *net; struct tipc_sock *tsk; struct sk_buff *skb; - u32 dnode, probing_state; + u32 dnode; /* * Exit if socket isn't fully initialized (occurs when a failed accept() @@ -447,10 +448,7 @@ static int tipc_release(struct socket *sock) } tipc_sk_withdraw(tsk, 0, NULL); - probing_state = tsk->probing_state; - if (del_timer_sync(&sk->sk_timer) && - probing_state != TIPC_CONN_PROBING) - sock_put(sk); + sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); if (tsk->connected) { skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 1c147c869c2e..350cca33ee0a 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -40,16 +40,21 @@ /** * struct tipc_subscriber - TIPC network topology subscriber + * @kref: reference counter to tipc_subscription object * @conid: connection identifier to server connecting to subscriber * @lock: control access to subscriber - * @subscription_list: list of subscription objects for this subscriber + * @subscrp_list: list of subscription objects for this subscriber */ struct tipc_subscriber { + struct kref kref; int conid; spinlock_t lock; - struct list_head subscription_list; + struct list_head subscrp_list; }; +static void tipc_subscrp_delete(struct tipc_subscription *sub); +static void tipc_subscrb_put(struct tipc_subscriber *subscriber); + /** * htohl - convert value to endianness used by destination * @in: value to convert @@ -62,9 +67,9 @@ static u32 htohl(u32 in, int swap) return swap ? swab32(in) : in; } -static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower, - u32 found_upper, u32 event, u32 port_ref, - u32 node) +static void tipc_subscrp_send_event(struct tipc_subscription *sub, + u32 found_lower, u32 found_upper, + u32 event, u32 port_ref, u32 node) { struct tipc_net *tn = net_generic(sub->net, tipc_net_id); struct tipc_subscriber *subscriber = sub->subscriber; @@ -82,12 +87,13 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower, } /** - * tipc_subscr_overlap - test for subscription overlap with the given values + * tipc_subscrp_check_overlap - test for subscription overlap with the + * given values * * Returns 1 if there is overlap, otherwise 0. */ -int tipc_subscr_overlap(struct tipc_subscription *sub, u32 found_lower, - u32 found_upper) +int tipc_subscrp_check_overlap(struct tipc_subscription *sub, u32 found_lower, + u32 found_upper) { if (found_lower < sub->seq.lower) found_lower = sub->seq.lower; @@ -98,138 +104,121 @@ int tipc_subscr_overlap(struct tipc_subscription *sub, u32 found_lower, return 1; } -/** - * tipc_subscr_report_overlap - issue event if there is subscription overlap - * - * Protected by nameseq.lock in name_table.c - */ -void tipc_subscr_report_overlap(struct tipc_subscription *sub, u32 found_lower, - u32 found_upper, u32 event, u32 port_ref, - u32 node, int must) +void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, + u32 found_upper, u32 event, u32 port_ref, + u32 node, int must) { - if (!tipc_subscr_overlap(sub, found_lower, found_upper)) + if (!tipc_subscrp_check_overlap(sub, found_lower, found_upper)) return; if (!must && !(sub->filter & TIPC_SUB_PORTS)) return; - subscr_send_event(sub, found_lower, found_upper, event, port_ref, node); + tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref, + node); } -static void subscr_timeout(unsigned long data) +static void tipc_subscrp_timeout(unsigned long data) { struct tipc_subscription *sub = (struct tipc_subscription *)data; struct tipc_subscriber *subscriber = sub->subscriber; - struct tipc_net *tn = net_generic(sub->net, tipc_net_id); - /* The spin lock per subscriber is used to protect its members */ - spin_lock_bh(&subscriber->lock); + /* Notify subscriber of timeout */ + tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper, + TIPC_SUBSCR_TIMEOUT, 0, 0); - /* Validate timeout (in case subscription is being cancelled) */ - if (sub->timeout == TIPC_WAIT_FOREVER) { - spin_unlock_bh(&subscriber->lock); - return; - } + spin_lock_bh(&subscriber->lock); + tipc_subscrp_delete(sub); + spin_unlock_bh(&subscriber->lock); - /* Unlink subscription from name table */ - tipc_nametbl_unsubscribe(sub); + tipc_subscrb_put(subscriber); +} - /* Unlink subscription from subscriber */ - list_del(&sub->subscription_list); +static void tipc_subscrb_kref_release(struct kref *kref) +{ + struct tipc_subscriber *subcriber = container_of(kref, + struct tipc_subscriber, kref); - spin_unlock_bh(&subscriber->lock); + kfree(subcriber); +} - /* Notify subscriber of timeout */ - subscr_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper, - TIPC_SUBSCR_TIMEOUT, 0, 0); +static void tipc_subscrb_put(struct tipc_subscriber *subscriber) +{ + kref_put(&subscriber->kref, tipc_subscrb_kref_release); +} - /* Now destroy subscription */ - kfree(sub); - atomic_dec(&tn->subscription_count); +static void tipc_subscrb_get(struct tipc_subscriber *subscriber) +{ + kref_get(&subscriber->kref); } -/** - * subscr_del - delete a subscription within a subscription list - * - * Called with subscriber lock held. - */ -static void subscr_del(struct tipc_subscription *sub) +static struct tipc_subscriber *tipc_subscrb_create(int conid) { - struct tipc_net *tn = net_generic(sub->net, tipc_net_id); + struct tipc_subscriber *subscriber; - tipc_nametbl_unsubscribe(sub); - list_del(&sub->subscription_list); - kfree(sub); - atomic_dec(&tn->subscription_count); + subscriber = kzalloc(sizeof(*subscriber), GFP_ATOMIC); + if (!subscriber) { + pr_warn("Subscriber rejected, no memory\n"); + return NULL; + } + kref_init(&subscriber->kref); + INIT_LIST_HEAD(&subscriber->subscrp_list); + subscriber->conid = conid; + spin_lock_init(&subscriber->lock); + + return subscriber; } -static void subscr_release(struct tipc_subscriber *subscriber) +static void tipc_subscrb_delete(struct tipc_subscriber *subscriber) { - struct tipc_subscription *sub; - struct tipc_subscription *sub_temp; + struct tipc_subscription *sub, *temp; spin_lock_bh(&subscriber->lock); - /* Destroy any existing subscriptions for subscriber */ - list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, - subscription_list) { - if (sub->timeout != TIPC_WAIT_FOREVER) { - spin_unlock_bh(&subscriber->lock); - del_timer_sync(&sub->timer); - spin_lock_bh(&subscriber->lock); + list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list, + subscrp_list) { + if (del_timer(&sub->timer)) { + tipc_subscrp_delete(sub); + tipc_subscrb_put(subscriber); } - subscr_del(sub); } spin_unlock_bh(&subscriber->lock); - /* Now destroy subscriber */ - kfree(subscriber); + tipc_subscrb_put(subscriber); } -/** - * subscr_cancel - handle subscription cancellation request - * - * Called with subscriber lock held. Routine must temporarily release lock - * to enable the subscription timeout routine to finish without deadlocking; - * the lock is then reclaimed to allow caller to release it upon return. - * - * Note that fields of 's' use subscriber's endianness! - */ -static void subscr_cancel(struct tipc_subscr *s, - struct tipc_subscriber *subscriber) +static void tipc_subscrp_delete(struct tipc_subscription *sub) { - struct tipc_subscription *sub; - struct tipc_subscription *sub_temp; - int found = 0; + struct tipc_net *tn = net_generic(sub->net, tipc_net_id); + + tipc_nametbl_unsubscribe(sub); + list_del(&sub->subscrp_list); + kfree(sub); + atomic_dec(&tn->subscription_count); +} +static void tipc_subscrp_cancel(struct tipc_subscr *s, + struct tipc_subscriber *subscriber) +{ + struct tipc_subscription *sub, *temp; + + spin_lock_bh(&subscriber->lock); /* Find first matching subscription, exit if not found */ - list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, - subscription_list) { + list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list, + subscrp_list) { if (!memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) { - found = 1; + if (del_timer(&sub->timer)) { + tipc_subscrp_delete(sub); + tipc_subscrb_put(subscriber); + } break; } } - if (!found) - return; - - /* Cancel subscription timer (if used), then delete subscription */ - if (sub->timeout != TIPC_WAIT_FOREVER) { - sub->timeout = TIPC_WAIT_FOREVER; - spin_unlock_bh(&subscriber->lock); - del_timer_sync(&sub->timer); - spin_lock_bh(&subscriber->lock); - } - subscr_del(sub); + spin_unlock_bh(&subscriber->lock); } -/** - * subscr_subscribe - create subscription for subscriber - * - * Called with subscriber lock held. - */ -static int subscr_subscribe(struct net *net, struct tipc_subscr *s, - struct tipc_subscriber *subscriber, - struct tipc_subscription **sub_p) +static int tipc_subscrp_create(struct net *net, struct tipc_subscr *s, + struct tipc_subscriber *subscriber, + struct tipc_subscription **sub_p) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_subscription *sub; @@ -241,7 +230,7 @@ static int subscr_subscribe(struct net *net, struct tipc_subscr *s, /* Detect & process a subscription cancellation request */ if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) { s->filter &= ~htohl(TIPC_SUB_CANCEL, swap); - subscr_cancel(s, subscriber); + tipc_subscrp_cancel(s, subscriber); return 0; } @@ -273,62 +262,51 @@ static int subscr_subscribe(struct net *net, struct tipc_subscr *s, kfree(sub); return -EINVAL; } - list_add(&sub->subscription_list, &subscriber->subscription_list); + spin_lock_bh(&subscriber->lock); + list_add(&sub->subscrp_list, &subscriber->subscrp_list); + spin_unlock_bh(&subscriber->lock); sub->subscriber = subscriber; sub->swap = swap; - memcpy(&sub->evt.s, s, sizeof(struct tipc_subscr)); + memcpy(&sub->evt.s, s, sizeof(*s)); atomic_inc(&tn->subscription_count); - if (sub->timeout != TIPC_WAIT_FOREVER) { - setup_timer(&sub->timer, subscr_timeout, (unsigned long)sub); - mod_timer(&sub->timer, jiffies + sub->timeout); - } + setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub); + if (sub->timeout != TIPC_WAIT_FOREVER) + sub->timeout += jiffies; + if (!mod_timer(&sub->timer, sub->timeout)) + tipc_subscrb_get(subscriber); *sub_p = sub; return 0; } /* Handle one termination request for the subscriber */ -static void subscr_conn_shutdown_event(int conid, void *usr_data) +static void tipc_subscrb_shutdown_cb(int conid, void *usr_data) { - subscr_release((struct tipc_subscriber *)usr_data); + tipc_subscrb_delete((struct tipc_subscriber *)usr_data); } /* Handle one request to create a new subscription for the subscriber */ -static void subscr_conn_msg_event(struct net *net, int conid, - struct sockaddr_tipc *addr, void *usr_data, - void *buf, size_t len) +static void tipc_subscrb_rcv_cb(struct net *net, int conid, + struct sockaddr_tipc *addr, void *usr_data, + void *buf, size_t len) { struct tipc_subscriber *subscriber = usr_data; struct tipc_subscription *sub = NULL; struct tipc_net *tn = net_generic(net, tipc_net_id); - spin_lock_bh(&subscriber->lock); - subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub); + tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscriber, &sub); if (sub) tipc_nametbl_subscribe(sub); else tipc_conn_terminate(tn->topsrv, subscriber->conid); - spin_unlock_bh(&subscriber->lock); } /* Handle one request to establish a new subscriber */ -static void *subscr_named_msg_event(int conid) +static void *tipc_subscrb_connect_cb(int conid) { - struct tipc_subscriber *subscriber; - - /* Create subscriber object */ - subscriber = kzalloc(sizeof(struct tipc_subscriber), GFP_ATOMIC); - if (subscriber == NULL) { - pr_warn("Subscriber rejected, no memory\n"); - return NULL; - } - INIT_LIST_HEAD(&subscriber->subscription_list); - subscriber->conid = conid; - spin_lock_init(&subscriber->lock); - - return (void *)subscriber; + return (void *)tipc_subscrb_create(conid); } -int tipc_subscr_start(struct net *net) +int tipc_topsrv_start(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); const char name[] = "topology_server"; @@ -355,9 +333,9 @@ int tipc_subscr_start(struct net *net) topsrv->imp = TIPC_CRITICAL_IMPORTANCE; topsrv->type = SOCK_SEQPACKET; topsrv->max_rcvbuf_size = sizeof(struct tipc_subscr); - topsrv->tipc_conn_recvmsg = subscr_conn_msg_event; - topsrv->tipc_conn_new = subscr_named_msg_event; - topsrv->tipc_conn_shutdown = subscr_conn_shutdown_event; + topsrv->tipc_conn_recvmsg = tipc_subscrb_rcv_cb; + topsrv->tipc_conn_new = tipc_subscrb_connect_cb; + topsrv->tipc_conn_shutdown = tipc_subscrb_shutdown_cb; strncpy(topsrv->name, name, strlen(name) + 1); tn->topsrv = topsrv; @@ -366,7 +344,7 @@ int tipc_subscr_start(struct net *net) return tipc_server_start(topsrv); } -void tipc_subscr_stop(struct net *net) +void tipc_topsrv_stop(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_server *topsrv = tn->topsrv; diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index 33488bd9fe3c..92ee18cc5fe6 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -54,7 +54,7 @@ struct tipc_subscriber; * @filter: event filtering to be done for subscription * @timer: timer governing subscription duration (optional) * @nameseq_list: adjacent subscriptions in name sequence's subscription list - * @subscription_list: adjacent subscriptions in subscriber's subscription list + * @subscrp_list: adjacent subscriptions in subscriber's subscription list * @server_ref: object reference of server port associated with subscription * @swap: indicates if subscriber uses opposite endianness in its messages * @evt: template for events generated by subscription @@ -67,17 +67,17 @@ struct tipc_subscription { u32 filter; struct timer_list timer; struct list_head nameseq_list; - struct list_head subscription_list; + struct list_head subscrp_list; int swap; struct tipc_event evt; }; -int tipc_subscr_overlap(struct tipc_subscription *sub, u32 found_lower, - u32 found_upper); -void tipc_subscr_report_overlap(struct tipc_subscription *sub, u32 found_lower, - u32 found_upper, u32 event, u32 port_ref, - u32 node, int must); -int tipc_subscr_start(struct net *net); -void tipc_subscr_stop(struct net *net); +int tipc_subscrp_check_overlap(struct tipc_subscription *sub, u32 found_lower, + u32 found_upper); +void tipc_subscrp_report_overlap(struct tipc_subscription *sub, + u32 found_lower, u32 found_upper, u32 event, + u32 port_ref, u32 node, int must); +int tipc_topsrv_start(struct net *net); +void tipc_topsrv_stop(struct net *net); #endif diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 06430598cf51..f25e1675b865 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -518,6 +518,11 @@ static int unix_ioctl(struct socket *, unsigned int, unsigned long); static int unix_shutdown(struct socket *, int); static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int); +static ssize_t unix_stream_sendpage(struct socket *, struct page *, int offset, + size_t size, int flags); +static ssize_t unix_stream_splice_read(struct socket *, loff_t *ppos, + struct pipe_inode_info *, size_t size, + unsigned int flags); static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int); static int unix_dgram_connect(struct socket *, struct sockaddr *, @@ -558,7 +563,8 @@ static const struct proto_ops unix_stream_ops = { .sendmsg = unix_stream_sendmsg, .recvmsg = unix_stream_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, + .sendpage = unix_stream_sendpage, + .splice_read = unix_stream_splice_read, .set_peek_off = unix_set_peek_off, }; @@ -620,7 +626,7 @@ static struct proto unix_proto = { */ static struct lock_class_key af_unix_sk_receive_queue_lock_key; -static struct sock *unix_create1(struct net *net, struct socket *sock) +static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) { struct sock *sk = NULL; struct unix_sock *u; @@ -629,7 +635,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) goto out; - sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto); + sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto, kern); if (!sk) goto out; @@ -688,7 +694,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, return -ESOCKTNOSUPPORT; } - return unix_create1(net, sock) ? 0 : -ENOMEM; + return unix_create1(net, sock, kern) ? 0 : -ENOMEM; } static int unix_release(struct socket *sock) @@ -1088,7 +1094,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = -ENOMEM; /* create new sock for complete connection */ - newsk = unix_create1(sock_net(sk), NULL); + newsk = unix_create1(sock_net(sk), NULL, 0); if (newsk == NULL) goto out; @@ -1720,6 +1726,101 @@ out_err: return sent ? : err; } +static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, + int offset, size_t size, int flags) +{ + int err = 0; + bool send_sigpipe = true; + struct sock *other, *sk = socket->sk; + struct sk_buff *skb, *newskb = NULL, *tail = NULL; + + if (flags & MSG_OOB) + return -EOPNOTSUPP; + + other = unix_peer(sk); + if (!other || sk->sk_state != TCP_ESTABLISHED) + return -ENOTCONN; + + if (false) { +alloc_skb: + unix_state_unlock(other); + mutex_unlock(&unix_sk(other)->readlock); + newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, + &err, 0); + if (!newskb) + return err; + } + + /* we must acquire readlock as we modify already present + * skbs in the sk_receive_queue and mess with skb->len + */ + err = mutex_lock_interruptible(&unix_sk(other)->readlock); + if (err) { + err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS; + send_sigpipe = false; + goto err; + } + + if (sk->sk_shutdown & SEND_SHUTDOWN) { + err = -EPIPE; + goto err_unlock; + } + + unix_state_lock(other); + + if (sock_flag(other, SOCK_DEAD) || + other->sk_shutdown & RCV_SHUTDOWN) { + err = -EPIPE; + goto err_state_unlock; + } + + skb = skb_peek_tail(&other->sk_receive_queue); + if (tail && tail == skb) { + skb = newskb; + } else if (!skb) { + if (newskb) + skb = newskb; + else + goto alloc_skb; + } else if (newskb) { + /* this is fast path, we don't necessarily need to + * call to kfree_skb even though with newskb == NULL + * this - does no harm + */ + consume_skb(newskb); + } + + if (skb_append_pagefrags(skb, page, offset, size)) { + tail = skb; + goto alloc_skb; + } + + skb->len += size; + skb->data_len += size; + skb->truesize += size; + atomic_add(size, &sk->sk_wmem_alloc); + + if (newskb) + __skb_queue_tail(&other->sk_receive_queue, newskb); + + unix_state_unlock(other); + mutex_unlock(&unix_sk(other)->readlock); + + other->sk_data_ready(other); + + return size; + +err_state_unlock: + unix_state_unlock(other); +err_unlock: + mutex_unlock(&unix_sk(other)->readlock); +err: + kfree_skb(newskb); + if (send_sigpipe && !(flags & MSG_NOSIGNAL)) + send_sig(SIGPIPE, current, 0); + return err; +} + static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { @@ -1860,8 +1961,9 @@ out: * Sleep until more data has arrived. But check for races.. */ static long unix_stream_data_wait(struct sock *sk, long timeo, - struct sk_buff *last) + struct sk_buff *last, unsigned int last_len) { + struct sk_buff *tail; DEFINE_WAIT(wait); unix_state_lock(sk); @@ -1869,7 +1971,9 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (skb_peek_tail(&sk->sk_receive_queue) != last || + tail = skb_peek_tail(&sk->sk_receive_queue); + if (tail != last || + (tail && tail->len != last_len) || sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current) || @@ -1897,38 +2001,50 @@ static unsigned int unix_skb_len(const struct sk_buff *skb) return skb->len - UNIXCB(skb).consumed; } -static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, - size_t size, int flags) +struct unix_stream_read_state { + int (*recv_actor)(struct sk_buff *, int, int, + struct unix_stream_read_state *); + struct socket *socket; + struct msghdr *msg; + struct pipe_inode_info *pipe; + size_t size; + int flags; + unsigned int splice_flags; +}; + +static int unix_stream_read_generic(struct unix_stream_read_state *state) { struct scm_cookie scm; + struct socket *sock = state->socket; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name); int copied = 0; + int flags = state->flags; int noblock = flags & MSG_DONTWAIT; - int check_creds = 0; + bool check_creds = false; int target; int err = 0; long timeo; int skip; + size_t size = state->size; + unsigned int last_len; err = -EINVAL; if (sk->sk_state != TCP_ESTABLISHED) goto out; err = -EOPNOTSUPP; - if (flags&MSG_OOB) + if (flags & MSG_OOB) goto out; - target = sock_rcvlowat(sk, flags&MSG_WAITALL, size); + target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, noblock); + memset(&scm, 0, sizeof(scm)); + /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ - - memset(&scm, 0, sizeof(scm)); - err = mutex_lock_interruptible(&u->readlock); if (unlikely(err)) { /* recvmsg() in non blocking mode is supposed to return -EAGAIN @@ -1948,6 +2064,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, goto unlock; } last = skb = skb_peek(&sk->sk_receive_queue); + last_len = last ? last->len : 0; again: if (skb == NULL) { unix_sk(sk)->recursion_level = 0; @@ -1970,16 +2087,17 @@ again: break; mutex_unlock(&u->readlock); - timeo = unix_stream_data_wait(sk, timeo, last); + timeo = unix_stream_data_wait(sk, timeo, last, + last_len); - if (signal_pending(current) - || mutex_lock_interruptible(&u->readlock)) { + if (signal_pending(current) || + mutex_lock_interruptible(&u->readlock)) { err = sock_intr_errno(timeo); goto out; } continue; - unlock: +unlock: unix_state_unlock(sk); break; } @@ -1988,6 +2106,7 @@ again: while (skip >= unix_skb_len(skb)) { skip -= unix_skb_len(skb); last = skb; + last_len = skb->len; skb = skb_peek_next(skb, &sk->sk_receive_queue); if (!skb) goto again; @@ -2004,18 +2123,20 @@ again: } else if (test_bit(SOCK_PASSCRED, &sock->flags)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); - check_creds = 1; + check_creds = true; } /* Copy address just once */ - if (sunaddr) { - unix_copy_addr(msg, skb->sk); + if (state->msg && state->msg->msg_name) { + DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, + state->msg->msg_name); + unix_copy_addr(state->msg, skb->sk); sunaddr = NULL; } chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size); - if (skb_copy_datagram_msg(skb, UNIXCB(skb).consumed + skip, - msg, chunk)) { + chunk = state->recv_actor(skb, skip, chunk, state); + if (chunk < 0) { if (copied == 0) copied = -EFAULT; break; @@ -2053,11 +2174,85 @@ again: } while (size); mutex_unlock(&u->readlock); - scm_recv(sock, msg, &scm, flags); + if (state->msg) + scm_recv(sock, state->msg, &scm, flags); + else + scm_destroy(&scm); out: return copied ? : err; } +static int unix_stream_read_actor(struct sk_buff *skb, + int skip, int chunk, + struct unix_stream_read_state *state) +{ + int ret; + + ret = skb_copy_datagram_msg(skb, UNIXCB(skb).consumed + skip, + state->msg, chunk); + return ret ?: chunk; +} + +static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct unix_stream_read_state state = { + .recv_actor = unix_stream_read_actor, + .socket = sock, + .msg = msg, + .size = size, + .flags = flags + }; + + return unix_stream_read_generic(&state); +} + +static ssize_t skb_unix_socket_splice(struct sock *sk, + struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd) +{ + int ret; + struct unix_sock *u = unix_sk(sk); + + mutex_unlock(&u->readlock); + ret = splice_to_pipe(pipe, spd); + mutex_lock(&u->readlock); + + return ret; +} + +static int unix_stream_splice_actor(struct sk_buff *skb, + int skip, int chunk, + struct unix_stream_read_state *state) +{ + return skb_splice_bits(skb, state->socket->sk, + UNIXCB(skb).consumed + skip, + state->pipe, chunk, state->splice_flags, + skb_unix_socket_splice); +} + +static ssize_t unix_stream_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t size, unsigned int flags) +{ + struct unix_stream_read_state state = { + .recv_actor = unix_stream_splice_actor, + .socket = sock, + .pipe = pipe, + .size = size, + .splice_flags = flags, + }; + + if (unlikely(*ppos)) + return -ESPIPE; + + if (sock->file->f_flags & O_NONBLOCK || + flags & SPLICE_F_NONBLOCK) + state.flags = MSG_DONTWAIT; + + return unix_stream_read_generic(&state); +} + static int unix_shutdown(struct socket *sock, int mode) { struct sock *sk = sock->sk; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 2ec86e652a19..df5fc6b340f1 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -581,13 +581,14 @@ struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, gfp_t priority, - unsigned short type) + unsigned short type, + int kern) { struct sock *sk; struct vsock_sock *psk; struct vsock_sock *vsk; - sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto); + sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto, kern); if (!sk) return NULL; @@ -1866,7 +1867,7 @@ static int vsock_create(struct net *net, struct socket *sock, sock->state = SS_UNCONNECTED; - return __vsock_create(net, sock, NULL, GFP_KERNEL, 0) ? 0 : -ENOMEM; + return __vsock_create(net, sock, NULL, GFP_KERNEL, 0, kern) ? 0 : -ENOMEM; } static const struct net_proto_family vsock_family_ops = { diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c294da095461..1f63daff3965 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1022,7 +1022,7 @@ static int vmci_transport_recv_listen(struct sock *sk, } pending = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL, - sk->sk_type); + sk->sk_type, 0); if (!pending) { vmci_transport_send_reset(sk, pkt); return -ENOMEM; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 7aaf7415dc4c..915b328b9ac5 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -698,19 +698,20 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, EXPORT_SYMBOL(cfg80211_chandef_usable); /* - * For GO only, check if the channel can be used under permissive conditions - * mandated by the some regulatory bodies, i.e., the channel is marked with - * IEEE80211_CHAN_GO_CONCURRENT and there is an additional station interface + * Check if the channel can be used under permissive conditions mandated by + * some regulatory bodies, i.e., the channel is marked with + * IEEE80211_CHAN_IR_CONCURRENT and there is an additional station interface * associated to an AP on the same channel or on the same UNII band * (assuming that the AP is an authorized master). - * In addition allow the GO to operate on a channel on which indoor operation is + * In addition allow operation on a channel on which indoor operation is * allowed, iff we are currently operating in an indoor environment. */ -static bool cfg80211_go_permissive_chan(struct cfg80211_registered_device *rdev, +static bool cfg80211_ir_permissive_chan(struct wiphy *wiphy, + enum nl80211_iftype iftype, struct ieee80211_channel *chan) { - struct wireless_dev *wdev_iter; - struct wiphy *wiphy = wiphy_idx_to_wiphy(rdev->wiphy_idx); + struct wireless_dev *wdev; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); ASSERT_RTNL(); @@ -718,32 +719,48 @@ static bool cfg80211_go_permissive_chan(struct cfg80211_registered_device *rdev, !(wiphy->regulatory_flags & REGULATORY_ENABLE_RELAX_NO_IR)) return false; + /* only valid for GO and TDLS off-channel (station/p2p-CL) */ + if (iftype != NL80211_IFTYPE_P2P_GO && + iftype != NL80211_IFTYPE_STATION && + iftype != NL80211_IFTYPE_P2P_CLIENT) + return false; + if (regulatory_indoor_allowed() && (chan->flags & IEEE80211_CHAN_INDOOR_ONLY)) return true; - if (!(chan->flags & IEEE80211_CHAN_GO_CONCURRENT)) + if (!(chan->flags & IEEE80211_CHAN_IR_CONCURRENT)) return false; /* * Generally, it is possible to rely on another device/driver to allow - * the GO concurrent relaxation, however, since the device can further + * the IR concurrent relaxation, however, since the device can further * enforce the relaxation (by doing a similar verifications as this), * and thus fail the GO instantiation, consider only the interfaces of * the current registered device. */ - list_for_each_entry(wdev_iter, &rdev->wdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { struct ieee80211_channel *other_chan = NULL; int r1, r2; - if (wdev_iter->iftype != NL80211_IFTYPE_STATION || - !netif_running(wdev_iter->netdev)) - continue; - - wdev_lock(wdev_iter); - if (wdev_iter->current_bss) - other_chan = wdev_iter->current_bss->pub.channel; - wdev_unlock(wdev_iter); + wdev_lock(wdev); + if (wdev->iftype == NL80211_IFTYPE_STATION && + wdev->current_bss) + other_chan = wdev->current_bss->pub.channel; + + /* + * If a GO already operates on the same GO_CONCURRENT channel, + * this one (maybe the same one) can beacon as well. We allow + * the operation even if the station we relied on with + * GO_CONCURRENT is disconnected now. But then we must make sure + * we're not outdoor on an indoor-only channel. + */ + if (iftype == NL80211_IFTYPE_P2P_GO && + wdev->iftype == NL80211_IFTYPE_P2P_GO && + wdev->beacon_interval && + !(chan->flags & IEEE80211_CHAN_INDOOR_ONLY)) + other_chan = wdev->chandef.chan; + wdev_unlock(wdev); if (!other_chan) continue; @@ -784,7 +801,6 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype) { - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); bool res; u32 prohibited_flags = IEEE80211_CHAN_DISABLED | IEEE80211_CHAN_RADAR; @@ -792,13 +808,12 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy, trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype); /* - * Under certain conditions suggested by the some regulatory bodies - * a GO can operate on channels marked with IEEE80211_NO_IR - * so set this flag only if such relaxations are not enabled and - * the conditions are not met. + * Under certain conditions suggested by some regulatory bodies a + * GO/STA can IR on channels marked with IEEE80211_NO_IR. Set this flag + * only if such relaxations are not enabled and the conditions are not + * met. */ - if (iftype != NL80211_IFTYPE_P2P_GO || - !cfg80211_go_permissive_chan(rdev, chandef->chan)) + if (!cfg80211_ir_permissive_chan(wiphy, iftype, chandef->chan)) prohibited_flags |= IEEE80211_CHAN_NO_IR; if (cfg80211_chandef_dfs_required(wiphy, chandef, iftype) > 0 && diff --git a/net/wireless/core.h b/net/wireless/core.h index 801cd49c5a0c..311eef26bf88 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -222,6 +222,7 @@ struct cfg80211_event { const u8 *ie; size_t ie_len; u16 reason; + bool locally_generated; } dc; struct { u8 bssid[ETH_ALEN]; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index dd78445c7d50..c264effd00a6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -639,8 +639,8 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, if ((chan->flags & IEEE80211_CHAN_INDOOR_ONLY) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_INDOOR_ONLY)) goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_GO_CONCURRENT) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_GO_CONCURRENT)) + if ((chan->flags & IEEE80211_CHAN_IR_CONCURRENT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_IR_CONCURRENT)) goto nla_put_failure; if ((chan->flags & IEEE80211_CHAN_NO_20MHZ) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_20MHZ)) @@ -4061,7 +4061,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, return -EINVAL; break; case CFG80211_STA_MESH_PEER_USER: - if (params->plink_action != NL80211_PLINK_ACTION_NO_ACTION) + if (params->plink_action != NL80211_PLINK_ACTION_NO_ACTION && + params->plink_action != NL80211_PLINK_ACTION_BLOCK) return -EINVAL; break; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 0e347f888fe9..d359e0610198 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -989,8 +989,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_OFDM; if (rd_flags & NL80211_RRF_NO_OUTDOOR) channel_flags |= IEEE80211_CHAN_INDOOR_ONLY; - if (rd_flags & NL80211_RRF_GO_CONCURRENT) - channel_flags |= IEEE80211_CHAN_GO_CONCURRENT; + if (rd_flags & NL80211_RRF_IR_CONCURRENT) + channel_flags |= IEEE80211_CHAN_IR_CONCURRENT; if (rd_flags & NL80211_RRF_NO_HT40MINUS) channel_flags |= IEEE80211_CHAN_NO_HT40MINUS; if (rd_flags & NL80211_RRF_NO_HT40PLUS) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d11454f87bac..8020b5b094d4 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -938,7 +938,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, } void cfg80211_disconnected(struct net_device *dev, u16 reason, - const u8 *ie, size_t ie_len, gfp_t gfp) + const u8 *ie, size_t ie_len, + bool locally_generated, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -954,6 +955,7 @@ void cfg80211_disconnected(struct net_device *dev, u16 reason, ev->dc.ie_len = ie_len; memcpy((void *)ev->dc.ie, ie, ie_len); ev->dc.reason = reason; + ev->dc.locally_generated = locally_generated; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 9ee6bc1a7610..9cee0220665d 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -86,7 +86,7 @@ static int wiphy_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static void cfg80211_leave_all(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; @@ -95,7 +95,7 @@ static void cfg80211_leave_all(struct cfg80211_registered_device *rdev) cfg80211_leave(rdev, wdev); } -static int wiphy_suspend(struct device *dev, pm_message_t state) +static int wiphy_suspend(struct device *dev) { struct cfg80211_registered_device *rdev = dev_to_rdev(dev); int ret = 0; @@ -136,6 +136,11 @@ static int wiphy_resume(struct device *dev) return ret; } + +static SIMPLE_DEV_PM_OPS(wiphy_pm_ops, wiphy_suspend, wiphy_resume); +#define WIPHY_PM_OPS (&wiphy_pm_ops) +#else +#define WIPHY_PM_OPS NULL #endif static const void *wiphy_namespace(struct device *d) @@ -151,10 +156,7 @@ struct class ieee80211_class = { .dev_release = wiphy_dev_release, .dev_groups = ieee80211_groups, .dev_uevent = wiphy_uevent, -#ifdef CONFIG_PM - .suspend = wiphy_suspend, - .resume = wiphy_resume, -#endif + .pm = WIPHY_PM_OPS, .ns_type = &net_ns_type_operations, .namespace = wiphy_namespace, }; diff --git a/net/wireless/util.c b/net/wireless/util.c index 70051ab52f4f..baf7218cec15 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -887,7 +887,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) case EVENT_DISCONNECTED: __cfg80211_disconnected(wdev->netdev, ev->dc.ie, ev->dc.ie_len, - ev->dc.reason, true); + ev->dc.reason, + !ev->dc.locally_generated); break; case EVENT_IBSS_JOINED: __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid, @@ -944,7 +945,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, ntype == NL80211_IFTYPE_P2P_CLIENT)) return -EBUSY; - if (ntype != otype && netif_running(dev)) { + if (ntype != otype) { dev->ieee80211_ptr->use_4addr = false; dev->ieee80211_ptr->mesh_id_up_len = 0; wdev_lock(dev->ieee80211_ptr); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index c3ab230e4493..a750f330b8dd 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -515,10 +515,10 @@ static struct proto x25_proto = { .obj_size = sizeof(struct x25_sock), }; -static struct sock *x25_alloc_socket(struct net *net) +static struct sock *x25_alloc_socket(struct net *net, int kern) { struct x25_sock *x25; - struct sock *sk = sk_alloc(net, AF_X25, GFP_ATOMIC, &x25_proto); + struct sock *sk = sk_alloc(net, AF_X25, GFP_ATOMIC, &x25_proto, kern); if (!sk) goto out; @@ -553,7 +553,7 @@ static int x25_create(struct net *net, struct socket *sock, int protocol, goto out; rc = -ENOBUFS; - if ((sk = x25_alloc_socket(net)) == NULL) + if ((sk = x25_alloc_socket(net, kern)) == NULL) goto out; x25 = x25_sk(sk); @@ -602,7 +602,7 @@ static struct sock *x25_make_new(struct sock *osk) if (osk->sk_type != SOCK_SEQPACKET) goto out; - if ((sk = x25_alloc_socket(sock_net(osk))) == NULL) + if ((sk = x25_alloc_socket(sock_net(osk), 0)) == NULL) goto out; x25 = x25_sk(sk); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index b58286ecd156..60ce7014e1b0 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -31,7 +31,7 @@ int xfrm_input_register_afinfo(struct xfrm_input_afinfo *afinfo) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_input_afinfo_lock); if (unlikely(xfrm_input_afinfo[afinfo->family] != NULL)) - err = -ENOBUFS; + err = -EEXIST; else rcu_assign_pointer(xfrm_input_afinfo[afinfo->family], afinfo); spin_unlock_bh(&xfrm_input_afinfo_lock); @@ -254,13 +254,13 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; spin_lock(&x->lock); - if (unlikely(x->km.state == XFRM_STATE_ACQ)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); - goto drop_unlock; - } if (unlikely(x->km.state != XFRM_STATE_VALID)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); + if (x->km.state == XFRM_STATE_ACQ) + XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); + else + XFRM_INC_STATS(net, + LINUX_MIB_XFRMINSTATEINVALID); goto drop_unlock; } diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index fbcedbe33190..68ada2ca4b60 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -38,6 +38,18 @@ static int xfrm_skb_check_space(struct sk_buff *skb) return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC); } +/* Children define the path of the packet through the + * Linux networking. Thus, destinations are stackable. + */ + +static struct dst_entry *skb_dst_pop(struct sk_buff *skb) +{ + struct dst_entry *child = dst_clone(skb_dst(skb)->child); + + skb_dst_drop(skb); + return child; +} + static int xfrm_output_one(struct sk_buff *skb, int err) { struct dst_entry *dst = skb_dst(skb); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 638af0655aaf..18cead7645be 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -315,14 +315,6 @@ void xfrm_policy_destroy(struct xfrm_policy *policy) } EXPORT_SYMBOL(xfrm_policy_destroy); -static void xfrm_queue_purge(struct sk_buff_head *list) -{ - struct sk_buff *skb; - - while ((skb = skb_dequeue(list)) != NULL) - kfree_skb(skb); -} - /* Rule must be locked. Release descentant resources, announce * entry dead. The rule must be unlinked from lists to the moment. */ @@ -335,7 +327,7 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) if (del_timer(&policy->polq.hold_timer)) xfrm_pol_put(policy); - xfrm_queue_purge(&policy->polq.hold_queue); + skb_queue_purge(&policy->polq.hold_queue); if (del_timer(&policy->timer)) xfrm_pol_put(policy); @@ -708,6 +700,9 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, struct xfrm_policy_queue *pq = &old->polq; struct sk_buff_head list; + if (skb_queue_empty(&pq->hold_queue)) + return; + __skb_queue_head_init(&list); spin_lock_bh(&pq->hold_queue.lock); @@ -716,9 +711,6 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); - if (skb_queue_empty(&list)) - return; - pq = &new->polq; spin_lock_bh(&pq->hold_queue.lock); @@ -1012,7 +1004,9 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else - x = list_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all); + x = list_first_entry(&walk->walk.all, + struct xfrm_policy_walk_entry, all); + list_for_each_entry_from(x, &net->xfrm.policy_all, all) { if (x->dead) continue; @@ -1120,6 +1114,9 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } chain = &net->xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, chain, bydst) { + if ((pol->priority >= priority) && ret) + break; + err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -1128,13 +1125,13 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, ret = ERR_PTR(err); goto fail; } - } else if (pol->priority < priority) { + } else { ret = pol; break; } } - if (ret) - xfrm_pol_hold(ret); + + xfrm_pol_hold(ret); fail: read_unlock_bh(&net->xfrm.xfrm_policy_lock); @@ -1955,7 +1952,7 @@ out: purge_queue: pq->timeout = 0; - xfrm_queue_purge(&pq->hold_queue); + skb_queue_purge(&pq->hold_queue); xfrm_pol_put(pol); } @@ -2814,7 +2811,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) return -EAFNOSUPPORT; spin_lock(&xfrm_policy_afinfo_lock); if (unlikely(xfrm_policy_afinfo[afinfo->family] != NULL)) - err = -ENOBUFS; + err = -EEXIST; else { struct dst_ops *dst_ops = afinfo->dst_ops; if (likely(dst_ops->kmem_cachep == NULL)) @@ -3209,16 +3206,17 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector * } chain = &net->xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, chain, bydst) { + if ((pol->priority >= priority) && ret) + break; + if (xfrm_migrate_selector_match(sel, &pol->selector) && - pol->type == type && - pol->priority < priority) { + pol->type == type) { ret = pol; break; } } - if (ret) - xfrm_pol_hold(ret); + xfrm_pol_hold(ret); read_unlock_bh(&net->xfrm.xfrm_policy_lock); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 96688cd0f6f1..9895a8c56d8c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1626,7 +1626,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, if (list_empty(&walk->all)) x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else - x = list_entry(&walk->all, struct xfrm_state_walk, all); + x = list_first_entry(&walk->all, struct xfrm_state_walk, all); list_for_each_entry_from(x, &net->xfrm.state_all, all) { if (x->state == XFRM_STATE_DEAD) continue; @@ -1908,7 +1908,7 @@ int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) - err = -ENOBUFS; + err = -EEXIST; else rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo); spin_unlock_bh(&xfrm_state_afinfo_lock); |