diff options
Diffstat (limited to 'net')
150 files changed, 3560 insertions, 1373 deletions
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index a8cb6b2e20c1..4072e9d394d6 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -953,8 +953,8 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, if (copy > len) copy = len; vaddr = kmap_atomic(skb_frag_page(frag)); - sum = atalk_sum_partial(vaddr + frag->page_offset + - offset - start, copy, sum); + sum = atalk_sum_partial(vaddr + skb_frag_off(frag) + + offset - start, copy, sum); kunmap_atomic(vaddr); if (!(len -= copy)) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 22672cb3e25d..64054edc2e3c 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -79,6 +79,7 @@ static int batadv_v_iface_enable(struct batadv_hard_iface *hard_iface) static void batadv_v_iface_disable(struct batadv_hard_iface *hard_iface) { + batadv_v_ogm_iface_disable(hard_iface); batadv_v_elp_iface_disable(hard_iface); } @@ -1081,6 +1082,12 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface) */ atomic_set(&hard_iface->bat_v.throughput_override, 0); atomic_set(&hard_iface->bat_v.elp_interval, 500); + + hard_iface->bat_v.aggr_len = 0; + skb_queue_head_init(&hard_iface->bat_v.aggr_list); + spin_lock_init(&hard_iface->bat_v.aggr_list_lock); + INIT_DELAYED_WORK(&hard_iface->bat_v.aggr_wq, + batadv_v_ogm_aggr_work); } /** diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index fad95ef64e01..319249f0f85f 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -17,12 +17,14 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> @@ -77,6 +79,20 @@ struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv, } /** + * batadv_v_ogm_start_queue_timer() - restart the OGM aggregation timer + * @hard_iface: the interface to use to send the OGM + */ +static void batadv_v_ogm_start_queue_timer(struct batadv_hard_iface *hard_iface) +{ + unsigned int msecs = BATADV_MAX_AGGREGATION_MS * 1000; + + /* msecs * [0.9, 1.1] */ + msecs += prandom_u32() % (msecs / 5) - (msecs / 10); + queue_delayed_work(batadv_event_workqueue, &hard_iface->bat_v.aggr_wq, + msecs_to_jiffies(msecs / 1000)); +} + +/** * batadv_v_ogm_start_timer() - restart the OGM sending timer * @bat_priv: the bat priv with all the soft interface information */ @@ -116,6 +132,130 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, } /** + * batadv_v_ogm_len() - OGMv2 packet length + * @skb: the OGM to check + * + * Return: Length of the given OGMv2 packet, including tvlv length, excluding + * ethernet header length. + */ +static unsigned int batadv_v_ogm_len(struct sk_buff *skb) +{ + struct batadv_ogm2_packet *ogm_packet; + + ogm_packet = (struct batadv_ogm2_packet *)skb->data; + return BATADV_OGM2_HLEN + ntohs(ogm_packet->tvlv_len); +} + +/** + * batadv_v_ogm_queue_left() - check if given OGM still fits aggregation queue + * @skb: the OGM to check + * @hard_iface: the interface to use to send the OGM + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + * + * Return: True, if the given OGMv2 packet still fits, false otherwise. + */ +static bool batadv_v_ogm_queue_left(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface) +{ + unsigned int max = min_t(unsigned int, hard_iface->net_dev->mtu, + BATADV_MAX_AGGREGATION_BYTES); + unsigned int ogm_len = batadv_v_ogm_len(skb); + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + return hard_iface->bat_v.aggr_len + ogm_len <= max; +} + +/** + * batadv_v_ogm_aggr_list_free - free all elements in an aggregation queue + * @hard_iface: the interface holding the aggregation queue + * + * Empties the OGMv2 aggregation queue and frees all the skbs it contained. + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + */ +static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) +{ + struct sk_buff *skb; + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) + kfree_skb(skb); + + hard_iface->bat_v.aggr_len = 0; +} + +/** + * batadv_v_ogm_aggr_send() - flush & send aggregation queue + * @hard_iface: the interface with the aggregation queue to flush + * + * Aggregates all OGMv2 packets currently in the aggregation queue into a + * single OGMv2 packet and transmits this aggregate. + * + * The aggregation queue is empty after this call. + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + */ +static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) +{ + unsigned int aggr_len = hard_iface->bat_v.aggr_len; + struct sk_buff *skb_aggr; + unsigned int ogm_len; + struct sk_buff *skb; + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + if (!aggr_len) + return; + + skb_aggr = dev_alloc_skb(aggr_len + ETH_HLEN + NET_IP_ALIGN); + if (!skb_aggr) { + batadv_v_ogm_aggr_list_free(hard_iface); + return; + } + + skb_reserve(skb_aggr, ETH_HLEN + NET_IP_ALIGN); + skb_reset_network_header(skb_aggr); + + while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) { + hard_iface->bat_v.aggr_len -= batadv_v_ogm_len(skb); + + ogm_len = batadv_v_ogm_len(skb); + skb_put_data(skb_aggr, skb->data, ogm_len); + + consume_skb(skb); + } + + batadv_v_ogm_send_to_if(skb_aggr, hard_iface); +} + +/** + * batadv_v_ogm_queue_on_if() - queue a batman ogm on a given interface + * @skb: the OGM to queue + * @hard_iface: the interface to queue the OGM on + */ +static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface) +{ + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + + if (!atomic_read(&bat_priv->aggregated_ogms)) { + batadv_v_ogm_send_to_if(skb, hard_iface); + return; + } + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + if (!batadv_v_ogm_queue_left(skb, hard_iface)) + batadv_v_ogm_aggr_send(hard_iface); + + hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb); + skb_queue_tail(&hard_iface->bat_v.aggr_list, skb); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); +} + +/** * batadv_v_ogm_send() - periodic worker broadcasting the own OGM * @work: work queue item */ @@ -210,7 +350,7 @@ static void batadv_v_ogm_send(struct work_struct *work) break; } - batadv_v_ogm_send_to_if(skb_tmp, hard_iface); + batadv_v_ogm_queue_on_if(skb_tmp, hard_iface); batadv_hardif_put(hard_iface); } rcu_read_unlock(); @@ -224,6 +364,27 @@ out: } /** + * batadv_v_ogm_aggr_work() - OGM queue periodic task per interface + * @work: work queue item + * + * Emits aggregated OGM message in regular intervals. + */ +void batadv_v_ogm_aggr_work(struct work_struct *work) +{ + struct batadv_hard_iface_bat_v *batv; + struct batadv_hard_iface *hard_iface; + + batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work); + hard_iface = container_of(batv, struct batadv_hard_iface, bat_v); + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + batadv_v_ogm_aggr_send(hard_iface); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); + + batadv_v_ogm_start_queue_timer(hard_iface); +} + +/** * batadv_v_ogm_iface_enable() - prepare an interface for B.A.T.M.A.N. V * @hard_iface: the interface to prepare * @@ -235,12 +396,26 @@ int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + batadv_v_ogm_start_queue_timer(hard_iface); batadv_v_ogm_start_timer(bat_priv); return 0; } /** + * batadv_v_ogm_iface_disable() - release OGM interface private resources + * @hard_iface: interface for which the resources have to be released + */ +void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface) +{ + cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq); + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + batadv_v_ogm_aggr_list_free(hard_iface); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); +} + +/** * batadv_v_ogm_primary_iface_set() - set a new primary interface * @primary_iface: the new primary interface */ @@ -382,7 +557,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, if_outgoing->net_dev->name, ntohl(ogm_forward->throughput), ogm_forward->ttl, if_incoming->net_dev->name); - batadv_v_ogm_send_to_if(skb, if_outgoing); + batadv_v_ogm_queue_on_if(skb, if_outgoing); out: if (orig_ifinfo) diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index 2a50df7fc2bf..bf16d040461d 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -11,10 +11,13 @@ #include <linux/skbuff.h> #include <linux/types.h> +#include <linux/workqueue.h> int batadv_v_ogm_init(struct batadv_priv *bat_priv); void batadv_v_ogm_free(struct batadv_priv *bat_priv); +void batadv_v_ogm_aggr_work(struct work_struct *work); int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface); +void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface); struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr); void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 3d4c04d87ff3..6967f2e4c3f4 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2019.3" +#define BATADV_SOURCE_VERSION "2019.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index c7a2e77ca1da..a1146cb10919 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -943,10 +943,10 @@ static const struct net_device_ops batadv_netdev_ops = { static void batadv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver)); - strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version)); - strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); - strlcpy(info->bus_info, "batman", sizeof(info->bus_info)); + strscpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver)); + strscpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version)); + strscpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strscpy(info->bus_info, "batman", sizeof(info->bus_info)); } /* Inspired by drivers/net/ethernet/dlink/sundance.c:1702 diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 1efcb97039cd..e5bbc28ed12c 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1070,7 +1070,7 @@ static ssize_t batadv_store_mesh_iface(struct kobject *kobj, dev_hold(net_dev); INIT_WORK(&store_work->work, batadv_store_mesh_iface_work); store_work->net_dev = net_dev; - strlcpy(store_work->soft_iface_name, buff, + strscpy(store_work->soft_iface_name, buff, sizeof(store_work->soft_iface_name)); queue_work(batadv_event_workqueue, &store_work->work); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 6ae139d74e0f..be7c02aa91e2 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -117,6 +117,18 @@ struct batadv_hard_iface_bat_v { /** @elp_wq: workqueue used to schedule ELP transmissions */ struct delayed_work elp_wq; + /** @aggr_wq: workqueue used to transmit queued OGM packets */ + struct delayed_work aggr_wq; + + /** @aggr_list: queue for to be aggregated OGM packets */ + struct sk_buff_head aggr_list; + + /** @aggr_len: size of the OGM aggregate (excluding ethernet header) */ + unsigned int aggr_len; + + /** @aggr_list_lock: protects aggr_list */ + spinlock_t aggr_list_lock; + /** * @throughput_override: throughput override to disable link * auto-detection diff --git a/net/bridge/br.c b/net/bridge/br.c index d164f63a4345..8a8f9e5f264f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -37,12 +37,15 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v int err; if (dev->priv_flags & IFF_EBRIDGE) { + err = br_vlan_bridge_event(dev, event, ptr); + if (err) + return notifier_from_errno(err); + if (event == NETDEV_REGISTER) { /* register of bridge completed, add sysfs entries */ br_sysfs_addbr(dev); return NOTIFY_DONE; } - br_vlan_bridge_event(dev, event, ptr); } /* not a port of a bridge */ diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index bf6acd34234d..428af1abf8cc 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -60,6 +60,8 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) e->flags = 0; if (flags & MDB_PG_FLAGS_OFFLOAD) e->flags |= MDB_FLAGS_OFFLOAD; + if (flags & MDB_PG_FLAGS_FAST_LEAVE) + e->flags |= MDB_FLAGS_FAST_LEAVE; } static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3d8deac2353d..9b379e110129 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1388,12 +1388,15 @@ br_multicast_leave_group(struct net_bridge *br, if (!br_port_group_equal(p, port, src)) continue; + if (p->flags & MDB_PG_FLAGS_PERMANENT) + break; + rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); kfree_rcu(p, rcu); br_mdb_notify(br->dev, port, group, RTM_DELMDB, - p->flags); + p->flags | MDB_PG_FLAGS_FAST_LEAVE); if (!mp->ports && !mp->host_joined && netif_running(br->dev)) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e8cf03b43b7d..b7a4942ff1b3 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -199,6 +199,7 @@ struct net_bridge_fdb_entry { #define MDB_PG_FLAGS_PERMANENT BIT(0) #define MDB_PG_FLAGS_OFFLOAD BIT(1) +#define MDB_PG_FLAGS_FAST_LEAVE BIT(2) struct net_bridge_port_group { struct net_bridge_port *port; @@ -894,8 +895,8 @@ int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask); void br_vlan_get_stats(const struct net_bridge_vlan *v, struct br_vlan_stats *stats); void br_vlan_port_event(struct net_bridge_port *p, unsigned long event); -void br_vlan_bridge_event(struct net_device *dev, unsigned long event, - void *ptr); +int br_vlan_bridge_event(struct net_device *dev, unsigned long event, + void *ptr); static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) @@ -1085,9 +1086,10 @@ static inline void br_vlan_port_event(struct net_bridge_port *p, { } -static inline void br_vlan_bridge_event(struct net_device *dev, - unsigned long event, void *ptr) +static inline int br_vlan_bridge_event(struct net_device *dev, + unsigned long event, void *ptr) { + return 0; } #endif diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 021cc9f66804..f5b2aeebbfe9 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1053,7 +1053,6 @@ int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; - bool changed; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) @@ -1068,17 +1067,10 @@ int br_vlan_init(struct net_bridge *br) br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); - ret = br_vlan_add(br, 1, - BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); - if (ret) - goto err_vlan_add; out: return ret; -err_vlan_add: - vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: @@ -1464,13 +1456,23 @@ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) } /* Must be protected by RTNL. */ -void br_vlan_bridge_event(struct net_device *dev, unsigned long event, - void *ptr) +int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; - struct net_bridge *br; + struct net_bridge *br = netdev_priv(dev); + bool changed; + int ret = 0; switch (event) { + case NETDEV_REGISTER: + ret = br_vlan_add(br, br->default_pvid, + BRIDGE_VLAN_INFO_PVID | + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); + break; + case NETDEV_UNREGISTER: + br_vlan_delete(br, br->default_pvid); + break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); @@ -1478,12 +1480,13 @@ void br_vlan_bridge_event(struct net_device *dev, unsigned long event, case NETDEV_CHANGE: case NETDEV_UP: - br = netdev_priv(dev); if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) - return; + break; br_vlan_link_state_change(dev, br); break; } + + return ret; } /* Must be protected by RTNL. */ diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 963dfdc14827..c8177a89f52c 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1770,20 +1770,28 @@ static int compat_calc_entry(const struct ebt_entry *e, return 0; } +static int ebt_compat_init_offsets(unsigned int number) +{ + if (number > INT_MAX) + return -EINVAL; + + /* also count the base chain policies */ + number += NF_BR_NUMHOOKS; + + return xt_compat_init_offsets(NFPROTO_BRIDGE, number); +} static int compat_table_info(const struct ebt_table_info *info, struct compat_ebt_replace *newinfo) { unsigned int size = info->entries_size; const void *entries = info->entries; + int ret; newinfo->entries_size = size; - if (info->nentries) { - int ret = xt_compat_init_offsets(NFPROTO_BRIDGE, - info->nentries); - if (ret) - return ret; - } + ret = ebt_compat_init_offsets(info->nentries); + if (ret) + return ret; return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); @@ -2234,11 +2242,9 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - if (tmp.nentries) { - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; - } + ret = ebt_compat_init_offsets(tmp.nentries); + if (ret < 0) + goto out_unlock; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) @@ -2261,8 +2267,10 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - if (WARN_ON(ret < 0)) + if (WARN_ON(ret < 0)) { + vfree(entries_tmp); goto out_unlock; + } vfree(entries_tmp); tmp.entries_size = size64; diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index bed66f536b34..1804e867f715 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -30,13 +30,9 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, switch (priv->key) { case NFT_META_BRI_IIFNAME: br_dev = nft_meta_get_bridge(in); - if (!br_dev) - goto err; break; case NFT_META_BRI_OIFNAME: br_dev = nft_meta_get_bridge(out); - if (!br_dev) - goto err; break; case NFT_META_BRI_IIFPVID: { u16 p_pvid; @@ -61,13 +57,11 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, return; } default: - goto out; + return nft_meta_get_eval(expr, regs, pkt); } - strncpy((char *)dest, br_dev->name, IFNAMSIZ); + strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; -out: - return nft_meta_get_eval(expr, regs, pkt); err: regs->verdict.code = NFT_BREAK; } diff --git a/net/can/Kconfig b/net/can/Kconfig index 0f9fe846ddef..d4319aa3e1b1 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -8,11 +8,12 @@ menuconfig CAN tristate "CAN bus subsystem support" ---help--- Controller Area Network (CAN) is a slow (up to 1Mbit/s) serial - communications protocol which was developed by Bosch in - 1991, mainly for automotive, but now widely used in marine - (NMEA2000), industrial, and medical applications. - More information on the CAN network protocol family PF_CAN - is contained in <Documentation/networking/can.rst>. + communications protocol. Development of the CAN bus started in + 1983 at Robert Bosch GmbH, and the protocol was officially + released in 1986. The CAN bus was originally mainly for automotive, + but is now widely used in marine (NMEA2000), industrial, and medical + applications. More information on the CAN network protocol family + PF_CAN is contained in <Documentation/networking/can.rst>. If you want CAN support you should say Y here and also to the specific driver for your controller(s) below. diff --git a/net/can/af_can.c b/net/can/af_can.c index 80281ef2ccbd..76cf83b2bd40 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * af_can.c - Protocol family CAN core module * (used by different CAN protocol modules) @@ -87,15 +88,6 @@ static atomic_t skbcounter = ATOMIC_INIT(0); * af_can socket functions */ -int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - default: - return -ENOIOCTLCMD; - } -} -EXPORT_SYMBOL(can_ioctl); - static void can_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); diff --git a/net/can/af_can.h b/net/can/af_can.h index 9cb3719632bd..ef21f7c6bc80 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. diff --git a/net/can/bcm.c b/net/can/bcm.c index a34ee52f19ea..bf1d0bbecec8 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content * @@ -1679,6 +1680,13 @@ static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, return size; } +int bcm_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + /* no ioctls for socket layer -> hand it down to NIC layer */ + return -ENOIOCTLCMD; +} + static const struct proto_ops bcm_ops = { .family = PF_CAN, .release = bcm_release, @@ -1688,7 +1696,7 @@ static const struct proto_ops bcm_ops = { .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, - .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .ioctl = bcm_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, diff --git a/net/can/gw.c b/net/can/gw.c index 5275ddf580bc..ce17f836262b 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * gw.c - CAN frame Gateway/Router/Bridge with netlink interface * @@ -1046,32 +1047,50 @@ static __init int cgw_module_init(void) pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n", max_hops); - register_pernet_subsys(&cangw_pernet_ops); + ret = register_pernet_subsys(&cangw_pernet_ops); + if (ret) + return ret; + + ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); - if (!cgw_cache) - return -ENOMEM; + goto out_cache_create; /* set notifier */ notifier.notifier_call = cgw_notifier; - register_netdevice_notifier(¬ifier); + ret = register_netdevice_notifier(¬ifier); + if (ret) + goto out_register_notifier; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0); - if (ret) { - unregister_netdevice_notifier(¬ifier); - kmem_cache_destroy(cgw_cache); - return -ENOBUFS; - } - - /* Only the first call to rtnl_register_module can fail */ - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, - cgw_create_job, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, - cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register1; + + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, + cgw_create_job, NULL, 0); + if (ret) + goto out_rtnl_register2; + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, + cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register3; return 0; + +out_rtnl_register3: + rtnl_unregister(PF_CAN, RTM_NEWROUTE); +out_rtnl_register2: + rtnl_unregister(PF_CAN, RTM_GETROUTE); +out_rtnl_register1: + unregister_netdevice_notifier(¬ifier); +out_register_notifier: + kmem_cache_destroy(cgw_cache); +out_cache_create: + unregister_pernet_subsys(&cangw_pernet_ops); + + return ret; } static __exit void cgw_module_exit(void) diff --git a/net/can/proc.c b/net/can/proc.c index 70fea17bb04c..edb822c31902 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * proc.c - procfs support for Protocol family CAN core module * diff --git a/net/can/raw.c b/net/can/raw.c index afcbff063a67..da386f1fa815 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * raw.c - Raw sockets for protocol family CAN * @@ -836,6 +837,13 @@ static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, return size; } +int raw_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + /* no ioctls for socket layer -> hand it down to NIC layer */ + return -ENOIOCTLCMD; +} + static const struct proto_ops raw_ops = { .family = PF_CAN, .release = raw_release, @@ -845,7 +853,7 @@ static const struct proto_ops raw_ops = { .accept = sock_no_accept, .getname = raw_getname, .poll = datagram_poll, - .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .ioctl = raw_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, diff --git a/net/core/datagram.c b/net/core/datagram.c index 45a162ef5e02..4cc8dc5db2b7 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -442,8 +442,8 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, if (copy > len) copy = len; - n = cb(vaddr + frag->page_offset + - offset - start, copy, data, to); + n = cb(vaddr + skb_frag_off(frag) + offset - start, + copy, data, to); kunmap(page); offset += n; if (n != copy) @@ -573,7 +573,7 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, if (copy > len) copy = len; copied = copy_page_from_iter(skb_frag_page(frag), - frag->page_offset + offset - start, + skb_frag_off(frag) + offset - start, copy, from); if (copied != copy) goto fault; diff --git a/net/core/dev.c b/net/core/dev.c index fc676b2610e3..49589ed2018d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3963,6 +3963,8 @@ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; +/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ +int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -4374,12 +4376,17 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, act = bpf_prog_run_xdp(xdp_prog, xdp); + /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; - if (off > 0) - __skb_pull(skb, off); - else if (off < 0) - __skb_push(skb, -off); - skb->mac_header += off; + if (off) { + if (off > 0) + __skb_pull(skb, off); + else if (off < 0) + __skb_push(skb, -off); + + skb->mac_header += off; + skb_reset_network_header(skb); + } /* check if bpf_xdp_adjust_tail was used. it can only "shrink" * pckt. @@ -5481,7 +5488,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) skb->data_len -= grow; skb->tail += grow; - pinfo->frags[0].page_offset += grow; + skb_frag_off_add(&pinfo->frags[0], grow); skb_frag_size_sub(&pinfo->frags[0], grow); if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { @@ -5742,6 +5749,26 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) +{ + list_add_tail(&skb->list, &napi->rx_list); + if (++napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) @@ -5751,8 +5778,8 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, case GRO_HELD: __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, skb->dev); - if (ret == GRO_NORMAL && netif_receive_skb_internal(skb)) - ret = GRO_DROP; + if (ret == GRO_NORMAL) + gro_normal_one(napi, skb); break; case GRO_DROP: @@ -6029,6 +6056,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; + gro_normal_list(n); + if (n->gro_bitmask) { unsigned long timeout = 0; @@ -6114,10 +6143,19 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, BUSY_POLL_BUDGET); + /* We can't gro_normal_list() here, because napi->poll() might have + * rearmed the napi (napi_complete_done()) in which case it could + * already be running on another CPU. + */ trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); netpoll_poll_unlock(have_poll_lock); - if (rc == BUSY_POLL_BUDGET) + if (rc == BUSY_POLL_BUDGET) { + /* As the whole budget was spent, we still own the napi so can + * safely handle the rx_list. + */ + gro_normal_list(napi); __napi_schedule(napi); + } local_bh_enable(); } @@ -6162,6 +6200,7 @@ restart: } work = napi_poll(napi, BUSY_POLL_BUDGET); trace_napi_poll(napi, work, BUSY_POLL_BUDGET); + gro_normal_list(napi); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), @@ -6267,6 +6306,8 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, @@ -6363,6 +6404,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } + gro_normal_list(n); + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. @@ -9701,6 +9744,8 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); + if (__dev_get_by_name(&init_net, fb_name)) + snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/devlink.c b/net/core/devlink.c index 4f40aeace902..e3a1ae44f93d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -342,7 +342,6 @@ struct devlink_snapshot { struct list_head list; struct devlink_region *region; devlink_snapshot_data_dest_t *data_destructor; - u64 data_len; u8 *data; u32 id; }; @@ -371,14 +370,6 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) return NULL; } -static void devlink_region_snapshot_del(struct devlink_snapshot *snapshot) -{ - snapshot->region->cur_snapshots--; - list_del(&snapshot->list); - (*snapshot->data_destructor)(snapshot->data); - kfree(snapshot); -} - #define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) #define DEVLINK_NL_FLAG_NEED_PORT BIT(1) #define DEVLINK_NL_FLAG_NEED_SB BIT(2) @@ -3596,6 +3587,16 @@ out_free_msg: nlmsg_free(msg); } +static void devlink_region_snapshot_del(struct devlink_region *region, + struct devlink_snapshot *snapshot) +{ + devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); + region->cur_snapshots--; + list_del(&snapshot->list); + (*snapshot->data_destructor)(snapshot->data); + kfree(snapshot); +} + static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -3691,8 +3692,7 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb, if (!snapshot) return -EINVAL; - devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); - devlink_region_snapshot_del(snapshot); + devlink_region_snapshot_del(region, snapshot); return 0; } @@ -3748,8 +3748,8 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb, if (!snapshot) return -EINVAL; - if (end_offset > snapshot->data_len || dump) - end_offset = snapshot->data_len; + if (end_offset > region->size || dump) + end_offset = region->size; while (curr_offset < end_offset) { u32 data_size; @@ -6744,7 +6744,7 @@ void devlink_region_destroy(struct devlink_region *region) /* Free all snapshots of region */ list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list) - devlink_region_snapshot_del(snapshot); + devlink_region_snapshot_del(region, snapshot); list_del(®ion->list); @@ -6784,12 +6784,11 @@ EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get); * The @snapshot_id should be obtained using the getter function. * * @region: devlink region of the snapshot - * @data_len: size of snapshot data * @data: snapshot data * @snapshot_id: snapshot id to be created * @data_destructor: pointer to destructor function to free data */ -int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, +int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor) { @@ -6819,7 +6818,6 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, snapshot->id = snapshot_id; snapshot->region = region; snapshot->data = data; - snapshot->data_len = data_len; snapshot->data_destructor = data_destructor; list_add_tail(&snapshot->list, ®ion->snapshot_list); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 4ea4347f5062..39e094907391 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -43,13 +43,26 @@ * netlink alerts */ static int trace_state = TRACE_OFF; -static DEFINE_MUTEX(trace_state_mutex); + +/* net_dm_mutex + * + * An overall lock guarding every operation coming from userspace. + * It also guards the global 'hw_stats_list' list. + */ +static DEFINE_MUTEX(net_dm_mutex); + +struct net_dm_stats { + u64 dropped; + struct u64_stats_sync syncp; +}; struct per_cpu_dm_data { - spinlock_t lock; + spinlock_t lock; /* Protects 'skb' and 'send_timer' */ struct sk_buff *skb; + struct sk_buff_head drop_queue; struct work_struct dm_alert_work; struct timer_list send_timer; + struct net_dm_stats stats; }; struct dm_hw_stat_delta { @@ -69,6 +82,24 @@ static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); +static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY; +static u32 net_dm_trunc_len; +static u32 net_dm_queue_len = 1000; + +struct net_dm_alert_ops { + void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, + void *location); + void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, + int work, int budget); + void (*work_item_func)(struct work_struct *work); +}; + +struct net_dm_skb_cb { + void *pc; +}; + +#define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) + static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; @@ -235,48 +266,330 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, rcu_read_unlock(); } -static int set_all_monitor_traces(int state) +static const struct net_dm_alert_ops net_dm_alert_summary_ops = { + .kfree_skb_probe = trace_kfree_skb_hit, + .napi_poll_probe = trace_napi_poll_hit, + .work_item_func = send_dm_alert, +}; + +static void net_dm_packet_trace_kfree_skb_hit(void *ignore, + struct sk_buff *skb, + void *location) { - int rc = 0; - struct dm_hw_stat_delta *new_stat = NULL; - struct dm_hw_stat_delta *temp; + ktime_t tstamp = ktime_get_real(); + struct per_cpu_dm_data *data; + struct sk_buff *nskb; + unsigned long flags; - mutex_lock(&trace_state_mutex); + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return; - if (state == trace_state) { - rc = -EAGAIN; - goto out_unlock; + NET_DM_SKB_CB(nskb)->pc = location; + /* Override the timestamp because we care about the time when the + * packet was dropped. + */ + nskb->tstamp = tstamp; + + data = this_cpu_ptr(&dm_cpu_data); + + spin_lock_irqsave(&data->drop_queue.lock, flags); + if (skb_queue_len(&data->drop_queue) < net_dm_queue_len) + __skb_queue_tail(&data->drop_queue, nskb); + else + goto unlock_free; + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + + schedule_work(&data->dm_alert_work); + + return; + +unlock_free: + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + u64_stats_update_begin(&data->stats.syncp); + data->stats.dropped++; + u64_stats_update_end(&data->stats.syncp); + consume_skb(nskb); +} + +static void net_dm_packet_trace_napi_poll_hit(void *ignore, + struct napi_struct *napi, + int work, int budget) +{ +} + +static size_t net_dm_in_port_size(void) +{ + /* NET_DM_ATTR_IN_PORT nest */ + return nla_total_size(0) + + /* NET_DM_ATTR_PORT_NETDEV_IFINDEX */ + nla_total_size(sizeof(u32)); +} + +#define NET_DM_MAX_SYMBOL_LEN 40 + +static size_t net_dm_packet_report_size(size_t payload_len) +{ + size_t size; + + size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); + + return NLMSG_ALIGN(size) + + /* NET_DM_ATTR_PC */ + nla_total_size(sizeof(u64)) + + /* NET_DM_ATTR_SYMBOL */ + nla_total_size(NET_DM_MAX_SYMBOL_LEN + 1) + + /* NET_DM_ATTR_IN_PORT */ + net_dm_in_port_size() + + /* NET_DM_ATTR_TIMESTAMP */ + nla_total_size(sizeof(struct timespec)) + + /* NET_DM_ATTR_ORIG_LEN */ + nla_total_size(sizeof(u32)) + + /* NET_DM_ATTR_PROTO */ + nla_total_size(sizeof(u16)) + + /* NET_DM_ATTR_PAYLOAD */ + nla_total_size(payload_len); +} + +static int net_dm_packet_report_in_port_put(struct sk_buff *msg, int ifindex) +{ + struct nlattr *attr; + + attr = nla_nest_start(msg, NET_DM_ATTR_IN_PORT); + if (!attr) + return -EMSGSIZE; + + if (ifindex && + nla_put_u32(msg, NET_DM_ATTR_PORT_NETDEV_IFINDEX, ifindex)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, + size_t payload_len) +{ + u64 pc = (u64)(uintptr_t) NET_DM_SKB_CB(skb)->pc; + char buf[NET_DM_MAX_SYMBOL_LEN]; + struct nlattr *attr; + struct timespec ts; + void *hdr; + int rc; + + hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, + NET_DM_CMD_PACKET_ALERT); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, pc, NET_DM_ATTR_PAD)) + goto nla_put_failure; + + snprintf(buf, sizeof(buf), "%pS", NET_DM_SKB_CB(skb)->pc); + if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) + goto nla_put_failure; + + rc = net_dm_packet_report_in_port_put(msg, skb->skb_iif); + if (rc) + goto nla_put_failure; + + if (ktime_to_timespec_cond(skb->tstamp, &ts) && + nla_put(msg, NET_DM_ATTR_TIMESTAMP, sizeof(ts), &ts)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) + goto nla_put_failure; + + if (!payload_len) + goto out; + + if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) + goto nla_put_failure; + + attr = skb_put(msg, nla_total_size(payload_len)); + attr->nla_type = NET_DM_ATTR_PAYLOAD; + attr->nla_len = nla_attr_size(payload_len); + if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +#define NET_DM_MAX_PACKET_SIZE (0xffff - NLA_HDRLEN - NLA_ALIGNTO) + +static void net_dm_packet_report(struct sk_buff *skb) +{ + struct sk_buff *msg; + size_t payload_len; + int rc; + + /* Make sure we start copying the packet from the MAC header */ + if (skb->data > skb_mac_header(skb)) + skb_push(skb, skb->data - skb_mac_header(skb)); + else + skb_pull(skb, skb_mac_header(skb) - skb->data); + + /* Ensure packet fits inside a single netlink attribute */ + payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); + if (net_dm_trunc_len) + payload_len = min_t(size_t, net_dm_trunc_len, payload_len); + + msg = nlmsg_new(net_dm_packet_report_size(payload_len), GFP_KERNEL); + if (!msg) + goto out; + + rc = net_dm_packet_report_fill(msg, skb, payload_len); + if (rc) { + nlmsg_free(msg); + goto out; } - switch (state) { - case TRACE_ON: - if (!try_module_get(THIS_MODULE)) { - rc = -ENODEV; - break; - } + genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); - rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL); - rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL); - break; +out: + consume_skb(skb); +} - case TRACE_OFF: - rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL); - rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL); +static void net_dm_packet_work(struct work_struct *work) +{ + struct per_cpu_dm_data *data; + struct sk_buff_head list; + struct sk_buff *skb; + unsigned long flags; + + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); - tracepoint_synchronize_unregister(); + __skb_queue_head_init(&list); - /* - * Clean the device list + spin_lock_irqsave(&data->drop_queue.lock, flags); + skb_queue_splice_tail_init(&data->drop_queue, &list); + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + + while ((skb = __skb_dequeue(&list))) + net_dm_packet_report(skb); +} + +static const struct net_dm_alert_ops net_dm_alert_packet_ops = { + .kfree_skb_probe = net_dm_packet_trace_kfree_skb_hit, + .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, + .work_item_func = net_dm_packet_work, +}; + +static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { + [NET_DM_ALERT_MODE_SUMMARY] = &net_dm_alert_summary_ops, + [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, +}; + +static int net_dm_trace_on_set(struct netlink_ext_ack *extack) +{ + const struct net_dm_alert_ops *ops; + int cpu, rc; + + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + + if (!try_module_get(THIS_MODULE)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); + return -ENODEV; + } + + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct sk_buff *skb; + + INIT_WORK(&data->dm_alert_work, ops->work_item_func); + timer_setup(&data->send_timer, sched_send_work, 0); + /* Allocate a new per-CPU skb for the summary alert message and + * free the old one which might contain stale data from + * previous tracing. */ - list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { - if (new_stat->dev == NULL) { - list_del_rcu(&new_stat->list); - kfree_rcu(new_stat, rcu); - } + skb = reset_per_cpu_data(data); + consume_skb(skb); + } + + rc = register_trace_kfree_skb(ops->kfree_skb_probe, NULL); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to kfree_skb() tracepoint"); + goto err_module_put; + } + + rc = register_trace_napi_poll(ops->napi_poll_probe, NULL); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to napi_poll() tracepoint"); + goto err_unregister_trace; + } + + return 0; + +err_unregister_trace: + unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); +err_module_put: + module_put(THIS_MODULE); + return rc; +} + +static void net_dm_trace_off_set(void) +{ + struct dm_hw_stat_delta *new_stat, *temp; + const struct net_dm_alert_ops *ops; + int cpu; + + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + + unregister_trace_napi_poll(ops->napi_poll_probe, NULL); + unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); + + tracepoint_synchronize_unregister(); + + /* Make sure we do not send notifications to user space after request + * to stop tracing returns. + */ + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct sk_buff *skb; + + del_timer_sync(&data->send_timer); + cancel_work_sync(&data->dm_alert_work); + while ((skb = __skb_dequeue(&data->drop_queue))) + consume_skb(skb); + } + + list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { + if (new_stat->dev == NULL) { + list_del_rcu(&new_stat->list); + kfree_rcu(new_stat, rcu); } + } + + module_put(THIS_MODULE); +} + +static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack) +{ + int rc = 0; - module_put(THIS_MODULE); + if (state == trace_state) { + NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state"); + return -EAGAIN; + } + switch (state) { + case TRACE_ON: + rc = net_dm_trace_on_set(extack); + break; + case TRACE_OFF: + net_dm_trace_off_set(); break; default: rc = 1; @@ -288,17 +601,84 @@ static int set_all_monitor_traces(int state) else rc = -EINPROGRESS; -out_unlock: - mutex_unlock(&trace_state_mutex); - return rc; } +static int net_dm_alert_mode_get_from_info(struct genl_info *info, + enum net_dm_alert_mode *p_alert_mode) +{ + u8 val; + + val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]); + + switch (val) { + case NET_DM_ALERT_MODE_SUMMARY: /* fall-through */ + case NET_DM_ALERT_MODE_PACKET: + *p_alert_mode = val; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int net_dm_alert_mode_set(struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + enum net_dm_alert_mode alert_mode; + int rc; + + if (!info->attrs[NET_DM_ATTR_ALERT_MODE]) + return 0; + + rc = net_dm_alert_mode_get_from_info(info, &alert_mode); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Invalid alert mode"); + return -EINVAL; + } + + net_dm_alert_mode = alert_mode; + + return 0; +} + +static void net_dm_trunc_len_set(struct genl_info *info) +{ + if (!info->attrs[NET_DM_ATTR_TRUNC_LEN]) + return; + + net_dm_trunc_len = nla_get_u32(info->attrs[NET_DM_ATTR_TRUNC_LEN]); +} + +static void net_dm_queue_len_set(struct genl_info *info) +{ + if (!info->attrs[NET_DM_ATTR_QUEUE_LEN]) + return; + + net_dm_queue_len = nla_get_u32(info->attrs[NET_DM_ATTR_QUEUE_LEN]); +} static int net_dm_cmd_config(struct sk_buff *skb, struct genl_info *info) { - return -ENOTSUPP; + struct netlink_ext_ack *extack = info->extack; + int rc; + + if (trace_state == TRACE_ON) { + NL_SET_ERR_MSG_MOD(extack, "Cannot configure drop monitor while tracing is on"); + return -EBUSY; + } + + rc = net_dm_alert_mode_set(info); + if (rc) + return rc; + + net_dm_trunc_len_set(info); + + net_dm_queue_len_set(info); + + return 0; } static int net_dm_cmd_trace(struct sk_buff *skb, @@ -306,12 +686,146 @@ static int net_dm_cmd_trace(struct sk_buff *skb, { switch (info->genlhdr->cmd) { case NET_DM_CMD_START: - return set_all_monitor_traces(TRACE_ON); + return set_all_monitor_traces(TRACE_ON, info->extack); case NET_DM_CMD_STOP: - return set_all_monitor_traces(TRACE_OFF); + return set_all_monitor_traces(TRACE_OFF, info->extack); + } + + return -EOPNOTSUPP; +} + +static int net_dm_config_fill(struct sk_buff *msg, struct genl_info *info) +{ + void *hdr; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &net_drop_monitor_family, 0, NET_DM_CMD_CONFIG_NEW); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u8(msg, NET_DM_ATTR_ALERT_MODE, net_dm_alert_mode)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_TRUNC_LEN, net_dm_trunc_len)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_QUEUE_LEN, net_dm_queue_len)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int net_dm_cmd_config_get(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + int rc; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + rc = net_dm_config_fill(msg, info); + if (rc) + goto free_msg; + + return genlmsg_reply(msg, info); + +free_msg: + nlmsg_free(msg); + return rc; +} + +static void net_dm_stats_read(struct net_dm_stats *stats) +{ + int cpu; + + memset(stats, 0, sizeof(*stats)); + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct net_dm_stats *cpu_stats = &data->stats; + unsigned int start; + u64 dropped; + + do { + start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + dropped = cpu_stats->dropped; + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + + stats->dropped += dropped; } +} + +static int net_dm_stats_put(struct sk_buff *msg) +{ + struct net_dm_stats stats; + struct nlattr *attr; + + net_dm_stats_read(&stats); + + attr = nla_nest_start(msg, NET_DM_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, + stats.dropped, NET_DM_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} - return -ENOTSUPP; +static int net_dm_stats_fill(struct sk_buff *msg, struct genl_info *info) +{ + void *hdr; + int rc; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &net_drop_monitor_family, 0, NET_DM_CMD_STATS_NEW); + if (!hdr) + return -EMSGSIZE; + + rc = net_dm_stats_put(msg); + if (rc) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int net_dm_cmd_stats_get(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + int rc; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + rc = net_dm_stats_fill(msg, info); + if (rc) + goto free_msg; + + return genlmsg_reply(msg, info); + +free_msg: + nlmsg_free(msg); + return rc; } static int dropmon_net_event(struct notifier_block *ev_block, @@ -330,12 +844,12 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - mutex_lock(&trace_state_mutex); + mutex_lock(&net_dm_mutex); list_add_rcu(&new_stat->list, &hw_stats_list); - mutex_unlock(&trace_state_mutex); + mutex_unlock(&net_dm_mutex); break; case NETDEV_UNREGISTER: - mutex_lock(&trace_state_mutex); + mutex_lock(&net_dm_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { new_stat->dev = NULL; @@ -346,18 +860,26 @@ static int dropmon_net_event(struct notifier_block *ev_block, } } } - mutex_unlock(&trace_state_mutex); + mutex_unlock(&net_dm_mutex); break; } out: return NOTIFY_DONE; } +static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { + [NET_DM_ATTR_UNSPEC] = { .strict_start_type = NET_DM_ATTR_UNSPEC + 1 }, + [NET_DM_ATTR_ALERT_MODE] = { .type = NLA_U8 }, + [NET_DM_ATTR_TRUNC_LEN] = { .type = NLA_U32 }, + [NET_DM_ATTR_QUEUE_LEN] = { .type = NLA_U32 }, +}; + static const struct genl_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_config, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_START, @@ -369,12 +891,38 @@ static const struct genl_ops dropmon_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, }, + { + .cmd = NET_DM_CMD_CONFIG_GET, + .doit = net_dm_cmd_config_get, + }, + { + .cmd = NET_DM_CMD_STATS_GET, + .doit = net_dm_cmd_stats_get, + }, }; +static int net_dm_nl_pre_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + mutex_lock(&net_dm_mutex); + + return 0; +} + +static void net_dm_nl_post_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + mutex_unlock(&net_dm_mutex); +} + static struct genl_family net_drop_monitor_family __ro_after_init = { .hdrsize = 0, .name = "NET_DM", .version = 2, + .maxattr = NET_DM_ATTR_MAX, + .policy = net_dm_nl_policy, + .pre_doit = net_dm_nl_pre_doit, + .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, .ops = dropmon_ops, .n_ops = ARRAY_SIZE(dropmon_ops), @@ -415,13 +963,11 @@ static int __init init_net_drop_monitor(void) for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - INIT_WORK(&data->dm_alert_work, send_dm_alert); - timer_setup(&data->send_timer, sched_send_work, 0); spin_lock_init(&data->lock); - reset_per_cpu_data(data); + skb_queue_head_init(&data->drop_queue); + u64_stats_init(&data->stats.syncp); } - goto out; out_unreg: @@ -440,19 +986,16 @@ static void exit_net_drop_monitor(void) /* * Because of the module_get/put we do in the trace state change path * we are guarnateed not to have any current users when we get here - * all we need to do is make sure that we don't have any running timers - * or pending schedule calls */ for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - del_timer_sync(&data->send_timer); - cancel_work_sync(&data->dm_alert_work); /* * At this point, we should have exclusive access * to this struct and can free the skb inside it */ kfree_skb(data->skb); + WARN_ON(!skb_queue_empty(&data->drop_queue)); } BUG_ON(genl_unregister_family(&net_drop_monitor_family)); diff --git a/net/core/filter.c b/net/core/filter.c index 5a2707918629..0c1059cdad3d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7539,12 +7539,12 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, gso_segs): /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), - si->dst_reg, si->src_reg, - offsetof(struct sk_buff, head)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, end)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index d63b970784dc..64c3d4d72b9c 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -2,6 +2,8 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <net/flow_offload.h> +#include <linux/rtnetlink.h> +#include <linux/mutex.h> struct flow_rule *flow_rule_alloc(unsigned int num_actions) { @@ -280,3 +282,241 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, } } EXPORT_SYMBOL(flow_block_cb_setup_simple); + +static LIST_HEAD(block_ing_cb_list); + +static struct rhashtable indr_setup_block_ht; + +struct flow_indr_block_cb { + struct list_head list; + void *cb_priv; + flow_indr_block_bind_cb_t *cb; + void *cb_ident; +}; + +struct flow_indr_block_dev { + struct rhash_head ht_node; + struct net_device *dev; + unsigned int refcnt; + struct list_head cb_list; +}; + +static const struct rhashtable_params flow_indr_setup_block_ht_params = { + .key_offset = offsetof(struct flow_indr_block_dev, dev), + .head_offset = offsetof(struct flow_indr_block_dev, ht_node), + .key_len = sizeof(struct net_device *), +}; + +static struct flow_indr_block_dev * +flow_indr_block_dev_lookup(struct net_device *dev) +{ + return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, + flow_indr_setup_block_ht_params); +} + +static struct flow_indr_block_dev * +flow_indr_block_dev_get(struct net_device *dev) +{ + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (indr_dev) + goto inc_ref; + + indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); + if (!indr_dev) + return NULL; + + INIT_LIST_HEAD(&indr_dev->cb_list); + indr_dev->dev = dev; + if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, + flow_indr_setup_block_ht_params)) { + kfree(indr_dev); + return NULL; + } + +inc_ref: + indr_dev->refcnt++; + return indr_dev; +} + +static void flow_indr_block_dev_put(struct flow_indr_block_dev *indr_dev) +{ + if (--indr_dev->refcnt) + return; + + rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, + flow_indr_setup_block_ht_params); + kfree(indr_dev); +} + +static struct flow_indr_block_cb * +flow_indr_block_cb_lookup(struct flow_indr_block_dev *indr_dev, + flow_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + + list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) + if (indr_block_cb->cb == cb && + indr_block_cb->cb_ident == cb_ident) + return indr_block_cb; + return NULL; +} + +static struct flow_indr_block_cb * +flow_indr_block_cb_add(struct flow_indr_block_dev *indr_dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + + indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident); + if (indr_block_cb) + return ERR_PTR(-EEXIST); + + indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); + if (!indr_block_cb) + return ERR_PTR(-ENOMEM); + + indr_block_cb->cb_priv = cb_priv; + indr_block_cb->cb = cb; + indr_block_cb->cb_ident = cb_ident; + list_add(&indr_block_cb->list, &indr_dev->cb_list); + + return indr_block_cb; +} + +static void flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb) +{ + list_del(&indr_block_cb->list); + kfree(indr_block_cb); +} + +static void flow_block_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) +{ + struct flow_indr_block_ing_entry *entry; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &block_ing_cb_list, list) { + entry->cb(dev, cb, cb_priv, command); + } + rcu_read_unlock(); +} + +int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + int err; + + indr_dev = flow_indr_block_dev_get(dev); + if (!indr_dev) + return -ENOMEM; + + indr_block_cb = flow_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); + err = PTR_ERR_OR_ZERO(indr_block_cb); + if (err) + goto err_dev_put; + + flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_BIND); + + return 0; + +err_dev_put: + flow_indr_block_dev_put(indr_dev); + return err; +} +EXPORT_SYMBOL_GPL(__flow_indr_block_cb_register); + +int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + int err; + + rtnl_lock(); + err = __flow_indr_block_cb_register(dev, cb_priv, cb, cb_ident); + rtnl_unlock(); + + return err; +} +EXPORT_SYMBOL_GPL(flow_indr_block_cb_register); + +void __flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (!indr_dev) + return; + + indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident); + if (!indr_block_cb) + return; + + flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_UNBIND); + + flow_indr_block_cb_del(indr_block_cb); + flow_indr_block_dev_put(indr_dev); +} +EXPORT_SYMBOL_GPL(__flow_indr_block_cb_unregister); + +void flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + rtnl_lock(); + __flow_indr_block_cb_unregister(dev, cb, cb_ident); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(flow_indr_block_cb_unregister); + +void flow_indr_block_call(struct net_device *dev, + struct flow_block_offload *bo, + enum flow_block_command command) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (!indr_dev) + return; + + list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) + indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, + bo); +} +EXPORT_SYMBOL_GPL(flow_indr_block_call); + +static DEFINE_MUTEX(flow_indr_block_ing_cb_lock); +void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry) +{ + mutex_lock(&flow_indr_block_ing_cb_lock); + list_add_tail_rcu(&entry->list, &block_ing_cb_list); + mutex_unlock(&flow_indr_block_ing_cb_lock); +} +EXPORT_SYMBOL_GPL(flow_indr_add_block_ing_cb); + +void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry) +{ + mutex_lock(&flow_indr_block_ing_cb_lock); + list_del_rcu(&entry->list); + mutex_unlock(&flow_indr_block_ing_cb_lock); +} +EXPORT_SYMBOL_GPL(flow_indr_del_block_ing_cb); + +static int __init init_flow_indr_rhashtable(void) +{ + return rhashtable_init(&indr_setup_block_ht, + &flow_indr_setup_block_ht_params); +} +subsys_initcall(init_flow_indr_rhashtable); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f79e61c570ea..5480edff0c86 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3033,7 +3033,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); struct neigh_hash_table *nht = state->nht; struct neighbour *n = NULL; - int bucket = state->bucket; + int bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index bb9915291644..c5dbdc87342a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2652,7 +2652,7 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, } get_page(pkt_dev->page); skb_frag_set_page(skb, i, pkt_dev->page); - skb_shinfo(skb)->frags[i].page_offset = 0; + skb_frag_off_set(&skb_shinfo(skb)->frags[i], 0); /*last fragment, fill rest of data*/ if (i == (frags - 1)) skb_frag_size_set(&skb_shinfo(skb)->frags[i], diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0b788df5a75b..ea8e8d332d85 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -785,7 +785,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) struct page *p; u8 *vaddr; - skb_frag_foreach_page(frag, frag->page_offset, + skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { seg_len = min_t(int, p_len, len); @@ -1375,7 +1375,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) struct page *p; u8 *vaddr; - skb_frag_foreach_page(f, f->page_offset, skb_frag_size(f), + skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), p, p_off, p_len, copied) { u32 copy, done = 0; vaddr = kmap_atomic(p); @@ -2144,10 +2144,12 @@ pull_pages: skb_frag_unref(skb, i); eat -= size; } else { - skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; + + *frag = skb_shinfo(skb)->frags[i]; if (eat) { - skb_shinfo(skb)->frags[k].page_offset += eat; - skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat); + skb_frag_off_add(frag, eat); + skb_frag_size_sub(frag, eat); if (!i) goto end; eat = 0; @@ -2219,7 +2221,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) copy = len; skb_frag_foreach_page(f, - f->page_offset + offset - start, + skb_frag_off(f) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(to + copied, vaddr + p_off, p_len); @@ -2395,7 +2397,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (__splice_segment(skb_frag_page(f), - f->page_offset, skb_frag_size(f), + skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) return true; } @@ -2498,7 +2500,7 @@ do_frag_list: while (slen) { ret = kernel_sendpage_locked(sk, skb_frag_page(frag), - frag->page_offset + offset, + skb_frag_off(frag) + offset, slen, MSG_DONTWAIT); if (ret <= 0) goto error; @@ -2580,7 +2582,7 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) copy = len; skb_frag_foreach_page(frag, - frag->page_offset + offset - start, + skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(vaddr + p_off, from + copied, p_len); @@ -2660,7 +2662,7 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, copy = len; skb_frag_foreach_page(frag, - frag->page_offset + offset - start, + skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = INDIRECT_CALL_1(ops->update, @@ -2759,7 +2761,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, copy = len; skb_frag_foreach_page(frag, - frag->page_offset + offset - start, + skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial_copy_nocheck(vaddr + p_off, @@ -3234,7 +3236,7 @@ static inline void skb_split_no_header(struct sk_buff *skb, * 2. Split is accurately. We make this. */ skb_frag_ref(skb, i); - skb_shinfo(skb1)->frags[0].page_offset += len - pos; + skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; @@ -3316,7 +3318,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) */ if (!to || !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), - fragfrom->page_offset)) { + skb_frag_off(fragfrom))) { merge = -1; } else { merge = to - 1; @@ -3333,7 +3335,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) skb_frag_size_add(fragto, shiftlen); skb_frag_size_sub(fragfrom, shiftlen); - fragfrom->page_offset += shiftlen; + skb_frag_off_add(fragfrom, shiftlen); goto onlymerged; } @@ -3364,11 +3366,11 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) } else { __skb_frag_ref(fragfrom); - fragto->bv_page = fragfrom->bv_page; - fragto->page_offset = fragfrom->page_offset; + skb_frag_page_copy(fragto, fragfrom); + skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); - fragfrom->page_offset += todo; + skb_frag_off_add(fragfrom, todo); skb_frag_size_sub(fragfrom, todo); todo = 0; @@ -3493,7 +3495,7 @@ next_skb: if (!st->frag_data) st->frag_data = kmap_atomic(skb_frag_page(frag)); - *data = (u8 *) st->frag_data + frag->page_offset + + *data = (u8 *) st->frag_data + skb_frag_off(frag) + (abs_offset - st->stepped_offset); return block_limit - abs_offset; @@ -3630,8 +3632,8 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) page = virt_to_head_page(frag_skb->head); __skb_frag_set_page(&head_frag, page); - head_frag.page_offset = frag_skb->data - - (unsigned char *)page_address(page); + skb_frag_off_set(&head_frag, frag_skb->data - + (unsigned char *)page_address(page)); skb_frag_size_set(&head_frag, skb_headlen(frag_skb)); return head_frag; } @@ -3875,7 +3877,7 @@ normal: size = skb_frag_size(nskb_frag); if (pos < offset) { - nskb_frag->page_offset += offset - pos; + skb_frag_off_add(nskb_frag, offset - pos); skb_frag_size_sub(nskb_frag, offset - pos); } @@ -3996,7 +3998,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) *--frag = *--frag2; } while (--i); - frag->page_offset += offset; + skb_frag_off_add(frag, offset); skb_frag_size_sub(frag, offset); /* all fragments truesize : remove (head size + sk_buff) */ @@ -4026,7 +4028,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; __skb_frag_set_page(frag, page); - frag->page_offset = first_offset; + skb_frag_off_set(frag, first_offset); skb_frag_size_set(frag, first_size); memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); @@ -4042,7 +4044,7 @@ merge: if (offset > headlen) { unsigned int eat = offset - headlen; - skbinfo->frags[0].page_offset += eat; + skb_frag_off_add(&skbinfo->frags[0], eat); skb_frag_size_sub(&skbinfo->frags[0], eat); skb->data_len -= eat; skb->len -= eat; @@ -4167,7 +4169,7 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, if (copy > len) copy = len; sg_set_page(&sg[elt], skb_frag_page(frag), copy, - frag->page_offset+offset-start); + skb_frag_off(frag) + offset - start); elt++; if (!(len -= copy)) return elt; @@ -5838,7 +5840,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, * where splitting is expensive. * 2. Split is accurately. We make this. */ - shinfo->frags[0].page_offset += off - pos; + skb_frag_off_add(&shinfo->frags[0], off - pos); skb_frag_size_sub(&shinfo->frags[0], off - pos); } skb_frag_ref(skb, i); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 93bffaad2135..6832eeb4b785 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -585,12 +585,12 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - rcu_assign_sk_user_data(sk, NULL); sk_psock_cork_free(psock); sk_psock_zap_ingress(psock); - sk_psock_restore_proto(sk, psock); write_lock_bh(&sk->sk_callback_lock); + sk_psock_restore_proto(sk, psock); + rcu_assign_sk_user_data(sk, NULL); if (psock->progs.skb_parser) sk_psock_stop_strp(sk, psock); write_unlock_bh(&sk->sk_callback_lock); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 52d4faeee18b..1330a7442e5b 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -247,6 +247,8 @@ static void sock_map_free(struct bpf_map *map) raw_spin_unlock_bh(&stab->lock); rcu_read_unlock(); + synchronize_rcu(); + bpf_map_area_free(stab->sks); kfree(stab); } @@ -276,16 +278,20 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { struct sock *sk; + int err = 0; raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) - *psk = NULL; + sk = xchg(psk, NULL); + + if (likely(sk)) + sock_map_unref(sk, psk); + else + err = -EINVAL; + raw_spin_unlock_bh(&stab->lock); - if (unlikely(!sk)) - return -EINVAL; - sock_map_unref(sk, psk); - return 0; + return err; } static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, @@ -328,6 +334,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct inet_connection_sock *icsk = inet_csk(sk); struct sk_psock_link *link; struct sk_psock *psock; struct sock *osk; @@ -338,6 +345,8 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; + if (unlikely(icsk->icsk_ulp_data)) + return -EINVAL; link = sk_psock_init_link(); if (!link) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8da5b3a54dac..eb29e5adc84d 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -567,6 +567,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_do_static_key, }, + { + .procname = "gro_normal_batch", + .data = &gro_normal_batch, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, { } }; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 6e942dda1bcd..2f69d4b53d46 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -84,13 +84,6 @@ config NET_DSA_TAG_KSZ Say Y if you want to enable support for tagging frames for the Microchip 9893 family of switches. -config NET_DSA_TAG_KSZ9477 - tristate "Tag driver for Microchip 9477 family of switches" - select NET_DSA_TAG_KSZ_COMMON - help - Say Y if you want to enable support for tagging frames for the - Microchip 9477 family of switches. - config NET_DSA_TAG_QCA tristate "Tag driver for Qualcomm Atheros QCA8K switches" help diff --git a/net/dsa/master.c b/net/dsa/master.c index 4b52f8bac5e1..a8e52c9967f4 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -8,6 +8,70 @@ #include "dsa_priv.h" +static int dsa_master_get_regs_len(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int ret = 0; + int len; + + if (ops->get_regs_len) { + len = ops->get_regs_len(dev); + if (len < 0) + return len; + ret += len; + } + + ret += sizeof(struct ethtool_drvinfo); + ret += sizeof(struct ethtool_regs); + + if (ds->ops->get_regs_len) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return len; + ret += len; + } + + return ret; +} + +static void dsa_master_get_regs(struct net_device *dev, + struct ethtool_regs *regs, void *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + struct ethtool_drvinfo *cpu_info; + struct ethtool_regs *cpu_regs; + int port = cpu_dp->index; + int len; + + if (ops->get_regs_len && ops->get_regs) { + len = ops->get_regs_len(dev); + if (len < 0) + return; + regs->len = len; + ops->get_regs(dev, regs, data); + data += regs->len; + } + + cpu_info = (struct ethtool_drvinfo *)data; + strlcpy(cpu_info->driver, "dsa", sizeof(cpu_info->driver)); + data += sizeof(*cpu_info); + cpu_regs = (struct ethtool_regs *)data; + data += sizeof(*cpu_regs); + + if (ds->ops->get_regs_len && ds->ops->get_regs) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return; + cpu_regs->len = len; + ds->ops->get_regs(ds, port, cpu_regs, data); + } +} + static void dsa_master_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) @@ -147,6 +211,8 @@ static int dsa_master_ethtool_setup(struct net_device *dev) if (cpu_dp->orig_ethtool_ops) memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); + ops->get_regs_len = dsa_master_get_regs_len; + ops->get_regs = dsa_master_get_regs; ops->get_sset_count = dsa_master_get_sset_count; ops->get_ethtool_stats = dsa_master_get_ethtool_stats; ops->get_strings = dsa_master_get_strings; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index b4872b87d4a6..73605bcbb385 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -70,6 +70,67 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, } /* + * For Ingress (Host -> KSZ8795), 1 byte is added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5) + * + * For Egress (KSZ8795 -> Host), 1 byte is added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag0 : zero-based value represents port + * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + */ + +#define KSZ8795_INGRESS_TAG_LEN 1 + +#define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) +#define KSZ8795_TAIL_TAG_LOOKUP BIT(7) + +static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct sk_buff *nskb; + u8 *tag; + u8 *addr; + + nskb = ksz_common_xmit(skb, dev, KSZ8795_INGRESS_TAG_LEN); + if (!nskb) + return NULL; + + /* Tag encoding */ + tag = skb_put(nskb, KSZ8795_INGRESS_TAG_LEN); + addr = skb_mac_header(nskb); + + *tag = 1 << dp->index; + if (is_link_local_ether_addr(addr)) + *tag |= KSZ8795_TAIL_TAG_OVERRIDE; + + return nskb; +} + +static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + + return ksz_common_rcv(skb, dev, tag[0] & 7, KSZ_EGRESS_TAG_LEN); +} + +static const struct dsa_device_ops ksz8795_netdev_ops = { + .name = "ksz8795", + .proto = DSA_TAG_PROTO_KSZ8795, + .xmit = ksz8795_xmit, + .rcv = ksz8795_rcv, + .overhead = KSZ8795_INGRESS_TAG_LEN, +}; + +DSA_TAG_DRIVER(ksz8795_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795); + +/* * For Ingress (Host -> KSZ9477), 2 bytes are added before FCS. * --------------------------------------------------------------------------- * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes) @@ -183,6 +244,7 @@ DSA_TAG_DRIVER(ksz9893_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893); static struct dsa_tag_driver *dsa_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(ksz8795_netdev_ops), &DSA_TAG_DRIVER_NAME(ksz9477_netdev_ops), &DSA_TAG_DRIVER_NAME(ksz9893_netdev_ops), }; diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 26363d72d25b..47ee88163a9d 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -165,6 +165,7 @@ static struct sk_buff "Expected meta frame, is %12llx " "in the DSA master multicast filter?\n", SJA1105_META_DMAC); + kfree_skb(sp->data->stampable_skb); } /* Hold a reference to avoid dsa_switch_rcv @@ -211,17 +212,8 @@ static struct sk_buff * for further processing up the network stack. */ kfree_skb(skb); - - skb = skb_copy(stampable_skb, GFP_ATOMIC); - if (!skb) { - dev_err_ratelimited(dp->ds->dev, - "Failed to copy stampable skb\n"); - spin_unlock(&sp->data->meta_lock); - return NULL; - } + skb = stampable_skb; sja1105_transfer_meta(skb, meta); - /* The cached copy will be freed now */ - skb_unref(stampable_skb); spin_unlock(&sp->data->meta_lock); } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index d666756be5f1..a999451345f9 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -331,7 +331,7 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); - if (prev && !IS_ERR(prev)) { + if (!IS_ERR_OR_NULL(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 43adfc1641ba..2f01cf6fa0de 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -275,6 +275,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto; + if (!pskb_inet_may_pull(skb)) + goto tx_error; + switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0b980e841927..59ded25acd04 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -820,6 +820,15 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &tcp_min_snd_mss_max, }, { + .procname = "tcp_mtu_probe_floor", + .data = &init_net.ipv4.sysctl_tcp_mtu_probe_floor, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_min_snd_mss_min, + .extra2 = &tcp_min_snd_mss_max, + }, + { .procname = "tcp_probe_threshold", .data = &init_net.ipv4.sysctl_tcp_probe_threshold, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f62f0e7e3cdd..f8fa1686f7f3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1162,7 +1162,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; - bool process_backlog = false; + int process_backlog = 0; bool zc = false; long timeo; @@ -1254,9 +1254,10 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - if (process_backlog && sk_flush_backlog(sk)) { - process_backlog = false; - goto restart; + if (unlikely(process_backlog >= 16)) { + process_backlog = 0; + if (sk_flush_backlog(sk)) + goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, @@ -1264,7 +1265,7 @@ new_segment: if (!skb) goto wait_for_memory; - process_backlog = true; + process_backlog++; skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); @@ -1782,12 +1783,12 @@ static int tcp_zerocopy_receive(struct sock *sk, frags++; } } - if (skb_frag_size(frags) != PAGE_SIZE || frags->page_offset) { + if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { int remaining = zc->recv_skip_hint; int size = skb_frag_size(frags); while (remaining && (size != PAGE_SIZE || - frags->page_offset)) { + skb_frag_off(frags))) { remaining -= size; frags++; size = skb_frag_size(frags); @@ -3784,7 +3785,7 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, for (i = 0; i < shi->nr_frags; ++i) { const skb_frag_t *f = &shi->frags[i]; - unsigned int offset = f->page_offset; + unsigned int offset = skb_frag_off(f); struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT); sg_set_page(&sg, page, skb_frag_size(f), diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 10217393cda6..fd394ad179a0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2652,6 +2652,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; + net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6e4afc48d7bb..e6d02e05bb1c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1402,7 +1402,7 @@ static int __pskb_trim_head(struct sk_buff *skb, int len) } else { shinfo->frags[k] = shinfo->frags[i]; if (eat) { - shinfo->frags[k].page_offset += eat; + skb_frag_off_add(&shinfo->frags[k], eat); skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c801cd37cc2a..dbd9d2d0ee63 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -154,7 +154,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(net->ipv4.sysctl_tcp_base_mss, mss); - mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len); + mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor); mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 3d8a1d835471..4849edb62d52 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -96,6 +96,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen) rcu_read_unlock(); } +void tcp_update_ulp(struct sock *sk, struct proto *proto) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ulp_ops) { + sk->sk_prot = proto; + return; + } + + if (icsk->icsk_ulp_ops->update) + icsk->icsk_ulp_ops->update(sk, proto); +} + void tcp_cleanup_ulp(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index b358f1a4dd08..da46c4284676 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -197,10 +197,8 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, struct ipv6hdr _ip6, *ip6; ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6); - if (!ip6 || (ip6->version != 6)) { - printk(KERN_ERR "IPv6 header not found\n"); + if (!ip6 || (ip6->version != 6)) return -EBADMSG; - } start = *offset + sizeof(struct ipv6hdr); nexthdr = ip6->nexthdr; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c2049c72f3e5..dd2d0b963260 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -660,12 +660,13 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, struct flowi6 *fl6, __u8 *dsfield, int *encap_limit) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; struct ip6_tnl *t = netdev_priv(dev); __u16 offset; offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3134fbb65d7f..754a484d35df 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1278,12 +1278,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); + dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph)); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; - dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph)); - skb_set_inner_ipproto(skb, IPPROTO_IPIP); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, @@ -1367,12 +1366,11 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); + dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h)); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; - dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h)); - skb_set_inner_ipproto(skb, IPPROTO_IPV6); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e49fec767a10..7a5d331cdefa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1951,7 +1951,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) - return; + goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; @@ -2725,10 +2725,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); - if (!res.f6i) { - rcu_read_unlock(); - return; - } + if (!res.f6i) + goto out_unlock; + res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; @@ -2744,10 +2743,8 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ - if (!arg.match) { - rcu_read_unlock(); - return; - } + if (!arg.match) + goto out_unlock; res.nh = arg.match; } else { @@ -2760,6 +2757,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } +out_unlock: rcu_read_unlock(); } } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 09e1694b6d34..ebb62a4ebe30 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -512,7 +512,9 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); } - case IUCV_DISCONN: /* fall through */ + /* fall through */ + + case IUCV_DISCONN: sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); @@ -525,8 +527,9 @@ static void iucv_sock_close(struct sock *sk) iucv_sock_in_state(sk, IUCV_CLOSED, 0), timeo); } + /* fall through */ - case IUCV_CLOSING: /* fall through */ + case IUCV_CLOSING: sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); @@ -535,8 +538,9 @@ static void iucv_sock_close(struct sock *sk) skb_queue_purge(&iucv->send_skb_q); skb_queue_purge(&iucv->backlog_skb_q); + /* fall through */ - default: /* fall through */ + default: iucv_sever_path(sk, 1); } @@ -2247,10 +2251,10 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, kfree_skb(skb); break; } - /* fall through and receive non-zero length data */ + /* fall through - and receive non-zero length data */ case (AF_IUCV_FLAG_SHT): /* shutdown request */ - /* fall through and receive zero length data */ + /* fall through - and receive zero length data */ case 0: /* plain data frame */ IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 05f63c4300e9..4ff75c3a8d6e 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -642,7 +642,7 @@ do_frag: ret = kernel_sendpage(psock->sk->sk_socket, skb_frag_page(frag), - frag->page_offset + frag_offset, + skb_frag_off(frag) + frag_offset, skb_frag_size(frag) - frag_offset, MSG_DONTWAIT); if (ret <= 0) { diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1d0e5904dedf..c54cb59593ef 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1681,6 +1681,9 @@ static const struct proto_ops pppol2tp_ops = { .recvmsg = pppol2tp_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif }; static const struct pppox_proto pppol2tp_proto = { diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 01b0dad24500..4d1c335e06e5 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -178,17 +178,54 @@ static void sta_rx_agg_reorder_timer_expired(struct timer_list *t) rcu_read_unlock(); } -static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *da, u16 tid, +static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + const struct ieee80211_addba_ext_ie *req) +{ + struct ieee80211_supported_band *sband; + struct ieee80211_addba_ext_ie *resp; + const struct ieee80211_sta_he_cap *he_cap; + u8 frag_level, cap_frag_level; + u8 *pos; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return; + he_cap = ieee80211_get_he_iftype_cap(sband, sdata->vif.type); + if (!he_cap) + return; + + pos = skb_put_zero(skb, 2 + sizeof(struct ieee80211_addba_ext_ie)); + *pos++ = WLAN_EID_ADDBA_EXT; + *pos++ = sizeof(struct ieee80211_addba_ext_ie); + resp = (struct ieee80211_addba_ext_ie *)pos; + resp->data = req->data & IEEE80211_ADDBA_EXT_NO_FRAG; + + frag_level = u32_get_bits(req->data, + IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); + cap_frag_level = u32_get_bits(he_cap->he_cap_elem.mac_cap_info[0], + IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK); + if (frag_level > cap_frag_level) + frag_level = cap_frag_level; + resp->data |= u8_encode_bits(frag_level, + IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); +} + +static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid, u8 dialog_token, u16 status, u16 policy, - u16 buf_size, u16 timeout) + u16 buf_size, u16 timeout, + const struct ieee80211_addba_ext_ie *addbaext) { + struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; bool amsdu = ieee80211_hw_check(&local->hw, SUPPORTS_AMSDU_IN_AMPDU); u16 capab; - skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); + skb = dev_alloc_skb(sizeof(*mgmt) + + 2 + sizeof(struct ieee80211_addba_ext_ie) + + local->hw.extra_tx_headroom); if (!skb) return; @@ -222,13 +259,17 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d mgmt->u.action.u.addba_resp.timeout = cpu_to_le16(timeout); mgmt->u.action.u.addba_resp.status = cpu_to_le16(status); + if (sta->sta.he_cap.has_he && addbaext) + ieee80211_add_addbaext(sdata, skb, addbaext); + ieee80211_tx_skb(sdata, skb); } void ___ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, - u16 buf_size, bool tx, bool auto_seq) + u16 buf_size, bool tx, bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext) { struct ieee80211_local *local = sta->sdata->local; struct tid_ampdu_rx *tid_agg_rx; @@ -410,21 +451,22 @@ end: } if (tx) - ieee80211_send_addba_resp(sta->sdata, sta->sta.addr, tid, + ieee80211_send_addba_resp(sta, sta->sta.addr, tid, dialog_token, status, 1, buf_size, - timeout); + timeout, addbaext); } static void __ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, u16 buf_size, bool tx, - bool auto_seq) + bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext) { mutex_lock(&sta->ampdu_mlme.mtx); ___ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, - buf_size, tx, auto_seq); + buf_size, tx, auto_seq, addbaext); mutex_unlock(&sta->ampdu_mlme.mtx); } @@ -434,7 +476,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, size_t len) { u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num; + struct ieee802_11_elems elems = { 0 }; u8 dialog_token; + int ies_len; /* extract session parameters from addba request frame */ dialog_token = mgmt->u.action.u.addba_req.dialog_token; @@ -447,9 +491,19 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; + ies_len = len - offsetof(struct ieee80211_mgmt, + u.action.u.addba_req.variable); + if (ies_len) { + ieee802_11_parse_elems(mgmt->u.action.u.addba_req.variable, + ies_len, true, &elems, mgmt->bssid, NULL); + if (elems.parse_error) + return; + } + __ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, - buf_size, true, false); + buf_size, true, false, + elems.addba_ext_ie); } void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4d458067d80d..ed56b0c6fe19 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -980,7 +980,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_SSID | BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER | - BSS_CHANGED_TWT; + BSS_CHANGED_TWT | + BSS_CHANGED_HE_OBSS_PD; int err; int prev_beacon_int; @@ -1051,6 +1052,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.enable_beacon = true; sdata->vif.bss_conf.allow_p2p_go_ps = sdata->vif.p2p; sdata->vif.bss_conf.twt_responder = params->twt_responder; + memcpy(&sdata->vif.bss_conf.he_obss_pd, ¶ms->he_obss_pd, + sizeof(struct ieee80211_he_obss_pd)); sdata->vif.bss_conf.ssid_len = params->ssid_len; if (params->ssid_len) @@ -1543,7 +1546,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (ether_addr_equal(mac, sdata->vif.addr)) return -EINVAL; - if (is_multicast_ether_addr(mac)) + if (!is_valid_ether_addr(mac)) return -EINVAL; sta = sta_info_alloc(sdata, mac, GFP_KERNEL); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 2e7f75938c51..568b3b276931 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -271,8 +271,7 @@ static const char *hw_flag_names[] = { FLAG(TX_STATUS_NO_AMPDU_LEN), FLAG(SUPPORTS_MULTI_BSSID), FLAG(SUPPORTS_ONLY_HE_MULTI_BSSID), - FLAG(EXT_KEY_ID_NATIVE), - FLAG(NO_AMPDU_KEYBORDER_SUPPORT), + FLAG(AMPDU_KEYBORDER_SUPPORT), #undef FLAG }; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index c2d8b5451a5e..2c9b3eb8b652 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -692,14 +692,16 @@ static inline int drv_remain_on_channel(struct ieee80211_local *local, return ret; } -static inline int drv_cancel_remain_on_channel(struct ieee80211_local *local) +static inline int +drv_cancel_remain_on_channel(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { int ret; might_sleep(); - trace_drv_cancel_remain_on_channel(local); - ret = local->ops->cancel_remain_on_channel(&local->hw); + trace_drv_cancel_remain_on_channel(local, sdata); + ret = local->ops->cancel_remain_on_channel(&local->hw, &sdata->vif); trace_drv_return_int(local, ret); return ret; diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 219650591c79..a02abfc424aa 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -50,3 +50,42 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, he_cap->has_he = true; } + +void +ieee80211_he_op_ie_to_bss_conf(struct ieee80211_vif *vif, + const struct ieee80211_he_operation *he_op_ie_elem) +{ + struct ieee80211_he_operation *he_operation = + &vif->bss_conf.he_operation; + + if (!he_op_ie_elem) { + memset(he_operation, 0, sizeof(*he_operation)); + return; + } + + vif->bss_conf.he_operation = *he_op_ie_elem; +} + +void +ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif, + const struct ieee80211_he_spr *he_spr_ie_elem) +{ + struct ieee80211_he_obss_pd *he_obss_pd = + &vif->bss_conf.he_obss_pd; + const u8 *data = he_spr_ie_elem->optional; + + memset(he_obss_pd, 0, sizeof(*he_obss_pd)); + + if (!he_spr_ie_elem) + return; + + if (he_spr_ie_elem->he_sr_control & + IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) + data++; + if (he_spr_ie_elem->he_sr_control & + IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) { + he_obss_pd->max_offset = *data++; + he_obss_pd->min_offset = *data++; + he_obss_pd->enable = true; + } +} diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index d5a500b2a448..a2e4d6b8fd98 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -359,7 +359,7 @@ void ieee80211_ba_session_work(struct work_struct *work) sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, IEEE80211_MAX_AMPDU_BUF_HT, - false, true); + false, true, NULL); if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, sta->ampdu_mlme.tid_rx_manage_offl)) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 004e2e3adb88..791ce58d0f09 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1480,6 +1480,7 @@ struct ieee802_11_elems { const struct ieee80211_meshconf_ie *mesh_config; const u8 *he_cap; const struct ieee80211_he_operation *he_operation; + const struct ieee80211_he_spr *he_spr; const struct ieee80211_mu_edca_param_set *mu_edca_param_set; const u8 *uora_element; const u8 *mesh_id; @@ -1506,6 +1507,7 @@ struct ieee802_11_elems { u8 max_bssid_indicator; u8 dtim_count; u8 dtim_period; + const struct ieee80211_addba_ext_ie *addba_ext_ie; /* length of them, respectively */ u8 ext_capab_len; @@ -1767,7 +1769,8 @@ ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 info_flags); void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, struct ieee80211_supported_band *sband, - int retry_count, int shift, bool send_to_cooked); + int retry_count, int shift, bool send_to_cooked, + struct ieee80211_tx_status *status); void ieee80211_check_fast_xmit(struct sta_info *sta); void ieee80211_check_fast_xmit_all(struct ieee80211_local *local); @@ -1804,7 +1807,8 @@ void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, void ___ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, - u16 buf_size, bool tx, bool auto_seq); + u16 buf_size, bool tx, bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext); void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, enum ieee80211_agg_stop_reason reason); void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, @@ -1869,6 +1873,13 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const u8 *he_cap_ie, u8 he_cap_len, struct sta_info *sta); +void +ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif, + const struct ieee80211_he_spr *he_spr_ie_elem); + +void +ieee80211_he_op_ie_to_bss_conf(struct ieee80211_vif *vif, + const struct ieee80211_he_operation *he_op_ie_elem); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, @@ -2133,9 +2144,11 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap); u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, const struct cfg80211_chan_def *chandef); +u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype); u8 *ieee80211_ie_build_he_cap(u8 *pos, const struct ieee80211_sta_he_cap *he_cap, u8 *end); +u8 *ieee80211_ie_build_he_oper(u8 *pos); int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef, const struct ieee80211_supported_band *sband, const u8 *srates, int srates_len, u32 *rates); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 06aac0aaae64..8dc6580e1787 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1222,7 +1222,6 @@ static void ieee80211_if_setup(struct net_device *dev) static void ieee80211_if_setup_no_queue(struct net_device *dev) { ieee80211_if_setup(dev); - dev->features |= NETIF_F_LLTX; dev->priv_flags |= IFF_NO_QUEUE; } diff --git a/net/mac80211/key.c b/net/mac80211/key.c index dd60f6428049..7dfee848abac 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -270,7 +270,7 @@ int ieee80211_set_tx_key(struct ieee80211_key *key) sta->ptk_idx = key->conf.keyidx; - if (ieee80211_hw_check(&local->hw, NO_AMPDU_KEYBORDER_SUPPORT)) + if (!ieee80211_hw_check(&local->hw, AMPDU_KEYBORDER_SUPPORT)) clear_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_check_fast_xmit(sta); @@ -290,15 +290,15 @@ static void ieee80211_pairwise_rekey(struct ieee80211_key *old, /* Extended Key ID key install, initial one or rekey */ if (sta->ptk_idx != INVALID_PTK_KEYIDX && - ieee80211_hw_check(&local->hw, - NO_AMPDU_KEYBORDER_SUPPORT)) { + !ieee80211_hw_check(&local->hw, AMPDU_KEYBORDER_SUPPORT)) { /* Aggregation Sessions with Extended Key ID must not * mix MPDUs with different keyIDs within one A-MPDU. - * Tear down any running Tx aggregation and all new - * Rx/Tx aggregation request during rekey if the driver - * asks us to do so. (Blocking Tx only would be - * sufficient but WLAN_STA_BLOCK_BA gets the job done - * for the few ms we need it.) + * Tear down running Tx aggregation sessions and block + * new Rx/Tx aggregation requests during rekey to + * ensure there are no A-MPDUs when the driver is not + * supporting A-MPDU key borders. (Blocking Tx only + * would be sufficient but WLAN_STA_BLOCK_BA gets the + * job done for the few ms we need it.) */ set_sta_flag(sta, WLAN_STA_BLOCK_BA); mutex_lock(&sta->ampdu_mlme.mtx); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4c2702f128f3..29b9d57df1a3 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1048,21 +1048,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } } - /* Enable Extended Key IDs when driver allowed it, or when it - * supports neither HW crypto nor A-MPDUs + /* Mac80211 and therefore all drivers using SW crypto only + * are able to handle PTK rekeys and Extended Key ID. */ - if ((!local->ops->set_key && - !ieee80211_hw_check(hw, AMPDU_AGGREGATION)) || - ieee80211_hw_check(&local->hw, EXT_KEY_ID_NATIVE)) - wiphy_ext_feature_set(local->hw.wiphy, - NL80211_EXT_FEATURE_EXT_KEY_ID); - - /* Mac80211 and therefore all cards only using SW crypto are able to - * handle PTK rekeys correctly - */ - if (!local->ops->set_key) + if (!local->ops->set_key) { wiphy_ext_feature_set(local->hw.wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0); + wiphy_ext_feature_set(local->hw.wiphy, + NL80211_EXT_FEATURE_EXT_KEY_ID); + } /* * Calculate scan IE length -- we need this to alloc diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 2e7fa743c892..d09b3c789314 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -532,6 +532,61 @@ int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, return 0; } +int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, u8 ie_len) +{ + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_supported_band *sband; + u8 *pos; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return -EINVAL; + + he_cap = ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); + + if (!he_cap || + sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + return 0; + + if (skb_tailroom(skb) < ie_len) + return -ENOMEM; + + pos = skb_put(skb, ie_len); + ieee80211_ie_build_he_cap(pos, he_cap, pos + ie_len); + + return 0; +} + +int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_supported_band *sband; + u8 *pos; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return -EINVAL; + + he_cap = ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); + if (!he_cap || + sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + return 0; + + if (skb_tailroom(skb) < 2 + 1 + sizeof(struct ieee80211_he_operation)) + return -ENOMEM; + + pos = skb_put(skb, 2 + 1 + sizeof(struct ieee80211_he_operation)); + ieee80211_ie_build_he_oper(pos); + + return 0; +} + static void ieee80211_mesh_path_timer(struct timer_list *t) { struct ieee80211_sub_if_data *sdata = @@ -677,6 +732,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) struct ieee80211_chanctx_conf *chanctx_conf; struct mesh_csa_settings *csa; enum nl80211_band band; + u8 ie_len_he_cap; u8 *pos; struct ieee80211_sub_if_data *sdata; int hdr_len = offsetofend(struct ieee80211_mgmt, u.beacon); @@ -687,6 +743,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) band = chanctx_conf->def.chan->band; rcu_read_unlock(); + ie_len_he_cap = ieee80211_ie_len_he_cap(sdata, + NL80211_IFTYPE_MESH_POINT); head_len = hdr_len + 2 + /* NULL SSID */ /* Channel Switch Announcement */ @@ -706,6 +764,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) 2 + sizeof(__le16) + /* awake window */ 2 + sizeof(struct ieee80211_vht_cap) + 2 + sizeof(struct ieee80211_vht_operation) + + ie_len_he_cap + + 2 + 1 + sizeof(struct ieee80211_he_operation) + ifmsh->ie_len; bcn = kzalloc(sizeof(*bcn) + head_len + tail_len, GFP_KERNEL); @@ -823,6 +883,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) mesh_add_awake_window_ie(sdata, skb) || mesh_add_vht_cap_ie(sdata, skb) || mesh_add_vht_oper_ie(sdata, skb) || + mesh_add_he_cap_ie(sdata, skb, ie_len_he_cap) || + mesh_add_he_oper_ie(sdata, skb) || mesh_add_vendor_ies(sdata, skb)) goto out_free; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 94d57cce70da..953f720754e8 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -218,6 +218,10 @@ int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); +int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, u8 ie_len); +int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index dd3aefd052a9..737c5f4dbf52 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -218,9 +218,12 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, bool include_plid = false; u16 peering_proto = 0; u8 *pos, ie_len = 4; + u8 ie_len_he_cap; int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.self_prot); int err = -ENOMEM; + ie_len_he_cap = ieee80211_ie_len_he_cap(sdata, + NL80211_IFTYPE_MESH_POINT); skb = dev_alloc_skb(local->tx_headroom + hdr_len + 2 + /* capability info */ @@ -233,6 +236,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, 2 + sizeof(struct ieee80211_ht_operation) + 2 + sizeof(struct ieee80211_vht_cap) + 2 + sizeof(struct ieee80211_vht_operation) + + ie_len_he_cap + + 2 + 1 + sizeof(struct ieee80211_he_operation) + 2 + 8 + /* peering IE */ sdata->u.mesh.ie_len); if (!skb) @@ -321,7 +326,9 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, if (mesh_add_ht_cap_ie(sdata, skb) || mesh_add_ht_oper_ie(sdata, skb) || mesh_add_vht_cap_ie(sdata, skb) || - mesh_add_vht_oper_ie(sdata, skb)) + mesh_add_vht_oper_ie(sdata, skb) || + mesh_add_he_cap_ie(sdata, skb, ie_len_he_cap) || + mesh_add_he_oper_ie(sdata, skb)) goto free; } @@ -433,6 +440,9 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, elems->vht_cap_elem, sta); + ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, elems->he_cap, + elems->he_cap_len, sta); + if (bw != sta->sta.bandwidth) changed |= IEEE80211_RC_BW_CHANGED; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a99ad0325309..641876982ab9 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2042,6 +2042,16 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local, ieee80211_regulatory_limit_wmm_params(sdata, ¶ms[ac], ac); } + /* WMM specification requires all 4 ACIs. */ + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + if (params[ac].cw_min == 0) { + sdata_info(sdata, + "AP has invalid WMM params (missing AC %d), using defaults\n", + ac); + return false; + } + } + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { mlme_dbg(sdata, "WMM AC=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n", @@ -2512,7 +2522,10 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) if (ieee80211_hw_check(&sdata->local->hw, REPORTS_TX_ACK_STATUS)) { ifmgd->nullfunc_failed = false; - ieee80211_send_nullfunc(sdata->local, sdata, false); + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) + ifmgd->probe_send_count--; + else + ieee80211_send_nullfunc(sdata->local, sdata, false); } else { int ssid_len; @@ -3381,6 +3394,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, if (elems.uora_element) bss_conf->uora_ocw_range = elems.uora_element[0]; + ieee80211_he_op_ie_to_bss_conf(&sdata->vif, elems.he_operation); + ieee80211_he_spr_ie_to_bss_conf(&sdata->vif, elems.he_spr); /* TODO: OPEN: what happens if BSS color disable is set? */ } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 60ef8972b254..c710504ccf1a 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -8,6 +8,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2019 Intel Corporation */ #include <linux/export.h> #include <net/mac80211.h> @@ -732,7 +733,7 @@ static int ieee80211_cancel_roc(struct ieee80211_local *local, } if (local->ops->remain_on_channel) { - ret = drv_cancel_remain_on_channel(local); + ret = drv_cancel_remain_on_channel(local, roc->sdata); if (WARN_ON_ONCE(ret)) { mutex_unlock(&local->mtx); return ret; @@ -991,7 +992,7 @@ void ieee80211_roc_purge(struct ieee80211_local *local, if (roc->started) { if (local->ops->remain_on_channel) { /* can race, so ignore return value */ - drv_cancel_remain_on_channel(local); + drv_cancel_remain_on_channel(local, sdata); ieee80211_roc_notify_destroy(roc); } else { roc->abort = true; diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 5d5348bc41ec..5397c6dad056 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -60,15 +60,6 @@ static inline void rate_control_add_sta_debugfs(struct sta_info *sta) #endif } -static inline void rate_control_remove_sta_debugfs(struct sta_info *sta) -{ -#ifdef CONFIG_MAC80211_DEBUGFS - struct rate_control_ref *ref = sta->rate_ctrl; - if (ref && ref->ops->remove_sta_debugfs) - ref->ops->remove_sta_debugfs(ref->priv, sta->rate_ctrl_priv); -#endif -} - void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata); /* Get a reference to the rate control algorithm. If `name' is NULL, get the diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 95eb8220e2e4..fb6614f57cbc 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1065,7 +1065,6 @@ static void __sta_info_destroy_part2(struct sta_info *sta) cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); kfree(sinfo); - rate_control_remove_sta_debugfs(sta); ieee80211_sta_debugfs_remove(sta); cleanup_single_sta(sta); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index a88e3bf17e9d..f03aa8924d23 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -254,7 +254,8 @@ static void ieee80211_set_bar_pending(struct sta_info *sta, u8 tid, u16 ssn) tid_tx->bar_pending = true; } -static int ieee80211_tx_radiotap_len(struct ieee80211_tx_info *info) +static int ieee80211_tx_radiotap_len(struct ieee80211_tx_info *info, + struct ieee80211_tx_status *status) { int len = sizeof(struct ieee80211_radiotap_header); @@ -272,7 +273,14 @@ static int ieee80211_tx_radiotap_len(struct ieee80211_tx_info *info) /* IEEE80211_RADIOTAP_MCS * IEEE80211_RADIOTAP_VHT */ - if (info->status.rates[0].idx >= 0) { + if (status && status->rate) { + if (status->rate->flags & RATE_INFO_FLAGS_MCS) + len += 3; + else if (status->rate->flags & RATE_INFO_FLAGS_VHT_MCS) + len = ALIGN(len, 2) + 12; + else if (status->rate->flags & RATE_INFO_FLAGS_HE_MCS) + len = ALIGN(len, 2) + 12; + } else if (info->status.rates[0].idx >= 0) { if (info->status.rates[0].flags & IEEE80211_TX_RC_MCS) len += 3; else if (info->status.rates[0].flags & IEEE80211_TX_RC_VHT_MCS) @@ -286,12 +294,14 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, struct ieee80211_supported_band *sband, struct sk_buff *skb, int retry_count, - int rtap_len, int shift) + int rtap_len, int shift, + struct ieee80211_tx_status *status) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_radiotap_header *rthdr; unsigned char *pos; + u16 legacy_rate = 0; u16 txflags; rthdr = skb_push(skb, rtap_len); @@ -310,14 +320,22 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, */ /* IEEE80211_RADIOTAP_RATE */ - if (info->status.rates[0].idx >= 0 && - !(info->status.rates[0].flags & (IEEE80211_TX_RC_MCS | - IEEE80211_TX_RC_VHT_MCS))) { - u16 rate; + if (status && status->rate && !(status->rate->flags & + (RATE_INFO_FLAGS_MCS | + RATE_INFO_FLAGS_60G | + RATE_INFO_FLAGS_VHT_MCS | + RATE_INFO_FLAGS_HE_MCS))) + legacy_rate = status->rate->legacy; + else if (info->status.rates[0].idx >= 0 && + !(info->status.rates[0].flags & (IEEE80211_TX_RC_MCS | + IEEE80211_TX_RC_VHT_MCS))) + legacy_rate = + sband->bitrates[info->status.rates[0].idx].bitrate; + + if (legacy_rate) { rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_RATE); - rate = sband->bitrates[info->status.rates[0].idx].bitrate; - *pos = DIV_ROUND_UP(rate, 5 * (1 << shift)); + *pos = DIV_ROUND_UP(legacy_rate, 5 * (1 << shift)); /* padding for tx flags */ pos += 2; } @@ -341,7 +359,139 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, *pos = retry_count; pos++; - if (info->status.rates[0].idx < 0) + if (status && status->rate && + (status->rate->flags & RATE_INFO_FLAGS_MCS)) { + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS); + pos[0] = IEEE80211_RADIOTAP_MCS_HAVE_MCS | + IEEE80211_RADIOTAP_MCS_HAVE_GI | + IEEE80211_RADIOTAP_MCS_HAVE_BW; + if (status->rate->flags & RATE_INFO_FLAGS_SHORT_GI) + pos[1] |= IEEE80211_RADIOTAP_MCS_SGI; + if (status->rate->bw == RATE_INFO_BW_40) + pos[1] |= IEEE80211_RADIOTAP_MCS_BW_40; + pos[2] = status->rate->mcs; + pos += 3; + } else if (status && status->rate && + (status->rate->flags & RATE_INFO_FLAGS_VHT_MCS)) { + u16 known = local->hw.radiotap_vht_details & + (IEEE80211_RADIOTAP_VHT_KNOWN_GI | + IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH); + + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT); + + /* required alignment from rthdr */ + pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); + + /* u16 known - IEEE80211_RADIOTAP_VHT_KNOWN_* */ + put_unaligned_le16(known, pos); + pos += 2; + + /* u8 flags - IEEE80211_RADIOTAP_VHT_FLAG_* */ + if (status->rate->flags & RATE_INFO_FLAGS_SHORT_GI) + *pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI; + pos++; + + /* u8 bandwidth */ + switch (status->rate->bw) { + case RATE_INFO_BW_160: + *pos = 11; + break; + case RATE_INFO_BW_80: + *pos = 2; + break; + case RATE_INFO_BW_40: + *pos = 1; + break; + default: + *pos = 0; + break; + } + + /* u8 mcs_nss[4] */ + *pos = (status->rate->mcs << 4) | status->rate->nss; + pos += 4; + + /* u8 coding */ + pos++; + /* u8 group_id */ + pos++; + /* u16 partial_aid */ + pos += 2; + } else if (status && status->rate && + (status->rate->flags & RATE_INFO_FLAGS_HE_MCS)) { + struct ieee80211_radiotap_he *he; + + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE); + + /* required alignment from rthdr */ + pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); + he = (struct ieee80211_radiotap_he *)pos; + + he->data1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_SU | + IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN); + + he->data2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN); + +#define HE_PREP(f, val) le16_encode_bits(val, IEEE80211_RADIOTAP_HE_##f) + + he->data6 |= HE_PREP(DATA6_NSTS, status->rate->nss); + +#define CHECK_GI(s) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_GI_##s != \ + (int)NL80211_RATE_INFO_HE_GI_##s) + + CHECK_GI(0_8); + CHECK_GI(1_6); + CHECK_GI(3_2); + + he->data3 |= HE_PREP(DATA3_DATA_MCS, status->rate->mcs); + he->data3 |= HE_PREP(DATA3_DATA_DCM, status->rate->he_dcm); + + he->data5 |= HE_PREP(DATA5_GI, status->rate->he_gi); + + switch (status->rate->bw) { + case RATE_INFO_BW_20: + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ); + break; + case RATE_INFO_BW_40: + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ); + break; + case RATE_INFO_BW_80: + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ); + break; + case RATE_INFO_BW_160: + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ); + break; + case RATE_INFO_BW_HE_RU: +#define CHECK_RU_ALLOC(s) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_##s##T != \ + NL80211_RATE_INFO_HE_RU_ALLOC_##s + 4) + + CHECK_RU_ALLOC(26); + CHECK_RU_ALLOC(52); + CHECK_RU_ALLOC(106); + CHECK_RU_ALLOC(242); + CHECK_RU_ALLOC(484); + CHECK_RU_ALLOC(996); + CHECK_RU_ALLOC(2x996); + + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + status->rate->he_ru_alloc + 4); + break; + default: + WARN_ONCE(1, "Invalid SU BW %d\n", status->rate->bw); + } + + pos += sizeof(struct ieee80211_radiotap_he); + } + + if ((status && status->rate) || info->status.rates[0].idx < 0) return; /* IEEE80211_RADIOTAP_MCS @@ -645,7 +795,8 @@ static int ieee80211_tx_get_rates(struct ieee80211_hw *hw, void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, struct ieee80211_supported_band *sband, - int retry_count, int shift, bool send_to_cooked) + int retry_count, int shift, bool send_to_cooked, + struct ieee80211_tx_status *status) { struct sk_buff *skb2; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -654,14 +805,14 @@ void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, int rtap_len; /* send frame to monitor interfaces now */ - rtap_len = ieee80211_tx_radiotap_len(info); + rtap_len = ieee80211_tx_radiotap_len(info, status); if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) { pr_err("ieee80211_tx_status: headroom too small\n"); dev_kfree_skb(skb); return; } ieee80211_add_tx_radiotap_header(local, sband, skb, retry_count, - rtap_len, shift); + rtap_len, shift, status); /* XXX: is this sufficient for BPF? */ skb_reset_mac_header(skb); @@ -901,7 +1052,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, } /* send to monitor interfaces */ - ieee80211_tx_monitor(local, skb, sband, retry_count, shift, send_to_cooked); + ieee80211_tx_monitor(local, skb, sband, retry_count, shift, + send_to_cooked, status); } void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 3bb4459b52c7..4768322dc202 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -1242,9 +1242,10 @@ TRACE_EVENT(drv_remain_on_channel, ) ); -DEFINE_EVENT(local_only_evt, drv_cancel_remain_on_channel, - TP_PROTO(struct ieee80211_local *local), - TP_ARGS(local) +DEFINE_EVENT(local_sdata_evt, drv_cancel_remain_on_channel, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + TP_ARGS(local, sdata) ); TRACE_EVENT(drv_set_ringparam, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f13eb2f61ccf..235c6377a203 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3546,6 +3546,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, ieee80211_tx_result r; struct ieee80211_vif *vif = txq->vif; + WARN_ON_ONCE(softirq_count() == 0); + begin: spin_lock_bh(&fq->lock); @@ -4647,7 +4649,8 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, if (!sband) return bcn; - ieee80211_tx_monitor(hw_to_local(hw), copy, sband, 1, shift, false); + ieee80211_tx_monitor(hw_to_local(hw), copy, sband, 1, shift, false, + NULL); return bcn; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1b224fa27367..286c7ee35e63 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1200,6 +1200,13 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->cisco_dtpc_elem = pos; break; + case WLAN_EID_ADDBA_EXT: + if (elen != sizeof(struct ieee80211_addba_ext_ie)) { + elem_parse_failed = true; + break; + } + elems->addba_ext_ie = (void *)pos; + break; case WLAN_EID_TIMEOUT_INTERVAL: if (elen >= sizeof(struct ieee80211_timeout_interval_ie)) elems->timeout_int = (void *)pos; @@ -1233,6 +1240,10 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION && elen == 3) { elems->mbssid_config_ie = (void *)&pos[1]; + } else if (pos[0] == WLAN_EID_EXT_HE_SPR && + elen >= sizeof(*elems->he_spr) && + elen >= ieee80211_he_spr_size(&pos[1])) { + elems->he_spr = (void *)&pos[1]; } break; default: @@ -2702,6 +2713,27 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, return pos; } +u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) +{ + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_supported_band *sband; + u8 n; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return 0; + + he_cap = ieee80211_get_he_iftype_cap(sband, iftype); + if (!he_cap) + return 0; + + n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem); + return 2 + 1 + + sizeof(he_cap->he_cap_elem) + n + + ieee80211_he_ppe_size(he_cap->ppe_thres[0], + he_cap->he_cap_elem.phy_cap_info); +} + u8 *ieee80211_ie_build_he_cap(u8 *pos, const struct ieee80211_sta_he_cap *he_cap, u8 *end) @@ -2891,6 +2923,34 @@ u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, return pos + sizeof(struct ieee80211_vht_operation); } +u8 *ieee80211_ie_build_he_oper(u8 *pos) +{ + struct ieee80211_he_operation *he_oper; + u32 he_oper_params; + + *pos++ = WLAN_EID_EXTENSION; + *pos++ = 1 + sizeof(struct ieee80211_he_operation); + *pos++ = WLAN_EID_EXT_HE_OPERATION; + + he_oper_params = 0; + he_oper_params |= u32_encode_bits(1023, /* disabled */ + IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); + he_oper_params |= u32_encode_bits(1, + IEEE80211_HE_OPERATION_ER_SU_DISABLE); + he_oper_params |= u32_encode_bits(1, + IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED); + + he_oper = (struct ieee80211_he_operation *)pos; + he_oper->he_oper_params = cpu_to_le32(he_oper_params); + + /* don't require special HE peer rates */ + he_oper->he_mcs_nss_set = cpu_to_le16(0xffff); + + /* TODO add VHT operational and 6GHz operational subelement? */ + + return pos + sizeof(struct ieee80211_vht_operation); +} + bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, struct cfg80211_chan_def *chandef) { @@ -3796,9 +3856,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, } /* Always allow software iftypes */ - if (local->hw.wiphy->software_iftypes & BIT(iftype) || - (iftype == NL80211_IFTYPE_AP_VLAN && - local->hw.wiphy->flags & WIPHY_FLAG_4ADDR_AP)) { + if (cfg80211_iftype_allowed(local->hw.wiphy, iftype, 0, 1)) { if (radar_detect) return -EINVAL; return 0; @@ -3833,7 +3891,8 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, if (sdata_iter == sdata || !ieee80211_sdata_running(sdata_iter) || - local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype)) + cfg80211_iftype_allowed(local->hw.wiphy, + wdev_iter->iftype, 0, 1)) continue; params.iftype_num[wdev_iter->iftype]++; diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index ee72779729e5..91bf32af55e9 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -946,7 +946,8 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) info = IEEE80211_SKB_CB(skb); - if (info->control.hw_key) + if (info->control.hw_key && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIE)) return TX_CONTINUE; if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) @@ -962,6 +963,9 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) bip_ipn_set64(mmie->sequence_number, pn64); + if (info->control.hw_key) + return TX_CONTINUE; + bip_aad(skb, aad); /* diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index ca7ac4a25ada..1d4e63326e68 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -226,7 +226,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, e.id = ip_to_id(map, ip); - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 2e151856ad99..e64d5f9a89dd 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1161,7 +1161,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, return -ENOENT; write_lock_bh(&ip_set_ref_lock); - if (set->ref != 0) { + if (set->ref != 0 || set->ref_netlink != 0) { ret = -IPSET_ERR_REFERENCED; goto out; } diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index faf59b6a998f..24d8f4df4230 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -89,15 +89,11 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - /* MAC can be src only */ - if (!(opt->flags & IPSET_DIM_TWO_SRC)) - return 0; - if (skb_mac_header(skb) < skb->head || (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 060565e7d227..145c8c992927 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -262,7 +262,7 @@ static inline unsigned int ip_vs_svc_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { - register unsigned int porth = ntohs(port); + unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; __u32 ahash; @@ -493,7 +493,7 @@ static inline unsigned int ip_vs_rs_hashkey(int af, const union nf_inet_addr *addr, __be16 port) { - register unsigned int porth = ntohs(port); + unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; #ifdef CONFIG_IP_VS_IPV6 diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index c8b5a504476c..77c323c36a88 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -160,7 +160,7 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) /* get weighted least-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) { - register struct ip_vs_dest_set_elem *e; + struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *least; int loh, doh; @@ -209,7 +209,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) /* get weighted most-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) { - register struct ip_vs_dest_set_elem *e; + struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *most; int moh, doh; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 605a7cfe7ca7..fe3b7b0c6c66 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7593,6 +7593,11 @@ static struct pernet_operations nf_tables_net_ops = { .exit = nf_tables_exit_net, }; +static struct flow_indr_block_ing_entry block_ing_entry = { + .cb = nft_indr_block_get_and_ing_cmd, + .list = LIST_HEAD_INIT(block_ing_entry.list), +}; + static int __init nf_tables_module_init(void) { int err; @@ -7624,6 +7629,7 @@ static int __init nf_tables_module_init(void) goto err5; nft_chain_route_init(); + flow_indr_add_block_ing_cb(&block_ing_entry); return err; err5: rhltable_destroy(&nft_objname_ht); @@ -7640,6 +7646,7 @@ err1: static void __exit nf_tables_module_exit(void) { + flow_indr_del_block_ing_cb(&block_ing_entry); nfnetlink_subsys_unregister(&nf_tables_subsys); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 64f5fd5f240e..d3c4c9c88bc8 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -171,24 +171,110 @@ static int nft_flow_offload_unbind(struct flow_block_offload *bo, return 0; } +static int nft_block_setup(struct nft_base_chain *basechain, + struct flow_block_offload *bo, + enum flow_block_command cmd) +{ + int err; + + switch (cmd) { + case FLOW_BLOCK_BIND: + err = nft_flow_offload_bind(bo, basechain); + break; + case FLOW_BLOCK_UNBIND: + err = nft_flow_offload_unbind(bo, basechain); + break; + default: + WARN_ON_ONCE(1); + err = -EOPNOTSUPP; + } + + return err; +} + +static int nft_block_offload_cmd(struct nft_base_chain *chain, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + int err; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + if (err < 0) + return err; + + return nft_block_setup(chain, &bo, cmd); +} + +static void nft_indr_block_ing_cmd(struct net_device *dev, + struct nft_base_chain *chain, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + + if (!chain) + return; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + cb(dev, cb_priv, TC_SETUP_BLOCK, &bo); + + nft_block_setup(chain, &bo, cmd); +} + +static int nft_indr_block_offload_cmd(struct nft_base_chain *chain, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct flow_block_offload bo = {}; + struct netlink_ext_ack extack = {}; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + flow_indr_block_call(dev, &bo, cmd); + + if (list_empty(&bo.cb_list)) + return -EOPNOTSUPP; + + return nft_block_setup(chain, &bo, cmd); +} + #define FLOW_SETUP_BLOCK TC_SETUP_BLOCK static int nft_flow_offload_chain(struct nft_trans *trans, enum flow_block_command cmd) { struct nft_chain *chain = trans->ctx.chain; - struct netlink_ext_ack extack = {}; - struct flow_block_offload bo = {}; struct nft_base_chain *basechain; struct net_device *dev; - int err; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); dev = basechain->ops.dev; - if (!dev || !dev->netdev_ops->ndo_setup_tc) + if (!dev) return -EOPNOTSUPP; /* Only default policy to accept is supported for now. */ @@ -197,26 +283,10 @@ static int nft_flow_offload_chain(struct nft_trans *trans, nft_trans_chain_policy(trans) != NF_ACCEPT) return -EOPNOTSUPP; - bo.command = cmd; - bo.block = &basechain->flow_block; - bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; - bo.extack = &extack; - INIT_LIST_HEAD(&bo.cb_list); - - err = dev->netdev_ops->ndo_setup_tc(dev, FLOW_SETUP_BLOCK, &bo); - if (err < 0) - return err; - - switch (cmd) { - case FLOW_BLOCK_BIND: - err = nft_flow_offload_bind(&bo, basechain); - break; - case FLOW_BLOCK_UNBIND: - err = nft_flow_offload_unbind(&bo, basechain); - break; - } - - return err; + if (dev->netdev_ops->ndo_setup_tc) + return nft_block_offload_cmd(basechain, dev, cmd); + else + return nft_indr_block_offload_cmd(basechain, dev, cmd); } int nft_flow_rule_offload_commit(struct net *net) @@ -266,3 +336,33 @@ int nft_flow_rule_offload_commit(struct net *net) return err; } + +void nft_indr_block_get_and_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) +{ + struct net *net = dev_net(dev); + const struct nft_table *table; + const struct nft_chain *chain; + + list_for_each_entry_rcu(table, &net->nft.tables, list) { + if (table->family != NFPROTO_NETDEV) + continue; + + list_for_each_entry_rcu(chain, &table->chains, list) { + if (nft_is_base_chain(chain)) { + struct nft_base_chain *basechain; + + basechain = nft_base_chain(chain); + if (!strncmp(basechain->dev_name, dev->name, + IFNAMSIZ)) { + nft_indr_block_ing_cmd(dev, basechain, + cb, cb_priv, + command); + return; + } + } + } + } +} diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index f1b1d948c07b..f69afb9ff3cb 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -60,24 +60,16 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = skb->mark; break; case NFT_META_IIF: - if (in == NULL) - goto err; - *dest = in->ifindex; + *dest = in ? in->ifindex : 0; break; case NFT_META_OIF: - if (out == NULL) - goto err; - *dest = out->ifindex; + *dest = out ? out->ifindex : 0; break; case NFT_META_IIFNAME: - if (in == NULL) - goto err; - strncpy((char *)dest, in->name, IFNAMSIZ); + strncpy((char *)dest, in ? in->name : "", IFNAMSIZ); break; case NFT_META_OIFNAME: - if (out == NULL) - goto err; - strncpy((char *)dest, out->name, IFNAMSIZ); + strncpy((char *)dest, out ? out->name : "", IFNAMSIZ); break; case NFT_META_IIFTYPE: if (in == NULL) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 96740d389377..c4f54ad2b98a 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -967,6 +967,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) window = skb->data[20]; + sock_hold(make); skb->sk = make; skb->destructor = sock_efree; make->sk_state = TCP_ESTABLISHED; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index ea64c90b14e8..17e6ca62f1be 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -970,7 +970,8 @@ static int nfc_genl_dep_link_down(struct sk_buff *skb, struct genl_info *info) int rc; u32 idx; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || + !info->attrs[NFC_ATTR_TARGET_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); @@ -1018,7 +1019,8 @@ static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg = NULL; u32 idx; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || + !info->attrs[NFC_ATTR_FIRMWARE_NAME]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 892287d06c17..65122bbccd27 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -222,6 +222,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) struct dp_stats_percpu *stats; u64 *stats_counter; u32 n_mask_hit; + int error; stats = this_cpu_ptr(dp->stats_percpu); @@ -229,7 +230,6 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) flow = ovs_flow_tbl_lookup_stats(&dp->table, key, &n_mask_hit); if (unlikely(!flow)) { struct dp_upcall_info upcall; - int error; memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; @@ -246,7 +246,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) ovs_flow_stats_update(flow, key->tp.flags, skb); sf_acts = rcu_dereference(flow->sf_acts); - ovs_execute_actions(dp, skb, sf_acts, key); + error = ovs_execute_actions(dp, skb, sf_acts, key); + if (unlikely(error)) + net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n", + ovs_dp_name(dp), error); stats_counter = &stats->n_hit; @@ -1047,7 +1050,7 @@ error: } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ -static struct sw_flow_actions *get_flow_actions(struct net *net, +static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net, const struct nlattr *a, const struct sw_flow_key *key, const struct sw_flow_mask *mask, @@ -1081,12 +1084,13 @@ static struct sw_flow_actions *get_flow_actions(struct net *net, * we should not to return match object with dangling reference * to mask. * */ -static int ovs_nla_init_match_and_action(struct net *net, - struct sw_flow_match *match, - struct sw_flow_key *key, - struct nlattr **a, - struct sw_flow_actions **acts, - bool log) +static noinline_for_stack int +ovs_nla_init_match_and_action(struct net *net, + struct sw_flow_match *match, + struct sw_flow_key *key, + struct nlattr **a, + struct sw_flow_actions **acts, + bool log) { struct sw_flow_mask mask; int error = 0; diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index ff74c4bbb9fc..9986d6065c4d 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -105,7 +105,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ESTABLISHED: - trans->cm_connect_complete(conn, event); + if (conn) + trans->cm_connect_complete(conn, event); break; case RDMA_CM_EVENT_REJECTED: @@ -137,6 +138,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_DISCONNECTED: + if (!conn) + break; rdsdebug("DISCONNECT event - dropping connection " "%pI6c->%pI6c\n", &conn->c_laddr, &conn->c_faddr); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 80335b4ee4fd..63b26baa108a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -226,6 +226,9 @@ struct rxrpc_security { int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, unsigned int, unsigned int, rxrpc_seq_t, u16); + /* Free crypto request on a call */ + void (*free_call_crypto)(struct rxrpc_call *); + /* Locate the data in a received packet that has been verified. */ void (*locate_data)(struct rxrpc_call *, struct sk_buff *, unsigned int *, unsigned int *); @@ -557,6 +560,7 @@ struct rxrpc_call { unsigned long expect_term_by; /* When we expect call termination by */ u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ + struct skcipher_request *cipher_req; /* Packet cipher request buffer */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ @@ -1061,6 +1065,7 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); +void rxrpc_put_peer_locked(struct rxrpc_peer *); /* * proc.c diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 217b12be9e08..60cbc81dc461 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -476,8 +476,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - if (conn) + if (conn) { rxrpc_disconnect_call(call); + conn->security->free_call_crypto(call); + } for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { rxrpc_free_skb(call->rxtx_buffer[i], diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index a29d26c273b5..f6c59f5fae9d 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -33,6 +33,10 @@ static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, return 0; } +static void none_free_call_crypto(struct rxrpc_call *call) +{ +} + static void none_locate_data(struct rxrpc_call *call, struct sk_buff *skb, unsigned int *_offset, unsigned int *_len) { @@ -83,6 +87,7 @@ const struct rxrpc_security rxrpc_no_security = { .exit = none_exit, .init_connection_security = none_init_connection_security, .prime_packet_security = none_prime_packet_security, + .free_call_crypto = none_free_call_crypto, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, .locate_data = none_locate_data, diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 9f2f45c09e58..7666ec72d37e 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -378,7 +378,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - rxrpc_put_peer(peer); + rxrpc_put_peer_locked(peer); } spin_unlock_bh(&rxnet->peer_hash_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9d3ce81cf8ae..9c3ac96f71cb 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -437,6 +437,24 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) } /* + * Drop a ref on a peer record where the caller already holds the + * peer_hash_lock. + */ +void rxrpc_put_peer_locked(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_dec_return(&peer->usage); + trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + if (n == 0) { + hash_del_rcu(&peer->hash_link); + list_del_init(&peer->keepalive_link); + kfree_rcu(peer, rcu); + } +} + +/* * Make sure all peer records have been discarded. */ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet) diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index ae8cd8926456..dbb109da1835 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -43,6 +43,7 @@ struct rxkad_level2_hdr { * packets */ static struct crypto_sync_skcipher *rxkad_ci; +static struct skcipher_request *rxkad_ci_req; static DEFINE_MUTEX(rxkad_ci_mutex); /* @@ -99,8 +100,8 @@ error: */ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) { + struct skcipher_request *req; struct rxrpc_key_token *token; - SYNC_SKCIPHER_REQUEST_ON_STACK(req, conn->cipher); struct scatterlist sg; struct rxrpc_crypt iv; __be32 *tmpbuf; @@ -115,6 +116,12 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) if (!tmpbuf) return -ENOMEM; + req = skcipher_request_alloc(&conn->cipher->base, GFP_NOFS); + if (!req) { + kfree(tmpbuf); + return -ENOMEM; + } + token = conn->params.key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); @@ -128,7 +135,7 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, tmpsize, iv.x); crypto_skcipher_encrypt(req); - skcipher_request_zero(req); + skcipher_request_free(req); memcpy(&conn->csum_iv, tmpbuf + 2, sizeof(conn->csum_iv)); kfree(tmpbuf); @@ -137,6 +144,35 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) } /* + * Allocate and prepare the crypto request on a call. For any particular call, + * this is called serially for the packets, so no lock should be necessary. + */ +static struct skcipher_request *rxkad_get_call_crypto(struct rxrpc_call *call) +{ + struct crypto_skcipher *tfm = &call->conn->cipher->base; + struct skcipher_request *cipher_req = call->cipher_req; + + if (!cipher_req) { + cipher_req = skcipher_request_alloc(tfm, GFP_NOFS); + if (!cipher_req) + return NULL; + call->cipher_req = cipher_req; + } + + return cipher_req; +} + +/* + * Clean up the crypto on a call. + */ +static void rxkad_free_call_crypto(struct rxrpc_call *call) +{ + if (call->cipher_req) + skcipher_request_free(call->cipher_req); + call->cipher_req = NULL; +} + +/* * partially encrypt a packet (level 1 security) */ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, @@ -246,7 +282,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, void *sechdr) { struct rxrpc_skb_priv *sp; - SYNC_SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); + struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; u32 x, y; @@ -265,6 +301,10 @@ static int rxkad_secure_packet(struct rxrpc_call *call, if (ret < 0) return ret; + req = rxkad_get_call_crypto(call); + if (!req) + return -ENOMEM; + /* continue encrypting from where we left off */ memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); @@ -502,7 +542,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, unsigned int offset, unsigned int len, rxrpc_seq_t seq, u16 expected_cksum) { - SYNC_SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); + struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; bool aborted; @@ -515,6 +555,10 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, if (!call->conn->cipher) return 0; + req = rxkad_get_call_crypto(call); + if (!req) + return -ENOMEM; + /* continue encrypting from where we left off */ memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); @@ -747,14 +791,18 @@ static void rxkad_calc_response_checksum(struct rxkad_response *response) /* * encrypt the response packet */ -static void rxkad_encrypt_response(struct rxrpc_connection *conn, - struct rxkad_response *resp, - const struct rxkad_key *s2) +static int rxkad_encrypt_response(struct rxrpc_connection *conn, + struct rxkad_response *resp, + const struct rxkad_key *s2) { - SYNC_SKCIPHER_REQUEST_ON_STACK(req, conn->cipher); + struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg[1]; + req = skcipher_request_alloc(&conn->cipher->base, GFP_NOFS); + if (!req) + return -ENOMEM; + /* continue encrypting from where we left off */ memcpy(&iv, s2->session_key, sizeof(iv)); @@ -764,7 +812,8 @@ static void rxkad_encrypt_response(struct rxrpc_connection *conn, skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x); crypto_skcipher_encrypt(req); - skcipher_request_zero(req); + skcipher_request_free(req); + return 0; } /* @@ -839,8 +888,9 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, /* calculate the response checksum and then do the encryption */ rxkad_calc_response_checksum(resp); - rxkad_encrypt_response(conn, resp, token->kad); - ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad); + ret = rxkad_encrypt_response(conn, resp, token->kad); + if (ret == 0) + ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad); kfree(resp); return ret; @@ -1017,18 +1067,16 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn, struct rxkad_response *resp, const struct rxrpc_crypt *session_key) { - SYNC_SKCIPHER_REQUEST_ON_STACK(req, rxkad_ci); + struct skcipher_request *req = rxkad_ci_req; struct scatterlist sg[1]; struct rxrpc_crypt iv; _enter(",,%08x%08x", ntohl(session_key->n[0]), ntohl(session_key->n[1])); - ASSERT(rxkad_ci != NULL); - mutex_lock(&rxkad_ci_mutex); if (crypto_sync_skcipher_setkey(rxkad_ci, session_key->x, - sizeof(*session_key)) < 0) + sizeof(*session_key)) < 0) BUG(); memcpy(&iv, session_key, sizeof(iv)); @@ -1222,10 +1270,26 @@ static void rxkad_clear(struct rxrpc_connection *conn) */ static int rxkad_init(void) { + struct crypto_sync_skcipher *tfm; + struct skcipher_request *req; + /* pin the cipher we need so that the crypto layer doesn't invoke * keventd to go get it */ - rxkad_ci = crypto_alloc_sync_skcipher("pcbc(fcrypt)", 0, 0); - return PTR_ERR_OR_ZERO(rxkad_ci); + tfm = crypto_alloc_sync_skcipher("pcbc(fcrypt)", 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + req = skcipher_request_alloc(&tfm->base, GFP_KERNEL); + if (!req) + goto nomem_tfm; + + rxkad_ci_req = req; + rxkad_ci = tfm; + return 0; + +nomem_tfm: + crypto_free_sync_skcipher(tfm); + return -ENOMEM; } /* @@ -1233,8 +1297,8 @@ static int rxkad_init(void) */ static void rxkad_exit(void) { - if (rxkad_ci) - crypto_free_sync_skcipher(rxkad_ci); + crypto_free_sync_skcipher(rxkad_ci); + skcipher_request_free(rxkad_ci_req); } /* @@ -1249,6 +1313,7 @@ const struct rxrpc_security rxkad = { .prime_packet_security = rxkad_prime_packet_security, .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, + .free_call_crypto = rxkad_free_call_crypto, .locate_data = rxkad_locate_data, .issue_challenge = rxkad_issue_challenge, .respond_to_challenge = rxkad_respond_to_challenge, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5d3f33ce6d41..bae14438f869 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -226,6 +226,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_notify_socket(call); goto out; } _debug("need instant resend %d", ret); diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 8126b26f125e..fd1f7e799e23 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -285,6 +285,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct tcf_bpf *prog; bool is_bpf, is_ebpf; int ret, res = 0; + u32 index; if (!nla) return -EINVAL; @@ -298,13 +299,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - - ret = tcf_idr_check_alloc(tn, &parm->index, act, bind); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { - ret = tcf_idr_create(tn, parm->index, est, act, + ret = tcf_idr_create(tn, index, est, act, &act_bpf_ops, bind, true); if (ret < 0) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index ce36b0f7e1dc..32ac04d77a45 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -103,6 +103,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct tcf_connmark_info *ci; struct tc_connmark *parm; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; @@ -116,13 +117,13 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_CONNMARK_PARMS]); - - ret = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, a, bind); if (!ret) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_connmark_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 621fb22ce2a9..9b9288267a54 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -52,6 +52,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -64,13 +65,13 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, if (tb[TCA_CSUM_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_csum_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b501ce0cf116..33a1a7406e87 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -666,6 +666,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, struct tc_ct *parm; struct tcf_ct *c; int err, res = 0; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed"); @@ -681,16 +682,16 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_CT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; if (!err) { - err = tcf_idr_create(tn, parm->index, est, a, + err = tcf_idr_create(tn, index, est, a, &act_ct_ops, bind, true); if (err) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return err; } res = ACT_P_CREATED; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 10eb2bb99861..06ef74b74911 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -157,10 +157,10 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + u32 dscpmask = 0, dscpstatemask, index; struct nlattr *tb[TCA_CTINFO_MAX + 1]; struct tcf_ctinfo_params *cp_new; struct tcf_chain *goto_ch = NULL; - u32 dscpmask = 0, dscpstatemask; struct tc_ctinfo *actparm; struct tcf_ctinfo *ci; u8 dscpmaskshift; @@ -206,12 +206,13 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, } /* done the validation:now to the actual action allocation */ - err = tcf_idr_check_alloc(tn, &actparm->index, a, bind); + index = actparm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, actparm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_ctinfo_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, actparm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b2380c5284e6..8f0140c6ca58 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -61,6 +61,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, struct tc_gact *parm; struct tcf_gact *gact; int ret = 0; + u32 index; int err; #ifdef CONFIG_GACT_PROB struct tc_gact_p *p_parm = NULL; @@ -77,6 +78,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, if (tb[TCA_GACT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_GACT_PARMS]); + index = parm->index; #ifndef CONFIG_GACT_PROB if (tb[TCA_GACT_PROB] != NULL) @@ -94,12 +96,12 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_gact_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 41d5398dd2f2..92ee853d43e6 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -479,8 +479,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, u8 *saddr = NULL; bool exists = false; int ret = 0; + u32 index; int err; + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed"); + return -EINVAL; + } + err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy, NULL); if (err < 0) @@ -502,7 +508,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { kfree(p); return err; @@ -514,10 +521,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, + ret = tcf_idr_create(tn, index, est, a, &act_ife_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); kfree(p); return ret; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 055faa298c8e..be3f88dfc37e 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -104,6 +104,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct net_device *dev; bool exists = false; int ret, err; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); @@ -118,8 +119,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_MIRRED_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -136,21 +137,21 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (!exists) { if (!parm->ifindex) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; } - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_mirred_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index ca2597ce4ac9..0f299e3b618c 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -138,6 +138,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, struct tcf_mpls *m; int ret = 0, err; u8 mpls_ttl = 0; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes"); @@ -153,6 +154,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_MPLS_PARMS]); + index = parm->index; /* Verify parameters against action type. */ switch (parm->m_action) { @@ -209,7 +211,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return -EINVAL; } - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -217,10 +219,10 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 45923ebb7a4f..7b858c11b1b5 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -44,6 +44,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; + u32 index; if (nla == NULL) return -EINVAL; @@ -56,13 +57,13 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (tb[TCA_NAT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_nat_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 45e9d6bfddb3..17360c6faeaa 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -149,6 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct tcf_pedit *p; int ret = 0, err; int ksize; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed"); @@ -179,18 +180,19 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (IS_ERR(keys_ex)) return PTR_ERR(keys_ex); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { if (!parm->nkeys) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); ret = -EINVAL; goto out_free; } - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_pedit_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); goto out_free; } ret = ACT_P_CREATED; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index a065f62fa79c..49cec3e64a4d 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -57,6 +57,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, police_net_id); struct tcf_police_params *new; bool exists = false; + u32 index; if (nla == NULL) return -EINVAL; @@ -73,7 +74,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -81,10 +83,10 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, NULL, a, + ret = tcf_idr_create(tn, index, NULL, a, &act_police_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 274d7a0c0e25..595308d60133 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -41,8 +41,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; + u32 psample_group_num, rate, index; struct tcf_chain *goto_ch = NULL; - u32 psample_group_num, rate; struct tc_sample *parm; struct tcf_sample *s; bool exists = false; @@ -59,8 +59,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -68,10 +68,10 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_sample_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index f28ddbabff76..33aefa25b545 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -95,6 +95,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, struct tcf_defact *d; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -108,7 +109,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -119,15 +121,15 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_simp_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 215a06705cef..b100870f02a6 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,6 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, u16 *queue_mapping = NULL, *ptype = NULL; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -146,8 +147,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -158,15 +159,15 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_skbedit_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 4f07706eff07..7da3518e18ef 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -87,12 +87,12 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct tcf_skbmod_params *p, *p_old; struct tcf_chain *goto_ch = NULL; struct tc_skbmod *parm; + u32 lflags = 0, index; struct tcf_skbmod *d; bool exists = false; u8 *daddr = NULL; u8 *saddr = NULL; u16 eth_type = 0; - u32 lflags = 0; int ret = 0, err; if (!nla) @@ -122,10 +122,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBMOD_PARMS]); + index = parm->index; if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -136,15 +137,15 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_skbmod_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 10dffda1d5cc..6d0debdc9b97 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -225,6 +225,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, __be16 flags = 0; u8 tos, ttl; int ret = 0; + u32 index; int err; if (!nla) { @@ -245,7 +246,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -345,7 +347,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); @@ -403,7 +405,7 @@ err_out: if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 9269d350fb8a..a3c9eea1ee8a 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -116,6 +116,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, u8 push_prio = 0; bool exists = false; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; @@ -128,7 +129,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -144,7 +146,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); @@ -152,7 +154,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -ERANGE; } @@ -166,7 +168,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EPROTONOSUPPORT; } } else { @@ -180,16 +182,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } action = parm->v_action; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_vlan_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -306,6 +308,14 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static size_t tcf_vlan_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_vlan)) + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */ + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */ + + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ +} + static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .id = TCA_ID_VLAN, @@ -315,6 +325,7 @@ static struct tc_action_ops act_vlan_ops = { .init = tcf_vlan_init, .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, + .get_fill_size = tcf_vlan_get_fill_size, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 3565d9aa09aa..e0d8b456e9f5 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -37,6 +37,7 @@ #include <net/tc_act/tc_skbedit.h> #include <net/tc_act/tc_ct.h> #include <net/tc_act/tc_mpls.h> +#include <net/flow_offload.h> extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; @@ -545,235 +546,71 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) } } -static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) -{ - const struct Qdisc_class_ops *cops; - struct Qdisc *qdisc; - - if (!dev_ingress_queue(dev)) - return NULL; - - qdisc = dev_ingress_queue(dev)->qdisc_sleeping; - if (!qdisc) - return NULL; - - cops = qdisc->ops->cl_ops; - if (!cops) - return NULL; - - if (!cops->tcf_block) - return NULL; - - return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); -} - -static struct rhashtable indr_setup_block_ht; - -struct tc_indr_block_dev { - struct rhash_head ht_node; - struct net_device *dev; - unsigned int refcnt; - struct list_head cb_list; - struct tcf_block *block; -}; - -struct tc_indr_block_cb { - struct list_head list; - void *cb_priv; - tc_indr_block_bind_cb_t *cb; - void *cb_ident; -}; - -static const struct rhashtable_params tc_indr_setup_block_ht_params = { - .key_offset = offsetof(struct tc_indr_block_dev, dev), - .head_offset = offsetof(struct tc_indr_block_dev, ht_node), - .key_len = sizeof(struct net_device *), -}; - -static struct tc_indr_block_dev * -tc_indr_block_dev_lookup(struct net_device *dev) -{ - return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, - tc_indr_setup_block_ht_params); -} - -static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev) -{ - struct tc_indr_block_dev *indr_dev; - - indr_dev = tc_indr_block_dev_lookup(dev); - if (indr_dev) - goto inc_ref; - - indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); - if (!indr_dev) - return NULL; - - INIT_LIST_HEAD(&indr_dev->cb_list); - indr_dev->dev = dev; - indr_dev->block = tc_dev_ingress_block(dev); - if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params)) { - kfree(indr_dev); - return NULL; - } - -inc_ref: - indr_dev->refcnt++; - return indr_dev; -} - -static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev) -{ - if (--indr_dev->refcnt) - return; - - rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params); - kfree(indr_dev); -} - -static struct tc_indr_block_cb * -tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - if (indr_block_cb->cb == cb && - indr_block_cb->cb_ident == cb_ident) - return indr_block_cb; - return NULL; -} - -static struct tc_indr_block_cb * -tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (indr_block_cb) - return ERR_PTR(-EEXIST); - - indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); - if (!indr_block_cb) - return ERR_PTR(-ENOMEM); - - indr_block_cb->cb_priv = cb_priv; - indr_block_cb->cb = cb; - indr_block_cb->cb_ident = cb_ident; - list_add(&indr_block_cb->list, &indr_dev->cb_list); - - return indr_block_cb; -} - -static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb) -{ - list_del(&indr_block_cb->list); - kfree(indr_block_cb); -} - static int tcf_block_setup(struct tcf_block *block, struct flow_block_offload *bo); -static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, - struct tc_indr_block_cb *indr_block_cb, +static void tc_indr_block_ing_cmd(struct net_device *dev, + struct tcf_block *block, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, enum flow_block_command command) { struct flow_block_offload bo = { .command = command, .binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, - .net = dev_net(indr_dev->dev), - .block_shared = tcf_block_non_null_shared(indr_dev->block), + .net = dev_net(dev), + .block_shared = tcf_block_non_null_shared(block), }; INIT_LIST_HEAD(&bo.cb_list); - if (!indr_dev->block) + if (!block) return; - bo.block = &indr_dev->block->flow_block; - - indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); - tcf_block_setup(indr_dev->block, &bo); -} - -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; - int err; - - indr_dev = tc_indr_block_dev_get(dev); - if (!indr_dev) - return -ENOMEM; - - indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); - err = PTR_ERR_OR_ZERO(indr_block_cb); - if (err) - goto err_dev_put; + bo.block = &block->flow_block; - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_BIND); - return 0; + cb(dev, cb_priv, TC_SETUP_BLOCK, &bo); -err_dev_put: - tc_indr_block_dev_put(indr_dev); - return err; + tcf_block_setup(block, &bo); } -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register); -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) { - int err; - - rtnl_lock(); - err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident); - rtnl_unlock(); + const struct Qdisc_class_ops *cops; + struct Qdisc *qdisc; - return err; -} -EXPORT_SYMBOL_GPL(tc_indr_block_cb_register); + if (!dev_ingress_queue(dev)) + return NULL; -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; + qdisc = dev_ingress_queue(dev)->qdisc_sleeping; + if (!qdisc) + return NULL; - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; + cops = qdisc->ops->cl_ops; + if (!cops) + return NULL; - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (!indr_block_cb) - return; + if (!cops->tcf_block) + return NULL; - /* Send unbind message if required to free any block cbs. */ - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_UNBIND); - tc_indr_block_cb_del(indr_block_cb); - tc_indr_block_dev_put(indr_dev); + return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); } -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister); -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static void tc_indr_block_get_and_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) { - rtnl_lock(); - __tc_indr_block_cb_unregister(dev, cb, cb_ident); - rtnl_unlock(); + struct tcf_block *block = tc_dev_ingress_block(dev); + + tc_indr_block_ing_cmd(dev, block, cb, cb_priv, command); } -EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister); -static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, +static void tc_indr_block_call(struct tcf_block *block, + struct net_device *dev, struct tcf_block_ext_info *ei, enum flow_block_command command, struct netlink_ext_ack *extack) { - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; struct flow_block_offload bo = { .command = command, .binder_type = ei->binder_type, @@ -784,16 +621,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, }; INIT_LIST_HEAD(&bo.cb_list); - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; - - indr_dev->block = command == FLOW_BLOCK_BIND ? block : NULL; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); - + flow_indr_block_call(dev, &bo, command); tcf_block_setup(block, &bo); } @@ -3205,6 +3033,12 @@ int tc_setup_flow_action(struct flow_action *flow_action, } else if (is_tcf_mirred_egress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED; entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_ingress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT_INGRESS; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_ingress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED_INGRESS; + entry->dev = tcf_mirred_dev(act); } else if (is_tcf_vlan(act)) { switch (tcf_vlan_action(act)) { case TCA_VLAN_ACT_PUSH: @@ -3294,6 +3128,9 @@ int tc_setup_flow_action(struct flow_action *flow_action, default: goto err_out; } + } else if (is_tcf_skbedit_ptype(act)) { + entry->id = FLOW_ACTION_PTYPE; + entry->ptype = tcf_skbedit_ptype(act); } else { goto err_out; } @@ -3346,6 +3183,11 @@ static struct pernet_operations tcf_net_ops = { .size = sizeof(struct tcf_net), }; +static struct flow_indr_block_ing_entry block_ing_entry = { + .cb = tc_indr_block_get_and_ing_cmd, + .list = LIST_HEAD_INIT(block_ing_entry.list), +}; + static int __init tc_filter_init(void) { int err; @@ -3358,10 +3200,7 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - err = rhashtable_init(&indr_setup_block_ht, - &tc_indr_setup_block_ht_params); - if (err) - goto err_rhash_setup_block_ht; + flow_indr_add_block_ing_cb(&block_ing_entry); rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, RTNL_FLAG_DOIT_UNLOCKED); @@ -3376,8 +3215,6 @@ static int __init tc_filter_init(void) return 0; -err_rhash_setup_block_ht: - unregister_pernet_subsys(&tcf_net_ops); err_register_pernet_subsys: destroy_workqueue(tc_filter_wq); return err; diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 25ef172c23df..30169b3adbbb 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -71,10 +71,10 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); - if (skb) + if (skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); - - prefetch(&skb->end); /* we'll need skb_shinfo() */ + prefetch(&skb->end); /* we'll need skb_shinfo() */ + } return skb; } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index d59fbcc745d1..c261c0a18868 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -45,7 +45,6 @@ struct fq_codel_flow { struct sk_buff *tail; struct list_head flowchain; int deficit; - u32 dropped; /* number of drops (or ECN marks) on this flow */ struct codel_vars cvars; }; /* please try to keep this structure <= 64 bytes */ @@ -173,7 +172,8 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, __qdisc_drop(skb, to_free); } while (++i < max_packets && len < threshold); - flow->dropped += i; + /* Tell codel to increase its signal strength also */ + flow->cvars.count += i; q->backlogs[idx] -= len; q->memory_usage -= mem; sch->qstats.drops += i; @@ -211,7 +211,6 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_add_tail(&flow->flowchain, &q->new_flows); q->new_flow_count++; flow->deficit = q->quantum; - flow->dropped = 0; } get_codel_cb(skb)->mem_usage = skb->truesize; q->memory_usage += get_codel_cb(skb)->mem_usage; @@ -286,7 +285,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct sk_buff *skb; struct fq_codel_flow *flow; struct list_head *head; - u32 prev_drop_count, prev_ecn_mark; begin: head = &q->new_flows; @@ -303,16 +301,10 @@ begin: goto begin; } - prev_drop_count = q->cstats.drop_count; - prev_ecn_mark = q->cstats.ecn_mark; - skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams, &flow->cvars, &q->cstats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - flow->dropped += q->cstats.drop_count - prev_drop_count; - flow->dropped += q->cstats.ecn_mark - prev_ecn_mark; - if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &q->new_flows) && !list_empty(&q->old_flows)) @@ -658,7 +650,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch_tree_unlock(sch); } qs.backlog = q->backlogs[idx]; - qs.drops = flow->dropped; + qs.drops = 0; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c39db507ba3f..046fd2c102b4 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -677,10 +677,6 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, }; -static const struct nla_policy entry_list_policy[TCA_TAPRIO_SCHED_MAX + 1] = { - [TCA_TAPRIO_SCHED_ENTRY] = { .type = NLA_NESTED }, -}; - static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index aa80cda36581..12503e16fa96 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -985,7 +985,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); - if (unlikely(IS_ERR(kaddrs))) + if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); /* Walk through the addrs buffer and count the number of addresses. */ @@ -1044,158 +1044,161 @@ out: return err; } -/* __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, int addrs_size) - * - * Common routine for handling connect() and sctp_connectx(). - * Connect will come in with just a single address. - */ -static int __sctp_connect(struct sock *sk, - struct sockaddr *kaddrs, - int addrs_size, int flags, - sctp_assoc_t *assoc_id) +static int sctp_connect_new_asoc(struct sctp_endpoint *ep, + const union sctp_addr *daddr, + const struct sctp_initmsg *init, + struct sctp_transport **tp) { + struct sctp_association *asoc; + struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); - struct sctp_sock *sp; - struct sctp_endpoint *ep; - struct sctp_association *asoc = NULL; - struct sctp_association *asoc2; - struct sctp_transport *transport; - union sctp_addr to; enum sctp_scope scope; - long timeo; - int err = 0; - int addrcnt = 0; - int walk_size = 0; - union sctp_addr *sa_addr = NULL; - void *addr_buf; - unsigned short port; + int err; - sp = sctp_sk(sk); - ep = sp->ep; + if (sctp_endpoint_is_peeled_off(ep, daddr)) + return -EADDRNOTAVAIL; - /* connect() cannot be done on a socket that is already in ESTABLISHED - * state - UDP-style peeled off socket or a TCP-style socket that - * is already connected. - * It cannot be done even on a TCP-style listening socket. - */ - if (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING) || - (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) { - err = -EISCONN; - goto out_free; + if (!ep->base.bind_addr.port) { + if (sctp_autobind(sk)) + return -EAGAIN; + } else { + if (ep->base.bind_addr.port < inet_prot_sock(net) && + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) + return -EACCES; } - /* Walk through the addrs buffer and count the number of addresses. */ - addr_buf = kaddrs; - while (walk_size < addrs_size) { - struct sctp_af *af; - - if (walk_size + sizeof(sa_family_t) > addrs_size) { - err = -EINVAL; - goto out_free; - } + scope = sctp_scope(daddr); + asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); + if (!asoc) + return -ENOMEM; - sa_addr = addr_buf; - af = sctp_get_af_specific(sa_addr->sa.sa_family); + err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL); + if (err < 0) + goto free; - /* If the address family is not supported or if this address - * causes the address buffer to overflow return EINVAL. - */ - if (!af || (walk_size + af->sockaddr_len) > addrs_size) { - err = -EINVAL; - goto out_free; - } + *tp = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); + if (!*tp) { + err = -ENOMEM; + goto free; + } - port = ntohs(sa_addr->v4.sin_port); + if (!init) + return 0; - /* Save current address so we can work with it */ - memcpy(&to, sa_addr, af->sockaddr_len); + if (init->sinit_num_ostreams) { + __u16 outcnt = init->sinit_num_ostreams; - err = sctp_verify_addr(sk, &to, af->sockaddr_len); + asoc->c.sinit_num_ostreams = outcnt; + /* outcnt has been changed, need to re-init stream */ + err = sctp_stream_init(&asoc->stream, outcnt, 0, GFP_KERNEL); if (err) - goto out_free; + goto free; + } - /* Make sure the destination port is correctly set - * in all addresses. - */ - if (asoc && asoc->peer.port && asoc->peer.port != port) { - err = -EINVAL; - goto out_free; - } + if (init->sinit_max_instreams) + asoc->c.sinit_max_instreams = init->sinit_max_instreams; - /* Check if there already is a matching association on the - * endpoint (other than the one created here). - */ - asoc2 = sctp_endpoint_lookup_assoc(ep, &to, &transport); - if (asoc2 && asoc2 != asoc) { - if (asoc2->state >= SCTP_STATE_ESTABLISHED) - err = -EISCONN; - else - err = -EALREADY; - goto out_free; - } + if (init->sinit_max_attempts) + asoc->max_init_attempts = init->sinit_max_attempts; - /* If we could not find a matching association on the endpoint, - * make sure that there is no peeled-off association matching - * the peer address even on another socket. - */ - if (sctp_endpoint_is_peeled_off(ep, &to)) { - err = -EADDRNOTAVAIL; - goto out_free; - } + if (init->sinit_max_init_timeo) + asoc->max_init_timeo = + msecs_to_jiffies(init->sinit_max_init_timeo); - if (!asoc) { - /* If a bind() or sctp_bindx() is not called prior to - * an sctp_connectx() call, the system picks an - * ephemeral port and will choose an address set - * equivalent to binding with a wildcard address. - */ - if (!ep->base.bind_addr.port) { - if (sctp_autobind(sk)) { - err = -EAGAIN; - goto out_free; - } - } else { - /* - * If an unprivileged user inherits a 1-many - * style socket with open associations on a - * privileged port, it MAY be permitted to - * accept new associations, but it SHOULD NOT - * be permitted to open new associations. - */ - if (ep->base.bind_addr.port < - inet_prot_sock(net) && - !ns_capable(net->user_ns, - CAP_NET_BIND_SERVICE)) { - err = -EACCES; - goto out_free; - } - } + return 0; +free: + sctp_association_free(asoc); + return err; +} - scope = sctp_scope(&to); - asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); - if (!asoc) { - err = -ENOMEM; - goto out_free; - } +static int sctp_connect_add_peer(struct sctp_association *asoc, + union sctp_addr *daddr, int addr_len) +{ + struct sctp_endpoint *ep = asoc->ep; + struct sctp_association *old; + struct sctp_transport *t; + int err; - err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, - GFP_KERNEL); - if (err < 0) { - goto out_free; - } + err = sctp_verify_addr(ep->base.sk, daddr, addr_len); + if (err) + return err; - } + old = sctp_endpoint_lookup_assoc(ep, daddr, &t); + if (old && old != asoc) + return old->state >= SCTP_STATE_ESTABLISHED ? -EISCONN + : -EALREADY; - /* Prime the peer's transport structures. */ - transport = sctp_assoc_add_peer(asoc, &to, GFP_KERNEL, - SCTP_UNKNOWN); - if (!transport) { - err = -ENOMEM; + if (sctp_endpoint_is_peeled_off(ep, daddr)) + return -EADDRNOTAVAIL; + + t = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); + if (!t) + return -ENOMEM; + + return 0; +} + +/* __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, int addrs_size) + * + * Common routine for handling connect() and sctp_connectx(). + * Connect will come in with just a single address. + */ +static int __sctp_connect(struct sock *sk, struct sockaddr *kaddrs, + int addrs_size, int flags, sctp_assoc_t *assoc_id) +{ + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_endpoint *ep = sp->ep; + struct sctp_transport *transport; + struct sctp_association *asoc; + void *addr_buf = kaddrs; + union sctp_addr *daddr; + struct sctp_af *af; + int walk_size, err; + long timeo; + + if (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING) || + (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) + return -EISCONN; + + daddr = addr_buf; + af = sctp_get_af_specific(daddr->sa.sa_family); + if (!af || af->sockaddr_len > addrs_size) + return -EINVAL; + + err = sctp_verify_addr(sk, daddr, af->sockaddr_len); + if (err) + return err; + + asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); + if (asoc) + return asoc->state >= SCTP_STATE_ESTABLISHED ? -EISCONN + : -EALREADY; + + err = sctp_connect_new_asoc(ep, daddr, NULL, &transport); + if (err) + return err; + asoc = transport->asoc; + + addr_buf += af->sockaddr_len; + walk_size = af->sockaddr_len; + while (walk_size < addrs_size) { + err = -EINVAL; + if (walk_size + sizeof(sa_family_t) > addrs_size) goto out_free; - } - addrcnt++; - addr_buf += af->sockaddr_len; + daddr = addr_buf; + af = sctp_get_af_specific(daddr->sa.sa_family); + if (!af || af->sockaddr_len + walk_size > addrs_size) + goto out_free; + + if (asoc->peer.port != ntohs(daddr->v4.sin_port)) + goto out_free; + + err = sctp_connect_add_peer(asoc, daddr, af->sockaddr_len); + if (err) + goto out_free; + + addr_buf += af->sockaddr_len; walk_size += af->sockaddr_len; } @@ -1208,40 +1211,25 @@ static int __sctp_connect(struct sock *sk, goto out_free; } - err = sctp_primitive_ASSOCIATE(net, asoc, NULL); - if (err < 0) { + err = sctp_primitive_ASSOCIATE(sock_net(sk), asoc, NULL); + if (err < 0) goto out_free; - } /* Initialize sk's dport and daddr for getpeername() */ inet_sk(sk)->inet_dport = htons(asoc->peer.port); - sp->pf->to_sk_daddr(sa_addr, sk); + sp->pf->to_sk_daddr(daddr, sk); sk->sk_err = 0; - timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); - if (assoc_id) *assoc_id = asoc->assoc_id; - err = sctp_wait_for_connect(asoc, &timeo); - /* Note: the asoc may be freed after the return of - * sctp_wait_for_connect. - */ - - /* Don't free association on exit. */ - asoc = NULL; + timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); + return sctp_wait_for_connect(asoc, &timeo); out_free: pr_debug("%s: took out_free path with asoc:%p kaddrs:%p err:%d\n", __func__, asoc, kaddrs, err); - - if (asoc) { - /* sctp_primitive_ASSOCIATE may have added this association - * To the hash table, try to unhash it, just in case, its a noop - * if it wasn't hashed so we're safe - */ - sctp_association_free(asoc); - } + sctp_association_free(asoc); return err; } @@ -1311,11 +1299,12 @@ static int __sctp_setsockopt_connectx(struct sock *sk, pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n", __func__, sk, addrs, addrs_size); - if (unlikely(addrs_size <= 0)) + /* make sure the 1st addr's sa_family is accessible later */ + if (unlikely(addrs_size < sizeof(sa_family_t))) return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); - if (unlikely(IS_ERR(kaddrs))) + if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); /* Allow security module to validate connectx addresses. */ @@ -1659,9 +1648,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, struct sctp_transport **tp) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; - struct net *net = sock_net(sk); struct sctp_association *asoc; - enum sctp_scope scope; struct cmsghdr *cmsg; __be32 flowinfo = 0; struct sctp_af *af; @@ -1676,20 +1663,6 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, sctp_sstate(sk, CLOSING))) return -EADDRNOTAVAIL; - if (sctp_endpoint_is_peeled_off(ep, daddr)) - return -EADDRNOTAVAIL; - - if (!ep->base.bind_addr.port) { - if (sctp_autobind(sk)) - return -EAGAIN; - } else { - if (ep->base.bind_addr.port < inet_prot_sock(net) && - !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) - return -EACCES; - } - - scope = sctp_scope(daddr); - /* Label connection socket for first association 1-to-many * style for client sequence socket()->sendmsg(). This * needs to be done before sctp_assoc_add_peer() as that will @@ -1705,45 +1678,10 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, if (err < 0) return err; - asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); - if (!asoc) - return -ENOMEM; - - if (sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL) < 0) { - err = -ENOMEM; - goto free; - } - - if (cmsgs->init) { - struct sctp_initmsg *init = cmsgs->init; - - if (init->sinit_num_ostreams) { - __u16 outcnt = init->sinit_num_ostreams; - - asoc->c.sinit_num_ostreams = outcnt; - /* outcnt has been changed, need to re-init stream */ - err = sctp_stream_init(&asoc->stream, outcnt, 0, - GFP_KERNEL); - if (err) - goto free; - } - - if (init->sinit_max_instreams) - asoc->c.sinit_max_instreams = init->sinit_max_instreams; - - if (init->sinit_max_attempts) - asoc->max_init_attempts = init->sinit_max_attempts; - - if (init->sinit_max_init_timeo) - asoc->max_init_timeo = - msecs_to_jiffies(init->sinit_max_init_timeo); - } - - *tp = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); - if (!*tp) { - err = -ENOMEM; - goto free; - } + err = sctp_connect_new_asoc(ep, daddr, cmsgs->init, tp); + if (err) + return err; + asoc = (*tp)->asoc; if (!cmsgs->addrs_msg) return 0; @@ -1753,8 +1691,6 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, /* sendv addr list parse */ for_each_cmsghdr(cmsg, cmsgs->addrs_msg) { - struct sctp_transport *transport; - struct sctp_association *old; union sctp_addr _daddr; int dlen; @@ -1788,30 +1724,10 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, daddr->v6.sin6_port = htons(asoc->peer.port); memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen); } - err = sctp_verify_addr(sk, daddr, sizeof(*daddr)); - if (err) - goto free; - - old = sctp_endpoint_lookup_assoc(ep, daddr, &transport); - if (old && old != asoc) { - if (old->state >= SCTP_STATE_ESTABLISHED) - err = -EISCONN; - else - err = -EALREADY; - goto free; - } - - if (sctp_endpoint_is_peeled_off(ep, daddr)) { - err = -EADDRNOTAVAIL; - goto free; - } - transport = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, - SCTP_UNKNOWN); - if (!transport) { - err = -ENOMEM; + err = sctp_connect_add_peer(asoc, daddr, sizeof(*daddr)); + if (err) goto free; - } } return 0; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index e2f8e369cd08..7235a6032671 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -43,8 +43,8 @@ static struct sctp_transport *sctp_transport_init(struct net *net, gfp_t gfp) { /* Copy in the address. */ - peer->ipaddr = *addr; peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); + memcpy(&peer->ipaddr, addr, peer->af_specific->sockaddr_len); memset(&peer->saddr, 0, sizeof(union sctp_addr)); peer->sack_generation = 0; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 302e355f2ebc..5b932583e407 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -263,7 +263,7 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr, /* Check if socket is already active */ rc = -EINVAL; - if (sk->sk_state != SMC_INIT) + if (sk->sk_state != SMC_INIT || smc->connect_nonblock) goto out_rel; smc->clcsock->sk->sk_reuse = sk->sk_reuse; @@ -1390,7 +1390,8 @@ static int smc_listen(struct socket *sock, int backlog) lock_sock(sk); rc = -EINVAL; - if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN)) + if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) || + smc->connect_nonblock) goto out; rc = 0; @@ -1518,7 +1519,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; if (msg->msg_flags & MSG_FASTOPEN) { - if (sk->sk_state == SMC_INIT) { + if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { @@ -1732,14 +1733,18 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, } break; case TCP_NODELAY: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } break; case TCP_CORK: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (!val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 1336f3cdad38..34f3e5641438 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -406,8 +406,10 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, rc = tipc_bcast_xmit(net, pkts, cong_link_cnt); } - if (dests->local) + if (dests->local) { + tipc_loopback_trace(net, &localq); tipc_sk_mcast_rcv(net, &localq, &inputq); + } exit: /* This queue should normally be empty by now */ __skb_queue_purge(pkts); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a809c0ec8d15..0214aa1c4427 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -389,6 +389,11 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev_put(dev); return -EINVAL; } + if (dev == net->loopback_dev) { + dev_put(dev); + pr_info("Enabling <%s> not permitted\n", b->name); + return -EINVAL; + } /* Autoconfigure own node identity if needed */ if (!tipc_own_id(net) && hwaddr_len <= NODE_ID_LEN) { @@ -674,6 +679,65 @@ void tipc_bearer_stop(struct net *net) } } +void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts) +{ + struct net_device *dev = net->loopback_dev; + struct sk_buff *skb, *_skb; + int exp; + + skb_queue_walk(pkts, _skb) { + skb = pskb_copy(_skb, GFP_ATOMIC); + if (!skb) + continue; + + exp = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb)); + if (exp > 0 && pskb_expand_head(skb, exp, 0, GFP_ATOMIC)) { + kfree_skb(skb); + continue; + } + + skb_reset_network_header(skb); + dev_hard_header(skb, dev, ETH_P_TIPC, dev->dev_addr, + dev->dev_addr, skb->len); + skb->dev = dev; + skb->pkt_type = PACKET_HOST; + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->protocol = eth_type_trans(skb, dev); + netif_rx_ni(skb); + } +} + +static int tipc_loopback_rcv_pkt(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *od) +{ + consume_skb(skb); + return NET_RX_SUCCESS; +} + +int tipc_attach_loopback(struct net *net) +{ + struct net_device *dev = net->loopback_dev; + struct tipc_net *tn = tipc_net(net); + + if (!dev) + return -ENODEV; + + dev_hold(dev); + tn->loopback_pt.dev = dev; + tn->loopback_pt.type = htons(ETH_P_TIPC); + tn->loopback_pt.func = tipc_loopback_rcv_pkt; + dev_add_pack(&tn->loopback_pt); + return 0; +} + +void tipc_detach_loopback(struct net *net) +{ + struct tipc_net *tn = tipc_net(net); + + dev_remove_pack(&tn->loopback_pt); + dev_put(net->loopback_dev); +} + /* Caller should hold rtnl_lock to protect the bearer */ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, struct tipc_bearer *bearer, int nlflags) diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 7f4c569594a5..ea0f3c49cbed 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -232,6 +232,16 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct tipc_media_addr *dst); void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); +void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts); +int tipc_attach_loopback(struct net *net); +void tipc_detach_loopback(struct net *net); + +static inline void tipc_loopback_trace(struct net *net, + struct sk_buff_head *pkts) +{ + if (unlikely(dev_nit_active(net->loopback_dev))) + tipc_clone_to_loopback(net, pkts); +} /* check if device MTU is too low for tipc headers */ static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) diff --git a/net/tipc/core.c b/net/tipc/core.c index c8370722f0bb..23cb379a93d6 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -82,6 +82,10 @@ static int __net_init tipc_init_net(struct net *net) if (err) goto out_bclink; + err = tipc_attach_loopback(net); + if (err) + goto out_bclink; + return 0; out_bclink: @@ -94,6 +98,7 @@ out_sk_rht: static void __net_exit tipc_exit_net(struct net *net) { + tipc_detach_loopback(net); tipc_net_stop(net); tipc_bcast_stop(net); tipc_nametbl_stop(net); diff --git a/net/tipc/core.h b/net/tipc/core.h index 7a68e1b6a066..60d829581068 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -125,6 +125,9 @@ struct tipc_net { /* Cluster capabilities */ u16 capabilities; + + /* Tracing of node internal messages */ + struct packet_type loopback_pt; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/link.c b/net/tipc/link.c index 66d3a07bc571..dd3155b14654 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -180,6 +180,7 @@ struct tipc_link { /* Fragmentation/reassembly */ struct sk_buff *reasm_buf; + struct sk_buff *reasm_tnlmsg; /* Broadcast */ u16 ackers; @@ -853,18 +854,31 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) */ static void link_prepare_wakeup(struct tipc_link *l) { + struct sk_buff_head *wakeupq = &l->wakeupq; + struct sk_buff_head *inputq = l->inputq; struct sk_buff *skb, *tmp; - int imp, i = 0; + struct sk_buff_head tmpq; + int avail[5] = {0,}; + int imp = 0; + + __skb_queue_head_init(&tmpq); + + for (; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) + avail[imp] = l->backlog[imp].limit - l->backlog[imp].len; - skb_queue_walk_safe(&l->wakeupq, skb, tmp) { + skb_queue_walk_safe(wakeupq, skb, tmp) { imp = TIPC_SKB_CB(skb)->chain_imp; - if (l->backlog[imp].len < l->backlog[imp].limit) { - skb_unlink(skb, &l->wakeupq); - skb_queue_tail(l->inputq, skb); - } else if (i++ > 10) { - break; - } + if (avail[imp] <= 0) + continue; + avail[imp]--; + __skb_unlink(skb, wakeupq); + __skb_queue_tail(&tmpq, skb); } + + spin_lock_bh(&inputq->lock); + skb_queue_splice_tail(&tmpq, inputq); + spin_unlock_bh(&inputq->lock); + } void tipc_link_reset(struct tipc_link *l) @@ -897,8 +911,10 @@ void tipc_link_reset(struct tipc_link *l) l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0; l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0; kfree_skb(l->reasm_buf); + kfree_skb(l->reasm_tnlmsg); kfree_skb(l->failover_reasm_skb); l->reasm_buf = NULL; + l->reasm_tnlmsg = NULL; l->failover_reasm_skb = NULL; l->rcv_unacked = 0; l->snd_nxt = 1; @@ -940,6 +956,9 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, int rc = 0; if (unlikely(msg_size(hdr) > mtu)) { + pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n", + skb_queue_len(list), msg_user(hdr), + msg_type(hdr), msg_size(hdr), mtu); skb_queue_purge(list); return -EMSGSIZE; } @@ -1233,6 +1252,7 @@ static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { struct sk_buff **reasm_skb = &l->failover_reasm_skb; + struct sk_buff **reasm_tnlmsg = &l->reasm_tnlmsg; struct sk_buff_head *fdefq = &l->failover_deferdq; struct tipc_msg *hdr = buf_msg(skb); struct sk_buff *iskb; @@ -1240,40 +1260,56 @@ static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb, int rc = 0; u16 seqno; - /* SYNCH_MSG */ - if (msg_type(hdr) == SYNCH_MSG) - goto drop; + if (msg_type(hdr) == SYNCH_MSG) { + kfree_skb(skb); + return 0; + } - /* FAILOVER_MSG */ - if (!tipc_msg_extract(skb, &iskb, &ipos)) { - pr_warn_ratelimited("Cannot extract FAILOVER_MSG, defq: %d\n", - skb_queue_len(fdefq)); - return rc; + /* Not a fragment? */ + if (likely(!msg_nof_fragms(hdr))) { + if (unlikely(!tipc_msg_extract(skb, &iskb, &ipos))) { + pr_warn_ratelimited("Unable to extract msg, defq: %d\n", + skb_queue_len(fdefq)); + return 0; + } + kfree_skb(skb); + } else { + /* Set fragment type for buf_append */ + if (msg_fragm_no(hdr) == 1) + msg_set_type(hdr, FIRST_FRAGMENT); + else if (msg_fragm_no(hdr) < msg_nof_fragms(hdr)) + msg_set_type(hdr, FRAGMENT); + else + msg_set_type(hdr, LAST_FRAGMENT); + + if (!tipc_buf_append(reasm_tnlmsg, &skb)) { + /* Successful but non-complete reassembly? */ + if (*reasm_tnlmsg || link_is_bc_rcvlink(l)) + return 0; + pr_warn_ratelimited("Unable to reassemble tunnel msg\n"); + return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); + } + iskb = skb; } do { seqno = buf_seqno(iskb); - if (unlikely(less(seqno, l->drop_point))) { kfree_skb(iskb); continue; } - if (unlikely(seqno != l->drop_point)) { __tipc_skb_queue_sorted(fdefq, seqno, iskb); continue; } l->drop_point++; - if (!tipc_data_input(l, iskb, inputq)) rc |= tipc_link_input(l, iskb, inputq, reasm_skb); if (unlikely(rc)) break; } while ((iskb = __tipc_skb_dequeue(fdefq, l->drop_point))); -drop: - kfree_skb(skb); return rc; } @@ -1663,14 +1699,18 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, struct sk_buff *skb, *tnlskb; struct tipc_msg *hdr, tnlhdr; struct sk_buff_head *queue = &l->transmq; - struct sk_buff_head tmpxq, tnlq; + struct sk_buff_head tmpxq, tnlq, frags; u16 pktlen, pktcnt, seqno = l->snd_nxt; + bool pktcnt_need_update = false; + u16 syncpt; + int rc; if (!tnl) return; skb_queue_head_init(&tnlq); skb_queue_head_init(&tmpxq); + skb_queue_head_init(&frags); /* At least one packet required for safe algorithm => add dummy */ skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, @@ -1684,6 +1724,31 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, tipc_link_xmit(l, &tnlq, &tmpxq); __skb_queue_purge(&tmpxq); + /* Link Synching: + * From now on, send only one single ("dummy") SYNCH message + * to peer. The SYNCH message does not contain any data, just + * a header conveying the synch point to the peer. + */ + if (mtyp == SYNCH_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { + tnlskb = tipc_msg_create(TUNNEL_PROTOCOL, SYNCH_MSG, + INT_H_SIZE, 0, l->addr, + tipc_own_addr(l->net), + 0, 0, 0); + if (!tnlskb) { + pr_warn("%sunable to create dummy SYNCH_MSG\n", + link_co_err); + return; + } + + hdr = buf_msg(tnlskb); + syncpt = l->snd_nxt + skb_queue_len(&l->backlogq) - 1; + msg_set_syncpt(hdr, syncpt); + msg_set_bearer_id(hdr, l->peer_bearer_id); + __skb_queue_tail(&tnlq, tnlskb); + tipc_link_xmit(tnl, &tnlq, xmitq); + return; + } + /* Initialize reusable tunnel packet header */ tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL, mtyp, INT_H_SIZE, l->addr); @@ -1701,6 +1766,39 @@ tnl: if (queue == &l->backlogq) msg_set_seqno(hdr, seqno++); pktlen = msg_size(hdr); + + /* Tunnel link MTU is not large enough? This could be + * due to: + * 1) Link MTU has just changed or set differently; + * 2) Or FAILOVER on the top of a SYNCH message + * + * The 2nd case should not happen if peer supports + * TIPC_TUNNEL_ENHANCED + */ + if (pktlen > tnl->mtu - INT_H_SIZE) { + if (mtyp == FAILOVER_MSG && + (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { + rc = tipc_msg_fragment(skb, &tnlhdr, tnl->mtu, + &frags); + if (rc) { + pr_warn("%sunable to frag msg: rc %d\n", + link_co_err, rc); + return; + } + pktcnt += skb_queue_len(&frags) - 1; + pktcnt_need_update = true; + skb_queue_splice_tail_init(&frags, &tnlq); + continue; + } + /* Unluckily, peer doesn't have TIPC_TUNNEL_ENHANCED + * => Just warn it and return! + */ + pr_warn_ratelimited("%stoo large msg <%d, %d>: %d!\n", + link_co_err, msg_user(hdr), + msg_type(hdr), msg_size(hdr)); + return; + } + msg_set_size(&tnlhdr, pktlen + INT_H_SIZE); tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC); if (!tnlskb) { @@ -1716,6 +1814,12 @@ tnl: goto tnl; } + if (pktcnt_need_update) + skb_queue_walk(&tnlq, skb) { + hdr = buf_msg(skb); + msg_set_msgcnt(hdr, pktcnt); + } + tipc_link_xmit(tnl, &tnlq, xmitq); if (mtyp == FAILOVER_MSG) { diff --git a/net/tipc/msg.c b/net/tipc/msg.c index f48e5857210f..e6d49cdc61b4 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -244,6 +244,65 @@ bool tipc_msg_validate(struct sk_buff **_skb) } /** + * tipc_msg_fragment - build a fragment skb list for TIPC message + * + * @skb: TIPC message skb + * @hdr: internal msg header to be put on the top of the fragments + * @pktmax: max size of a fragment incl. the header + * @frags: returned fragment skb list + * + * Returns 0 if the fragmentation is successful, otherwise: -EINVAL + * or -ENOMEM + */ +int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, + int pktmax, struct sk_buff_head *frags) +{ + int pktno, nof_fragms, dsz, dmax, eat; + struct tipc_msg *_hdr; + struct sk_buff *_skb; + u8 *data; + + /* Non-linear buffer? */ + if (skb_linearize(skb)) + return -ENOMEM; + + data = (u8 *)skb->data; + dsz = msg_size(buf_msg(skb)); + dmax = pktmax - INT_H_SIZE; + if (dsz <= dmax || !dmax) + return -EINVAL; + + nof_fragms = dsz / dmax + 1; + for (pktno = 1; pktno <= nof_fragms; pktno++) { + if (pktno < nof_fragms) + eat = dmax; + else + eat = dsz % dmax; + /* Allocate a new fragment */ + _skb = tipc_buf_acquire(INT_H_SIZE + eat, GFP_ATOMIC); + if (!_skb) + goto error; + skb_orphan(_skb); + __skb_queue_tail(frags, _skb); + /* Copy header & data to the fragment */ + skb_copy_to_linear_data(_skb, hdr, INT_H_SIZE); + skb_copy_to_linear_data_offset(_skb, INT_H_SIZE, data, eat); + data += eat; + /* Update the fragment's header */ + _hdr = buf_msg(_skb); + msg_set_fragm_no(_hdr, pktno); + msg_set_nof_fragms(_hdr, nof_fragms); + msg_set_size(_hdr, INT_H_SIZE + eat); + } + return 0; + +error: + __skb_queue_purge(frags); + __skb_queue_head_init(frags); + return -ENOMEM; +} + +/** * tipc_msg_build - create buffer chain containing specified header and data * @mhdr: Message header, to be prepended to data * @m: User message diff --git a/net/tipc/msg.h b/net/tipc/msg.h index da509f0eb9ca..1c8c8dd32a4e 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -721,12 +721,26 @@ static inline void msg_set_last_bcast(struct tipc_msg *m, u32 n) msg_set_bits(m, 4, 16, 0xffff, n); } +static inline u32 msg_nof_fragms(struct tipc_msg *m) +{ + return msg_bits(m, 4, 0, 0xffff); +} + +static inline void msg_set_nof_fragms(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 4, 0, 0xffff, n); +} + +static inline u32 msg_fragm_no(struct tipc_msg *m) +{ + return msg_bits(m, 4, 16, 0xffff); +} + static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 16, 0xffff, n); } - static inline u16 msg_next_sent(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); @@ -877,6 +891,16 @@ static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n) msg_set_bits(m, 9, 16, 0xffff, n); } +static inline u16 msg_syncpt(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_syncpt(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + static inline u32 msg_conn_ack(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); @@ -1035,6 +1059,8 @@ 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_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, + int pktmax, struct sk_buff_head *frags); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index d86030ef1232..e135d4e11231 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; + int req_size; struct net *net; struct sk_buff *rep; struct tlv_desc *req; @@ -257,7 +258,8 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, int err; struct sk_buff *arg; - if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type)) + if (msg->req_type && (!msg->req_size || + !TLV_CHECK_TYPE(msg->req, msg->req_type))) return -EINVAL; msg->rep = tipc_tlv_alloc(msg->rep_size); @@ -354,7 +356,8 @@ static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd, { int err; - if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type)) + if (msg->req_type && (!msg->req_size || + !TLV_CHECK_TYPE(msg->req, msg->req_type))) return -EINVAL; err = __tipc_nl_compat_doit(cmd, msg); @@ -1278,8 +1281,8 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) goto send; } - len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (!len || !TLV_OK(msg.req, len)) { + msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); + if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send; diff --git a/net/tipc/node.c b/net/tipc/node.c index 3a5be1d7e572..1bdcf0fc1a4d 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1443,6 +1443,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, int rc; if (in_own_node(net, dnode)) { + tipc_loopback_trace(net, list); tipc_sk_rcv(net, list); return 0; } @@ -1649,7 +1650,6 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, int usr = msg_user(hdr); int mtyp = msg_type(hdr); u16 oseqno = msg_seqno(hdr); - u16 iseqno = msg_seqno(msg_inner_hdr(hdr)); u16 exp_pkts = msg_msgcnt(hdr); u16 rcv_nxt, syncpt, dlv_nxt, inputq_len; int state = n->state; @@ -1748,7 +1748,10 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, /* Initiate synch mode if applicable */ if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) { - syncpt = iseqno + exp_pkts - 1; + if (n->capabilities & TIPC_TUNNEL_ENHANCED) + syncpt = msg_syncpt(hdr); + else + syncpt = msg_seqno(msg_inner_hdr(hdr)) + exp_pkts - 1; if (!tipc_link_is_up(l)) __tipc_node_link_up(n, bearer_id, xmitq); if (n->state == SELF_UP_PEER_UP) { diff --git a/net/tipc/node.h b/net/tipc/node.h index c0bf49ea3de4..291d0ecd4101 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -53,7 +53,8 @@ enum { TIPC_NODE_ID128 = (1 << 5), TIPC_LINK_PROTO_SEQNO = (1 << 6), TIPC_MCAST_RBCTL = (1 << 7), - TIPC_GAP_ACK_BLOCK = (1 << 8) + TIPC_GAP_ACK_BLOCK = (1 << 8), + TIPC_TUNNEL_ENHANCED = (1 << 9) }; #define TIPC_NODE_CAPABILITIES (TIPC_SYN_BIT | \ @@ -64,7 +65,8 @@ enum { TIPC_NODE_ID128 | \ TIPC_LINK_PROTO_SEQNO | \ TIPC_MCAST_RBCTL | \ - TIPC_GAP_ACK_BLOCK) + TIPC_GAP_ACK_BLOCK | \ + TIPC_TUNNEL_ENHANCED) #define INVALID_BEARER_ID -1 void tipc_node_stop(struct net *net); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index dd8537f988c4..83ae41d7e554 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -485,9 +485,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock, tsk_set_unreturnable(tsk, true); if (sock->type == SOCK_DGRAM) tsk_set_unreliable(tsk, true); - __skb_queue_head_init(&tsk->mc_method.deferredq); } - + __skb_queue_head_init(&tsk->mc_method.deferredq); trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " "); return 0; } diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index ca8ac96d22a9..3a12fc18239b 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -40,6 +40,7 @@ #include "socket.h" #include "addr.h" #include "msg.h" +#include "bearer.h" #include <net/sock.h> #include <linux/module.h> @@ -608,6 +609,7 @@ static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt) memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); skb_queue_head_init(&evtq); __skb_queue_tail(&evtq, skb); + tipc_loopback_trace(net, &evtq); tipc_sk_rcv(net, &evtq); } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 4ec8a06fa5d1..d184230665eb 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -244,12 +244,12 @@ static void tls_append_frag(struct tls_record_info *record, frag = &record->frags[record->num_frags - 1]; if (skb_frag_page(frag) == pfrag->page && - frag->page_offset + skb_frag_size(frag) == pfrag->offset) { + skb_frag_off(frag) + skb_frag_size(frag) == pfrag->offset) { skb_frag_size_add(frag, size); } else { ++frag; __skb_frag_set_page(frag, pfrag->page); - frag->page_offset = pfrag->offset; + skb_frag_off_set(frag, pfrag->offset); skb_frag_size_set(frag, size); ++record->num_frags; get_page(pfrag->page); @@ -301,7 +301,7 @@ static int tls_push_record(struct sock *sk, frag = &record->frags[i]; sg_unmark_end(&offload_ctx->sg_tx_data[i]); sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag), - skb_frag_size(frag), frag->page_offset); + skb_frag_size(frag), skb_frag_off(frag)); sk_mem_charge(sk, skb_frag_size(frag)); get_page(skb_frag_page(frag)); } @@ -324,7 +324,7 @@ static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, frag = &record->frags[0]; __skb_frag_set_page(frag, pfrag->page); - frag->page_offset = pfrag->offset; + skb_frag_off_set(frag, pfrag->offset); skb_frag_size_set(frag, prepend_size); get_page(pfrag->page); diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 9070d68a92a4..28895333701e 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -273,7 +273,7 @@ static int fill_sg_in(struct scatterlist *sg_in, __skb_frag_ref(frag); sg_set_page(sg_in + i, skb_frag_page(frag), - skb_frag_size(frag), frag->page_offset); + skb_frag_size(frag), skb_frag_off(frag)); remaining -= skb_frag_size(frag); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 4674e57e66b0..9cbbae606ced 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -261,24 +261,9 @@ void tls_ctx_free(struct tls_context *ctx) kfree(ctx); } -static void tls_sk_proto_close(struct sock *sk, long timeout) +static void tls_sk_proto_cleanup(struct sock *sk, + struct tls_context *ctx, long timeo) { - struct tls_context *ctx = tls_get_ctx(sk); - long timeo = sock_sndtimeo(sk, 0); - void (*sk_proto_close)(struct sock *sk, long timeout); - bool free_ctx = false; - - lock_sock(sk); - sk_proto_close = ctx->sk_proto_close; - - if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) - goto skip_tx_cleanup; - - if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) { - free_ctx = true; - goto skip_tx_cleanup; - } - if (unlikely(sk->sk_write_pending) && !wait_on_pending_writer(sk, &timeo)) tls_handle_open_record(sk, 0); @@ -287,7 +272,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) if (ctx->tx_conf == TLS_SW) { kfree(ctx->tx.rec_seq); kfree(ctx->tx.iv); - tls_sw_free_resources_tx(sk); + tls_sw_release_resources_tx(sk); #ifdef CONFIG_TLS_DEVICE } else if (ctx->tx_conf == TLS_HW) { tls_device_free_resources_tx(sk); @@ -295,26 +280,44 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) } if (ctx->rx_conf == TLS_SW) - tls_sw_free_resources_rx(sk); + tls_sw_release_resources_rx(sk); #ifdef CONFIG_TLS_DEVICE if (ctx->rx_conf == TLS_HW) tls_device_offload_cleanup_rx(sk); - - if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) { -#else - { #endif - tls_ctx_free(ctx); - ctx = NULL; - } +} -skip_tx_cleanup: +static void tls_sk_proto_close(struct sock *sk, long timeout) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tls_context *ctx = tls_get_ctx(sk); + long timeo = sock_sndtimeo(sk, 0); + bool free_ctx; + + if (ctx->tx_conf == TLS_SW) + tls_sw_cancel_work_tx(ctx); + + lock_sock(sk); + free_ctx = ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW; + + if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE) + tls_sk_proto_cleanup(sk, ctx, timeo); + + write_lock_bh(&sk->sk_callback_lock); + if (free_ctx) + icsk->icsk_ulp_data = NULL; + sk->sk_prot = ctx->sk_proto; + write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); - sk_proto_close(sk, timeout); - /* free ctx for TLS_HW_RECORD, used by tcp_set_state - * for sk->sk_prot->unhash [tls_hw_unhash] - */ + if (ctx->tx_conf == TLS_SW) + tls_sw_free_ctx_tx(ctx); + if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) + tls_sw_strparser_done(ctx); + if (ctx->rx_conf == TLS_SW) + tls_sw_free_ctx_rx(ctx); + ctx->sk_proto_close(sk, timeout); + if (free_ctx) tls_ctx_free(ctx); } @@ -526,6 +529,8 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { #endif rc = tls_set_sw_offload(sk, ctx, 1); + if (rc) + goto err_crypto_info; conf = TLS_SW; } } else { @@ -537,13 +542,13 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { #endif rc = tls_set_sw_offload(sk, ctx, 0); + if (rc) + goto err_crypto_info; conf = TLS_SW; } + tls_sw_strparser_arm(sk, ctx); } - if (rc) - goto err_crypto_info; - if (tx) ctx->tx_conf = conf; else @@ -607,6 +612,7 @@ static struct tls_context *create_ctx(struct sock *sk) ctx->setsockopt = sk->sk_prot->setsockopt; ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; + ctx->unhash = sk->sk_prot->unhash; return ctx; } @@ -764,7 +770,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_hw_hash; prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_hw_unhash; - prot[TLS_HW_RECORD][TLS_HW_RECORD].close = tls_sk_proto_close; } static int tls_init(struct sock *sk) @@ -773,7 +778,7 @@ static int tls_init(struct sock *sk) int rc = 0; if (tls_hw_prot(sk)) - goto out; + return 0; /* The TLS ulp is currently supported only for TCP sockets * in ESTABLISHED state. @@ -784,21 +789,38 @@ static int tls_init(struct sock *sk) if (sk->sk_state != TCP_ESTABLISHED) return -ENOTSUPP; + tls_build_proto(sk); + /* allocate tls context */ + write_lock_bh(&sk->sk_callback_lock); ctx = create_ctx(sk); if (!ctx) { rc = -ENOMEM; goto out; } - tls_build_proto(sk); ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; + ctx->sk_proto = sk->sk_prot; update_sk_prot(sk, ctx); out: + write_unlock_bh(&sk->sk_callback_lock); return rc; } +static void tls_update(struct sock *sk, struct proto *p) +{ + struct tls_context *ctx; + + ctx = tls_get_ctx(sk); + if (likely(ctx)) { + ctx->sk_proto_close = p->close; + ctx->sk_proto = p; + } else { + sk->sk_prot = p; + } +} + void tls_register_device(struct tls_device *device) { spin_lock_bh(&device_spinlock); @@ -819,6 +841,7 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .name = "tls", .owner = THIS_MODULE, .init = tls_init, + .update = tls_update, }; static int __init tls_register(void) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 53b4ad94e74a..91d21b048a9b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2054,7 +2054,16 @@ static void tls_data_ready(struct sock *sk) } } -void tls_sw_free_resources_tx(struct sock *sk) +void tls_sw_cancel_work_tx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + + set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask); + set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask); + cancel_delayed_work_sync(&ctx->tx_work.work); +} + +void tls_sw_release_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); @@ -2065,11 +2074,6 @@ void tls_sw_free_resources_tx(struct sock *sk) if (atomic_read(&ctx->encrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - release_sock(sk); - cancel_delayed_work_sync(&ctx->tx_work.work); - lock_sock(sk); - - /* Tx whatever records we can transmit and abandon the rest */ tls_tx_records(sk, -1); /* Free up un-sent records in tx_list. First, free @@ -2092,6 +2096,11 @@ void tls_sw_free_resources_tx(struct sock *sk) crypto_free_aead(ctx->aead_send); tls_free_open_rec(sk); +} + +void tls_sw_free_ctx_tx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); kfree(ctx); } @@ -2110,25 +2119,40 @@ void tls_sw_release_resources_rx(struct sock *sk) skb_queue_purge(&ctx->rx_list); crypto_free_aead(ctx->aead_recv); strp_stop(&ctx->strp); - write_lock_bh(&sk->sk_callback_lock); - sk->sk_data_ready = ctx->saved_data_ready; - write_unlock_bh(&sk->sk_callback_lock); - release_sock(sk); - strp_done(&ctx->strp); - lock_sock(sk); + /* If tls_sw_strparser_arm() was not called (cleanup paths) + * we still want to strp_stop(), but sk->sk_data_ready was + * never swapped. + */ + if (ctx->saved_data_ready) { + write_lock_bh(&sk->sk_callback_lock); + sk->sk_data_ready = ctx->saved_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + } } } -void tls_sw_free_resources_rx(struct sock *sk) +void tls_sw_strparser_done(struct tls_context *tls_ctx) { - struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - tls_sw_release_resources_rx(sk); + strp_done(&ctx->strp); +} + +void tls_sw_free_ctx_rx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); kfree(ctx); } +void tls_sw_free_resources_rx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + tls_sw_release_resources_rx(sk); + tls_sw_free_ctx_rx(tls_ctx); +} + /* The work handler to transmitt the encrypted records in tx_list */ static void tx_work_handler(struct work_struct *work) { @@ -2137,11 +2161,17 @@ static void tx_work_handler(struct work_struct *work) struct tx_work, work); struct sock *sk = tx_work->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_sw_context_tx *ctx; - if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) + if (unlikely(!tls_ctx)) return; + ctx = tls_sw_ctx_tx(tls_ctx); + if (test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask)) + return; + + if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) + return; lock_sock(sk); tls_tx_records(sk, -1); release_sock(sk); @@ -2160,6 +2190,18 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) } } +void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx); + + write_lock_bh(&sk->sk_callback_lock); + rx_ctx->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = tls_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + + strp_check_rcv(&rx_ctx->strp); +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2357,13 +2399,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) cb.parse_msg = tls_read_size; strp_init(&sw_ctx_rx->strp, sk, &cb); - - write_lock_bh(&sk->sk_callback_lock); - sw_ctx_rx->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = tls_data_ready; - write_unlock_bh(&sk->sk_callback_lock); - - strp_check_rcv(&sw_ctx_rx->strp); } goto out; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 2a1719c0f8d2..261521d286d6 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -312,6 +312,11 @@ static void hvs_close_connection(struct vmbus_channel *chan) lock_sock(sk); hvs_do_close_lock_held(vsock_sk(sk), true); release_sock(sk); + + /* Release the refcnt for the channel that's opened in + * hvs_open_connection(). + */ + sock_put(sk); } static void hvs_open_connection(struct vmbus_channel *chan) @@ -407,6 +412,9 @@ static void hvs_open_connection(struct vmbus_channel *chan) } set_per_channel_state(chan, conn_from_host ? new : sk); + + /* This reference will be dropped by hvs_close_connection(). */ + sock_hold(conn_from_host ? new : sk); vmbus_set_chn_rescind_callback(chan, hvs_close_connection); /* Set the pending send size to max packet size to always get diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 0815d1357861..082a30936690 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -307,6 +307,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) break; } + pkt->buf_len = buf_len; pkt->len = buf_len; sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 6f1a8aff65c5..94cc0fa3e848 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -26,6 +26,9 @@ /* How long to wait for graceful shutdown of a connection */ #define VSOCK_CLOSE_TIMEOUT (8 * HZ) +/* Threshold for detecting small packets to copy */ +#define GOOD_COPY_LEN 128 + static const struct virtio_transport *virtio_transport_get_ops(void) { const struct vsock_transport *t = vsock_core_get_transport(); @@ -64,6 +67,9 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, pkt->buf = kmalloc(len, GFP_KERNEL); if (!pkt->buf) goto out_pkt; + + pkt->buf_len = len; + err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; @@ -91,8 +97,17 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct virtio_vsock_pkt *pkt = opaque; struct af_vsockmon_hdr *hdr; struct sk_buff *skb; + size_t payload_len; + void *payload_buf; + + /* A packet could be split to fit the RX buffer, so we can retrieve + * the payload length from the header and the buffer pointer taking + * care of the offset in the original packet. + */ + payload_len = le32_to_cpu(pkt->hdr.len); + payload_buf = pkt->buf + pkt->off; - skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len, + skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len, GFP_ATOMIC); if (!skb) return NULL; @@ -132,8 +147,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr)); - if (pkt->len) { - skb_put_data(skb, pkt->buf, pkt->len); + if (payload_len) { + skb_put_data(skb, payload_buf, payload_len); } return skb; @@ -166,8 +181,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, vvs = vsk->trans; /* we can send less than pkt_len bytes */ - if (pkt_len > VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE) - pkt_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; + if (pkt_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + pkt_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE; /* virtio_transport_get_credit might return less than pkt_len credit */ pkt_len = virtio_transport_get_credit(vvs, pkt_len); @@ -204,10 +219,11 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { - spin_lock_bh(&vvs->tx_lock); + spin_lock_bh(&vvs->rx_lock); + vvs->last_fwd_cnt = vvs->fwd_cnt; pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); - spin_unlock_bh(&vvs->tx_lock); + spin_unlock_bh(&vvs->rx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); @@ -255,6 +271,7 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_sock *vvs = vsk->trans; struct virtio_vsock_pkt *pkt; size_t bytes, total = 0; + u32 free_space; int err = -EFAULT; spin_lock_bh(&vvs->rx_lock); @@ -285,11 +302,19 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, virtio_transport_free_pkt(pkt); } } + + free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt); + spin_unlock_bh(&vvs->rx_lock); - /* Send a credit pkt to peer */ - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + /* We send a credit update only when the space available seen + * by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + */ + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { + virtio_transport_send_credit_update(vsk, + VIRTIO_VSOCK_TYPE_STREAM, + NULL); + } return total; @@ -841,24 +866,60 @@ destroy: return err; } +static void +virtio_transport_recv_enqueue(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + bool free_pkt = false; + + pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->off = 0; + + spin_lock_bh(&vvs->rx_lock); + + virtio_transport_inc_rx_pkt(vvs, pkt); + + /* Try to copy small packets into the buffer of last packet queued, + * to avoid wasting memory queueing the entire buffer with a small + * payload. + */ + if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) { + struct virtio_vsock_pkt *last_pkt; + + last_pkt = list_last_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + /* If there is space in the last packet queued, we copy the + * new packet in its buffer. + */ + if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + memcpy(last_pkt->buf + last_pkt->len, pkt->buf, + pkt->len); + last_pkt->len += pkt->len; + free_pkt = true; + goto out; + } + } + + list_add_tail(&pkt->list, &vvs->rx_queue); + +out: + spin_unlock_bh(&vvs->rx_lock); + if (free_pkt) + virtio_transport_free_pkt(pkt); +} + static int virtio_transport_recv_connected(struct sock *sk, struct virtio_vsock_pkt *pkt) { struct vsock_sock *vsk = vsock_sk(sk); - struct virtio_vsock_sock *vvs = vsk->trans; int err = 0; switch (le16_to_cpu(pkt->hdr.op)) { case VIRTIO_VSOCK_OP_RW: - pkt->len = le32_to_cpu(pkt->hdr.len); - pkt->off = 0; - - spin_lock_bh(&vvs->rx_lock); - virtio_transport_inc_rx_pkt(vvs, pkt); - list_add_tail(&pkt->list, &vvs->rx_queue); - spin_unlock_bh(&vvs->rx_lock); - + virtio_transport_recv_enqueue(vsk, pkt); sk->sk_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c index 1af56df30276..3c54bb6b925a 100644 --- a/net/wimax/debugfs.c +++ b/net/wimax/debugfs.c @@ -13,49 +13,23 @@ #define D_SUBMODULE debugfs #include "debug-levels.h" - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - -int wimax_debugfs_add(struct wimax_dev *wimax_dev) +void wimax_debugfs_add(struct wimax_dev *wimax_dev) { - int result; struct net_device *net_dev = wimax_dev->net_dev; - struct device *dev = net_dev->dev.parent; struct dentry *dentry; char buf[128]; snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name); dentry = debugfs_create_dir(buf, NULL); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - else - dev_err(dev, "Can't create debugfs dentry: %d\n", - result); - goto out; - } wimax_dev->debugfs_dentry = dentry; - __debugfs_register("wimax_dl_", debugfs, dentry); - __debugfs_register("wimax_dl_", id_table, dentry); - __debugfs_register("wimax_dl_", op_msg, dentry); - __debugfs_register("wimax_dl_", op_reset, dentry); - __debugfs_register("wimax_dl_", op_rfkill, dentry); - __debugfs_register("wimax_dl_", op_state_get, dentry); - __debugfs_register("wimax_dl_", stack, dentry); - result = 0; -out: - return result; -error: - debugfs_remove_recursive(wimax_dev->debugfs_dentry); - return result; + d_level_register_debugfs("wimax_dl_", debugfs, dentry); + d_level_register_debugfs("wimax_dl_", id_table, dentry); + d_level_register_debugfs("wimax_dl_", op_msg, dentry); + d_level_register_debugfs("wimax_dl_", op_reset, dentry); + d_level_register_debugfs("wimax_dl_", op_rfkill, dentry); + d_level_register_debugfs("wimax_dl_", op_state_get, dentry); + d_level_register_debugfs("wimax_dl_", stack, dentry); } void wimax_debugfs_rm(struct wimax_dev *wimax_dev) diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 1ba99d65feca..4b9b1c5e8f3a 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -481,12 +481,7 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev) /* Set up user-space interaction */ mutex_lock(&wimax_dev->mutex); wimax_id_table_add(wimax_dev); - result = wimax_debugfs_add(wimax_dev); - if (result < 0) { - dev_err(dev, "cannot initialize debugfs: %d\n", - result); - goto error_debugfs_add; - } + wimax_debugfs_add(wimax_dev); __wimax_state_set(wimax_dev, WIMAX_ST_DOWN); mutex_unlock(&wimax_dev->mutex); @@ -498,10 +493,6 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev) d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev); return 0; -error_debugfs_add: - wimax_id_table_rm(wimax_dev); - mutex_unlock(&wimax_dev->mutex); - wimax_rfkill_rm(wimax_dev); error_rfkill_add: d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n", wimax_dev, net_dev, result); diff --git a/net/wimax/wimax-internal.h b/net/wimax/wimax-internal.h index e819a09337ee..40751207296c 100644 --- a/net/wimax/wimax-internal.h +++ b/net/wimax/wimax-internal.h @@ -57,13 +57,10 @@ void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state) void __wimax_state_change(struct wimax_dev *, enum wimax_st); #ifdef CONFIG_DEBUG_FS -int wimax_debugfs_add(struct wimax_dev *); +void wimax_debugfs_add(struct wimax_dev *); void wimax_debugfs_rm(struct wimax_dev *); #else -static inline int wimax_debugfs_add(struct wimax_dev *wimax_dev) -{ - return 0; -} +static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {} static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {} #endif diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 67f8360dfcee..63cf7131f601 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -217,6 +217,8 @@ config LIB80211_CRYPT_WEP config LIB80211_CRYPT_CCMP tristate + select CRYPTO_AES + select CRYPTO_CCM config LIB80211_CRYPT_TKIP tristate diff --git a/net/wireless/core.c b/net/wireless/core.c index 45d9afcff6d5..a599469b8157 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -142,12 +142,10 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, if (result) return result; - if (rdev->wiphy.debugfsdir && - !debugfs_rename(rdev->wiphy.debugfsdir->d_parent, - rdev->wiphy.debugfsdir, - rdev->wiphy.debugfsdir->d_parent, - newname)) - pr_err("failed to rename debugfs dir to %s!\n", newname); + if (rdev->wiphy.debugfsdir) + debugfs_rename(rdev->wiphy.debugfsdir->d_parent, + rdev->wiphy.debugfsdir, + rdev->wiphy.debugfsdir->d_parent, newname); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); @@ -899,11 +897,8 @@ int wiphy_register(struct wiphy *wiphy) cfg80211_rdev_list_generation++; /* add to debugfs */ - rdev->wiphy.debugfsdir = - debugfs_create_dir(wiphy_name(&rdev->wiphy), - ieee80211_debugfs_dir); - if (IS_ERR(rdev->wiphy.debugfsdir)) - rdev->wiphy.debugfsdir = NULL; + rdev->wiphy.debugfsdir = debugfs_create_dir(wiphy_name(&rdev->wiphy), + ieee80211_debugfs_dir); cfg80211_debugfs_rdev_add(rdev); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); @@ -1410,10 +1405,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, } break; case NETDEV_PRE_UP: - if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)) && - !(wdev->iftype == NL80211_IFTYPE_AP_VLAN && - rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP && - wdev->use_4addr)) + if (!cfg80211_iftype_allowed(wdev->wiphy, wdev->iftype, + wdev->use_4addr, 0)) return notifier_from_errno(-EOPNOTSUPP); if (rfkill_blocked(rdev->rfkill)) diff --git a/net/wireless/core.h b/net/wireless/core.h index ee8388fe4a92..77556c58d9ac 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -306,6 +306,8 @@ void ieee80211_set_bitrate_flags(struct wiphy *wiphy); void cfg80211_bss_expire(struct cfg80211_registered_device *rdev); void cfg80211_bss_age(struct cfg80211_registered_device *rdev, unsigned long age_secs); +void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev, + struct ieee80211_channel *channel); /* IBSS */ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c index 7e8ff9d7dcfa..6a5f08f7491e 100644 --- a/net/wireless/lib80211_crypt_ccmp.c +++ b/net/wireless/lib80211_crypt_ccmp.c @@ -22,6 +22,7 @@ #include <linux/ieee80211.h> #include <linux/crypto.h> +#include <crypto/aead.h> #include <net/lib80211.h> @@ -48,20 +49,13 @@ struct lib80211_ccmp_data { int key_idx; - struct crypto_cipher *tfm; + struct crypto_aead *tfm; /* scratch buffers for virt_to_page() (crypto API) */ - u8 tx_b0[AES_BLOCK_LEN], tx_b[AES_BLOCK_LEN], - tx_e[AES_BLOCK_LEN], tx_s0[AES_BLOCK_LEN]; - u8 rx_b0[AES_BLOCK_LEN], rx_b[AES_BLOCK_LEN], rx_a[AES_BLOCK_LEN]; + u8 tx_aad[2 * AES_BLOCK_LEN]; + u8 rx_aad[2 * AES_BLOCK_LEN]; }; -static inline void lib80211_ccmp_aes_encrypt(struct crypto_cipher *tfm, - const u8 pt[16], u8 ct[16]) -{ - crypto_cipher_encrypt_one(tfm, ct, pt); -} - static void *lib80211_ccmp_init(int key_idx) { struct lib80211_ccmp_data *priv; @@ -71,7 +65,7 @@ static void *lib80211_ccmp_init(int key_idx) goto fail; priv->key_idx = key_idx; - priv->tfm = crypto_alloc_cipher("aes", 0, 0); + priv->tfm = crypto_alloc_aead("ccm(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->tfm)) { priv->tfm = NULL; goto fail; @@ -82,7 +76,7 @@ static void *lib80211_ccmp_init(int key_idx) fail: if (priv) { if (priv->tfm) - crypto_free_cipher(priv->tfm); + crypto_free_aead(priv->tfm); kfree(priv); } @@ -93,25 +87,16 @@ static void lib80211_ccmp_deinit(void *priv) { struct lib80211_ccmp_data *_priv = priv; if (_priv && _priv->tfm) - crypto_free_cipher(_priv->tfm); + crypto_free_aead(_priv->tfm); kfree(priv); } -static inline void xor_block(u8 * b, u8 * a, size_t len) -{ - int i; - for (i = 0; i < len; i++) - b[i] ^= a[i]; -} - -static void ccmp_init_blocks(struct crypto_cipher *tfm, - struct ieee80211_hdr *hdr, - u8 * pn, size_t dlen, u8 * b0, u8 * auth, u8 * s0) +static int ccmp_init_iv_and_aad(const struct ieee80211_hdr *hdr, + const u8 *pn, u8 *iv, u8 *aad) { u8 *pos, qc = 0; size_t aad_len; int a4_included, qc_included; - u8 aad[2 * AES_BLOCK_LEN]; a4_included = ieee80211_has_a4(hdr->frame_control); qc_included = ieee80211_is_data_qos(hdr->frame_control); @@ -127,17 +112,19 @@ static void ccmp_init_blocks(struct crypto_cipher *tfm, aad_len += 2; } - /* CCM Initial Block: - * Flag (Include authentication header, M=3 (8-octet MIC), - * L=1 (2-octet Dlen)) - * Nonce: 0x00 | A2 | PN - * Dlen */ - b0[0] = 0x59; - b0[1] = qc; - memcpy(b0 + 2, hdr->addr2, ETH_ALEN); - memcpy(b0 + 8, pn, CCMP_PN_LEN); - b0[14] = (dlen >> 8) & 0xff; - b0[15] = dlen & 0xff; + /* In CCM, the initial vectors (IV) used for CTR mode encryption and CBC + * mode authentication are not allowed to collide, yet both are derived + * from the same vector. We only set L := 1 here to indicate that the + * data size can be represented in (L+1) bytes. The CCM layer will take + * care of storing the data length in the top (L+1) bytes and setting + * and clearing the other bits as is required to derive the two IVs. + */ + iv[0] = 0x1; + + /* Nonce: QC | A2 | PN */ + iv[1] = qc; + memcpy(iv + 2, hdr->addr2, ETH_ALEN); + memcpy(iv + 8, pn, CCMP_PN_LEN); /* AAD: * FC with bits 4..6 and 11..13 masked to zero; 14 is always one @@ -147,31 +134,20 @@ static void ccmp_init_blocks(struct crypto_cipher *tfm, * QC (if present) */ pos = (u8 *) hdr; - aad[0] = 0; /* aad_len >> 8 */ - aad[1] = aad_len & 0xff; - aad[2] = pos[0] & 0x8f; - aad[3] = pos[1] & 0xc7; - memcpy(aad + 4, hdr->addr1, 3 * ETH_ALEN); + aad[0] = pos[0] & 0x8f; + aad[1] = pos[1] & 0xc7; + memcpy(aad + 2, hdr->addr1, 3 * ETH_ALEN); pos = (u8 *) & hdr->seq_ctrl; - aad[22] = pos[0] & 0x0f; - aad[23] = 0; /* all bits masked */ - memset(aad + 24, 0, 8); + aad[20] = pos[0] & 0x0f; + aad[21] = 0; /* all bits masked */ + memset(aad + 22, 0, 8); if (a4_included) - memcpy(aad + 24, hdr->addr4, ETH_ALEN); + memcpy(aad + 22, hdr->addr4, ETH_ALEN); if (qc_included) { - aad[a4_included ? 30 : 24] = qc; + aad[a4_included ? 28 : 22] = qc; /* rest of QC masked */ } - - /* Start with the first block and AAD */ - lib80211_ccmp_aes_encrypt(tfm, b0, auth); - xor_block(auth, aad, AES_BLOCK_LEN); - lib80211_ccmp_aes_encrypt(tfm, auth, auth); - xor_block(auth, &aad[AES_BLOCK_LEN], AES_BLOCK_LEN); - lib80211_ccmp_aes_encrypt(tfm, auth, auth); - b0[0] &= 0x07; - b0[14] = b0[15] = 0; - lib80211_ccmp_aes_encrypt(tfm, b0, s0); + return aad_len; } static int lib80211_ccmp_hdr(struct sk_buff *skb, int hdr_len, @@ -214,13 +190,13 @@ static int lib80211_ccmp_hdr(struct sk_buff *skb, int hdr_len, static int lib80211_ccmp_encrypt(struct sk_buff *skb, int hdr_len, void *priv) { struct lib80211_ccmp_data *key = priv; - int data_len, i, blocks, last, len; - u8 *pos, *mic; struct ieee80211_hdr *hdr; - u8 *b0 = key->tx_b0; - u8 *b = key->tx_b; - u8 *e = key->tx_e; - u8 *s0 = key->tx_s0; + struct aead_request *req; + struct scatterlist sg[2]; + u8 *aad = key->tx_aad; + u8 iv[AES_BLOCK_LEN]; + int len, data_len, aad_len; + int ret; if (skb_tailroom(skb) < CCMP_MIC_LEN || skb->len < hdr_len) return -1; @@ -230,31 +206,28 @@ static int lib80211_ccmp_encrypt(struct sk_buff *skb, int hdr_len, void *priv) if (len < 0) return -1; - pos = skb->data + hdr_len + CCMP_HDR_LEN; + req = aead_request_alloc(key->tfm, GFP_ATOMIC); + if (!req) + return -ENOMEM; + hdr = (struct ieee80211_hdr *)skb->data; - ccmp_init_blocks(key->tfm, hdr, key->tx_pn, data_len, b0, b, s0); - - blocks = DIV_ROUND_UP(data_len, AES_BLOCK_LEN); - last = data_len % AES_BLOCK_LEN; - - for (i = 1; i <= blocks; i++) { - len = (i == blocks && last) ? last : AES_BLOCK_LEN; - /* Authentication */ - xor_block(b, pos, len); - lib80211_ccmp_aes_encrypt(key->tfm, b, b); - /* Encryption, with counter */ - b0[14] = (i >> 8) & 0xff; - b0[15] = i & 0xff; - lib80211_ccmp_aes_encrypt(key->tfm, b0, e); - xor_block(pos, e, len); - pos += len; - } + aad_len = ccmp_init_iv_and_aad(hdr, key->tx_pn, iv, aad); - mic = skb_put(skb, CCMP_MIC_LEN); - for (i = 0; i < CCMP_MIC_LEN; i++) - mic[i] = b[i] ^ s0[i]; + skb_put(skb, CCMP_MIC_LEN); - return 0; + sg_init_table(sg, 2); + sg_set_buf(&sg[0], aad, aad_len); + sg_set_buf(&sg[1], skb->data + hdr_len + CCMP_HDR_LEN, + data_len + CCMP_MIC_LEN); + + aead_request_set_callback(req, 0, NULL, NULL); + aead_request_set_ad(req, aad_len); + aead_request_set_crypt(req, sg, sg, data_len, iv); + + ret = crypto_aead_encrypt(req); + aead_request_free(req); + + return ret; } /* @@ -283,13 +256,13 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) struct lib80211_ccmp_data *key = priv; u8 keyidx, *pos; struct ieee80211_hdr *hdr; - u8 *b0 = key->rx_b0; - u8 *b = key->rx_b; - u8 *a = key->rx_a; + struct aead_request *req; + struct scatterlist sg[2]; + u8 *aad = key->rx_aad; + u8 iv[AES_BLOCK_LEN]; u8 pn[6]; - int i, blocks, last, len; - size_t data_len = skb->len - hdr_len - CCMP_HDR_LEN - CCMP_MIC_LEN; - u8 *mic = skb->data + skb->len - CCMP_MIC_LEN; + int aad_len, ret; + size_t data_len = skb->len - hdr_len - CCMP_HDR_LEN; if (skb->len < hdr_len + CCMP_HDR_LEN + CCMP_MIC_LEN) { key->dot11RSNAStatsCCMPFormatErrors++; @@ -337,28 +310,26 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) return -4; } - ccmp_init_blocks(key->tfm, hdr, pn, data_len, b0, a, b); - xor_block(mic, b, CCMP_MIC_LEN); - - blocks = DIV_ROUND_UP(data_len, AES_BLOCK_LEN); - last = data_len % AES_BLOCK_LEN; - - for (i = 1; i <= blocks; i++) { - len = (i == blocks && last) ? last : AES_BLOCK_LEN; - /* Decrypt, with counter */ - b0[14] = (i >> 8) & 0xff; - b0[15] = i & 0xff; - lib80211_ccmp_aes_encrypt(key->tfm, b0, b); - xor_block(pos, b, len); - /* Authentication */ - xor_block(a, pos, len); - lib80211_ccmp_aes_encrypt(key->tfm, a, a); - pos += len; - } + req = aead_request_alloc(key->tfm, GFP_ATOMIC); + if (!req) + return -ENOMEM; - if (memcmp(mic, a, CCMP_MIC_LEN) != 0) { - net_dbg_ratelimited("CCMP: decrypt failed: STA=%pM\n", - hdr->addr2); + aad_len = ccmp_init_iv_and_aad(hdr, pn, iv, aad); + + sg_init_table(sg, 2); + sg_set_buf(&sg[0], aad, aad_len); + sg_set_buf(&sg[1], pos, data_len); + + aead_request_set_callback(req, 0, NULL, NULL); + aead_request_set_ad(req, aad_len); + aead_request_set_crypt(req, sg, sg, data_len, iv); + + ret = crypto_aead_decrypt(req); + aead_request_free(req); + + if (ret) { + net_dbg_ratelimited("CCMP: decrypt failed: STA=%pM (%d)\n", + hdr->addr2, ret); key->dot11RSNAStatsCCMPDecryptErrors++; return -5; } @@ -377,7 +348,7 @@ static int lib80211_ccmp_set_key(void *key, int len, u8 * seq, void *priv) { struct lib80211_ccmp_data *data = priv; int keyidx; - struct crypto_cipher *tfm = data->tfm; + struct crypto_aead *tfm = data->tfm; keyidx = data->key_idx; memset(data, 0, sizeof(*data)); @@ -394,7 +365,9 @@ static int lib80211_ccmp_set_key(void *key, int len, u8 * seq, void *priv) data->rx_pn[4] = seq[1]; data->rx_pn[5] = seq[0]; } - crypto_cipher_setkey(data->tfm, data->key, CCMP_TK_LEN); + if (crypto_aead_setauthsize(data->tfm, CCMP_MIC_LEN) || + crypto_aead_setkey(data->tfm, data->key, CCMP_TK_LEN)) + return -1; } else if (len == 0) data->key_set = 0; else diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fc83dd179c1a..92e06482563c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -281,7 +281,16 @@ nl80211_pmsr_attr_policy[NL80211_PMSR_ATTR_MAX + 1] = { NLA_POLICY_NESTED_ARRAY(nl80211_psmr_peer_attr_policy), }; +static const struct nla_policy +he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = { + [NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] = + NLA_POLICY_RANGE(NLA_U8, 1, 20), + [NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET] = + NLA_POLICY_RANGE(NLA_U8, 1, 20), +}; + const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { + [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING, .len = 20-1 }, @@ -574,6 +583,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_SAE_PASSWORD] = { .type = NLA_BINARY, .len = SAE_PASSWORD_MAX_LEN }, [NL80211_ATTR_TWT_RESPONDER] = { .type = NLA_FLAG }, + [NL80211_ATTR_HE_OBSS_PD] = NLA_POLICY_NESTED(he_obss_pd_policy), }; /* policy for the key attributes */ @@ -749,17 +759,25 @@ int nl80211_prepare_wdev_dump(struct netlink_callback *cb, int err; if (!cb->args[0]) { + struct nlattr **attrbuf; + + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), + GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + err = nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, - genl_family_attrbuf(&nl80211_fam), - nl80211_fam.maxattr, + attrbuf, nl80211_fam.maxattr, nl80211_policy, NULL); - if (err) + if (err) { + kfree(attrbuf); return err; + } - *wdev = __cfg80211_wdev_from_attrs( - sock_net(cb->skb->sk), - genl_family_attrbuf(&nl80211_fam)); + *wdev = __cfg80211_wdev_from_attrs(sock_net(cb->skb->sk), + attrbuf); + kfree(attrbuf); if (IS_ERR(*wdev)) return PTR_ERR(*wdev); *rdev = wiphy_to_rdev((*wdev)->wiphy); @@ -2172,6 +2190,30 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.vht_capa_mod_mask)) goto nla_put_failure; + if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, + rdev->wiphy.perm_addr)) + goto nla_put_failure; + + if (!is_zero_ether_addr(rdev->wiphy.addr_mask) && + nla_put(msg, NL80211_ATTR_MAC_MASK, ETH_ALEN, + rdev->wiphy.addr_mask)) + goto nla_put_failure; + + if (rdev->wiphy.n_addresses > 1) { + void *attr; + + attr = nla_nest_start(msg, NL80211_ATTR_MAC_ADDRS); + if (!attr) + goto nla_put_failure; + + for (i = 0; i < rdev->wiphy.n_addresses; i++) + if (nla_put(msg, i + 1, ETH_ALEN, + rdev->wiphy.addresses[i].addr)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + } + state->split_start++; break; case 10: @@ -2366,14 +2408,21 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb, struct netlink_callback *cb, struct nl80211_dump_wiphy_state *state) { - struct nlattr **tb = genl_family_attrbuf(&nl80211_fam); - int ret = nlmsg_parse_deprecated(cb->nlh, - GENL_HDRLEN + nl80211_fam.hdrsize, - tb, nl80211_fam.maxattr, - nl80211_policy, NULL); + struct nlattr **tb = kcalloc(NUM_NL80211_ATTR, sizeof(*tb), GFP_KERNEL); + int ret; + + if (!tb) + return -ENOMEM; + + ret = nlmsg_parse_deprecated(cb->nlh, + GENL_HDRLEN + nl80211_fam.hdrsize, + tb, nl80211_fam.maxattr, + nl80211_policy, NULL); /* ignore parse errors for backward compatibility */ - if (ret) - return 0; + if (ret) { + ret = 0; + goto out; + } state->split = tb[NL80211_ATTR_SPLIT_WIPHY_DUMP]; if (tb[NL80211_ATTR_WIPHY]) @@ -2386,8 +2435,10 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb, int ifidx = nla_get_u32(tb[NL80211_ATTR_IFINDEX]); netdev = __dev_get_by_index(sock_net(skb->sk), ifidx); - if (!netdev) - return -ENODEV; + if (!netdev) { + ret = -ENODEV; + goto out; + } if (netdev->ieee80211_ptr) { rdev = wiphy_to_rdev( netdev->ieee80211_ptr->wiphy); @@ -2395,7 +2446,10 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb, } } - return 0; + ret = 0; +out: + kfree(tb); + return ret; } static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) @@ -3484,9 +3538,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) return err; } - if (!(rdev->wiphy.interface_modes & (1 << type)) && - !(type == NL80211_IFTYPE_AP_VLAN && params.use_4addr && - rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP)) + if (!cfg80211_iftype_allowed(&rdev->wiphy, type, params.use_4addr, 0)) return -EOPNOTSUPP; err = nl80211_parse_mon_options(rdev, type, info, ¶ms); @@ -4361,6 +4413,34 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, return 0; } +static int nl80211_parse_he_obss_pd(struct nlattr *attrs, + struct ieee80211_he_obss_pd *he_obss_pd) +{ + struct nlattr *tb[NL80211_HE_OBSS_PD_ATTR_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NL80211_HE_OBSS_PD_ATTR_MAX, attrs, + he_obss_pd_policy, NULL); + if (err) + return err; + + if (!tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] || + !tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]) + return -EINVAL; + + he_obss_pd->min_offset = + nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]); + he_obss_pd->max_offset = + nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]); + + if (he_obss_pd->min_offset >= he_obss_pd->max_offset) + return -EINVAL; + + he_obss_pd->enable = true; + + return 0; +} + static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params, const u8 *rates) { @@ -4645,6 +4725,14 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params.twt_responder = nla_get_flag(info->attrs[NL80211_ATTR_TWT_RESPONDER]); + if (info->attrs[NL80211_ATTR_HE_OBSS_PD]) { + err = nl80211_parse_he_obss_pd( + info->attrs[NL80211_ATTR_HE_OBSS_PD], + ¶ms.he_obss_pd); + if (err) + return err; + } + nl80211_calculate_ap_params(¶ms); if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) @@ -8700,7 +8788,7 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) { - struct nlattr **attrbuf = genl_family_attrbuf(&nl80211_fam); + struct nlattr **attrbuf; struct survey_info survey; struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; @@ -8708,6 +8796,10 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) int res; bool radio_stats; + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + rtnl_lock(); res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); if (res) @@ -8752,6 +8844,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) cb->args[2] = survey_idx; res = skb->len; out_err: + kfree(attrbuf); rtnl_unlock(); return res; } @@ -9611,6 +9704,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg80211_registered_device *rdev; + struct nlattr **attrbuf = NULL; int err; long phy_idx; void *data = NULL; @@ -9631,7 +9725,12 @@ static int nl80211_testmode_dump(struct sk_buff *skb, goto out_err; } } else { - struct nlattr **attrbuf = genl_family_attrbuf(&nl80211_fam); + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), + GFP_KERNEL); + if (!attrbuf) { + err = -ENOMEM; + goto out_err; + } err = nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, @@ -9698,6 +9797,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, /* see above */ cb->args[0] = phy_idx + 1; out_err: + kfree(attrbuf); rtnl_unlock(); return err; } @@ -12791,7 +12891,7 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, struct cfg80211_registered_device **rdev, struct wireless_dev **wdev) { - struct nlattr **attrbuf = genl_family_attrbuf(&nl80211_fam); + struct nlattr **attrbuf; u32 vid, subcmd; unsigned int i; int vcmd_idx = -1; @@ -12822,24 +12922,32 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, return 0; } + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + err = nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, attrbuf, nl80211_fam.maxattr, nl80211_policy, NULL); if (err) - return err; + goto out; if (!attrbuf[NL80211_ATTR_VENDOR_ID] || - !attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) - return -EINVAL; + !attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) { + err = -EINVAL; + goto out; + } *wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), attrbuf); if (IS_ERR(*wdev)) *wdev = NULL; *rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk), attrbuf); - if (IS_ERR(*rdev)) - return PTR_ERR(*rdev); + if (IS_ERR(*rdev)) { + err = PTR_ERR(*rdev); + goto out; + } vid = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_ID]); subcmd = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_SUBCMD]); @@ -12852,15 +12960,19 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd) continue; - if (!vcmd->dumpit) - return -EOPNOTSUPP; + if (!vcmd->dumpit) { + err = -EOPNOTSUPP; + goto out; + } vcmd_idx = i; break; } - if (vcmd_idx < 0) - return -EOPNOTSUPP; + if (vcmd_idx < 0) { + err = -EOPNOTSUPP; + goto out; + } if (attrbuf[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(attrbuf[NL80211_ATTR_VENDOR_DATA]); @@ -12871,7 +12983,7 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, attrbuf[NL80211_ATTR_VENDOR_DATA], cb->extack); if (err) - return err; + goto out; } /* 0 is the first index - add 1 to parse only once */ @@ -12883,7 +12995,10 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, cb->args[4] = data_len; /* keep rtnl locked in successful case */ - return 0; + err = 0; +out: + kfree(attrbuf); + return err; } static int nl80211_vendor_cmd_dump(struct sk_buff *skb, @@ -14561,6 +14676,7 @@ static struct genl_family nl80211_fam __ro_after_init = { .n_ops = ARRAY_SIZE(nl80211_ops), .mcgrps = nl80211_mcgrps, .n_mcgrps = ARRAY_SIZE(nl80211_mcgrps), + .parallel_ops = true, }; /* notification functions */ @@ -16092,7 +16208,9 @@ void cfg80211_ch_switch_notify(struct net_device *dev, if (wdev->iftype == NL80211_IFTYPE_STATION && !WARN_ON(!wdev->current_bss)) - wdev->current_bss->pub.channel = chandef->chan; + cfg80211_update_assoc_bss_entry(wdev, chandef->chan); + + cfg80211_sched_dfs_chan_update(rdev); nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL, NL80211_CMD_CH_SWITCH_NOTIFY, 0); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d66e6d4b7555..d313c9befa23 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1091,6 +1091,93 @@ struct cfg80211_non_tx_bss { u8 bssid_index; }; +static bool +cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, + struct cfg80211_internal_bss *known, + struct cfg80211_internal_bss *new, + bool signal_valid) +{ + lockdep_assert_held(&rdev->bss_lock); + + /* Update IEs */ + if (rcu_access_pointer(new->pub.proberesp_ies)) { + const struct cfg80211_bss_ies *old; + + old = rcu_access_pointer(known->pub.proberesp_ies); + + rcu_assign_pointer(known->pub.proberesp_ies, + new->pub.proberesp_ies); + /* Override possible earlier Beacon frame IEs */ + rcu_assign_pointer(known->pub.ies, + new->pub.proberesp_ies); + if (old) + kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); + } else if (rcu_access_pointer(new->pub.beacon_ies)) { + const struct cfg80211_bss_ies *old; + struct cfg80211_internal_bss *bss; + + if (known->pub.hidden_beacon_bss && + !list_empty(&known->hidden_list)) { + const struct cfg80211_bss_ies *f; + + /* The known BSS struct is one of the probe + * response members of a group, but we're + * receiving a beacon (beacon_ies in the new + * bss is used). This can only mean that the + * AP changed its beacon from not having an + * SSID to showing it, which is confusing so + * drop this information. + */ + + f = rcu_access_pointer(new->pub.beacon_ies); + kfree_rcu((struct cfg80211_bss_ies *)f, rcu_head); + return false; + } + + old = rcu_access_pointer(known->pub.beacon_ies); + + rcu_assign_pointer(known->pub.beacon_ies, new->pub.beacon_ies); + + /* Override IEs if they were from a beacon before */ + if (old == rcu_access_pointer(known->pub.ies)) + rcu_assign_pointer(known->pub.ies, new->pub.beacon_ies); + + /* Assign beacon IEs to all sub entries */ + list_for_each_entry(bss, &known->hidden_list, hidden_list) { + const struct cfg80211_bss_ies *ies; + + ies = rcu_access_pointer(bss->pub.beacon_ies); + WARN_ON(ies != old); + + rcu_assign_pointer(bss->pub.beacon_ies, + new->pub.beacon_ies); + } + + if (old) + kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); + } + + known->pub.beacon_interval = new->pub.beacon_interval; + + /* don't update the signal if beacon was heard on + * adjacent channel. + */ + if (signal_valid) + known->pub.signal = new->pub.signal; + known->pub.capability = new->pub.capability; + known->ts = new->ts; + known->ts_boottime = new->ts_boottime; + known->parent_tsf = new->parent_tsf; + known->pub.chains = new->pub.chains; + memcpy(known->pub.chain_signal, new->pub.chain_signal, + IEEE80211_MAX_CHAINS); + ether_addr_copy(known->parent_bssid, new->parent_bssid); + known->pub.max_bssid_indicator = new->pub.max_bssid_indicator; + known->pub.bssid_index = new->pub.bssid_index; + + return true; +} + /* Returned bss is reference counted and must be cleaned up appropriately. */ struct cfg80211_internal_bss * cfg80211_bss_update(struct cfg80211_registered_device *rdev, @@ -1114,88 +1201,8 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, found = rb_find_bss(rdev, tmp, BSS_CMP_REGULAR); if (found) { - /* Update IEs */ - if (rcu_access_pointer(tmp->pub.proberesp_ies)) { - const struct cfg80211_bss_ies *old; - - old = rcu_access_pointer(found->pub.proberesp_ies); - - rcu_assign_pointer(found->pub.proberesp_ies, - tmp->pub.proberesp_ies); - /* Override possible earlier Beacon frame IEs */ - rcu_assign_pointer(found->pub.ies, - tmp->pub.proberesp_ies); - if (old) - kfree_rcu((struct cfg80211_bss_ies *)old, - rcu_head); - } else if (rcu_access_pointer(tmp->pub.beacon_ies)) { - const struct cfg80211_bss_ies *old; - struct cfg80211_internal_bss *bss; - - if (found->pub.hidden_beacon_bss && - !list_empty(&found->hidden_list)) { - const struct cfg80211_bss_ies *f; - - /* - * The found BSS struct is one of the probe - * response members of a group, but we're - * receiving a beacon (beacon_ies in the tmp - * bss is used). This can only mean that the - * AP changed its beacon from not having an - * SSID to showing it, which is confusing so - * drop this information. - */ - - f = rcu_access_pointer(tmp->pub.beacon_ies); - kfree_rcu((struct cfg80211_bss_ies *)f, - rcu_head); - goto drop; - } - - old = rcu_access_pointer(found->pub.beacon_ies); - - rcu_assign_pointer(found->pub.beacon_ies, - tmp->pub.beacon_ies); - - /* Override IEs if they were from a beacon before */ - if (old == rcu_access_pointer(found->pub.ies)) - rcu_assign_pointer(found->pub.ies, - tmp->pub.beacon_ies); - - /* Assign beacon IEs to all sub entries */ - list_for_each_entry(bss, &found->hidden_list, - hidden_list) { - const struct cfg80211_bss_ies *ies; - - ies = rcu_access_pointer(bss->pub.beacon_ies); - WARN_ON(ies != old); - - rcu_assign_pointer(bss->pub.beacon_ies, - tmp->pub.beacon_ies); - } - - if (old) - kfree_rcu((struct cfg80211_bss_ies *)old, - rcu_head); - } - - found->pub.beacon_interval = tmp->pub.beacon_interval; - /* - * don't update the signal if beacon was heard on - * adjacent channel. - */ - if (signal_valid) - found->pub.signal = tmp->pub.signal; - found->pub.capability = tmp->pub.capability; - found->ts = tmp->ts; - found->ts_boottime = tmp->ts_boottime; - found->parent_tsf = tmp->parent_tsf; - found->pub.chains = tmp->pub.chains; - memcpy(found->pub.chain_signal, tmp->pub.chain_signal, - IEEE80211_MAX_CHAINS); - ether_addr_copy(found->parent_bssid, tmp->parent_bssid); - found->pub.max_bssid_indicator = tmp->pub.max_bssid_indicator; - found->pub.bssid_index = tmp->pub.bssid_index; + if (!cfg80211_update_known_bss(rdev, found, tmp, signal_valid)) + goto drop; } else { struct cfg80211_internal_bss *new; struct cfg80211_internal_bss *hidden; @@ -1368,6 +1375,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, struct cfg80211_internal_bss tmp = {}, *res; int bss_type; bool signal_valid; + unsigned long ts; if (WARN_ON(!wiphy)) return NULL; @@ -1390,8 +1398,11 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, tmp.ts_boottime = data->boottime_ns; if (non_tx_data) { tmp.pub.transmitted_bss = non_tx_data->tx_bss; + ts = bss_from_pub(non_tx_data->tx_bss)->ts; tmp.pub.bssid_index = non_tx_data->bssid_index; tmp.pub.max_bssid_indicator = non_tx_data->max_bssid_indicator; + } else { + ts = jiffies; } /* @@ -1425,8 +1436,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; - res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, - jiffies); + res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, ts); if (!res) return NULL; @@ -1440,7 +1450,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, regulatory_hint_found_beacon(wiphy, channel, gfp); } - if (non_tx_data && non_tx_data->tx_bss) { + if (non_tx_data) { /* this is a nontransmitting bss, we need to add it to * transmitting bss' list if it is not there */ @@ -1659,6 +1669,8 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, res = cfg80211_inform_single_bss_data(wiphy, data, ftype, bssid, tsf, capability, beacon_interval, ie, ielen, NULL, gfp); + if (!res) + return NULL; non_tx_data.tx_bss = res; cfg80211_parse_mbssid_data(wiphy, data, ftype, bssid, tsf, beacon_interval, ie, ielen, &non_tx_data, @@ -1776,7 +1788,6 @@ static struct cfg80211_bss * cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, struct cfg80211_inform_bss *data, struct ieee80211_mgmt *mgmt, size_t len, - struct cfg80211_non_tx_bss *non_tx_data, gfp_t gfp) { struct cfg80211_internal_bss tmp = {}, *res; @@ -1835,11 +1846,6 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, tmp.pub.chains = data->chains; memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS); ether_addr_copy(tmp.parent_bssid, data->parent_bssid); - if (non_tx_data) { - tmp.pub.transmitted_bss = non_tx_data->tx_bss; - tmp.pub.bssid_index = non_tx_data->bssid_index; - tmp.pub.max_bssid_indicator = non_tx_data->max_bssid_indicator; - } signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; @@ -1877,7 +1883,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, struct cfg80211_non_tx_bss non_tx_data; res = cfg80211_inform_single_bss_frame_data(wiphy, data, mgmt, - len, NULL, gfp); + len, gfp); if (!res || !wiphy->support_mbssid || !cfg80211_find_ie(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) return res; @@ -1995,6 +2001,85 @@ void cfg80211_bss_iter(struct wiphy *wiphy, } EXPORT_SYMBOL(cfg80211_bss_iter); +void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev, + struct ieee80211_channel *chan) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct cfg80211_internal_bss *cbss = wdev->current_bss; + struct cfg80211_internal_bss *new = NULL; + struct cfg80211_internal_bss *bss; + struct cfg80211_bss *nontrans_bss; + struct cfg80211_bss *tmp; + + spin_lock_bh(&rdev->bss_lock); + + if (WARN_ON(cbss->pub.channel == chan)) + goto done; + + /* use transmitting bss */ + if (cbss->pub.transmitted_bss) + cbss = container_of(cbss->pub.transmitted_bss, + struct cfg80211_internal_bss, + pub); + + cbss->pub.channel = chan; + + list_for_each_entry(bss, &rdev->bss_list, list) { + if (!cfg80211_bss_type_match(bss->pub.capability, + bss->pub.channel->band, + wdev->conn_bss_type)) + continue; + + if (bss == cbss) + continue; + + if (!cmp_bss(&bss->pub, &cbss->pub, BSS_CMP_REGULAR)) { + new = bss; + break; + } + } + + if (new) { + /* to save time, update IEs for transmitting bss only */ + if (cfg80211_update_known_bss(rdev, cbss, new, false)) { + new->pub.proberesp_ies = NULL; + new->pub.beacon_ies = NULL; + } + + list_for_each_entry_safe(nontrans_bss, tmp, + &new->pub.nontrans_list, + nontrans_list) { + bss = container_of(nontrans_bss, + struct cfg80211_internal_bss, pub); + if (__cfg80211_unlink_bss(rdev, bss)) + rdev->bss_generation++; + } + + WARN_ON(atomic_read(&new->hold)); + if (!WARN_ON(!__cfg80211_unlink_bss(rdev, new))) + rdev->bss_generation++; + } + + rb_erase(&cbss->rbn, &rdev->bss_tree); + rb_insert_bss(rdev, cbss); + rdev->bss_generation++; + + list_for_each_entry_safe(nontrans_bss, tmp, + &cbss->pub.nontrans_list, + nontrans_list) { + bss = container_of(nontrans_bss, + struct cfg80211_internal_bss, pub); + bss->pub.channel = chan; + rb_erase(&bss->rbn, &rdev->bss_tree); + rb_insert_bss(rdev, bss); + rdev->bss_generation++; + } + +done: + spin_unlock_bh(&rdev->bss_lock); +} + #ifdef CONFIG_CFG80211_WEXT static struct cfg80211_registered_device * cfg80211_get_dev_from_ifindex(struct net *net, int ifindex) diff --git a/net/wireless/util.c b/net/wireless/util.c index 1c39d6a2e850..d0e35b7b9e35 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1697,7 +1697,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { num_interfaces += params->iftype_num[iftype]; if (params->iftype_num[iftype] > 0 && - !(wiphy->software_iftypes & BIT(iftype))) + !cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) used_iftypes |= BIT(iftype); } @@ -1719,7 +1719,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, return -ENOMEM; for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { - if (wiphy->software_iftypes & BIT(iftype)) + if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) continue; for (j = 0; j < c->n_limits; j++) { all_iftypes |= limits[j].types; @@ -2072,3 +2072,26 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, return max_vht_nss; } EXPORT_SYMBOL(ieee80211_get_vht_max_nss); + +bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, + bool is_4addr, u8 check_swif) + +{ + bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN; + + switch (check_swif) { + case 0: + if (is_vlan && is_4addr) + return wiphy->flags & WIPHY_FLAG_4ADDR_AP; + return wiphy->interface_modes & BIT(iftype); + case 1: + if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan) + return wiphy->flags & WIPHY_FLAG_4ADDR_AP; + return wiphy->software_iftypes & BIT(iftype); + default: + break; + } + + return false; +} +EXPORT_SYMBOL(cfg80211_iftype_allowed); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 32c364d3bfb3..4d422447aadc 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -85,7 +85,7 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) if (dlen < len) len = dlen; - frag->page_offset = 0; + skb_frag_off_set(frag, 0); skb_frag_size_set(frag, len); memcpy(skb_frag_address(frag), scratch, len); |