diff options
Diffstat (limited to 'net')
219 files changed, 8651 insertions, 3300 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 175273f..44ebd5c 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -169,6 +169,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; + vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 8f025af..ad2ac3c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -493,48 +493,10 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change) } } -static int vlan_calculate_locking_subclass(struct net_device *real_dev) -{ - int subclass = 0; - - while (is_vlan_dev(real_dev)) { - subclass++; - real_dev = vlan_dev_priv(real_dev)->real_dev; - } - - return subclass; -} - -static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from) -{ - int err = 0, subclass; - - subclass = vlan_calculate_locking_subclass(to); - - spin_lock_nested(&to->addr_list_lock, subclass); - err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); - if (!err) - __dev_set_rx_mode(to); - spin_unlock(&to->addr_list_lock); -} - -static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from) -{ - int err = 0, subclass; - - subclass = vlan_calculate_locking_subclass(to); - - spin_lock_nested(&to->addr_list_lock, subclass); - err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); - if (!err) - __dev_set_rx_mode(to); - spin_unlock(&to->addr_list_lock); -} - static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) { - vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); - vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); + dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); + dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } /* @@ -562,6 +524,11 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass); } +static int vlan_dev_get_lock_subclass(struct net_device *dev) +{ + return vlan_dev_priv(dev)->nest_level; +} + static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .rebuild = vlan_dev_rebuild_header, @@ -597,7 +564,6 @@ static const struct net_device_ops vlan_netdev_ops; static int vlan_dev_init(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - int subclass = 0; netif_carrier_off(dev); @@ -646,8 +612,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - subclass = vlan_calculate_locking_subclass(dev); - vlan_dev_set_lockdep_class(dev, subclass); + vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev)); vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan_dev_priv(dev)->vlan_pcpu_stats) @@ -678,9 +643,9 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev, struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; netdev_features_t old_features = features; - features &= real_dev->vlan_features; + features = netdev_intersect_features(features, real_dev->vlan_features); features |= NETIF_F_RXCSUM; - features &= real_dev->features; + features = netdev_intersect_features(features, real_dev->features); features |= old_features & NETIF_F_SOFT_FEATURES; features |= NETIF_F_LLTX; @@ -817,6 +782,7 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, + .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, }; void vlan_setup(struct net_device *dev) diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 786ee2f..01a1082 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1669,7 +1669,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr goto out; } - if (sk->sk_no_check == 1) + if (sk->sk_no_check_tx) ddp->deh_sum = 0; else ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp)); diff --git a/net/atm/svc.c b/net/atm/svc.c index 1281049..d8e5d0c2 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -263,17 +263,11 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, goto out; } } -/* - * Not supported yet - * - * #ifndef CONFIG_SINGLE_SIGITF - */ + vcc->qos.txtp.max_pcr = SELECT_TOP_PCR(vcc->qos.txtp); vcc->qos.txtp.pcr = 0; vcc->qos.txtp.min_pcr = 0; -/* - * #endif - */ + error = vcc_connect(sock, vcc->itf, vcc->vpi, vcc->vci); if (!error) sock->state = SS_CONNECTED; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index b3bd4ec..f04224c 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1545,6 +1545,8 @@ out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) batadv_orig_node_free_ref(orig_neigh_node); out: + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); if (router) batadv_neigh_node_free_ref(router); if (router_router) diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index b758881..a12e25e 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -245,6 +245,7 @@ static int batadv_algorithms_open(struct inode *inode, struct file *file) static int batadv_originators_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_orig_seq_print_text, net_dev); } @@ -258,18 +259,21 @@ static int batadv_originators_hardif_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_orig_hardif_seq_print_text, net_dev); } static int batadv_gateways_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_gw_client_seq_print_text, net_dev); } static int batadv_transtable_global_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_tt_global_seq_print_text, net_dev); } @@ -277,6 +281,7 @@ static int batadv_transtable_global_open(struct inode *inode, struct file *file) static int batadv_bla_claim_table_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_bla_claim_table_seq_print_text, net_dev); } @@ -285,6 +290,7 @@ static int batadv_bla_backbone_table_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_bla_backbone_table_seq_print_text, net_dev); } @@ -300,6 +306,7 @@ static int batadv_bla_backbone_table_open(struct inode *inode, static int batadv_dat_cache_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_dat_cache_seq_print_text, net_dev); } #endif @@ -307,6 +314,7 @@ static int batadv_dat_cache_open(struct inode *inode, struct file *file) static int batadv_transtable_local_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_tt_local_seq_print_text, net_dev); } @@ -319,6 +327,7 @@ struct batadv_debuginfo { static int batadv_nc_nodes_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_nc_nodes_seq_print_text, net_dev); } #endif @@ -333,7 +342,7 @@ struct batadv_debuginfo batadv_debuginfo_##_name = { \ .llseek = seq_lseek, \ .release = single_release, \ } \ -}; +} /* the following attributes are general and therefore they will be directly * placed in the BATADV_DEBUGFS_SUBDIR subdirectory of debugfs @@ -395,7 +404,7 @@ struct batadv_debuginfo batadv_hardif_debuginfo_##_name = { \ .llseek = seq_lseek, \ .release = single_release, \ }, \ -}; +} static BATADV_HARDIF_DEBUGINFO(originators, S_IRUGO, batadv_originators_hardif_open); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b25fd64..dcd99b2 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -662,6 +662,7 @@ static void batadv_dat_tvlv_container_update(struct batadv_priv *bat_priv) void batadv_dat_status_update(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); + batadv_dat_tvlv_container_update(bat_priv); } @@ -940,8 +941,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, * additional DAT answer may trigger kernel warnings about * a packet coming from the wrong port. */ - if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, - BATADV_NO_FLAGS)) { + if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, vid)) { ret = true; goto out; } diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index bcc4bea..f14e54a 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -418,12 +418,13 @@ bool batadv_frag_send_packet(struct sk_buff *skb, struct batadv_neigh_node *neigh_node) { struct batadv_priv *bat_priv; - struct batadv_hard_iface *primary_if; + struct batadv_hard_iface *primary_if = NULL; struct batadv_frag_packet frag_header; struct sk_buff *skb_fragment; unsigned mtu = neigh_node->if_incoming->net_dev->mtu; unsigned header_size = sizeof(frag_header); unsigned max_fragment_size, max_packet_size; + bool ret = false; /* To avoid merge and refragmentation at next-hops we never send * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE @@ -483,7 +484,11 @@ bool batadv_frag_send_packet(struct sk_buff *skb, skb->len + ETH_HLEN); batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); - return true; + ret = true; + out_err: - return false; + if (primary_if) + batadv_hardif_free_ref(primary_if); + + return ret; } diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index c835e13..90cff58 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -42,8 +42,10 @@ static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node) { - if (atomic_dec_and_test(&gw_node->refcount)) + if (atomic_dec_and_test(&gw_node->refcount)) { + batadv_orig_node_free_ref(gw_node->orig_node); kfree_rcu(gw_node, rcu); + } } static struct batadv_gw_node * @@ -406,9 +408,14 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, if (gateway->bandwidth_down == 0) return; + if (!atomic_inc_not_zero(&orig_node->refcount)) + return; + gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC); - if (!gw_node) + if (!gw_node) { + batadv_orig_node_free_ref(orig_node); return; + } INIT_HLIST_NODE(&gw_node->list); gw_node->orig_node = orig_node; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index b851cc5..fbda6b5 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -83,7 +83,7 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) return true; /* no more parents..stop recursion */ - if (net_dev->iflink == net_dev->ifindex) + if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex) return false; /* recurse over the parent device */ diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 770dc89..118b990 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2014.2.0" +#define BATADV_SOURCE_VERSION "2014.3.0" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index a9546fe..40a2fc4 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -86,6 +86,7 @@ static void batadv_nc_tvlv_container_update(struct batadv_priv *bat_priv) void batadv_nc_status_update(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); + batadv_nc_tvlv_container_update(bat_priv); } diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index ffd9dfb..6a48451 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -501,12 +501,17 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node, static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) { struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_neigh_node *router; orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + /* this is the last reference to this object */ + router = rcu_dereference_protected(orig_ifinfo->router, true); + if (router) + batadv_neigh_node_free_ref_now(router); kfree(orig_ifinfo); } @@ -702,6 +707,47 @@ free_orig_node: } /** + * batadv_purge_neigh_ifinfo - purge obsolete ifinfo entries from neighbor + * @bat_priv: the bat priv with all the soft interface information + * @neigh: orig node which is to be checked + */ +static void +batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv, + struct batadv_neigh_node *neigh) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo; + struct batadv_hard_iface *if_outgoing; + struct hlist_node *node_tmp; + + spin_lock_bh(&neigh->ifinfo_lock); + + /* for all ifinfo objects for this neighinator */ + hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, + &neigh->ifinfo_list, list) { + if_outgoing = neigh_ifinfo->if_outgoing; + + /* always keep the default interface */ + if (if_outgoing == BATADV_IF_DEFAULT) + continue; + + /* don't purge if the interface is not (going) down */ + if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && + (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && + (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + continue; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "neighbor/ifinfo purge: neighbor %pM, iface: %s\n", + neigh->addr, if_outgoing->net_dev->name); + + hlist_del_rcu(&neigh_ifinfo->list); + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + } + + spin_unlock_bh(&neigh->ifinfo_lock); +} + +/** * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node which is to be checked @@ -800,6 +846,11 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, hlist_del_rcu(&neigh_node->list); batadv_neigh_node_free_ref(neigh_node); + } else { + /* only necessary if not the whole neighbor is to be + * deleted, but some interface has been removed. + */ + batadv_purge_neigh_ifinfo(bat_priv, neigh_node); } } @@ -857,7 +908,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, { struct batadv_neigh_node *best_neigh_node; struct batadv_hard_iface *hard_iface; - bool changed; + bool changed_ifinfo, changed_neigh; if (batadv_has_timed_out(orig_node->last_seen, 2 * BATADV_PURGE_TIMEOUT)) { @@ -867,10 +918,10 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, jiffies_to_msecs(orig_node->last_seen)); return true; } - changed = batadv_purge_orig_ifinfo(bat_priv, orig_node); - changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node); + changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node); + changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node); - if (!changed) + if (!changed_ifinfo && !changed_neigh) return false; /* first for NULL ... */ @@ -1028,7 +1079,8 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset) bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface); out: - batadv_hardif_free_ref(hard_iface); + if (hard_iface) + batadv_hardif_free_ref(hard_iface); return 0; } diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 1ebb0d9..fc47baa 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -29,12 +29,14 @@ static struct net_device *batadv_kobj_to_netdev(struct kobject *obj) { struct device *dev = container_of(obj->parent, struct device, kobj); + return to_net_dev(dev); } static struct batadv_priv *batadv_kobj_to_batpriv(struct kobject *obj) { struct net_device *net_dev = batadv_kobj_to_netdev(obj); + return netdev_priv(net_dev); } @@ -106,7 +108,7 @@ struct batadv_attribute batadv_attr_vlan_##_name = { \ .mode = _mode }, \ .show = _show, \ .store = _store, \ -}; +} /* Use this, if you have customized show and store functions */ #define BATADV_ATTR(_name, _mode, _show, _store) \ @@ -115,7 +117,7 @@ struct batadv_attribute batadv_attr_##_name = { \ .mode = _mode }, \ .show = _show, \ .store = _store, \ -}; +} #define BATADV_ATTR_SIF_STORE_BOOL(_name, _post_func) \ ssize_t batadv_store_##_name(struct kobject *kobj, \ @@ -124,6 +126,7 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ { \ struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ struct batadv_priv *bat_priv = netdev_priv(net_dev); \ + \ return __batadv_store_bool_attr(buff, count, _post_func, attr, \ &bat_priv->_name, net_dev); \ } @@ -133,6 +136,7 @@ ssize_t batadv_show_##_name(struct kobject *kobj, \ struct attribute *attr, char *buff) \ { \ struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); \ + \ return sprintf(buff, "%s\n", \ atomic_read(&bat_priv->_name) == 0 ? \ "disabled" : "enabled"); \ @@ -155,6 +159,7 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ { \ struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ struct batadv_priv *bat_priv = netdev_priv(net_dev); \ + \ return __batadv_store_uint_attr(buff, count, _min, _max, \ _post_func, attr, \ &bat_priv->_name, net_dev); \ @@ -165,6 +170,7 @@ ssize_t batadv_show_##_name(struct kobject *kobj, \ struct attribute *attr, char *buff) \ { \ struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); \ + \ return sprintf(buff, "%i\n", atomic_read(&bat_priv->_name)); \ } \ @@ -188,6 +194,7 @@ ssize_t batadv_store_vlan_##_name(struct kobject *kobj, \ size_t res = __batadv_store_bool_attr(buff, count, _post_func, \ attr, &vlan->_name, \ bat_priv->soft_iface); \ + \ batadv_softif_vlan_free_ref(vlan); \ return res; \ } @@ -202,6 +209,7 @@ ssize_t batadv_show_vlan_##_name(struct kobject *kobj, \ size_t res = sprintf(buff, "%s\n", \ atomic_read(&vlan->_name) == 0 ? \ "disabled" : "enabled"); \ + \ batadv_softif_vlan_free_ref(vlan); \ return res; \ } @@ -324,12 +332,14 @@ static ssize_t batadv_show_bat_algo(struct kobject *kobj, struct attribute *attr, char *buff) { struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name); } static void batadv_post_gw_reselect(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); + batadv_gw_reselect(bat_priv); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 095943c..8671bc7 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -28,6 +28,7 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include <net/bluetooth/l2cap.h> #include "smp.h" #include "a2mp.h" @@ -407,6 +408,8 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) conn->io_capability = hdev->io_capability; conn->remote_auth = 0xff; conn->key_type = 0xff; + conn->tx_power = HCI_TX_POWER_INVALID; + conn->max_tx_power = HCI_TX_POWER_INVALID; set_bit(HCI_CONN_POWER_SAVE, &conn->flags); conn->disc_timeout = HCI_DISCONN_TIMEOUT; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index d31f144..0a43cce 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -34,6 +34,7 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include <net/bluetooth/l2cap.h> #include "smp.h" @@ -579,6 +580,62 @@ static int sniff_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(sniff_max_interval_fops, sniff_max_interval_get, sniff_max_interval_set, "%llu\n"); +static int conn_info_min_age_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + if (val == 0 || val > hdev->conn_info_max_age) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->conn_info_min_age = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int conn_info_min_age_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->conn_info_min_age; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(conn_info_min_age_fops, conn_info_min_age_get, + conn_info_min_age_set, "%llu\n"); + +static int conn_info_max_age_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + if (val == 0 || val < hdev->conn_info_min_age) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->conn_info_max_age = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int conn_info_max_age_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->conn_info_max_age; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(conn_info_max_age_fops, conn_info_max_age_get, + conn_info_max_age_set, "%llu\n"); + static int identity_show(struct seq_file *f, void *p) { struct hci_dev *hdev = f->private; @@ -1754,6 +1811,11 @@ static int __hci_init(struct hci_dev *hdev) &blacklist_fops); debugfs_create_file("uuids", 0444, hdev->debugfs, hdev, &uuids_fops); + debugfs_create_file("conn_info_min_age", 0644, hdev->debugfs, hdev, + &conn_info_min_age_fops); + debugfs_create_file("conn_info_max_age", 0644, hdev->debugfs, hdev, + &conn_info_max_age_fops); + if (lmp_bredr_capable(hdev)) { debugfs_create_file("inquiry_cache", 0444, hdev->debugfs, hdev, &inquiry_cache_fops); @@ -3789,6 +3851,8 @@ struct hci_dev *hci_alloc_dev(void) hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT; + hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE; + hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE; mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ca19fd4..3454807 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1245,6 +1245,59 @@ static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev, amp_write_rem_assoc_continue(hdev, rp->phy_handle); } +static void hci_cc_read_rssi(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_rp_read_rssi *rp = (void *) skb->data; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (rp->status) + return; + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); + if (conn) + conn->rssi = rp->rssi; + + hci_dev_unlock(hdev); +} + +static void hci_cc_read_tx_power(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_cp_read_tx_power *sent; + struct hci_rp_read_tx_power *rp = (void *) skb->data; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (rp->status) + return; + + sent = hci_sent_cmd_data(hdev, HCI_OP_READ_TX_POWER); + if (!sent) + return; + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); + if (!conn) + goto unlock; + + switch (sent->type) { + case 0x00: + conn->tx_power = rp->tx_power; + break; + case 0x01: + conn->max_tx_power = rp->tx_power; + break; + } + +unlock: + hci_dev_unlock(hdev); +} + static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -2637,6 +2690,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_write_remote_amp_assoc(hdev, skb); break; + case HCI_OP_READ_RSSI: + hci_cc_read_rssi(hdev, skb); + break; + + case HCI_OP_READ_TX_POWER: + hci_cc_read_tx_power(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); break; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a1e5bb7..dc4d301 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7519,9 +7519,9 @@ int __init l2cap_init(void) l2cap_debugfs = debugfs_create_file("l2cap", 0444, bt_debugfs, NULL, &l2cap_debugfs_fops); - debugfs_create_u16("l2cap_le_max_credits", 0466, bt_debugfs, + debugfs_create_u16("l2cap_le_max_credits", 0644, bt_debugfs, &le_max_credits); - debugfs_create_u16("l2cap_le_default_mps", 0466, bt_debugfs, + debugfs_create_u16("l2cap_le_default_mps", 0644, bt_debugfs, &le_default_mps); bt_6lowpan_init(); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 54abbce..5e9c21a 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -29,12 +29,13 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include <net/bluetooth/l2cap.h> #include <net/bluetooth/mgmt.h> #include "smp.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 5 +#define MGMT_REVISION 6 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -83,6 +84,7 @@ static const u16 mgmt_commands[] = { MGMT_OP_SET_DEBUG_KEYS, MGMT_OP_SET_PRIVACY, MGMT_OP_LOAD_IRKS, + MGMT_OP_GET_CONN_INFO, }; static const u16 mgmt_events[] = { @@ -4532,7 +4534,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, for (i = 0; i < key_count; i++) { struct mgmt_ltk_info *key = &cp->keys[i]; - u8 type, addr_type; + u8 type, addr_type, authenticated; if (key->addr.type == BDADDR_LE_PUBLIC) addr_type = ADDR_LE_DEV_PUBLIC; @@ -4544,8 +4546,13 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, else type = HCI_SMP_LTK_SLAVE; + if (key->type == MGMT_LTK_UNAUTHENTICATED) + authenticated = 0x00; + else + authenticated = 0x01; + hci_add_ltk(hdev, &key->addr.bdaddr, addr_type, type, - key->type, key->val, key->enc_size, key->ediv, + authenticated, key->val, key->enc_size, key->ediv, key->rand); } @@ -4557,6 +4564,218 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, return err; } +struct cmd_conn_lookup { + struct hci_conn *conn; + bool valid_tx_power; + u8 mgmt_status; +}; + +static void get_conn_info_complete(struct pending_cmd *cmd, void *data) +{ + struct cmd_conn_lookup *match = data; + struct mgmt_cp_get_conn_info *cp; + struct mgmt_rp_get_conn_info rp; + struct hci_conn *conn = cmd->user_data; + + if (conn != match->conn) + return; + + cp = (struct mgmt_cp_get_conn_info *) cmd->param; + + memset(&rp, 0, sizeof(rp)); + bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr); + rp.addr.type = cp->addr.type; + + if (!match->mgmt_status) { + rp.rssi = conn->rssi; + + if (match->valid_tx_power) { + rp.tx_power = conn->tx_power; + rp.max_tx_power = conn->max_tx_power; + } else { + rp.tx_power = HCI_TX_POWER_INVALID; + rp.max_tx_power = HCI_TX_POWER_INVALID; + } + } + + cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO, + match->mgmt_status, &rp, sizeof(rp)); + + hci_conn_drop(conn); + + mgmt_pending_remove(cmd); +} + +static void conn_info_refresh_complete(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_read_rssi *cp; + struct hci_conn *conn; + struct cmd_conn_lookup match; + u16 handle; + + BT_DBG("status 0x%02x", status); + + hci_dev_lock(hdev); + + /* TX power data is valid in case request completed successfully, + * otherwise we assume it's not valid. At the moment we assume that + * either both or none of current and max values are valid to keep code + * simple. + */ + match.valid_tx_power = !status; + + /* Commands sent in request are either Read RSSI or Read Transmit Power + * Level so we check which one was last sent to retrieve connection + * handle. Both commands have handle as first parameter so it's safe to + * cast data on the same command struct. + * + * First command sent is always Read RSSI and we fail only if it fails. + * In other case we simply override error to indicate success as we + * already remembered if TX power value is actually valid. + */ + cp = hci_sent_cmd_data(hdev, HCI_OP_READ_RSSI); + if (!cp) { + cp = hci_sent_cmd_data(hdev, HCI_OP_READ_TX_POWER); + status = 0; + } + + if (!cp) { + BT_ERR("invalid sent_cmd in response"); + goto unlock; + } + + handle = __le16_to_cpu(cp->handle); + conn = hci_conn_hash_lookup_handle(hdev, handle); + if (!conn) { + BT_ERR("unknown handle (%d) in response", handle); + goto unlock; + } + + match.conn = conn; + match.mgmt_status = mgmt_status(status); + + /* Cache refresh is complete, now reply for mgmt request for given + * connection only. + */ + mgmt_pending_foreach(MGMT_OP_GET_CONN_INFO, hdev, + get_conn_info_complete, &match); + +unlock: + hci_dev_unlock(hdev); +} + +static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data, + u16 len) +{ + struct mgmt_cp_get_conn_info *cp = data; + struct mgmt_rp_get_conn_info rp; + struct hci_conn *conn; + unsigned long conn_info_age; + int err = 0; + + BT_DBG("%s", hdev->name); + + memset(&rp, 0, sizeof(rp)); + bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr); + rp.addr.type = cp->addr.type; + + if (!bdaddr_type_is_valid(cp->addr.type)) + return cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, + MGMT_STATUS_INVALID_PARAMS, + &rp, sizeof(rp)); + + hci_dev_lock(hdev); + + if (!hdev_is_powered(hdev)) { + err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, + MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp)); + goto unlock; + } + + if (cp->addr.type == BDADDR_BREDR) + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, + &cp->addr.bdaddr); + else + conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr); + + if (!conn || conn->state != BT_CONNECTED) { + err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, + MGMT_STATUS_NOT_CONNECTED, &rp, sizeof(rp)); + goto unlock; + } + + /* To avoid client trying to guess when to poll again for information we + * calculate conn info age as random value between min/max set in hdev. + */ + conn_info_age = hdev->conn_info_min_age + + prandom_u32_max(hdev->conn_info_max_age - + hdev->conn_info_min_age); + + /* Query controller to refresh cached values if they are too old or were + * never read. + */ + if (time_after(jiffies, conn->conn_info_timestamp + + msecs_to_jiffies(conn_info_age)) || + !conn->conn_info_timestamp) { + struct hci_request req; + struct hci_cp_read_tx_power req_txp_cp; + struct hci_cp_read_rssi req_rssi_cp; + struct pending_cmd *cmd; + + hci_req_init(&req, hdev); + req_rssi_cp.handle = cpu_to_le16(conn->handle); + hci_req_add(&req, HCI_OP_READ_RSSI, sizeof(req_rssi_cp), + &req_rssi_cp); + + /* For LE links TX power does not change thus we don't need to + * query for it once value is known. + */ + if (!bdaddr_type_is_le(cp->addr.type) || + conn->tx_power == HCI_TX_POWER_INVALID) { + req_txp_cp.handle = cpu_to_le16(conn->handle); + req_txp_cp.type = 0x00; + hci_req_add(&req, HCI_OP_READ_TX_POWER, + sizeof(req_txp_cp), &req_txp_cp); + } + + /* Max TX power needs to be read only once per connection */ + if (conn->max_tx_power == HCI_TX_POWER_INVALID) { + req_txp_cp.handle = cpu_to_le16(conn->handle); + req_txp_cp.type = 0x01; + hci_req_add(&req, HCI_OP_READ_TX_POWER, + sizeof(req_txp_cp), &req_txp_cp); + } + + err = hci_req_run(&req, conn_info_refresh_complete); + if (err < 0) + goto unlock; + + cmd = mgmt_pending_add(sk, MGMT_OP_GET_CONN_INFO, hdev, + data, len); + if (!cmd) { + err = -ENOMEM; + goto unlock; + } + + hci_conn_hold(conn); + cmd->user_data = conn; + + conn->conn_info_timestamp = jiffies; + } else { + /* Cache is valid, just reply with values cached in hci_conn */ + rp.rssi = conn->rssi; + rp.tx_power = conn->tx_power; + rp.max_tx_power = conn->max_tx_power; + + err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, + MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); + } + +unlock: + hci_dev_unlock(hdev); + return err; +} + static const struct mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len); @@ -4612,6 +4831,7 @@ static const struct mgmt_handler { { set_debug_keys, false, MGMT_SETTING_SIZE }, { set_privacy, false, MGMT_SET_PRIVACY_SIZE }, { load_irks, true, MGMT_LOAD_IRKS_SIZE }, + { get_conn_info, false, MGMT_GET_CONN_INFO_SIZE }, }; @@ -5007,6 +5227,14 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL); } +static u8 mgmt_ltk_type(struct smp_ltk *ltk) +{ + if (ltk->authenticated) + return MGMT_LTK_AUTHENTICATED; + + return MGMT_LTK_UNAUTHENTICATED; +} + void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) { struct mgmt_ev_new_long_term_key ev; @@ -5032,7 +5260,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) bacpy(&ev.key.addr.bdaddr, &key->bdaddr); ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); - ev.key.type = key->authenticated; + ev.key.type = mgmt_ltk_type(key); ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; ev.key.rand = key->rand; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index cf620260..754b6fe 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -307,7 +307,7 @@ struct rfcomm_dlc *rfcomm_dlc_alloc(gfp_t prio) setup_timer(&d->timer, rfcomm_dlc_timeout, (unsigned long)d); skb_queue_head_init(&d->tx_queue); - spin_lock_init(&d->lock); + mutex_init(&d->lock); atomic_set(&d->refcnt, 1); rfcomm_dlc_clear_state(d); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 403ec09..8e385a0 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -70,7 +70,7 @@ struct rfcomm_dev { }; static LIST_HEAD(rfcomm_dev_list); -static DEFINE_SPINLOCK(rfcomm_dev_lock); +static DEFINE_MUTEX(rfcomm_dev_lock); static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb); static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err); @@ -96,9 +96,9 @@ static void rfcomm_dev_destruct(struct tty_port *port) if (dev->tty_dev) tty_unregister_device(rfcomm_tty_driver, dev->id); - spin_lock(&rfcomm_dev_lock); + mutex_lock(&rfcomm_dev_lock); list_del(&dev->list); - spin_unlock(&rfcomm_dev_lock); + mutex_unlock(&rfcomm_dev_lock); kfree(dev); @@ -161,14 +161,14 @@ static struct rfcomm_dev *rfcomm_dev_get(int id) { struct rfcomm_dev *dev; - spin_lock(&rfcomm_dev_lock); + mutex_lock(&rfcomm_dev_lock); dev = __rfcomm_dev_lookup(id); if (dev && !tty_port_get(&dev->port)) dev = NULL; - spin_unlock(&rfcomm_dev_lock); + mutex_unlock(&rfcomm_dev_lock); return dev; } @@ -224,7 +224,7 @@ static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req, if (!dev) return ERR_PTR(-ENOMEM); - spin_lock(&rfcomm_dev_lock); + mutex_lock(&rfcomm_dev_lock); if (req->dev_id < 0) { dev->id = 0; @@ -305,11 +305,11 @@ static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req, holds reference to this module. */ __module_get(THIS_MODULE); - spin_unlock(&rfcomm_dev_lock); + mutex_unlock(&rfcomm_dev_lock); return dev; out: - spin_unlock(&rfcomm_dev_lock); + mutex_unlock(&rfcomm_dev_lock); kfree(dev); return ERR_PTR(err); } @@ -524,7 +524,7 @@ static int rfcomm_get_dev_list(void __user *arg) di = dl->dev_info; - spin_lock(&rfcomm_dev_lock); + mutex_lock(&rfcomm_dev_lock); list_for_each_entry(dev, &rfcomm_dev_list, list) { if (!tty_port_get(&dev->port)) @@ -540,7 +540,7 @@ static int rfcomm_get_dev_list(void __user *arg) break; } - spin_unlock(&rfcomm_dev_lock); + mutex_unlock(&rfcomm_dev_lock); dl->dev_num = n; size = sizeof(*dl) + n * sizeof(*di); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index dfb4e11..4f9662d 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -35,6 +35,33 @@ #define AUTH_REQ_MASK 0x07 +#define SMP_FLAG_TK_VALID 1 +#define SMP_FLAG_CFM_PENDING 2 +#define SMP_FLAG_MITM_AUTH 3 +#define SMP_FLAG_COMPLETE 4 +#define SMP_FLAG_INITIATOR 5 + +struct smp_chan { + struct l2cap_conn *conn; + u8 preq[7]; /* SMP Pairing Request */ + u8 prsp[7]; /* SMP Pairing Response */ + u8 prnd[16]; /* SMP Pairing Random (local) */ + u8 rrnd[16]; /* SMP Pairing Random (remote) */ + u8 pcnf[16]; /* SMP Pairing Confirm */ + u8 tk[16]; /* SMP Temporary Key */ + u8 enc_key_size; + u8 remote_key_dist; + bdaddr_t id_addr; + u8 id_addr_type; + u8 irk[16]; + struct smp_csrk *csrk; + struct smp_csrk *slave_csrk; + struct smp_ltk *ltk; + struct smp_ltk *slave_ltk; + struct smp_irk *remote_irk; + unsigned long flags; +}; + static inline void swap128(const u8 src[16], u8 dst[16]) { int i; @@ -369,7 +396,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, /* Initialize key for JUST WORKS */ memset(smp->tk, 0, sizeof(smp->tk)); - clear_bit(SMP_FLAG_TK_VALID, &smp->smp_flags); + clear_bit(SMP_FLAG_TK_VALID, &smp->flags); BT_DBG("tk_request: auth:%d lcl:%d rem:%d", auth, local_io, remote_io); @@ -388,19 +415,18 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, method = JUST_WORKS; /* Don't confirm locally initiated pairing attempts */ - if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR, - &smp->smp_flags)) + if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR, &smp->flags)) method = JUST_WORKS; /* If Just Works, Continue with Zero TK */ if (method == JUST_WORKS) { - set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags); + set_bit(SMP_FLAG_TK_VALID, &smp->flags); return 0; } /* Not Just Works/Confirm results in MITM Authentication */ if (method != JUST_CFM) - set_bit(SMP_FLAG_MITM_AUTH, &smp->smp_flags); + set_bit(SMP_FLAG_MITM_AUTH, &smp->flags); /* If both devices have Keyoard-Display I/O, the master * Confirms and the slave Enters the passkey. @@ -419,7 +445,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, passkey %= 1000000; put_unaligned_le32(passkey, smp->tk); BT_DBG("PassKey: %d", passkey); - set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags); + set_bit(SMP_FLAG_TK_VALID, &smp->flags); } hci_dev_lock(hcon->hdev); @@ -441,15 +467,13 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, return ret; } -static void confirm_work(struct work_struct *work) +static u8 smp_confirm(struct smp_chan *smp) { - struct smp_chan *smp = container_of(work, struct smp_chan, confirm); struct l2cap_conn *conn = smp->conn; struct hci_dev *hdev = conn->hcon->hdev; struct crypto_blkcipher *tfm = hdev->tfm_aes; struct smp_cmd_pairing_confirm cp; int ret; - u8 reason; BT_DBG("conn %p", conn); @@ -463,35 +487,27 @@ static void confirm_work(struct work_struct *work) hci_dev_unlock(hdev); - if (ret) { - reason = SMP_UNSPECIFIED; - goto error; - } + if (ret) + return SMP_UNSPECIFIED; - clear_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags); + clear_bit(SMP_FLAG_CFM_PENDING, &smp->flags); smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); - return; - -error: - smp_failure(conn, reason); + return 0; } -static void random_work(struct work_struct *work) +static u8 smp_random(struct smp_chan *smp) { - struct smp_chan *smp = container_of(work, struct smp_chan, random); struct l2cap_conn *conn = smp->conn; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; struct crypto_blkcipher *tfm = hdev->tfm_aes; - u8 reason, confirm[16]; + u8 confirm[16]; int ret; - if (IS_ERR_OR_NULL(tfm)) { - reason = SMP_UNSPECIFIED; - goto error; - } + if (IS_ERR_OR_NULL(tfm)) + return SMP_UNSPECIFIED; BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); @@ -504,15 +520,12 @@ static void random_work(struct work_struct *work) hci_dev_unlock(hdev); - if (ret) { - reason = SMP_UNSPECIFIED; - goto error; - } + if (ret) + return SMP_UNSPECIFIED; if (memcmp(smp->pcnf, confirm, sizeof(smp->pcnf)) != 0) { BT_ERR("Pairing failed (confirmation values mismatch)"); - reason = SMP_CONFIRM_FAILED; - goto error; + return SMP_CONFIRM_FAILED; } if (hcon->out) { @@ -525,10 +538,8 @@ static void random_work(struct work_struct *work) memset(stk + smp->enc_key_size, 0, SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size); - if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags)) { - reason = SMP_UNSPECIFIED; - goto error; - } + if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags)) + return SMP_UNSPECIFIED; hci_le_start_enc(hcon, ediv, rand, stk); hcon->enc_key_size = smp->enc_key_size; @@ -550,10 +561,7 @@ static void random_work(struct work_struct *work) ediv, rand); } - return; - -error: - smp_failure(conn, reason); + return 0; } static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) @@ -564,9 +572,6 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) if (!smp) return NULL; - INIT_WORK(&smp->confirm, confirm_work); - INIT_WORK(&smp->random, random_work); - smp->conn = conn; conn->smp_chan = smp; conn->hcon->smp_conn = conn; @@ -583,7 +588,7 @@ void smp_chan_destroy(struct l2cap_conn *conn) BUG_ON(!smp); - complete = test_bit(SMP_FLAG_COMPLETE, &smp->smp_flags); + complete = test_bit(SMP_FLAG_COMPLETE, &smp->flags); mgmt_smp_complete(conn->hcon, complete); kfree(smp->csrk); @@ -634,7 +639,7 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) put_unaligned_le32(value, smp->tk); /* Fall Through */ case MGMT_OP_USER_CONFIRM_REPLY: - set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags); + set_bit(SMP_FLAG_TK_VALID, &smp->flags); break; case MGMT_OP_USER_PASSKEY_NEG_REPLY: case MGMT_OP_USER_CONFIRM_NEG_REPLY: @@ -646,8 +651,11 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) } /* If it is our turn to send Pairing Confirm, do so now */ - if (test_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags)) - queue_work(hcon->hdev->workqueue, &smp->confirm); + if (test_bit(SMP_FLAG_CFM_PENDING, &smp->flags)) { + u8 rsp = smp_confirm(smp); + if (rsp) + smp_failure(conn, rsp); + } return 0; } @@ -656,14 +664,13 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_pairing rsp, *req = (void *) skb->data; struct smp_chan *smp; - u8 key_size; - u8 auth = SMP_AUTH_NONE; + u8 key_size, auth; int ret; BT_DBG("conn %p", conn); if (skb->len < sizeof(*req)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; if (conn->hcon->link_mode & HCI_LM_MASTER) return SMP_CMD_NOTSUPP; @@ -681,8 +688,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) skb_pull(skb, sizeof(*req)); /* We didn't start the pairing, so match remote */ - if (req->auth_req & SMP_AUTH_BONDING) - auth = req->auth_req; + auth = req->auth_req; conn->hcon->pending_sec_level = authreq_to_seclevel(auth); @@ -704,7 +710,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (ret) return SMP_UNSPECIFIED; - clear_bit(SMP_FLAG_INITIATOR, &smp->smp_flags); + clear_bit(SMP_FLAG_INITIATOR, &smp->flags); return 0; } @@ -713,14 +719,13 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_pairing *req, *rsp = (void *) skb->data; struct smp_chan *smp = conn->smp_chan; - struct hci_dev *hdev = conn->hcon->hdev; u8 key_size, auth = SMP_AUTH_NONE; int ret; BT_DBG("conn %p", conn); if (skb->len < sizeof(*rsp)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; if (!(conn->hcon->link_mode & HCI_LM_MASTER)) return SMP_CMD_NOTSUPP; @@ -753,11 +758,11 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (ret) return SMP_UNSPECIFIED; - set_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags); + set_bit(SMP_FLAG_CFM_PENDING, &smp->flags); /* Can't compose response until we have been confirmed */ - if (test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags)) - queue_work(hdev->workqueue, &smp->confirm); + if (test_bit(SMP_FLAG_TK_VALID, &smp->flags)) + return smp_confirm(smp); return 0; } @@ -765,12 +770,11 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_chan *smp = conn->smp_chan; - struct hci_dev *hdev = conn->hcon->hdev; BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); if (skb->len < sizeof(smp->pcnf)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; memcpy(smp->pcnf, skb->data, sizeof(smp->pcnf)); skb_pull(skb, sizeof(smp->pcnf)); @@ -778,10 +782,10 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) if (conn->hcon->out) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); - else if (test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags)) - queue_work(hdev->workqueue, &smp->confirm); + else if (test_bit(SMP_FLAG_TK_VALID, &smp->flags)) + return smp_confirm(smp); else - set_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags); + set_bit(SMP_FLAG_CFM_PENDING, &smp->flags); return 0; } @@ -789,19 +793,16 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_chan *smp = conn->smp_chan; - struct hci_dev *hdev = conn->hcon->hdev; BT_DBG("conn %p", conn); if (skb->len < sizeof(smp->rrnd)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; memcpy(smp->rrnd, skb->data, sizeof(smp->rrnd)); skb_pull(skb, sizeof(smp->rrnd)); - queue_work(hdev->workqueue, &smp->random); - - return 0; + return smp_random(smp); } static u8 smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level) @@ -836,7 +837,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); if (skb->len < sizeof(*rp)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; if (!(conn->hcon->link_mode & HCI_LM_MASTER)) return SMP_CMD_NOTSUPP; @@ -861,7 +862,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - clear_bit(SMP_FLAG_INITIATOR, &smp->smp_flags); + clear_bit(SMP_FLAG_INITIATOR, &smp->flags); return 0; } @@ -928,7 +929,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); } - set_bit(SMP_FLAG_INITIATOR, &smp->smp_flags); + set_bit(SMP_FLAG_INITIATOR, &smp->flags); done: hcon->pending_sec_level = sec_level; @@ -944,7 +945,7 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); if (skb->len < sizeof(*rp)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; /* Ignore this PDU if it wasn't requested */ if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY)) @@ -969,7 +970,7 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); if (skb->len < sizeof(*rp)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; /* Ignore this PDU if it wasn't requested */ if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY)) @@ -1001,7 +1002,7 @@ static int smp_cmd_ident_info(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG(""); if (skb->len < sizeof(*info)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; /* Ignore this PDU if it wasn't requested */ if (!(smp->remote_key_dist & SMP_DIST_ID_KEY)) @@ -1025,7 +1026,7 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn, BT_DBG(""); if (skb->len < sizeof(*info)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; /* Ignore this PDU if it wasn't requested */ if (!(smp->remote_key_dist & SMP_DIST_ID_KEY)) @@ -1075,7 +1076,7 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); if (skb->len < sizeof(*rp)) - return SMP_UNSPECIFIED; + return SMP_INVALID_PARAMS; /* Ignore this PDU if it wasn't requested */ if (!(smp->remote_key_dist & SMP_DIST_SIGN)) @@ -1358,7 +1359,7 @@ int smp_distribute_keys(struct l2cap_conn *conn) clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags); cancel_delayed_work_sync(&conn->security_timer); - set_bit(SMP_FLAG_COMPLETE, &smp->smp_flags); + set_bit(SMP_FLAG_COMPLETE, &smp->flags); smp_notify_keys(conn); smp_chan_destroy(conn); diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index 1277147..5a8dc36 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -111,39 +111,11 @@ struct smp_cmd_security_req { #define SMP_CMD_NOTSUPP 0x07 #define SMP_UNSPECIFIED 0x08 #define SMP_REPEATED_ATTEMPTS 0x09 +#define SMP_INVALID_PARAMS 0x0a #define SMP_MIN_ENC_KEY_SIZE 7 #define SMP_MAX_ENC_KEY_SIZE 16 -#define SMP_FLAG_TK_VALID 1 -#define SMP_FLAG_CFM_PENDING 2 -#define SMP_FLAG_MITM_AUTH 3 -#define SMP_FLAG_COMPLETE 4 -#define SMP_FLAG_INITIATOR 5 - -struct smp_chan { - struct l2cap_conn *conn; - u8 preq[7]; /* SMP Pairing Request */ - u8 prsp[7]; /* SMP Pairing Response */ - u8 prnd[16]; /* SMP Pairing Random (local) */ - u8 rrnd[16]; /* SMP Pairing Random (remote) */ - u8 pcnf[16]; /* SMP Pairing Confirm */ - u8 tk[16]; /* SMP Temporary Key */ - u8 enc_key_size; - u8 remote_key_dist; - bdaddr_t id_addr; - u8 id_addr_type; - u8 irk[16]; - struct smp_csrk *csrk; - struct smp_csrk *slave_csrk; - struct smp_ltk *ltk; - struct smp_ltk *slave_ltk; - struct smp_irk *remote_irk; - unsigned long smp_flags; - struct work_struct confirm; - struct work_struct random; -}; - /* SMP Commands */ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level); diff --git a/net/bridge/Makefile b/net/bridge/Makefile index e85498b2f..8590b94 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_BRIDGE) += bridge.o bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \ - br_ioctl.o br_notify.o br_stp.o br_stp_bpdu.o \ + br_ioctl.o br_stp.o br_stp_bpdu.o \ br_stp_if.o br_stp_timer.o br_netlink.o bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o @@ -16,4 +16,4 @@ bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o -obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/ +obj-$(CONFIG_NETFILTER) += netfilter/ diff --git a/net/bridge/br.c b/net/bridge/br.c index 19311aaf..1a755a1 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -22,6 +22,104 @@ #include "br_private.h" +/* + * Handle changes in state of network devices enslaved to a bridge. + * + * Note: don't care about up/down if bridge itself is down, because + * port state is checked when bridge is brought up. + */ +static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net_bridge_port *p; + struct net_bridge *br; + bool changed_addr; + int err; + + /* register of bridge completed, add sysfs entries */ + if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) { + br_sysfs_addbr(dev); + return NOTIFY_DONE; + } + + /* not a port of a bridge */ + p = br_port_get_rtnl(dev); + if (!p) + return NOTIFY_DONE; + + br = p->br; + + switch (event) { + case NETDEV_CHANGEMTU: + dev_set_mtu(br->dev, br_min_mtu(br)); + break; + + case NETDEV_CHANGEADDR: + spin_lock_bh(&br->lock); + br_fdb_changeaddr(p, dev->dev_addr); + changed_addr = br_stp_recalculate_bridge_id(br); + spin_unlock_bh(&br->lock); + + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); + + break; + + case NETDEV_CHANGE: + br_port_carrier_check(p); + break; + + case NETDEV_FEAT_CHANGE: + netdev_update_features(br->dev); + break; + + case NETDEV_DOWN: + spin_lock_bh(&br->lock); + if (br->dev->flags & IFF_UP) + br_stp_disable_port(p); + spin_unlock_bh(&br->lock); + break; + + case NETDEV_UP: + if (netif_running(br->dev) && netif_oper_up(dev)) { + spin_lock_bh(&br->lock); + br_stp_enable_port(p); + spin_unlock_bh(&br->lock); + } + break; + + case NETDEV_UNREGISTER: + br_del_if(br, dev); + break; + + case NETDEV_CHANGENAME: + err = br_sysfs_renameif(p); + if (err) + return notifier_from_errno(err); + break; + + case NETDEV_PRE_TYPE_CHANGE: + /* Forbid underlaying device to change its type. */ + return NOTIFY_BAD; + + case NETDEV_RESEND_IGMP: + /* Propagate to master device */ + call_netdevice_notifiers(event, br->dev); + break; + } + + /* Events that may cause spanning tree to refresh */ + if (event == NETDEV_CHANGEADDR || event == NETDEV_UP || + event == NETDEV_CHANGE || event == NETDEV_DOWN) + br_ifinfo_notify(RTM_NEWLINK, p); + + return NOTIFY_DONE; +} + +static struct notifier_block br_device_notifier = { + .notifier_call = br_device_event +}; + static void __net_exit br_net_exit(struct net *net) { struct net_device *dev; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 9212015..d77e2f0 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -112,6 +112,12 @@ static void br_dev_set_multicast_list(struct net_device *dev) { } +static void br_dev_change_rx_flags(struct net_device *dev, int change) +{ + if (change & IFF_PROMISC) + br_manage_promisc(netdev_priv(dev)); +} + static int br_dev_stop(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -309,6 +315,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_get_stats64 = br_get_stats64, .ndo_set_mac_address = br_set_mac_address, .ndo_set_rx_mode = br_dev_set_multicast_list, + .ndo_change_rx_flags = br_dev_change_rx_flags, .ndo_change_mtu = br_change_mtu, .ndo_do_ioctl = br_dev_ioctl, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 9203d5a..2c45c06 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -85,8 +85,58 @@ static void fdb_rcu_free(struct rcu_head *head) kmem_cache_free(br_fdb_cache, ent); } +/* When a static FDB entry is added, the mac address from the entry is + * added to the bridge private HW address list and all required ports + * are then updated with the new information. + * Called under RTNL. + */ +static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr) +{ + int err; + struct net_bridge_port *p, *tmp; + + ASSERT_RTNL(); + + list_for_each_entry(p, &br->port_list, list) { + if (!br_promisc_port(p)) { + err = dev_uc_add(p->dev, addr); + if (err) + goto undo; + } + } + + return; +undo: + list_for_each_entry(tmp, &br->port_list, list) { + if (tmp == p) + break; + if (!br_promisc_port(tmp)) + dev_uc_del(tmp->dev, addr); + } +} + +/* When a static FDB entry is deleted, the HW address from that entry is + * also removed from the bridge private HW address list and updates all + * the ports with needed information. + * Called under RTNL. + */ +static void fdb_del_hw(struct net_bridge *br, const unsigned char *addr) +{ + struct net_bridge_port *p; + + ASSERT_RTNL(); + + list_for_each_entry(p, &br->port_list, list) { + if (!br_promisc_port(p)) + dev_uc_del(p->dev, addr); + } +} + static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) { + if (f->is_static) + fdb_del_hw(br, f->addr.addr); + hlist_del_rcu(&f->hlist); fdb_notify(br, f, RTM_DELNEIGH); call_rcu(&f->rcu, fdb_rcu_free); @@ -466,6 +516,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, return -ENOMEM; fdb->is_local = fdb->is_static = 1; + fdb_add_hw(br, addr); fdb_notify(br, fdb, RTM_NEWNEIGH); return 0; } @@ -565,6 +616,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr)) goto nla_put_failure; + if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) + goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); @@ -586,6 +639,7 @@ static inline size_t fdb_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + + nla_total_size(sizeof(u32)) /* NDA_MASTER */ + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)); } @@ -678,13 +732,25 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, } if (fdb_to_nud(fdb) != state) { - if (state & NUD_PERMANENT) - fdb->is_local = fdb->is_static = 1; - else if (state & NUD_NOARP) { + if (state & NUD_PERMANENT) { + fdb->is_local = 1; + if (!fdb->is_static) { + fdb->is_static = 1; + fdb_add_hw(br, addr); + } + } else if (state & NUD_NOARP) { fdb->is_local = 0; - fdb->is_static = 1; - } else - fdb->is_local = fdb->is_static = 0; + if (!fdb->is_static) { + fdb->is_static = 1; + fdb_add_hw(br, addr); + } + } else { + fdb->is_local = 0; + if (fdb->is_static) { + fdb->is_static = 0; + fdb_del_hw(br, addr); + } + } modified = true; } @@ -874,3 +940,59 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], out: return err; } + +int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p) +{ + struct net_bridge_fdb_entry *fdb, *tmp; + int i; + int err; + + ASSERT_RTNL(); + + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry(fdb, &br->hash[i], hlist) { + /* We only care for static entries */ + if (!fdb->is_static) + continue; + + err = dev_uc_add(p->dev, fdb->addr.addr); + if (err) + goto rollback; + } + } + return 0; + +rollback: + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry(tmp, &br->hash[i], hlist) { + /* If we reached the fdb that failed, we can stop */ + if (tmp == fdb) + break; + + /* We only care for static entries */ + if (!tmp->is_static) + continue; + + dev_uc_del(p->dev, tmp->addr.addr); + } + } + return err; +} + +void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) +{ + struct net_bridge_fdb_entry *fdb; + int i; + + ASSERT_RTNL(); + + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry_rcu(fdb, &br->hash[i], hlist) { + /* We only care for static entries */ + if (!fdb->is_static) + continue; + + dev_uc_del(p->dev, fdb->addr.addr); + } + } +} diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 5262b86..a08d2b8 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -85,6 +85,110 @@ void br_port_carrier_check(struct net_bridge_port *p) spin_unlock_bh(&br->lock); } +static void br_port_set_promisc(struct net_bridge_port *p) +{ + int err = 0; + + if (br_promisc_port(p)) + return; + + err = dev_set_promiscuity(p->dev, 1); + if (err) + return; + + br_fdb_unsync_static(p->br, p); + p->flags |= BR_PROMISC; +} + +static void br_port_clear_promisc(struct net_bridge_port *p) +{ + int err; + + /* Check if the port is already non-promisc or if it doesn't + * support UNICAST filtering. Without unicast filtering support + * we'll end up re-enabling promisc mode anyway, so just check for + * it here. + */ + if (!br_promisc_port(p) || !(p->dev->priv_flags & IFF_UNICAST_FLT)) + return; + + /* Since we'll be clearing the promisc mode, program the port + * first so that we don't have interruption in traffic. + */ + err = br_fdb_sync_static(p->br, p); + if (err) + return; + + dev_set_promiscuity(p->dev, -1); + p->flags &= ~BR_PROMISC; +} + +/* When a port is added or removed or when certain port flags + * change, this function is called to automatically manage + * promiscuity setting of all the bridge ports. We are always called + * under RTNL so can skip using rcu primitives. + */ +void br_manage_promisc(struct net_bridge *br) +{ + struct net_bridge_port *p; + bool set_all = false; + + /* If vlan filtering is disabled or bridge interface is placed + * into promiscuous mode, place all ports in promiscuous mode. + */ + if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br)) + set_all = true; + + list_for_each_entry(p, &br->port_list, list) { + if (set_all) { + br_port_set_promisc(p); + } else { + /* If the number of auto-ports is <= 1, then all other + * ports will have their output configuration + * statically specified through fdbs. Since ingress + * on the auto-port becomes forwarding/egress to other + * ports and egress configuration is statically known, + * we can say that ingress configuration of the + * auto-port is also statically known. + * This lets us disable promiscuous mode and write + * this config to hw. + */ + if (br->auto_cnt <= br_auto_port(p)) + br_port_clear_promisc(p); + else + br_port_set_promisc(p); + } + } +} + +static void nbp_update_port_count(struct net_bridge *br) +{ + struct net_bridge_port *p; + u32 cnt = 0; + + list_for_each_entry(p, &br->port_list, list) { + if (br_auto_port(p)) + cnt++; + } + if (br->auto_cnt != cnt) { + br->auto_cnt = cnt; + br_manage_promisc(br); + } +} + +static void nbp_delete_promisc(struct net_bridge_port *p) +{ + /* If port is currently promiscuous, unset promiscuity. + * Otherwise, it is a static port so remove all addresses + * from it. + */ + dev_set_allmulti(p->dev, -1); + if (br_promisc_port(p)) + dev_set_promiscuity(p->dev, -1); + else + br_fdb_unsync_static(p->br, p); +} + static void release_nbp(struct kobject *kobj) { struct net_bridge_port *p @@ -133,7 +237,7 @@ static void del_nbp(struct net_bridge_port *p) sysfs_remove_link(br->ifobj, p->dev->name); - dev_set_promiscuity(dev, -1); + nbp_delete_promisc(p); spin_lock_bh(&br->lock); br_stp_disable_port(p); @@ -141,10 +245,11 @@ static void del_nbp(struct net_bridge_port *p) br_ifinfo_notify(RTM_DELLINK, p); + list_del_rcu(&p->list); + nbp_vlan_flush(p); br_fdb_delete_by_port(br, p, 1); - - list_del_rcu(&p->list); + nbp_update_port_count(br); dev->priv_flags &= ~IFF_BRIDGE_PORT; @@ -353,7 +458,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) call_netdevice_notifiers(NETDEV_JOIN, dev); - err = dev_set_promiscuity(dev, 1); + err = dev_set_allmulti(dev, 1); if (err) goto put_back; @@ -384,6 +489,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) list_add_rcu(&p->list, &br->port_list); + nbp_update_port_count(br); + netdev_update_features(br->dev); if (br->dev->needed_headroom < dev->needed_headroom) @@ -421,7 +528,7 @@ err2: kobject_put(&p->kobj); p = NULL; /* kobject_put frees */ err1: - dev_set_promiscuity(dev, -1); + dev_set_allmulti(dev, -1); put_back: dev_put(dev); kfree(p); @@ -455,3 +562,11 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) return 0; } + +void br_port_flags_change(struct net_bridge_port *p, unsigned long mask) +{ + struct net_bridge *br = p->br; + + if (mask & BR_AUTO_MASK) + nbp_update_port_count(br); +} diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e8844d9..26edb51 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -328,6 +328,7 @@ static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) { int err; + unsigned long old_flags = p->flags; br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); @@ -353,6 +354,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) if (err) return err; } + + br_port_flags_change(p, old_flags ^ p->flags); return 0; } diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c deleted file mode 100644 index 2998dd1..0000000 --- a/net/bridge/br_notify.c +++ /dev/null @@ -1,118 +0,0 @@ -/* - * Device event handling - * Linux ethernet bridge - * - * Authors: - * Lennert Buytenhek <buytenh@gnu.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/rtnetlink.h> -#include <net/net_namespace.h> - -#include "br_private.h" - -static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr); - -struct notifier_block br_device_notifier = { - .notifier_call = br_device_event -}; - -/* - * Handle changes in state of network devices enslaved to a bridge. - * - * Note: don't care about up/down if bridge itself is down, because - * port state is checked when bridge is brought up. - */ -static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct net_bridge_port *p; - struct net_bridge *br; - bool changed_addr; - int err; - - /* register of bridge completed, add sysfs entries */ - if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) { - br_sysfs_addbr(dev); - return NOTIFY_DONE; - } - - /* not a port of a bridge */ - p = br_port_get_rtnl(dev); - if (!p) - return NOTIFY_DONE; - - br = p->br; - - switch (event) { - case NETDEV_CHANGEMTU: - dev_set_mtu(br->dev, br_min_mtu(br)); - break; - - case NETDEV_CHANGEADDR: - spin_lock_bh(&br->lock); - br_fdb_changeaddr(p, dev->dev_addr); - changed_addr = br_stp_recalculate_bridge_id(br); - spin_unlock_bh(&br->lock); - - if (changed_addr) - call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); - - break; - - case NETDEV_CHANGE: - br_port_carrier_check(p); - break; - - case NETDEV_FEAT_CHANGE: - netdev_update_features(br->dev); - break; - - case NETDEV_DOWN: - spin_lock_bh(&br->lock); - if (br->dev->flags & IFF_UP) - br_stp_disable_port(p); - spin_unlock_bh(&br->lock); - break; - - case NETDEV_UP: - if (netif_running(br->dev) && netif_oper_up(dev)) { - spin_lock_bh(&br->lock); - br_stp_enable_port(p); - spin_unlock_bh(&br->lock); - } - break; - - case NETDEV_UNREGISTER: - br_del_if(br, dev); - break; - - case NETDEV_CHANGENAME: - err = br_sysfs_renameif(p); - if (err) - return notifier_from_errno(err); - break; - - case NETDEV_PRE_TYPE_CHANGE: - /* Forbid underlaying device to change its type. */ - return NOTIFY_BAD; - - case NETDEV_RESEND_IGMP: - /* Propagate to master device */ - call_netdevice_notifiers(event, br->dev); - break; - } - - /* Events that may cause spanning tree to refresh */ - if (event == NETDEV_CHANGEADDR || event == NETDEV_UP || - event == NETDEV_CHANGE || event == NETDEV_DOWN) - br_ifinfo_notify(RTM_NEWLINK, p); - - return NOTIFY_DONE; -} diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 06811d7..53d6e32 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -174,6 +174,8 @@ struct net_bridge_port #define BR_ADMIN_COST 0x00000010 #define BR_LEARNING 0x00000020 #define BR_FLOOD 0x00000040 +#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING) +#define BR_PROMISC 0x00000080 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING struct bridge_mcast_query ip4_query; @@ -198,6 +200,9 @@ struct net_bridge_port #endif }; +#define br_auto_port(p) ((p)->flags & BR_AUTO_MASK) +#define br_promisc_port(p) ((p)->flags & BR_PROMISC) + #define br_port_exists(dev) (dev->priv_flags & IFF_BRIDGE_PORT) static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev) @@ -290,6 +295,7 @@ struct net_bridge struct timer_list topology_change_timer; struct timer_list gc_timer; struct kobject *ifobj; + u32 auto_cnt; #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_enabled; struct net_port_vlans __rcu *vlan_info; @@ -327,8 +333,6 @@ struct br_input_skb_cb { #define br_debug(br, format, args...) \ pr_debug("%s: " format, (br)->dev->name, ##args) -extern struct notifier_block br_device_notifier; - /* called under bridge lock */ static inline int br_is_root_bridge(const struct net_bridge *br) { @@ -395,6 +399,8 @@ int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 nlh_flags); int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, int idx); +int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); +void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); /* br_forward.c */ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb); @@ -415,6 +421,8 @@ int br_del_if(struct net_bridge *br, struct net_device *dev); int br_min_mtu(const struct net_bridge *br); netdev_features_t br_features_recompute(struct net_bridge *br, netdev_features_t features); +void br_port_flags_change(struct net_bridge_port *port, unsigned long mask); +void br_manage_promisc(struct net_bridge *br); /* br_input.c */ int br_handle_frame_finish(struct sk_buff *skb); @@ -632,6 +640,10 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v) return v->pvid ?: VLAN_N_VID; } +static inline int br_vlan_enabled(struct net_bridge *br) +{ + return br->vlan_enabled; +} #else static inline bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, @@ -712,6 +724,11 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v) { return VLAN_N_VID; /* Returns invalid vid */ } + +static inline int br_vlan_enabled(struct net_bridge *br) +{ + return 0; +} #endif /* br_netfilter.c */ diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index dd595bd..e561cd5 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -41,20 +41,30 @@ static ssize_t show_##_name(struct net_bridge_port *p, char *buf) \ } \ static int store_##_name(struct net_bridge_port *p, unsigned long v) \ { \ - unsigned long flags = p->flags; \ - if (v) \ - flags |= _mask; \ - else \ - flags &= ~_mask; \ - if (flags != p->flags) { \ - p->flags = flags; \ - br_ifinfo_notify(RTM_NEWLINK, p); \ - } \ - return 0; \ + return store_flag(p, v, _mask); \ } \ static BRPORT_ATTR(_name, S_IRUGO | S_IWUSR, \ show_##_name, store_##_name) +static int store_flag(struct net_bridge_port *p, unsigned long v, + unsigned long mask) +{ + unsigned long flags; + + flags = p->flags; + + if (v) + flags |= mask; + else + flags &= ~mask; + + if (flags != p->flags) { + p->flags = flags; + br_port_flags_change(p, mask); + br_ifinfo_notify(RTM_NEWLINK, p); + } + return 0; +} static ssize_t show_path_cost(struct net_bridge_port *p, char *buf) { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 4a37161..24c5cc5 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -332,6 +332,7 @@ int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) goto unlock; br->vlan_enabled = val; + br_manage_promisc(br); unlock: rtnl_unlock(); diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 5ca74a0..629dc77 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -2,14 +2,23 @@ # Bridge netfilter configuration # # -config NF_TABLES_BRIDGE - depends on NF_TABLES +menuconfig NF_TABLES_BRIDGE + depends on BRIDGE && NETFILTER && NF_TABLES tristate "Ethernet Bridge nf_tables support" +if NF_TABLES_BRIDGE + +config NFT_BRIDGE_META + tristate "Netfilter nf_table bridge meta support" + depends on NFT_META + help + Add support for bridge dedicated meta key. + +endif # NF_TABLES_BRIDGE + menuconfig BRIDGE_NF_EBTABLES tristate "Ethernet Bridge tables (ebtables) support" - depends on BRIDGE && NETFILTER - select NETFILTER_XTABLES + depends on BRIDGE && NETFILTER && NETFILTER_XTABLES help ebtables is a general, extensible frame/packet identification framework. Say 'Y' or 'M' here if you want to do Ethernet diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile index ea7629f..6f2f394 100644 --- a/net/bridge/netfilter/Makefile +++ b/net/bridge/netfilter/Makefile @@ -3,6 +3,7 @@ # obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o +obj-$(CONFIG_NFT_BRIDGE_META) += nft_meta_bridge.o obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c new file mode 100644 index 0000000..4f02109 --- /dev/null +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -0,0 +1,139 @@ +/* + * Copyright (c) 2014 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_meta.h> + +#include "../br_private.h" + +static void nft_meta_bridge_get_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + const struct nft_meta *priv = nft_expr_priv(expr); + const struct net_device *in = pkt->in, *out = pkt->out; + struct nft_data *dest = &data[priv->dreg]; + const struct net_bridge_port *p; + + switch (priv->key) { + case NFT_META_BRI_IIFNAME: + if (in == NULL || (p = br_port_get_rcu(in)) == NULL) + goto err; + break; + case NFT_META_BRI_OIFNAME: + if (out == NULL || (p = br_port_get_rcu(out)) == NULL) + goto err; + break; + default: + goto out; + } + + strncpy((char *)dest->data, p->br->dev->name, sizeof(dest->data)); + return; +out: + return nft_meta_get_eval(expr, data, pkt); +err: + data[NFT_REG_VERDICT].verdict = NFT_BREAK; +} + +static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_meta *priv = nft_expr_priv(expr); + int err; + + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); + switch (priv->key) { + case NFT_META_BRI_IIFNAME: + case NFT_META_BRI_OIFNAME: + break; + default: + return nft_meta_get_init(ctx, expr, tb); + } + + priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); + err = nft_validate_output_register(priv->dreg); + if (err < 0) + return err; + + err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + if (err < 0) + return err; + + return 0; +} + +static struct nft_expr_type nft_meta_bridge_type; +static const struct nft_expr_ops nft_meta_bridge_get_ops = { + .type = &nft_meta_bridge_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .eval = nft_meta_bridge_get_eval, + .init = nft_meta_bridge_get_init, + .dump = nft_meta_get_dump, +}; + +static const struct nft_expr_ops nft_meta_bridge_set_ops = { + .type = &nft_meta_bridge_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .eval = nft_meta_set_eval, + .init = nft_meta_set_init, + .dump = nft_meta_set_dump, +}; + +static const struct nft_expr_ops * +nft_meta_bridge_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_META_KEY] == NULL) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_META_DREG]) + return &nft_meta_bridge_get_ops; + + if (tb[NFTA_META_SREG]) + return &nft_meta_bridge_set_ops; + + return ERR_PTR(-EINVAL); +} + +static struct nft_expr_type nft_meta_bridge_type __read_mostly = { + .family = NFPROTO_BRIDGE, + .name = "meta", + .select_ops = &nft_meta_bridge_select_ops, + .policy = nft_meta_policy, + .maxattr = NFTA_META_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_meta_bridge_module_init(void) +{ + return nft_register_expr(&nft_meta_bridge_type); +} + +static void __exit nft_meta_bridge_module_exit(void) +{ + nft_unregister_expr(&nft_meta_bridge_type); +} + +module_init(nft_meta_bridge_module_init); +module_exit(nft_meta_bridge_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); diff --git a/net/can/af_can.c b/net/can/af_can.c index a27f8aa..ce82337 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -338,6 +338,29 @@ static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev) } /** + * effhash - hash function for 29 bit CAN identifier reduction + * @can_id: 29 bit CAN identifier + * + * Description: + * To reduce the linear traversal in one linked list of _single_ EFF CAN + * frame subscriptions the 29 bit identifier is mapped to 10 bits. + * (see CAN_EFF_RCV_HASH_BITS definition) + * + * Return: + * Hash value from 0x000 - 0x3FF ( enforced by CAN_EFF_RCV_HASH_BITS mask ) + */ +static unsigned int effhash(canid_t can_id) +{ + unsigned int hash; + + hash = can_id; + hash ^= can_id >> CAN_EFF_RCV_HASH_BITS; + hash ^= can_id >> (2 * CAN_EFF_RCV_HASH_BITS); + + return hash & ((1 << CAN_EFF_RCV_HASH_BITS) - 1); +} + +/** * find_rcv_list - determine optimal filterlist inside device filter struct * @can_id: pointer to CAN identifier of a given can_filter * @mask: pointer to CAN mask of a given can_filter @@ -400,10 +423,8 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, !(*can_id & CAN_RTR_FLAG)) { if (*can_id & CAN_EFF_FLAG) { - if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) { - /* RFC: a future use-case for hash-tables? */ - return &d->rx[RX_EFF]; - } + if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) + return &d->rx_eff[effhash(*can_id)]; } else { if (*mask == (CAN_SFF_MASK | CAN_EFF_RTR_FLAGS)) return &d->rx_sff[*can_id]; @@ -632,7 +653,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) return matches; if (can_id & CAN_EFF_FLAG) { - hlist_for_each_entry_rcu(r, &d->rx[RX_EFF], list) { + hlist_for_each_entry_rcu(r, &d->rx_eff[effhash(can_id)], list) { if (r->can_id == can_id) { deliver(skb, r); matches++; diff --git a/net/can/af_can.h b/net/can/af_can.h index 6de58b4..fca0fe9 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -59,12 +59,17 @@ struct receiver { char *ident; }; -enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_EFF, RX_MAX }; +#define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) +#define CAN_EFF_RCV_HASH_BITS 10 +#define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) + +enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX }; /* per device receive filters linked at dev->ml_priv */ struct dev_rcv_lists { struct hlist_head rx[RX_MAX]; - struct hlist_head rx_sff[0x800]; + struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ]; + struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ]; int remove_on_zero_entries; int entries; }; diff --git a/net/can/proc.c b/net/can/proc.c index b543470..1a19b98 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -80,7 +80,6 @@ static const char rx_list_name[][8] = { [RX_ALL] = "rx_all", [RX_FIL] = "rx_fil", [RX_INV] = "rx_inv", - [RX_EFF] = "rx_eff", }; /* @@ -389,25 +388,26 @@ static const struct file_operations can_rcvlist_proc_fops = { .release = single_release, }; -static inline void can_rcvlist_sff_proc_show_one(struct seq_file *m, - struct net_device *dev, - struct dev_rcv_lists *d) +static inline void can_rcvlist_proc_show_array(struct seq_file *m, + struct net_device *dev, + struct hlist_head *rcv_array, + unsigned int rcv_array_sz) { - int i; + unsigned int i; int all_empty = 1; /* check whether at least one list is non-empty */ - for (i = 0; i < 0x800; i++) - if (!hlist_empty(&d->rx_sff[i])) { + for (i = 0; i < rcv_array_sz; i++) + if (!hlist_empty(&rcv_array[i])) { all_empty = 0; break; } if (!all_empty) { can_print_recv_banner(m); - for (i = 0; i < 0x800; i++) { - if (!hlist_empty(&d->rx_sff[i])) - can_print_rcvlist(m, &d->rx_sff[i], dev); + for (i = 0; i < rcv_array_sz; i++) { + if (!hlist_empty(&rcv_array[i])) + can_print_rcvlist(m, &rcv_array[i], dev); } } else seq_printf(m, " (%s: no entry)\n", DNAME(dev)); @@ -425,12 +425,15 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) /* sff receive list for 'all' CAN devices (dev == NULL) */ d = &can_rx_alldev_list; - can_rcvlist_sff_proc_show_one(m, NULL, d); + can_rcvlist_proc_show_array(m, NULL, d->rx_sff, ARRAY_SIZE(d->rx_sff)); /* sff receive list for registered CAN devices */ for_each_netdev_rcu(&init_net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) - can_rcvlist_sff_proc_show_one(m, dev, dev->ml_priv); + if (dev->type == ARPHRD_CAN && dev->ml_priv) { + d = dev->ml_priv; + can_rcvlist_proc_show_array(m, dev, d->rx_sff, + ARRAY_SIZE(d->rx_sff)); + } } rcu_read_unlock(); @@ -452,6 +455,49 @@ static const struct file_operations can_rcvlist_sff_proc_fops = { .release = single_release, }; + +static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) +{ + struct net_device *dev; + struct dev_rcv_lists *d; + + /* RX_EFF */ + seq_puts(m, "\nreceive list 'rx_eff':\n"); + + rcu_read_lock(); + + /* eff receive list for 'all' CAN devices (dev == NULL) */ + d = &can_rx_alldev_list; + can_rcvlist_proc_show_array(m, NULL, d->rx_eff, ARRAY_SIZE(d->rx_eff)); + + /* eff receive list for registered CAN devices */ + for_each_netdev_rcu(&init_net, dev) { + if (dev->type == ARPHRD_CAN && dev->ml_priv) { + d = dev->ml_priv; + can_rcvlist_proc_show_array(m, dev, d->rx_eff, + ARRAY_SIZE(d->rx_eff)); + } + } + + rcu_read_unlock(); + + seq_putc(m, '\n'); + return 0; +} + +static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, can_rcvlist_eff_proc_show, NULL); +} + +static const struct file_operations can_rcvlist_eff_proc_fops = { + .owner = THIS_MODULE, + .open = can_rcvlist_eff_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + /* * proc utility functions */ @@ -491,8 +537,8 @@ void can_init_proc(void) &can_rcvlist_proc_fops, (void *)RX_FIL); pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, can_dir, &can_rcvlist_proc_fops, (void *)RX_INV); - pde_rcvlist_eff = proc_create_data(CAN_PROC_RCVLIST_EFF, 0644, can_dir, - &can_rcvlist_proc_fops, (void *)RX_EFF); + pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644, can_dir, + &can_rcvlist_eff_proc_fops); pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, can_dir, &can_rcvlist_sff_proc_fops); } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index dac7f9b..1948d59 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -557,7 +557,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, return r; } -static int ceph_tcp_sendpage(struct socket *sock, struct page *page, +static int __ceph_tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, bool more) { int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR); @@ -570,6 +570,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, return ret; } +static int ceph_tcp_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, bool more) +{ + int ret; + struct kvec iov; + + /* sendpage cannot properly handle pages with page_count == 0, + * we need to fallback to sendmsg if that's the case */ + if (page_count(page) >= 1) + return __ceph_tcp_sendpage(sock, page, offset, size, more); + + iov.iov_base = kmap(page) + offset; + iov.iov_len = size; + ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more); + kunmap(page); + + return ret; +} /* * Shutdown/close the socket for the given connection. diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 8b8a5a2..c547e46 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -329,6 +329,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end) dout("crush decode tunable chooseleaf_descend_once = %d", c->chooseleaf_descend_once); + ceph_decode_need(p, end, sizeof(u8), done); + c->chooseleaf_vary_r = ceph_decode_8(p); + dout("crush decode tunable chooseleaf_vary_r = %d", + c->chooseleaf_vary_r); + done: dout("crush_decode success\n"); return c; diff --git a/net/core/Makefile b/net/core/Makefile index 826b925..71093d9 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ - sock_diag.o dev_ioctl.o + sock_diag.o dev_ioctl.o tso.o obj-$(CONFIG_XFRM) += flow.o obj-y += net-sysfs.o diff --git a/net/core/dev.c b/net/core/dev.c index 867adb2..0355ca5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3957,6 +3957,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; + NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); skb->next = napi->gro_list; napi->gro_list = skb; @@ -4547,6 +4548,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list) EXPORT_SYMBOL(netdev_adjacent_get_private); /** + * netdev_upper_get_next_dev_rcu - Get the next dev from upper list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next device from the dev's upper list, starting from iter + * position. The caller must hold RCU read lock. + */ +struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *upper; + + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); + + upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->adj_list.upper) + return NULL; + + *iter = &upper->list; + + return upper->dev; +} +EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); + +/** * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list * @dev: device * @iter: list_head ** of the current position @@ -4628,6 +4655,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** + * netdev_lower_get_next - Get the next device from the lower neighbour + * list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent from the dev's lower neighbour + * list, starting from iter position. The caller must hold RTNL lock or + * its own locking that guarantees that the neighbour lower + * list will remain unchainged. + */ +void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + + return lower->dev; +} +EXPORT_SYMBOL(netdev_lower_get_next); + +/** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU * variant @@ -5077,6 +5130,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev, } EXPORT_SYMBOL(netdev_lower_dev_get_private); + +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)) +{ + struct net_device *lower = NULL; + struct list_head *iter; + int max_nest = -1; + int nest; + + ASSERT_RTNL(); + + netdev_for_each_lower_dev(dev, lower, iter) { + nest = dev_get_nest_level(lower, type_check); + if (max_nest < nest) + max_nest = nest; + } + + if (type_check(dev)) + max_nest++; + + return max_nest; +} +EXPORT_SYMBOL(dev_get_nest_level); + static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -5242,7 +5319,6 @@ void __dev_set_rx_mode(struct net_device *dev) if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } -EXPORT_SYMBOL(__dev_set_rx_mode); void dev_set_rx_mode(struct net_device *dev) { @@ -5547,7 +5623,7 @@ static int dev_new_index(struct net *net) /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); -static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); +DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 329d579..b6b2306 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -225,6 +225,91 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, } EXPORT_SYMBOL(__hw_addr_unsync); +/** + * __hw_addr_sync_dev - Synchonize device's multicast list + * @list: address list to syncronize + * @dev: device to sync + * @sync: function to call if address should be added + * @unsync: function to call if address should be removed + * + * This funciton is intended to be called from the ndo_set_rx_mode + * function of devices that require explicit address add/remove + * notifications. The unsync function may be NULL in which case + * the addresses requiring removal will simply be removed without + * any notification to the device. + **/ +int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*sync)(struct net_device *, const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + struct netdev_hw_addr *ha, *tmp; + int err; + + /* first go through and flush out any stale entries */ + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (!ha->sync_cnt || ha->refcount != 1) + continue; + + /* if unsync is defined and fails defer unsyncing address */ + if (unsync && unsync(dev, ha->addr)) + continue; + + ha->sync_cnt--; + __hw_addr_del_entry(list, ha, false, false); + } + + /* go through and sync new entries to the list */ + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (ha->sync_cnt) + continue; + + err = sync(dev, ha->addr); + if (err) + return err; + + ha->sync_cnt++; + ha->refcount++; + } + + return 0; +} +EXPORT_SYMBOL(__hw_addr_sync_dev); + +/** + * __hw_addr_unsync_dev - Remove synchonized addresses from device + * @list: address list to remove syncronized addresses from + * @dev: device to sync + * @unsync: function to call if address should be removed + * + * Remove all addresses that were added to the device by __hw_addr_sync_dev(). + * This function is intended to be called from the ndo_stop or ndo_open + * functions on devices that require explicit address add/remove + * notifications. If the unsync function pointer is NULL then this function + * can be used to just reset the sync_cnt for the addresses in the list. + **/ +void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (!ha->sync_cnt) + continue; + + /* if unsync is defined and fails defer unsyncing address */ + if (unsync && unsync(dev, ha->addr)) + continue; + + ha->sync_cnt--; + __hw_addr_del_entry(list, ha, false, false); + } +} +EXPORT_SYMBOL(__hw_addr_unsync_dev); + static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; diff --git a/net/core/filter.c b/net/core/filter.c index c442a0d..842f839 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -153,102 +153,107 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) * keep, 0 for none. @ctx is the data we are operating on, @insn is the * array of filter instructions. */ -unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) +static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) { u64 stack[MAX_BPF_STACK / sizeof(u64)]; u64 regs[MAX_BPF_REG], tmp; static const void *jumptable[256] = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ -#define DL(A, B, C) [BPF_##A|BPF_##B|BPF_##C] = &&A##_##B##_##C - DL(ALU, ADD, X), - DL(ALU, ADD, K), - DL(ALU, SUB, X), - DL(ALU, SUB, K), - DL(ALU, AND, X), - DL(ALU, AND, K), - DL(ALU, OR, X), - DL(ALU, OR, K), - DL(ALU, LSH, X), - DL(ALU, LSH, K), - DL(ALU, RSH, X), - DL(ALU, RSH, K), - DL(ALU, XOR, X), - DL(ALU, XOR, K), - DL(ALU, MUL, X), - DL(ALU, MUL, K), - DL(ALU, MOV, X), - DL(ALU, MOV, K), - DL(ALU, DIV, X), - DL(ALU, DIV, K), - DL(ALU, MOD, X), - DL(ALU, MOD, K), - DL(ALU, NEG, 0), - DL(ALU, END, TO_BE), - DL(ALU, END, TO_LE), - DL(ALU64, ADD, X), - DL(ALU64, ADD, K), - DL(ALU64, SUB, X), - DL(ALU64, SUB, K), - DL(ALU64, AND, X), - DL(ALU64, AND, K), - DL(ALU64, OR, X), - DL(ALU64, OR, K), - DL(ALU64, LSH, X), - DL(ALU64, LSH, K), - DL(ALU64, RSH, X), - DL(ALU64, RSH, K), - DL(ALU64, XOR, X), - DL(ALU64, XOR, K), - DL(ALU64, MUL, X), - DL(ALU64, MUL, K), - DL(ALU64, MOV, X), - DL(ALU64, MOV, K), - DL(ALU64, ARSH, X), - DL(ALU64, ARSH, K), - DL(ALU64, DIV, X), - DL(ALU64, DIV, K), - DL(ALU64, MOD, X), - DL(ALU64, MOD, K), - DL(ALU64, NEG, 0), - DL(JMP, CALL, 0), - DL(JMP, JA, 0), - DL(JMP, JEQ, X), - DL(JMP, JEQ, K), - DL(JMP, JNE, X), - DL(JMP, JNE, K), - DL(JMP, JGT, X), - DL(JMP, JGT, K), - DL(JMP, JGE, X), - DL(JMP, JGE, K), - DL(JMP, JSGT, X), - DL(JMP, JSGT, K), - DL(JMP, JSGE, X), - DL(JMP, JSGE, K), - DL(JMP, JSET, X), - DL(JMP, JSET, K), - DL(JMP, EXIT, 0), - DL(STX, MEM, B), - DL(STX, MEM, H), - DL(STX, MEM, W), - DL(STX, MEM, DW), - DL(STX, XADD, W), - DL(STX, XADD, DW), - DL(ST, MEM, B), - DL(ST, MEM, H), - DL(ST, MEM, W), - DL(ST, MEM, DW), - DL(LDX, MEM, B), - DL(LDX, MEM, H), - DL(LDX, MEM, W), - DL(LDX, MEM, DW), - DL(LD, ABS, W), - DL(LD, ABS, H), - DL(LD, ABS, B), - DL(LD, IND, W), - DL(LD, IND, H), - DL(LD, IND, B), -#undef DL + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, + [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, + [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, + [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, + [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, + [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, + [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, + [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, + [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, + [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, + [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, + [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, + [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, + [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, + [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, + [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, + [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, + [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, + [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, + [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, + [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, + [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, + [BPF_ALU | BPF_NEG] = &&ALU_NEG, + [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, + [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE, + /* 64 bit ALU operations */ + [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X, + [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K, + [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X, + [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K, + [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X, + [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K, + [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X, + [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K, + [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X, + [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K, + [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X, + [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K, + [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X, + [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K, + [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X, + [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K, + [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X, + [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K, + [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X, + [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K, + [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X, + [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K, + [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X, + [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K, + [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, + /* Call instruction */ + [BPF_JMP | BPF_CALL] = &&JMP_CALL, + /* Jumps */ + [BPF_JMP | BPF_JA] = &&JMP_JA, + [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, + [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K, + [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X, + [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, + [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, + [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, + [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, + [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, + [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, + [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, + [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, + [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, + [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, + [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, + /* Program return */ + [BPF_JMP | BPF_EXIT] = &&JMP_EXIT, + /* Store instructions */ + [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B, + [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H, + [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W, + [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW, + [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W, + [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW, + [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B, + [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H, + [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W, + [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW, + /* Load instructions */ + [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B, + [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H, + [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W, + [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW, + [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W, + [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H, + [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B, + [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W, + [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H, + [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B, }; void *ptr; int off; @@ -290,10 +295,10 @@ select_insn: ALU(XOR, ^) ALU(MUL, *) #undef ALU - ALU_NEG_0: + ALU_NEG: A = (u32) -A; CONT; - ALU64_NEG_0: + ALU64_NEG: A = -A; CONT; ALU_MOV_X: @@ -382,7 +387,7 @@ select_insn: CONT; /* CALL */ - JMP_CALL_0: + JMP_CALL: /* Function call scratches BPF_R1-BPF_R5 registers, * preserves BPF_R6-BPF_R9, and stores return value * into BPF_R0. @@ -392,7 +397,7 @@ select_insn: CONT; /* JMP */ - JMP_JA_0: + JMP_JA: insn += insn->off; CONT; JMP_JEQ_X: @@ -479,7 +484,7 @@ select_insn: CONT_JMP; } CONT; - JMP_EXIT_0: + JMP_EXIT: return BPF_R0; /* STX and ST and LDX*/ @@ -531,11 +536,13 @@ load_word: * Output: * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness */ + ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp); if (likely(ptr != NULL)) { BPF_R0 = get_unaligned_be32(ptr); CONT; } + return 0; LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + K)) */ off = K; @@ -545,6 +552,7 @@ load_half: BPF_R0 = get_unaligned_be16(ptr); CONT; } + return 0; LD_ABS_B: /* BPF_R0 = *(u8 *) (ctx + K) */ off = K; @@ -554,6 +562,7 @@ load_byte: BPF_R0 = *(u8 *)ptr; CONT; } + return 0; LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + X + K)) */ off = K + X; @@ -571,15 +580,6 @@ load_byte: return 0; } -u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, - const struct sock_filter_int *insni) - __attribute__ ((alias ("__sk_run_filter"))); - -u32 sk_run_filter_int_skb(const struct sk_buff *ctx, - const struct sock_filter_int *insni) - __attribute__ ((alias ("__sk_run_filter"))); -EXPORT_SYMBOL_GPL(sk_run_filter_int_skb); - /* Helper to find the offset of pkt_type in sk_buff structure. We want * to make sure its still a 3bit field starting at a byte boundary; * taken from arch/x86/net/bpf_jit_comp.c. @@ -672,14 +672,10 @@ static bool convert_bpf_extensions(struct sock_filter *fp, BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); /* A = *(u16 *) (ctx + offsetof(protocol)) */ - *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, - offsetof(struct sk_buff, protocol)); - insn++; - + *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, protocol)); /* A = ntohs(A) [emitting a nop or swap16] */ - insn->code = BPF_ALU | BPF_END | BPF_FROM_BE; - insn->a_reg = BPF_REG_A; - insn->imm = 16; + *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PKTTYPE: @@ -688,37 +684,27 @@ static bool convert_bpf_extensions(struct sock_filter *fp, if (insn->off < 0) return false; insn++; - *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX); break; case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: - *insn = BPF_LDX_MEM(size_to_bpf(FIELD_SIZEOF(struct sk_buff, dev)), - BPF_REG_TMP, BPF_REG_CTX, - offsetof(struct sk_buff, dev)); - insn++; - - /* if (tmp != 0) goto pc+1 */ - *insn = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); - insn++; - - *insn = BPF_EXIT_INSN(); - insn++; - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); - - insn->a_reg = BPF_REG_A; - insn->x_reg = BPF_REG_TMP; - - if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) { - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->off = offsetof(struct net_device, ifindex); - } else { - insn->code = BPF_LDX | BPF_MEM | BPF_H; - insn->off = offsetof(struct net_device, type); - } + BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0); + + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + BPF_REG_TMP, BPF_REG_CTX, + offsetof(struct sk_buff, dev)); + /* if (tmp != 0) goto pc + 1 */ + *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); + *insn++ = BPF_EXIT_INSN(); + if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, + offsetof(struct net_device, ifindex)); + else + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, + offsetof(struct net_device, type)); break; case SKF_AD_OFF + SKF_AD_MARK: @@ -745,22 +731,17 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_VLAN_TAG: case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - - /* A = *(u16 *) (ctx + offsetof(vlan_tci)) */ - *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, - offsetof(struct sk_buff, vlan_tci)); - insn++; - BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + /* A = *(u16 *) (ctx + offsetof(vlan_tci)) */ + *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, vlan_tci)); if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, ~VLAN_TAG_PRESENT); } else { /* A >>= 12 */ - *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12); - insn++; - + *insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12); /* A &= 1 */ *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1); } @@ -772,34 +753,27 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_CPU: case SKF_AD_OFF + SKF_AD_RANDOM: /* arg1 = ctx */ - *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG1, BPF_REG_CTX); - insn++; - + *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); /* arg2 = A */ - *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG2, BPF_REG_A); - insn++; - + *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); /* arg3 = X */ - *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG3, BPF_REG_X); - insn++; - + *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); /* Emit call(ctx, arg2=A, arg3=X) */ - insn->code = BPF_JMP | BPF_CALL; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: - insn->imm = __skb_get_pay_offset - __bpf_call_base; + *insn = BPF_EMIT_CALL(__skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: - insn->imm = __skb_get_nlattr - __bpf_call_base; + *insn = BPF_EMIT_CALL(__skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: - insn->imm = __skb_get_nlattr_nest - __bpf_call_base; + *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: - insn->imm = __get_raw_cpu_id - __bpf_call_base; + *insn = BPF_EMIT_CALL(__get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: - insn->imm = __get_random_u32 - __bpf_call_base; + *insn = BPF_EMIT_CALL(__get_random_u32); break; } break; @@ -871,9 +845,8 @@ do_pass: new_insn = new_prog; fp = prog; - if (new_insn) { - *new_insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_CTX, BPF_REG_ARG1); - } + if (new_insn) + *new_insn = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); new_insn++; for (i = 0; i < len; fp++, i++) { @@ -921,17 +894,16 @@ do_pass: convert_bpf_extensions(fp, &insn)) break; - insn->code = fp->code; - insn->a_reg = BPF_REG_A; - insn->x_reg = BPF_REG_X; - insn->imm = fp->k; + *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break; - /* Jump opcodes map as-is, but offsets need adjustment. */ - case BPF_JMP | BPF_JA: - target = i + fp->k + 1; - insn->code = fp->code; -#define EMIT_JMP \ + /* Jump transformation cannot use BPF block macros + * everywhere as offset calculation and target updates + * require a bit more work than the rest, i.e. jump + * opcodes map as-is, but offsets need adjustment. + */ + +#define BPF_EMIT_JMP \ do { \ if (target >= len || target < 0) \ goto err; \ @@ -940,7 +912,10 @@ do_pass: insn->off -= insn - tmp_insns; \ } while (0) - EMIT_JMP; + case BPF_JMP | BPF_JA: + target = i + fp->k + 1; + insn->code = fp->code; + BPF_EMIT_JMP; break; case BPF_JMP | BPF_JEQ | BPF_K: @@ -956,10 +931,7 @@ do_pass: * immediate into tmp register and use it * in compare insn. */ - insn->code = BPF_ALU | BPF_MOV | BPF_K; - insn->a_reg = BPF_REG_TMP; - insn->imm = fp->k; - insn++; + *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k); insn->a_reg = BPF_REG_A; insn->x_reg = BPF_REG_TMP; @@ -975,7 +947,7 @@ do_pass: if (fp->jf == 0) { insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; target = i + fp->jt + 1; - EMIT_JMP; + BPF_EMIT_JMP; break; } @@ -983,116 +955,94 @@ do_pass: if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) { insn->code = BPF_JMP | BPF_JNE | bpf_src; target = i + fp->jf + 1; - EMIT_JMP; + BPF_EMIT_JMP; break; } /* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; - EMIT_JMP; + BPF_EMIT_JMP; insn++; insn->code = BPF_JMP | BPF_JA; target = i + fp->jf + 1; - EMIT_JMP; + BPF_EMIT_JMP; break; /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: /* tmp = A */ - *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_TMP, BPF_REG_A); - insn++; - + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A); /* A = BPF_R0 = *(u8 *) (skb->data + K) */ - *insn = BPF_LD_ABS(BPF_B, fp->k); - insn++; - + *insn++ = BPF_LD_ABS(BPF_B, fp->k); /* A &= 0xf */ - *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); - insn++; - + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); /* A <<= 2 */ - *insn = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); - insn++; - + *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); /* X = A */ - *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_X, BPF_REG_A); - insn++; - + *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = tmp */ - *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_A, BPF_REG_TMP); + *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; /* RET_K, RET_A are remaped into 2 insns. */ case BPF_RET | BPF_A: case BPF_RET | BPF_K: - insn->code = BPF_ALU | BPF_MOV | - (BPF_RVAL(fp->code) == BPF_K ? - BPF_K : BPF_X); - insn->a_reg = 0; - insn->x_reg = BPF_REG_A; - insn->imm = fp->k; - insn++; - + *insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ? + BPF_K : BPF_X, BPF_REG_0, + BPF_REG_A, fp->k); *insn = BPF_EXIT_INSN(); break; /* Store to stack. */ case BPF_ST: case BPF_STX: - insn->code = BPF_STX | BPF_MEM | BPF_W; - insn->a_reg = BPF_REG_FP; - insn->x_reg = fp->code == BPF_ST ? - BPF_REG_A : BPF_REG_X; - insn->off = -(BPF_MEMWORDS - fp->k) * 4; + *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == + BPF_ST ? BPF_REG_A : BPF_REG_X, + -(BPF_MEMWORDS - fp->k) * 4); break; /* Load from stack. */ case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - BPF_REG_A : BPF_REG_X; - insn->x_reg = BPF_REG_FP; - insn->off = -(BPF_MEMWORDS - fp->k) * 4; + *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, BPF_REG_FP, + -(BPF_MEMWORDS - fp->k) * 4); break; /* A = K or X = K */ case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: - insn->code = BPF_ALU | BPF_MOV | BPF_K; - insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - BPF_REG_A : BPF_REG_X; - insn->imm = fp->k; + *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, fp->k); break; /* X = A */ case BPF_MISC | BPF_TAX: - *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_X, BPF_REG_A); + *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); break; /* A = X */ case BPF_MISC | BPF_TXA: - *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_A, BPF_REG_X); + *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); break; /* A = skb->len or X = skb->len */ case BPF_LD | BPF_W | BPF_LEN: case BPF_LDX | BPF_W | BPF_LEN: - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - BPF_REG_A : BPF_REG_X; - insn->x_reg = BPF_REG_CTX; - insn->off = offsetof(struct sk_buff, len); + *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, BPF_REG_CTX, + offsetof(struct sk_buff, len)); break; - /* access seccomp_data fields */ + /* Access seccomp_data fields. */ case BPF_LDX | BPF_ABS | BPF_W: /* A = *(u32 *) (ctx + K) */ *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break; + /* Unkown instruction. */ default: goto err; } @@ -1101,7 +1051,6 @@ do_pass: if (new_prog) memcpy(new_insn, tmp_insns, sizeof(*insn) * (insn - tmp_insns)); - new_insn += insn - tmp_insns; } @@ -1116,7 +1065,6 @@ do_pass: new_flen = new_insn - new_prog; if (pass > 2) goto err; - goto do_pass; } @@ -1140,44 +1088,46 @@ err: */ static int check_load_and_stores(struct sock_filter *filter, int flen) { - u16 *masks, memvalid = 0; /* one bit per cell, 16 cells */ + u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; BUILD_BUG_ON(BPF_MEMWORDS > 16); + masks = kmalloc(flen * sizeof(*masks), GFP_KERNEL); if (!masks) return -ENOMEM; + memset(masks, 0xff, flen * sizeof(*masks)); for (pc = 0; pc < flen; pc++) { memvalid &= masks[pc]; switch (filter[pc].code) { - case BPF_S_ST: - case BPF_S_STX: + case BPF_ST: + case BPF_STX: memvalid |= (1 << filter[pc].k); break; - case BPF_S_LD_MEM: - case BPF_S_LDX_MEM: + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: if (!(memvalid & (1 << filter[pc].k))) { ret = -EINVAL; goto error; } break; - case BPF_S_JMP_JA: - /* a jump must set masks on target */ + case BPF_JMP | BPF_JA: + /* A jump must set masks on target */ masks[pc + 1 + filter[pc].k] &= memvalid; memvalid = ~0; break; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JSET_X: - case BPF_S_JMP_JSET_K: - /* a jump must set masks on targets */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + /* A jump must set masks on targets */ masks[pc + 1 + filter[pc].jt] &= memvalid; masks[pc + 1 + filter[pc].jf] &= memvalid; memvalid = ~0; @@ -1189,6 +1139,72 @@ error: return ret; } +static bool chk_code_allowed(u16 code_to_probe) +{ + static const bool codes[] = { + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_K] = true, + [BPF_ALU | BPF_ADD | BPF_X] = true, + [BPF_ALU | BPF_SUB | BPF_K] = true, + [BPF_ALU | BPF_SUB | BPF_X] = true, + [BPF_ALU | BPF_MUL | BPF_K] = true, + [BPF_ALU | BPF_MUL | BPF_X] = true, + [BPF_ALU | BPF_DIV | BPF_K] = true, + [BPF_ALU | BPF_DIV | BPF_X] = true, + [BPF_ALU | BPF_MOD | BPF_K] = true, + [BPF_ALU | BPF_MOD | BPF_X] = true, + [BPF_ALU | BPF_AND | BPF_K] = true, + [BPF_ALU | BPF_AND | BPF_X] = true, + [BPF_ALU | BPF_OR | BPF_K] = true, + [BPF_ALU | BPF_OR | BPF_X] = true, + [BPF_ALU | BPF_XOR | BPF_K] = true, + [BPF_ALU | BPF_XOR | BPF_X] = true, + [BPF_ALU | BPF_LSH | BPF_K] = true, + [BPF_ALU | BPF_LSH | BPF_X] = true, + [BPF_ALU | BPF_RSH | BPF_K] = true, + [BPF_ALU | BPF_RSH | BPF_X] = true, + [BPF_ALU | BPF_NEG] = true, + /* Load instructions */ + [BPF_LD | BPF_W | BPF_ABS] = true, + [BPF_LD | BPF_H | BPF_ABS] = true, + [BPF_LD | BPF_B | BPF_ABS] = true, + [BPF_LD | BPF_W | BPF_LEN] = true, + [BPF_LD | BPF_W | BPF_IND] = true, + [BPF_LD | BPF_H | BPF_IND] = true, + [BPF_LD | BPF_B | BPF_IND] = true, + [BPF_LD | BPF_IMM] = true, + [BPF_LD | BPF_MEM] = true, + [BPF_LDX | BPF_W | BPF_LEN] = true, + [BPF_LDX | BPF_B | BPF_MSH] = true, + [BPF_LDX | BPF_IMM] = true, + [BPF_LDX | BPF_MEM] = true, + /* Store instructions */ + [BPF_ST] = true, + [BPF_STX] = true, + /* Misc instructions */ + [BPF_MISC | BPF_TAX] = true, + [BPF_MISC | BPF_TXA] = true, + /* Return instructions */ + [BPF_RET | BPF_K] = true, + [BPF_RET | BPF_A] = true, + /* Jump instructions */ + [BPF_JMP | BPF_JA] = true, + [BPF_JMP | BPF_JEQ | BPF_K] = true, + [BPF_JMP | BPF_JEQ | BPF_X] = true, + [BPF_JMP | BPF_JGE | BPF_K] = true, + [BPF_JMP | BPF_JGE | BPF_X] = true, + [BPF_JMP | BPF_JGT | BPF_K] = true, + [BPF_JMP | BPF_JGT | BPF_X] = true, + [BPF_JMP | BPF_JSET | BPF_K] = true, + [BPF_JMP | BPF_JSET | BPF_X] = true, + }; + + if (code_to_probe >= ARRAY_SIZE(codes)) + return false; + + return codes[code_to_probe]; +} + /** * sk_chk_filter - verify socket filter code * @filter: filter to verify @@ -1205,154 +1221,76 @@ error: */ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) { - /* - * Valid instructions are initialized to non-0. - * Invalid instructions are initialized to 0. - */ - static const u8 codes[] = { - [BPF_ALU|BPF_ADD|BPF_K] = BPF_S_ALU_ADD_K, - [BPF_ALU|BPF_ADD|BPF_X] = BPF_S_ALU_ADD_X, - [BPF_ALU|BPF_SUB|BPF_K] = BPF_S_ALU_SUB_K, - [BPF_ALU|BPF_SUB|BPF_X] = BPF_S_ALU_SUB_X, - [BPF_ALU|BPF_MUL|BPF_K] = BPF_S_ALU_MUL_K, - [BPF_ALU|BPF_MUL|BPF_X] = BPF_S_ALU_MUL_X, - [BPF_ALU|BPF_DIV|BPF_X] = BPF_S_ALU_DIV_X, - [BPF_ALU|BPF_MOD|BPF_K] = BPF_S_ALU_MOD_K, - [BPF_ALU|BPF_MOD|BPF_X] = BPF_S_ALU_MOD_X, - [BPF_ALU|BPF_AND|BPF_K] = BPF_S_ALU_AND_K, - [BPF_ALU|BPF_AND|BPF_X] = BPF_S_ALU_AND_X, - [BPF_ALU|BPF_OR|BPF_K] = BPF_S_ALU_OR_K, - [BPF_ALU|BPF_OR|BPF_X] = BPF_S_ALU_OR_X, - [BPF_ALU|BPF_XOR|BPF_K] = BPF_S_ALU_XOR_K, - [BPF_ALU|BPF_XOR|BPF_X] = BPF_S_ALU_XOR_X, - [BPF_ALU|BPF_LSH|BPF_K] = BPF_S_ALU_LSH_K, - [BPF_ALU|BPF_LSH|BPF_X] = BPF_S_ALU_LSH_X, - [BPF_ALU|BPF_RSH|BPF_K] = BPF_S_ALU_RSH_K, - [BPF_ALU|BPF_RSH|BPF_X] = BPF_S_ALU_RSH_X, - [BPF_ALU|BPF_NEG] = BPF_S_ALU_NEG, - [BPF_LD|BPF_W|BPF_ABS] = BPF_S_LD_W_ABS, - [BPF_LD|BPF_H|BPF_ABS] = BPF_S_LD_H_ABS, - [BPF_LD|BPF_B|BPF_ABS] = BPF_S_LD_B_ABS, - [BPF_LD|BPF_W|BPF_LEN] = BPF_S_LD_W_LEN, - [BPF_LD|BPF_W|BPF_IND] = BPF_S_LD_W_IND, - [BPF_LD|BPF_H|BPF_IND] = BPF_S_LD_H_IND, - [BPF_LD|BPF_B|BPF_IND] = BPF_S_LD_B_IND, - [BPF_LD|BPF_IMM] = BPF_S_LD_IMM, - [BPF_LDX|BPF_W|BPF_LEN] = BPF_S_LDX_W_LEN, - [BPF_LDX|BPF_B|BPF_MSH] = BPF_S_LDX_B_MSH, - [BPF_LDX|BPF_IMM] = BPF_S_LDX_IMM, - [BPF_MISC|BPF_TAX] = BPF_S_MISC_TAX, - [BPF_MISC|BPF_TXA] = BPF_S_MISC_TXA, - [BPF_RET|BPF_K] = BPF_S_RET_K, - [BPF_RET|BPF_A] = BPF_S_RET_A, - [BPF_ALU|BPF_DIV|BPF_K] = BPF_S_ALU_DIV_K, - [BPF_LD|BPF_MEM] = BPF_S_LD_MEM, - [BPF_LDX|BPF_MEM] = BPF_S_LDX_MEM, - [BPF_ST] = BPF_S_ST, - [BPF_STX] = BPF_S_STX, - [BPF_JMP|BPF_JA] = BPF_S_JMP_JA, - [BPF_JMP|BPF_JEQ|BPF_K] = BPF_S_JMP_JEQ_K, - [BPF_JMP|BPF_JEQ|BPF_X] = BPF_S_JMP_JEQ_X, - [BPF_JMP|BPF_JGE|BPF_K] = BPF_S_JMP_JGE_K, - [BPF_JMP|BPF_JGE|BPF_X] = BPF_S_JMP_JGE_X, - [BPF_JMP|BPF_JGT|BPF_K] = BPF_S_JMP_JGT_K, - [BPF_JMP|BPF_JGT|BPF_X] = BPF_S_JMP_JGT_X, - [BPF_JMP|BPF_JSET|BPF_K] = BPF_S_JMP_JSET_K, - [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X, - }; - int pc; bool anc_found; + int pc; if (flen == 0 || flen > BPF_MAXINSNS) return -EINVAL; - /* check the filter code now */ + /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { struct sock_filter *ftest = &filter[pc]; - u16 code = ftest->code; - if (code >= ARRAY_SIZE(codes)) - return -EINVAL; - code = codes[code]; - if (!code) + /* May we actually operate on this code? */ + if (!chk_code_allowed(ftest->code)) return -EINVAL; + /* Some instructions need special checks */ - switch (code) { - case BPF_S_ALU_DIV_K: - case BPF_S_ALU_MOD_K: - /* check for division by zero */ + switch (ftest->code) { + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_MOD | BPF_K: + /* Check for division by zero */ if (ftest->k == 0) return -EINVAL; break; - case BPF_S_LD_MEM: - case BPF_S_LDX_MEM: - case BPF_S_ST: - case BPF_S_STX: - /* check for invalid memory addresses */ + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + case BPF_ST: + case BPF_STX: + /* Check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; break; - case BPF_S_JMP_JA: - /* - * Note, the large ftest->k might cause loops. + case BPF_JMP | BPF_JA: + /* Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ - if (ftest->k >= (unsigned int)(flen-pc-1)) + if (ftest->k >= (unsigned int)(flen - pc - 1)) return -EINVAL; break; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JSET_X: - case BPF_S_JMP_JSET_K: - /* for conditionals both must be safe */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: anc_found = false; -#define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ - code = BPF_S_ANC_##CODE; \ - anc_found = true; \ - break - switch (ftest->k) { - ANCILLARY(PROTOCOL); - ANCILLARY(PKTTYPE); - ANCILLARY(IFINDEX); - ANCILLARY(NLATTR); - ANCILLARY(NLATTR_NEST); - ANCILLARY(MARK); - ANCILLARY(QUEUE); - ANCILLARY(HATYPE); - ANCILLARY(RXHASH); - ANCILLARY(CPU); - ANCILLARY(ALU_XOR_X); - ANCILLARY(VLAN_TAG); - ANCILLARY(VLAN_TAG_PRESENT); - ANCILLARY(PAY_OFFSET); - ANCILLARY(RANDOM); - } - - /* ancillary operation unknown or unsupported */ + if (bpf_anc_helper(ftest) & BPF_ANC) + anc_found = true; + /* Ancillary operation unknown or unsupported */ if (anc_found == false && ftest->k >= SKF_AD_OFF) return -EINVAL; } - ftest->code = code; } - /* last instruction must be a RET code */ + /* Last instruction must be a RET code */ switch (filter[flen - 1].code) { - case BPF_S_RET_K: - case BPF_S_RET_A: + case BPF_RET | BPF_K: + case BPF_RET | BPF_A: return check_load_and_stores(filter, flen); } + return -EINVAL; } EXPORT_SYMBOL(sk_chk_filter); @@ -1397,7 +1335,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu) struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); sk_release_orig_filter(fp); - bpf_jit_free(fp); + sk_filter_free(fp); } /** @@ -1452,7 +1390,7 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, { struct sock_filter *old_prog; struct sk_filter *old_fp; - int i, err, new_len, old_len = fp->len; + int err, new_len, old_len = fp->len; /* We are free to overwrite insns et al right here as it * won't be used at this point in time anymore internally @@ -1462,13 +1400,6 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, BUILD_BUG_ON(sizeof(struct sock_filter) != sizeof(struct sock_filter_int)); - /* For now, we need to unfiddle BPF_S_* identifiers in place. - * This can sooner or later on be subject to removal, e.g. when - * JITs have been converted. - */ - for (i = 0; i < fp->len; i++) - sk_decode_filter(&fp->insns[i], &fp->insns[i]); - /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. @@ -1497,7 +1428,6 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, goto out_err_free; } - fp->bpf_func = sk_run_filter_int_skb; fp->len = new_len; /* 2nd pass: remap sock_filter insns into sock_filter_int insns. */ @@ -1510,6 +1440,8 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, */ goto out_err_free; + sk_filter_select_runtime(fp); + kfree(old_prog); return fp; @@ -1524,6 +1456,33 @@ out_err: return ERR_PTR(err); } +void __weak bpf_int_jit_compile(struct sk_filter *prog) +{ +} + +/** + * sk_filter_select_runtime - select execution runtime for BPF program + * @fp: sk_filter populated with internal BPF program + * + * try to JIT internal BPF program, if JIT is not available select interpreter + * BPF program will be executed via SK_RUN_FILTER() macro + */ +void sk_filter_select_runtime(struct sk_filter *fp) +{ + fp->bpf_func = (void *) __sk_run_filter; + + /* Probe if internal BPF can be JITed */ + bpf_int_jit_compile(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_select_runtime); + +/* free internal BPF program */ +void sk_filter_free(struct sk_filter *fp) +{ + bpf_jit_free(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_free); + static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, struct sock *sk) { @@ -1561,7 +1520,7 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, * a negative errno code is returned. On success the return is zero. */ int sk_unattached_filter_create(struct sk_filter **pfp, - struct sock_fprog *fprog) + struct sock_fprog_kern *fprog) { unsigned int fsize = sk_filter_proglen(fprog); struct sk_filter *fp; @@ -1682,84 +1641,6 @@ int sk_detach_filter(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_detach_filter); -void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) -{ - static const u16 decodes[] = { - [BPF_S_ALU_ADD_K] = BPF_ALU|BPF_ADD|BPF_K, - [BPF_S_ALU_ADD_X] = BPF_ALU|BPF_ADD|BPF_X, - [BPF_S_ALU_SUB_K] = BPF_ALU|BPF_SUB|BPF_K, - [BPF_S_ALU_SUB_X] = BPF_ALU|BPF_SUB|BPF_X, - [BPF_S_ALU_MUL_K] = BPF_ALU|BPF_MUL|BPF_K, - [BPF_S_ALU_MUL_X] = BPF_ALU|BPF_MUL|BPF_X, - [BPF_S_ALU_DIV_X] = BPF_ALU|BPF_DIV|BPF_X, - [BPF_S_ALU_MOD_K] = BPF_ALU|BPF_MOD|BPF_K, - [BPF_S_ALU_MOD_X] = BPF_ALU|BPF_MOD|BPF_X, - [BPF_S_ALU_AND_K] = BPF_ALU|BPF_AND|BPF_K, - [BPF_S_ALU_AND_X] = BPF_ALU|BPF_AND|BPF_X, - [BPF_S_ALU_OR_K] = BPF_ALU|BPF_OR|BPF_K, - [BPF_S_ALU_OR_X] = BPF_ALU|BPF_OR|BPF_X, - [BPF_S_ALU_XOR_K] = BPF_ALU|BPF_XOR|BPF_K, - [BPF_S_ALU_XOR_X] = BPF_ALU|BPF_XOR|BPF_X, - [BPF_S_ALU_LSH_K] = BPF_ALU|BPF_LSH|BPF_K, - [BPF_S_ALU_LSH_X] = BPF_ALU|BPF_LSH|BPF_X, - [BPF_S_ALU_RSH_K] = BPF_ALU|BPF_RSH|BPF_K, - [BPF_S_ALU_RSH_X] = BPF_ALU|BPF_RSH|BPF_X, - [BPF_S_ALU_NEG] = BPF_ALU|BPF_NEG, - [BPF_S_LD_W_ABS] = BPF_LD|BPF_W|BPF_ABS, - [BPF_S_LD_H_ABS] = BPF_LD|BPF_H|BPF_ABS, - [BPF_S_LD_B_ABS] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_PROTOCOL] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_PKTTYPE] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_IFINDEX] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_NLATTR] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_NLATTR_NEST] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_MARK] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_QUEUE] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_HATYPE] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_RXHASH] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_CPU] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_ALU_XOR_X] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_PAY_OFFSET] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_RANDOM] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_LD_W_LEN] = BPF_LD|BPF_W|BPF_LEN, - [BPF_S_LD_W_IND] = BPF_LD|BPF_W|BPF_IND, - [BPF_S_LD_H_IND] = BPF_LD|BPF_H|BPF_IND, - [BPF_S_LD_B_IND] = BPF_LD|BPF_B|BPF_IND, - [BPF_S_LD_IMM] = BPF_LD|BPF_IMM, - [BPF_S_LDX_W_LEN] = BPF_LDX|BPF_W|BPF_LEN, - [BPF_S_LDX_B_MSH] = BPF_LDX|BPF_B|BPF_MSH, - [BPF_S_LDX_IMM] = BPF_LDX|BPF_IMM, - [BPF_S_MISC_TAX] = BPF_MISC|BPF_TAX, - [BPF_S_MISC_TXA] = BPF_MISC|BPF_TXA, - [BPF_S_RET_K] = BPF_RET|BPF_K, - [BPF_S_RET_A] = BPF_RET|BPF_A, - [BPF_S_ALU_DIV_K] = BPF_ALU|BPF_DIV|BPF_K, - [BPF_S_LD_MEM] = BPF_LD|BPF_MEM, - [BPF_S_LDX_MEM] = BPF_LDX|BPF_MEM, - [BPF_S_ST] = BPF_ST, - [BPF_S_STX] = BPF_STX, - [BPF_S_JMP_JA] = BPF_JMP|BPF_JA, - [BPF_S_JMP_JEQ_K] = BPF_JMP|BPF_JEQ|BPF_K, - [BPF_S_JMP_JEQ_X] = BPF_JMP|BPF_JEQ|BPF_X, - [BPF_S_JMP_JGE_K] = BPF_JMP|BPF_JGE|BPF_K, - [BPF_S_JMP_JGE_X] = BPF_JMP|BPF_JGE|BPF_X, - [BPF_S_JMP_JGT_K] = BPF_JMP|BPF_JGT|BPF_K, - [BPF_S_JMP_JGT_X] = BPF_JMP|BPF_JGT|BPF_X, - [BPF_S_JMP_JSET_K] = BPF_JMP|BPF_JSET|BPF_K, - [BPF_S_JMP_JSET_X] = BPF_JMP|BPF_JSET|BPF_X, - }; - u16 code; - - code = filt->code; - - to->code = decodes[code]; - to->jt = filt->jt; - to->jf = filt->jf; - to->k = filt->k; -} - int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8f8a96e..32d872e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1248,8 +1248,8 @@ void __neigh_set_probe_once(struct neighbour *neigh) neigh->updated = jiffies; if (!(neigh->nud_state & NUD_FAILED)) return; - neigh->nud_state = NUD_PROBE; - atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); + neigh->nud_state = NUD_INCOMPLETE; + atomic_set(&neigh->probes, neigh_max_probes(neigh)); neigh_add_timer(neigh, jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 05e949d..85b6269 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -24,7 +24,7 @@ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; -static DEFINE_MUTEX(net_mutex); +DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 0304f98..fc17a9d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -573,7 +573,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) is_zero_ether_addr(pkt_dev->src_mac) ? pkt_dev->odev->dev_addr : pkt_dev->src_mac); - seq_printf(seq, "dst_mac: "); + seq_puts(seq, "dst_mac: "); seq_printf(seq, "%pM\n", pkt_dev->dst_mac); seq_printf(seq, @@ -588,7 +588,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->nr_labels) { unsigned int i; - seq_printf(seq, " mpls: "); + seq_puts(seq, " mpls: "); for (i = 0; i < pkt_dev->nr_labels; i++) seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]), i == pkt_dev->nr_labels-1 ? "\n" : ", "); @@ -613,67 +613,67 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->node >= 0) seq_printf(seq, " node: %d\n", pkt_dev->node); - seq_printf(seq, " Flags: "); + seq_puts(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) - seq_printf(seq, "IPV6 "); + seq_puts(seq, "IPV6 "); if (pkt_dev->flags & F_IPSRC_RND) - seq_printf(seq, "IPSRC_RND "); + seq_puts(seq, "IPSRC_RND "); if (pkt_dev->flags & F_IPDST_RND) - seq_printf(seq, "IPDST_RND "); + seq_puts(seq, "IPDST_RND "); if (pkt_dev->flags & F_TXSIZE_RND) - seq_printf(seq, "TXSIZE_RND "); + seq_puts(seq, "TXSIZE_RND "); if (pkt_dev->flags & F_UDPSRC_RND) - seq_printf(seq, "UDPSRC_RND "); + seq_puts(seq, "UDPSRC_RND "); if (pkt_dev->flags & F_UDPDST_RND) - seq_printf(seq, "UDPDST_RND "); + seq_puts(seq, "UDPDST_RND "); if (pkt_dev->flags & F_UDPCSUM) - seq_printf(seq, "UDPCSUM "); + seq_puts(seq, "UDPCSUM "); if (pkt_dev->flags & F_MPLS_RND) - seq_printf(seq, "MPLS_RND "); + seq_puts(seq, "MPLS_RND "); if (pkt_dev->flags & F_QUEUE_MAP_RND) - seq_printf(seq, "QUEUE_MAP_RND "); + seq_puts(seq, "QUEUE_MAP_RND "); if (pkt_dev->flags & F_QUEUE_MAP_CPU) - seq_printf(seq, "QUEUE_MAP_CPU "); + seq_puts(seq, "QUEUE_MAP_CPU "); if (pkt_dev->cflows) { if (pkt_dev->flags & F_FLOW_SEQ) - seq_printf(seq, "FLOW_SEQ "); /*in sequence flows*/ + seq_puts(seq, "FLOW_SEQ "); /*in sequence flows*/ else - seq_printf(seq, "FLOW_RND "); + seq_puts(seq, "FLOW_RND "); } #ifdef CONFIG_XFRM if (pkt_dev->flags & F_IPSEC_ON) { - seq_printf(seq, "IPSEC "); + seq_puts(seq, "IPSEC "); if (pkt_dev->spi) seq_printf(seq, "spi:%u", pkt_dev->spi); } #endif if (pkt_dev->flags & F_MACSRC_RND) - seq_printf(seq, "MACSRC_RND "); + seq_puts(seq, "MACSRC_RND "); if (pkt_dev->flags & F_MACDST_RND) - seq_printf(seq, "MACDST_RND "); + seq_puts(seq, "MACDST_RND "); if (pkt_dev->flags & F_VID_RND) - seq_printf(seq, "VID_RND "); + seq_puts(seq, "VID_RND "); if (pkt_dev->flags & F_SVID_RND) - seq_printf(seq, "SVID_RND "); + seq_puts(seq, "SVID_RND "); if (pkt_dev->flags & F_NODE) - seq_printf(seq, "NODE_ALLOC "); + seq_puts(seq, "NODE_ALLOC "); seq_puts(seq, "\n"); @@ -716,7 +716,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->result[0]) seq_printf(seq, "Result: %s\n", pkt_dev->result); else - seq_printf(seq, "Result: Idle\n"); + seq_puts(seq, "Result: Idle\n"); return 0; } @@ -1735,14 +1735,14 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) BUG_ON(!t); - seq_printf(seq, "Running: "); + seq_puts(seq, "Running: "); if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) seq_printf(seq, "%s ", pkt_dev->odevname); - seq_printf(seq, "\nStopped: "); + seq_puts(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) @@ -1751,7 +1751,7 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); else - seq_printf(seq, "\nResult: NA\n"); + seq_puts(seq, "\nResult: NA\n"); if_unlock(t); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index 37d8615..d3027a7 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -133,7 +133,7 @@ void __init ptp_classifier_init(void) { 0x16, 0, 0, 0x00000000 }, { 0x06, 0, 0, 0x00000000 }, }; - struct sock_fprog ptp_prog = { + struct sock_fprog_kern ptp_prog = { .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter, }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9837beb..f31268d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops) } EXPORT_SYMBOL_GPL(__rtnl_link_unregister); +/* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace. + */ +static void rtnl_lock_unregistering_all(void) +{ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + for_each_net(net) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + /** * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister */ void rtnl_link_unregister(struct rtnl_link_ops *ops) { - rtnl_lock(); + /* Close the race with cleanup_net() */ + mutex_lock(&net_mutex); + rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); + mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); @@ -767,8 +798,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, size += num_vfs * (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + - nla_total_size(sizeof(struct ifla_vf_tx_rate)) + - nla_total_size(sizeof(struct ifla_vf_spoofchk))); + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_rate))); return size; } else return 0; @@ -1034,6 +1065,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct ifla_vf_info ivi; struct ifla_vf_mac vf_mac; struct ifla_vf_vlan vf_vlan; + struct ifla_vf_rate vf_rate; struct ifla_vf_tx_rate vf_tx_rate; struct ifla_vf_spoofchk vf_spoofchk; struct ifla_vf_link_state vf_linkstate; @@ -1054,6 +1086,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, break; vf_mac.vf = vf_vlan.vf = + vf_rate.vf = vf_tx_rate.vf = vf_spoofchk.vf = vf_linkstate.vf = ivi.vf; @@ -1061,7 +1094,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; - vf_tx_rate.rate = ivi.tx_rate; + vf_tx_rate.rate = ivi.max_tx_rate; + vf_rate.min_tx_rate = ivi.min_tx_rate; + vf_rate.max_tx_rate = ivi.max_tx_rate; vf_spoofchk.setting = ivi.spoofchk; vf_linkstate.link_state = ivi.linkstate; vf = nla_nest_start(skb, IFLA_VF_INFO); @@ -1071,6 +1106,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, } if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || + nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), + &vf_rate) || nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate) || nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), @@ -1177,6 +1214,8 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { .len = sizeof(struct ifla_vf_tx_rate) }, [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_rate) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1336,11 +1375,29 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) } case IFLA_VF_TX_RATE: { struct ifla_vf_tx_rate *ivt; + struct ifla_vf_info ivf; + ivt = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_get_vf_config) + err = ops->ndo_get_vf_config(dev, ivt->vf, + &ivf); + if (err) + break; + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivf.min_tx_rate, + ivt->rate); + break; + } + case IFLA_VF_RATE: { + struct ifla_vf_rate *ivt; ivt = nla_data(vf); err = -EOPNOTSUPP; - if (ops->ndo_set_vf_tx_rate) - err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, - ivt->rate); + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivt->min_tx_rate, + ivt->max_tx_rate); break; } case IFLA_VF_SPOOFCHK: { diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 897da56..ba71212 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -__u32 secure_ip_id(__be32 daddr) -{ - u32 hash[MD5_DIGEST_WORDS]; - - net_secret_init(); - hash[0] = (__force __u32) daddr; - hash[1] = net_secret[13]; - hash[2] = net_secret[14]; - hash[3] = net_secret[15]; - - md5_transform(hash, net_secret); - - return hash[0]; -} - -__u32 secure_ipv6_id(const __be32 daddr[4]) -{ - __u32 hash[4]; - - net_secret_init(); - memcpy(hash, daddr, 16); - md5_transform(hash, net_secret); - - return hash[0]; -} __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3d74530..3f6c7e8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3076,7 +3076,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) if (unlikely(p->len + len >= 65536)) return -E2BIG; - lp = NAPI_GRO_CB(p)->last ?: p; + lp = NAPI_GRO_CB(p)->last; pinfo = skb_shinfo(lp); if (headlen <= offset) { @@ -3192,7 +3192,7 @@ merge: __skb_pull(skb, offset); - if (!NAPI_GRO_CB(p)->last) + if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; diff --git a/net/core/sock.c b/net/core/sock.c index 664ee42..026e01f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -784,7 +784,7 @@ set_rcvbuf: break; case SO_NO_CHECK: - sk->sk_no_check = valbool; + sk->sk_no_check_tx = valbool; break; case SO_PRIORITY: @@ -1064,7 +1064,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_NO_CHECK: - v.val = sk->sk_no_check; + v.val = sk->sk_no_check_tx; break; case SO_PRIORITY: diff --git a/net/core/tso.c b/net/core/tso.c new file mode 100644 index 0000000..8c3203c --- /dev/null +++ b/net/core/tso.c @@ -0,0 +1,77 @@ +#include <linux/export.h> +#include <net/ip.h> +#include <net/tso.h> + +/* Calculate expected number of TX descriptors */ +int tso_count_descs(struct sk_buff *skb) +{ + /* The Marvell Way */ + return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags; +} +EXPORT_SYMBOL(tso_count_descs); + +void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso, + int size, bool is_last) +{ + struct iphdr *iph; + struct tcphdr *tcph; + int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + int mac_hdr_len = skb_network_offset(skb); + + memcpy(hdr, skb->data, hdr_len); + iph = (struct iphdr *)(hdr + mac_hdr_len); + iph->id = htons(tso->ip_id); + iph->tot_len = htons(size + hdr_len - mac_hdr_len); + tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb)); + tcph->seq = htonl(tso->tcp_seq); + tso->ip_id++; + + if (!is_last) { + /* Clear all special flags for not last packet */ + tcph->psh = 0; + tcph->fin = 0; + tcph->rst = 0; + } +} +EXPORT_SYMBOL(tso_build_hdr); + +void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size) +{ + tso->tcp_seq += size; + tso->size -= size; + tso->data += size; + + if ((tso->size == 0) && + (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; + + /* Move to next segment */ + tso->size = frag->size; + tso->data = page_address(frag->page.p) + frag->page_offset; + tso->next_frag_idx++; + } +} +EXPORT_SYMBOL(tso_build_data); + +void tso_start(struct sk_buff *skb, struct tso_t *tso) +{ + int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + + tso->ip_id = ntohs(ip_hdr(skb)->id); + tso->tcp_seq = ntohl(tcp_hdr(skb)->seq); + tso->next_frag_idx = 0; + + /* Build first data */ + tso->size = skb_headlen(skb) - hdr_len; + tso->data = skb->data + hdr_len; + if ((tso->size == 0) && + (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; + + /* Move to next segment */ + tso->size = frag->size; + tso->data = page_address(frag->page.p) + frag->page_offset; + tso->next_frag_idx++; + } +} +EXPORT_SYMBOL(tso_start); diff --git a/net/core/utils.c b/net/core/utils.c index 2f737bf..eed3433 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w) { struct __net_random_once_work *work = container_of(w, struct __net_random_once_work, work); - if (!static_key_enabled(work->key)) - static_key_slow_inc(work->key); + BUG_ON(!static_key_enabled(work->key)); + static_key_slow_dec(work->key); kfree(work); } @@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key) } bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *done_key) + struct static_key *once_key) { static DEFINE_SPINLOCK(lock); unsigned long flags; @@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done, *done = true; spin_unlock_irqrestore(&lock, flags); - __net_random_once_disable_jump(done_key); + __net_random_once_disable_jump(once_key); return true; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 22b5d81..6ca645c 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1024,7 +1024,6 @@ static struct inet_protosw dccp_v4_protosw = { .protocol = IPPROTO_DCCP, .prot = &dccp_v4_prot, .ops = &inet_dccp_ops, - .no_check = 0, .flags = INET_PROTOSW_ICSK, }; diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 16f0b22..1cd46a3 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -280,7 +280,7 @@ static ktime_t dccp_timestamp_seed; */ u32 dccp_timestamp(void) { - s64 delta = ktime_us_delta(ktime_get_real(), dccp_timestamp_seed); + u64 delta = (u64)ktime_us_delta(ktime_get_real(), dccp_timestamp_seed); do_div(delta, 10); return delta; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 4c04848..ae011b4 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -481,7 +481,7 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf sk->sk_backlog_rcv = dn_nsp_backlog_rcv; sk->sk_destruct = dn_destruct; - sk->sk_no_check = 1; + sk->sk_no_check_tx = 1; sk->sk_family = PF_DECnet; sk->sk_protocol = 0; sk->sk_allocation = gfp; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 0eb5d5e..5db37ce 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -406,8 +406,9 @@ static int dsa_of_probe(struct platform_device *pdev) goto out_free; } - chip_index = 0; + chip_index = -1; for_each_available_child_of_node(np, child) { + chip_index++; cd = &pd->chip[chip_index]; cd->mii_bus = &mdio_bus->dev; diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c index 0f5a69e..fe6bd7a 100644 --- a/net/ieee802154/6lowpan_rtnl.c +++ b/net/ieee802154/6lowpan_rtnl.c @@ -92,6 +92,7 @@ static int lowpan_header_create(struct sk_buff *skb, const u8 *saddr = _saddr; const u8 *daddr = _daddr; struct ieee802154_addr sa, da; + struct ieee802154_mac_cb *cb = mac_cb_init(skb); /* TODO: * if this package isn't ipv6 one, where should it be routed? @@ -115,8 +116,7 @@ static int lowpan_header_create(struct sk_buff *skb, * from MAC subif of the 'dev' and 'real_dev' network devices, but * this isn't implemented in mainline yet, so currently we assign 0xff */ - mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA; - mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev); + cb->type = IEEE802154_FC_TYPE_DATA; /* prepare wpan address data */ sa.mode = IEEE802154_ADDR_LONG; @@ -135,11 +135,10 @@ static int lowpan_header_create(struct sk_buff *skb, } else { da.mode = IEEE802154_ADDR_LONG; da.extended_addr = ieee802154_devaddr_from_raw(daddr); - - /* request acknowledgment */ - mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; } + cb->ackreq = !lowpan_is_addr_broadcast(daddr); + return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, type, (void *)&da, (void *)&sa, 0); } @@ -221,139 +220,149 @@ static int lowpan_set_address(struct net_device *dev, void *p) return 0; } -static int -lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, - int mlen, int plen, int offset, int type) +static struct sk_buff* +lowpan_alloc_frag(struct sk_buff *skb, int size, + const struct ieee802154_hdr *master_hdr) { + struct net_device *real_dev = lowpan_dev_info(skb->dev)->real_dev; struct sk_buff *frag; - int hlen; - - hlen = (type == LOWPAN_DISPATCH_FRAG1) ? - LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE; - - raw_dump_inline(__func__, "6lowpan fragment header", head, hlen); + int rc; + + frag = alloc_skb(real_dev->hard_header_len + + real_dev->needed_tailroom + size, + GFP_ATOMIC); + + if (likely(frag)) { + frag->dev = real_dev; + frag->priority = skb->priority; + skb_reserve(frag, real_dev->hard_header_len); + skb_reset_network_header(frag); + *mac_cb(frag) = *mac_cb(skb); + + rc = dev_hard_header(frag, real_dev, 0, &master_hdr->dest, + &master_hdr->source, size); + if (rc < 0) { + kfree_skb(frag); + return ERR_PTR(-rc); + } + } else { + frag = ERR_PTR(ENOMEM); + } - frag = netdev_alloc_skb(skb->dev, - hlen + mlen + plen + IEEE802154_MFR_SIZE); - if (!frag) - return -ENOMEM; + return frag; +} - frag->priority = skb->priority; +static int +lowpan_xmit_fragment(struct sk_buff *skb, const struct ieee802154_hdr *wpan_hdr, + u8 *frag_hdr, int frag_hdrlen, + int offset, int len) +{ + struct sk_buff *frag; - /* copy header, MFR and payload */ - skb_put(frag, mlen); - skb_copy_to_linear_data(frag, skb_mac_header(skb), mlen); + raw_dump_inline(__func__, " fragment header", frag_hdr, frag_hdrlen); - skb_put(frag, hlen); - skb_copy_to_linear_data_offset(frag, mlen, head, hlen); + frag = lowpan_alloc_frag(skb, frag_hdrlen + len, wpan_hdr); + if (IS_ERR(frag)) + return -PTR_ERR(frag); - skb_put(frag, plen); - skb_copy_to_linear_data_offset(frag, mlen + hlen, - skb_network_header(skb) + offset, plen); + memcpy(skb_put(frag, frag_hdrlen), frag_hdr, frag_hdrlen); + memcpy(skb_put(frag, len), skb_network_header(skb) + offset, len); - raw_dump_table(__func__, " raw fragment dump", frag->data, frag->len); + raw_dump_table(__func__, " fragment dump", frag->data, frag->len); return dev_queue_xmit(frag); } static int -lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev) +lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *dev, + const struct ieee802154_hdr *wpan_hdr) { - int err; - u16 dgram_offset, dgram_size, payload_length, header_length, - lowpan_size, frag_plen, offset; - __be16 tag; - u8 head[5]; - - header_length = skb->mac_len; - payload_length = skb->len - header_length; - tag = lowpan_dev_info(dev)->fragment_tag++; - lowpan_size = skb_network_header_len(skb); + u16 dgram_size, dgram_offset; + __be16 frag_tag; + u8 frag_hdr[5]; + int frag_cap, frag_len, payload_cap, rc; + int skb_unprocessed, skb_offset; + dgram_size = lowpan_uncompress_size(skb, &dgram_offset) - - header_length; + skb->mac_len; + frag_tag = lowpan_dev_info(dev)->fragment_tag++; - /* first fragment header */ - head[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x7); - head[1] = dgram_size & 0xff; - memcpy(head + 2, &tag, sizeof(tag)); + frag_hdr[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x07); + frag_hdr[1] = dgram_size & 0xff; + memcpy(frag_hdr + 2, &frag_tag, sizeof(frag_tag)); - /* calc the nearest payload length(divided to 8) for first fragment - * which fits into a IEEE802154_MTU - */ - frag_plen = round_down(IEEE802154_MTU - header_length - - LOWPAN_FRAG1_HEAD_SIZE - lowpan_size - - IEEE802154_MFR_SIZE, 8); - - err = lowpan_fragment_xmit(skb, head, header_length, - frag_plen + lowpan_size, 0, - LOWPAN_DISPATCH_FRAG1); - if (err) { - pr_debug("%s unable to send FRAG1 packet (tag: %d)", - __func__, tag); - goto exit; - } + payload_cap = ieee802154_max_payload(wpan_hdr); - offset = lowpan_size + frag_plen; - dgram_offset += frag_plen; + frag_len = round_down(payload_cap - LOWPAN_FRAG1_HEAD_SIZE - + skb_network_header_len(skb), 8); - /* next fragment header */ - head[0] &= ~LOWPAN_DISPATCH_FRAG1; - head[0] |= LOWPAN_DISPATCH_FRAGN; + skb_offset = skb_network_header_len(skb); + skb_unprocessed = skb->len - skb->mac_len - skb_offset; - frag_plen = round_down(IEEE802154_MTU - header_length - - LOWPAN_FRAGN_HEAD_SIZE - IEEE802154_MFR_SIZE, 8); + rc = lowpan_xmit_fragment(skb, wpan_hdr, frag_hdr, + LOWPAN_FRAG1_HEAD_SIZE, 0, + frag_len + skb_network_header_len(skb)); + if (rc) { + pr_debug("%s unable to send FRAG1 packet (tag: %d)", + __func__, frag_tag); + goto err; + } - while (payload_length - offset > 0) { - int len = frag_plen; + frag_hdr[0] &= ~LOWPAN_DISPATCH_FRAG1; + frag_hdr[0] |= LOWPAN_DISPATCH_FRAGN; + frag_cap = round_down(payload_cap - LOWPAN_FRAGN_HEAD_SIZE, 8); - head[4] = dgram_offset >> 3; + do { + dgram_offset += frag_len; + skb_offset += frag_len; + skb_unprocessed -= frag_len; + frag_len = min(frag_cap, skb_unprocessed); - if (payload_length - offset < len) - len = payload_length - offset; + frag_hdr[4] = dgram_offset >> 3; - err = lowpan_fragment_xmit(skb, head, header_length, len, - offset, LOWPAN_DISPATCH_FRAGN); - if (err) { + rc = lowpan_xmit_fragment(skb, wpan_hdr, frag_hdr, + LOWPAN_FRAGN_HEAD_SIZE, skb_offset, + frag_len); + if (rc) { pr_debug("%s unable to send a FRAGN packet. (tag: %d, offset: %d)\n", - __func__, tag, offset); - goto exit; + __func__, frag_tag, skb_offset); + goto err; } + } while (skb_unprocessed > frag_cap); - offset += len; - dgram_offset += len; - } + consume_skb(skb); + return NET_XMIT_SUCCESS; -exit: - return err; +err: + kfree_skb(skb); + return rc; } static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) { - int err = -1; + struct ieee802154_hdr wpan_hdr; + int max_single; pr_debug("package xmit\n"); - skb->dev = lowpan_dev_info(dev)->real_dev; - if (skb->dev == NULL) { - pr_debug("ERROR: no real wpan device found\n"); - goto error; + if (ieee802154_hdr_peek(skb, &wpan_hdr) < 0) { + kfree_skb(skb); + return NET_XMIT_DROP; } - /* Send directly if less than the MTU minus the 2 checksum bytes. */ - if (skb->len <= IEEE802154_MTU - IEEE802154_MFR_SIZE) { - err = dev_queue_xmit(skb); - goto out; - } + max_single = ieee802154_max_payload(&wpan_hdr); - pr_debug("frame is too big, fragmentation is needed\n"); - err = lowpan_skb_fragmentation(skb, dev); -error: - dev_kfree_skb(skb); -out: - if (err) - pr_debug("ERROR: xmit failed\n"); + if (skb_tail_pointer(skb) - skb_network_header(skb) <= max_single) { + skb->dev = lowpan_dev_info(dev)->real_dev; + return dev_queue_xmit(skb); + } else { + netdev_tx_t rc; + + pr_debug("frame is too big, fragmentation is needed\n"); + rc = lowpan_xmit_fragmented(skb, dev, &wpan_hdr); - return (err < 0) ? NET_XMIT_DROP : err; + return rc < 0 ? NET_XMIT_DROP : rc; + } } static struct wpan_phy *lowpan_get_phy(const struct net_device *dev) diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 786437b..4f0ed87 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -21,6 +21,7 @@ * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> */ +#include <linux/capability.h> #include <linux/net.h> #include <linux/module.h> #include <linux/if_arp.h> @@ -45,7 +46,12 @@ struct dgram_sock { struct ieee802154_addr dst_addr; unsigned int bound:1; + unsigned int connected:1; unsigned int want_ack:1; + unsigned int secen:1; + unsigned int secen_override:1; + unsigned int seclevel:3; + unsigned int seclevel_override:1; }; static inline struct dgram_sock *dgram_sk(const struct sock *sk) @@ -73,10 +79,7 @@ static int dgram_init(struct sock *sk) { struct dgram_sock *ro = dgram_sk(sk); - ro->dst_addr.mode = IEEE802154_ADDR_LONG; - ro->dst_addr.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); ro->want_ack = 1; - memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN); return 0; } @@ -183,6 +186,7 @@ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr, } ieee802154_addr_from_sa(&ro->dst_addr, &addr->addr); + ro->connected = 1; out: release_sock(sk); @@ -194,10 +198,7 @@ static int dgram_disconnect(struct sock *sk, int flags) struct dgram_sock *ro = dgram_sk(sk); lock_sock(sk); - - ro->dst_addr.mode = IEEE802154_ADDR_LONG; - memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN); - + ro->connected = 0; release_sock(sk); return 0; @@ -209,7 +210,9 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, struct net_device *dev; unsigned int mtu; struct sk_buff *skb; + struct ieee802154_mac_cb *cb; struct dgram_sock *ro = dgram_sk(sk); + struct ieee802154_addr dst_addr; int hlen, tlen; int err; @@ -218,6 +221,11 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, return -EOPNOTSUPP; } + if (!ro->connected && !msg->msg_name) + return -EDESTADDRREQ; + else if (ro->connected && msg->msg_name) + return -EISCONN; + if (!ro->bound) dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154); else @@ -249,18 +257,28 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, skb_reset_network_header(skb); - mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA; - if (ro->want_ack) - mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; + cb = mac_cb_init(skb); + cb->type = IEEE802154_FC_TYPE_DATA; + cb->ackreq = ro->want_ack; + + if (msg->msg_name) { + DECLARE_SOCKADDR(struct sockaddr_ieee802154*, daddr, msg->msg_name); - mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev); - err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &ro->dst_addr, - ro->bound ? &ro->src_addr : NULL, size); + ieee802154_addr_from_sa(&dst_addr, &daddr->addr); + } else { + dst_addr = ro->dst_addr; + } + + cb->secen = ro->secen; + cb->secen_override = ro->secen_override; + cb->seclevel = ro->seclevel; + cb->seclevel_override = ro->seclevel_override; + + err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &dst_addr, + ro->bound ? &ro->src_addr : NULL, size); if (err < 0) goto out_skb; - skb_reset_mac_header(skb); - err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); if (err < 0) goto out_skb; @@ -419,6 +437,20 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname, case WPAN_WANTACK: val = ro->want_ack; break; + case WPAN_SECURITY: + if (!ro->secen_override) + val = WPAN_SECURITY_DEFAULT; + else if (ro->secen) + val = WPAN_SECURITY_ON; + else + val = WPAN_SECURITY_OFF; + break; + case WPAN_SECURITY_LEVEL: + if (!ro->seclevel_override) + val = WPAN_SECURITY_LEVEL_DEFAULT; + else + val = ro->seclevel; + break; default: return -ENOPROTOOPT; } @@ -434,6 +466,7 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct dgram_sock *ro = dgram_sk(sk); + struct net *net = sock_net(sk); int val; int err = 0; @@ -449,6 +482,47 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname, case WPAN_WANTACK: ro->want_ack = !!val; break; + case WPAN_SECURITY: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN) && + !ns_capable(net->user_ns, CAP_NET_RAW)) { + err = -EPERM; + break; + } + + switch (val) { + case WPAN_SECURITY_DEFAULT: + ro->secen_override = 0; + break; + case WPAN_SECURITY_ON: + ro->secen_override = 1; + ro->secen = 1; + break; + case WPAN_SECURITY_OFF: + ro->secen_override = 1; + ro->secen = 0; + break; + default: + err = -EINVAL; + break; + } + break; + case WPAN_SECURITY_LEVEL: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN) && + !ns_capable(net->user_ns, CAP_NET_RAW)) { + err = -EPERM; + break; + } + + if (val < WPAN_SECURITY_LEVEL_DEFAULT || + val > IEEE802154_SCF_SECLEVEL_ENC_MIC128) { + err = -EINVAL; + } else if (val == WPAN_SECURITY_LEVEL_DEFAULT) { + ro->seclevel_override = 0; + } else { + ro->seclevel_override = 1; + ro->seclevel = val; + } + break; default: err = -ENOPROTOOPT; break; diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c index bed42a4..c09294e 100644 --- a/net/ieee802154/header_ops.c +++ b/net/ieee802154/header_ops.c @@ -195,15 +195,16 @@ ieee802154_hdr_get_sechdr(const u8 *buf, struct ieee802154_sechdr *hdr) return pos; } +static int ieee802154_sechdr_lengths[4] = { + [IEEE802154_SCF_KEY_IMPLICIT] = 5, + [IEEE802154_SCF_KEY_INDEX] = 6, + [IEEE802154_SCF_KEY_SHORT_INDEX] = 10, + [IEEE802154_SCF_KEY_HW_INDEX] = 14, +}; + static int ieee802154_hdr_sechdr_len(u8 sc) { - switch (IEEE802154_SCF_KEY_ID_MODE(sc)) { - case IEEE802154_SCF_KEY_IMPLICIT: return 5; - case IEEE802154_SCF_KEY_INDEX: return 6; - case IEEE802154_SCF_KEY_SHORT_INDEX: return 10; - case IEEE802154_SCF_KEY_HW_INDEX: return 14; - default: return -EINVAL; - } + return ieee802154_sechdr_lengths[IEEE802154_SCF_KEY_ID_MODE(sc)]; } static int ieee802154_hdr_minlen(const struct ieee802154_hdr *hdr) @@ -285,3 +286,40 @@ ieee802154_hdr_peek_addrs(const struct sk_buff *skb, struct ieee802154_hdr *hdr) return pos; } EXPORT_SYMBOL_GPL(ieee802154_hdr_peek_addrs); + +int +ieee802154_hdr_peek(const struct sk_buff *skb, struct ieee802154_hdr *hdr) +{ + const u8 *buf = skb_mac_header(skb); + int pos; + + pos = ieee802154_hdr_peek_addrs(skb, hdr); + if (pos < 0) + return -EINVAL; + + if (hdr->fc.security_enabled) { + u8 key_id_mode = IEEE802154_SCF_KEY_ID_MODE(*(buf + pos)); + int want = pos + ieee802154_sechdr_lengths[key_id_mode]; + + if (buf + want > skb_tail_pointer(skb)) + return -EINVAL; + + pos += ieee802154_hdr_get_sechdr(buf + pos, &hdr->sec); + } + + return pos; +} +EXPORT_SYMBOL_GPL(ieee802154_hdr_peek); + +int ieee802154_max_payload(const struct ieee802154_hdr *hdr) +{ + int hlen = ieee802154_hdr_minlen(hdr); + + if (hdr->fc.security_enabled) { + hlen += ieee802154_sechdr_lengths[hdr->sec.key_id_mode] - 1; + hlen += ieee802154_sechdr_authtag_len(&hdr->sec); + } + + return IEEE802154_MTU - hlen - IEEE802154_MFR_SIZE; +} +EXPORT_SYMBOL_GPL(ieee802154_max_payload); diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h index 6693a5c..8b83a23 100644 --- a/net/ieee802154/ieee802154.h +++ b/net/ieee802154/ieee802154.h @@ -68,4 +68,23 @@ int ieee802154_list_iface(struct sk_buff *skb, struct genl_info *info); int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb); int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_setparams(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_add_key(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_del_key(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_dump_keys(struct sk_buff *skb, + struct netlink_callback *cb); +int ieee802154_llsec_add_dev(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_del_dev(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_dump_devs(struct sk_buff *skb, + struct netlink_callback *cb); +int ieee802154_llsec_add_devkey(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_del_devkey(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_dump_devkeys(struct sk_buff *skb, + struct netlink_callback *cb); +int ieee802154_llsec_add_seclevel(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_del_seclevel(struct sk_buff *skb, struct genl_info *info); +int ieee802154_llsec_dump_seclevels(struct sk_buff *skb, + struct netlink_callback *cb); + #endif diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 04b2058..26efcf4 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -124,6 +124,26 @@ static const struct genl_ops ieee8021154_ops[] = { IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface, ieee802154_dump_iface), IEEE802154_OP(IEEE802154_SET_MACPARAMS, ieee802154_set_macparams), + IEEE802154_OP(IEEE802154_LLSEC_GETPARAMS, ieee802154_llsec_getparams), + IEEE802154_OP(IEEE802154_LLSEC_SETPARAMS, ieee802154_llsec_setparams), + IEEE802154_DUMP(IEEE802154_LLSEC_LIST_KEY, NULL, + ieee802154_llsec_dump_keys), + IEEE802154_OP(IEEE802154_LLSEC_ADD_KEY, ieee802154_llsec_add_key), + IEEE802154_OP(IEEE802154_LLSEC_DEL_KEY, ieee802154_llsec_del_key), + IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEV, NULL, + ieee802154_llsec_dump_devs), + IEEE802154_OP(IEEE802154_LLSEC_ADD_DEV, ieee802154_llsec_add_dev), + IEEE802154_OP(IEEE802154_LLSEC_DEL_DEV, ieee802154_llsec_del_dev), + IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEVKEY, NULL, + ieee802154_llsec_dump_devkeys), + IEEE802154_OP(IEEE802154_LLSEC_ADD_DEVKEY, ieee802154_llsec_add_devkey), + IEEE802154_OP(IEEE802154_LLSEC_DEL_DEVKEY, ieee802154_llsec_del_devkey), + IEEE802154_DUMP(IEEE802154_LLSEC_LIST_SECLEVEL, NULL, + ieee802154_llsec_dump_seclevels), + IEEE802154_OP(IEEE802154_LLSEC_ADD_SECLEVEL, + ieee802154_llsec_add_seclevel), + IEEE802154_OP(IEEE802154_LLSEC_DEL_SECLEVEL, + ieee802154_llsec_del_seclevel), }; static const struct genl_multicast_group ieee802154_mcgrps[] = { diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 5d28549..a3281b8 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -715,3 +715,812 @@ out: dev_put(dev); return rc; } + + + +static int +ieee802154_llsec_parse_key_id(struct genl_info *info, + struct ieee802154_llsec_key_id *desc) +{ + memset(desc, 0, sizeof(*desc)); + + if (!info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]) + return -EINVAL; + + desc->mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]); + + if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) { + if (!info->attrs[IEEE802154_ATTR_PAN_ID] && + !(info->attrs[IEEE802154_ATTR_SHORT_ADDR] || + info->attrs[IEEE802154_ATTR_HW_ADDR])) + return -EINVAL; + + desc->device_addr.pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]); + + if (info->attrs[IEEE802154_ATTR_SHORT_ADDR]) { + desc->device_addr.mode = IEEE802154_ADDR_SHORT; + desc->device_addr.short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]); + } else { + desc->device_addr.mode = IEEE802154_ADDR_LONG; + desc->device_addr.extended_addr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); + } + } + + if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT && + !info->attrs[IEEE802154_ATTR_LLSEC_KEY_ID]) + return -EINVAL; + + if (desc->mode == IEEE802154_SCF_KEY_SHORT_INDEX && + !info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT]) + return -EINVAL; + + if (desc->mode == IEEE802154_SCF_KEY_HW_INDEX && + !info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED]) + return -EINVAL; + + if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT) + desc->id = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_ID]); + + switch (desc->mode) { + case IEEE802154_SCF_KEY_SHORT_INDEX: + { + u32 source = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT]); + desc->short_source = cpu_to_le32(source); + break; + } + case IEEE802154_SCF_KEY_HW_INDEX: + desc->extended_source = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED]); + break; + } + + return 0; +} + +static int +ieee802154_llsec_fill_key_id(struct sk_buff *msg, + const struct ieee802154_llsec_key_id *desc) +{ + if (nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_MODE, desc->mode)) + return -EMSGSIZE; + + if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) { + if (nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, + desc->device_addr.pan_id)) + return -EMSGSIZE; + + if (desc->device_addr.mode == IEEE802154_ADDR_SHORT && + nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, + desc->device_addr.short_addr)) + return -EMSGSIZE; + + if (desc->device_addr.mode == IEEE802154_ADDR_LONG && + nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, + desc->device_addr.extended_addr)) + return -EMSGSIZE; + } + + if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT && + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_ID, desc->id)) + return -EMSGSIZE; + + if (desc->mode == IEEE802154_SCF_KEY_SHORT_INDEX && + nla_put_u32(msg, IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT, + le32_to_cpu(desc->short_source))) + return -EMSGSIZE; + + if (desc->mode == IEEE802154_SCF_KEY_HW_INDEX && + nla_put_hwaddr(msg, IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED, + desc->extended_source)) + return -EMSGSIZE; + + return 0; +} + +int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + struct net_device *dev = NULL; + int rc = -ENOBUFS; + struct ieee802154_mlme_ops *ops; + void *hdr; + struct ieee802154_llsec_params params; + + pr_debug("%s\n", __func__); + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + ops = ieee802154_mlme_ops(dev); + if (!ops->llsec) { + rc = -EOPNOTSUPP; + goto out_dev; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + goto out_dev; + + hdr = genlmsg_put(msg, 0, info->snd_seq, &nl802154_family, 0, + IEEE802154_LLSEC_GETPARAMS); + if (!hdr) + goto out_free; + + rc = ops->llsec->get_params(dev, ¶ms); + if (rc < 0) + goto out_free; + + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_ENABLED, params.enabled) || + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVEL, params.out_level) || + nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, + be32_to_cpu(params.frame_counter)) || + ieee802154_llsec_fill_key_id(msg, ¶ms.out_key)) + goto out_free; + + dev_put(dev); + + return ieee802154_nl_reply(msg, info); +out_free: + nlmsg_free(msg); +out_dev: + dev_put(dev); + return rc; +} + +int ieee802154_llsec_setparams(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *dev = NULL; + int rc = -EINVAL; + struct ieee802154_mlme_ops *ops; + struct ieee802154_llsec_params params; + int changed = 0; + + pr_debug("%s\n", __func__); + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + if (!info->attrs[IEEE802154_ATTR_LLSEC_ENABLED] && + !info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE] && + !info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) + goto out; + + ops = ieee802154_mlme_ops(dev); + if (!ops->llsec) { + rc = -EOPNOTSUPP; + goto out; + } + + if (info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL] && + nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) > 7) + goto out; + + if (info->attrs[IEEE802154_ATTR_LLSEC_ENABLED]) { + params.enabled = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_ENABLED]); + changed |= IEEE802154_LLSEC_PARAM_ENABLED; + } + + if (info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]) { + if (ieee802154_llsec_parse_key_id(info, ¶ms.out_key)) + goto out; + + changed |= IEEE802154_LLSEC_PARAM_OUT_KEY; + } + + if (info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) { + params.out_level = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]); + changed |= IEEE802154_LLSEC_PARAM_OUT_LEVEL; + } + + if (info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]) { + u32 fc = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]); + + params.frame_counter = cpu_to_be32(fc); + changed |= IEEE802154_LLSEC_PARAM_FRAME_COUNTER; + } + + rc = ops->llsec->set_params(dev, ¶ms, changed); + + dev_put(dev); + + return rc; +out: + dev_put(dev); + return rc; +} + + + +struct llsec_dump_data { + struct sk_buff *skb; + int s_idx, s_idx2; + int portid; + int nlmsg_seq; + struct net_device *dev; + struct ieee802154_mlme_ops *ops; + struct ieee802154_llsec_table *table; +}; + +static int +ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb, + int (*step)(struct llsec_dump_data*)) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + struct llsec_dump_data data; + int idx = 0; + int first_dev = cb->args[0]; + int rc; + + for_each_netdev(net, dev) { + if (idx < first_dev || dev->type != ARPHRD_IEEE802154) + goto skip; + + data.ops = ieee802154_mlme_ops(dev); + if (!data.ops->llsec) + goto skip; + + data.skb = skb; + data.s_idx = cb->args[1]; + data.s_idx2 = cb->args[2]; + data.dev = dev; + data.portid = NETLINK_CB(cb->skb).portid; + data.nlmsg_seq = cb->nlh->nlmsg_seq; + + data.ops->llsec->lock_table(dev); + data.ops->llsec->get_table(data.dev, &data.table); + rc = step(&data); + data.ops->llsec->unlock_table(dev); + + if (rc < 0) + break; + +skip: + idx++; + } + cb->args[0] = idx; + + return skb->len; +} + +static int +ieee802154_nl_llsec_change(struct sk_buff *skb, struct genl_info *info, + int (*fn)(struct net_device*, struct genl_info*)) +{ + struct net_device *dev = NULL; + int rc = -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + if (!ieee802154_mlme_ops(dev)->llsec) + rc = -EOPNOTSUPP; + else + rc = fn(dev, info); + + dev_put(dev); + return rc; +} + + + +static int +ieee802154_llsec_parse_key(struct genl_info *info, + struct ieee802154_llsec_key *key) +{ + u8 frames; + u32 commands[256 / 32]; + + memset(key, 0, sizeof(*key)); + + if (!info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES] || + !info->attrs[IEEE802154_ATTR_LLSEC_KEY_BYTES]) + return -EINVAL; + + frames = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES]); + if ((frames & BIT(IEEE802154_FC_TYPE_MAC_CMD)) && + !info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS]) + return -EINVAL; + + if (info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS]) { + nla_memcpy(commands, + info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS], + 256 / 8); + + if (commands[0] || commands[1] || commands[2] || commands[3] || + commands[4] || commands[5] || commands[6] || + commands[7] >= BIT(IEEE802154_CMD_GTS_REQ + 1)) + return -EINVAL; + + key->cmd_frame_ids = commands[7]; + } + + key->frame_types = frames; + + nla_memcpy(key->key, info->attrs[IEEE802154_ATTR_LLSEC_KEY_BYTES], + IEEE802154_LLSEC_KEY_SIZE); + + return 0; +} + +static int llsec_add_key(struct net_device *dev, struct genl_info *info) +{ + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + struct ieee802154_llsec_key key; + struct ieee802154_llsec_key_id id; + + if (ieee802154_llsec_parse_key(info, &key) || + ieee802154_llsec_parse_key_id(info, &id)) + return -EINVAL; + + return ops->llsec->add_key(dev, &id, &key); +} + +int ieee802154_llsec_add_key(struct sk_buff *skb, struct genl_info *info) +{ + if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) != + (NLM_F_CREATE | NLM_F_EXCL)) + return -EINVAL; + + return ieee802154_nl_llsec_change(skb, info, llsec_add_key); +} + +static int llsec_remove_key(struct net_device *dev, struct genl_info *info) +{ + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + struct ieee802154_llsec_key_id id; + + if (ieee802154_llsec_parse_key_id(info, &id)) + return -EINVAL; + + return ops->llsec->del_key(dev, &id); +} + +int ieee802154_llsec_del_key(struct sk_buff *skb, struct genl_info *info) +{ + return ieee802154_nl_llsec_change(skb, info, llsec_remove_key); +} + +static int +ieee802154_nl_fill_key(struct sk_buff *msg, u32 portid, u32 seq, + const struct ieee802154_llsec_key_entry *key, + const struct net_device *dev) +{ + void *hdr; + u32 commands[256 / 32]; + + hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI, + IEEE802154_LLSEC_LIST_KEY); + if (!hdr) + goto out; + + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + ieee802154_llsec_fill_key_id(msg, &key->id) || + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES, + key->key->frame_types)) + goto nla_put_failure; + + if (key->key->frame_types & BIT(IEEE802154_FC_TYPE_MAC_CMD)) { + memset(commands, 0, sizeof(commands)); + commands[7] = key->key->cmd_frame_ids; + if (nla_put(msg, IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS, + sizeof(commands), commands)) + goto nla_put_failure; + } + + if (nla_put(msg, IEEE802154_ATTR_LLSEC_KEY_BYTES, + IEEE802154_LLSEC_KEY_SIZE, key->key->key)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +out: + return -EMSGSIZE; +} + +static int llsec_iter_keys(struct llsec_dump_data *data) +{ + struct ieee802154_llsec_key_entry *pos; + int rc = 0, idx = 0; + + list_for_each_entry(pos, &data->table->keys, list) { + if (idx++ < data->s_idx) + continue; + + if (ieee802154_nl_fill_key(data->skb, data->portid, + data->nlmsg_seq, pos, data->dev)) { + rc = -EMSGSIZE; + break; + } + + data->s_idx++; + } + + return rc; +} + +int ieee802154_llsec_dump_keys(struct sk_buff *skb, struct netlink_callback *cb) +{ + return ieee802154_llsec_dump_table(skb, cb, llsec_iter_keys); +} + + + +static int +llsec_parse_dev(struct genl_info *info, + struct ieee802154_llsec_device *dev) +{ + memset(dev, 0, sizeof(*dev)); + + if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] || + !info->attrs[IEEE802154_ATTR_HW_ADDR] || + !info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE] || + !info->attrs[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE] || + (!!info->attrs[IEEE802154_ATTR_PAN_ID] != + !!info->attrs[IEEE802154_ATTR_SHORT_ADDR])) + return -EINVAL; + + if (info->attrs[IEEE802154_ATTR_PAN_ID]) { + dev->pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]); + dev->short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]); + } else { + dev->short_addr = cpu_to_le16(IEEE802154_ADDR_UNDEF); + } + + dev->hwaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); + dev->frame_counter = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]); + dev->seclevel_exempt = !!nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]); + dev->key_mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE]); + + if (dev->key_mode >= __IEEE802154_LLSEC_DEVKEY_MAX) + return -EINVAL; + + return 0; +} + +static int llsec_add_dev(struct net_device *dev, struct genl_info *info) +{ + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + struct ieee802154_llsec_device desc; + + if (llsec_parse_dev(info, &desc)) + return -EINVAL; + + return ops->llsec->add_dev(dev, &desc); +} + +int ieee802154_llsec_add_dev(struct sk_buff *skb, struct genl_info *info) +{ + if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) != + (NLM_F_CREATE | NLM_F_EXCL)) + return -EINVAL; + + return ieee802154_nl_llsec_change(skb, info, llsec_add_dev); +} + +static int llsec_del_dev(struct net_device *dev, struct genl_info *info) +{ + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + __le64 devaddr; + + if (!info->attrs[IEEE802154_ATTR_HW_ADDR]) + return -EINVAL; + + devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); + + return ops->llsec->del_dev(dev, devaddr); +} + +int ieee802154_llsec_del_dev(struct sk_buff *skb, struct genl_info *info) +{ + return ieee802154_nl_llsec_change(skb, info, llsec_del_dev); +} + +static int +ieee802154_nl_fill_dev(struct sk_buff *msg, u32 portid, u32 seq, + const struct ieee802154_llsec_device *desc, + const struct net_device *dev) +{ + void *hdr; + + hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI, + IEEE802154_LLSEC_LIST_DEV); + if (!hdr) + goto out; + + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, desc->pan_id) || + nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, + desc->short_addr) || + nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, desc->hwaddr) || + nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, + desc->frame_counter) || + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_OVERRIDE, + desc->seclevel_exempt) || + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_KEY_MODE, desc->key_mode)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +out: + return -EMSGSIZE; +} + +static int llsec_iter_devs(struct llsec_dump_data *data) +{ + struct ieee802154_llsec_device *pos; + int rc = 0, idx = 0; + + list_for_each_entry(pos, &data->table->devices, list) { + if (idx++ < data->s_idx) + continue; + + if (ieee802154_nl_fill_dev(data->skb, data->portid, + data->nlmsg_seq, pos, data->dev)) { + rc = -EMSGSIZE; + break; + } + + data->s_idx++; + } + + return rc; +} + +int ieee802154_llsec_dump_devs(struct sk_buff *skb, struct netlink_callback *cb) +{ + return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devs); +} + + + +static int llsec_add_devkey(struct net_device *dev, struct genl_info *info) +{ + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + struct ieee802154_llsec_device_key key; + __le64 devaddr; + + if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] || + !info->attrs[IEEE802154_ATTR_HW_ADDR] || + ieee802154_llsec_parse_key_id(info, &key.key_id)) + return -EINVAL; + + devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); + key.frame_counter = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]); + + return ops->llsec->add_devkey(dev, devaddr, &key); +} + +int ieee802154_llsec_add_devkey(struct sk_buff *skb, struct genl_info *info) +{ + if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) != + (NLM_F_CREATE | NLM_F_EXCL)) + return -EINVAL; + + return ieee802154_nl_llsec_change(skb, info, llsec_add_devkey); +} + +static int llsec_del_devkey(struct net_device *dev, struct genl_info *info) +{ + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + struct ieee802154_llsec_device_key key; + __le64 devaddr; + + if (!info->attrs[IEEE802154_ATTR_HW_ADDR] || + ieee802154_llsec_parse_key_id(info, &key.key_id)) + return -EINVAL; + + devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); + + return ops->llsec->del_devkey(dev, devaddr, &key); +} + +int ieee802154_llsec_del_devkey(struct sk_buff *skb, struct genl_info *info) +{ + return ieee802154_nl_llsec_change(skb, info, llsec_del_devkey); +} + +static int +ieee802154_nl_fill_devkey(struct sk_buff *msg, u32 portid, u32 seq, + __le64 devaddr, + const struct ieee802154_llsec_device_key *devkey, + const struct net_device *dev) +{ + void *hdr; + + hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI, + IEEE802154_LLSEC_LIST_DEVKEY); + if (!hdr) + goto out; + + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, devaddr) || + nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, + devkey->frame_counter) || + ieee802154_llsec_fill_key_id(msg, &devkey->key_id)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +out: + return -EMSGSIZE; +} + +static int llsec_iter_devkeys(struct llsec_dump_data *data) +{ + struct ieee802154_llsec_device *dpos; + struct ieee802154_llsec_device_key *kpos; + int rc = 0, idx = 0, idx2; + + list_for_each_entry(dpos, &data->table->devices, list) { + if (idx++ < data->s_idx) + continue; + + idx2 = 0; + + list_for_each_entry(kpos, &dpos->keys, list) { + if (idx2++ < data->s_idx2) + continue; + + if (ieee802154_nl_fill_devkey(data->skb, data->portid, + data->nlmsg_seq, + dpos->hwaddr, kpos, + data->dev)) { + return rc = -EMSGSIZE; + } + + data->s_idx2++; + } + + data->s_idx++; + } + + return rc; +} + +int ieee802154_llsec_dump_devkeys(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devkeys); +} + + + +static int +llsec_parse_seclevel(struct genl_info *info, + struct ieee802154_llsec_seclevel *sl) +{ + memset(sl, 0, sizeof(*sl)); + + if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_TYPE] || + !info->attrs[IEEE802154_ATTR_LLSEC_SECLEVELS] || + !info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]) + return -EINVAL; + + sl->frame_type = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_TYPE]); + if (sl->frame_type == IEEE802154_FC_TYPE_MAC_CMD) { + if (!info->attrs[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID]) + return -EINVAL; + + sl->cmd_frame_id = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID]); + } + + sl->sec_levels = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVELS]); + sl->device_override = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]); + + return 0; +} + +static int llsec_add_seclevel(struct net_device *dev, struct genl_info *info) +{ + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + struct ieee802154_llsec_seclevel sl; + + if (llsec_parse_seclevel(info, &sl)) + return -EINVAL; + + return ops->llsec->add_seclevel(dev, &sl); +} + +int ieee802154_llsec_add_seclevel(struct sk_buff *skb, struct genl_info *info) +{ + if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) != + (NLM_F_CREATE | NLM_F_EXCL)) + return -EINVAL; + + return ieee802154_nl_llsec_change(skb, info, llsec_add_seclevel); +} + +static int llsec_del_seclevel(struct net_device *dev, struct genl_info *info) +{ + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + struct ieee802154_llsec_seclevel sl; + + if (llsec_parse_seclevel(info, &sl)) + return -EINVAL; + + return ops->llsec->del_seclevel(dev, &sl); +} + +int ieee802154_llsec_del_seclevel(struct sk_buff *skb, struct genl_info *info) +{ + return ieee802154_nl_llsec_change(skb, info, llsec_del_seclevel); +} + +static int +ieee802154_nl_fill_seclevel(struct sk_buff *msg, u32 portid, u32 seq, + const struct ieee802154_llsec_seclevel *sl, + const struct net_device *dev) +{ + void *hdr; + + hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI, + IEEE802154_LLSEC_LIST_SECLEVEL); + if (!hdr) + goto out; + + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || + nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_FRAME_TYPE, sl->frame_type) || + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVELS, sl->sec_levels) || + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_OVERRIDE, + sl->device_override)) + goto nla_put_failure; + + if (sl->frame_type == IEEE802154_FC_TYPE_MAC_CMD && + nla_put_u8(msg, IEEE802154_ATTR_LLSEC_CMD_FRAME_ID, + sl->cmd_frame_id)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +out: + return -EMSGSIZE; +} + +static int llsec_iter_seclevels(struct llsec_dump_data *data) +{ + struct ieee802154_llsec_seclevel *pos; + int rc = 0, idx = 0; + + list_for_each_entry(pos, &data->table->security_levels, list) { + if (idx++ < data->s_idx) + continue; + + if (ieee802154_nl_fill_seclevel(data->skb, data->portid, + data->nlmsg_seq, pos, + data->dev)) { + rc = -EMSGSIZE; + break; + } + + data->s_idx++; + } + + return rc; +} + +int ieee802154_llsec_dump_seclevels(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return ieee802154_llsec_dump_table(skb, cb, llsec_iter_seclevels); +} diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index fd7be5e..3a703ab8 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -62,5 +62,21 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_CSMA_MAX_BE] = { .type = NLA_U8, }, [IEEE802154_ATTR_FRAME_RETRIES] = { .type = NLA_S8, }, + + [IEEE802154_ATTR_LLSEC_ENABLED] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_SECLEVEL] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_KEY_MODE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT] = { .type = NLA_U32, }, + [IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED] = { .type = NLA_HW_ADDR, }, + [IEEE802154_ATTR_LLSEC_KEY_ID] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_FRAME_COUNTER] = { .type = NLA_U32 }, + [IEEE802154_ATTR_LLSEC_KEY_BYTES] = { .len = 16, }, + [IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS] = { .len = 258 / 8 }, + [IEEE802154_ATTR_LLSEC_FRAME_TYPE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_CMD_FRAME_ID] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_SECLEVELS] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_DEV_OVERRIDE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_LLSEC_DEV_KEY_MODE] = { .type = NLA_U8, }, }; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 279132b..0e9bb08 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -254,7 +254,6 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, struct inet_sock *inet; struct proto *answer_prot; unsigned char answer_flags; - char answer_no_check; int try_loading_module = 0; int err; @@ -312,7 +311,6 @@ lookup_protocol: sock->ops = answer->ops; answer_prot = answer->prot; - answer_no_check = answer->no_check; answer_flags = answer->flags; rcu_read_unlock(); @@ -324,7 +322,6 @@ lookup_protocol: goto out; err = 0; - sk->sk_no_check = answer_no_check; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; @@ -1002,7 +999,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_TCP, .prot = &tcp_prot, .ops = &inet_stream_ops, - .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }, @@ -1012,7 +1008,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_UDP, .prot = &udp_prot, .ops = &inet_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }, @@ -1021,7 +1016,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_ICMP, .prot = &ping_prot, .ops = &inet_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, }, @@ -1030,7 +1024,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_IP, /* wild card */ .prot = &raw_prot, .ops = &inet_sockraw_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, } }; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 78692e4..e944937 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -827,7 +827,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) ifa_existing = find_matching_ifa(ifa); if (!ifa_existing) { /* It would be best to check for !NLM_F_CREATE here but - * userspace alreay relies on not having to provide this. + * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 5afeb5a..243c7f4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2166,7 +2166,7 @@ static void fib_table_print(struct seq_file *seq, struct fib_table *tb) static int fib_triestat_seq_show(struct seq_file *seq, void *v) { - struct net *net = (struct net *)seq->private; + struct net *net = seq_file_net(seq); unsigned int h; seq_printf(seq, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 17d34e3..6748d42 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index c98cf14..4ced1b9 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -26,20 +26,7 @@ * Theory of operations. * We keep one entry for each peer IP address. The nodes contains long-living * information about the peer which doesn't depend on routes. - * At this moment this information consists only of ID field for the next - * outgoing IP packet. This field is incremented with each packet as encoded - * in inet_getid() function (include/net/inetpeer.h). - * At the moment of writing this notes identifier of IP packets is generated - * to be unpredictable using this code only for packets subjected - * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size when local fragmentation is disabled use a constant ID and do - * not use this code (see ip_select_ident() in include/net/ip.h). * - * Route cache entries hold references to our nodes. - * New cache entries get references via lookup by destination IP address in - * the avl tree. The reference is grabbed only when it's needed i.e. only - * when we try to output IP packet which needs an unpredictable ID (see - * __ip_select_ident() in net/ipv4/route.c). * Nodes are removed only when reference counter goes to 0. * When it's happened the node may be removed when a sufficient amount of * time has been passed since its last use. The less-recently-used entry can @@ -62,7 +49,6 @@ * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing * daddr: unchangeable - * ip_id_count: atomic value (no lock needed) */ static struct kmem_cache *peer_cachep __read_mostly; @@ -497,10 +483,6 @@ relookup: p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, - (daddr->family == AF_INET) ? - secure_ip_id(daddr->addr.a4) : - secure_ipv6_id(daddr->addr.a6)); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6e231ab..8d3b6b0 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(skb, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -430,8 +430,7 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(skb, &rt->dst, sk, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); + ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; @@ -1379,7 +1378,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(skb, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt) { iph->ihl += opt->optlen>>2; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index b3f8597..86a00bd 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -395,11 +395,10 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, struct ip_tunnel_parm *parms) { - struct ip_tunnel *nt, *fbt; + struct ip_tunnel *nt; struct net_device *dev; BUG_ON(!itn->fb_tunnel_dev); - fbt = netdev_priv(itn->fb_tunnel_dev); dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms); if (IS_ERR(dev)) return ERR_CAST(dev); @@ -540,9 +539,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, unsigned int max_headroom; /* The extra header space needed */ __be32 dst; int err; - bool connected = true; + bool connected; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); + connected = (tunnel->parms.iph.daddr != 0); dst = tnl_params->daddr; if (dst == 0) { @@ -755,10 +755,8 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) if (!t && (cmd == SIOCADDTUNNEL)) { t = ip_tunnel_create(net, itn, p); - if (IS_ERR(t)) { - err = PTR_ERR(t); - break; - } + err = PTR_ERR_OR_ZERO(t); + break; } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t != NULL) { @@ -882,6 +880,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, */ if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); } rtnl_unlock(); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index bcf206c..847e69c 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -74,7 +74,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1); + __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1); err = ip_local_out_sk(sk, skb); if (unlikely(net_xmit_eval(err))) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index afcee51..13ef00f 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -239,6 +239,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) static int vti4_err(struct sk_buff *skb, u32 info) { __be32 spi; + __u32 mark; struct xfrm_state *x; struct ip_tunnel *tunnel; struct ip_esp_hdr *esph; @@ -254,6 +255,8 @@ static int vti4_err(struct sk_buff *skb, u32 info) if (!tunnel) return -1; + mark = be32_to_cpu(tunnel->parms.o_key); + switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); @@ -281,7 +284,7 @@ static int vti4_err(struct sk_buff *skb, u32 info) return 0; } - x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET); if (!x) return 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 812b183..4bc508f 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -486,4 +486,5 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index d84dc8d..65bcaa7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -484,7 +484,7 @@ static void reg_vif_setup(struct net_device *dev) dev->type = ARPHRD_PIMREG; dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 8; dev->flags = IFF_NOARP; - dev->netdev_ops = ®_vif_netdev_ops, + dev->netdev_ops = ®_vif_netdev_ops; dev->destructor = free_netdev; dev->features |= NETIF_F_NETNS_LOCAL; } @@ -1663,7 +1663,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(skb, skb_dst(skb), NULL); + ip_select_ident(skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index ee28861..f1787c0 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -91,17 +91,9 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, if (nf_ct_is_untracked(ct)) return NF_ACCEPT; - nat = nfct_nat(ct); - if (!nat) { - /* NAT module was loaded late. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) { - pr_debug("failed to add NAT extension\n"); - return NF_ACCEPT; - } - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; switch (ctinfo) { case IP_CT_RELATED: diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index b5b256d..3964157 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -48,15 +48,9 @@ static unsigned int nf_nat_fn(const struct nf_hook_ops *ops, NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET))); - nat = nfct_nat(ct); - if (nat == NULL) { - /* Conntrack module was loaded late, can't add extension. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) - return NF_ACCEPT; - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; switch (ctinfo) { case IP_CT_RELATED: diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a9dbe58..2c65160 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -389,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 50e1e0f..082239f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -89,6 +89,7 @@ #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/jhash.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -456,39 +457,19 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, return neigh_create(&arp_tbl, pkey, dev); } -/* - * Peer allocation may fail only in serious out-of-memory conditions. However - * we still can generate some output. - * Random ID selection looks a bit dangerous because we have no chances to - * select ID being unique in a reasonable period of time. - * But broken packet identifier may be better than no packet at all. - */ -static void ip_select_fb_ident(struct iphdr *iph) -{ - static DEFINE_SPINLOCK(ip_fb_id_lock); - static u32 ip_fallback_id; - u32 salt; +atomic_t *ip_idents __read_mostly; +EXPORT_SYMBOL(ip_idents); - spin_lock_bh(&ip_fb_id_lock); - salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); - iph->id = htons(salt & 0xFFFF); - ip_fallback_id = salt; - spin_unlock_bh(&ip_fb_id_lock); -} - -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) +void __ip_select_ident(struct iphdr *iph, int segs) { - struct net *net = dev_net(dst->dev); - struct inet_peer *peer; + static u32 ip_idents_hashrnd __read_mostly; + u32 hash, id; - peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1); - if (peer) { - iph->id = htons(inet_getid(peer, more)); - inet_putpeer(peer); - return; - } + net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); - ip_select_fb_ident(iph); + hash = jhash_1word((__force u32)iph->daddr, ip_idents_hashrnd); + id = ip_idents_reserve(hash, segs); + iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); @@ -1526,7 +1507,7 @@ static int __mkroute_input(struct sk_buff *skb, struct in_device *out_dev; unsigned int flags = 0; bool do_cache; - u32 itag; + u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); @@ -2711,6 +2692,12 @@ int __init ip_rt_init(void) { int rc = 0; + ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); + if (!ip_idents) + panic("IP: failed to allocate ip_idents\n"); + + prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3d61c52..d463c35 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1402,11 +1402,19 @@ static void tcp_cwnd_application_limited(struct sock *sk) tp->snd_cwnd_stamp = tcp_time_stamp; } -static void tcp_cwnd_validate(struct sock *sk, u32 unsent_segs) +static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { struct tcp_sock *tp = tcp_sk(sk); - tp->lsnd_pending = tp->packets_out + unsent_segs; + /* Track the maximum number of outstanding packets in each + * window, and remember whether we were cwnd-limited then. + */ + if (!before(tp->snd_una, tp->max_packets_seq) || + tp->packets_out > tp->max_packets_out) { + tp->max_packets_out = tp->packets_out; + tp->max_packets_seq = tp->snd_nxt; + tp->is_cwnd_limited = is_cwnd_limited; + } if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ @@ -1660,7 +1668,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, * * This algorithm is from John Heffner. */ -static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) +static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, + bool *is_cwnd_limited) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1724,6 +1733,9 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) if (!tp->tso_deferred) tp->tso_deferred = 1 | (jiffies << 1); + if (cong_win < send_win && cong_win < skb->len) + *is_cwnd_limited = true; + return true; send_now: @@ -1881,9 +1893,10 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - unsigned int tso_segs, sent_pkts, unsent_segs = 0; + unsigned int tso_segs, sent_pkts; int cwnd_quota; int result; + bool is_cwnd_limited = false; sent_pkts = 0; @@ -1908,6 +1921,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { + is_cwnd_limited = true; if (push_one == 2) /* Force out a loss probe pkt. */ cwnd_quota = 1; @@ -1924,8 +1938,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, nonagle : TCP_NAGLE_PUSH)))) break; } else { - if (!push_one && tcp_tso_should_defer(sk, skb)) - goto compute_unsent_segs; + if (!push_one && + tcp_tso_should_defer(sk, skb, &is_cwnd_limited)) + break; } /* TCP Small Queues : @@ -1950,14 +1965,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, * there is no smp_mb__after_set_bit() yet */ smp_mb__after_clear_bit(); - if (atomic_read(&sk->sk_wmem_alloc) > limit) { - u32 unsent_bytes; - -compute_unsent_segs: - unsent_bytes = tp->write_seq - tp->snd_nxt; - unsent_segs = DIV_ROUND_UP(unsent_bytes, mss_now); + if (atomic_read(&sk->sk_wmem_alloc) > limit) break; - } } limit = mss_now; @@ -1997,7 +2006,7 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk); - tcp_cwnd_validate(sk, unsent_segs); + tcp_cwnd_validate(sk, is_cwnd_limited); return false; } return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk)); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 590532a..e07d52b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -785,7 +785,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); - else if (sk->sk_no_check == UDP_CSUM_NOXMIT) { /* UDP csum disabled */ + else if (sk->sk_no_check_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; @@ -1968,7 +1968,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); - int val; + int val, valbool; int err = 0; int is_udplite = IS_UDPLITE(sk); @@ -1978,6 +1978,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, if (get_user(val, (int __user *)optval)) return -EFAULT; + valbool = val ? 1 : 0; + switch (optname) { case UDP_CORK: if (val != 0) { @@ -2007,6 +2009,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, } break; + case UDP_NO_CHECK6_TX: + up->no_check6_tx = valbool; + break; + + case UDP_NO_CHECK6_RX: + up->no_check6_rx = valbool; + break; + /* * UDP-Lite's partial checksum coverage (RFC 3828). */ @@ -2089,6 +2099,14 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, val = up->encap_type; break; + case UDP_NO_CHECK6_TX: + val = up->no_check6_tx; + break; + + case UDP_NO_CHECK6_RX: + val = up->no_check6_rx; + break; + /* The following two cannot be changed on UDP sockets, the return is * always 0 (which corresponds to the full checksum coverage of UDP). */ case UDPLITE_SEND_CSCOV: diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 2c46acd..3b3efbd 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -70,7 +70,6 @@ static struct inet_protosw udplite4_protosw = { .protocol = IPPROTO_UDPLITE, .prot = &udplite_prot, .ops = &inet_dgram_ops, - .no_check = 0, /* must checksum (RFC 3828) */ .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 05f2b48..91771a7 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -58,12 +58,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(skb, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; + ip_select_ident(skb, NULL); return 0; } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 8e8c018..d5f6bd9 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -62,10 +62,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) if (err) return err; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED; - - skb->protocol = htons(ETH_P_IP); + IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; return x->outer_mode->output2(x, skb); } @@ -73,27 +70,34 @@ EXPORT_SYMBOL(xfrm4_prepare_output); int xfrm4_output_finish(struct sk_buff *skb) { + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + skb->protocol = htons(ETH_P_IP); + +#ifdef CONFIG_NETFILTER + IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; +#endif + + return xfrm_output(skb); +} + +static int __xfrm4_output(struct sk_buff *skb) +{ + struct xfrm_state *x = skb_dst(skb)->xfrm; + #ifdef CONFIG_NETFILTER - if (!skb_dst(skb)->xfrm) { + if (!x) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(skb); } - - IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; #endif - skb->protocol = htons(ETH_P_IP); - return xfrm_output(skb); + return x->outer_mode->afinfo->output_finish(skb); } int xfrm4_output(struct sock *sk, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); - struct xfrm_state *x = dst->xfrm; - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, - NULL, dst->dev, - x->outer_mode->afinfo->output_finish, + NULL, skb_dst(skb)->dev, __xfrm4_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index 7f7b243..a2ce010 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -50,8 +50,12 @@ int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err) { int ret; struct xfrm4_protocol *handler; + struct xfrm4_protocol __rcu **head = proto_handlers(protocol); - for_each_protocol_rcu(*proto_handlers(protocol), handler) + if (!head) + return 0; + + for_each_protocol_rcu(*head, handler) if ((ret = handler->cb_handler(skb, err)) <= 0) return ret; @@ -64,15 +68,20 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, { int ret; struct xfrm4_protocol *handler; + struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - for_each_protocol_rcu(*proto_handlers(nexthdr), handler) + if (!head) + goto out; + + for_each_protocol_rcu(*head, handler) if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) return ret; +out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); kfree_skb(skb); @@ -208,6 +217,9 @@ int xfrm4_protocol_register(struct xfrm4_protocol *handler, int ret = -EEXIST; int priority = handler->priority; + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + mutex_lock(&xfrm4_protocol_mutex); if (!rcu_dereference_protected(*proto_handlers(protocol), @@ -250,6 +262,9 @@ int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, struct xfrm4_protocol *t; int ret = -ENOENT; + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + mutex_lock(&xfrm4_protocol_mutex); for (pprev = proto_handlers(protocol); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index dc47cc7..7cb4392 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -106,7 +106,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, struct inet_protosw *answer; struct proto *answer_prot; unsigned char answer_flags; - char answer_no_check; int try_loading_module = 0; int err; @@ -162,7 +161,6 @@ lookup_protocol: sock->ops = answer->ops; answer_prot = answer->prot; - answer_no_check = answer->no_check; answer_flags = answer->flags; rcu_read_unlock(); @@ -176,7 +174,6 @@ lookup_protocol: sock_init_data(sock, sk); err = 0; - sk->sk_no_check = answer_no_check; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 59f95af..b2f0915 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -196,7 +196,6 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, unsigned int off; u16 flush = 1; int proto; - __wsum csum; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); @@ -264,13 +263,10 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, NAPI_GRO_CB(skb)->flush |= flush; - csum = skb->csum; - skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); + skb_gro_postpull_rcsum(skb, iph, nlen); pp = ops->callbacks.gro_receive(head, skb); - skb->csum = csum; - out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ab0cc57..cb9df0e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -537,6 +537,18 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } +static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static u32 ip6_idents_hashrnd __read_mostly; + u32 hash, id; + + net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); + + hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd); + id = ip_idents_reserve(hash, 1); + fhdr->identification = htonl(id); +} + int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; @@ -1229,7 +1241,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, unsigned int maxnonfragsize, headersize; headersize = sizeof(struct ipv6hdr) + - (opt ? opt->tot_len : 0) + + (opt ? opt->opt_flen + opt->opt_nflen : 0) + (dst_allfrag(&rt->dst) ? sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b05b609..afa0824 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -61,6 +61,7 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG @@ -1557,7 +1558,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) { u8 proto; - if (!data) + if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index b7c0f82..9aaa6bb 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -511,6 +511,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __be32 spi; + __u32 mark; struct xfrm_state *x; struct ip6_tnl *t; struct ip_esp_hdr *esph; @@ -524,6 +525,8 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!t) return -1; + mark = be32_to_cpu(t->parms.o_key); + switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data + offset); @@ -545,7 +548,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, type != NDISC_REDIRECT) return 0; - x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET6); if (!x) return 0; @@ -792,15 +795,12 @@ static const struct net_device_ops vti6_netdev_ops = { **/ static void vti6_dev_setup(struct net_device *dev) { - struct ip6_tnl *t; - dev->netdev_ops = &vti6_netdev_ops; dev->destructor = vti6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr); dev->mtu = ETH_DATA_LEN; - t = netdev_priv(dev); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; @@ -1097,7 +1097,6 @@ static int __init vti6_tunnel_init(void) err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP); if (err < 0) { - unregister_pernet_device(&vti6_net_ops); pr_err("%s: can't register vti6 protocol\n", __func__); goto out; @@ -1106,7 +1105,6 @@ static int __init vti6_tunnel_init(void) err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH); if (err < 0) { xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); - unregister_pernet_device(&vti6_net_ops); pr_err("%s: can't register vti6 protocol\n", __func__); goto out; @@ -1116,7 +1114,6 @@ static int __init vti6_tunnel_init(void) if (err < 0) { xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); - unregister_pernet_device(&vti6_net_ops); pr_err("%s: can't register vti6 protocol\n", __func__); goto out; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 09a22f4..ca8d4ea 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -851,7 +851,7 @@ out: static void ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); - const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + @@ -944,10 +944,7 @@ static void ndisc_recv_na(struct sk_buff *skb) /* * Change: router to host */ - struct rt6_info *rt; - rt = rt6_get_dflt_router(saddr, dev); - if (rt) - ip6_del_rt(rt); + rt6_clean_tohost(dev_net(dev), saddr); } out: diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 84c7f33..387d8b8 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -90,17 +90,9 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, if (nf_ct_is_untracked(ct)) return NF_ACCEPT; - nat = nfct_nat(ct); - if (!nat) { - /* NAT module was loaded late. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) { - pr_debug("failed to add NAT extension\n"); - return NF_ACCEPT; - } - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; switch (ctinfo) { case IP_CT_RELATED: diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index 9c3297a..d189fcb 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -47,15 +47,9 @@ static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, if (ct == NULL || nf_ct_is_untracked(ct)) return NF_ACCEPT; - nat = nfct_nat(ct); - if (nat == NULL) { - /* Conntrack module was loaded late, can't add extension. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) - return NF_ACCEPT; - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; switch (ctinfo) { case IP_CT_RELATED: diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 6313abd..6179ac1 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -8,36 +8,6 @@ #include <net/addrconf.h> #include <net/secure_seq.h> -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) -{ - static atomic_t ipv6_fragmentation_id; - struct in6_addr addr; - int old, new; - -#if IS_ENABLED(CONFIG_IPV6) - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } -#endif - do { - old = atomic_read(&ipv6_fragmentation_id); - new = old + 1; - if (!new) - new = 1; - } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - - addr = rt->rt6i_dst.addr; - addr.s6_addr32[0] ^= (__force __be32)new; - fhdr->identification = htonl(secure_ipv6_id(addr.s6_addr32)); -} -EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index a2a1d80..5b7a1ed 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -51,7 +51,6 @@ static struct inet_protosw pingv6_protosw = { .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, .ops = &inet6_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index dddfb5f..b2dc60b 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1322,7 +1322,6 @@ static struct inet_protosw rawv6_protosw = { .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f0a8ff9..f23fbd2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1455,7 +1455,7 @@ static int ip6_dst_gc(struct dst_ops *ops) goto out; net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size); + fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; @@ -2234,6 +2234,27 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) fib6_clean_all(net, fib6_remove_prefsrc, &adni); } +#define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +/* Remove routers and update dst entries when gateway turn into host. */ +static int fib6_clean_tohost(struct rt6_info *rt, void *arg) +{ + struct in6_addr *gateway = (struct in6_addr *)arg; + + if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || + ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + return -1; + } + return 0; +} + +void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) +{ + fib6_clean_all(net, fib6_clean_tohost, gateway); +} + struct arg_dev_net { struct net_device *dev; struct net *net; @@ -2709,6 +2730,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh) if (tb[RTA_OIF]) oif = nla_get_u32(tb[RTA_OIF]); + if (tb[RTA_MARK]) + fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); + if (iif) { struct net_device *dev; int flags = 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index e5a453c..f438004 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1828,4 +1828,5 @@ xfrm_tunnel_failed: module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f07b2ab..229239a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1992,7 +1992,6 @@ static struct inet_protosw tcpv6_protosw = { .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, - .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }; diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 0d78132..8517d3c 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -42,7 +42,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, if (NAPI_GRO_CB(skb)->flush) goto skip_csum; - wsum = skb->csum; + wsum = NAPI_GRO_CB(skb)->csum; switch (skb->ip_summed) { case CHECKSUM_NONE: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7edf096..6032523 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -794,10 +794,10 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, dif = inet6_iif(skb); sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); while (sk) { - /* If zero checksum and sk_no_check is not on for + /* If zero checksum and no_check is not on for * the socket then skip it. */ - if (uh->check || sk->sk_no_check) + if (uh->check || udp_sk(sk)->no_check6_rx) stack[count++] = sk; sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr, @@ -887,7 +887,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (sk != NULL) { int ret; - if (!uh->check && !sk->sk_no_check) { + if (!uh->check && !udp_sk(sk)->no_check6_rx) { sock_put(sk); udp6_csum_zero_error(skb); goto csum_error; @@ -1037,7 +1037,7 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (is_udplite) csum = udplite_csum_outgoing(sk, skb); - else if (sk->sk_no_check == UDP_CSUM_NOXMIT) { /* UDP csum disabled */ + else if (up->no_check6_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ @@ -1507,7 +1507,6 @@ static struct inet_protosw udpv6_protosw = { .protocol = IPPROTO_UDP, .prot = &udpv6_prot, .ops = &inet6_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index dfcc4be..9cf097e 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -64,7 +64,6 @@ static struct inet_protosw udplite6_protosw = { .protocol = IPPROTO_UDPLITE, .prot = &udplitev6_prot, .ops = &inet6_dgram_ops, - .no_check = 0, .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index f47c8b1..433672d 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -114,12 +114,6 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) if (err) return err; - memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); -#ifdef CONFIG_NETFILTER - IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; -#endif - - skb->protocol = htons(ETH_P_IPV6); skb->ignore_df = 1; return x->outer_mode->output2(x, skb); @@ -128,11 +122,13 @@ EXPORT_SYMBOL(xfrm6_prepare_output); int xfrm6_output_finish(struct sk_buff *skb) { + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + skb->protocol = htons(ETH_P_IPV6); + #ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; #endif - skb->protocol = htons(ETH_P_IPV6); return xfrm_output(skb); } @@ -142,6 +138,13 @@ static int __xfrm6_output(struct sk_buff *skb) struct xfrm_state *x = dst->xfrm; int mtu; +#ifdef CONFIG_NETFILTER + if (!x) { + IP6CB(skb)->flags |= IP6SKB_REROUTED; + return dst_output(skb); + } +#endif + if (skb->protocol == htons(ETH_P_IPV6)) mtu = ip6_skb_dst_mtu(skb); else @@ -165,6 +168,7 @@ static int __xfrm6_output(struct sk_buff *skb) int xfrm6_output(struct sock *sk, struct sk_buff *skb) { - return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, - skb_dst(skb)->dev, __xfrm6_output); + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, + NULL, skb_dst(skb)->dev, __xfrm6_output, + !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c index 6ab989c..54d13f8 100644 --- a/net/ipv6/xfrm6_protocol.c +++ b/net/ipv6/xfrm6_protocol.c @@ -50,6 +50,10 @@ int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err) { int ret; struct xfrm6_protocol *handler; + struct xfrm6_protocol __rcu **head = proto_handlers(protocol); + + if (!head) + return 0; for_each_protocol_rcu(*proto_handlers(protocol), handler) if ((ret = handler->cb_handler(skb, err)) <= 0) @@ -184,10 +188,12 @@ int xfrm6_protocol_register(struct xfrm6_protocol *handler, struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; bool add_netproto = false; - int ret = -EEXIST; int priority = handler->priority; + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + mutex_lock(&xfrm6_protocol_mutex); if (!rcu_dereference_protected(*proto_handlers(protocol), @@ -230,6 +236,9 @@ int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, struct xfrm6_protocol *t; int ret = -ENOENT; + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + mutex_lock(&xfrm6_protocol_mutex); for (pprev = proto_handlers(protocol); diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 41e4e93..91729b8 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1353,7 +1353,7 @@ static int ipx_create(struct net *net, struct socket *sock, int protocol, sk_refcnt_debug_inc(sk); sock_init_data(sock, sk); - sk->sk_no_check = 1; /* Checksum off by default */ + sk->sk_no_check_tx = 1; /* Checksum off by default */ sock->ops = &ipx_dgram_ops; rc = 0; out: diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c index c1f0318..67e7ad3 100644 --- a/net/ipx/ipx_route.c +++ b/net/ipx/ipx_route.c @@ -236,7 +236,8 @@ int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx, } /* Apply checksum. Not allowed on 802.3 links. */ - if (sk->sk_no_check || intrfc->if_dlink_type == htons(IPX_FRAME_8023)) + if (sk->sk_no_check_tx || + intrfc->if_dlink_type == htons(IPX_FRAME_8023)) ipx->ipx_checksum = htons(0xFFFF); else ipx->ipx_checksum = ipx_cksum(ipx, len + sizeof(struct ipxhdr)); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 01e77b0..7a95fa4 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -682,6 +682,18 @@ struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock) return NULL; } +static void __iucv_auto_name(struct iucv_sock *iucv) +{ + char name[12]; + + sprintf(name, "%08x", atomic_inc_return(&iucv_sk_list.autobind_name)); + while (__iucv_get_sock_by_name(name)) { + sprintf(name, "%08x", + atomic_inc_return(&iucv_sk_list.autobind_name)); + } + memcpy(iucv->src_name, name, 8); +} + /* Bind an unbound socket */ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) @@ -724,8 +736,12 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { if (!memcmp(dev->perm_addr, uid, 8)) { - memcpy(iucv->src_name, sa->siucv_name, 8); memcpy(iucv->src_user_id, sa->siucv_user_id, 8); + /* Check for unitialized siucv_name */ + if (strncmp(sa->siucv_name, " ", 8) == 0) + __iucv_auto_name(iucv); + else + memcpy(iucv->src_name, sa->siucv_name, 8); sk->sk_bound_dev_if = dev->ifindex; iucv->hs_dev = dev; dev_hold(dev); @@ -763,7 +779,6 @@ done: static int iucv_sock_autobind(struct sock *sk) { struct iucv_sock *iucv = iucv_sk(sk); - char name[12]; int err = 0; if (unlikely(!pr_iucv)) @@ -772,17 +787,9 @@ static int iucv_sock_autobind(struct sock *sk) memcpy(iucv->src_user_id, iucv_userid, 8); write_lock_bh(&iucv_sk_list.lock); - - sprintf(name, "%08x", atomic_inc_return(&iucv_sk_list.autobind_name)); - while (__iucv_get_sock_by_name(name)) { - sprintf(name, "%08x", - atomic_inc_return(&iucv_sk_list.autobind_name)); - } - + __iucv_auto_name(iucv); write_unlock_bh(&iucv_sk_list.lock); - memcpy(&iucv->src_name, name, 8); - if (!iucv->msglimit) iucv->msglimit = IUCV_QUEUELEN_DEFAULT; @@ -1830,7 +1837,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { + if (msg->tag == IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } @@ -1936,11 +1943,10 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) sk_acceptq_is_full(sk) || !nsk) { /* error on server socket - connection refused */ - if (nsk) - sk_free(nsk); afiucv_swap_src_dest(skb); trans_hdr->flags = AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_FIN; err = dev_queue_xmit(skb); + iucv_sock_kill(nsk); bh_unlock_sock(sk); goto out; } diff --git a/net/key/af_key.c b/net/key/af_key.c index f3c8307..ba2a2f9 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1476,9 +1476,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, const struct sadb_msg else err = xfrm_state_update(x); - xfrm_audit_state_add(x, err ? 0 : 1, - audit_get_loginuid(current), - audit_get_sessionid(current), 0); + xfrm_audit_state_add(x, err ? 0 : 1, true); if (err < 0) { x->km.state = XFRM_STATE_DEAD; @@ -1532,9 +1530,7 @@ static int pfkey_delete(struct sock *sk, struct sk_buff *skb, const struct sadb_ c.event = XFRM_MSG_DELSA; km_state_notify(x, &c); out: - xfrm_audit_state_delete(x, err ? 0 : 1, - audit_get_loginuid(current), - audit_get_sessionid(current), 0); + xfrm_audit_state_delete(x, err ? 0 : 1, true); xfrm_state_put(x); return err; @@ -1726,17 +1722,13 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m struct net *net = sock_net(sk); unsigned int proto; struct km_event c; - struct xfrm_audit audit_info; int err, err2; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; - audit_info.loginuid = audit_get_loginuid(current); - audit_info.sessionid = audit_get_sessionid(current); - audit_info.secid = 0; - err = xfrm_state_flush(net, proto, &audit_info); + err = xfrm_state_flush(net, proto, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ @@ -2288,9 +2280,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_ err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp, hdr->sadb_msg_type != SADB_X_SPDUPDATE); - xfrm_audit_policy_add(xp, err ? 0 : 1, - audit_get_loginuid(current), - audit_get_sessionid(current), 0); + xfrm_audit_policy_add(xp, err ? 0 : 1, true); if (err) goto out; @@ -2372,9 +2362,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa if (xp == NULL) return -ENOENT; - xfrm_audit_policy_delete(xp, err ? 0 : 1, - audit_get_loginuid(current), - audit_get_sessionid(current), 0); + xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err) goto out; @@ -2553,7 +2541,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, sel.sport_mask = htons(0xffff); /* set destination address info of selector */ - sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1], + sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1]; pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); sel.prefixlen_d = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); @@ -2622,9 +2610,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -ENOENT; if (delete) { - xfrm_audit_policy_delete(xp, err ? 0 : 1, - audit_get_loginuid(current), - audit_get_sessionid(current), 0); + xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err) goto out; @@ -2733,13 +2719,9 @@ static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sad { struct net *net = sock_net(sk); struct km_event c; - struct xfrm_audit audit_info; int err, err2; - audit_info.loginuid = audit_get_loginuid(current); - audit_info.sessionid = audit_get_sessionid(current); - audit_info.secid = 0; - err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info); + err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - old silent behavior */ diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ed0716a..3795580 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1102,7 +1102,9 @@ static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb, struct ipv6_pinfo *np = inet6_sk(sk); struct udphdr *uh = udp_hdr(skb); - if (!skb_dst(skb) || !skb_dst(skb)->dev || + if (udp_get_no_check6_tx(sk)) + skb->ip_summed = CHECKSUM_NONE; + else if (!skb_dst(skb) || !skb_dst(skb)->dev || !(skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { __wsum csum = skb_checksum(skb, 0, udp_len, 0); skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1188,7 +1190,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len l2tp_xmit_ipv6_csum(sk, skb, udp_len); else #endif - if (sk->sk_no_check == UDP_CSUM_NOXMIT) + if (sk->sk_no_check_tx) skb->ip_summed = CHECKSUM_NONE; else if ((skb_dst(skb) && skb_dst(skb)->dev) && (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) { @@ -1435,6 +1437,11 @@ static int l2tp_tunnel_sock_create(struct net *net, sizeof(udp6_addr), 0); if (err < 0) goto out; + + if (cfg->udp6_zero_tx_checksums) + udp_set_no_check6_tx(sock->sk, true); + if (cfg->udp6_zero_rx_checksums) + udp_set_no_check6_rx(sock->sk, true); } else #endif { @@ -1463,7 +1470,7 @@ static int l2tp_tunnel_sock_create(struct net *net, } if (!cfg->use_udp_checksums) - sock->sk->sk_no_check = UDP_CSUM_NOXMIT; + sock->sk->sk_no_check_tx = 1; break; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 3f93ccd..68aa9ff 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -162,7 +162,9 @@ struct l2tp_tunnel_cfg { #endif u16 local_udp_port; u16 peer_udp_port; - unsigned int use_udp_checksums:1; + unsigned int use_udp_checksums:1, + udp6_zero_tx_checksums:1, + udp6_zero_rx_checksums:1; }; struct l2tp_tunnel { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 3397fe6..369a982 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -606,7 +606,6 @@ static struct inet_protosw l2tp_ip_protosw = { .protocol = IPPROTO_L2TP, .prot = &l2tp_ip_prot, .ops = &l2tp_ip_ops, - .no_check = 0, }; static struct net_protocol l2tp_ip_protocol __read_mostly = { diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index e472d44..f3f98a1 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -755,7 +755,6 @@ static struct inet_protosw l2tp_ip6_protosw = { .protocol = IPPROTO_L2TP, .prot = &l2tp_ip6_prot, .ops = &l2tp_ip6_ops, - .no_check = 0, }; static struct inet6_protocol l2tp_ip6_protocol __read_mostly = { diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index bd7387a..0ac907a 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -161,6 +161,13 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info cfg.peer_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_DPORT]); if (info->attrs[L2TP_ATTR_UDP_CSUM]) cfg.use_udp_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_CSUM]); + +#if IS_ENABLED(CONFIG_IPV6) + if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX]) + cfg.udp6_zero_tx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX]); + if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX]) + cfg.udp6_zero_rx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX]); +#endif } if (info->attrs[L2TP_ATTR_DEBUG]) @@ -297,8 +304,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla case L2TP_ENCAPTYPE_UDP: if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) || nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)) || - nla_put_u8(skb, L2TP_ATTR_UDP_CSUM, - (sk->sk_no_check != UDP_CSUM_NOXMIT))) + nla_put_u8(skb, L2TP_ATTR_UDP_CSUM, !sk->sk_no_check_tx)) goto nla_put_failure; /* NOBREAK */ case L2TP_ENCAPTYPE_IP: diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 9d7d840..1e46ffa 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -25,7 +25,8 @@ mac80211-y := \ wme.o \ event.o \ chan.o \ - trace.o mlme.o + trace.o mlme.o \ + tdls.o mac80211-$(CONFIG_MAC80211_LEDS) += led.o mac80211-$(CONFIG_MAC80211_DEBUGFS) += \ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 7b8d3cf..d7513a5 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -472,8 +472,10 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; + struct rate_control_ref *ref = local->rate_ctrl; struct timespec uptime; u64 packets = 0; + u32 thr = 0; int i, ac; sinfo->generation = sdata->local->sta_generation; @@ -587,6 +589,17 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_ASSOCIATED); if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER); + + /* check if the driver has a SW RC implementation */ + if (ref && ref->ops->get_expected_throughput) + thr = ref->ops->get_expected_throughput(sta->rate_ctrl_priv); + else + thr = drv_get_expected_throughput(local, &sta->sta); + + if (thr != 0) { + sinfo->filled |= STATION_INFO_EXPECTED_THROUGHPUT; + sinfo->expected_throughput = thr; + } } static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = { @@ -777,7 +790,7 @@ static void ieee80211_get_et_strings(struct wiphy *wiphy, } static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, - int idx, u8 *mac, struct station_info *sinfo) + int idx, u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -807,7 +820,7 @@ static int ieee80211_dump_survey(struct wiphy *wiphy, struct net_device *dev, } static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, - u8 *mac, struct station_info *sinfo) + const u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -1084,6 +1097,31 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, return 0; } +bool ieee80211_csa_needs_block_tx(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + + lockdep_assert_held(&local->mtx); + + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(sdata)) + continue; + + if (!sdata->vif.csa_active) + continue; + + if (!sdata->csa_block_tx) + continue; + + rcu_read_unlock(); + return true; + } + rcu_read_unlock(); + + return false; +} + static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -1101,7 +1139,14 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) old_probe_resp = sdata_dereference(sdata->u.ap.probe_resp, sdata); /* abort any running channel switch */ + mutex_lock(&local->mtx); sdata->vif.csa_active = false; + if (!ieee80211_csa_needs_block_tx(local)) + ieee80211_wake_queues_by_reason(&local->hw, + IEEE80211_MAX_QUEUE_MAP, + IEEE80211_QUEUE_STOP_REASON_CSA); + mutex_unlock(&local->mtx); + kfree(sdata->u.ap.next_beacon); sdata->u.ap.next_beacon = NULL; @@ -1425,7 +1470,8 @@ static int sta_apply_parameters(struct ieee80211_local *local, } static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, - u8 *mac, struct station_parameters *params) + const u8 *mac, + struct station_parameters *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; @@ -1459,6 +1505,8 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))) { sta_info_pre_move_state(sta, IEEE80211_STA_AUTH); sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC); + } else { + sta->sta.tdls = true; } err = sta_apply_parameters(local, sta, params); @@ -1492,7 +1540,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, } static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, - u8 *mac) + const u8 *mac) { struct ieee80211_sub_if_data *sdata; @@ -1506,7 +1554,7 @@ static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, } static int ieee80211_change_station(struct wiphy *wiphy, - struct net_device *dev, u8 *mac, + struct net_device *dev, const u8 *mac, struct station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -1631,7 +1679,7 @@ out_err: #ifdef CONFIG_MAC80211_MESH static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev, - u8 *dst, u8 *next_hop) + const u8 *dst, const u8 *next_hop) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; @@ -1659,7 +1707,7 @@ static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev, } static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev, - u8 *dst) + const u8 *dst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -1670,9 +1718,8 @@ static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev, return 0; } -static int ieee80211_change_mpath(struct wiphy *wiphy, - struct net_device *dev, - u8 *dst, u8 *next_hop) +static int ieee80211_change_mpath(struct wiphy *wiphy, struct net_device *dev, + const u8 *dst, const u8 *next_hop) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; @@ -1764,8 +1811,8 @@ static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, } static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev, - int idx, u8 *dst, u8 *next_hop, - struct mpath_info *pinfo) + int idx, u8 *dst, u8 *next_hop, + struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; @@ -3019,26 +3066,11 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif) } EXPORT_SYMBOL(ieee80211_csa_finish); -static void ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) +static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, + u32 *changed) { - struct ieee80211_local *local = sdata->local; - int err, changed = 0; - - sdata_assert_lock(sdata); - - mutex_lock(&local->mtx); - sdata->radar_required = sdata->csa_radar_required; - err = ieee80211_vif_change_channel(sdata, &changed); - mutex_unlock(&local->mtx); - if (WARN_ON(err < 0)) - return; - - if (!local->use_chanctx) { - local->_oper_chandef = sdata->csa_chandef; - ieee80211_hw_config(local, 0); - } + int err; - sdata->vif.csa_active = false; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: err = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon); @@ -3046,35 +3078,74 @@ static void ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) sdata->u.ap.next_beacon = NULL; if (err < 0) - return; - changed |= err; + return err; + *changed |= err; break; case NL80211_IFTYPE_ADHOC: err = ieee80211_ibss_finish_csa(sdata); if (err < 0) - return; - changed |= err; + return err; + *changed |= err; break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: err = ieee80211_mesh_finish_csa(sdata); if (err < 0) - return; - changed |= err; + return err; + *changed |= err; break; #endif default: WARN_ON(1); - return; + return -EINVAL; + } + + return 0; +} + +static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + u32 changed = 0; + int err; + + sdata_assert_lock(sdata); + lockdep_assert_held(&local->mtx); + + sdata->radar_required = sdata->csa_radar_required; + err = ieee80211_vif_change_channel(sdata, &changed); + if (err < 0) + return err; + + if (!local->use_chanctx) { + local->_oper_chandef = sdata->csa_chandef; + ieee80211_hw_config(local, 0); } + sdata->vif.csa_active = false; + + err = ieee80211_set_after_csa_beacon(sdata, &changed); + if (err) + return err; + ieee80211_bss_info_change_notify(sdata, changed); + cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef); - ieee80211_wake_queues_by_reason(&sdata->local->hw, + if (!ieee80211_csa_needs_block_tx(local)) + ieee80211_wake_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); - cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef); + return 0; +} + +static void ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) +{ + if (__ieee80211_csa_finalize(sdata)) { + sdata_info(sdata, "failed to finalize CSA, disconnecting\n"); + cfg80211_stop_iface(sdata->local->hw.wiphy, &sdata->wdev, + GFP_KERNEL); + } } void ieee80211_csa_finalize_work(struct work_struct *work) @@ -3082,8 +3153,11 @@ void ieee80211_csa_finalize_work(struct work_struct *work) struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, csa_finalize_work); + struct ieee80211_local *local = sdata->local; sdata_lock(sdata); + mutex_lock(&local->mtx); + /* AP might have been stopped while waiting for the lock. */ if (!sdata->vif.csa_active) goto unlock; @@ -3094,6 +3168,7 @@ void ieee80211_csa_finalize_work(struct work_struct *work) ieee80211_csa_finalize(sdata); unlock: + mutex_unlock(&local->mtx); sdata_unlock(sdata); } @@ -3129,9 +3204,25 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, if (params->count <= 1) break; - sdata->csa_counter_offset_beacon = - params->counter_offset_beacon; - sdata->csa_counter_offset_presp = params->counter_offset_presp; + if ((params->n_counter_offsets_beacon > + IEEE80211_MAX_CSA_COUNTERS_NUM) || + (params->n_counter_offsets_presp > + IEEE80211_MAX_CSA_COUNTERS_NUM)) + return -EINVAL; + + /* make sure we don't have garbage in other counters */ + memset(sdata->csa_counter_offset_beacon, 0, + sizeof(sdata->csa_counter_offset_beacon)); + memset(sdata->csa_counter_offset_presp, 0, + sizeof(sdata->csa_counter_offset_presp)); + + memcpy(sdata->csa_counter_offset_beacon, + params->counter_offsets_beacon, + params->n_counter_offsets_beacon * sizeof(u16)); + memcpy(sdata->csa_counter_offset_presp, + params->counter_offsets_presp, + params->n_counter_offsets_presp * sizeof(u16)); + err = ieee80211_assign_beacon(sdata, ¶ms->beacon_csa); if (err < 0) { kfree(sdata->u.ap.next_beacon); @@ -3220,8 +3311,9 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, return 0; } -int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, - struct cfg80211_csa_settings *params) +static int +__ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_csa_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -3230,6 +3322,7 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, int err, num_chanctx, changed = 0; sdata_assert_lock(sdata); + lockdep_assert_held(&local->mtx); if (!list_empty(&local->roc_list) || local->scanning) return -EBUSY; @@ -3272,15 +3365,16 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, return err; sdata->csa_radar_required = params->radar_required; - - if (params->block_tx) - ieee80211_stop_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_chandef = params->chandef; + sdata->csa_block_tx = params->block_tx; + sdata->csa_current_counter = params->count; sdata->vif.csa_active = true; + if (sdata->csa_block_tx) + ieee80211_stop_queues_by_reason(&local->hw, + IEEE80211_MAX_QUEUE_MAP, + IEEE80211_QUEUE_STOP_REASON_CSA); + if (changed) { ieee80211_bss_info_change_notify(sdata, changed); drv_channel_switch_beacon(sdata, ¶ms->chandef); @@ -3292,6 +3386,20 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, return 0; } +int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_csa_settings *params) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + int err; + + mutex_lock(&local->mtx); + err = __ieee80211_channel_switch(wiphy, dev, params); + mutex_unlock(&local->mtx); + + return err; +} + static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_mgmt_tx_params *params, u64 *cookie) @@ -3304,6 +3412,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, bool need_offchan = false; u32 flags; int ret; + u8 *data; if (params->dont_wait_for_ack) flags = IEEE80211_TX_CTL_NO_ACK; @@ -3397,7 +3506,20 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, } skb_reserve(skb, local->hw.extra_tx_headroom); - memcpy(skb_put(skb, params->len), params->buf, params->len); + data = skb_put(skb, params->len); + memcpy(data, params->buf, params->len); + + /* Update CSA counters */ + if (sdata->vif.csa_active && + (sdata->vif.type == NL80211_IFTYPE_AP || + sdata->vif.type == NL80211_IFTYPE_ADHOC) && + params->n_csa_offsets) { + int i; + u8 c = sdata->csa_current_counter; + + for (i = 0; i < params->n_csa_offsets; i++) + data[params->csa_offsets[i]] = c; + } IEEE80211_SKB_CB(skb)->flags = flags; @@ -3506,320 +3628,6 @@ static int ieee80211_set_rekey_data(struct wiphy *wiphy, return 0; } -static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb) -{ - u8 *pos = (void *)skb_put(skb, 7); - - *pos++ = WLAN_EID_EXT_CAPABILITY; - *pos++ = 5; /* len */ - *pos++ = 0x0; - *pos++ = 0x0; - *pos++ = 0x0; - *pos++ = 0x0; - *pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED; -} - -static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_local *local = sdata->local; - u16 capab; - - capab = 0; - if (ieee80211_get_sdata_band(sdata) != IEEE80211_BAND_2GHZ) - return capab; - - if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE)) - capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME; - if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE)) - capab |= WLAN_CAPABILITY_SHORT_PREAMBLE; - - return capab; -} - -static void ieee80211_tdls_add_link_ie(struct sk_buff *skb, u8 *src_addr, - u8 *peer, u8 *bssid) -{ - struct ieee80211_tdls_lnkie *lnkid; - - lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie)); - - lnkid->ie_type = WLAN_EID_LINK_ID; - lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2; - - memcpy(lnkid->bssid, bssid, ETH_ALEN); - memcpy(lnkid->init_sta, src_addr, ETH_ALEN); - memcpy(lnkid->resp_sta, peer, ETH_ALEN); -} - -static int -ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, - u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, struct sk_buff *skb) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - enum ieee80211_band band = ieee80211_get_sdata_band(sdata); - struct ieee80211_tdls_data *tf; - - tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u)); - - memcpy(tf->da, peer, ETH_ALEN); - memcpy(tf->sa, sdata->vif.addr, ETH_ALEN); - tf->ether_type = cpu_to_be16(ETH_P_TDLS); - tf->payload_type = WLAN_TDLS_SNAP_RFTYPE; - - switch (action_code) { - case WLAN_TDLS_SETUP_REQUEST: - tf->category = WLAN_CATEGORY_TDLS; - tf->action_code = WLAN_TDLS_SETUP_REQUEST; - - skb_put(skb, sizeof(tf->u.setup_req)); - tf->u.setup_req.dialog_token = dialog_token; - tf->u.setup_req.capability = - cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - - ieee80211_add_srates_ie(sdata, skb, false, band); - ieee80211_add_ext_srates_ie(sdata, skb, false, band); - ieee80211_tdls_add_ext_capab(skb); - break; - case WLAN_TDLS_SETUP_RESPONSE: - tf->category = WLAN_CATEGORY_TDLS; - tf->action_code = WLAN_TDLS_SETUP_RESPONSE; - - skb_put(skb, sizeof(tf->u.setup_resp)); - tf->u.setup_resp.status_code = cpu_to_le16(status_code); - tf->u.setup_resp.dialog_token = dialog_token; - tf->u.setup_resp.capability = - cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - - ieee80211_add_srates_ie(sdata, skb, false, band); - ieee80211_add_ext_srates_ie(sdata, skb, false, band); - ieee80211_tdls_add_ext_capab(skb); - break; - case WLAN_TDLS_SETUP_CONFIRM: - tf->category = WLAN_CATEGORY_TDLS; - tf->action_code = WLAN_TDLS_SETUP_CONFIRM; - - skb_put(skb, sizeof(tf->u.setup_cfm)); - tf->u.setup_cfm.status_code = cpu_to_le16(status_code); - tf->u.setup_cfm.dialog_token = dialog_token; - break; - case WLAN_TDLS_TEARDOWN: - tf->category = WLAN_CATEGORY_TDLS; - tf->action_code = WLAN_TDLS_TEARDOWN; - - skb_put(skb, sizeof(tf->u.teardown)); - tf->u.teardown.reason_code = cpu_to_le16(status_code); - break; - case WLAN_TDLS_DISCOVERY_REQUEST: - tf->category = WLAN_CATEGORY_TDLS; - tf->action_code = WLAN_TDLS_DISCOVERY_REQUEST; - - skb_put(skb, sizeof(tf->u.discover_req)); - tf->u.discover_req.dialog_token = dialog_token; - break; - default: - return -EINVAL; - } - - return 0; -} - -static int -ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, - u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, struct sk_buff *skb) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - enum ieee80211_band band = ieee80211_get_sdata_band(sdata); - struct ieee80211_mgmt *mgmt; - - mgmt = (void *)skb_put(skb, 24); - memset(mgmt, 0, 24); - memcpy(mgmt->da, peer, ETH_ALEN); - memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); - memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN); - - mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | - IEEE80211_STYPE_ACTION); - - switch (action_code) { - case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: - skb_put(skb, 1 + sizeof(mgmt->u.action.u.tdls_discover_resp)); - mgmt->u.action.category = WLAN_CATEGORY_PUBLIC; - mgmt->u.action.u.tdls_discover_resp.action_code = - WLAN_PUB_ACTION_TDLS_DISCOVER_RES; - mgmt->u.action.u.tdls_discover_resp.dialog_token = - dialog_token; - mgmt->u.action.u.tdls_discover_resp.capability = - cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - - ieee80211_add_srates_ie(sdata, skb, false, band); - ieee80211_add_ext_srates_ie(sdata, skb, false, band); - ieee80211_tdls_add_ext_capab(skb); - break; - default: - return -EINVAL; - } - - return 0; -} - -static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, - u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, u32 peer_capability, - const u8 *extra_ies, size_t extra_ies_len) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; - struct sk_buff *skb = NULL; - bool send_direct; - int ret; - - if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) - return -ENOTSUPP; - - /* make sure we are in managed mode, and associated */ - if (sdata->vif.type != NL80211_IFTYPE_STATION || - !sdata->u.mgd.associated) - return -EINVAL; - - tdls_dbg(sdata, "TDLS mgmt action %d peer %pM\n", - action_code, peer); - - skb = dev_alloc_skb(local->hw.extra_tx_headroom + - max(sizeof(struct ieee80211_mgmt), - sizeof(struct ieee80211_tdls_data)) + - 50 + /* supported rates */ - 7 + /* ext capab */ - extra_ies_len + - sizeof(struct ieee80211_tdls_lnkie)); - if (!skb) - return -ENOMEM; - - skb_reserve(skb, local->hw.extra_tx_headroom); - - switch (action_code) { - case WLAN_TDLS_SETUP_REQUEST: - case WLAN_TDLS_SETUP_RESPONSE: - case WLAN_TDLS_SETUP_CONFIRM: - case WLAN_TDLS_TEARDOWN: - case WLAN_TDLS_DISCOVERY_REQUEST: - ret = ieee80211_prep_tdls_encap_data(wiphy, dev, peer, - action_code, dialog_token, - status_code, skb); - send_direct = false; - break; - case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: - ret = ieee80211_prep_tdls_direct(wiphy, dev, peer, action_code, - dialog_token, status_code, - skb); - send_direct = true; - break; - default: - ret = -ENOTSUPP; - break; - } - - if (ret < 0) - goto fail; - - if (extra_ies_len) - memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len); - - /* the TDLS link IE is always added last */ - switch (action_code) { - case WLAN_TDLS_SETUP_REQUEST: - case WLAN_TDLS_SETUP_CONFIRM: - case WLAN_TDLS_TEARDOWN: - case WLAN_TDLS_DISCOVERY_REQUEST: - /* we are the initiator */ - ieee80211_tdls_add_link_ie(skb, sdata->vif.addr, peer, - sdata->u.mgd.bssid); - break; - case WLAN_TDLS_SETUP_RESPONSE: - case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: - /* we are the responder */ - ieee80211_tdls_add_link_ie(skb, peer, sdata->vif.addr, - sdata->u.mgd.bssid); - break; - default: - ret = -ENOTSUPP; - goto fail; - } - - if (send_direct) { - ieee80211_tx_skb(sdata, skb); - return 0; - } - - /* - * According to 802.11z: Setup req/resp are sent in AC_BK, otherwise - * we should default to AC_VI. - */ - switch (action_code) { - case WLAN_TDLS_SETUP_REQUEST: - case WLAN_TDLS_SETUP_RESPONSE: - skb_set_queue_mapping(skb, IEEE80211_AC_BK); - skb->priority = 2; - break; - default: - skb_set_queue_mapping(skb, IEEE80211_AC_VI); - skb->priority = 5; - break; - } - - /* disable bottom halves when entering the Tx path */ - local_bh_disable(); - ret = ieee80211_subif_start_xmit(skb, dev); - local_bh_enable(); - - return ret; - -fail: - dev_kfree_skb(skb); - return ret; -} - -static int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, - u8 *peer, enum nl80211_tdls_operation oper) -{ - struct sta_info *sta; - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) - return -ENOTSUPP; - - if (sdata->vif.type != NL80211_IFTYPE_STATION) - return -EINVAL; - - tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer); - - switch (oper) { - case NL80211_TDLS_ENABLE_LINK: - rcu_read_lock(); - sta = sta_info_get(sdata, peer); - if (!sta) { - rcu_read_unlock(); - return -ENOLINK; - } - - set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); - rcu_read_unlock(); - break; - case NL80211_TDLS_DISABLE_LINK: - return sta_info_destroy_addr(sdata, peer); - case NL80211_TDLS_TEARDOWN: - case NL80211_TDLS_SETUP: - case NL80211_TDLS_DISCOVERY_REQ: - /* We don't support in-driver setup/teardown/discovery */ - return -ENOTSUPP; - default: - return -ENOTSUPP; - } - - return 0; -} - static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u64 *cookie) { diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 48e6d6f..a310e33 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -855,7 +855,7 @@ static void __ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata, bool clear) { - struct ieee80211_local *local = sdata->local; + struct ieee80211_local *local __maybe_unused = sdata->local; struct ieee80211_sub_if_data *vlan; struct ieee80211_chanctx_conf *conf; @@ -871,7 +871,7 @@ __ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata, * to a channel context that has already been freed. */ conf = rcu_dereference_protected(sdata->vif.chanctx_conf, - lockdep_is_held(&local->chanctx_mtx)); + lockdep_is_held(&local->chanctx_mtx)); WARN_ON(!conf); if (clear) diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 40a6489..e205eba 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -34,8 +34,7 @@ static ssize_t ieee80211_if_read( ssize_t ret = -EINVAL; read_lock(&dev_base_lock); - if (sdata->dev->reg_state == NETREG_REGISTERED) - ret = (*format)(sdata, buf, sizeof(buf)); + ret = (*format)(sdata, buf, sizeof(buf)); read_unlock(&dev_base_lock); if (ret >= 0) @@ -62,8 +61,7 @@ static ssize_t ieee80211_if_write( ret = -ENODEV; rtnl_lock(); - if (sdata->dev->reg_state == NETREG_REGISTERED) - ret = (*write)(sdata, buf, count); + ret = (*write)(sdata, buf, count); rtnl_unlock(); return ret; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 5331582..bd782dc 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -5,11 +5,11 @@ #include "ieee80211_i.h" #include "trace.h" -static inline void check_sdata_in_driver(struct ieee80211_sub_if_data *sdata) +static inline bool check_sdata_in_driver(struct ieee80211_sub_if_data *sdata) { - WARN(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER), - "%s: Failed check-sdata-in-driver check, flags: 0x%x\n", - sdata->dev ? sdata->dev->name : sdata->name, sdata->flags); + return !WARN(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER), + "%s: Failed check-sdata-in-driver check, flags: 0x%x\n", + sdata->dev ? sdata->dev->name : sdata->name, sdata->flags); } static inline struct ieee80211_sub_if_data * @@ -168,7 +168,8 @@ static inline int drv_change_interface(struct ieee80211_local *local, might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_change_interface(local, sdata, type, p2p); ret = local->ops->change_interface(&local->hw, &sdata->vif, type, p2p); @@ -181,7 +182,8 @@ static inline void drv_remove_interface(struct ieee80211_local *local, { might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_remove_interface(local, sdata); local->ops->remove_interface(&local->hw, &sdata->vif); @@ -219,7 +221,8 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local, sdata->vif.type == NL80211_IFTYPE_MONITOR)) return; - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_bss_info_changed(local, sdata, info, changed); if (local->ops->bss_info_changed) @@ -278,7 +281,8 @@ static inline int drv_set_key(struct ieee80211_local *local, might_sleep(); sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_set_key(local, cmd, sdata, sta, key); ret = local->ops->set_key(&local->hw, cmd, &sdata->vif, sta, key); @@ -298,7 +302,8 @@ static inline void drv_update_tkip_key(struct ieee80211_local *local, ista = &sta->sta; sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_update_tkip_key(local, sdata, conf, ista, iv32); if (local->ops->update_tkip_key) @@ -315,7 +320,8 @@ static inline int drv_hw_scan(struct ieee80211_local *local, might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_hw_scan(local, sdata); ret = local->ops->hw_scan(&local->hw, &sdata->vif, req); @@ -328,7 +334,8 @@ static inline void drv_cancel_hw_scan(struct ieee80211_local *local, { might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_cancel_hw_scan(local, sdata); local->ops->cancel_hw_scan(&local->hw, &sdata->vif); @@ -345,7 +352,8 @@ drv_sched_scan_start(struct ieee80211_local *local, might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_sched_scan_start(local, sdata); ret = local->ops->sched_scan_start(&local->hw, &sdata->vif, @@ -361,7 +369,8 @@ static inline int drv_sched_scan_stop(struct ieee80211_local *local, might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_sched_scan_stop(local, sdata); ret = local->ops->sched_scan_stop(&local->hw, &sdata->vif); @@ -462,7 +471,8 @@ static inline void drv_sta_notify(struct ieee80211_local *local, struct ieee80211_sta *sta) { sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_sta_notify(local, sdata, cmd, sta); if (local->ops->sta_notify) @@ -479,7 +489,8 @@ static inline int drv_sta_add(struct ieee80211_local *local, might_sleep(); sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_sta_add(local, sdata, sta); if (local->ops->sta_add) @@ -497,7 +508,8 @@ static inline void drv_sta_remove(struct ieee80211_local *local, might_sleep(); sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_sta_remove(local, sdata, sta); if (local->ops->sta_remove) @@ -515,7 +527,8 @@ static inline void drv_sta_add_debugfs(struct ieee80211_local *local, might_sleep(); sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; if (local->ops->sta_add_debugfs) local->ops->sta_add_debugfs(&local->hw, &sdata->vif, @@ -545,7 +558,8 @@ static inline void drv_sta_pre_rcu_remove(struct ieee80211_local *local, might_sleep(); sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_sta_pre_rcu_remove(local, sdata, &sta->sta); if (local->ops->sta_pre_rcu_remove) @@ -566,7 +580,8 @@ int drv_sta_state(struct ieee80211_local *local, might_sleep(); sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_sta_state(local, sdata, &sta->sta, old_state, new_state); if (local->ops->sta_state) { @@ -590,7 +605,8 @@ static inline void drv_sta_rc_update(struct ieee80211_local *local, struct ieee80211_sta *sta, u32 changed) { sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; WARN_ON(changed & IEEE80211_RC_SUPP_RATES_CHANGED && (sdata->vif.type != NL80211_IFTYPE_ADHOC && @@ -612,7 +628,8 @@ static inline int drv_conf_tx(struct ieee80211_local *local, might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_conf_tx(local, sdata, ac, params); if (local->ops->conf_tx) @@ -629,7 +646,8 @@ static inline u64 drv_get_tsf(struct ieee80211_local *local, might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return ret; trace_drv_get_tsf(local, sdata); if (local->ops->get_tsf) @@ -644,7 +662,8 @@ static inline void drv_set_tsf(struct ieee80211_local *local, { might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_set_tsf(local, sdata, tsf); if (local->ops->set_tsf) @@ -657,7 +676,8 @@ static inline void drv_reset_tsf(struct ieee80211_local *local, { might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_reset_tsf(local, sdata); if (local->ops->reset_tsf) @@ -689,7 +709,8 @@ static inline int drv_ampdu_action(struct ieee80211_local *local, might_sleep(); sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, buf_size); @@ -733,8 +754,8 @@ static inline void drv_flush(struct ieee80211_local *local, might_sleep(); - if (sdata) - check_sdata_in_driver(sdata); + if (sdata && !check_sdata_in_driver(sdata)) + return; trace_drv_flush(local, queues, drop); if (local->ops->flush) @@ -854,7 +875,8 @@ static inline int drv_set_bitrate_mask(struct ieee80211_local *local, might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_set_bitrate_mask(local, sdata, mask); if (local->ops->set_bitrate_mask) @@ -869,7 +891,8 @@ static inline void drv_set_rekey_data(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct cfg80211_gtk_rekey_data *data) { - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_set_rekey_data(local, sdata, data); if (local->ops->set_rekey_data) @@ -937,7 +960,8 @@ static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, { might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION); trace_drv_mgd_prepare_tx(local, sdata); @@ -964,6 +988,9 @@ static inline int drv_add_chanctx(struct ieee80211_local *local, static inline void drv_remove_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { + if (WARN_ON(!ctx->driver_present)) + return; + trace_drv_remove_chanctx(local, ctx); if (local->ops->remove_chanctx) local->ops->remove_chanctx(&local->hw, &ctx->conf); @@ -989,7 +1016,8 @@ static inline int drv_assign_vif_chanctx(struct ieee80211_local *local, { int ret = 0; - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_assign_vif_chanctx(local, sdata, ctx); if (local->ops->assign_vif_chanctx) { @@ -1007,7 +1035,8 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_chanctx *ctx) { - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_unassign_vif_chanctx(local, sdata, ctx); if (local->ops->unassign_vif_chanctx) { @@ -1019,12 +1048,66 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline int +drv_switch_vif_chanctx(struct ieee80211_local *local, + struct ieee80211_vif_chanctx_switch *vifs, + int n_vifs, + enum ieee80211_chanctx_switch_mode mode) +{ + int ret = 0; + int i; + + if (!local->ops->switch_vif_chanctx) + return -EOPNOTSUPP; + + for (i = 0; i < n_vifs; i++) { + struct ieee80211_chanctx *new_ctx = + container_of(vifs[i].new_ctx, + struct ieee80211_chanctx, + conf); + struct ieee80211_chanctx *old_ctx = + container_of(vifs[i].old_ctx, + struct ieee80211_chanctx, + conf); + + WARN_ON_ONCE(!old_ctx->driver_present); + WARN_ON_ONCE((mode == CHANCTX_SWMODE_SWAP_CONTEXTS && + new_ctx->driver_present) || + (mode == CHANCTX_SWMODE_REASSIGN_VIF && + !new_ctx->driver_present)); + } + + trace_drv_switch_vif_chanctx(local, vifs, n_vifs, mode); + ret = local->ops->switch_vif_chanctx(&local->hw, + vifs, n_vifs, mode); + trace_drv_return_int(local, ret); + + if (!ret && mode == CHANCTX_SWMODE_SWAP_CONTEXTS) { + for (i = 0; i < n_vifs; i++) { + struct ieee80211_chanctx *new_ctx = + container_of(vifs[i].new_ctx, + struct ieee80211_chanctx, + conf); + struct ieee80211_chanctx *old_ctx = + container_of(vifs[i].old_ctx, + struct ieee80211_chanctx, + conf); + + new_ctx->driver_present = true; + old_ctx->driver_present = false; + } + } + + return ret; +} + static inline int drv_start_ap(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { int ret = 0; - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_start_ap(local, sdata, &sdata->vif.bss_conf); if (local->ops->start_ap) @@ -1036,7 +1119,8 @@ static inline int drv_start_ap(struct ieee80211_local *local, static inline void drv_stop_ap(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_stop_ap(local, sdata); if (local->ops->stop_ap) @@ -1059,7 +1143,8 @@ drv_set_default_unicast_key(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, int key_idx) { - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; WARN_ON_ONCE(key_idx < -1 || key_idx > 3); @@ -1101,7 +1186,8 @@ static inline int drv_join_ibss(struct ieee80211_local *local, int ret = 0; might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; trace_drv_join_ibss(local, sdata, &sdata->vif.bss_conf); if (local->ops->join_ibss) @@ -1114,7 +1200,8 @@ static inline void drv_leave_ibss(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { might_sleep(); - check_sdata_in_driver(sdata); + if (!check_sdata_in_driver(sdata)) + return; trace_drv_leave_ibss(local, sdata); if (local->ops->leave_ibss) @@ -1122,4 +1209,17 @@ static inline void drv_leave_ibss(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline u32 drv_get_expected_throughput(struct ieee80211_local *local, + struct ieee80211_sta *sta) +{ + u32 ret = 0; + + trace_drv_get_expected_throughput(sta); + if (local->ops->get_expected_throughput) + ret = local->ops->get_expected_throughput(sta); + trace_drv_return_u32(local, ret); + + return ret; +} + #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index ff4d415..18ee0a2 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -143,7 +143,7 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, *pos++ = csa_settings->block_tx ? 1 : 0; *pos++ = ieee80211_frequency_to_channel( csa_settings->chandef.chan->center_freq); - sdata->csa_counter_offset_beacon = (pos - presp->head); + sdata->csa_counter_offset_beacon[0] = (pos - presp->head); *pos++ = csa_settings->count; } @@ -1677,6 +1677,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, sdata->u.ibss.control_port = params->control_port; sdata->u.ibss.userspace_handles_dfs = params->userspace_handles_dfs; sdata->u.ibss.basic_rates = params->basic_rates; + sdata->u.ibss.last_scan_completed = jiffies; /* fix basic_rates if channel does not support these rates */ rate_flags = ieee80211_chandef_rate_flags(¶ms->chandef); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b455f62..ac9836e 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -317,6 +317,7 @@ struct ieee80211_roc_work { bool started, abort, hw_begun, notified; bool to_be_freed; + bool on_channel; unsigned long hw_start_time; @@ -753,9 +754,10 @@ struct ieee80211_sub_if_data { struct mac80211_qos_map __rcu *qos_map; struct work_struct csa_finalize_work; - int csa_counter_offset_beacon; - int csa_counter_offset_presp; + u16 csa_counter_offset_beacon[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 csa_counter_offset_presp[IEEE80211_MAX_CSA_COUNTERS_NUM]; bool csa_radar_required; + bool csa_block_tx; /* write-protected by sdata_lock and local->mtx */ struct cfg80211_chan_def csa_chandef; struct list_head assigned_chanctx_list; /* protected by chanctx_mtx */ @@ -765,6 +767,7 @@ struct ieee80211_sub_if_data { struct ieee80211_chanctx *reserved_chanctx; struct cfg80211_chan_def reserved_chandef; bool reserved_radar_required; + u8 csa_current_counter; /* used to reconfigure hardware SM PS */ struct work_struct recalc_smps; @@ -1458,6 +1461,7 @@ __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req); int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata); +void ieee80211_sched_scan_end(struct ieee80211_local *local); void ieee80211_sched_scan_stopped_work(struct work_struct *work); /* off-channel helpers */ @@ -1472,6 +1476,7 @@ void ieee80211_sw_roc_work(struct work_struct *work); void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc); /* channel switch handling */ +bool ieee80211_csa_needs_block_tx(struct ieee80211_local *local); void ieee80211_csa_finalize_work(struct work_struct *work); int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params); @@ -1833,6 +1838,15 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, u8 radar_detect); int ieee80211_max_num_channels(struct ieee80211_local *local); +/* TDLS */ +int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, u32 peer_capability, + const u8 *extra_ies, size_t extra_ies_len); +int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, enum nl80211_tdls_operation oper); + + #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline #else diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7fff3dc..81a8e2a 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -399,6 +399,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) sdata->vif.type = NL80211_IFTYPE_MONITOR; snprintf(sdata->name, IFNAMSIZ, "%s-monitor", wiphy_name(local->hw.wiphy)); + sdata->wdev.iftype = NL80211_IFTYPE_MONITOR; sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; @@ -838,8 +839,15 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, cancel_work_sync(&sdata->recalc_smps); sdata_lock(sdata); + mutex_lock(&local->mtx); sdata->vif.csa_active = false; + if (!ieee80211_csa_needs_block_tx(local)) + ieee80211_wake_queues_by_reason(&local->hw, + IEEE80211_MAX_QUEUE_MAP, + IEEE80211_QUEUE_STOP_REASON_CSA); + mutex_unlock(&local->mtx); sdata_unlock(sdata); + cancel_work_sync(&sdata->csa_finalize_work); cancel_delayed_work_sync(&sdata->dfs_cac_timer_work); @@ -1278,6 +1286,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->control_port_protocol = cpu_to_be16(ETH_P_PAE); sdata->control_port_no_encrypt = false; sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; + sdata->vif.bss_conf.idle = true; sdata->noack_map = 0; diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 6ff65a1..16d97f0 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -325,7 +325,8 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, struct ieee80211_key *key; int i, j, err; - BUG_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS); + if (WARN_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS)) + return ERR_PTR(-EINVAL); key = kzalloc(sizeof(struct ieee80211_key) + key_len, GFP_KERNEL); if (!key) @@ -481,8 +482,8 @@ int ieee80211_key_link(struct ieee80211_key *key, int idx, ret; bool pairwise; - BUG_ON(!sdata); - BUG_ON(!key); + if (WARN_ON(!sdata || !key)) + return -EINVAL; pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; idx = key->conf.keyidx; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 27b9364..d17c26d 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -956,6 +956,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (local->hw.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) local->hw.wiphy->flags |= WIPHY_FLAG_TDLS_EXTERNAL_SETUP; + local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM; + result = wiphy_register(local->hw.wiphy); if (result < 0) goto fail_wiphy_register; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index b06ddc9..6495a3f 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -679,7 +679,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) *pos++ = 0x0; *pos++ = ieee80211_frequency_to_channel( csa->settings.chandef.chan->center_freq); - sdata->csa_counter_offset_beacon = hdr_len + 6; + sdata->csa_counter_offset_beacon[0] = hdr_len + 6; *pos++ = csa->settings.count; *pos++ = WLAN_EID_CHAN_SWITCH_PARAM; *pos++ = 6; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 7d050ed..cf032a8 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -287,8 +287,10 @@ static void mesh_path_move_to_queue(struct mesh_path *gate_mpath, struct sk_buff_head failq; unsigned long flags; - BUG_ON(gate_mpath == from_mpath); - BUG_ON(!gate_mpath->next_hop); + if (WARN_ON(gate_mpath == from_mpath)) + return; + if (WARN_ON(!gate_mpath->next_hop)) + return; __skb_queue_head_init(&failq); diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c index 2bc5dc2..09625d6 100644 --- a/net/mac80211/mesh_sync.c +++ b/net/mac80211/mesh_sync.c @@ -171,7 +171,7 @@ static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata, u8 cap; WARN_ON(ifmsh->mesh_sp_id != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET); - BUG_ON(!rcu_read_lock_held()); + WARN_ON(!rcu_read_lock_held()); cap = beacon->meshconf->meshconf_cap; spin_lock_bh(&ifmsh->sync_offset_lock); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 488826f..3345401 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -975,16 +975,23 @@ static void ieee80211_chswitch_work(struct work_struct *work) /* XXX: shouldn't really modify cfg80211-owned data! */ ifmgd->associated->channel = sdata->csa_chandef.chan; + ieee80211_bss_info_change_notify(sdata, changed); + + mutex_lock(&local->mtx); + sdata->vif.csa_active = false; /* XXX: wait for a beacon first? */ - ieee80211_wake_queues_by_reason(&local->hw, + if (!ieee80211_csa_needs_block_tx(local)) + ieee80211_wake_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); + mutex_unlock(&local->mtx); - ieee80211_bss_info_change_notify(sdata, changed); - - out: - sdata->vif.csa_active = false; ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; + + ieee80211_sta_reset_beacon_monitor(sdata); + ieee80211_sta_reset_conn_monitor(sdata); + +out: sdata_unlock(sdata); } @@ -1100,12 +1107,16 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, mutex_unlock(&local->chanctx_mtx); sdata->csa_chandef = csa_ie.chandef; + + mutex_lock(&local->mtx); sdata->vif.csa_active = true; + sdata->csa_block_tx = csa_ie.mode; - if (csa_ie.mode) + if (sdata->csa_block_tx) ieee80211_stop_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); + IEEE80211_MAX_QUEUE_MAP, + IEEE80211_QUEUE_STOP_REASON_CSA); + mutex_unlock(&local->mtx); if (local->ops->channel_switch) { /* use driver's channel switch callback */ @@ -1817,6 +1828,12 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ifmgd->flags = 0; mutex_lock(&local->mtx); ieee80211_vif_release_channel(sdata); + + sdata->vif.csa_active = false; + if (!ieee80211_csa_needs_block_tx(local)) + ieee80211_wake_queues_by_reason(&local->hw, + IEEE80211_MAX_QUEUE_MAP, + IEEE80211_QUEUE_STOP_REASON_CSA); mutex_unlock(&local->mtx); sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; @@ -2045,6 +2062,7 @@ EXPORT_SYMBOL(ieee80211_ap_probereq_get); static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) { + struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; @@ -2058,10 +2076,14 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, true, frame_buf); ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; + + mutex_lock(&local->mtx); sdata->vif.csa_active = false; - ieee80211_wake_queues_by_reason(&sdata->local->hw, + if (!ieee80211_csa_needs_block_tx(local)) + ieee80211_wake_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); + mutex_unlock(&local->mtx); cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, IEEE80211_DEAUTH_FRAME_LEN); @@ -3546,6 +3568,9 @@ static void ieee80211_sta_bcn_mon_timer(unsigned long data) if (local->quiescing) return; + if (sdata->vif.csa_active) + return; + sdata->u.mgd.connection_loss = false; ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.beacon_connection_loss_work); @@ -3561,6 +3586,9 @@ static void ieee80211_sta_conn_mon_timer(unsigned long data) if (local->quiescing) return; + if (sdata->vif.csa_active) + return; + ieee80211_queue_work(&local->hw, &ifmgd->monitor_work); } @@ -3598,18 +3626,24 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata) sdata_lock(sdata); - if (ifmgd->auth_data) { + if (ifmgd->auth_data || ifmgd->assoc_data) { + const u8 *bssid = ifmgd->auth_data ? + ifmgd->auth_data->bss->bssid : + ifmgd->assoc_data->bss->bssid; + /* - * If we are trying to authenticate while suspending, cfg80211 - * won't know and won't actually abort those attempts, thus we - * need to do that ourselves. + * If we are trying to authenticate / associate while suspending, + * cfg80211 won't know and won't actually abort those attempts, + * thus we need to do that ourselves. */ - ieee80211_send_deauth_disassoc(sdata, - ifmgd->auth_data->bss->bssid, + ieee80211_send_deauth_disassoc(sdata, bssid, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DEAUTH_LEAVING, false, frame_buf); - ieee80211_destroy_auth_data(sdata, false); + if (ifmgd->assoc_data) + ieee80211_destroy_assoc_data(sdata, false); + if (ifmgd->auth_data) + ieee80211_destroy_auth_data(sdata, false); cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, IEEE80211_DEAUTH_FRAME_LEN); } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 6fb3855..7a17dec 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work) container_of(work, struct ieee80211_roc_work, work.work); struct ieee80211_sub_if_data *sdata = roc->sdata; struct ieee80211_local *local = sdata->local; - bool started; + bool started, on_channel; mutex_lock(&local->mtx); @@ -354,14 +354,26 @@ void ieee80211_sw_roc_work(struct work_struct *work) if (!roc->started) { struct ieee80211_roc_work *dep; - /* start this ROC */ - ieee80211_offchannel_stop_vifs(local); + WARN_ON(local->use_chanctx); + + /* If actually operating on the desired channel (with at least + * 20 MHz channel width) don't stop all the operations but still + * treat it as though the ROC operation started properly, so + * other ROC operations won't interfere with this one. + */ + roc->on_channel = roc->chan == local->_oper_chandef.chan && + local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 && + local->_oper_chandef.width != NL80211_CHAN_WIDTH_10; - /* switch channel etc */ + /* start this ROC */ ieee80211_recalc_idle(local); - local->tmp_channel = roc->chan; - ieee80211_hw_config(local, 0); + if (!roc->on_channel) { + ieee80211_offchannel_stop_vifs(local); + + local->tmp_channel = roc->chan; + ieee80211_hw_config(local, 0); + } /* tell userspace or send frame */ ieee80211_handle_roc_started(roc); @@ -380,9 +392,10 @@ void ieee80211_sw_roc_work(struct work_struct *work) finish: list_del(&roc->list); started = roc->started; + on_channel = roc->on_channel; ieee80211_roc_notify_destroy(roc, !roc->abort); - if (started) { + if (started && !on_channel) { ieee80211_flush_queues(local, NULL); local->tmp_channel = NULL; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 26fd94f..1c1469c 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -657,6 +657,17 @@ minstrel_free(void *priv) kfree(priv); } +static u32 minstrel_get_expected_throughput(void *priv_sta) +{ + struct minstrel_sta_info *mi = priv_sta; + int idx = mi->max_tp_rate[0]; + + /* convert pkt per sec in kbps (1200 is the average pkt size used for + * computing cur_tp + */ + return MINSTREL_TRUNC(mi->r[idx].cur_tp) * 1200 * 8 / 1024; +} + const struct rate_control_ops mac80211_minstrel = { .name = "minstrel", .tx_status = minstrel_tx_status, @@ -670,6 +681,7 @@ const struct rate_control_ops mac80211_minstrel = { .add_sta_debugfs = minstrel_add_sta_debugfs, .remove_sta_debugfs = minstrel_remove_sta_debugfs, #endif + .get_expected_throughput = minstrel_get_expected_throughput, }; int __init diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index bccaf85..85c1e74 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -22,7 +22,7 @@ #define MCS_NBITS (AVG_PKT_SIZE << 3) /* Number of symbols for a packet with (bps) bits per symbol */ -#define MCS_NSYMS(bps) ((MCS_NBITS + (bps) - 1) / (bps)) +#define MCS_NSYMS(bps) DIV_ROUND_UP(MCS_NBITS, (bps)) /* Transmission time (nanoseconds) for a packet containing (syms) symbols */ #define MCS_SYMBOL_TIME(sgi, syms) \ @@ -226,8 +226,9 @@ minstrel_ht_calc_tp(struct minstrel_ht_sta *mi, int group, int rate) nsecs = 1000 * mi->overhead / MINSTREL_TRUNC(mi->avg_ampdu_len); nsecs += minstrel_mcs_groups[group].duration[rate]; - tp = 1000000 * ((prob * 1000) / nsecs); + /* prob is scaled - see MINSTREL_FRAC above */ + tp = 1000000 * ((prob * 1000) / nsecs); mr->cur_tp = MINSTREL_TRUNC(tp); } @@ -1031,6 +1032,22 @@ minstrel_ht_free(void *priv) mac80211_minstrel.free(priv); } +static u32 minstrel_ht_get_expected_throughput(void *priv_sta) +{ + struct minstrel_ht_sta_priv *msp = priv_sta; + struct minstrel_ht_sta *mi = &msp->ht; + int i, j; + + if (!msp->is_ht) + return mac80211_minstrel.get_expected_throughput(priv_sta); + + i = mi->max_tp_rate / MCS_GROUP_RATES; + j = mi->max_tp_rate % MCS_GROUP_RATES; + + /* convert cur_tp from pkt per second in kbps */ + return mi->groups[i].rates[j].cur_tp * AVG_PKT_SIZE * 8 / 1024; +} + static const struct rate_control_ops mac80211_minstrel_ht = { .name = "minstrel_ht", .tx_status = minstrel_ht_tx_status, @@ -1045,6 +1062,7 @@ static const struct rate_control_ops mac80211_minstrel_ht = { .add_sta_debugfs = minstrel_ht_add_sta_debugfs, .remove_sta_debugfs = minstrel_ht_remove_sta_debugfs, #endif + .get_expected_throughput = minstrel_ht_get_expected_throughput, }; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 28185c8..f40661e 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -1076,12 +1076,8 @@ void ieee80211_sched_scan_results(struct ieee80211_hw *hw) } EXPORT_SYMBOL(ieee80211_sched_scan_results); -void ieee80211_sched_scan_stopped_work(struct work_struct *work) +void ieee80211_sched_scan_end(struct ieee80211_local *local) { - struct ieee80211_local *local = - container_of(work, struct ieee80211_local, - sched_scan_stopped_work); - mutex_lock(&local->mtx); if (!rcu_access_pointer(local->sched_scan_sdata)) { @@ -1099,6 +1095,15 @@ void ieee80211_sched_scan_stopped_work(struct work_struct *work) cfg80211_sched_scan_stopped(local->hw.wiphy); } +void ieee80211_sched_scan_stopped_work(struct work_struct *work) +{ + struct ieee80211_local *local = + container_of(work, struct ieee80211_local, + sched_scan_stopped_work); + + ieee80211_sched_scan_end(local); +} + void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 632d372..a9b46d8 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -240,6 +240,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr); + kfree(rcu_dereference_raw(sta->sta.rates)); kfree(sta); } diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 60cb7a6..ba29ebc 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -541,6 +541,23 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local, */ #define STA_LOST_PKT_THRESHOLD 50 +static void ieee80211_lost_packet(struct sta_info *sta, struct sk_buff *skb) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + /* This packet was aggregated but doesn't carry status info */ + if ((info->flags & IEEE80211_TX_CTL_AMPDU) && + !(info->flags & IEEE80211_TX_STAT_AMPDU)) + return; + + if (++sta->lost_packets < STA_LOST_PKT_THRESHOLD) + return; + + cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr, + sta->lost_packets, GFP_ATOMIC); + sta->lost_packets = 0; +} + void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) { struct sk_buff *skb2; @@ -680,12 +697,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (info->flags & IEEE80211_TX_STAT_ACK) { if (sta->lost_packets) sta->lost_packets = 0; - } else if (++sta->lost_packets >= STA_LOST_PKT_THRESHOLD) { - cfg80211_cqm_pktloss_notify(sta->sdata->dev, - sta->sta.addr, - sta->lost_packets, - GFP_ATOMIC); - sta->lost_packets = 0; + } else { + ieee80211_lost_packet(sta, skb); } } diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c new file mode 100644 index 0000000..652813b --- /dev/null +++ b/net/mac80211/tdls.c @@ -0,0 +1,325 @@ +/* + * mac80211 TDLS handling code + * + * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2014, Intel Corporation + * + * This file is GPLv2 as found in COPYING. + */ + +#include <linux/ieee80211.h> +#include "ieee80211_i.h" + +static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb) +{ + u8 *pos = (void *)skb_put(skb, 7); + + *pos++ = WLAN_EID_EXT_CAPABILITY; + *pos++ = 5; /* len */ + *pos++ = 0x0; + *pos++ = 0x0; + *pos++ = 0x0; + *pos++ = 0x0; + *pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED; +} + +static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + u16 capab; + + capab = 0; + if (ieee80211_get_sdata_band(sdata) != IEEE80211_BAND_2GHZ) + return capab; + + if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE)) + capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME; + if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE)) + capab |= WLAN_CAPABILITY_SHORT_PREAMBLE; + + return capab; +} + +static void ieee80211_tdls_add_link_ie(struct sk_buff *skb, const u8 *src_addr, + const u8 *peer, const u8 *bssid) +{ + struct ieee80211_tdls_lnkie *lnkid; + + lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie)); + + lnkid->ie_type = WLAN_EID_LINK_ID; + lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2; + + memcpy(lnkid->bssid, bssid, ETH_ALEN); + memcpy(lnkid->init_sta, src_addr, ETH_ALEN); + memcpy(lnkid->resp_sta, peer, ETH_ALEN); +} + +static int +ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, struct sk_buff *skb) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); + struct ieee80211_tdls_data *tf; + + tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u)); + + memcpy(tf->da, peer, ETH_ALEN); + memcpy(tf->sa, sdata->vif.addr, ETH_ALEN); + tf->ether_type = cpu_to_be16(ETH_P_TDLS); + tf->payload_type = WLAN_TDLS_SNAP_RFTYPE; + + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_SETUP_REQUEST; + + skb_put(skb, sizeof(tf->u.setup_req)); + tf->u.setup_req.dialog_token = dialog_token; + tf->u.setup_req.capability = + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); + + ieee80211_add_srates_ie(sdata, skb, false, band); + ieee80211_add_ext_srates_ie(sdata, skb, false, band); + ieee80211_tdls_add_ext_capab(skb); + break; + case WLAN_TDLS_SETUP_RESPONSE: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_SETUP_RESPONSE; + + skb_put(skb, sizeof(tf->u.setup_resp)); + tf->u.setup_resp.status_code = cpu_to_le16(status_code); + tf->u.setup_resp.dialog_token = dialog_token; + tf->u.setup_resp.capability = + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); + + ieee80211_add_srates_ie(sdata, skb, false, band); + ieee80211_add_ext_srates_ie(sdata, skb, false, band); + ieee80211_tdls_add_ext_capab(skb); + break; + case WLAN_TDLS_SETUP_CONFIRM: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_SETUP_CONFIRM; + + skb_put(skb, sizeof(tf->u.setup_cfm)); + tf->u.setup_cfm.status_code = cpu_to_le16(status_code); + tf->u.setup_cfm.dialog_token = dialog_token; + break; + case WLAN_TDLS_TEARDOWN: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_TEARDOWN; + + skb_put(skb, sizeof(tf->u.teardown)); + tf->u.teardown.reason_code = cpu_to_le16(status_code); + break; + case WLAN_TDLS_DISCOVERY_REQUEST: + tf->category = WLAN_CATEGORY_TDLS; + tf->action_code = WLAN_TDLS_DISCOVERY_REQUEST; + + skb_put(skb, sizeof(tf->u.discover_req)); + tf->u.discover_req.dialog_token = dialog_token; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int +ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, struct sk_buff *skb) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); + struct ieee80211_mgmt *mgmt; + + mgmt = (void *)skb_put(skb, 24); + memset(mgmt, 0, 24); + memcpy(mgmt->da, peer, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN); + + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + + switch (action_code) { + case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: + skb_put(skb, 1 + sizeof(mgmt->u.action.u.tdls_discover_resp)); + mgmt->u.action.category = WLAN_CATEGORY_PUBLIC; + mgmt->u.action.u.tdls_discover_resp.action_code = + WLAN_PUB_ACTION_TDLS_DISCOVER_RES; + mgmt->u.action.u.tdls_discover_resp.dialog_token = + dialog_token; + mgmt->u.action.u.tdls_discover_resp.capability = + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); + + ieee80211_add_srates_ie(sdata, skb, false, band); + ieee80211_add_ext_srates_ie(sdata, skb, false, band); + ieee80211_tdls_add_ext_capab(skb); + break; + default: + return -EINVAL; + } + + return 0; +} + +int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, u32 peer_capability, + const u8 *extra_ies, size_t extra_ies_len) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + struct sk_buff *skb = NULL; + bool send_direct; + int ret; + + if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) + return -ENOTSUPP; + + /* make sure we are in managed mode, and associated */ + if (sdata->vif.type != NL80211_IFTYPE_STATION || + !sdata->u.mgd.associated) + return -EINVAL; + + tdls_dbg(sdata, "TDLS mgmt action %d peer %pM\n", + action_code, peer); + + skb = dev_alloc_skb(local->hw.extra_tx_headroom + + max(sizeof(struct ieee80211_mgmt), + sizeof(struct ieee80211_tdls_data)) + + 50 + /* supported rates */ + 7 + /* ext capab */ + extra_ies_len + + sizeof(struct ieee80211_tdls_lnkie)); + if (!skb) + return -ENOMEM; + + skb_reserve(skb, local->hw.extra_tx_headroom); + + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + case WLAN_TDLS_SETUP_RESPONSE: + case WLAN_TDLS_SETUP_CONFIRM: + case WLAN_TDLS_TEARDOWN: + case WLAN_TDLS_DISCOVERY_REQUEST: + ret = ieee80211_prep_tdls_encap_data(wiphy, dev, peer, + action_code, dialog_token, + status_code, skb); + send_direct = false; + break; + case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: + ret = ieee80211_prep_tdls_direct(wiphy, dev, peer, action_code, + dialog_token, status_code, + skb); + send_direct = true; + break; + default: + ret = -ENOTSUPP; + break; + } + + if (ret < 0) + goto fail; + + if (extra_ies_len) + memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len); + + /* the TDLS link IE is always added last */ + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + case WLAN_TDLS_SETUP_CONFIRM: + case WLAN_TDLS_TEARDOWN: + case WLAN_TDLS_DISCOVERY_REQUEST: + /* we are the initiator */ + ieee80211_tdls_add_link_ie(skb, sdata->vif.addr, peer, + sdata->u.mgd.bssid); + break; + case WLAN_TDLS_SETUP_RESPONSE: + case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: + /* we are the responder */ + ieee80211_tdls_add_link_ie(skb, peer, sdata->vif.addr, + sdata->u.mgd.bssid); + break; + default: + ret = -ENOTSUPP; + goto fail; + } + + if (send_direct) { + ieee80211_tx_skb(sdata, skb); + return 0; + } + + /* + * According to 802.11z: Setup req/resp are sent in AC_BK, otherwise + * we should default to AC_VI. + */ + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + case WLAN_TDLS_SETUP_RESPONSE: + skb_set_queue_mapping(skb, IEEE80211_AC_BK); + skb->priority = 2; + break; + default: + skb_set_queue_mapping(skb, IEEE80211_AC_VI); + skb->priority = 5; + break; + } + + /* disable bottom halves when entering the Tx path */ + local_bh_disable(); + ret = ieee80211_subif_start_xmit(skb, dev); + local_bh_enable(); + + return ret; + +fail: + dev_kfree_skb(skb); + return ret; +} + +int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, enum nl80211_tdls_operation oper) +{ + struct sta_info *sta; + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) + return -ENOTSUPP; + + if (sdata->vif.type != NL80211_IFTYPE_STATION) + return -EINVAL; + + tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer); + + switch (oper) { + case NL80211_TDLS_ENABLE_LINK: + rcu_read_lock(); + sta = sta_info_get(sdata, peer); + if (!sta) { + rcu_read_unlock(); + return -ENOLINK; + } + + set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); + rcu_read_unlock(); + break; + case NL80211_TDLS_DISABLE_LINK: + return sta_info_destroy_addr(sdata, peer); + case NL80211_TDLS_TEARDOWN: + case NL80211_TDLS_SETUP: + case NL80211_TDLS_DISCOVERY_REQ: + /* We don't support in-driver setup/teardown/discovery */ + return -ENOTSUPP; + default: + return -ENOTSUPP; + } + + return 0; +} diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index a0b0aea..cfe1a06 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -21,10 +21,10 @@ #define VIF_ENTRY __field(enum nl80211_iftype, vif_type) __field(void *, sdata) \ __field(bool, p2p) \ - __string(vif_name, sdata->dev ? sdata->dev->name : "<nodev>") + __string(vif_name, sdata->name) #define VIF_ASSIGN __entry->vif_type = sdata->vif.type; __entry->sdata = sdata; \ __entry->p2p = sdata->vif.p2p; \ - __assign_str(vif_name, sdata->dev ? sdata->dev->name : sdata->name) + __assign_str(vif_name, sdata->name) #define VIF_PR_FMT " vif:%s(%d%s)" #define VIF_PR_ARG __get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : "" @@ -184,6 +184,20 @@ TRACE_EVENT(drv_return_bool, "true" : "false") ); +TRACE_EVENT(drv_return_u32, + TP_PROTO(struct ieee80211_local *local, u32 ret), + TP_ARGS(local, ret), + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u32, ret) + ), + TP_fast_assign( + LOCAL_ASSIGN; + __entry->ret = ret; + ), + TP_printk(LOCAL_PR_FMT " - %u", LOCAL_PR_ARG, __entry->ret) +); + TRACE_EVENT(drv_return_u64, TP_PROTO(struct ieee80211_local *local, u64 ret), TP_ARGS(local, ret), @@ -1375,6 +1389,91 @@ TRACE_EVENT(drv_change_chanctx, ) ); +#if !defined(__TRACE_VIF_ENTRY) +#define __TRACE_VIF_ENTRY +struct trace_vif_entry { + enum nl80211_iftype vif_type; + bool p2p; + char vif_name[IFNAMSIZ]; +} __packed; + +struct trace_chandef_entry { + u32 control_freq; + u32 chan_width; + u32 center_freq1; + u32 center_freq2; +} __packed; + +struct trace_switch_entry { + struct trace_vif_entry vif; + struct trace_chandef_entry old_chandef; + struct trace_chandef_entry new_chandef; +} __packed; + +#define SWITCH_ENTRY_ASSIGN(to, from) local_vifs[i].to = vifs[i].from +#endif + +TRACE_EVENT(drv_switch_vif_chanctx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_vif_chanctx_switch *vifs, + int n_vifs, enum ieee80211_chanctx_switch_mode mode), + TP_ARGS(local, vifs, n_vifs, mode), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(int, n_vifs) + __field(u32, mode) + __dynamic_array(u8, vifs, + sizeof(struct trace_switch_entry) * n_vifs) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->n_vifs = n_vifs; + __entry->mode = mode; + { + struct trace_switch_entry *local_vifs = + __get_dynamic_array(vifs); + int i; + + for (i = 0; i < n_vifs; i++) { + struct ieee80211_sub_if_data *sdata; + + sdata = container_of(vifs[i].vif, + struct ieee80211_sub_if_data, + vif); + + SWITCH_ENTRY_ASSIGN(vif.vif_type, vif->type); + SWITCH_ENTRY_ASSIGN(vif.p2p, vif->p2p); + strncpy(local_vifs[i].vif.vif_name, + sdata->name, + sizeof(local_vifs[i].vif.vif_name)); + SWITCH_ENTRY_ASSIGN(old_chandef.control_freq, + old_ctx->def.chan->center_freq); + SWITCH_ENTRY_ASSIGN(old_chandef.chan_width, + old_ctx->def.width); + SWITCH_ENTRY_ASSIGN(old_chandef.center_freq1, + old_ctx->def.center_freq1); + SWITCH_ENTRY_ASSIGN(old_chandef.center_freq2, + old_ctx->def.center_freq2); + SWITCH_ENTRY_ASSIGN(new_chandef.control_freq, + new_ctx->def.chan->center_freq); + SWITCH_ENTRY_ASSIGN(new_chandef.chan_width, + new_ctx->def.width); + SWITCH_ENTRY_ASSIGN(new_chandef.center_freq1, + new_ctx->def.center_freq1); + SWITCH_ENTRY_ASSIGN(new_chandef.center_freq2, + new_ctx->def.center_freq2); + } + } + ), + + TP_printk( + LOCAL_PR_FMT " n_vifs:%d mode:%d", + LOCAL_PR_ARG, __entry->n_vifs, __entry->mode + ) +); + DECLARE_EVENT_CLASS(local_sdata_chanctx, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, @@ -1499,6 +1598,24 @@ DEFINE_EVENT(local_sdata_evt, drv_leave_ibss, TP_ARGS(local, sdata) ); +TRACE_EVENT(drv_get_expected_throughput, + TP_PROTO(struct ieee80211_sta *sta), + + TP_ARGS(sta), + + TP_STRUCT__entry( + STA_ENTRY + ), + + TP_fast_assign( + STA_ASSIGN; + ), + + TP_printk( + STA_PR_FMT, STA_PR_ARG + ) +); + /* * Tracing for API calls that drivers call. */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 19d36d4..5214686 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2328,7 +2328,8 @@ void ieee80211_tx_pending(unsigned long data) /* functions for drivers to get certain frames */ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, - struct ps_data *ps, struct sk_buff *skb) + struct ps_data *ps, struct sk_buff *skb, + bool is_template) { u8 *pos, *tim; int aid0 = 0; @@ -2341,11 +2342,12 @@ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, * checking byte-for-byte */ have_bits = !bitmap_empty((unsigned long *)ps->tim, IEEE80211_MAX_AID+1); - - if (ps->dtim_count == 0) - ps->dtim_count = sdata->vif.bss_conf.dtim_period - 1; - else - ps->dtim_count--; + if (!is_template) { + if (ps->dtim_count == 0) + ps->dtim_count = sdata->vif.bss_conf.dtim_period - 1; + else + ps->dtim_count--; + } tim = pos = (u8 *) skb_put(skb, 6); *pos++ = WLAN_EID_TIM; @@ -2391,7 +2393,8 @@ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, } static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, - struct ps_data *ps, struct sk_buff *skb) + struct ps_data *ps, struct sk_buff *skb, + bool is_template) { struct ieee80211_local *local = sdata->local; @@ -2403,24 +2406,24 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, * of the tim bitmap in mac80211 and the driver. */ if (local->tim_in_locked_section) { - __ieee80211_beacon_add_tim(sdata, ps, skb); + __ieee80211_beacon_add_tim(sdata, ps, skb, is_template); } else { spin_lock_bh(&local->tim_lock); - __ieee80211_beacon_add_tim(sdata, ps, skb); + __ieee80211_beacon_add_tim(sdata, ps, skb, is_template); spin_unlock_bh(&local->tim_lock); } return 0; } -static void ieee80211_update_csa(struct ieee80211_sub_if_data *sdata, - struct beacon_data *beacon) +static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, + struct beacon_data *beacon) { struct probe_resp *resp; - int counter_offset_beacon = sdata->csa_counter_offset_beacon; - int counter_offset_presp = sdata->csa_counter_offset_presp; u8 *beacon_data; size_t beacon_data_len; + int i; + u8 count = sdata->csa_current_counter; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: @@ -2438,40 +2441,57 @@ static void ieee80211_update_csa(struct ieee80211_sub_if_data *sdata, default: return; } - if (WARN_ON(counter_offset_beacon >= beacon_data_len)) - return; - /* Warn if the driver did not check for/react to csa - * completeness. A beacon with CSA counter set to 0 should - * never occur, because a counter of 1 means switch just - * before the next beacon. - */ - if (WARN_ON(beacon_data[counter_offset_beacon] == 1)) - return; + for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) { + u16 counter_offset_beacon = + sdata->csa_counter_offset_beacon[i]; + u16 counter_offset_presp = sdata->csa_counter_offset_presp[i]; - beacon_data[counter_offset_beacon]--; + if (counter_offset_beacon) { + if (WARN_ON(counter_offset_beacon >= beacon_data_len)) + return; - if (sdata->vif.type == NL80211_IFTYPE_AP && counter_offset_presp) { - rcu_read_lock(); - resp = rcu_dereference(sdata->u.ap.probe_resp); + beacon_data[counter_offset_beacon] = count; + } + + if (sdata->vif.type == NL80211_IFTYPE_AP && + counter_offset_presp) { + rcu_read_lock(); + resp = rcu_dereference(sdata->u.ap.probe_resp); - /* if nl80211 accepted the offset, this should not happen. */ - if (WARN_ON(!resp)) { + /* If nl80211 accepted the offset, this should + * not happen. + */ + if (WARN_ON(!resp)) { + rcu_read_unlock(); + return; + } + resp->data[counter_offset_presp] = count; rcu_read_unlock(); - return; } - resp->data[counter_offset_presp]--; - rcu_read_unlock(); } } +u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + sdata->csa_current_counter--; + + /* the counter should never reach 0 */ + WARN_ON(!sdata->csa_current_counter); + + return sdata->csa_current_counter; +} +EXPORT_SYMBOL(ieee80211_csa_update_counter); + bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; u8 *beacon_data; size_t beacon_data_len; - int counter_beacon = sdata->csa_counter_offset_beacon; + int counter_beacon = sdata->csa_counter_offset_beacon[0]; int ret = false; if (!ieee80211_sdata_running(sdata)) @@ -2521,9 +2541,11 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) } EXPORT_SYMBOL(ieee80211_csa_is_complete); -struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - u16 *tim_offset, u16 *tim_length) +static struct sk_buff * +__ieee80211_beacon_get(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_mutable_offsets *offs, + bool is_template) { struct ieee80211_local *local = hw_to_local(hw); struct sk_buff *skb = NULL; @@ -2532,6 +2554,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, enum ieee80211_band band; struct ieee80211_tx_rate_control txrc; struct ieee80211_chanctx_conf *chanctx_conf; + int csa_off_base = 0; rcu_read_lock(); @@ -2541,18 +2564,20 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, if (!ieee80211_sdata_running(sdata) || !chanctx_conf) goto out; - if (tim_offset) - *tim_offset = 0; - if (tim_length) - *tim_length = 0; + if (offs) + memset(offs, 0, sizeof(*offs)); if (sdata->vif.type == NL80211_IFTYPE_AP) { struct ieee80211_if_ap *ap = &sdata->u.ap; struct beacon_data *beacon = rcu_dereference(ap->beacon); if (beacon) { - if (sdata->vif.csa_active) - ieee80211_update_csa(sdata, beacon); + if (sdata->vif.csa_active) { + if (!is_template) + ieee80211_csa_update_counter(vif); + + ieee80211_set_csa(sdata, beacon); + } /* * headroom, head length, @@ -2569,12 +2594,16 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, memcpy(skb_put(skb, beacon->head_len), beacon->head, beacon->head_len); - ieee80211_beacon_add_tim(sdata, &ap->ps, skb); + ieee80211_beacon_add_tim(sdata, &ap->ps, skb, + is_template); - if (tim_offset) - *tim_offset = beacon->head_len; - if (tim_length) - *tim_length = skb->len - beacon->head_len; + if (offs) { + offs->tim_offset = beacon->head_len; + offs->tim_length = skb->len - beacon->head_len; + + /* for AP the csa offsets are from tail */ + csa_off_base = skb->len; + } if (beacon->tail) memcpy(skb_put(skb, beacon->tail_len), @@ -2589,9 +2618,12 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, if (!presp) goto out; - if (sdata->vif.csa_active) - ieee80211_update_csa(sdata, presp); + if (sdata->vif.csa_active) { + if (!is_template) + ieee80211_csa_update_counter(vif); + ieee80211_set_csa(sdata, presp); + } skb = dev_alloc_skb(local->tx_headroom + presp->head_len + local->hw.extra_beacon_tailroom); @@ -2611,8 +2643,17 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, if (!bcn) goto out; - if (sdata->vif.csa_active) - ieee80211_update_csa(sdata, bcn); + if (sdata->vif.csa_active) { + if (!is_template) + /* TODO: For mesh csa_counter is in TU, so + * decrementing it by one isn't correct, but + * for now we leave it consistent with overall + * mac80211's behavior. + */ + ieee80211_csa_update_counter(vif); + + ieee80211_set_csa(sdata, bcn); + } if (ifmsh->sync_ops) ifmsh->sync_ops->adjust_tbtt(sdata, bcn); @@ -2626,13 +2667,33 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, goto out; skb_reserve(skb, local->tx_headroom); memcpy(skb_put(skb, bcn->head_len), bcn->head, bcn->head_len); - ieee80211_beacon_add_tim(sdata, &ifmsh->ps, skb); + ieee80211_beacon_add_tim(sdata, &ifmsh->ps, skb, is_template); + + if (offs) { + offs->tim_offset = bcn->head_len; + offs->tim_length = skb->len - bcn->head_len; + } + memcpy(skb_put(skb, bcn->tail_len), bcn->tail, bcn->tail_len); } else { WARN_ON(1); goto out; } + /* CSA offsets */ + if (offs) { + int i; + + for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) { + u16 csa_off = sdata->csa_counter_offset_beacon[i]; + + if (!csa_off) + continue; + + offs->csa_counter_offs[i] = csa_off_base + csa_off; + } + } + band = chanctx_conf->def.chan->band; info = IEEE80211_SKB_CB(skb); @@ -2663,6 +2724,32 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, out: rcu_read_unlock(); return skb; + +} + +struct sk_buff * +ieee80211_beacon_get_template(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_mutable_offsets *offs) +{ + return __ieee80211_beacon_get(hw, vif, offs, true); +} +EXPORT_SYMBOL(ieee80211_beacon_get_template); + +struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 *tim_offset, u16 *tim_length) +{ + struct ieee80211_mutable_offsets offs = {}; + struct sk_buff *bcn = __ieee80211_beacon_get(hw, vif, &offs, false); + + if (tim_offset) + *tim_offset = offs.tim_offset; + + if (tim_length) + *tim_length = offs.tim_length; + + return bcn; } EXPORT_SYMBOL(ieee80211_beacon_get_tim); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index c08bd4a..6886601 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1457,6 +1457,44 @@ void ieee80211_stop_device(struct ieee80211_local *local) drv_stop(local); } +static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + struct ieee80211_chanctx *ctx; + + /* + * We get here if during resume the device can't be restarted properly. + * We might also get here if this happens during HW reset, which is a + * slightly different situation and we need to drop all connections in + * the latter case. + * + * Ask cfg80211 to turn off all interfaces, this will result in more + * warnings but at least we'll then get into a clean stopped state. + */ + + local->resuming = false; + local->suspended = false; + local->started = false; + + /* scheduled scan clearly can't be running any more, but tell + * cfg80211 and clear local state + */ + ieee80211_sched_scan_end(local); + + list_for_each_entry(sdata, &local->interfaces, list) + sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER; + + /* Mark channel contexts as not being in the driver any more to avoid + * removing them from the driver during the shutdown process... + */ + mutex_lock(&local->chanctx_mtx); + list_for_each_entry(ctx, &local->chanctx_list, list) + ctx->driver_present = false; + mutex_unlock(&local->chanctx_mtx); + + cfg80211_shutdown_all_interfaces(local->hw.wiphy); +} + static void ieee80211_assign_chanctx(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { @@ -1520,9 +1558,11 @@ int ieee80211_reconfig(struct ieee80211_local *local) */ res = drv_start(local); if (res) { - WARN(local->suspended, "Hardware became unavailable " - "upon resume. This could be a software issue " - "prior to suspend or a hardware issue.\n"); + if (local->suspended) + WARN(1, "Hardware became unavailable upon resume. This could be a software issue prior to suspend or a hardware issue.\n"); + else + WARN(1, "Hardware became unavailable during restart.\n"); + ieee80211_handle_reconfig_failure(local); return res; } diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index e9e36a2..9265adf 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -129,9 +129,12 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, if (!vht_cap_ie || !sband->vht_cap.vht_supported) return; - /* A VHT STA must support 40 MHz */ - if (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40)) - return; + /* + * A VHT STA must support 40 MHz, but if we verify that here + * then we break a few things - some APs (e.g. Netgear R6300v2 + * and others based on the BCM4360 chipset) will unset this + * capability bit when operating in 20 MHz. + */ vht_cap->vht_supported = true; diff --git a/net/mac802154/Kconfig b/net/mac802154/Kconfig index b33dd76..1818a99 100644 --- a/net/mac802154/Kconfig +++ b/net/mac802154/Kconfig @@ -2,6 +2,10 @@ config MAC802154 tristate "Generic IEEE 802.15.4 Soft Networking Stack (mac802154)" depends on IEEE802154 select CRC_CCITT + select CRYPTO_AUTHENC + select CRYPTO_CCM + select CRYPTO_CTR + select CRYPTO_AES ---help--- This option enables the hardware independent IEEE 802.15.4 networking stack for SoftMAC devices (the ones implementing diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile index 15d62df5..9723d6f 100644 --- a/net/mac802154/Makefile +++ b/net/mac802154/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_MAC802154) += mac802154.o -mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o wpan.o +mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o \ + monitor.o wpan.o llsec.o ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c new file mode 100644 index 0000000..e4a2558 --- /dev/null +++ b/net/mac802154/llsec.c @@ -0,0 +1,1069 @@ +/* + * Copyright (C) 2014 Fraunhofer ITWM + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Written by: + * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> + */ + +#include <linux/err.h> +#include <linux/bug.h> +#include <linux/completion.h> +#include <net/ieee802154.h> +#include <crypto/algapi.h> + +#include "mac802154.h" +#include "llsec.h" + +static void llsec_key_put(struct mac802154_llsec_key *key); +static bool llsec_key_id_equal(const struct ieee802154_llsec_key_id *a, + const struct ieee802154_llsec_key_id *b); + +static void llsec_dev_free(struct mac802154_llsec_device *dev); + +void mac802154_llsec_init(struct mac802154_llsec *sec) +{ + memset(sec, 0, sizeof(*sec)); + + memset(&sec->params.default_key_source, 0xFF, IEEE802154_ADDR_LEN); + + INIT_LIST_HEAD(&sec->table.security_levels); + INIT_LIST_HEAD(&sec->table.devices); + INIT_LIST_HEAD(&sec->table.keys); + hash_init(sec->devices_short); + hash_init(sec->devices_hw); + rwlock_init(&sec->lock); +} + +void mac802154_llsec_destroy(struct mac802154_llsec *sec) +{ + struct ieee802154_llsec_seclevel *sl, *sn; + struct ieee802154_llsec_device *dev, *dn; + struct ieee802154_llsec_key_entry *key, *kn; + + list_for_each_entry_safe(sl, sn, &sec->table.security_levels, list) { + struct mac802154_llsec_seclevel *msl; + + msl = container_of(sl, struct mac802154_llsec_seclevel, level); + list_del(&sl->list); + kfree(msl); + } + + list_for_each_entry_safe(dev, dn, &sec->table.devices, list) { + struct mac802154_llsec_device *mdev; + + mdev = container_of(dev, struct mac802154_llsec_device, dev); + list_del(&dev->list); + llsec_dev_free(mdev); + } + + list_for_each_entry_safe(key, kn, &sec->table.keys, list) { + struct mac802154_llsec_key *mkey; + + mkey = container_of(key->key, struct mac802154_llsec_key, key); + list_del(&key->list); + llsec_key_put(mkey); + kfree(key); + } +} + + + +int mac802154_llsec_get_params(struct mac802154_llsec *sec, + struct ieee802154_llsec_params *params) +{ + read_lock_bh(&sec->lock); + *params = sec->params; + read_unlock_bh(&sec->lock); + + return 0; +} + +int mac802154_llsec_set_params(struct mac802154_llsec *sec, + const struct ieee802154_llsec_params *params, + int changed) +{ + write_lock_bh(&sec->lock); + + if (changed & IEEE802154_LLSEC_PARAM_ENABLED) + sec->params.enabled = params->enabled; + if (changed & IEEE802154_LLSEC_PARAM_FRAME_COUNTER) + sec->params.frame_counter = params->frame_counter; + if (changed & IEEE802154_LLSEC_PARAM_OUT_LEVEL) + sec->params.out_level = params->out_level; + if (changed & IEEE802154_LLSEC_PARAM_OUT_KEY) + sec->params.out_key = params->out_key; + if (changed & IEEE802154_LLSEC_PARAM_KEY_SOURCE) + sec->params.default_key_source = params->default_key_source; + if (changed & IEEE802154_LLSEC_PARAM_PAN_ID) + sec->params.pan_id = params->pan_id; + if (changed & IEEE802154_LLSEC_PARAM_HWADDR) + sec->params.hwaddr = params->hwaddr; + if (changed & IEEE802154_LLSEC_PARAM_COORD_HWADDR) + sec->params.coord_hwaddr = params->coord_hwaddr; + if (changed & IEEE802154_LLSEC_PARAM_COORD_SHORTADDR) + sec->params.coord_shortaddr = params->coord_shortaddr; + + write_unlock_bh(&sec->lock); + + return 0; +} + + + +static struct mac802154_llsec_key* +llsec_key_alloc(const struct ieee802154_llsec_key *template) +{ + const int authsizes[3] = { 4, 8, 16 }; + struct mac802154_llsec_key *key; + int i; + + key = kzalloc(sizeof(*key), GFP_KERNEL); + if (!key) + return NULL; + + kref_init(&key->ref); + key->key = *template; + + BUILD_BUG_ON(ARRAY_SIZE(authsizes) != ARRAY_SIZE(key->tfm)); + + for (i = 0; i < ARRAY_SIZE(key->tfm); i++) { + key->tfm[i] = crypto_alloc_aead("ccm(aes)", 0, + CRYPTO_ALG_ASYNC); + if (!key->tfm[i]) + goto err_tfm; + if (crypto_aead_setkey(key->tfm[i], template->key, + IEEE802154_LLSEC_KEY_SIZE)) + goto err_tfm; + if (crypto_aead_setauthsize(key->tfm[i], authsizes[i])) + goto err_tfm; + } + + key->tfm0 = crypto_alloc_blkcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC); + if (!key->tfm0) + goto err_tfm; + + if (crypto_blkcipher_setkey(key->tfm0, template->key, + IEEE802154_LLSEC_KEY_SIZE)) + goto err_tfm0; + + return key; + +err_tfm0: + crypto_free_blkcipher(key->tfm0); +err_tfm: + for (i = 0; i < ARRAY_SIZE(key->tfm); i++) + if (key->tfm[i]) + crypto_free_aead(key->tfm[i]); + + kfree(key); + return NULL; +} + +static void llsec_key_release(struct kref *ref) +{ + struct mac802154_llsec_key *key; + int i; + + key = container_of(ref, struct mac802154_llsec_key, ref); + + for (i = 0; i < ARRAY_SIZE(key->tfm); i++) + crypto_free_aead(key->tfm[i]); + + crypto_free_blkcipher(key->tfm0); + kfree(key); +} + +static struct mac802154_llsec_key* +llsec_key_get(struct mac802154_llsec_key *key) +{ + kref_get(&key->ref); + return key; +} + +static void llsec_key_put(struct mac802154_llsec_key *key) +{ + kref_put(&key->ref, llsec_key_release); +} + +static bool llsec_key_id_equal(const struct ieee802154_llsec_key_id *a, + const struct ieee802154_llsec_key_id *b) +{ + if (a->mode != b->mode) + return false; + + if (a->mode == IEEE802154_SCF_KEY_IMPLICIT) + return ieee802154_addr_equal(&a->device_addr, &b->device_addr); + + if (a->id != b->id) + return false; + + switch (a->mode) { + case IEEE802154_SCF_KEY_INDEX: + return true; + case IEEE802154_SCF_KEY_SHORT_INDEX: + return a->short_source == b->short_source; + case IEEE802154_SCF_KEY_HW_INDEX: + return a->extended_source == b->extended_source; + } + + return false; +} + +int mac802154_llsec_key_add(struct mac802154_llsec *sec, + const struct ieee802154_llsec_key_id *id, + const struct ieee802154_llsec_key *key) +{ + struct mac802154_llsec_key *mkey = NULL; + struct ieee802154_llsec_key_entry *pos, *new; + + if (!(key->frame_types & (1 << IEEE802154_FC_TYPE_MAC_CMD)) && + key->cmd_frame_ids) + return -EINVAL; + + list_for_each_entry(pos, &sec->table.keys, list) { + if (llsec_key_id_equal(&pos->id, id)) + return -EEXIST; + + if (memcmp(pos->key->key, key->key, + IEEE802154_LLSEC_KEY_SIZE)) + continue; + + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + /* Don't allow multiple instances of the same AES key to have + * different allowed frame types/command frame ids, as this is + * not possible in the 802.15.4 PIB. + */ + if (pos->key->frame_types != key->frame_types || + pos->key->cmd_frame_ids != key->cmd_frame_ids) + return -EEXIST; + + break; + } + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return -ENOMEM; + + if (!mkey) + mkey = llsec_key_alloc(key); + else + mkey = llsec_key_get(mkey); + + if (!mkey) + goto fail; + + new->id = *id; + new->key = &mkey->key; + + list_add_rcu(&new->list, &sec->table.keys); + + return 0; + +fail: + kfree(new); + return -ENOMEM; +} + +int mac802154_llsec_key_del(struct mac802154_llsec *sec, + const struct ieee802154_llsec_key_id *key) +{ + struct ieee802154_llsec_key_entry *pos; + + list_for_each_entry(pos, &sec->table.keys, list) { + struct mac802154_llsec_key *mkey; + + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + if (llsec_key_id_equal(&pos->id, key)) { + llsec_key_put(mkey); + return 0; + } + } + + return -ENOENT; +} + + + +static bool llsec_dev_use_shortaddr(__le16 short_addr) +{ + return short_addr != cpu_to_le16(IEEE802154_ADDR_UNDEF) && + short_addr != cpu_to_le16(0xffff); +} + +static u32 llsec_dev_hash_short(__le16 short_addr, __le16 pan_id) +{ + return ((__force u16) short_addr) << 16 | (__force u16) pan_id; +} + +static u64 llsec_dev_hash_long(__le64 hwaddr) +{ + return (__force u64) hwaddr; +} + +static struct mac802154_llsec_device* +llsec_dev_find_short(struct mac802154_llsec *sec, __le16 short_addr, + __le16 pan_id) +{ + struct mac802154_llsec_device *dev; + u32 key = llsec_dev_hash_short(short_addr, pan_id); + + hash_for_each_possible_rcu(sec->devices_short, dev, bucket_s, key) { + if (dev->dev.short_addr == short_addr && + dev->dev.pan_id == pan_id) + return dev; + } + + return NULL; +} + +static struct mac802154_llsec_device* +llsec_dev_find_long(struct mac802154_llsec *sec, __le64 hwaddr) +{ + struct mac802154_llsec_device *dev; + u64 key = llsec_dev_hash_long(hwaddr); + + hash_for_each_possible_rcu(sec->devices_hw, dev, bucket_hw, key) { + if (dev->dev.hwaddr == hwaddr) + return dev; + } + + return NULL; +} + +static void llsec_dev_free(struct mac802154_llsec_device *dev) +{ + struct ieee802154_llsec_device_key *pos, *pn; + struct mac802154_llsec_device_key *devkey; + + list_for_each_entry_safe(pos, pn, &dev->dev.keys, list) { + devkey = container_of(pos, struct mac802154_llsec_device_key, + devkey); + + list_del(&pos->list); + kfree(devkey); + } + + kfree(dev); +} + +int mac802154_llsec_dev_add(struct mac802154_llsec *sec, + const struct ieee802154_llsec_device *dev) +{ + struct mac802154_llsec_device *entry; + u32 skey = llsec_dev_hash_short(dev->short_addr, dev->pan_id); + u64 hwkey = llsec_dev_hash_long(dev->hwaddr); + + BUILD_BUG_ON(sizeof(hwkey) != IEEE802154_ADDR_LEN); + + if ((llsec_dev_use_shortaddr(dev->short_addr) && + llsec_dev_find_short(sec, dev->short_addr, dev->pan_id)) || + llsec_dev_find_long(sec, dev->hwaddr)) + return -EEXIST; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + entry->dev = *dev; + spin_lock_init(&entry->lock); + INIT_LIST_HEAD(&entry->dev.keys); + + if (llsec_dev_use_shortaddr(dev->short_addr)) + hash_add_rcu(sec->devices_short, &entry->bucket_s, skey); + else + INIT_HLIST_NODE(&entry->bucket_s); + + hash_add_rcu(sec->devices_hw, &entry->bucket_hw, hwkey); + list_add_tail_rcu(&entry->dev.list, &sec->table.devices); + + return 0; +} + +static void llsec_dev_free_rcu(struct rcu_head *rcu) +{ + llsec_dev_free(container_of(rcu, struct mac802154_llsec_device, rcu)); +} + +int mac802154_llsec_dev_del(struct mac802154_llsec *sec, __le64 device_addr) +{ + struct mac802154_llsec_device *pos; + + pos = llsec_dev_find_long(sec, device_addr); + if (!pos) + return -ENOENT; + + hash_del_rcu(&pos->bucket_s); + hash_del_rcu(&pos->bucket_hw); + call_rcu(&pos->rcu, llsec_dev_free_rcu); + + return 0; +} + + + +static struct mac802154_llsec_device_key* +llsec_devkey_find(struct mac802154_llsec_device *dev, + const struct ieee802154_llsec_key_id *key) +{ + struct ieee802154_llsec_device_key *devkey; + + list_for_each_entry_rcu(devkey, &dev->dev.keys, list) { + if (!llsec_key_id_equal(key, &devkey->key_id)) + continue; + + return container_of(devkey, struct mac802154_llsec_device_key, + devkey); + } + + return NULL; +} + +int mac802154_llsec_devkey_add(struct mac802154_llsec *sec, + __le64 dev_addr, + const struct ieee802154_llsec_device_key *key) +{ + struct mac802154_llsec_device *dev; + struct mac802154_llsec_device_key *devkey; + + dev = llsec_dev_find_long(sec, dev_addr); + + if (!dev) + return -ENOENT; + + if (llsec_devkey_find(dev, &key->key_id)) + return -EEXIST; + + devkey = kmalloc(sizeof(*devkey), GFP_KERNEL); + if (!devkey) + return -ENOMEM; + + devkey->devkey = *key; + list_add_tail_rcu(&devkey->devkey.list, &dev->dev.keys); + return 0; +} + +int mac802154_llsec_devkey_del(struct mac802154_llsec *sec, + __le64 dev_addr, + const struct ieee802154_llsec_device_key *key) +{ + struct mac802154_llsec_device *dev; + struct mac802154_llsec_device_key *devkey; + + dev = llsec_dev_find_long(sec, dev_addr); + + if (!dev) + return -ENOENT; + + devkey = llsec_devkey_find(dev, &key->key_id); + if (!devkey) + return -ENOENT; + + list_del_rcu(&devkey->devkey.list); + kfree_rcu(devkey, rcu); + return 0; +} + + + +static struct mac802154_llsec_seclevel* +llsec_find_seclevel(const struct mac802154_llsec *sec, + const struct ieee802154_llsec_seclevel *sl) +{ + struct ieee802154_llsec_seclevel *pos; + + list_for_each_entry(pos, &sec->table.security_levels, list) { + if (pos->frame_type != sl->frame_type || + (pos->frame_type == IEEE802154_FC_TYPE_MAC_CMD && + pos->cmd_frame_id != sl->cmd_frame_id) || + pos->device_override != sl->device_override || + pos->sec_levels != sl->sec_levels) + continue; + + return container_of(pos, struct mac802154_llsec_seclevel, + level); + } + + return NULL; +} + +int mac802154_llsec_seclevel_add(struct mac802154_llsec *sec, + const struct ieee802154_llsec_seclevel *sl) +{ + struct mac802154_llsec_seclevel *entry; + + if (llsec_find_seclevel(sec, sl)) + return -EEXIST; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + entry->level = *sl; + + list_add_tail_rcu(&entry->level.list, &sec->table.security_levels); + + return 0; +} + +int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec, + const struct ieee802154_llsec_seclevel *sl) +{ + struct mac802154_llsec_seclevel *pos; + + pos = llsec_find_seclevel(sec, sl); + if (!pos) + return -ENOENT; + + list_del_rcu(&pos->level.list); + kfree_rcu(pos, rcu); + + return 0; +} + + + +static int llsec_recover_addr(struct mac802154_llsec *sec, + struct ieee802154_addr *addr) +{ + __le16 caddr = sec->params.coord_shortaddr; + addr->pan_id = sec->params.pan_id; + + if (caddr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { + return -EINVAL; + } else if (caddr == cpu_to_le16(IEEE802154_ADDR_UNDEF)) { + addr->extended_addr = sec->params.coord_hwaddr; + addr->mode = IEEE802154_ADDR_LONG; + } else { + addr->short_addr = sec->params.coord_shortaddr; + addr->mode = IEEE802154_ADDR_SHORT; + } + + return 0; +} + +static struct mac802154_llsec_key* +llsec_lookup_key(struct mac802154_llsec *sec, + const struct ieee802154_hdr *hdr, + const struct ieee802154_addr *addr, + struct ieee802154_llsec_key_id *key_id) +{ + struct ieee802154_addr devaddr = *addr; + u8 key_id_mode = hdr->sec.key_id_mode; + struct ieee802154_llsec_key_entry *key_entry; + struct mac802154_llsec_key *key; + + if (key_id_mode == IEEE802154_SCF_KEY_IMPLICIT && + devaddr.mode == IEEE802154_ADDR_NONE) { + if (hdr->fc.type == IEEE802154_FC_TYPE_BEACON) { + devaddr.extended_addr = sec->params.coord_hwaddr; + devaddr.mode = IEEE802154_ADDR_LONG; + } else if (llsec_recover_addr(sec, &devaddr) < 0) { + return NULL; + } + } + + list_for_each_entry_rcu(key_entry, &sec->table.keys, list) { + const struct ieee802154_llsec_key_id *id = &key_entry->id; + + if (!(key_entry->key->frame_types & BIT(hdr->fc.type))) + continue; + + if (id->mode != key_id_mode) + continue; + + if (key_id_mode == IEEE802154_SCF_KEY_IMPLICIT) { + if (ieee802154_addr_equal(&devaddr, &id->device_addr)) + goto found; + } else { + if (id->id != hdr->sec.key_id) + continue; + + if ((key_id_mode == IEEE802154_SCF_KEY_INDEX) || + (key_id_mode == IEEE802154_SCF_KEY_SHORT_INDEX && + id->short_source == hdr->sec.short_src) || + (key_id_mode == IEEE802154_SCF_KEY_HW_INDEX && + id->extended_source == hdr->sec.extended_src)) + goto found; + } + } + + return NULL; + +found: + key = container_of(key_entry->key, struct mac802154_llsec_key, key); + if (key_id) + *key_id = key_entry->id; + return llsec_key_get(key); +} + + +static void llsec_geniv(u8 iv[16], __le64 addr, + const struct ieee802154_sechdr *sec) +{ + __be64 addr_bytes = (__force __be64) swab64((__force u64) addr); + __be32 frame_counter = (__force __be32) swab32((__force u32) sec->frame_counter); + + iv[0] = 1; /* L' = L - 1 = 1 */ + memcpy(iv + 1, &addr_bytes, sizeof(addr_bytes)); + memcpy(iv + 9, &frame_counter, sizeof(frame_counter)); + iv[13] = sec->level; + iv[14] = 0; + iv[15] = 1; +} + +static int +llsec_do_encrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec, + const struct ieee802154_hdr *hdr, + struct mac802154_llsec_key *key) +{ + u8 iv[16]; + struct scatterlist src; + struct blkcipher_desc req = { + .tfm = key->tfm0, + .info = iv, + .flags = 0, + }; + + llsec_geniv(iv, sec->params.hwaddr, &hdr->sec); + sg_init_one(&src, skb->data, skb->len); + return crypto_blkcipher_encrypt_iv(&req, &src, &src, skb->len); +} + +static struct crypto_aead* +llsec_tfm_by_len(struct mac802154_llsec_key *key, int authlen) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(key->tfm); i++) + if (crypto_aead_authsize(key->tfm[i]) == authlen) + return key->tfm[i]; + + BUG(); +} + +static int +llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, + const struct ieee802154_hdr *hdr, + struct mac802154_llsec_key *key) +{ + u8 iv[16]; + unsigned char *data; + int authlen, assoclen, datalen, rc; + struct scatterlist src, assoc[2], dst[2]; + struct aead_request *req; + + authlen = ieee802154_sechdr_authtag_len(&hdr->sec); + llsec_geniv(iv, sec->params.hwaddr, &hdr->sec); + + req = aead_request_alloc(llsec_tfm_by_len(key, authlen), GFP_ATOMIC); + if (!req) + return -ENOMEM; + + sg_init_table(assoc, 2); + sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len); + assoclen = skb->mac_len; + + data = skb_mac_header(skb) + skb->mac_len; + datalen = skb_tail_pointer(skb) - data; + + if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) { + sg_set_buf(&assoc[1], data, 0); + } else { + sg_set_buf(&assoc[1], data, datalen); + assoclen += datalen; + datalen = 0; + } + + sg_init_one(&src, data, datalen); + + sg_init_table(dst, 2); + sg_set_buf(&dst[0], data, datalen); + sg_set_buf(&dst[1], skb_put(skb, authlen), authlen); + + aead_request_set_callback(req, 0, NULL, NULL); + aead_request_set_assoc(req, assoc, assoclen); + aead_request_set_crypt(req, &src, dst, datalen, iv); + + rc = crypto_aead_encrypt(req); + + kfree(req); + + return rc; +} + +static int llsec_do_encrypt(struct sk_buff *skb, + const struct mac802154_llsec *sec, + const struct ieee802154_hdr *hdr, + struct mac802154_llsec_key *key) +{ + if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC) + return llsec_do_encrypt_unauth(skb, sec, hdr, key); + else + return llsec_do_encrypt_auth(skb, sec, hdr, key); +} + +int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb) +{ + struct ieee802154_hdr hdr; + int rc, authlen, hlen; + struct mac802154_llsec_key *key; + u32 frame_ctr; + + hlen = ieee802154_hdr_pull(skb, &hdr); + + if (hlen < 0 || hdr.fc.type != IEEE802154_FC_TYPE_DATA) + return -EINVAL; + + if (!hdr.fc.security_enabled || hdr.sec.level == 0) { + skb_push(skb, hlen); + return 0; + } + + authlen = ieee802154_sechdr_authtag_len(&hdr.sec); + + if (skb->len + hlen + authlen + IEEE802154_MFR_SIZE > IEEE802154_MTU) + return -EMSGSIZE; + + rcu_read_lock(); + + read_lock_bh(&sec->lock); + + if (!sec->params.enabled) { + rc = -EINVAL; + goto fail_read; + } + + key = llsec_lookup_key(sec, &hdr, &hdr.dest, NULL); + if (!key) { + rc = -ENOKEY; + goto fail_read; + } + + read_unlock_bh(&sec->lock); + + write_lock_bh(&sec->lock); + + frame_ctr = be32_to_cpu(sec->params.frame_counter); + hdr.sec.frame_counter = cpu_to_le32(frame_ctr); + if (frame_ctr == 0xFFFFFFFF) { + write_unlock_bh(&sec->lock); + llsec_key_put(key); + rc = -EOVERFLOW; + goto fail; + } + + sec->params.frame_counter = cpu_to_be32(frame_ctr + 1); + + write_unlock_bh(&sec->lock); + + rcu_read_unlock(); + + skb->mac_len = ieee802154_hdr_push(skb, &hdr); + skb_reset_mac_header(skb); + + rc = llsec_do_encrypt(skb, sec, &hdr, key); + llsec_key_put(key); + + return rc; + +fail_read: + read_unlock_bh(&sec->lock); +fail: + rcu_read_unlock(); + return rc; +} + + + +static struct mac802154_llsec_device* +llsec_lookup_dev(struct mac802154_llsec *sec, + const struct ieee802154_addr *addr) +{ + struct ieee802154_addr devaddr = *addr; + struct mac802154_llsec_device *dev = NULL; + + if (devaddr.mode == IEEE802154_ADDR_NONE && + llsec_recover_addr(sec, &devaddr) < 0) + return NULL; + + if (devaddr.mode == IEEE802154_ADDR_SHORT) { + u32 key = llsec_dev_hash_short(devaddr.short_addr, + devaddr.pan_id); + + hash_for_each_possible_rcu(sec->devices_short, dev, + bucket_s, key) { + if (dev->dev.pan_id == devaddr.pan_id && + dev->dev.short_addr == devaddr.short_addr) + return dev; + } + } else { + u64 key = llsec_dev_hash_long(devaddr.extended_addr); + + hash_for_each_possible_rcu(sec->devices_hw, dev, + bucket_hw, key) { + if (dev->dev.hwaddr == devaddr.extended_addr) + return dev; + } + } + + return NULL; +} + +static int +llsec_lookup_seclevel(const struct mac802154_llsec *sec, + u8 frame_type, u8 cmd_frame_id, + struct ieee802154_llsec_seclevel *rlevel) +{ + struct ieee802154_llsec_seclevel *level; + + list_for_each_entry_rcu(level, &sec->table.security_levels, list) { + if (level->frame_type == frame_type && + (frame_type != IEEE802154_FC_TYPE_MAC_CMD || + level->cmd_frame_id == cmd_frame_id)) { + *rlevel = *level; + return 0; + } + } + + return -EINVAL; +} + +static int +llsec_do_decrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec, + const struct ieee802154_hdr *hdr, + struct mac802154_llsec_key *key, __le64 dev_addr) +{ + u8 iv[16]; + unsigned char *data; + int datalen; + struct scatterlist src; + struct blkcipher_desc req = { + .tfm = key->tfm0, + .info = iv, + .flags = 0, + }; + + llsec_geniv(iv, dev_addr, &hdr->sec); + data = skb_mac_header(skb) + skb->mac_len; + datalen = skb_tail_pointer(skb) - data; + + sg_init_one(&src, data, datalen); + + return crypto_blkcipher_decrypt_iv(&req, &src, &src, datalen); +} + +static int +llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, + const struct ieee802154_hdr *hdr, + struct mac802154_llsec_key *key, __le64 dev_addr) +{ + u8 iv[16]; + unsigned char *data; + int authlen, datalen, assoclen, rc; + struct scatterlist src, assoc[2]; + struct aead_request *req; + + authlen = ieee802154_sechdr_authtag_len(&hdr->sec); + llsec_geniv(iv, dev_addr, &hdr->sec); + + req = aead_request_alloc(llsec_tfm_by_len(key, authlen), GFP_ATOMIC); + if (!req) + return -ENOMEM; + + sg_init_table(assoc, 2); + sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len); + assoclen = skb->mac_len; + + data = skb_mac_header(skb) + skb->mac_len; + datalen = skb_tail_pointer(skb) - data; + + if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) { + sg_set_buf(&assoc[1], data, 0); + } else { + sg_set_buf(&assoc[1], data, datalen - authlen); + assoclen += datalen - authlen; + data += datalen - authlen; + datalen = authlen; + } + + sg_init_one(&src, data, datalen); + + aead_request_set_callback(req, 0, NULL, NULL); + aead_request_set_assoc(req, assoc, assoclen); + aead_request_set_crypt(req, &src, &src, datalen, iv); + + rc = crypto_aead_decrypt(req); + + kfree(req); + skb_trim(skb, skb->len - authlen); + + return rc; +} + +static int +llsec_do_decrypt(struct sk_buff *skb, const struct mac802154_llsec *sec, + const struct ieee802154_hdr *hdr, + struct mac802154_llsec_key *key, __le64 dev_addr) +{ + if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC) + return llsec_do_decrypt_unauth(skb, sec, hdr, key, dev_addr); + else + return llsec_do_decrypt_auth(skb, sec, hdr, key, dev_addr); +} + +static int +llsec_update_devkey_record(struct mac802154_llsec_device *dev, + const struct ieee802154_llsec_key_id *in_key) +{ + struct mac802154_llsec_device_key *devkey; + + devkey = llsec_devkey_find(dev, in_key); + + if (!devkey) { + struct mac802154_llsec_device_key *next; + + next = kzalloc(sizeof(*devkey), GFP_ATOMIC); + if (!next) + return -ENOMEM; + + next->devkey.key_id = *in_key; + + spin_lock_bh(&dev->lock); + + devkey = llsec_devkey_find(dev, in_key); + if (!devkey) + list_add_rcu(&next->devkey.list, &dev->dev.keys); + else + kfree(next); + + spin_unlock_bh(&dev->lock); + } + + return 0; +} + +static int +llsec_update_devkey_info(struct mac802154_llsec_device *dev, + const struct ieee802154_llsec_key_id *in_key, + u32 frame_counter) +{ + struct mac802154_llsec_device_key *devkey = NULL; + + if (dev->dev.key_mode == IEEE802154_LLSEC_DEVKEY_RESTRICT) { + devkey = llsec_devkey_find(dev, in_key); + if (!devkey) + return -ENOENT; + } + + if (dev->dev.key_mode == IEEE802154_LLSEC_DEVKEY_RECORD) { + int rc = llsec_update_devkey_record(dev, in_key); + + if (rc < 0) + return rc; + } + + spin_lock_bh(&dev->lock); + + if ((!devkey && frame_counter < dev->dev.frame_counter) || + (devkey && frame_counter < devkey->devkey.frame_counter)) { + spin_unlock_bh(&dev->lock); + return -EINVAL; + } + + if (devkey) + devkey->devkey.frame_counter = frame_counter + 1; + else + dev->dev.frame_counter = frame_counter + 1; + + spin_unlock_bh(&dev->lock); + + return 0; +} + +int mac802154_llsec_decrypt(struct mac802154_llsec *sec, struct sk_buff *skb) +{ + struct ieee802154_hdr hdr; + struct mac802154_llsec_key *key; + struct ieee802154_llsec_key_id key_id; + struct mac802154_llsec_device *dev; + struct ieee802154_llsec_seclevel seclevel; + int err; + __le64 dev_addr; + u32 frame_ctr; + + if (ieee802154_hdr_peek(skb, &hdr) < 0) + return -EINVAL; + if (!hdr.fc.security_enabled) + return 0; + if (hdr.fc.version == 0) + return -EINVAL; + + read_lock_bh(&sec->lock); + if (!sec->params.enabled) { + read_unlock_bh(&sec->lock); + return -EINVAL; + } + read_unlock_bh(&sec->lock); + + rcu_read_lock(); + + key = llsec_lookup_key(sec, &hdr, &hdr.source, &key_id); + if (!key) { + err = -ENOKEY; + goto fail; + } + + dev = llsec_lookup_dev(sec, &hdr.source); + if (!dev) { + err = -EINVAL; + goto fail_dev; + } + + if (llsec_lookup_seclevel(sec, hdr.fc.type, 0, &seclevel) < 0) { + err = -EINVAL; + goto fail_dev; + } + + if (!(seclevel.sec_levels & BIT(hdr.sec.level)) && + (hdr.sec.level == 0 && seclevel.device_override && + !dev->dev.seclevel_exempt)) { + err = -EINVAL; + goto fail_dev; + } + + frame_ctr = le32_to_cpu(hdr.sec.frame_counter); + + if (frame_ctr == 0xffffffff) { + err = -EOVERFLOW; + goto fail_dev; + } + + err = llsec_update_devkey_info(dev, &key_id, frame_ctr); + if (err) + goto fail_dev; + + dev_addr = dev->dev.hwaddr; + + rcu_read_unlock(); + + err = llsec_do_decrypt(skb, sec, &hdr, key, dev_addr); + llsec_key_put(key); + return err; + +fail_dev: + llsec_key_put(key); +fail: + rcu_read_unlock(); + return err; +} diff --git a/net/mac802154/llsec.h b/net/mac802154/llsec.h new file mode 100644 index 0000000..950578e --- /dev/null +++ b/net/mac802154/llsec.h @@ -0,0 +1,108 @@ +/* + * Copyright (C) 2014 Fraunhofer ITWM + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Written by: + * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> + */ + +#ifndef MAC802154_LLSEC_H +#define MAC802154_LLSEC_H + +#include <linux/slab.h> +#include <linux/hashtable.h> +#include <linux/crypto.h> +#include <linux/kref.h> +#include <linux/spinlock.h> +#include <net/af_ieee802154.h> +#include <net/ieee802154_netdev.h> + +struct mac802154_llsec_key { + struct ieee802154_llsec_key key; + + /* one tfm for each authsize (4/8/16) */ + struct crypto_aead *tfm[3]; + struct crypto_blkcipher *tfm0; + + struct kref ref; +}; + +struct mac802154_llsec_device_key { + struct ieee802154_llsec_device_key devkey; + + struct rcu_head rcu; +}; + +struct mac802154_llsec_device { + struct ieee802154_llsec_device dev; + + struct hlist_node bucket_s; + struct hlist_node bucket_hw; + + /* protects dev.frame_counter and the elements of dev.keys */ + spinlock_t lock; + + struct rcu_head rcu; +}; + +struct mac802154_llsec_seclevel { + struct ieee802154_llsec_seclevel level; + + struct rcu_head rcu; +}; + +struct mac802154_llsec { + struct ieee802154_llsec_params params; + struct ieee802154_llsec_table table; + + DECLARE_HASHTABLE(devices_short, 6); + DECLARE_HASHTABLE(devices_hw, 6); + + /* protects params, all other fields are fine with RCU */ + rwlock_t lock; +}; + +void mac802154_llsec_init(struct mac802154_llsec *sec); +void mac802154_llsec_destroy(struct mac802154_llsec *sec); + +int mac802154_llsec_get_params(struct mac802154_llsec *sec, + struct ieee802154_llsec_params *params); +int mac802154_llsec_set_params(struct mac802154_llsec *sec, + const struct ieee802154_llsec_params *params, + int changed); + +int mac802154_llsec_key_add(struct mac802154_llsec *sec, + const struct ieee802154_llsec_key_id *id, + const struct ieee802154_llsec_key *key); +int mac802154_llsec_key_del(struct mac802154_llsec *sec, + const struct ieee802154_llsec_key_id *key); + +int mac802154_llsec_dev_add(struct mac802154_llsec *sec, + const struct ieee802154_llsec_device *dev); +int mac802154_llsec_dev_del(struct mac802154_llsec *sec, + __le64 device_addr); + +int mac802154_llsec_devkey_add(struct mac802154_llsec *sec, + __le64 dev_addr, + const struct ieee802154_llsec_device_key *key); +int mac802154_llsec_devkey_del(struct mac802154_llsec *sec, + __le64 dev_addr, + const struct ieee802154_llsec_device_key *key); + +int mac802154_llsec_seclevel_add(struct mac802154_llsec *sec, + const struct ieee802154_llsec_seclevel *sl); +int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec, + const struct ieee802154_llsec_seclevel *sl); + +int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb); +int mac802154_llsec_decrypt(struct mac802154_llsec *sec, struct sk_buff *skb); + +#endif /* MAC802154_LLSEC_H */ diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h index 28ef59c..762a6f8 100644 --- a/net/mac802154/mac802154.h +++ b/net/mac802154/mac802154.h @@ -23,8 +23,12 @@ #ifndef MAC802154_H #define MAC802154_H +#include <linux/mutex.h> +#include <net/mac802154.h> #include <net/ieee802154_netdev.h> +#include "llsec.h" + /* mac802154 device private data */ struct mac802154_priv { struct ieee802154_dev hw; @@ -90,6 +94,13 @@ struct mac802154_sub_if_data { u8 bsn; /* MAC DSN field */ u8 dsn; + + /* protects sec from concurrent access by netlink. access by + * encrypt/decrypt/header_create safe without additional protection. + */ + struct mutex sec_mtx; + + struct mac802154_llsec sec; }; #define mac802154_to_priv(_hw) container_of(_hw, struct mac802154_priv, hw) @@ -125,4 +136,37 @@ int mac802154_set_mac_params(struct net_device *dev, void mac802154_get_mac_params(struct net_device *dev, struct ieee802154_mac_params *params); +int mac802154_get_params(struct net_device *dev, + struct ieee802154_llsec_params *params); +int mac802154_set_params(struct net_device *dev, + const struct ieee802154_llsec_params *params, + int changed); + +int mac802154_add_key(struct net_device *dev, + const struct ieee802154_llsec_key_id *id, + const struct ieee802154_llsec_key *key); +int mac802154_del_key(struct net_device *dev, + const struct ieee802154_llsec_key_id *id); + +int mac802154_add_dev(struct net_device *dev, + const struct ieee802154_llsec_device *llsec_dev); +int mac802154_del_dev(struct net_device *dev, __le64 dev_addr); + +int mac802154_add_devkey(struct net_device *dev, + __le64 device_addr, + const struct ieee802154_llsec_device_key *key); +int mac802154_del_devkey(struct net_device *dev, + __le64 device_addr, + const struct ieee802154_llsec_device_key *key); + +int mac802154_add_seclevel(struct net_device *dev, + const struct ieee802154_llsec_seclevel *sl); +int mac802154_del_seclevel(struct net_device *dev, + const struct ieee802154_llsec_seclevel *sl); + +void mac802154_lock_table(struct net_device *dev); +void mac802154_get_table(struct net_device *dev, + struct ieee802154_llsec_table **t); +void mac802154_unlock_table(struct net_device *dev); + #endif /* MAC802154_H */ diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c index d40c092..bf80913 100644 --- a/net/mac802154/mac_cmd.c +++ b/net/mac802154/mac_cmd.c @@ -40,6 +40,9 @@ static int mac802154_mlme_start_req(struct net_device *dev, u8 pan_coord, u8 blx, u8 coord_realign) { + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + int rc = 0; + BUG_ON(addr->mode != IEEE802154_ADDR_SHORT); mac802154_dev_set_pan_id(dev, addr->pan_id); @@ -47,12 +50,31 @@ static int mac802154_mlme_start_req(struct net_device *dev, mac802154_dev_set_ieee_addr(dev); mac802154_dev_set_page_channel(dev, page, channel); + if (ops->llsec) { + struct ieee802154_llsec_params params; + int changed = 0; + + params.coord_shortaddr = addr->short_addr; + changed |= IEEE802154_LLSEC_PARAM_COORD_SHORTADDR; + + params.pan_id = addr->pan_id; + changed |= IEEE802154_LLSEC_PARAM_PAN_ID; + + params.hwaddr = ieee802154_devaddr_from_raw(dev->dev_addr); + changed |= IEEE802154_LLSEC_PARAM_HWADDR; + + params.coord_hwaddr = params.hwaddr; + changed |= IEEE802154_LLSEC_PARAM_COORD_HWADDR; + + rc = ops->llsec->set_params(dev, ¶ms, changed); + } + /* FIXME: add validation for unused parameters to be sane * for SoftMAC */ ieee802154_nl_start_confirm(dev, IEEE802154_SUCCESS); - return 0; + return rc; } static struct wpan_phy *mac802154_get_phy(const struct net_device *dev) @@ -64,6 +86,22 @@ static struct wpan_phy *mac802154_get_phy(const struct net_device *dev) return to_phy(get_device(&priv->hw->phy->dev)); } +static struct ieee802154_llsec_ops mac802154_llsec_ops = { + .get_params = mac802154_get_params, + .set_params = mac802154_set_params, + .add_key = mac802154_add_key, + .del_key = mac802154_del_key, + .add_dev = mac802154_add_dev, + .del_dev = mac802154_del_dev, + .add_devkey = mac802154_add_devkey, + .del_devkey = mac802154_del_devkey, + .add_seclevel = mac802154_add_seclevel, + .del_seclevel = mac802154_del_seclevel, + .lock_table = mac802154_lock_table, + .get_table = mac802154_get_table, + .unlock_table = mac802154_unlock_table, +}; + struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced = { .get_phy = mac802154_get_phy, }; @@ -75,6 +113,8 @@ struct ieee802154_mlme_ops mac802154_mlme_wpan = { .get_short_addr = mac802154_dev_get_short_addr, .get_dsn = mac802154_dev_get_dsn, + .llsec = &mac802154_llsec_ops, + .set_mac_params = mac802154_set_mac_params, .get_mac_params = mac802154_get_mac_params, }; diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index f0991f2..15aa2f2 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -213,3 +213,190 @@ void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan) } else mutex_unlock(&priv->hw->phy->pib_lock); } + + +int mac802154_get_params(struct net_device *dev, + struct ieee802154_llsec_params *params) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_get_params(&priv->sec, params); + mutex_unlock(&priv->sec_mtx); + + return res; +} + +int mac802154_set_params(struct net_device *dev, + const struct ieee802154_llsec_params *params, + int changed) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_set_params(&priv->sec, params, changed); + mutex_unlock(&priv->sec_mtx); + + return res; +} + + +int mac802154_add_key(struct net_device *dev, + const struct ieee802154_llsec_key_id *id, + const struct ieee802154_llsec_key *key) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_key_add(&priv->sec, id, key); + mutex_unlock(&priv->sec_mtx); + + return res; +} + +int mac802154_del_key(struct net_device *dev, + const struct ieee802154_llsec_key_id *id) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_key_del(&priv->sec, id); + mutex_unlock(&priv->sec_mtx); + + return res; +} + + +int mac802154_add_dev(struct net_device *dev, + const struct ieee802154_llsec_device *llsec_dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_dev_add(&priv->sec, llsec_dev); + mutex_unlock(&priv->sec_mtx); + + return res; +} + +int mac802154_del_dev(struct net_device *dev, __le64 dev_addr) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_dev_del(&priv->sec, dev_addr); + mutex_unlock(&priv->sec_mtx); + + return res; +} + + +int mac802154_add_devkey(struct net_device *dev, + __le64 device_addr, + const struct ieee802154_llsec_device_key *key) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_devkey_add(&priv->sec, device_addr, key); + mutex_unlock(&priv->sec_mtx); + + return res; +} + +int mac802154_del_devkey(struct net_device *dev, + __le64 device_addr, + const struct ieee802154_llsec_device_key *key) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_devkey_del(&priv->sec, device_addr, key); + mutex_unlock(&priv->sec_mtx); + + return res; +} + + +int mac802154_add_seclevel(struct net_device *dev, + const struct ieee802154_llsec_seclevel *sl) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_seclevel_add(&priv->sec, sl); + mutex_unlock(&priv->sec_mtx); + + return res; +} + +int mac802154_del_seclevel(struct net_device *dev, + const struct ieee802154_llsec_seclevel *sl) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int res; + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); + res = mac802154_llsec_seclevel_del(&priv->sec, sl); + mutex_unlock(&priv->sec_mtx); + + return res; +} + + +void mac802154_lock_table(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_lock(&priv->sec_mtx); +} + +void mac802154_get_table(struct net_device *dev, + struct ieee802154_llsec_table **t) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + *t = &priv->sec.table; +} + +void mac802154_unlock_table(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + + BUG_ON(dev->type != ARPHRD_IEEE802154); + + mutex_unlock(&priv->sec_mtx); +} diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index 03855b0..0597b96 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -59,8 +59,6 @@ mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi) skb->protocol = htons(ETH_P_IEEE802154); skb_reset_mac_header(skb); - BUILD_BUG_ON(sizeof(struct ieee802154_mac_cb) > sizeof(skb->cb)); - if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) { u16 crc; diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index 1df7a6a..23bc91c 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -35,6 +35,28 @@ #include "mac802154.h" +static int mac802154_wpan_update_llsec(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); + int rc = 0; + + if (ops->llsec) { + struct ieee802154_llsec_params params; + int changed = 0; + + params.pan_id = priv->pan_id; + changed |= IEEE802154_LLSEC_PARAM_PAN_ID; + + params.hwaddr = priv->extended_addr; + changed |= IEEE802154_LLSEC_PARAM_HWADDR; + + rc = ops->llsec->set_params(dev, ¶ms, changed); + } + + return rc; +} + static int mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -81,7 +103,7 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) priv->pan_id = cpu_to_le16(sa->addr.pan_id); priv->short_addr = cpu_to_le16(sa->addr.short_addr); - err = 0; + err = mac802154_wpan_update_llsec(dev); break; } @@ -99,7 +121,7 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) /* FIXME: validate addr */ memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); mac802154_dev_set_ieee_addr(dev); - return 0; + return mac802154_wpan_update_llsec(dev); } int mac802154_set_mac_params(struct net_device *dev, @@ -124,7 +146,7 @@ void mac802154_get_mac_params(struct net_device *dev, mutex_unlock(&priv->hw->slaves_mtx); } -int mac802154_wpan_open(struct net_device *dev) +static int mac802154_wpan_open(struct net_device *dev) { int rc; struct mac802154_sub_if_data *priv = netdev_priv(dev); @@ -183,6 +205,38 @@ out: return rc; } +static int mac802154_set_header_security(struct mac802154_sub_if_data *priv, + struct ieee802154_hdr *hdr, + const struct ieee802154_mac_cb *cb) +{ + struct ieee802154_llsec_params params; + u8 level; + + mac802154_llsec_get_params(&priv->sec, ¶ms); + + if (!params.enabled && cb->secen_override && cb->secen) + return -EINVAL; + if (!params.enabled || + (cb->secen_override && !cb->secen) || + !params.out_level) + return 0; + if (cb->seclevel_override && !cb->seclevel) + return -EINVAL; + + level = cb->seclevel_override ? cb->seclevel : params.out_level; + + hdr->fc.security_enabled = 1; + hdr->sec.level = level; + hdr->sec.key_id_mode = params.out_key.mode; + if (params.out_key.mode == IEEE802154_SCF_KEY_SHORT_INDEX) + hdr->sec.short_src = params.out_key.short_source; + else if (params.out_key.mode == IEEE802154_SCF_KEY_HW_INDEX) + hdr->sec.extended_src = params.out_key.extended_source; + hdr->sec.key_id = params.out_key.id; + + return 0; +} + static int mac802154_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -192,15 +246,20 @@ static int mac802154_header_create(struct sk_buff *skb, { struct ieee802154_hdr hdr; struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct ieee802154_mac_cb *cb = mac_cb(skb); int hlen; if (!daddr) return -EINVAL; memset(&hdr.fc, 0, sizeof(hdr.fc)); - hdr.fc.type = mac_cb_type(skb); - hdr.fc.security_enabled = mac_cb_is_secen(skb); - hdr.fc.ack_request = mac_cb_is_ackreq(skb); + hdr.fc.type = cb->type; + hdr.fc.security_enabled = cb->secen; + hdr.fc.ack_request = cb->ackreq; + hdr.seq = ieee802154_mlme_ops(dev)->get_dsn(dev); + + if (mac802154_set_header_security(priv, &hdr, cb) < 0) + return -EINVAL; if (!saddr) { spin_lock_bh(&priv->mib_lock); @@ -231,7 +290,7 @@ static int mac802154_header_create(struct sk_buff *skb, skb_reset_mac_header(skb); skb->mac_len = hlen; - if (hlen + len + 2 > dev->mtu) + if (len > ieee802154_max_payload(&hdr)) return -EMSGSIZE; return hlen; @@ -257,6 +316,7 @@ mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev) { struct mac802154_sub_if_data *priv; u8 chan, page; + int rc; priv = netdev_priv(dev); @@ -272,6 +332,13 @@ mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + rc = mac802154_llsec_encrypt(&priv->sec, skb); + if (rc) { + pr_warn("encryption failed: %i\n", rc); + kfree_skb(skb); + return NETDEV_TX_OK; + } + skb->skb_iif = dev->ifindex; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; @@ -292,6 +359,15 @@ static const struct net_device_ops mac802154_wpan_ops = { .ndo_set_mac_address = mac802154_wpan_mac_addr, }; +static void mac802154_wpan_free(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + + mac802154_llsec_destroy(&priv->sec); + + free_netdev(dev); +} + void mac802154_wpan_setup(struct net_device *dev) { struct mac802154_sub_if_data *priv; @@ -301,14 +377,14 @@ void mac802154_wpan_setup(struct net_device *dev) dev->hard_header_len = MAC802154_FRAME_HARD_HEADER_LEN; dev->header_ops = &mac802154_header_ops; - dev->needed_tailroom = 2; /* FCS */ + dev->needed_tailroom = 2 + 16; /* FCS + MIC */ dev->mtu = IEEE802154_MTU; dev->tx_queue_len = 300; dev->type = ARPHRD_IEEE802154; dev->flags = IFF_NOARP | IFF_BROADCAST; dev->watchdog_timeo = 0; - dev->destructor = free_netdev; + dev->destructor = mac802154_wpan_free; dev->netdev_ops = &mac802154_wpan_ops; dev->ml_priv = &mac802154_mlme_wpan; @@ -319,6 +395,7 @@ void mac802154_wpan_setup(struct net_device *dev) priv->page = 0; spin_lock_init(&priv->mib_lock); + mutex_init(&priv->sec_mtx); get_random_bytes(&priv->bsn, 1); get_random_bytes(&priv->dsn, 1); @@ -331,6 +408,8 @@ void mac802154_wpan_setup(struct net_device *dev) priv->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); priv->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); + + mac802154_llsec_init(&priv->sec); } static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) @@ -339,9 +418,11 @@ static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) } static int -mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) +mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb, + const struct ieee802154_hdr *hdr) { __le16 span, sshort; + int rc; pr_debug("getting packet via slave interface %s\n", sdata->dev->name); @@ -388,15 +469,21 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) skb->dev = sdata->dev; + rc = mac802154_llsec_decrypt(&sdata->sec, skb); + if (rc) { + pr_debug("decryption failed: %i\n", rc); + return NET_RX_DROP; + } + sdata->dev->stats.rx_packets++; sdata->dev->stats.rx_bytes += skb->len; - switch (mac_cb_type(skb)) { + switch (mac_cb(skb)->type) { case IEEE802154_FC_TYPE_DATA: return mac802154_process_data(sdata->dev, skb); default: pr_warn("ieee802154: bad frame received (type = %d)\n", - mac_cb_type(skb)); + mac_cb(skb)->type); kfree_skb(skb); return NET_RX_DROP; } @@ -419,62 +506,58 @@ static void mac802154_print_addr(const char *name, } } -static int mac802154_parse_frame_start(struct sk_buff *skb) +static int mac802154_parse_frame_start(struct sk_buff *skb, + struct ieee802154_hdr *hdr) { int hlen; - struct ieee802154_hdr hdr; + struct ieee802154_mac_cb *cb = mac_cb_init(skb); - hlen = ieee802154_hdr_pull(skb, &hdr); + hlen = ieee802154_hdr_pull(skb, hdr); if (hlen < 0) return -EINVAL; skb->mac_len = hlen; - pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr.fc), - hdr.seq); - - mac_cb(skb)->flags = hdr.fc.type; + pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr->fc), + hdr->seq); - if (hdr.fc.ack_request) - mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; - if (hdr.fc.security_enabled) - mac_cb(skb)->flags |= MAC_CB_FLAG_SECEN; + cb->type = hdr->fc.type; + cb->ackreq = hdr->fc.ack_request; + cb->secen = hdr->fc.security_enabled; - mac802154_print_addr("destination", &hdr.dest); - mac802154_print_addr("source", &hdr.source); + mac802154_print_addr("destination", &hdr->dest); + mac802154_print_addr("source", &hdr->source); - mac_cb(skb)->source = hdr.source; - mac_cb(skb)->dest = hdr.dest; + cb->source = hdr->source; + cb->dest = hdr->dest; - if (hdr.fc.security_enabled) { + if (hdr->fc.security_enabled) { u64 key; - pr_debug("seclevel %i\n", hdr.sec.level); + pr_debug("seclevel %i\n", hdr->sec.level); - switch (hdr.sec.key_id_mode) { + switch (hdr->sec.key_id_mode) { case IEEE802154_SCF_KEY_IMPLICIT: pr_debug("implicit key\n"); break; case IEEE802154_SCF_KEY_INDEX: - pr_debug("key %02x\n", hdr.sec.key_id); + pr_debug("key %02x\n", hdr->sec.key_id); break; case IEEE802154_SCF_KEY_SHORT_INDEX: pr_debug("key %04x:%04x %02x\n", - le32_to_cpu(hdr.sec.short_src) >> 16, - le32_to_cpu(hdr.sec.short_src) & 0xffff, - hdr.sec.key_id); + le32_to_cpu(hdr->sec.short_src) >> 16, + le32_to_cpu(hdr->sec.short_src) & 0xffff, + hdr->sec.key_id); break; case IEEE802154_SCF_KEY_HW_INDEX: - key = swab64((__force u64) hdr.sec.extended_src); + key = swab64((__force u64) hdr->sec.extended_src); pr_debug("key source %8phC %02x\n", &key, - hdr.sec.key_id); + hdr->sec.key_id); break; } - - return -EINVAL; } return 0; @@ -485,8 +568,9 @@ void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb) int ret; struct sk_buff *sskb; struct mac802154_sub_if_data *sdata; + struct ieee802154_hdr hdr; - ret = mac802154_parse_frame_start(skb); + ret = mac802154_parse_frame_start(skb, &hdr); if (ret) { pr_debug("got invalid frame\n"); return; @@ -499,7 +583,7 @@ void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb) sskb = skb_clone(skb, GFP_ATOMIC); if (sskb) - mac802154_subif_frame(sdata, sskb); + mac802154_subif_frame(sdata, sskb, &hdr); } rcu_read_unlock(); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f26ee4..d9da8c4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -97,7 +97,7 @@ const char *ip_vs_proto_name(unsigned int proto) return "ICMPv6"; #endif default: - sprintf(buf, "IP_%d", proto); + sprintf(buf, "IP_%u", proto); return buf; } } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 487b55e..73ba1cc 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 52ca952..09096a6 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -358,6 +358,19 @@ out: rcu_read_unlock(); } +struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct) +{ + struct nf_conn_nat *nat = nfct_nat(ct); + if (nat) + return nat; + + if (!nf_ct_is_confirmed(ct)) + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + + return nat; +} +EXPORT_SYMBOL_GPL(nf_ct_nat_ext_add); + unsigned int nf_nat_setup_info(struct nf_conn *ct, const struct nf_nat_range *range, @@ -368,14 +381,9 @@ nf_nat_setup_info(struct nf_conn *ct, struct nf_conn_nat *nat; /* nat helper or nfctnetlink also setup binding */ - nat = nfct_nat(ct); - if (!nat) { - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) { - pr_debug("failed to add NAT extension\n"); - return NF_ACCEPT; - } - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC || maniptype == NF_NAT_MANIP_DST); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3fd159d..0478847 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -88,6 +88,45 @@ nf_tables_afinfo_lookup(struct net *net, int family, bool autoload) return ERR_PTR(-EAFNOSUPPORT); } +static void nft_ctx_init(struct nft_ctx *ctx, + const struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nft_af_info *afi, + struct nft_table *table, + struct nft_chain *chain, + const struct nlattr * const *nla) +{ + ctx->net = sock_net(skb->sk); + ctx->afi = afi; + ctx->table = table; + ctx->chain = chain; + ctx->nla = nla; + ctx->portid = NETLINK_CB(skb).portid; + ctx->report = nlmsg_report(nlh); + ctx->seq = nlh->nlmsg_seq; +} + +static struct nft_trans *nft_trans_alloc(struct nft_ctx *ctx, int msg_type, + u32 size) +{ + struct nft_trans *trans; + + trans = kzalloc(sizeof(struct nft_trans) + size, GFP_KERNEL); + if (trans == NULL) + return NULL; + + trans->msg_type = msg_type; + trans->ctx = *ctx; + + return trans; +} + +static void nft_trans_destroy(struct nft_trans *trans) +{ + list_del(&trans->list); + kfree(trans); +} + /* * Tables */ @@ -197,20 +236,13 @@ nla_put_failure: return -1; } -static int nf_tables_table_notify(const struct sk_buff *oskb, - const struct nlmsghdr *nlh, - const struct nft_table *table, - int event, int family) +static int nf_tables_table_notify(const struct nft_ctx *ctx, int event) { struct sk_buff *skb; - u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; - u32 seq = nlh ? nlh->nlmsg_seq : 0; - struct net *net = oskb ? sock_net(oskb->sk) : &init_net; - bool report; int err; - report = nlh ? nlmsg_report(nlh) : false; - if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) + if (!ctx->report && + !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return 0; err = -ENOBUFS; @@ -218,18 +250,20 @@ static int nf_tables_table_notify(const struct sk_buff *oskb, if (skb == NULL) goto err; - err = nf_tables_fill_table_info(skb, portid, seq, event, 0, - family, table); + err = nf_tables_fill_table_info(skb, ctx->portid, ctx->seq, event, 0, + ctx->afi->family, ctx->table); if (err < 0) { kfree_skb(skb); goto err; } - err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, - GFP_KERNEL); + err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, + ctx->report, GFP_KERNEL); err: - if (err < 0) - nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err); + if (err < 0) { + nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, + err); + } return err; } @@ -269,6 +303,9 @@ done: return skb->len; } +/* Internal table flags */ +#define NFT_TABLE_INACTIVE (1 << 15) + static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -295,6 +332,8 @@ static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb, table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]); if (IS_ERR(table)) return PTR_ERR(table); + if (table->flags & NFT_TABLE_INACTIVE) + return -ENOENT; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) @@ -343,7 +382,7 @@ err: return err; } -static int nf_tables_table_disable(const struct nft_af_info *afi, +static void nf_tables_table_disable(const struct nft_af_info *afi, struct nft_table *table) { struct nft_chain *chain; @@ -353,45 +392,63 @@ static int nf_tables_table_disable(const struct nft_af_info *afi, nf_unregister_hooks(nft_base_chain(chain)->ops, afi->nops); } - - return 0; } -static int nf_tables_updtable(struct sock *nlsk, struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct nft_af_info *afi, struct nft_table *table) +static int nf_tables_updtable(struct nft_ctx *ctx) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - int family = nfmsg->nfgen_family, ret = 0; + struct nft_trans *trans; + u32 flags; + int ret = 0; - if (nla[NFTA_TABLE_FLAGS]) { - u32 flags; + if (!ctx->nla[NFTA_TABLE_FLAGS]) + return 0; - flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); - if (flags & ~NFT_TABLE_F_DORMANT) - return -EINVAL; + flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS])); + if (flags & ~NFT_TABLE_F_DORMANT) + return -EINVAL; + + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, + sizeof(struct nft_trans_table)); + if (trans == NULL) + return -ENOMEM; - if ((flags & NFT_TABLE_F_DORMANT) && - !(table->flags & NFT_TABLE_F_DORMANT)) { - ret = nf_tables_table_disable(afi, table); - if (ret >= 0) - table->flags |= NFT_TABLE_F_DORMANT; - } else if (!(flags & NFT_TABLE_F_DORMANT) && - table->flags & NFT_TABLE_F_DORMANT) { - ret = nf_tables_table_enable(afi, table); - if (ret >= 0) - table->flags &= ~NFT_TABLE_F_DORMANT; + if ((flags & NFT_TABLE_F_DORMANT) && + !(ctx->table->flags & NFT_TABLE_F_DORMANT)) { + nft_trans_table_enable(trans) = false; + } else if (!(flags & NFT_TABLE_F_DORMANT) && + ctx->table->flags & NFT_TABLE_F_DORMANT) { + ret = nf_tables_table_enable(ctx->afi, ctx->table); + if (ret >= 0) { + ctx->table->flags &= ~NFT_TABLE_F_DORMANT; + nft_trans_table_enable(trans) = true; } - if (ret < 0) - goto err; } + if (ret < 0) + goto err; - nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family); + nft_trans_table_update(trans) = true; + list_add_tail(&trans->list, &ctx->net->nft.commit_list); + return 0; err: + nft_trans_destroy(trans); return ret; } +static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) +{ + struct nft_trans *trans; + + trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_table)); + if (trans == NULL) + return -ENOMEM; + + if (msg_type == NFT_MSG_NEWTABLE) + ctx->table->flags |= NFT_TABLE_INACTIVE; + + list_add_tail(&trans->list, &ctx->net->nft.commit_list); + return 0; +} + static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -403,6 +460,8 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; u32 flags = 0; + struct nft_ctx ctx; + int err; afi = nf_tables_afinfo_lookup(net, family, true); if (IS_ERR(afi)) @@ -417,11 +476,15 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, } if (table != NULL) { + if (table->flags & NFT_TABLE_INACTIVE) + return -ENOENT; if (nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - return nf_tables_updtable(nlsk, skb, nlh, nla, afi, table); + + nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + return nf_tables_updtable(&ctx); } if (nla[NFTA_TABLE_FLAGS]) { @@ -444,8 +507,14 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, INIT_LIST_HEAD(&table->sets); table->flags = flags; + nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); + if (err < 0) { + kfree(table); + module_put(afi->owner); + return err; + } list_add_tail(&table->list, &afi->tables); - nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family); return 0; } @@ -457,7 +526,8 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb, struct nft_af_info *afi; struct nft_table *table; struct net *net = sock_net(skb->sk); - int family = nfmsg->nfgen_family; + int family = nfmsg->nfgen_family, err; + struct nft_ctx ctx; afi = nf_tables_afinfo_lookup(net, family, false); if (IS_ERR(afi)) @@ -466,17 +536,27 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb, table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]); if (IS_ERR(table)) return PTR_ERR(table); + if (table->flags & NFT_TABLE_INACTIVE) + return -ENOENT; if (!list_empty(&table->chains) || !list_empty(&table->sets)) return -EBUSY; + nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); + err = nft_trans_table_add(&ctx, NFT_MSG_DELTABLE); + if (err < 0) + return err; + list_del(&table->list); - nf_tables_table_notify(skb, nlh, table, NFT_MSG_DELTABLE, family); - kfree(table); - module_put(afi->owner); return 0; } +static void nf_tables_table_destroy(struct nft_ctx *ctx) +{ + kfree(ctx->table); + module_put(ctx->afi->owner); +} + int nft_register_chain_type(const struct nf_chain_type *ctype) { int err = 0; @@ -541,7 +621,7 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_CHAIN_HOOK] = { .type = NLA_NESTED }, [NFTA_CHAIN_POLICY] = { .type = NLA_U32 }, - [NFTA_CHAIN_TYPE] = { .type = NLA_NUL_STRING }, + [NFTA_CHAIN_TYPE] = { .type = NLA_STRING }, [NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED }, }; @@ -637,21 +717,13 @@ nla_put_failure: return -1; } -static int nf_tables_chain_notify(const struct sk_buff *oskb, - const struct nlmsghdr *nlh, - const struct nft_table *table, - const struct nft_chain *chain, - int event, int family) +static int nf_tables_chain_notify(const struct nft_ctx *ctx, int event) { struct sk_buff *skb; - u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; - struct net *net = oskb ? sock_net(oskb->sk) : &init_net; - u32 seq = nlh ? nlh->nlmsg_seq : 0; - bool report; int err; - report = nlh ? nlmsg_report(nlh) : false; - if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) + if (!ctx->report && + !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return 0; err = -ENOBUFS; @@ -659,18 +731,21 @@ static int nf_tables_chain_notify(const struct sk_buff *oskb, if (skb == NULL) goto err; - err = nf_tables_fill_chain_info(skb, portid, seq, event, 0, family, - table, chain); + err = nf_tables_fill_chain_info(skb, ctx->portid, ctx->seq, event, 0, + ctx->afi->family, ctx->table, + ctx->chain); if (err < 0) { kfree_skb(skb); goto err; } - err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, - GFP_KERNEL); + err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, + ctx->report, GFP_KERNEL); err: - if (err < 0) - nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err); + if (err < 0) { + nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, + err); + } return err; } @@ -740,10 +815,14 @@ static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb, table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]); if (IS_ERR(table)) return PTR_ERR(table); + if (table->flags & NFT_TABLE_INACTIVE) + return -ENOENT; chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]); if (IS_ERR(chain)) return PTR_ERR(chain); + if (chain->flags & NFT_CHAIN_INACTIVE) + return -ENOENT; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) @@ -767,8 +846,7 @@ static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = { [NFTA_COUNTER_BYTES] = { .type = NLA_U64 }, }; -static int -nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr) +static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) { struct nlattr *tb[NFTA_COUNTER_MAX+1]; struct nft_stats __percpu *newstats; @@ -777,14 +855,14 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr) err = nla_parse_nested(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy); if (err < 0) - return err; + return ERR_PTR(err); if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS]) - return -EINVAL; + return ERR_PTR(-EINVAL); newstats = alloc_percpu(struct nft_stats); if (newstats == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); /* Restore old counters on this cpu, no problem. Per-cpu statistics * are not exposed to userspace. @@ -793,6 +871,12 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr) stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); + return newstats; +} + +static void nft_chain_stats_replace(struct nft_base_chain *chain, + struct nft_stats __percpu *newstats) +{ if (chain->stats) { struct nft_stats __percpu *oldstats = nft_dereference(chain->stats); @@ -802,17 +886,43 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr) free_percpu(oldstats); } else rcu_assign_pointer(chain->stats, newstats); +} + +static int nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) +{ + struct nft_trans *trans; + + trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_chain)); + if (trans == NULL) + return -ENOMEM; + + if (msg_type == NFT_MSG_NEWCHAIN) + ctx->chain->flags |= NFT_CHAIN_INACTIVE; + list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; } +static void nf_tables_chain_destroy(struct nft_chain *chain) +{ + BUG_ON(chain->use > 0); + + if (chain->flags & NFT_BASE_CHAIN) { + module_put(nft_base_chain(chain)->type->owner); + free_percpu(nft_base_chain(chain)->stats); + kfree(nft_base_chain(chain)); + } else { + kfree(chain); + } +} + static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nlattr * uninitialized_var(name); - const struct nft_af_info *afi; + struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain; struct nft_base_chain *basechain = NULL; @@ -822,8 +932,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, u8 policy = NF_ACCEPT; u64 handle = 0; unsigned int i; + struct nft_stats __percpu *stats; int err; bool create; + struct nft_ctx ctx; create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; @@ -869,6 +981,11 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, } if (chain != NULL) { + struct nft_stats *stats = NULL; + struct nft_trans *trans; + + if (chain->flags & NFT_CHAIN_INACTIVE) + return -ENOENT; if (nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (nlh->nlmsg_flags & NLM_F_REPLACE) @@ -882,19 +999,31 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (!(chain->flags & NFT_BASE_CHAIN)) return -EOPNOTSUPP; - err = nf_tables_counters(nft_base_chain(chain), - nla[NFTA_CHAIN_COUNTERS]); - if (err < 0) - return err; + stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); + if (IS_ERR(stats)) + return PTR_ERR(stats); } - if (nla[NFTA_CHAIN_POLICY]) - nft_base_chain(chain)->policy = policy; + nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN, + sizeof(struct nft_trans_chain)); + if (trans == NULL) + return -ENOMEM; - if (nla[NFTA_CHAIN_HANDLE] && name) - nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN); + nft_trans_chain_stats(trans) = stats; + nft_trans_chain_update(trans) = true; - goto notify; + if (nla[NFTA_CHAIN_POLICY]) + nft_trans_chain_policy(trans) = policy; + else + nft_trans_chain_policy(trans) = -1; + + if (nla[NFTA_CHAIN_HANDLE] && name) { + nla_strlcpy(nft_trans_chain_name(trans), name, + NFT_CHAIN_MAXNAMELEN); + } + list_add_tail(&trans->list, &net->nft.commit_list); + return 0; } if (table->use == UINT_MAX) @@ -939,23 +1068,21 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, return -ENOMEM; if (nla[NFTA_CHAIN_COUNTERS]) { - err = nf_tables_counters(basechain, - nla[NFTA_CHAIN_COUNTERS]); - if (err < 0) { + stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); + if (IS_ERR(stats)) { module_put(type->owner); kfree(basechain); - return err; + return PTR_ERR(stats); } + basechain->stats = stats; } else { - struct nft_stats __percpu *newstats; - - newstats = alloc_percpu(struct nft_stats); - if (newstats == NULL) { + stats = alloc_percpu(struct nft_stats); + if (IS_ERR(stats)) { module_put(type->owner); kfree(basechain); - return -ENOMEM; + return PTR_ERR(stats); } - rcu_assign_pointer(basechain->stats, newstats); + rcu_assign_pointer(basechain->stats, stats); } basechain->type = type; @@ -992,31 +1119,26 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (!(table->flags & NFT_TABLE_F_DORMANT) && chain->flags & NFT_BASE_CHAIN) { err = nf_register_hooks(nft_base_chain(chain)->ops, afi->nops); - if (err < 0) { - module_put(basechain->type->owner); - free_percpu(basechain->stats); - kfree(basechain); - return err; - } + if (err < 0) + goto err1; } - list_add_tail(&chain->list, &table->chains); - table->use++; -notify: - nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_NEWCHAIN, - family); - return 0; -} -static void nf_tables_chain_destroy(struct nft_chain *chain) -{ - BUG_ON(chain->use > 0); + nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN); + if (err < 0) + goto err2; - if (chain->flags & NFT_BASE_CHAIN) { - module_put(nft_base_chain(chain)->type->owner); - free_percpu(nft_base_chain(chain)->stats); - kfree(nft_base_chain(chain)); - } else - kfree(chain); + list_add_tail(&chain->list, &table->chains); + return 0; +err2: + if (!(table->flags & NFT_TABLE_F_DORMANT) && + chain->flags & NFT_BASE_CHAIN) { + nf_unregister_hooks(nft_base_chain(chain)->ops, + afi->nops); + } +err1: + nf_tables_chain_destroy(chain); + return err; } static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, @@ -1024,11 +1146,13 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nft_af_info *afi; + struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nft_ctx ctx; + int err; afi = nf_tables_afinfo_lookup(net, family, false); if (IS_ERR(afi)) @@ -1037,48 +1161,26 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]); if (IS_ERR(table)) return PTR_ERR(table); + if (table->flags & NFT_TABLE_INACTIVE) + return -ENOENT; chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]); if (IS_ERR(chain)) return PTR_ERR(chain); - + if (chain->flags & NFT_CHAIN_INACTIVE) + return -ENOENT; if (!list_empty(&chain->rules) || chain->use > 0) return -EBUSY; - list_del(&chain->list); - table->use--; - - if (!(table->flags & NFT_TABLE_F_DORMANT) && - chain->flags & NFT_BASE_CHAIN) - nf_unregister_hooks(nft_base_chain(chain)->ops, afi->nops); - - nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_DELCHAIN, - family); - - /* Make sure all rule references are gone before this is released */ - synchronize_rcu(); + nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); + err = nft_trans_chain_add(&ctx, NFT_MSG_DELCHAIN); + if (err < 0) + return err; - nf_tables_chain_destroy(chain); + list_del(&chain->list); return 0; } -static void nft_ctx_init(struct nft_ctx *ctx, - const struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nft_af_info *afi, - const struct nft_table *table, - const struct nft_chain *chain, - const struct nlattr * const *nla) -{ - ctx->net = sock_net(skb->sk); - ctx->skb = skb; - ctx->nlh = nlh; - ctx->afi = afi; - ctx->table = table; - ctx->chain = chain; - ctx->nla = nla; -} - /* * Expressions */ @@ -1093,7 +1195,10 @@ static void nft_ctx_init(struct nft_ctx *ctx, int nft_register_expr(struct nft_expr_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_add_tail(&type->list, &nf_tables_expressions); + if (type->family == NFPROTO_UNSPEC) + list_add_tail(&type->list, &nf_tables_expressions); + else + list_add(&type->list, &nf_tables_expressions); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } @@ -1361,22 +1466,15 @@ nla_put_failure: return -1; } -static int nf_tables_rule_notify(const struct sk_buff *oskb, - const struct nlmsghdr *nlh, - const struct nft_table *table, - const struct nft_chain *chain, +static int nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, - int event, u32 flags, int family) + int event) { struct sk_buff *skb; - u32 portid = NETLINK_CB(oskb).portid; - struct net *net = oskb ? sock_net(oskb->sk) : &init_net; - u32 seq = nlh->nlmsg_seq; - bool report; int err; - report = nlmsg_report(nlh); - if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) + if (!ctx->report && + !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return 0; err = -ENOBUFS; @@ -1384,18 +1482,21 @@ static int nf_tables_rule_notify(const struct sk_buff *oskb, if (skb == NULL) goto err; - err = nf_tables_fill_rule_info(skb, portid, seq, event, flags, - family, table, chain, rule); + err = nf_tables_fill_rule_info(skb, ctx->portid, ctx->seq, event, 0, + ctx->afi->family, ctx->table, + ctx->chain, rule); if (err < 0) { kfree_skb(skb); goto err; } - err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, - GFP_KERNEL); + err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, + ctx->report, GFP_KERNEL); err: - if (err < 0) - nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err); + if (err < 0) { + nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, + err); + } return err; } @@ -1511,10 +1612,14 @@ static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb, table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]); if (IS_ERR(table)) return PTR_ERR(table); + if (table->flags & NFT_TABLE_INACTIVE) + return -ENOENT; chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]); if (IS_ERR(chain)) return PTR_ERR(chain); + if (chain->flags & NFT_CHAIN_INACTIVE) + return -ENOENT; rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) @@ -1554,37 +1659,36 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, kfree(rule); } -#define NFT_RULE_MAXEXPRS 128 - -static struct nft_expr_info *info; - -static struct nft_rule_trans * -nf_tables_trans_add(struct nft_ctx *ctx, struct nft_rule *rule) +static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, + struct nft_rule *rule) { - struct nft_rule_trans *rupd; + struct nft_trans *trans; - rupd = kmalloc(sizeof(struct nft_rule_trans), GFP_KERNEL); - if (rupd == NULL) - return NULL; + trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_rule)); + if (trans == NULL) + return NULL; - rupd->ctx = *ctx; - rupd->rule = rule; - list_add_tail(&rupd->list, &ctx->net->nft.commit_list); + nft_trans_rule(trans) = rule; + list_add_tail(&trans->list, &ctx->net->nft.commit_list); - return rupd; + return trans; } +#define NFT_RULE_MAXEXPRS 128 + +static struct nft_expr_info *info; + static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nft_af_info *afi; + struct nft_af_info *afi; struct net *net = sock_net(skb->sk); struct nft_table *table; struct nft_chain *chain; struct nft_rule *rule, *old_rule = NULL; - struct nft_rule_trans *repl = NULL; + struct nft_trans *trans = NULL; struct nft_expr *expr; struct nft_ctx ctx; struct nlattr *tmp; @@ -1682,8 +1786,9 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_REPLACE) { if (nft_rule_is_active_next(net, old_rule)) { - repl = nf_tables_trans_add(&ctx, old_rule); - if (repl == NULL) { + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, + old_rule); + if (trans == NULL) { err = -ENOMEM; goto err2; } @@ -1705,7 +1810,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, list_add_rcu(&rule->list, &chain->rules); } - if (nf_tables_trans_add(&ctx, rule) == NULL) { + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { err = -ENOMEM; goto err3; } @@ -1713,11 +1818,10 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, err3: list_del_rcu(&rule->list); - if (repl) { - list_del_rcu(&repl->rule->list); - list_del(&repl->list); - nft_rule_clear(net, repl->rule); - kfree(repl); + if (trans) { + list_del_rcu(&nft_trans_rule(trans)->list); + nft_rule_clear(net, nft_trans_rule(trans)); + nft_trans_destroy(trans); } err2: nf_tables_rule_destroy(&ctx, rule); @@ -1734,7 +1838,7 @@ nf_tables_delrule_one(struct nft_ctx *ctx, struct nft_rule *rule) { /* You cannot delete the same rule twice */ if (nft_rule_is_active_next(ctx->net, rule)) { - if (nf_tables_trans_add(ctx, rule) == NULL) + if (nft_trans_rule_add(ctx, NFT_MSG_DELRULE, rule) == NULL) return -ENOMEM; nft_rule_disactivate_next(ctx->net, rule); return 0; @@ -1760,9 +1864,9 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nft_af_info *afi; + struct nft_af_info *afi; struct net *net = sock_net(skb->sk); - const struct nft_table *table; + struct nft_table *table; struct nft_chain *chain = NULL; struct nft_rule *rule; int family = nfmsg->nfgen_family, err = 0; @@ -1775,6 +1879,8 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]); if (IS_ERR(table)) return PTR_ERR(table); + if (table->flags & NFT_TABLE_INACTIVE) + return -ENOENT; if (nla[NFTA_RULE_CHAIN]) { chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]); @@ -1807,88 +1913,6 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, return err; } -static int nf_tables_commit(struct sk_buff *skb) -{ - struct net *net = sock_net(skb->sk); - struct nft_rule_trans *rupd, *tmp; - - /* Bump generation counter, invalidate any dump in progress */ - net->nft.genctr++; - - /* A new generation has just started */ - net->nft.gencursor = gencursor_next(net); - - /* Make sure all packets have left the previous generation before - * purging old rules. - */ - synchronize_rcu(); - - list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - /* This rule was inactive in the past and just became active. - * Clear the next bit of the genmask since its meaning has - * changed, now it is the future. - */ - if (nft_rule_is_active(net, rupd->rule)) { - nft_rule_clear(net, rupd->rule); - nf_tables_rule_notify(skb, rupd->ctx.nlh, - rupd->ctx.table, rupd->ctx.chain, - rupd->rule, NFT_MSG_NEWRULE, 0, - rupd->ctx.afi->family); - list_del(&rupd->list); - kfree(rupd); - continue; - } - - /* This rule is in the past, get rid of it */ - list_del_rcu(&rupd->rule->list); - nf_tables_rule_notify(skb, rupd->ctx.nlh, - rupd->ctx.table, rupd->ctx.chain, - rupd->rule, NFT_MSG_DELRULE, 0, - rupd->ctx.afi->family); - } - - /* Make sure we don't see any packet traversing old rules */ - synchronize_rcu(); - - /* Now we can safely release unused old rules */ - list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - nf_tables_rule_destroy(&rupd->ctx, rupd->rule); - list_del(&rupd->list); - kfree(rupd); - } - - return 0; -} - -static int nf_tables_abort(struct sk_buff *skb) -{ - struct net *net = sock_net(skb->sk); - struct nft_rule_trans *rupd, *tmp; - - list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - if (!nft_rule_is_active_next(net, rupd->rule)) { - nft_rule_clear(net, rupd->rule); - list_del(&rupd->list); - kfree(rupd); - continue; - } - - /* This rule is inactive, get rid of it */ - list_del_rcu(&rupd->rule->list); - } - - /* Make sure we don't see any packet accessing aborted rules */ - synchronize_rcu(); - - list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - nf_tables_rule_destroy(&rupd->ctx, rupd->rule); - list_del(&rupd->list); - kfree(rupd); - } - - return 0; -} - /* * Sets */ @@ -1912,9 +1936,18 @@ void nft_unregister_set(struct nft_set_ops *ops) } EXPORT_SYMBOL_GPL(nft_unregister_set); -static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const nla[]) +/* + * Select a set implementation based on the data characteristics and the + * given policy. The total memory use might not be known if no size is + * given, in that case the amount of memory per element is used. + */ +static const struct nft_set_ops * +nft_select_set_ops(const struct nlattr * const nla[], + const struct nft_set_desc *desc, + enum nft_set_policies policy) { - const struct nft_set_ops *ops; + const struct nft_set_ops *ops, *bops; + struct nft_set_estimate est, best; u32 features; #ifdef CONFIG_MODULES @@ -1932,15 +1965,45 @@ static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const features &= NFT_SET_INTERVAL | NFT_SET_MAP; } - // FIXME: implement selection properly + bops = NULL; + best.size = ~0; + best.class = ~0; + list_for_each_entry(ops, &nf_tables_set_ops, list) { if ((ops->features & features) != features) continue; + if (!ops->estimate(desc, features, &est)) + continue; + + switch (policy) { + case NFT_SET_POL_PERFORMANCE: + if (est.class < best.class) + break; + if (est.class == best.class && est.size < best.size) + break; + continue; + case NFT_SET_POL_MEMORY: + if (est.size < best.size) + break; + if (est.size == best.size && est.class < best.class) + break; + continue; + default: + break; + } + if (!try_module_get(ops->owner)) continue; - return ops; + if (bops != NULL) + module_put(bops->owner); + + bops = ops; + best = est; } + if (bops != NULL) + return bops; + return ERR_PTR(-EOPNOTSUPP); } @@ -1953,6 +2016,13 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_KEY_LEN] = { .type = NLA_U32 }, [NFTA_SET_DATA_TYPE] = { .type = NLA_U32 }, [NFTA_SET_DATA_LEN] = { .type = NLA_U32 }, + [NFTA_SET_POLICY] = { .type = NLA_U32 }, + [NFTA_SET_DESC] = { .type = NLA_NESTED }, + [NFTA_SET_ID] = { .type = NLA_U32 }, +}; + +static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { + [NFTA_SET_DESC_SIZE] = { .type = NLA_U32 }, }; static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, @@ -1962,8 +2032,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, { struct net *net = sock_net(skb->sk); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nft_af_info *afi = NULL; - const struct nft_table *table = NULL; + struct nft_af_info *afi = NULL; + struct nft_table *table = NULL; if (nfmsg->nfgen_family != NFPROTO_UNSPEC) { afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false); @@ -1978,6 +2048,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]); if (IS_ERR(table)) return PTR_ERR(table); + if (table->flags & NFT_TABLE_INACTIVE) + return -ENOENT; } nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla); @@ -1999,13 +2071,27 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table, return ERR_PTR(-ENOENT); } +struct nft_set *nf_tables_set_lookup_byid(const struct net *net, + const struct nlattr *nla) +{ + struct nft_trans *trans; + u32 id = ntohl(nla_get_be32(nla)); + + list_for_each_entry(trans, &net->nft.commit_list, list) { + if (trans->msg_type == NFT_MSG_NEWSET && + id == nft_trans_set_id(trans)) + return nft_trans_set(trans); + } + return ERR_PTR(-ENOENT); +} + static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, const char *name) { const struct nft_set *i; const char *p; unsigned long *inuse; - unsigned int n = 0; + unsigned int n = 0, min = 0; p = strnchr(name, IFNAMSIZ, '%'); if (p != NULL) { @@ -2015,23 +2101,28 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (inuse == NULL) return -ENOMEM; - +cont: list_for_each_entry(i, &ctx->table->sets, list) { int tmp; if (!sscanf(i->name, name, &tmp)) continue; - if (tmp < 0 || tmp >= BITS_PER_BYTE * PAGE_SIZE) + if (tmp < min || tmp >= min + BITS_PER_BYTE * PAGE_SIZE) continue; - set_bit(tmp, inuse); + set_bit(tmp - min, inuse); } n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE); + if (n >= BITS_PER_BYTE * PAGE_SIZE) { + min += BITS_PER_BYTE * PAGE_SIZE; + memset(inuse, 0, PAGE_SIZE); + goto cont; + } free_page((unsigned long)inuse); } - snprintf(set->name, sizeof(set->name), name, n); + snprintf(set->name, sizeof(set->name), name, min + n); list_for_each_entry(i, &ctx->table->sets, list) { if (!strcmp(set->name, i->name)) return -ENFILE; @@ -2044,8 +2135,9 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, { struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; - u32 portid = NETLINK_CB(ctx->skb).portid; - u32 seq = ctx->nlh->nlmsg_seq; + struct nlattr *desc; + u32 portid = ctx->portid; + u32 seq = ctx->seq; event |= NFNL_SUBSYS_NFTABLES << 8; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), @@ -2077,6 +2169,14 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; } + desc = nla_nest_start(skb, NFTA_SET_DESC); + if (desc == NULL) + goto nla_put_failure; + if (set->size && + nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size))) + goto nla_put_failure; + nla_nest_end(skb, desc); + return nlmsg_end(skb, nlh); nla_put_failure: @@ -2089,12 +2189,11 @@ static int nf_tables_set_notify(const struct nft_ctx *ctx, int event) { struct sk_buff *skb; - u32 portid = NETLINK_CB(ctx->skb).portid; - bool report; + u32 portid = ctx->portid; int err; - report = nlmsg_report(ctx->nlh); - if (!report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) + if (!ctx->report && + !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return 0; err = -ENOBUFS; @@ -2108,8 +2207,8 @@ static int nf_tables_set_notify(const struct nft_ctx *ctx, goto err; } - err = nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, report, - GFP_KERNEL); + err = nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, + ctx->report, GFP_KERNEL); err: if (err < 0) nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, err); @@ -2183,7 +2282,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, { const struct nft_set *set; unsigned int idx, s_idx = cb->args[0]; - const struct nft_af_info *afi; + struct nft_af_info *afi; struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); int cur_family = cb->args[3]; @@ -2260,6 +2359,8 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) return ret; } +#define NFT_SET_INACTIVE (1 << 15) /* Internal set flag */ + static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -2289,6 +2390,8 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]); if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_INACTIVE) + return -ENOENT; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (skb2 == NULL) @@ -2305,13 +2408,50 @@ err: return err; } +static int nf_tables_set_desc_parse(const struct nft_ctx *ctx, + struct nft_set_desc *desc, + const struct nlattr *nla) +{ + struct nlattr *da[NFTA_SET_DESC_MAX + 1]; + int err; + + err = nla_parse_nested(da, NFTA_SET_DESC_MAX, nla, nft_set_desc_policy); + if (err < 0) + return err; + + if (da[NFTA_SET_DESC_SIZE] != NULL) + desc->size = ntohl(nla_get_be32(da[NFTA_SET_DESC_SIZE])); + + return 0; +} + +static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type, + struct nft_set *set) +{ + struct nft_trans *trans; + + trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_set)); + if (trans == NULL) + return -ENOMEM; + + if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) { + nft_trans_set_id(trans) = + ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID])); + set->flags |= NFT_SET_INACTIVE; + } + nft_trans_set(trans) = set; + list_add_tail(&trans->list, &ctx->net->nft.commit_list); + + return 0; +} + static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nft_set_ops *ops; - const struct nft_af_info *afi; + struct nft_af_info *afi; struct net *net = sock_net(skb->sk); struct nft_table *table; struct nft_set *set; @@ -2319,14 +2459,18 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, char name[IFNAMSIZ]; unsigned int size; bool create; - u32 ktype, klen, dlen, dtype, flags; + u32 ktype, dtype, flags, policy; + struct nft_set_desc desc; int err; if (nla[NFTA_SET_TABLE] == NULL || nla[NFTA_SET_NAME] == NULL || - nla[NFTA_SET_KEY_LEN] == NULL) + nla[NFTA_SET_KEY_LEN] == NULL || + nla[NFTA_SET_ID] == NULL) return -EINVAL; + memset(&desc, 0, sizeof(desc)); + ktype = NFT_DATA_VALUE; if (nla[NFTA_SET_KEY_TYPE] != NULL) { ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE])); @@ -2334,8 +2478,8 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, return -EINVAL; } - klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); - if (klen == 0 || klen > FIELD_SIZEOF(struct nft_data, data)) + desc.klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); + if (desc.klen == 0 || desc.klen > FIELD_SIZEOF(struct nft_data, data)) return -EINVAL; flags = 0; @@ -2347,7 +2491,6 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, } dtype = 0; - dlen = 0; if (nla[NFTA_SET_DATA_TYPE] != NULL) { if (!(flags & NFT_SET_MAP)) return -EINVAL; @@ -2360,15 +2503,25 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, if (dtype != NFT_DATA_VERDICT) { if (nla[NFTA_SET_DATA_LEN] == NULL) return -EINVAL; - dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN])); - if (dlen == 0 || - dlen > FIELD_SIZEOF(struct nft_data, data)) + desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN])); + if (desc.dlen == 0 || + desc.dlen > FIELD_SIZEOF(struct nft_data, data)) return -EINVAL; } else - dlen = sizeof(struct nft_data); + desc.dlen = sizeof(struct nft_data); } else if (flags & NFT_SET_MAP) return -EINVAL; + policy = NFT_SET_POL_PERFORMANCE; + if (nla[NFTA_SET_POLICY] != NULL) + policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); + + if (nla[NFTA_SET_DESC] != NULL) { + err = nf_tables_set_desc_parse(&ctx, &desc, nla[NFTA_SET_DESC]); + if (err < 0) + return err; + } + create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, create); @@ -2399,7 +2552,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, if (!(nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; - ops = nft_select_set_ops(nla); + ops = nft_select_set_ops(nla, &desc, policy); if (IS_ERR(ops)) return PTR_ERR(ops); @@ -2420,17 +2573,21 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, INIT_LIST_HEAD(&set->bindings); set->ops = ops; set->ktype = ktype; - set->klen = klen; + set->klen = desc.klen; set->dtype = dtype; - set->dlen = dlen; + set->dlen = desc.dlen; set->flags = flags; + set->size = desc.size; - err = ops->init(set, nla); + err = ops->init(set, &desc, nla); + if (err < 0) + goto err2; + + err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) goto err2; list_add_tail(&set->list, &table->sets); - nf_tables_set_notify(&ctx, set, NFT_MSG_NEWSET); return 0; err2: @@ -2440,16 +2597,20 @@ err1: return err; } -static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) +static void nft_set_destroy(struct nft_set *set) { - list_del(&set->list); - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET); - set->ops->destroy(set); module_put(set->ops->owner); kfree(set); } +static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) +{ + list_del(&set->list); + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET); + nft_set_destroy(set); +} + static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -2471,10 +2632,16 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]); if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_INACTIVE) + return -ENOENT; if (!list_empty(&set->bindings)) return -EBUSY; - nf_tables_set_destroy(&ctx, set); + err = nft_trans_set_add(&ctx, NFT_MSG_DELSET, set); + if (err < 0) + return err; + + list_del(&set->list); return 0; } @@ -2534,7 +2701,8 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, { list_del(&binding->list); - if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS) + if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS && + !(set->flags & NFT_SET_INACTIVE)) nf_tables_set_destroy(ctx, set); } @@ -2552,16 +2720,18 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + [NFTA_SET_ELEM_LIST_TABLE] = { .type = NLA_STRING }, [NFTA_SET_ELEM_LIST_SET] = { .type = NLA_STRING }, [NFTA_SET_ELEM_LIST_ELEMENTS] = { .type = NLA_NESTED }, + [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, const struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[]) + const struct nlattr * const nla[], + bool trans) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nft_af_info *afi; - const struct nft_table *table; + struct nft_af_info *afi; + struct nft_table *table; struct net *net = sock_net(skb->sk); afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false); @@ -2571,6 +2741,8 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE]); if (IS_ERR(table)) return PTR_ERR(table); + if (!trans && (table->flags & NFT_TABLE_INACTIVE)) + return -ENOENT; nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla); return 0; @@ -2644,13 +2816,16 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (err < 0) return err; - err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla); + err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla, + false); if (err < 0) return err; set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_INACTIVE) + return -ENOENT; event = NFT_MSG_NEWSETELEM; event |= NFNL_SUBSYS_NFTABLES << 8; @@ -2707,13 +2882,15 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb, struct nft_ctx ctx; int err; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla); + err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false); if (err < 0) return err; set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_INACTIVE) + return -ENOENT; if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -2724,7 +2901,98 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb, return -EOPNOTSUPP; } -static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set, +static int nf_tables_fill_setelem_info(struct sk_buff *skb, + const struct nft_ctx *ctx, u32 seq, + u32 portid, int event, u16 flags, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nfgenmsg *nfmsg; + struct nlmsghdr *nlh; + struct nlattr *nest; + int err; + + event |= NFNL_SUBSYS_NFTABLES << 8; + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), + flags); + if (nlh == NULL) + goto nla_put_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = ctx->afi->family; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) + goto nla_put_failure; + if (nla_put_string(skb, NFTA_SET_NAME, set->name)) + goto nla_put_failure; + + nest = nla_nest_start(skb, NFTA_SET_ELEM_LIST_ELEMENTS); + if (nest == NULL) + goto nla_put_failure; + + err = nf_tables_fill_setelem(skb, set, elem); + if (err < 0) + goto nla_put_failure; + + nla_nest_end(skb, nest); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_trim(skb, nlh); + return -1; +} + +static int nf_tables_setelem_notify(const struct nft_ctx *ctx, + const struct nft_set *set, + const struct nft_set_elem *elem, + int event, u16 flags) +{ + struct net *net = ctx->net; + u32 portid = ctx->portid; + struct sk_buff *skb; + int err; + + if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) + return 0; + + err = -ENOBUFS; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto err; + + err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, + set, elem); + if (err < 0) { + kfree_skb(skb); + goto err; + } + + err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report, + GFP_KERNEL); +err: + if (err < 0) + nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err); + return err; +} + +static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx, + int msg_type, + struct nft_set *set) +{ + struct nft_trans *trans; + + trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_elem)); + if (trans == NULL) + return NULL; + + nft_trans_elem_set(trans) = set; + return trans; +} + +static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; @@ -2732,8 +3000,12 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_elem elem; struct nft_set_binding *binding; enum nft_registers dreg; + struct nft_trans *trans; int err; + if (set->size && set->nelems == set->size) + return -ENFILE; + err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy); if (err < 0) @@ -2786,7 +3058,7 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set, struct nft_ctx bind_ctx = { .afi = ctx->afi, .table = ctx->table, - .chain = binding->chain, + .chain = (struct nft_chain *)binding->chain, }; err = nft_validate_data_load(&bind_ctx, dreg, @@ -2796,12 +3068,20 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set, } } + trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); + if (trans == NULL) + goto err3; + err = set->ops->insert(set, &elem); if (err < 0) - goto err3; + goto err4; + nft_trans_elem(trans) = elem; + list_add(&trans->list, &ctx->net->nft.commit_list); return 0; +err4: + kfree(trans); err3: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_uninit(&elem.data, d2.type); @@ -2815,35 +3095,44 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + struct net *net = sock_net(skb->sk); const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; - int rem, err; + int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla); + err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, true); if (err < 0) return err; set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); - if (IS_ERR(set)) - return PTR_ERR(set); + if (IS_ERR(set)) { + if (nla[NFTA_SET_ELEM_LIST_SET_ID]) { + set = nf_tables_set_lookup_byid(net, + nla[NFTA_SET_ELEM_LIST_SET_ID]); + } + if (IS_ERR(set)) + return PTR_ERR(set); + } + if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) return -EBUSY; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_add_set_elem(&ctx, set, attr); if (err < 0) - return err; + break; } - return 0; + return err; } -static int nft_del_setelem(const struct nft_ctx *ctx, struct nft_set *set, +static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_data_desc desc; struct nft_set_elem elem; + struct nft_trans *trans; int err; err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr, @@ -2867,7 +3156,12 @@ static int nft_del_setelem(const struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err2; - set->ops->remove(set, &elem); + trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); + if (trans == NULL) + goto err2; + + nft_trans_elem(trans) = elem; + list_add(&trans->list, &ctx->net->nft.commit_list); nft_data_uninit(&elem.key, NFT_DATA_VALUE); if (set->flags & NFT_SET_MAP) @@ -2886,9 +3180,9 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb, const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; - int rem, err; + int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla); + err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false); if (err < 0) return err; @@ -2901,14 +3195,14 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); if (err < 0) - return err; + break; } - return 0; + return err; } static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { [NFT_MSG_NEWTABLE] = { - .call = nf_tables_newtable, + .call_batch = nf_tables_newtable, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, @@ -2918,12 +3212,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_table_policy, }, [NFT_MSG_DELTABLE] = { - .call = nf_tables_deltable, + .call_batch = nf_tables_deltable, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_NEWCHAIN] = { - .call = nf_tables_newchain, + .call_batch = nf_tables_newchain, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, @@ -2933,7 +3227,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_chain_policy, }, [NFT_MSG_DELCHAIN] = { - .call = nf_tables_delchain, + .call_batch = nf_tables_delchain, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, @@ -2953,7 +3247,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_rule_policy, }, [NFT_MSG_NEWSET] = { - .call = nf_tables_newset, + .call_batch = nf_tables_newset, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, @@ -2963,12 +3257,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_set_policy, }, [NFT_MSG_DELSET] = { - .call = nf_tables_delset, + .call_batch = nf_tables_delset, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_NEWSETELEM] = { - .call = nf_tables_newsetelem, + .call_batch = nf_tables_newsetelem, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, @@ -2978,12 +3272,270 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_set_elem_list_policy, }, [NFT_MSG_DELSETELEM] = { - .call = nf_tables_delsetelem, + .call_batch = nf_tables_delsetelem, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, }; +static void nft_chain_commit_update(struct nft_trans *trans) +{ + struct nft_base_chain *basechain; + + if (nft_trans_chain_name(trans)[0]) + strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans)); + + if (!(trans->ctx.chain->flags & NFT_BASE_CHAIN)) + return; + + basechain = nft_base_chain(trans->ctx.chain); + nft_chain_stats_replace(basechain, nft_trans_chain_stats(trans)); + + switch (nft_trans_chain_policy(trans)) { + case NF_DROP: + case NF_ACCEPT: + basechain->policy = nft_trans_chain_policy(trans); + break; + } +} + +/* Schedule objects for release via rcu to make sure no packets are accesing + * removed rules. + */ +static void nf_tables_commit_release_rcu(struct rcu_head *rt) +{ + struct nft_trans *trans = container_of(rt, struct nft_trans, rcu_head); + + switch (trans->msg_type) { + case NFT_MSG_DELTABLE: + nf_tables_table_destroy(&trans->ctx); + break; + case NFT_MSG_DELCHAIN: + nf_tables_chain_destroy(trans->ctx.chain); + break; + case NFT_MSG_DELRULE: + nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); + break; + case NFT_MSG_DELSET: + nft_set_destroy(nft_trans_set(trans)); + break; + } + kfree(trans); +} + +static int nf_tables_commit(struct sk_buff *skb) +{ + struct net *net = sock_net(skb->sk); + struct nft_trans *trans, *next; + struct nft_set *set; + + /* Bump generation counter, invalidate any dump in progress */ + net->nft.genctr++; + + /* A new generation has just started */ + net->nft.gencursor = gencursor_next(net); + + /* Make sure all packets have left the previous generation before + * purging old rules. + */ + synchronize_rcu(); + + list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + switch (trans->msg_type) { + case NFT_MSG_NEWTABLE: + if (nft_trans_table_update(trans)) { + if (!nft_trans_table_enable(trans)) { + nf_tables_table_disable(trans->ctx.afi, + trans->ctx.table); + trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; + } + } else { + trans->ctx.table->flags &= ~NFT_TABLE_INACTIVE; + } + nf_tables_table_notify(&trans->ctx, NFT_MSG_NEWTABLE); + nft_trans_destroy(trans); + break; + case NFT_MSG_DELTABLE: + nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); + break; + case NFT_MSG_NEWCHAIN: + if (nft_trans_chain_update(trans)) + nft_chain_commit_update(trans); + else { + trans->ctx.chain->flags &= ~NFT_CHAIN_INACTIVE; + trans->ctx.table->use++; + } + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + nft_trans_destroy(trans); + break; + case NFT_MSG_DELCHAIN: + trans->ctx.table->use--; + nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN); + if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT) && + trans->ctx.chain->flags & NFT_BASE_CHAIN) { + nf_unregister_hooks(nft_base_chain(trans->ctx.chain)->ops, + trans->ctx.afi->nops); + } + break; + case NFT_MSG_NEWRULE: + nft_rule_clear(trans->ctx.net, nft_trans_rule(trans)); + nf_tables_rule_notify(&trans->ctx, + nft_trans_rule(trans), + NFT_MSG_NEWRULE); + nft_trans_destroy(trans); + break; + case NFT_MSG_DELRULE: + list_del_rcu(&nft_trans_rule(trans)->list); + nf_tables_rule_notify(&trans->ctx, + nft_trans_rule(trans), + NFT_MSG_DELRULE); + break; + case NFT_MSG_NEWSET: + nft_trans_set(trans)->flags &= ~NFT_SET_INACTIVE; + nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), + NFT_MSG_NEWSET); + nft_trans_destroy(trans); + break; + case NFT_MSG_DELSET: + nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), + NFT_MSG_DELSET); + break; + case NFT_MSG_NEWSETELEM: + nft_trans_elem_set(trans)->nelems++; + nf_tables_setelem_notify(&trans->ctx, + nft_trans_elem_set(trans), + &nft_trans_elem(trans), + NFT_MSG_NEWSETELEM, 0); + nft_trans_destroy(trans); + break; + case NFT_MSG_DELSETELEM: + nft_trans_elem_set(trans)->nelems--; + nf_tables_setelem_notify(&trans->ctx, + nft_trans_elem_set(trans), + &nft_trans_elem(trans), + NFT_MSG_DELSETELEM, 0); + set = nft_trans_elem_set(trans); + set->ops->get(set, &nft_trans_elem(trans)); + set->ops->remove(set, &nft_trans_elem(trans)); + nft_trans_destroy(trans); + break; + } + } + + list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_del(&trans->list); + trans->ctx.nla = NULL; + call_rcu(&trans->rcu_head, nf_tables_commit_release_rcu); + } + + return 0; +} + +/* Schedule objects for release via rcu to make sure no packets are accesing + * aborted rules. + */ +static void nf_tables_abort_release_rcu(struct rcu_head *rt) +{ + struct nft_trans *trans = container_of(rt, struct nft_trans, rcu_head); + + switch (trans->msg_type) { + case NFT_MSG_NEWTABLE: + nf_tables_table_destroy(&trans->ctx); + break; + case NFT_MSG_NEWCHAIN: + nf_tables_chain_destroy(trans->ctx.chain); + break; + case NFT_MSG_NEWRULE: + nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); + break; + case NFT_MSG_NEWSET: + nft_set_destroy(nft_trans_set(trans)); + break; + } + kfree(trans); +} + +static int nf_tables_abort(struct sk_buff *skb) +{ + struct net *net = sock_net(skb->sk); + struct nft_trans *trans, *next; + struct nft_set *set; + + list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + switch (trans->msg_type) { + case NFT_MSG_NEWTABLE: + if (nft_trans_table_update(trans)) { + if (nft_trans_table_enable(trans)) { + nf_tables_table_disable(trans->ctx.afi, + trans->ctx.table); + trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; + } + nft_trans_destroy(trans); + } else { + list_del(&trans->ctx.table->list); + } + break; + case NFT_MSG_DELTABLE: + list_add_tail(&trans->ctx.table->list, + &trans->ctx.afi->tables); + nft_trans_destroy(trans); + break; + case NFT_MSG_NEWCHAIN: + if (nft_trans_chain_update(trans)) { + if (nft_trans_chain_stats(trans)) + free_percpu(nft_trans_chain_stats(trans)); + + nft_trans_destroy(trans); + } else { + list_del(&trans->ctx.chain->list); + if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT) && + trans->ctx.chain->flags & NFT_BASE_CHAIN) { + nf_unregister_hooks(nft_base_chain(trans->ctx.chain)->ops, + trans->ctx.afi->nops); + } + } + break; + case NFT_MSG_DELCHAIN: + list_add_tail(&trans->ctx.chain->list, + &trans->ctx.table->chains); + nft_trans_destroy(trans); + break; + case NFT_MSG_NEWRULE: + list_del_rcu(&nft_trans_rule(trans)->list); + break; + case NFT_MSG_DELRULE: + nft_rule_clear(trans->ctx.net, nft_trans_rule(trans)); + nft_trans_destroy(trans); + break; + case NFT_MSG_NEWSET: + list_del(&nft_trans_set(trans)->list); + break; + case NFT_MSG_DELSET: + list_add_tail(&nft_trans_set(trans)->list, + &trans->ctx.table->sets); + nft_trans_destroy(trans); + break; + case NFT_MSG_NEWSETELEM: + set = nft_trans_elem_set(trans); + set->ops->get(set, &nft_trans_elem(trans)); + set->ops->remove(set, &nft_trans_elem(trans)); + nft_trans_destroy(trans); + break; + case NFT_MSG_DELSETELEM: + nft_trans_destroy(trans); + break; + } + } + + list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_del(&trans->list); + trans->ctx.nla = NULL; + call_rcu(&trans->rcu_head, nf_tables_abort_release_rcu); + } + + return 0; +} + static const struct nfnetlink_subsystem nf_tables_subsys = { .name = "nf_tables", .subsys_id = NFNL_SUBSYS_NFTABLES, diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 8041053..345acfb 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -66,20 +66,6 @@ struct nft_jumpstack { int rulenum; }; -static inline void -nft_chain_stats(const struct nft_chain *this, const struct nft_pktinfo *pkt, - struct nft_jumpstack *jumpstack, unsigned int stackptr) -{ - struct nft_stats __percpu *stats; - const struct nft_chain *chain = stackptr ? jumpstack[0].chain : this; - - rcu_read_lock_bh(); - stats = rcu_dereference(nft_base_chain(chain)->stats); - __this_cpu_inc(stats->pkts); - __this_cpu_add(stats->bytes, pkt->skb->len); - rcu_read_unlock_bh(); -} - enum nft_trace { NFT_TRACE_RULE, NFT_TRACE_RETURN, @@ -117,13 +103,14 @@ static void nft_trace_packet(const struct nft_pktinfo *pkt, unsigned int nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) { - const struct nft_chain *chain = ops->priv; + const struct nft_chain *chain = ops->priv, *basechain = chain; const struct nft_rule *rule; const struct nft_expr *expr, *last; struct nft_data data[NFT_REG_MAX + 1]; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; - int rulenum = 0; + struct nft_stats __percpu *stats; + int rulenum; /* * Cache cursor to avoid problems in case that the cursor is updated * while traversing the ruleset. @@ -131,6 +118,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor); do_chain: + rulenum = 0; rule = list_entry(&chain->rules, struct nft_rule, list); next_rule: data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; @@ -156,8 +144,10 @@ next_rule: switch (data[NFT_REG_VERDICT].verdict) { case NFT_BREAK: data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; - /* fall through */ + continue; case NFT_CONTINUE: + if (unlikely(pkt->skb->nf_trace)) + nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); continue; } break; @@ -183,37 +173,44 @@ next_rule: jumpstack[stackptr].rule = rule; jumpstack[stackptr].rulenum = rulenum; stackptr++; - /* fall through */ + chain = data[NFT_REG_VERDICT].chain; + goto do_chain; case NFT_GOTO: + if (unlikely(pkt->skb->nf_trace)) + nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); + chain = data[NFT_REG_VERDICT].chain; goto do_chain; case NFT_RETURN: if (unlikely(pkt->skb->nf_trace)) nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN); - - /* fall through */ + break; case NFT_CONTINUE: + if (unlikely(pkt->skb->nf_trace && !(chain->flags & NFT_BASE_CHAIN))) + nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN); break; default: WARN_ON(1); } if (stackptr > 0) { - if (unlikely(pkt->skb->nf_trace)) - nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN); - stackptr--; chain = jumpstack[stackptr].chain; rule = jumpstack[stackptr].rule; rulenum = jumpstack[stackptr].rulenum; goto next_rule; } - nft_chain_stats(chain, pkt, jumpstack, stackptr); if (unlikely(pkt->skb->nf_trace)) - nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_POLICY); + nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY); + + rcu_read_lock_bh(); + stats = rcu_dereference(nft_base_chain(basechain)->stats); + __this_cpu_inc(stats->pkts); + __this_cpu_add(stats->bytes, pkt->skb->len); + rcu_read_unlock_bh(); - return nft_base_chain(chain)->policy; + return nft_base_chain(basechain)->policy; } EXPORT_SYMBOL_GPL(nft_do_chain); diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index c7b6d46..70e86bb 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -32,18 +32,24 @@ static LIST_HEAD(nfnl_acct_list); struct nf_acct { atomic64_t pkts; atomic64_t bytes; + unsigned long flags; struct list_head head; atomic_t refcnt; char name[NFACCT_NAME_MAX]; struct rcu_head rcu_head; + char data[0]; }; +#define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES) + static int nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { struct nf_acct *nfacct, *matching = NULL; char *acct_name; + unsigned int size = 0; + u32 flags = 0; if (!tb[NFACCT_NAME]) return -EINVAL; @@ -68,15 +74,39 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, /* reset counters if you request a replacement. */ atomic64_set(&matching->pkts, 0); atomic64_set(&matching->bytes, 0); + smp_mb__before_clear_bit(); + /* reset overquota flag if quota is enabled. */ + if ((matching->flags & NFACCT_F_QUOTA)) + clear_bit(NFACCT_F_OVERQUOTA, &matching->flags); return 0; } return -EBUSY; } nfacct = kzalloc(sizeof(struct nf_acct), GFP_KERNEL); + if (tb[NFACCT_FLAGS]) { + flags = ntohl(nla_get_be32(tb[NFACCT_FLAGS])); + if (flags & ~NFACCT_F_QUOTA) + return -EOPNOTSUPP; + if ((flags & NFACCT_F_QUOTA) == NFACCT_F_QUOTA) + return -EINVAL; + if (flags & NFACCT_F_OVERQUOTA) + return -EINVAL; + + size += sizeof(u64); + } + + nfacct = kzalloc(sizeof(struct nf_acct) + size, GFP_KERNEL); if (nfacct == NULL) return -ENOMEM; + if (flags & NFACCT_F_QUOTA) { + u64 *quota = (u64 *)nfacct->data; + + *quota = be64_to_cpu(nla_get_be64(tb[NFACCT_QUOTA])); + nfacct->flags = flags; + } + strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX); if (tb[NFACCT_BYTES]) { @@ -117,6 +147,9 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, if (type == NFNL_MSG_ACCT_GET_CTRZERO) { pkts = atomic64_xchg(&acct->pkts, 0); bytes = atomic64_xchg(&acct->bytes, 0); + smp_mb__before_clear_bit(); + if (acct->flags & NFACCT_F_QUOTA) + clear_bit(NFACCT_F_OVERQUOTA, &acct->flags); } else { pkts = atomic64_read(&acct->pkts); bytes = atomic64_read(&acct->bytes); @@ -125,7 +158,13 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes)) || nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt)))) goto nla_put_failure; + if (acct->flags & NFACCT_F_QUOTA) { + u64 *quota = (u64 *)acct->data; + if (nla_put_be32(skb, NFACCT_FLAGS, htonl(acct->flags)) || + nla_put_be64(skb, NFACCT_QUOTA, cpu_to_be64(*quota))) + goto nla_put_failure; + } nlmsg_end(skb, nlh); return skb->len; @@ -270,6 +309,8 @@ static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = { [NFACCT_NAME] = { .type = NLA_NUL_STRING, .len = NFACCT_NAME_MAX-1 }, [NFACCT_BYTES] = { .type = NLA_U64 }, [NFACCT_PKTS] = { .type = NLA_U64 }, + [NFACCT_FLAGS] = { .type = NLA_U32 }, + [NFACCT_QUOTA] = { .type = NLA_U64 }, }; static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = { @@ -336,6 +377,50 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_update); +static void nfnl_overquota_report(struct nf_acct *nfacct) +{ + int ret; + struct sk_buff *skb; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (skb == NULL) + return; + + ret = nfnl_acct_fill_info(skb, 0, 0, NFNL_MSG_ACCT_OVERQUOTA, 0, + nfacct); + if (ret <= 0) { + kfree_skb(skb); + return; + } + netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, + GFP_ATOMIC); +} + +int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) +{ + u64 now; + u64 *quota; + int ret = NFACCT_UNDERQUOTA; + + /* no place here if we don't have a quota */ + if (!(nfacct->flags & NFACCT_F_QUOTA)) + return NFACCT_NO_QUOTA; + + quota = (u64 *)nfacct->data; + now = (nfacct->flags & NFACCT_F_QUOTA_PKTS) ? + atomic64_read(&nfacct->pkts) : atomic64_read(&nfacct->bytes); + + ret = now > *quota; + + if (now >= *quota && + !test_and_set_bit(NFACCT_F_OVERQUOTA, &nfacct->flags)) { + nfnl_overquota_report(nfacct); + } + + return ret; +} +EXPORT_SYMBOL_GPL(nfnl_acct_overquota); + static int __init nfnl_acct_init(void) { int ret; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index bd0d41e..cc56030 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -215,22 +215,14 @@ static void nft_ct_l3proto_module_put(uint8_t family) nf_ct_l3proto_module_put(family); } -static int nft_ct_init_validate_get(const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_ct_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_ct *priv = nft_expr_priv(expr); + int err; - if (tb[NFTA_CT_DIRECTION] != NULL) { - priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]); - switch (priv->dir) { - case IP_CT_DIR_ORIGINAL: - case IP_CT_DIR_REPLY: - break; - default: - return -EINVAL; - } - } - + priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); switch (priv->key) { case NFT_CT_STATE: case NFT_CT_DIRECTION: @@ -262,55 +254,55 @@ static int nft_ct_init_validate_get(const struct nft_expr *expr, return -EOPNOTSUPP; } - return 0; -} - -static int nft_ct_init_validate_set(uint32_t key) -{ - switch (key) { - case NFT_CT_MARK: - break; - default: - return -EOPNOTSUPP; + if (tb[NFTA_CT_DIRECTION] != NULL) { + priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]); + switch (priv->dir) { + case IP_CT_DIR_ORIGINAL: + case IP_CT_DIR_REPLY: + break; + default: + return -EINVAL; + } } + priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG])); + err = nft_validate_output_register(priv->dreg); + if (err < 0) + return err; + + err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + if (err < 0) + return err; + + err = nft_ct_l3proto_try_module_get(ctx->afi->family); + if (err < 0) + return err; + return 0; } -static int nft_ct_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_ct_set_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_ct *priv = nft_expr_priv(expr); int err; priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); - - if (tb[NFTA_CT_DREG]) { - err = nft_ct_init_validate_get(expr, tb); - if (err < 0) - return err; - - priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - - err = nft_validate_data_load(ctx, priv->dreg, NULL, - NFT_DATA_VALUE); - if (err < 0) - return err; - } else { - err = nft_ct_init_validate_set(priv->key); - if (err < 0) - return err; - - priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG])); - err = nft_validate_input_register(priv->sreg); - if (err < 0) - return err; + switch (priv->key) { +#ifdef CONFIG_NF_CONNTRACK_MARK + case NFT_CT_MARK: + break; +#endif + default: + return -EOPNOTSUPP; } + priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG])); + err = nft_validate_input_register(priv->sreg); + if (err < 0) + return err; + err = nft_ct_l3proto_try_module_get(ctx->afi->family); if (err < 0) return err; @@ -370,7 +362,7 @@ static const struct nft_expr_ops nft_ct_get_ops = { .type = &nft_ct_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), .eval = nft_ct_get_eval, - .init = nft_ct_init, + .init = nft_ct_get_init, .destroy = nft_ct_destroy, .dump = nft_ct_get_dump, }; @@ -379,7 +371,7 @@ static const struct nft_expr_ops nft_ct_set_ops = { .type = &nft_ct_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), .eval = nft_ct_set_eval, - .init = nft_ct_init, + .init = nft_ct_set_init, .destroy = nft_ct_destroy, .dump = nft_ct_set_dump, }; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 3b1ad87..1dfeb67 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/list.h> +#include <linux/log2.h> #include <linux/jhash.h> #include <linux/netlink.h> #include <linux/vmalloc.h> @@ -19,7 +20,7 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> -#define NFT_HASH_MIN_SIZE 4 +#define NFT_HASH_MIN_SIZE 4UL struct nft_hash { struct nft_hash_table __rcu *tbl; @@ -27,7 +28,6 @@ struct nft_hash { struct nft_hash_table { unsigned int size; - unsigned int elements; struct nft_hash_elem __rcu *buckets[]; }; @@ -82,6 +82,11 @@ static void nft_hash_tbl_free(const struct nft_hash_table *tbl) kfree(tbl); } +static unsigned int nft_hash_tbl_size(unsigned int nelem) +{ + return max(roundup_pow_of_two(nelem * 4 / 3), NFT_HASH_MIN_SIZE); +} + static struct nft_hash_table *nft_hash_tbl_alloc(unsigned int nbuckets) { struct nft_hash_table *tbl; @@ -161,7 +166,6 @@ static int nft_hash_tbl_expand(const struct nft_set *set, struct nft_hash *priv) break; } } - ntbl->elements = tbl->elements; /* Publish new table */ rcu_assign_pointer(priv->tbl, ntbl); @@ -201,7 +205,6 @@ static int nft_hash_tbl_shrink(const struct nft_set *set, struct nft_hash *priv) ; RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]); } - ntbl->elements = tbl->elements; /* Publish new table */ rcu_assign_pointer(priv->tbl, ntbl); @@ -237,10 +240,9 @@ static int nft_hash_insert(const struct nft_set *set, h = nft_hash_data(&he->key, tbl->size, set->klen); RCU_INIT_POINTER(he->next, tbl->buckets[h]); rcu_assign_pointer(tbl->buckets[h], he); - tbl->elements++; /* Expand table when exceeding 75% load */ - if (tbl->elements > tbl->size / 4 * 3) + if (set->nelems + 1 > tbl->size / 4 * 3) nft_hash_tbl_expand(set, priv); return 0; @@ -268,10 +270,9 @@ static void nft_hash_remove(const struct nft_set *set, RCU_INIT_POINTER(*pprev, he->next); synchronize_rcu(); kfree(he); - tbl->elements--; /* Shrink table beneath 30% load */ - if (tbl->elements < tbl->size * 3 / 10 && + if (set->nelems - 1 < tbl->size * 3 / 10 && tbl->size > NFT_HASH_MIN_SIZE) nft_hash_tbl_shrink(set, priv); } @@ -335,17 +336,23 @@ static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) } static int nft_hash_init(const struct nft_set *set, + const struct nft_set_desc *desc, const struct nlattr * const tb[]) { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_table *tbl; + unsigned int size; if (unlikely(!nft_hash_rnd_initted)) { get_random_bytes(&nft_hash_rnd, 4); nft_hash_rnd_initted = true; } - tbl = nft_hash_tbl_alloc(NFT_HASH_MIN_SIZE); + size = NFT_HASH_MIN_SIZE; + if (desc->size) + size = nft_hash_tbl_size(desc->size); + + tbl = nft_hash_tbl_alloc(size); if (tbl == NULL) return -ENOMEM; RCU_INIT_POINTER(priv->tbl, tbl); @@ -369,8 +376,37 @@ static void nft_hash_destroy(const struct nft_set *set) kfree(tbl); } +static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + unsigned int esize; + + esize = sizeof(struct nft_hash_elem); + if (features & NFT_SET_MAP) + esize += FIELD_SIZEOF(struct nft_hash_elem, data[0]); + + if (desc->size) { + est->size = sizeof(struct nft_hash) + + nft_hash_tbl_size(desc->size) * + sizeof(struct nft_hash_elem *) + + desc->size * esize; + } else { + /* Resizing happens when the load drops below 30% or goes + * above 75%. The average of 52.5% load (approximated by 50%) + * is used for the size estimation of the hash buckets, + * meaning we calculate two buckets per element. + */ + est->size = esize + 2 * sizeof(struct nft_hash_elem *); + } + + est->class = NFT_SET_CLASS_O_1; + + return true; +} + static struct nft_set_ops nft_hash_ops __read_mostly = { .privsize = nft_hash_privsize, + .estimate = nft_hash_estimate, .init = nft_hash_init, .destroy = nft_hash_destroy, .get = nft_hash_get, diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 7fd2bea..6404a72 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -56,8 +56,14 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return -EINVAL; set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET]); - if (IS_ERR(set)) - return PTR_ERR(set); + if (IS_ERR(set)) { + if (tb[NFTA_LOOKUP_SET_ID]) { + set = nf_tables_set_lookup_byid(ctx->net, + tb[NFTA_LOOKUP_SET_ID]); + } + if (IS_ERR(set)) + return PTR_ERR(set); + } priv->sreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_SREG])); err = nft_validate_input_register(priv->sreg); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 425cf39..852b178 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -18,18 +18,11 @@ #include <net/sock.h> #include <net/tcp_states.h> /* for TCP_TIME_WAIT */ #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_meta.h> -struct nft_meta { - enum nft_meta_keys key:8; - union { - enum nft_registers dreg:8; - enum nft_registers sreg:8; - }; -}; - -static void nft_meta_get_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) +void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; @@ -140,10 +133,11 @@ static void nft_meta_get_eval(const struct nft_expr *expr, err: data[NFT_REG_VERDICT].verdict = NFT_BREAK; } +EXPORT_SYMBOL_GPL(nft_meta_get_eval); -static void nft_meta_set_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) +void nft_meta_set_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) { const struct nft_meta *meta = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; @@ -163,28 +157,24 @@ static void nft_meta_set_eval(const struct nft_expr *expr, WARN_ON(1); } } +EXPORT_SYMBOL_GPL(nft_meta_set_eval); -static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = { +const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = { [NFTA_META_DREG] = { .type = NLA_U32 }, [NFTA_META_KEY] = { .type = NLA_U32 }, [NFTA_META_SREG] = { .type = NLA_U32 }, }; +EXPORT_SYMBOL_GPL(nft_meta_policy); -static int nft_meta_init_validate_set(uint32_t key) +int nft_meta_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { - switch (key) { - case NFT_META_MARK: - case NFT_META_PRIORITY: - case NFT_META_NFTRACE: - return 0; - default: - return -EOPNOTSUPP; - } -} + struct nft_meta *priv = nft_expr_priv(expr); + int err; -static int nft_meta_init_validate_get(uint32_t key) -{ - switch (key) { + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); + switch (priv->key) { case NFT_META_LEN: case NFT_META_PROTOCOL: case NFT_META_NFPROTO: @@ -205,39 +195,41 @@ static int nft_meta_init_validate_get(uint32_t key) #ifdef CONFIG_NETWORK_SECMARK case NFT_META_SECMARK: #endif - return 0; + break; default: return -EOPNOTSUPP; } + priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); + err = nft_validate_output_register(priv->dreg); + if (err < 0) + return err; + + err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + if (err < 0) + return err; + + return 0; } +EXPORT_SYMBOL_GPL(nft_meta_get_init); -static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nlattr * const tb[]) +int nft_meta_set_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); int err; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); - - if (tb[NFTA_META_DREG]) { - err = nft_meta_init_validate_get(priv->key); - if (err < 0) - return err; - - priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - - return nft_validate_data_load(ctx, priv->dreg, NULL, - NFT_DATA_VALUE); + switch (priv->key) { + case NFT_META_MARK: + case NFT_META_PRIORITY: + case NFT_META_NFTRACE: + break; + default: + return -EOPNOTSUPP; } - err = nft_meta_init_validate_set(priv->key); - if (err < 0) - return err; - priv->sreg = ntohl(nla_get_be32(tb[NFTA_META_SREG])); err = nft_validate_input_register(priv->sreg); if (err < 0) @@ -245,9 +237,10 @@ static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return 0; } +EXPORT_SYMBOL_GPL(nft_meta_set_init); -static int nft_meta_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) +int nft_meta_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -260,9 +253,10 @@ static int nft_meta_get_dump(struct sk_buff *skb, nla_put_failure: return -1; } +EXPORT_SYMBOL_GPL(nft_meta_get_dump); -static int nft_meta_set_dump(struct sk_buff *skb, - const struct nft_expr *expr) +int nft_meta_set_dump(struct sk_buff *skb, + const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -276,13 +270,14 @@ static int nft_meta_set_dump(struct sk_buff *skb, nla_put_failure: return -1; } +EXPORT_SYMBOL_GPL(nft_meta_set_dump); static struct nft_expr_type nft_meta_type; static const struct nft_expr_ops nft_meta_get_ops = { .type = &nft_meta_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_get_eval, - .init = nft_meta_init, + .init = nft_meta_get_init, .dump = nft_meta_get_dump, }; @@ -290,7 +285,7 @@ static const struct nft_expr_ops nft_meta_set_ops = { .type = &nft_meta_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_set_eval, - .init = nft_meta_init, + .init = nft_meta_set_init, .dump = nft_meta_set_dump, }; diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index e21d69d..072e611 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -201,6 +201,7 @@ static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[]) } static int nft_rbtree_init(const struct nft_set *set, + const struct nft_set_desc *desc, const struct nlattr * const nla[]) { struct nft_rbtree *priv = nft_set_priv(set); @@ -222,8 +223,28 @@ static void nft_rbtree_destroy(const struct nft_set *set) } } +static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + unsigned int nsize; + + nsize = sizeof(struct nft_rbtree_elem); + if (features & NFT_SET_MAP) + nsize += FIELD_SIZEOF(struct nft_rbtree_elem, data[0]); + + if (desc->size) + est->size = sizeof(struct nft_rbtree) + desc->size * nsize; + else + est->size = nsize; + + est->class = NFT_SET_CLASS_O_LOG_N; + + return true; +} + static struct nft_set_ops nft_rbtree_ops __read_mostly = { .privsize = nft_rbtree_privsize, + .estimate = nft_rbtree_estimate, .init = nft_rbtree_init, .destroy = nft_rbtree_destroy, .insert = nft_rbtree_insert, diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 12d4da8..bbffdbd 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -23,10 +23,11 @@ MODULE_ALIAS("ip6t_bpf"); static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; - struct sock_fprog program; + struct sock_fprog_kern program; program.len = info->bpf_program_num_elem; - program.filter = (struct sock_filter __user *) info->bpf_program; + program.filter = info->bpf_program; + if (sk_unattached_filter_create(&info->filter, &program)) { pr_info("bpf: check failed: parse error\n"); return -EINVAL; diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index b3be0ef..8c646ed 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -21,11 +21,14 @@ MODULE_ALIAS("ip6t_nfacct"); static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) { + int overquota; const struct xt_nfacct_match_info *info = par->targinfo; nfnl_acct_update(skb, info->nfacct); - return true; + overquota = nfnl_acct_overquota(skb, info->nfacct); + + return overquota == NFACCT_UNDERQUOTA ? false : true; } static int diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index a3ba3ca..76393f2 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -317,7 +317,7 @@ static void genl_unregister_mc_groups(struct genl_family *family) } } -static int genl_validate_ops(struct genl_family *family) +static int genl_validate_ops(const struct genl_family *family) { const struct genl_ops *ops = family->ops; unsigned int n_ops = family->n_ops; @@ -337,10 +337,6 @@ static int genl_validate_ops(struct genl_family *family) return -EINVAL; } - /* family is not registered yet, so no locking needed */ - family->ops = ops; - family->n_ops = n_ops; - return 0; } diff --git a/net/nfc/digital.h b/net/nfc/digital.h index 3759add..71ad7ee 100644 --- a/net/nfc/digital.h +++ b/net/nfc/digital.h @@ -71,6 +71,7 @@ static inline int digital_in_send_cmd(struct nfc_digital_dev *ddev, void digital_poll_next_tech(struct nfc_digital_dev *ddev); int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech); +int digital_in_send_sensb_req(struct nfc_digital_dev *ddev, u8 rf_tech); int digital_in_send_sensf_req(struct nfc_digital_dev *ddev, u8 rf_tech); int digital_in_send_iso15693_inv_req(struct nfc_digital_dev *ddev, u8 rf_tech); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index e01e15d..a6ce3c6 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -22,6 +22,8 @@ #define DIGITAL_PROTO_NFCA_RF_TECH \ (NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK | NFC_PROTO_NFC_DEP_MASK) +#define DIGITAL_PROTO_NFCB_RF_TECH NFC_PROTO_ISO14443_B_MASK + #define DIGITAL_PROTO_NFCF_RF_TECH \ (NFC_PROTO_FELICA_MASK | NFC_PROTO_NFC_DEP_MASK) @@ -345,6 +347,12 @@ int digital_target_found(struct nfc_digital_dev *ddev, add_crc = digital_skb_add_crc_a; break; + case NFC_PROTO_ISO14443_B: + framing = NFC_DIGITAL_FRAMING_NFCB_T4T; + check_crc = digital_skb_check_crc_b; + add_crc = digital_skb_add_crc_b; + break; + default: pr_err("Invalid protocol %d\n", protocol); return -EINVAL; @@ -378,6 +386,8 @@ int digital_target_found(struct nfc_digital_dev *ddev, void digital_poll_next_tech(struct nfc_digital_dev *ddev) { + u8 rand_mod; + digital_switch_rf(ddev, 0); mutex_lock(&ddev->poll_lock); @@ -387,8 +397,8 @@ void digital_poll_next_tech(struct nfc_digital_dev *ddev) return; } - ddev->poll_tech_index = (ddev->poll_tech_index + 1) % - ddev->poll_tech_count; + get_random_bytes(&rand_mod, sizeof(rand_mod)); + ddev->poll_tech_index = rand_mod % ddev->poll_tech_count; mutex_unlock(&ddev->poll_lock); @@ -475,6 +485,10 @@ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols, digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106A, digital_in_send_sens_req); + if (matching_im_protocols & DIGITAL_PROTO_NFCB_RF_TECH) + digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106B, + digital_in_send_sensb_req); + if (matching_im_protocols & DIGITAL_PROTO_NFCF_RF_TECH) { digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_212F, digital_in_send_sensf_req); @@ -635,7 +649,8 @@ static void digital_in_send_complete(struct nfc_digital_dev *ddev, void *arg, goto done; } - if (ddev->curr_protocol == NFC_PROTO_ISO14443) { + if ((ddev->curr_protocol == NFC_PROTO_ISO14443) || + (ddev->curr_protocol == NFC_PROTO_ISO14443_B)) { rc = digital_in_iso_dep_pull_sod(ddev, resp); if (rc) goto done; @@ -676,7 +691,8 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, goto exit; } - if (ddev->curr_protocol == NFC_PROTO_ISO14443) { + if ((ddev->curr_protocol == NFC_PROTO_ISO14443) || + (ddev->curr_protocol == NFC_PROTO_ISO14443_B)) { rc = digital_in_iso_dep_push_sod(ddev, skb); if (rc) goto exit; @@ -747,6 +763,8 @@ struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops, ddev->protocols |= NFC_PROTO_ISO15693_MASK; if (supported_protocols & NFC_PROTO_ISO14443_MASK) ddev->protocols |= NFC_PROTO_ISO14443_MASK; + if (supported_protocols & NFC_PROTO_ISO14443_B_MASK) + ddev->protocols |= NFC_PROTO_ISO14443_B_MASK; ddev->tx_headroom = tx_headroom + DIGITAL_MAX_HEADER_LEN; ddev->tx_tailroom = tx_tailroom + DIGITAL_CRC_LEN; diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index d4ed25f..171cb99 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -224,9 +224,8 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev, ddev->skb_add_crc(skb); - digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res, target); - - return 0; + return digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res, + target); } static int digital_in_send_rtox(struct nfc_digital_dev *ddev, diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c index 278c3fe..c2c1c01 100644 --- a/net/nfc/digital_technology.c +++ b/net/nfc/digital_technology.c @@ -41,6 +41,24 @@ #define DIGITAL_MIFARE_READ_RES_LEN 16 #define DIGITAL_MIFARE_ACK_RES 0x0A +#define DIGITAL_CMD_SENSB_REQ 0x05 +#define DIGITAL_SENSB_ADVANCED BIT(5) +#define DIGITAL_SENSB_EXTENDED BIT(4) +#define DIGITAL_SENSB_ALLB_REQ BIT(3) +#define DIGITAL_SENSB_N(n) ((n) & 0x7) + +#define DIGITAL_CMD_SENSB_RES 0x50 + +#define DIGITAL_CMD_ATTRIB_REQ 0x1D +#define DIGITAL_ATTRIB_P1_TR0_DEFAULT (0x0 << 6) +#define DIGITAL_ATTRIB_P1_TR1_DEFAULT (0x0 << 4) +#define DIGITAL_ATTRIB_P1_SUPRESS_EOS BIT(3) +#define DIGITAL_ATTRIB_P1_SUPRESS_SOS BIT(2) +#define DIGITAL_ATTRIB_P2_LISTEN_POLL_1 (0x0 << 6) +#define DIGITAL_ATTRIB_P2_POLL_LISTEN_1 (0x0 << 4) +#define DIGITAL_ATTRIB_P2_MAX_FRAME_256 0x8 +#define DIGITAL_ATTRIB_P4_DID(n) ((n) & 0xf) + #define DIGITAL_CMD_SENSF_REQ 0x00 #define DIGITAL_CMD_SENSF_RES 0x01 @@ -75,6 +93,7 @@ static const u8 digital_ats_fsc[] = { }; #define DIGITAL_ATS_FSCI(t0) ((t0) & 0x0F) +#define DIGITAL_SENSB_FSCI(pi2) (((pi2) & 0xF0) >> 4) #define DIGITAL_ATS_MAX_FSC 256 #define DIGITAL_RATS_BYTE1 0xE0 @@ -92,6 +111,32 @@ struct digital_sel_req { u8 bcc; } __packed; +struct digital_sensb_req { + u8 cmd; + u8 afi; + u8 param; +} __packed; + +struct digital_sensb_res { + u8 cmd; + u8 nfcid0[4]; + u8 app_data[4]; + u8 proto_info[3]; +} __packed; + +struct digital_attrib_req { + u8 cmd; + u8 nfcid0[4]; + u8 param1; + u8 param2; + u8 param3; + u8 param4; +} __packed; + +struct digital_attrib_res { + u8 mbli_did; +} __packed; + struct digital_sensf_req { u8 cmd; u8 sc1; @@ -531,6 +576,175 @@ int digital_in_recv_mifare_res(struct sk_buff *resp) return -EIO; } +static void digital_in_recv_attrib_res(struct nfc_digital_dev *ddev, void *arg, + struct sk_buff *resp) +{ + struct nfc_target *target = arg; + struct digital_attrib_res *attrib_res; + int rc; + + if (IS_ERR(resp)) { + rc = PTR_ERR(resp); + resp = NULL; + goto exit; + } + + if (resp->len < sizeof(*attrib_res)) { + PROTOCOL_ERR("12.6.2"); + rc = -EIO; + goto exit; + } + + attrib_res = (struct digital_attrib_res *)resp->data; + + if (attrib_res->mbli_did & 0x0f) { + PROTOCOL_ERR("12.6.2.1"); + rc = -EIO; + goto exit; + } + + rc = digital_target_found(ddev, target, NFC_PROTO_ISO14443_B); + +exit: + dev_kfree_skb(resp); + kfree(target); + + if (rc) + digital_poll_next_tech(ddev); +} + +static int digital_in_send_attrib_req(struct nfc_digital_dev *ddev, + struct nfc_target *target, + struct digital_sensb_res *sensb_res) +{ + struct digital_attrib_req *attrib_req; + struct sk_buff *skb; + int rc; + + skb = digital_skb_alloc(ddev, sizeof(*attrib_req)); + if (!skb) + return -ENOMEM; + + attrib_req = (struct digital_attrib_req *)skb_put(skb, + sizeof(*attrib_req)); + + attrib_req->cmd = DIGITAL_CMD_ATTRIB_REQ; + memcpy(attrib_req->nfcid0, sensb_res->nfcid0, + sizeof(attrib_req->nfcid0)); + attrib_req->param1 = DIGITAL_ATTRIB_P1_TR0_DEFAULT | + DIGITAL_ATTRIB_P1_TR1_DEFAULT; + attrib_req->param2 = DIGITAL_ATTRIB_P2_LISTEN_POLL_1 | + DIGITAL_ATTRIB_P2_POLL_LISTEN_1 | + DIGITAL_ATTRIB_P2_MAX_FRAME_256; + attrib_req->param3 = sensb_res->proto_info[1] & 0x07; + attrib_req->param4 = DIGITAL_ATTRIB_P4_DID(0); + + rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_attrib_res, + target); + if (rc) + kfree_skb(skb); + + return rc; +} + +static void digital_in_recv_sensb_res(struct nfc_digital_dev *ddev, void *arg, + struct sk_buff *resp) +{ + struct nfc_target *target = NULL; + struct digital_sensb_res *sensb_res; + u8 fsci; + int rc; + + if (IS_ERR(resp)) { + rc = PTR_ERR(resp); + resp = NULL; + goto exit; + } + + if (resp->len != sizeof(*sensb_res)) { + PROTOCOL_ERR("5.6.2.1"); + rc = -EIO; + goto exit; + } + + sensb_res = (struct digital_sensb_res *)resp->data; + + if (sensb_res->cmd != DIGITAL_CMD_SENSB_RES) { + PROTOCOL_ERR("5.6.2"); + rc = -EIO; + goto exit; + } + + if (!(sensb_res->proto_info[1] & BIT(0))) { + PROTOCOL_ERR("5.6.2.12"); + rc = -EIO; + goto exit; + } + + if (sensb_res->proto_info[1] & BIT(3)) { + PROTOCOL_ERR("5.6.2.16"); + rc = -EIO; + goto exit; + } + + fsci = DIGITAL_SENSB_FSCI(sensb_res->proto_info[1]); + if (fsci >= 8) + ddev->target_fsc = DIGITAL_ATS_MAX_FSC; + else + ddev->target_fsc = digital_ats_fsc[fsci]; + + target = kzalloc(sizeof(struct nfc_target), GFP_KERNEL); + if (!target) { + rc = -ENOMEM; + goto exit; + } + + rc = digital_in_send_attrib_req(ddev, target, sensb_res); + +exit: + dev_kfree_skb(resp); + + if (rc) { + kfree(target); + digital_poll_next_tech(ddev); + } +} + +int digital_in_send_sensb_req(struct nfc_digital_dev *ddev, u8 rf_tech) +{ + struct digital_sensb_req *sensb_req; + struct sk_buff *skb; + int rc; + + rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, + NFC_DIGITAL_RF_TECH_106B); + if (rc) + return rc; + + rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, + NFC_DIGITAL_FRAMING_NFCB); + if (rc) + return rc; + + skb = digital_skb_alloc(ddev, sizeof(*sensb_req)); + if (!skb) + return -ENOMEM; + + sensb_req = (struct digital_sensb_req *)skb_put(skb, + sizeof(*sensb_req)); + + sensb_req->cmd = DIGITAL_CMD_SENSB_REQ; + sensb_req->afi = 0x00; /* All families and sub-families */ + sensb_req->param = DIGITAL_SENSB_N(0); + + rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sensb_res, + NULL); + if (rc) + kfree_skb(skb); + + return rc; +} + static void digital_in_recv_sensf_res(struct nfc_digital_dev *ddev, void *arg, struct sk_buff *resp) { @@ -877,6 +1091,18 @@ exit: dev_kfree_skb(resp); } +static void digital_tg_recv_atr_or_sensf_req(struct nfc_digital_dev *ddev, + void *arg, struct sk_buff *resp) +{ + if (!IS_ERR(resp) && (resp->len >= 2) && + (resp->data[1] == DIGITAL_CMD_SENSF_REQ)) + digital_tg_recv_sensf_req(ddev, arg, resp); + else + digital_tg_recv_atr_req(ddev, arg, resp); + + return; +} + static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev, struct digital_sensf_req *sensf_req) { @@ -887,7 +1113,7 @@ static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev, size = sizeof(struct digital_sensf_res); - if (sensf_req->rc != DIGITAL_SENSF_REQ_RC_NONE) + if (sensf_req->rc == DIGITAL_SENSF_REQ_RC_NONE) size -= sizeof(sensf_res->rd); skb = digital_skb_alloc(ddev, size); @@ -922,7 +1148,7 @@ static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev, digital_skb_add_crc_f(skb); rc = digital_tg_send_cmd(ddev, skb, 300, - digital_tg_recv_atr_req, NULL); + digital_tg_recv_atr_or_sensf_req, NULL); if (rc) kfree_skb(skb); diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index a9f4d2e..677d24b 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -26,6 +26,8 @@ #include "hci.h" +#define MAX_FWI 4949 + static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, const u8 *param, size_t param_len, data_exchange_cb_t cb, void *cb_context) @@ -37,7 +39,7 @@ static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, * for all commands? */ return nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_COMMAND, cmd, - param, param_len, cb, cb_context, 3000); + param, param_len, cb, cb_context, MAX_FWI); } /* @@ -82,7 +84,7 @@ static int nfc_hci_execute_cmd(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, NFC_HCI_HCP_COMMAND, cmd, param, param_len, nfc_hci_execute_cb, &hcp_ew, - 3000); + MAX_FWI); if (hcp_ew.exec_result < 0) return hcp_ew.exec_result; diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index d45b638..4740370 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -225,7 +225,7 @@ int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) goto exit; } - targets->sens_res = be16_to_cpu(*(u16 *)atqa_skb->data); + targets->sens_res = be16_to_cpu(*(__be16 *)atqa_skb->data); targets->sel_res = sak_skb->data[0]; r = nfc_hci_get_param(hdev, NFC_HCI_RF_READER_A_GATE, @@ -380,34 +380,31 @@ static int hci_dev_session_init(struct nfc_hci_dev *hdev) if (r < 0) goto disconnect_all; - if (skb->len && skb->len == strlen(hdev->init_data.session_id)) - if (memcmp(hdev->init_data.session_id, skb->data, - skb->len) == 0) { - /* TODO ELa: restore gate<->pipe table from - * some TBD location. - * note: it doesn't seem possible to get the chip - * currently open gate/pipe table. - * It is only possible to obtain the supported - * gate list. - */ + if (skb->len && skb->len == strlen(hdev->init_data.session_id) && + (memcmp(hdev->init_data.session_id, skb->data, + skb->len) == 0) && hdev->ops->load_session) { + /* Restore gate<->pipe table from some proprietary location. */ - /* goto exit - * For now, always do a full initialization */ - } + r = hdev->ops->load_session(hdev); - r = nfc_hci_disconnect_all_gates(hdev); - if (r < 0) - goto exit; + if (r < 0) + goto disconnect_all; + } else { - r = hci_dev_connect_gates(hdev, hdev->init_data.gate_count, - hdev->init_data.gates); - if (r < 0) - goto disconnect_all; + r = nfc_hci_disconnect_all_gates(hdev); + if (r < 0) + goto exit; - r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE, - NFC_HCI_ADMIN_SESSION_IDENTITY, - hdev->init_data.session_id, - strlen(hdev->init_data.session_id)); + r = hci_dev_connect_gates(hdev, hdev->init_data.gate_count, + hdev->init_data.gates); + if (r < 0) + goto disconnect_all; + + r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE, + NFC_HCI_ADMIN_SESSION_IDENTITY, + hdev->init_data.session_id, + strlen(hdev->init_data.session_id)); + } if (r == 0) goto exit; diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index bec6ed1..a3ad69a 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -387,7 +387,7 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) __net_timestamp(skb); - nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_TX); + nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX); return nfc_data_exchange(dev, local->target_idx, skb, nfc_llcp_recv, local); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index b467195..f6278da 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -680,16 +680,17 @@ void nfc_llcp_send_to_raw_sock(struct nfc_llcp_local *local, continue; if (skb_copy == NULL) { - skb_copy = __pskb_copy(skb, NFC_LLCP_RAW_HEADER_SIZE, + skb_copy = __pskb_copy(skb, NFC_RAW_HEADER_SIZE, GFP_ATOMIC); if (skb_copy == NULL) continue; - data = skb_push(skb_copy, NFC_LLCP_RAW_HEADER_SIZE); + data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE); data[0] = local->dev ? local->dev->idx : 0xFF; - data[1] = direction; + data[1] = direction & 0x01; + data[1] |= (RAW_PAYLOAD_LLCP << 1); } nskb = skb_clone(skb_copy, GFP_ATOMIC); @@ -747,7 +748,7 @@ static void nfc_llcp_tx_work(struct work_struct *work) __net_timestamp(skb); nfc_llcp_send_to_raw_sock(local, skb, - NFC_LLCP_DIRECTION_TX); + NFC_DIRECTION_TX); ret = nfc_data_exchange(local->dev, local->target_idx, skb, nfc_llcp_recv, local); @@ -1476,7 +1477,7 @@ static void nfc_llcp_rx_work(struct work_struct *work) __net_timestamp(skb); - nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_RX); + nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_RX); nfc_llcp_rx_skb(local, skb); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6c34ac97..2b400e1 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -861,6 +861,10 @@ static int nci_send_frame(struct nci_dev *ndev, struct sk_buff *skb) /* Get rid of skb owner, prior to sending to the driver. */ skb_orphan(skb); + /* Send copy to sniffer */ + nfc_send_to_raw_sock(ndev->nfc_dev, skb, + RAW_PAYLOAD_NCI, NFC_DIRECTION_TX); + return ndev->ops->send(ndev, skb); } @@ -935,6 +939,11 @@ static void nci_rx_work(struct work_struct *work) struct sk_buff *skb; while ((skb = skb_dequeue(&ndev->rx_q))) { + + /* Send copy to sniffer */ + nfc_send_to_raw_sock(ndev->nfc_dev, skb, + RAW_PAYLOAD_NCI, NFC_DIRECTION_RX); + /* Process frame */ switch (nci_mt(skb->data)) { case NCI_MT_RSP_PKT: diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 1e90509..f8f6af2 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -366,7 +366,6 @@ static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev, struct nci_rf_intf_activated_ntf *ntf, __u8 *data) { struct activation_params_poll_nfc_dep *poll; - int i; switch (ntf->activation_rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: @@ -374,10 +373,8 @@ static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev, poll = &ntf->activation_params.poll_nfc_dep; poll->atr_res_len = min_t(__u8, *data++, 63); pr_debug("atr_res_len %d\n", poll->atr_res_len); - if (poll->atr_res_len > 0) { - for (i = 0; i < poll->atr_res_len; i++) - poll->atr_res[poll->atr_res_len-1-i] = data[i]; - } + if (poll->atr_res_len > 0) + memcpy(poll->atr_res, data, poll->atr_res_len); break; default: diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index 9d6e74f..88d6006 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -40,6 +40,12 @@ struct nfc_rawsock { struct work_struct tx_work; bool tx_work_scheduled; }; + +struct nfc_sock_list { + struct hlist_head head; + rwlock_t lock; +}; + #define nfc_rawsock(sk) ((struct nfc_rawsock *) sk) #define to_rawsock_sk(_tx_work) \ ((struct sock *) container_of(_tx_work, struct nfc_rawsock, tx_work)) diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index c27a6e8..55eefee 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -27,6 +27,24 @@ #include "nfc.h" +static struct nfc_sock_list raw_sk_list = { + .lock = __RW_LOCK_UNLOCKED(raw_sk_list.lock) +}; + +static void nfc_sock_link(struct nfc_sock_list *l, struct sock *sk) +{ + write_lock(&l->lock); + sk_add_node(sk, &l->head); + write_unlock(&l->lock); +} + +static void nfc_sock_unlink(struct nfc_sock_list *l, struct sock *sk) +{ + write_lock(&l->lock); + sk_del_node_init(sk); + write_unlock(&l->lock); +} + static void rawsock_write_queue_purge(struct sock *sk) { pr_debug("sk=%p\n", sk); @@ -57,6 +75,9 @@ static int rawsock_release(struct socket *sock) if (!sk) return 0; + if (sock->type == SOCK_RAW) + nfc_sock_unlink(&raw_sk_list, sk); + sock_orphan(sk); sock_put(sk); @@ -275,6 +296,26 @@ static const struct proto_ops rawsock_ops = { .mmap = sock_no_mmap, }; +static const struct proto_ops rawsock_raw_ops = { + .family = PF_NFC, + .owner = THIS_MODULE, + .release = rawsock_release, + .bind = sock_no_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = sock_no_setsockopt, + .getsockopt = sock_no_getsockopt, + .sendmsg = sock_no_sendmsg, + .recvmsg = rawsock_recvmsg, + .mmap = sock_no_mmap, +}; + static void rawsock_destruct(struct sock *sk) { pr_debug("sk=%p\n", sk); @@ -300,10 +341,13 @@ static int rawsock_create(struct net *net, struct socket *sock, pr_debug("sock=%p\n", sock); - if (sock->type != SOCK_SEQPACKET) + if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW)) return -ESOCKTNOSUPPORT; - sock->ops = &rawsock_ops; + if (sock->type == SOCK_RAW) + sock->ops = &rawsock_raw_ops; + else + sock->ops = &rawsock_ops; sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto); if (!sk) @@ -313,13 +357,53 @@ static int rawsock_create(struct net *net, struct socket *sock, sk->sk_protocol = nfc_proto->id; sk->sk_destruct = rawsock_destruct; sock->state = SS_UNCONNECTED; - - INIT_WORK(&nfc_rawsock(sk)->tx_work, rawsock_tx_work); - nfc_rawsock(sk)->tx_work_scheduled = false; + if (sock->type == SOCK_RAW) + nfc_sock_link(&raw_sk_list, sk); + else { + INIT_WORK(&nfc_rawsock(sk)->tx_work, rawsock_tx_work); + nfc_rawsock(sk)->tx_work_scheduled = false; + } return 0; } +void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, + u8 payload_type, u8 direction) +{ + struct sk_buff *skb_copy = NULL, *nskb; + struct sock *sk; + u8 *data; + + read_lock(&raw_sk_list.lock); + + sk_for_each(sk, &raw_sk_list.head) { + if (!skb_copy) { + skb_copy = __pskb_copy(skb, NFC_RAW_HEADER_SIZE, + GFP_ATOMIC); + if (!skb_copy) + continue; + + data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE); + + data[0] = dev ? dev->idx : 0xFF; + data[1] = direction & 0x01; + data[1] |= (payload_type << 1); + } + + nskb = skb_clone(skb_copy, GFP_ATOMIC); + if (!nskb) + continue; + + if (sock_queue_rcv_skb(sk, nskb)) + kfree_skb(nskb); + } + + read_unlock(&raw_sk_list.lock); + + kfree_skb(skb_copy); +} +EXPORT_SYMBOL(nfc_send_to_raw_sock); + static struct proto rawsock_proto = { .name = "NFC_RAW", .owner = THIS_MODULE, diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2c77e7b..c36856a 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -134,8 +134,8 @@ static int set_eth_addr(struct sk_buff *skb, skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2); - memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN); - memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src); + ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst); ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a3276e3..0d407bc 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -44,11 +44,11 @@ #include <linux/netfilter_ipv4.h> #include <linux/inetdevice.h> #include <linux/list.h> -#include <linux/lockdep.h> #include <linux/openvswitch.h> #include <linux/rculist.h> #include <linux/dmi.h> -#include <linux/workqueue.h> +#include <linux/genetlink.h> +#include <net/genetlink.h> #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -62,6 +62,31 @@ int ovs_net_id __read_mostly; +static struct genl_family dp_packet_genl_family; +static struct genl_family dp_flow_genl_family; +static struct genl_family dp_datapath_genl_family; + +static struct genl_multicast_group ovs_dp_flow_multicast_group = { + .name = OVS_FLOW_MCGROUP +}; + +static struct genl_multicast_group ovs_dp_datapath_multicast_group = { + .name = OVS_DATAPATH_MCGROUP +}; + +struct genl_multicast_group ovs_dp_vport_multicast_group = { + .name = OVS_VPORT_MCGROUP +}; + +/* Check if need to build a reply message. + * OVS userspace sets the NLM_F_ECHO flag if it needs the reply. */ +static bool ovs_must_notify(struct genl_info *info, + const struct genl_multicast_group *grp) +{ + return info->nlhdr->nlmsg_flags & NLM_F_ECHO || + netlink_has_listeners(genl_info_net(info)->genl_sock, 0); +} + static void ovs_notify(struct genl_family *family, struct sk_buff *skb, struct genl_info *info) { @@ -173,6 +198,7 @@ static struct hlist_head *vport_hash_bucket(const struct datapath *dp, return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)]; } +/* Called with ovs_mutex or RCU read lock. */ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) { struct vport *vport; @@ -262,16 +288,6 @@ out: u64_stats_update_end(&stats->syncp); } -static struct genl_family dp_packet_genl_family = { - .id = GENL_ID_GENERATE, - .hdrsize = sizeof(struct ovs_header), - .name = OVS_PACKET_FAMILY, - .version = OVS_PACKET_VERSION, - .maxattr = OVS_PACKET_ATTR_MAX, - .netnsok = true, - .parallel_ops = true, -}; - int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, const struct dp_upcall_info *upcall_info) { @@ -524,7 +540,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) packet->protocol = htons(ETH_P_802_2); /* Build an sw_flow for sending this packet. */ - flow = ovs_flow_alloc(false); + flow = ovs_flow_alloc(); err = PTR_ERR(flow); if (IS_ERR(flow)) goto err_kfree_skb; @@ -590,6 +606,18 @@ static const struct genl_ops dp_packet_genl_ops[] = { } }; +static struct genl_family dp_packet_genl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = sizeof(struct ovs_header), + .name = OVS_PACKET_FAMILY, + .version = OVS_PACKET_VERSION, + .maxattr = OVS_PACKET_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, + .ops = dp_packet_genl_ops, + .n_ops = ARRAY_SIZE(dp_packet_genl_ops), +}; + static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats, struct ovs_dp_megaflow_stats *mega_stats) { @@ -621,26 +649,6 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats, } } -static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { - [OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED }, - [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED }, - [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG }, -}; - -static struct genl_family dp_flow_genl_family = { - .id = GENL_ID_GENERATE, - .hdrsize = sizeof(struct ovs_header), - .name = OVS_FLOW_FAMILY, - .version = OVS_FLOW_VERSION, - .maxattr = OVS_FLOW_ATTR_MAX, - .netnsok = true, - .parallel_ops = true, -}; - -static struct genl_multicast_group ovs_dp_flow_multicast_group = { - .name = OVS_FLOW_MCGROUP -}; - static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts) { return NLMSG_ALIGN(sizeof(struct ovs_header)) @@ -652,8 +660,8 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts) + nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */ } -/* Called with ovs_mutex. */ -static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, +/* Called with ovs_mutex or RCU read lock. */ +static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { @@ -670,7 +678,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, if (!ovs_header) return -EMSGSIZE; - ovs_header->dp_ifindex = get_dpifindex(dp); + ovs_header->dp_ifindex = dp_ifindex; /* Fill flow key. */ nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY); @@ -693,6 +701,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, nla_nest_end(skb, nla); ovs_flow_stats_get(flow, &stats, &used, &tcp_flags); + if (used && nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used))) goto nla_put_failure; @@ -720,9 +729,9 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, const struct sw_flow_actions *sf_acts; sf_acts = rcu_dereference_ovsl(flow->sf_acts); - err = ovs_nla_put_actions(sf_acts->actions, sf_acts->actions_len, skb); + if (!err) nla_nest_end(skb, start); else { @@ -743,113 +752,128 @@ error: return err; } -static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow, - struct genl_info *info) +/* May not be called with RCU read lock. */ +static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts, + struct genl_info *info, + bool always) { - size_t len; + struct sk_buff *skb; + + if (!always && !ovs_must_notify(info, &ovs_dp_flow_multicast_group)) + return NULL; - len = ovs_flow_cmd_msg_size(ovsl_dereference(flow->sf_acts)); + skb = genlmsg_new_unicast(ovs_flow_cmd_msg_size(acts), info, GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOMEM); - return genlmsg_new_unicast(len, info, GFP_KERNEL); + return skb; } -static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow, - struct datapath *dp, - struct genl_info *info, - u8 cmd) +/* Called with ovs_mutex. */ +static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow, + int dp_ifindex, + struct genl_info *info, u8 cmd, + bool always) { struct sk_buff *skb; int retval; - skb = ovs_flow_cmd_alloc_info(flow, info); - if (!skb) - return ERR_PTR(-ENOMEM); + skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info, + always); + if (!skb || IS_ERR(skb)) + return skb; - retval = ovs_flow_cmd_fill_info(flow, dp, skb, info->snd_portid, - info->snd_seq, 0, cmd); + retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb, + info->snd_portid, info->snd_seq, 0, + cmd); BUG_ON(retval < 0); return skb; } -static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) +static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = info->userhdr; - struct sw_flow_key key, masked_key; - struct sw_flow *flow = NULL; + struct sw_flow *flow, *new_flow; struct sw_flow_mask mask; struct sk_buff *reply; struct datapath *dp; - struct sw_flow_actions *acts = NULL; + struct sw_flow_actions *acts; struct sw_flow_match match; - bool exact_5tuple; int error; - /* Extract key. */ + /* Must have key and actions. */ error = -EINVAL; if (!a[OVS_FLOW_ATTR_KEY]) goto error; + if (!a[OVS_FLOW_ATTR_ACTIONS]) + goto error; - ovs_match_init(&match, &key, &mask); - error = ovs_nla_get_match(&match, &exact_5tuple, + /* Most of the time we need to allocate a new flow, do it before + * locking. + */ + new_flow = ovs_flow_alloc(); + if (IS_ERR(new_flow)) { + error = PTR_ERR(new_flow); + goto error; + } + + /* Extract key. */ + ovs_match_init(&match, &new_flow->unmasked_key, &mask); + error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]); if (error) - goto error; + goto err_kfree_flow; + + ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask); /* Validate actions. */ - if (a[OVS_FLOW_ATTR_ACTIONS]) { - acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS])); - error = PTR_ERR(acts); - if (IS_ERR(acts)) - goto error; + acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS])); + error = PTR_ERR(acts); + if (IS_ERR(acts)) + goto err_kfree_flow; - ovs_flow_mask_key(&masked_key, &key, &mask); - error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], - &masked_key, 0, &acts); - if (error) { - OVS_NLERR("Flow actions may not be safe on all matching packets.\n"); - goto err_kfree; - } - } else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) { - error = -EINVAL; - goto error; + error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, + 0, &acts); + if (error) { + OVS_NLERR("Flow actions may not be safe on all matching packets.\n"); + goto err_kfree_acts; + } + + reply = ovs_flow_cmd_alloc_info(acts, info, false); + if (IS_ERR(reply)) { + error = PTR_ERR(reply); + goto err_kfree_acts; } ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); - error = -ENODEV; - if (!dp) + if (unlikely(!dp)) { + error = -ENODEV; goto err_unlock_ovs; - + } /* Check if this is a duplicate flow */ - flow = ovs_flow_tbl_lookup(&dp->table, &key); - if (!flow) { - /* Bail out if we're not allowed to create a new flow. */ - error = -ENOENT; - if (info->genlhdr->cmd == OVS_FLOW_CMD_SET) - goto err_unlock_ovs; - - /* Allocate flow. */ - flow = ovs_flow_alloc(!exact_5tuple); - if (IS_ERR(flow)) { - error = PTR_ERR(flow); - goto err_unlock_ovs; - } - - flow->key = masked_key; - flow->unmasked_key = key; - rcu_assign_pointer(flow->sf_acts, acts); + flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->unmasked_key); + if (likely(!flow)) { + rcu_assign_pointer(new_flow->sf_acts, acts); /* Put flow in bucket. */ - error = ovs_flow_tbl_insert(&dp->table, flow, &mask); - if (error) { + error = ovs_flow_tbl_insert(&dp->table, new_flow, &mask); + if (unlikely(error)) { acts = NULL; - goto err_flow_free; + goto err_unlock_ovs; } - reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); + if (unlikely(reply)) { + error = ovs_flow_cmd_fill_info(new_flow, + ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_NEW); + BUG_ON(error < 0); + } + ovs_unlock(); } else { - /* We found a matching flow. */ struct sw_flow_actions *old_acts; /* Bail out if we're not allowed to modify an existing flow. @@ -858,40 +882,154 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) * request. We also accept NLM_F_EXCL in case that bug ever * gets fixed. */ - error = -EEXIST; - if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW && - info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) + if (unlikely(info->nlhdr->nlmsg_flags & (NLM_F_CREATE + | NLM_F_EXCL))) { + error = -EEXIST; goto err_unlock_ovs; - + } /* The unmasked key has to be the same for flow updates. */ - if (!ovs_flow_cmp_unmasked_key(flow, &match)) + if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) { + error = -EEXIST; goto err_unlock_ovs; - + } /* Update actions. */ old_acts = ovsl_dereference(flow->sf_acts); rcu_assign_pointer(flow->sf_acts, acts); + + if (unlikely(reply)) { + error = ovs_flow_cmd_fill_info(flow, + ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_NEW); + BUG_ON(error < 0); + } + ovs_unlock(); + ovs_nla_free_flow_actions(old_acts); + ovs_flow_free(new_flow, false); + } + + if (reply) + ovs_notify(&dp_flow_genl_family, reply, info); + return 0; + +err_unlock_ovs: + ovs_unlock(); + kfree_skb(reply); +err_kfree_acts: + kfree(acts); +err_kfree_flow: + ovs_flow_free(new_flow, false); +error: + return error; +} + +static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr **a = info->attrs; + struct ovs_header *ovs_header = info->userhdr; + struct sw_flow_key key, masked_key; + struct sw_flow *flow; + struct sw_flow_mask mask; + struct sk_buff *reply = NULL; + struct datapath *dp; + struct sw_flow_actions *old_acts = NULL, *acts = NULL; + struct sw_flow_match match; + int error; + + /* Extract key. */ + error = -EINVAL; + if (!a[OVS_FLOW_ATTR_KEY]) + goto error; + + ovs_match_init(&match, &key, &mask); + error = ovs_nla_get_match(&match, + a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]); + if (error) + goto error; + + /* Validate actions. */ + if (a[OVS_FLOW_ATTR_ACTIONS]) { + acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS])); + error = PTR_ERR(acts); + if (IS_ERR(acts)) + goto error; + + ovs_flow_mask_key(&masked_key, &key, &mask); + error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], + &masked_key, 0, &acts); + if (error) { + OVS_NLERR("Flow actions may not be safe on all matching packets.\n"); + goto err_kfree_acts; + } + } + + /* Can allocate before locking if have acts. */ + if (acts) { + reply = ovs_flow_cmd_alloc_info(acts, info, false); + if (IS_ERR(reply)) { + error = PTR_ERR(reply); + goto err_kfree_acts; + } + } - reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); + ovs_lock(); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + if (unlikely(!dp)) { + error = -ENODEV; + goto err_unlock_ovs; + } + /* Check that the flow exists. */ + flow = ovs_flow_tbl_lookup(&dp->table, &key); + if (unlikely(!flow)) { + error = -ENOENT; + goto err_unlock_ovs; + } + /* The unmasked key has to be the same for flow updates. */ + if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) { + error = -EEXIST; + goto err_unlock_ovs; + } + /* Update actions, if present. */ + if (likely(acts)) { + old_acts = ovsl_dereference(flow->sf_acts); + rcu_assign_pointer(flow->sf_acts, acts); - /* Clear stats. */ - if (a[OVS_FLOW_ATTR_CLEAR]) - ovs_flow_stats_clear(flow); + if (unlikely(reply)) { + error = ovs_flow_cmd_fill_info(flow, + ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_NEW); + BUG_ON(error < 0); + } + } else { + /* Could not alloc without acts before locking. */ + reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, + info, OVS_FLOW_CMD_NEW, false); + if (unlikely(IS_ERR(reply))) { + error = PTR_ERR(reply); + goto err_unlock_ovs; + } } + + /* Clear stats. */ + if (a[OVS_FLOW_ATTR_CLEAR]) + ovs_flow_stats_clear(flow); ovs_unlock(); - if (!IS_ERR(reply)) + if (reply) ovs_notify(&dp_flow_genl_family, reply, info); - else - genl_set_err(&dp_flow_genl_family, sock_net(skb->sk), 0, - 0, PTR_ERR(reply)); + if (old_acts) + ovs_nla_free_flow_actions(old_acts); + return 0; -err_flow_free: - ovs_flow_free(flow, false); err_unlock_ovs: ovs_unlock(); -err_kfree: + kfree_skb(reply); +err_kfree_acts: kfree(acts); error: return error; @@ -914,7 +1052,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) } ovs_match_init(&match, &key, NULL); - err = ovs_nla_get_match(&match, NULL, a[OVS_FLOW_ATTR_KEY], NULL); + err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL); if (err) return err; @@ -931,7 +1069,8 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) goto unlock; } - reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); + reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info, + OVS_FLOW_CMD_NEW, true); if (IS_ERR(reply)) { err = PTR_ERR(reply); goto unlock; @@ -955,45 +1094,53 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) struct sw_flow_match match; int err; + if (likely(a[OVS_FLOW_ATTR_KEY])) { + ovs_match_init(&match, &key, NULL); + err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL); + if (unlikely(err)) + return err; + } + ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); - if (!dp) { + if (unlikely(!dp)) { err = -ENODEV; goto unlock; } - if (!a[OVS_FLOW_ATTR_KEY]) { + if (unlikely(!a[OVS_FLOW_ATTR_KEY])) { err = ovs_flow_tbl_flush(&dp->table); goto unlock; } - ovs_match_init(&match, &key, NULL); - err = ovs_nla_get_match(&match, NULL, a[OVS_FLOW_ATTR_KEY], NULL); - if (err) - goto unlock; - flow = ovs_flow_tbl_lookup(&dp->table, &key); - if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) { + if (unlikely(!flow || !ovs_flow_cmp_unmasked_key(flow, &match))) { err = -ENOENT; goto unlock; } - reply = ovs_flow_cmd_alloc_info(flow, info); - if (!reply) { - err = -ENOMEM; - goto unlock; - } - ovs_flow_tbl_remove(&dp->table, flow); + ovs_unlock(); - err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid, - info->snd_seq, 0, OVS_FLOW_CMD_DEL); - BUG_ON(err < 0); + reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts, + info, false); + if (likely(reply)) { + if (likely(!IS_ERR(reply))) { + rcu_read_lock(); /*To keep RCU checker happy. */ + err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_DEL); + rcu_read_unlock(); + BUG_ON(err < 0); + + ovs_notify(&dp_flow_genl_family, reply, info); + } else { + netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply)); + } + } ovs_flow_free(flow, true); - ovs_unlock(); - - ovs_notify(&dp_flow_genl_family, reply, info); return 0; unlock: ovs_unlock(); @@ -1024,7 +1171,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!flow) break; - if (ovs_flow_cmd_fill_info(flow, dp, skb, + if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_FLOW_CMD_NEW) < 0) @@ -1037,11 +1184,17 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static const struct genl_ops dp_flow_genl_ops[] = { +static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { + [OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED }, + [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED }, + [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG }, +}; + +static struct genl_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = flow_policy, - .doit = ovs_flow_cmd_new_or_set + .doit = ovs_flow_cmd_new }, { .cmd = OVS_FLOW_CMD_DEL, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ @@ -1057,28 +1210,22 @@ static const struct genl_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_SET, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = flow_policy, - .doit = ovs_flow_cmd_new_or_set, + .doit = ovs_flow_cmd_set, }, }; -static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { - [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, - [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 }, - [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, -}; - -static struct genl_family dp_datapath_genl_family = { +static struct genl_family dp_flow_genl_family = { .id = GENL_ID_GENERATE, .hdrsize = sizeof(struct ovs_header), - .name = OVS_DATAPATH_FAMILY, - .version = OVS_DATAPATH_VERSION, - .maxattr = OVS_DP_ATTR_MAX, + .name = OVS_FLOW_FAMILY, + .version = OVS_FLOW_VERSION, + .maxattr = OVS_FLOW_ATTR_MAX, .netnsok = true, .parallel_ops = true, -}; - -static struct genl_multicast_group ovs_dp_datapath_multicast_group = { - .name = OVS_DATAPATH_MCGROUP + .ops = dp_flow_genl_ops, + .n_ops = ARRAY_SIZE(dp_flow_genl_ops), + .mcgrps = &ovs_dp_flow_multicast_group, + .n_mcgrps = 1, }; static size_t ovs_dp_cmd_msg_size(void) @@ -1093,6 +1240,7 @@ static size_t ovs_dp_cmd_msg_size(void) return msgsize; } +/* Called with ovs_mutex or RCU read lock. */ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { @@ -1108,9 +1256,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, ovs_header->dp_ifindex = get_dpifindex(dp); - rcu_read_lock(); err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp)); - rcu_read_unlock(); if (err) goto nla_put_failure; @@ -1135,25 +1281,12 @@ error: return -EMSGSIZE; } -static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, - struct genl_info *info, u8 cmd) +static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info) { - struct sk_buff *skb; - int retval; - - skb = genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL); - if (!skb) - return ERR_PTR(-ENOMEM); - - retval = ovs_dp_cmd_fill_info(dp, skb, info->snd_portid, info->snd_seq, 0, cmd); - if (retval < 0) { - kfree_skb(skb); - return ERR_PTR(retval); - } - return skb; + return genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL); } -/* Called with ovs_mutex. */ +/* Called with rcu_read_lock or ovs_mutex. */ static struct datapath *lookup_datapath(struct net *net, struct ovs_header *ovs_header, struct nlattr *a[OVS_DP_ATTR_MAX + 1]) @@ -1165,10 +1298,8 @@ static struct datapath *lookup_datapath(struct net *net, else { struct vport *vport; - rcu_read_lock(); vport = ovs_vport_locate(net, nla_data(a[OVS_DP_ATTR_NAME])); dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL; - rcu_read_unlock(); } return dp ? dp : ERR_PTR(-ENODEV); } @@ -1205,12 +1336,14 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID]) goto err; - ovs_lock(); + reply = ovs_dp_cmd_alloc_info(info); + if (!reply) + return -ENOMEM; err = -ENOMEM; dp = kzalloc(sizeof(*dp), GFP_KERNEL); if (dp == NULL) - goto err_unlock_ovs; + goto err_free_reply; ovs_dp_set_net(dp, hold_net(sock_net(skb->sk))); @@ -1245,6 +1378,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_dp_change(dp, a); + /* So far only local changes have been made, now need the lock. */ + ovs_lock(); + vport = new_vport(&parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); @@ -1263,10 +1399,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_destroy_ports_array; } - reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto err_destroy_local_port; + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, + info->snd_seq, 0, OVS_DP_CMD_NEW); + BUG_ON(err < 0); ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id); list_add_tail_rcu(&dp->list_node, &ovs_net->dps); @@ -1276,9 +1411,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -err_destroy_local_port: - ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL)); err_destroy_ports_array: + ovs_unlock(); kfree(dp->ports); err_destroy_percpu: free_percpu(dp->stats_percpu); @@ -1287,8 +1421,8 @@ err_destroy_table: err_free_dp: release_net(ovs_dp_get_net(dp)); kfree(dp); -err_unlock_ovs: - ovs_unlock(); +err_free_reply: + kfree_skb(reply); err: return err; } @@ -1326,16 +1460,19 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; + reply = ovs_dp_cmd_alloc_info(info); + if (!reply) + return -ENOMEM; + ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) - goto unlock; + goto err_unlock_free; - reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_DEL); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto unlock; + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, + info->snd_seq, 0, OVS_DP_CMD_DEL); + BUG_ON(err < 0); __dp_destroy(dp); ovs_unlock(); @@ -1343,8 +1480,10 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -unlock: + +err_unlock_free: ovs_unlock(); + kfree_skb(reply); return err; } @@ -1354,29 +1493,30 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; + reply = ovs_dp_cmd_alloc_info(info); + if (!reply) + return -ENOMEM; + ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) - goto unlock; + goto err_unlock_free; ovs_dp_change(dp, info->attrs); - reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); - if (IS_ERR(reply)) { - err = PTR_ERR(reply); - genl_set_err(&dp_datapath_genl_family, sock_net(skb->sk), 0, - 0, err); - err = 0; - goto unlock; - } + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, + info->snd_seq, 0, OVS_DP_CMD_NEW); + BUG_ON(err < 0); ovs_unlock(); ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -unlock: + +err_unlock_free: ovs_unlock(); + kfree_skb(reply); return err; } @@ -1386,24 +1526,26 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; - ovs_lock(); + reply = ovs_dp_cmd_alloc_info(info); + if (!reply) + return -ENOMEM; + + rcu_read_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); if (IS_ERR(dp)) { err = PTR_ERR(dp); - goto unlock; - } - - reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); - if (IS_ERR(reply)) { - err = PTR_ERR(reply); - goto unlock; + goto err_unlock_free; } + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, + info->snd_seq, 0, OVS_DP_CMD_NEW); + BUG_ON(err < 0); + rcu_read_unlock(); - ovs_unlock(); return genlmsg_reply(reply, info); -unlock: - ovs_unlock(); +err_unlock_free: + rcu_read_unlock(); + kfree_skb(reply); return err; } @@ -1430,7 +1572,13 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static const struct genl_ops dp_datapath_genl_ops[] = { +static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { + [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, + [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 }, + [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, +}; + +static struct genl_ops dp_datapath_genl_ops[] = { { .cmd = OVS_DP_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = datapath_policy, @@ -1454,27 +1602,18 @@ static const struct genl_ops dp_datapath_genl_ops[] = { }, }; -static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { - [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, - [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) }, - [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 }, - [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, - [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 }, - [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, -}; - -struct genl_family dp_vport_genl_family = { +static struct genl_family dp_datapath_genl_family = { .id = GENL_ID_GENERATE, .hdrsize = sizeof(struct ovs_header), - .name = OVS_VPORT_FAMILY, - .version = OVS_VPORT_VERSION, - .maxattr = OVS_VPORT_ATTR_MAX, + .name = OVS_DATAPATH_FAMILY, + .version = OVS_DATAPATH_VERSION, + .maxattr = OVS_DP_ATTR_MAX, .netnsok = true, .parallel_ops = true, -}; - -static struct genl_multicast_group ovs_dp_vport_multicast_group = { - .name = OVS_VPORT_MCGROUP + .ops = dp_datapath_genl_ops, + .n_ops = ARRAY_SIZE(dp_datapath_genl_ops), + .mcgrps = &ovs_dp_datapath_multicast_group, + .n_mcgrps = 1, }; /* Called with ovs_mutex or RCU read lock. */ @@ -1516,7 +1655,12 @@ error: return err; } -/* Called with ovs_mutex or RCU read lock. */ +static struct sk_buff *ovs_vport_cmd_alloc_info(void) +{ + return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); +} + +/* Called with ovs_mutex, only via ovs_dp_notify_wq(). */ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, u32 seq, u8 cmd) { @@ -1578,33 +1722,35 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) u32 port_no; int err; - err = -EINVAL; if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] || !a[OVS_VPORT_ATTR_UPCALL_PID]) - goto exit; + return -EINVAL; + + port_no = a[OVS_VPORT_ATTR_PORT_NO] + ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0; + if (port_no >= DP_MAX_PORTS) + return -EFBIG; + + reply = ovs_vport_cmd_alloc_info(); + if (!reply) + return -ENOMEM; ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); err = -ENODEV; if (!dp) - goto exit_unlock; - - if (a[OVS_VPORT_ATTR_PORT_NO]) { - port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]); - - err = -EFBIG; - if (port_no >= DP_MAX_PORTS) - goto exit_unlock; + goto exit_unlock_free; + if (port_no) { vport = ovs_vport_ovsl(dp, port_no); err = -EBUSY; if (vport) - goto exit_unlock; + goto exit_unlock_free; } else { for (port_no = 1; ; port_no++) { if (port_no >= DP_MAX_PORTS) { err = -EFBIG; - goto exit_unlock; + goto exit_unlock_free; } vport = ovs_vport_ovsl(dp, port_no); if (!vport) @@ -1622,22 +1768,19 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) vport = new_vport(&parms); err = PTR_ERR(vport); if (IS_ERR(vport)) - goto exit_unlock; + goto exit_unlock_free; - err = 0; - reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, - OVS_VPORT_CMD_NEW); - if (IS_ERR(reply)) { - err = PTR_ERR(reply); - ovs_dp_detach_port(vport); - goto exit_unlock; - } + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_NEW); + BUG_ON(err < 0); + ovs_unlock(); ovs_notify(&dp_vport_genl_family, reply, info); + return 0; -exit_unlock: +exit_unlock_free: ovs_unlock(); -exit: + kfree_skb(reply); return err; } @@ -1648,28 +1791,26 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) struct vport *vport; int err; + reply = ovs_vport_cmd_alloc_info(); + if (!reply) + return -ENOMEM; + ovs_lock(); vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); err = PTR_ERR(vport); if (IS_ERR(vport)) - goto exit_unlock; + goto exit_unlock_free; if (a[OVS_VPORT_ATTR_TYPE] && nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) { err = -EINVAL; - goto exit_unlock; - } - - reply = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!reply) { - err = -ENOMEM; - goto exit_unlock; + goto exit_unlock_free; } if (a[OVS_VPORT_ATTR_OPTIONS]) { err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]); if (err) - goto exit_free; + goto exit_unlock_free; } if (a[OVS_VPORT_ATTR_UPCALL_PID]) @@ -1683,10 +1824,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_vport_genl_family, reply, info); return 0; -exit_free: - kfree_skb(reply); -exit_unlock: +exit_unlock_free: ovs_unlock(); + kfree_skb(reply); return err; } @@ -1697,30 +1837,33 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) struct vport *vport; int err; + reply = ovs_vport_cmd_alloc_info(); + if (!reply) + return -ENOMEM; + ovs_lock(); vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); err = PTR_ERR(vport); if (IS_ERR(vport)) - goto exit_unlock; + goto exit_unlock_free; if (vport->port_no == OVSP_LOCAL) { err = -EINVAL; - goto exit_unlock; + goto exit_unlock_free; } - reply = ovs_vport_cmd_build_info(vport, info->snd_portid, - info->snd_seq, OVS_VPORT_CMD_DEL); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto exit_unlock; - - err = 0; + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_DEL); + BUG_ON(err < 0); ovs_dp_detach_port(vport); + ovs_unlock(); ovs_notify(&dp_vport_genl_family, reply, info); + return 0; -exit_unlock: +exit_unlock_free: ovs_unlock(); + kfree_skb(reply); return err; } @@ -1732,24 +1875,25 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) struct vport *vport; int err; + reply = ovs_vport_cmd_alloc_info(); + if (!reply) + return -ENOMEM; + rcu_read_lock(); vport = lookup_vport(sock_net(skb->sk), ovs_header, a); err = PTR_ERR(vport); if (IS_ERR(vport)) - goto exit_unlock; - - reply = ovs_vport_cmd_build_info(vport, info->snd_portid, - info->snd_seq, OVS_VPORT_CMD_NEW); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto exit_unlock; - + goto exit_unlock_free; + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_NEW); + BUG_ON(err < 0); rcu_read_unlock(); return genlmsg_reply(reply, info); -exit_unlock: +exit_unlock_free: rcu_read_unlock(); + kfree_skb(reply); return err; } @@ -1792,7 +1936,16 @@ out: return skb->len; } -static const struct genl_ops dp_vport_genl_ops[] = { +static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { + [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, + [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) }, + [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, +}; + +static struct genl_ops dp_vport_genl_ops[] = { { .cmd = OVS_VPORT_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = vport_policy, @@ -1816,26 +1969,25 @@ static const struct genl_ops dp_vport_genl_ops[] = { }, }; -struct genl_family_and_ops { - struct genl_family *family; - const struct genl_ops *ops; - int n_ops; - const struct genl_multicast_group *group; +struct genl_family dp_vport_genl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = sizeof(struct ovs_header), + .name = OVS_VPORT_FAMILY, + .version = OVS_VPORT_VERSION, + .maxattr = OVS_VPORT_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, + .ops = dp_vport_genl_ops, + .n_ops = ARRAY_SIZE(dp_vport_genl_ops), + .mcgrps = &ovs_dp_vport_multicast_group, + .n_mcgrps = 1, }; -static const struct genl_family_and_ops dp_genl_families[] = { - { &dp_datapath_genl_family, - dp_datapath_genl_ops, ARRAY_SIZE(dp_datapath_genl_ops), - &ovs_dp_datapath_multicast_group }, - { &dp_vport_genl_family, - dp_vport_genl_ops, ARRAY_SIZE(dp_vport_genl_ops), - &ovs_dp_vport_multicast_group }, - { &dp_flow_genl_family, - dp_flow_genl_ops, ARRAY_SIZE(dp_flow_genl_ops), - &ovs_dp_flow_multicast_group }, - { &dp_packet_genl_family, - dp_packet_genl_ops, ARRAY_SIZE(dp_packet_genl_ops), - NULL }, +static struct genl_family * const dp_genl_families[] = { + &dp_datapath_genl_family, + &dp_vport_genl_family, + &dp_flow_genl_family, + &dp_packet_genl_family, }; static void dp_unregister_genl(int n_families) @@ -1843,33 +1995,25 @@ static void dp_unregister_genl(int n_families) int i; for (i = 0; i < n_families; i++) - genl_unregister_family(dp_genl_families[i].family); + genl_unregister_family(dp_genl_families[i]); } static int dp_register_genl(void) { - int n_registered; int err; int i; - n_registered = 0; for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) { - const struct genl_family_and_ops *f = &dp_genl_families[i]; - f->family->ops = f->ops; - f->family->n_ops = f->n_ops; - f->family->mcgrps = f->group; - f->family->n_mcgrps = f->group ? 1 : 0; - err = genl_register_family(f->family); + err = genl_register_family(dp_genl_families[i]); if (err) goto error; - n_registered++; } return 0; error: - dp_unregister_genl(n_registered); + dp_unregister_genl(i); return err; } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 0531738..7ede507 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -194,7 +194,9 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq, int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb); void ovs_dp_notify_wq(struct work_struct *work); -#define OVS_NLERR(fmt, ...) \ - pr_info_once("netlink: " fmt, ##__VA_ARGS__) - +#define OVS_NLERR(fmt, ...) \ +do { \ + if (net_ratelimit()) \ + pr_info("netlink: " fmt, ##__VA_ARGS__); \ +} while (0) #endif /* datapath.h */ diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 2998989..334751c 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -64,88 +64,110 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies) void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb) { struct flow_stats *stats; - __be16 tcp_flags = 0; - - if (!flow->stats.is_percpu) - stats = flow->stats.stat; - else - stats = this_cpu_ptr(flow->stats.cpu_stats); - - if ((flow->key.eth.type == htons(ETH_P_IP) || - flow->key.eth.type == htons(ETH_P_IPV6)) && - flow->key.ip.frag != OVS_FRAG_TYPE_LATER && - flow->key.ip.proto == IPPROTO_TCP && - likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) { - tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb)); + __be16 tcp_flags = flow->key.tp.flags; + int node = numa_node_id(); + + stats = rcu_dereference(flow->stats[node]); + + /* Check if already have node-specific stats. */ + if (likely(stats)) { + spin_lock(&stats->lock); + /* Mark if we write on the pre-allocated stats. */ + if (node == 0 && unlikely(flow->stats_last_writer != node)) + flow->stats_last_writer = node; + } else { + stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */ + spin_lock(&stats->lock); + + /* If the current NUMA-node is the only writer on the + * pre-allocated stats keep using them. + */ + if (unlikely(flow->stats_last_writer != node)) { + /* A previous locker may have already allocated the + * stats, so we need to check again. If node-specific + * stats were already allocated, we update the pre- + * allocated stats as we have already locked them. + */ + if (likely(flow->stats_last_writer != NUMA_NO_NODE) + && likely(!rcu_dereference(flow->stats[node]))) { + /* Try to allocate node-specific stats. */ + struct flow_stats *new_stats; + + new_stats = + kmem_cache_alloc_node(flow_stats_cache, + GFP_THISNODE | + __GFP_NOMEMALLOC, + node); + if (likely(new_stats)) { + new_stats->used = jiffies; + new_stats->packet_count = 1; + new_stats->byte_count = skb->len; + new_stats->tcp_flags = tcp_flags; + spin_lock_init(&new_stats->lock); + + rcu_assign_pointer(flow->stats[node], + new_stats); + goto unlock; + } + } + flow->stats_last_writer = node; + } } - spin_lock(&stats->lock); stats->used = jiffies; stats->packet_count++; stats->byte_count += skb->len; stats->tcp_flags |= tcp_flags; +unlock: spin_unlock(&stats->lock); } -static void stats_read(struct flow_stats *stats, - struct ovs_flow_stats *ovs_stats, - unsigned long *used, __be16 *tcp_flags) -{ - spin_lock(&stats->lock); - if (!*used || time_after(stats->used, *used)) - *used = stats->used; - *tcp_flags |= stats->tcp_flags; - ovs_stats->n_packets += stats->packet_count; - ovs_stats->n_bytes += stats->byte_count; - spin_unlock(&stats->lock); -} - -void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats, +/* Must be called with rcu_read_lock or ovs_mutex. */ +void ovs_flow_stats_get(const struct sw_flow *flow, + struct ovs_flow_stats *ovs_stats, unsigned long *used, __be16 *tcp_flags) { - int cpu; + int node; *used = 0; *tcp_flags = 0; memset(ovs_stats, 0, sizeof(*ovs_stats)); - local_bh_disable(); - if (!flow->stats.is_percpu) { - stats_read(flow->stats.stat, ovs_stats, used, tcp_flags); - } else { - for_each_possible_cpu(cpu) { - struct flow_stats *stats; + for_each_node(node) { + struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]); - stats = per_cpu_ptr(flow->stats.cpu_stats, cpu); - stats_read(stats, ovs_stats, used, tcp_flags); + if (stats) { + /* Local CPU may write on non-local stats, so we must + * block bottom-halves here. + */ + spin_lock_bh(&stats->lock); + if (!*used || time_after(stats->used, *used)) + *used = stats->used; + *tcp_flags |= stats->tcp_flags; + ovs_stats->n_packets += stats->packet_count; + ovs_stats->n_bytes += stats->byte_count; + spin_unlock_bh(&stats->lock); } } - local_bh_enable(); -} - -static void stats_reset(struct flow_stats *stats) -{ - spin_lock(&stats->lock); - stats->used = 0; - stats->packet_count = 0; - stats->byte_count = 0; - stats->tcp_flags = 0; - spin_unlock(&stats->lock); } +/* Called with ovs_mutex. */ void ovs_flow_stats_clear(struct sw_flow *flow) { - int cpu; - - local_bh_disable(); - if (!flow->stats.is_percpu) { - stats_reset(flow->stats.stat); - } else { - for_each_possible_cpu(cpu) { - stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu)); + int node; + + for_each_node(node) { + struct flow_stats *stats = ovsl_dereference(flow->stats[node]); + + if (stats) { + spin_lock_bh(&stats->lock); + stats->used = 0; + stats->packet_count = 0; + stats->byte_count = 0; + stats->tcp_flags = 0; + spin_unlock_bh(&stats->lock); } } - local_bh_enable(); } static int check_header(struct sk_buff *skb, int len) @@ -332,8 +354,8 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key, /* The ICMPv6 type and code fields use the 16-bit transport port * fields, so we need to store them in 16-bit network byte order. */ - key->ipv6.tp.src = htons(icmp->icmp6_type); - key->ipv6.tp.dst = htons(icmp->icmp6_code); + key->tp.src = htons(icmp->icmp6_type); + key->tp.dst = htons(icmp->icmp6_code); if (icmp->icmp6_code == 0 && (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION || @@ -372,14 +394,14 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key, && opt_len == 8) { if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll))) goto invalid; - memcpy(key->ipv6.nd.sll, - &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN); + ether_addr_copy(key->ipv6.nd.sll, + &nd->opt[offset+sizeof(*nd_opt)]); } else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR && opt_len == 8) { if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll))) goto invalid; - memcpy(key->ipv6.nd.tll, - &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN); + ether_addr_copy(key->ipv6.nd.tll, + &nd->opt[offset+sizeof(*nd_opt)]); } icmp_len -= opt_len; @@ -439,8 +461,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key) * header in the linear data area. */ eth = eth_hdr(skb); - memcpy(key->eth.src, eth->h_source, ETH_ALEN); - memcpy(key->eth.dst, eth->h_dest, ETH_ALEN); + ether_addr_copy(key->eth.src, eth->h_source); + ether_addr_copy(key->eth.dst, eth->h_dest); __skb_pull(skb, 2 * ETH_ALEN); /* We are going to push all headers that we pull, so no need to @@ -495,21 +517,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key) if (key->ip.proto == IPPROTO_TCP) { if (tcphdr_ok(skb)) { struct tcphdr *tcp = tcp_hdr(skb); - key->ipv4.tp.src = tcp->source; - key->ipv4.tp.dst = tcp->dest; - key->ipv4.tp.flags = TCP_FLAGS_BE16(tcp); + key->tp.src = tcp->source; + key->tp.dst = tcp->dest; + key->tp.flags = TCP_FLAGS_BE16(tcp); } } else if (key->ip.proto == IPPROTO_UDP) { if (udphdr_ok(skb)) { struct udphdr *udp = udp_hdr(skb); - key->ipv4.tp.src = udp->source; - key->ipv4.tp.dst = udp->dest; + key->tp.src = udp->source; + key->tp.dst = udp->dest; } } else if (key->ip.proto == IPPROTO_SCTP) { if (sctphdr_ok(skb)) { struct sctphdr *sctp = sctp_hdr(skb); - key->ipv4.tp.src = sctp->source; - key->ipv4.tp.dst = sctp->dest; + key->tp.src = sctp->source; + key->tp.dst = sctp->dest; } } else if (key->ip.proto == IPPROTO_ICMP) { if (icmphdr_ok(skb)) { @@ -517,8 +539,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key) /* The ICMP type and code fields use the 16-bit * transport port fields, so we need to store * them in 16-bit network byte order. */ - key->ipv4.tp.src = htons(icmp->type); - key->ipv4.tp.dst = htons(icmp->code); + key->tp.src = htons(icmp->type); + key->tp.dst = htons(icmp->code); } } @@ -538,8 +560,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key) key->ip.proto = ntohs(arp->ar_op); memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src)); memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst)); - memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN); - memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN); + ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha); + ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha); } } else if (key->eth.type == htons(ETH_P_IPV6)) { int nh_len; /* IPv6 Header + Extensions */ @@ -564,21 +586,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key) if (key->ip.proto == NEXTHDR_TCP) { if (tcphdr_ok(skb)) { struct tcphdr *tcp = tcp_hdr(skb); - key->ipv6.tp.src = tcp->source; - key->ipv6.tp.dst = tcp->dest; - key->ipv6.tp.flags = TCP_FLAGS_BE16(tcp); + key->tp.src = tcp->source; + key->tp.dst = tcp->dest; + key->tp.flags = TCP_FLAGS_BE16(tcp); } } else if (key->ip.proto == NEXTHDR_UDP) { if (udphdr_ok(skb)) { struct udphdr *udp = udp_hdr(skb); - key->ipv6.tp.src = udp->source; - key->ipv6.tp.dst = udp->dest; + key->tp.src = udp->source; + key->tp.dst = udp->dest; } } else if (key->ip.proto == NEXTHDR_SCTP) { if (sctphdr_ok(skb)) { struct sctphdr *sctp = sctp_hdr(skb); - key->ipv6.tp.src = sctp->source; - key->ipv6.tp.dst = sctp->dest; + key->tp.src = sctp->source; + key->tp.dst = sctp->dest; } } else if (key->ip.proto == NEXTHDR_ICMP) { if (icmp6hdr_ok(skb)) { diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 2d770e2..ac395d2 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -47,7 +47,7 @@ struct ovs_key_ipv4_tunnel { __be16 tun_flags; u8 ipv4_tos; u8 ipv4_ttl; -}; +} __packed __aligned(4); /* Minimize padding. */ static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key, const struct iphdr *iph, __be64 tun_id, @@ -71,7 +71,7 @@ struct sw_flow_key { u32 priority; /* Packet QoS priority. */ u32 skb_mark; /* SKB mark. */ u16 in_port; /* Input switch port (or DP_MAX_PORTS). */ - } phy; + } __packed phy; /* Safe when right after 'tun_key'. */ struct { u8 src[ETH_ALEN]; /* Ethernet source address. */ u8 dst[ETH_ALEN]; /* Ethernet destination address. */ @@ -84,23 +84,21 @@ struct sw_flow_key { u8 ttl; /* IP TTL/hop limit. */ u8 frag; /* One of OVS_FRAG_TYPE_*. */ } ip; + struct { + __be16 src; /* TCP/UDP/SCTP source port. */ + __be16 dst; /* TCP/UDP/SCTP destination port. */ + __be16 flags; /* TCP flags. */ + } tp; union { struct { struct { __be32 src; /* IP source address. */ __be32 dst; /* IP destination address. */ } addr; - union { - struct { - __be16 src; /* TCP/UDP/SCTP source port. */ - __be16 dst; /* TCP/UDP/SCTP destination port. */ - __be16 flags; /* TCP flags. */ - } tp; - struct { - u8 sha[ETH_ALEN]; /* ARP source hardware address. */ - u8 tha[ETH_ALEN]; /* ARP target hardware address. */ - } arp; - }; + struct { + u8 sha[ETH_ALEN]; /* ARP source hardware address. */ + u8 tha[ETH_ALEN]; /* ARP target hardware address. */ + } arp; } ipv4; struct { struct { @@ -109,11 +107,6 @@ struct sw_flow_key { } addr; __be32 label; /* IPv6 flow label. */ struct { - __be16 src; /* TCP/UDP/SCTP source port. */ - __be16 dst; /* TCP/UDP/SCTP destination port. */ - __be16 flags; /* TCP flags. */ - } tp; - struct { struct in6_addr target; /* ND target address. */ u8 sll[ETH_ALEN]; /* ND source link layer address. */ u8 tll[ETH_ALEN]; /* ND target link layer address. */ @@ -155,24 +148,22 @@ struct flow_stats { __be16 tcp_flags; /* Union of seen TCP flags. */ }; -struct sw_flow_stats { - bool is_percpu; - union { - struct flow_stats *stat; - struct flow_stats __percpu *cpu_stats; - }; -}; - struct sw_flow { struct rcu_head rcu; struct hlist_node hash_node[2]; u32 hash; - + int stats_last_writer; /* NUMA-node id of the last writer on + * 'stats[0]'. + */ struct sw_flow_key key; struct sw_flow_key unmasked_key; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; - struct sw_flow_stats stats; + struct flow_stats __rcu *stats[]; /* One for each NUMA node. First one + * is allocated at flow creation time, + * the rest are allocated on demand + * while holding the 'stats[0].lock'. + */ }; struct arp_eth_header { @@ -189,10 +180,10 @@ struct arp_eth_header { unsigned char ar_tip[4]; /* target IP address */ } __packed; -void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb); -void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *stats, +void ovs_flow_stats_update(struct sw_flow *, struct sk_buff *); +void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *, unsigned long *used, __be16 *tcp_flags); -void ovs_flow_stats_clear(struct sw_flow *flow); +void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 4d000ac..d757848 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -16,6 +16,8 @@ * 02110-1301, USA */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include "flow.h" #include "datapath.h" #include <linux/uaccess.h> @@ -202,11 +204,11 @@ static bool match_validate(const struct sw_flow_match *match, if (match->mask && (match->mask->key.ip.proto == 0xff)) mask_allowed |= 1 << OVS_KEY_ATTR_ICMPV6; - if (match->key->ipv6.tp.src == + if (match->key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) || - match->key->ipv6.tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { + match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { key_expected |= 1 << OVS_KEY_ATTR_ND; - if (match->mask && (match->mask->key.ipv6.tp.src == htons(0xffff))) + if (match->mask && (match->mask->key.tp.src == htons(0xffff))) mask_allowed |= 1 << OVS_KEY_ATTR_ND; } } @@ -216,14 +218,14 @@ static bool match_validate(const struct sw_flow_match *match, if ((key_attrs & key_expected) != key_expected) { /* Key attributes check failed. */ OVS_NLERR("Missing expected key attributes (key_attrs=%llx, expected=%llx).\n", - key_attrs, key_expected); + (unsigned long long)key_attrs, (unsigned long long)key_expected); return false; } if ((mask_attrs & mask_allowed) != mask_attrs) { /* Mask attributes check failed. */ OVS_NLERR("Contain more than allowed mask fields (mask_attrs=%llx, mask_allowed=%llx).\n", - mask_attrs, mask_allowed); + (unsigned long long)mask_attrs, (unsigned long long)mask_allowed); return false; } @@ -266,20 +268,6 @@ static bool is_all_zero(const u8 *fp, size_t size) return true; } -static bool is_all_set(const u8 *fp, size_t size) -{ - int i; - - if (!fp) - return false; - - for (i = 0; i < size; i++) - if (fp[i] != 0xff) - return false; - - return true; -} - static int __parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[], u64 *attrsp, bool nz) @@ -501,9 +489,8 @@ static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs, return 0; } -static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple, - u64 attrs, const struct nlattr **a, - bool is_mask) +static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, + const struct nlattr **a, bool is_mask) { int err; u64 orig_attrs = attrs; @@ -560,11 +547,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask); } - if (is_mask && exact_5tuple) { - if (match->mask->key.eth.type != htons(0xffff)) - *exact_5tuple = false; - } - if (attrs & (1 << OVS_KEY_ATTR_IPV4)) { const struct ovs_key_ipv4 *ipv4_key; @@ -587,13 +569,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple SW_FLOW_KEY_PUT(match, ipv4.addr.dst, ipv4_key->ipv4_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_IPV4); - - if (is_mask && exact_5tuple && *exact_5tuple) { - if (ipv4_key->ipv4_proto != 0xff || - ipv4_key->ipv4_src != htonl(0xffffffff) || - ipv4_key->ipv4_dst != htonl(0xffffffff)) - *exact_5tuple = false; - } } if (attrs & (1 << OVS_KEY_ATTR_IPV6)) { @@ -625,13 +600,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple is_mask); attrs &= ~(1 << OVS_KEY_ATTR_IPV6); - - if (is_mask && exact_5tuple && *exact_5tuple) { - if (ipv6_key->ipv6_proto != 0xff || - !is_all_set((u8 *)ipv6_key->ipv6_src, sizeof(match->key->ipv6.addr.src)) || - !is_all_set((u8 *)ipv6_key->ipv6_dst, sizeof(match->key->ipv6.addr.dst))) - *exact_5tuple = false; - } } if (attrs & (1 << OVS_KEY_ATTR_ARP)) { @@ -662,32 +630,18 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple const struct ovs_key_tcp *tcp_key; tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]); - if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) { - SW_FLOW_KEY_PUT(match, ipv4.tp.src, - tcp_key->tcp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv4.tp.dst, - tcp_key->tcp_dst, is_mask); - } else { - SW_FLOW_KEY_PUT(match, ipv6.tp.src, - tcp_key->tcp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv6.tp.dst, - tcp_key->tcp_dst, is_mask); - } + SW_FLOW_KEY_PUT(match, tp.src, tcp_key->tcp_src, is_mask); + SW_FLOW_KEY_PUT(match, tp.dst, tcp_key->tcp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_TCP); - - if (is_mask && exact_5tuple && *exact_5tuple && - (tcp_key->tcp_src != htons(0xffff) || - tcp_key->tcp_dst != htons(0xffff))) - *exact_5tuple = false; } if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) { if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) { - SW_FLOW_KEY_PUT(match, ipv4.tp.flags, + SW_FLOW_KEY_PUT(match, tp.flags, nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]), is_mask); } else { - SW_FLOW_KEY_PUT(match, ipv6.tp.flags, + SW_FLOW_KEY_PUT(match, tp.flags, nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]), is_mask); } @@ -698,40 +652,17 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple const struct ovs_key_udp *udp_key; udp_key = nla_data(a[OVS_KEY_ATTR_UDP]); - if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) { - SW_FLOW_KEY_PUT(match, ipv4.tp.src, - udp_key->udp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv4.tp.dst, - udp_key->udp_dst, is_mask); - } else { - SW_FLOW_KEY_PUT(match, ipv6.tp.src, - udp_key->udp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv6.tp.dst, - udp_key->udp_dst, is_mask); - } + SW_FLOW_KEY_PUT(match, tp.src, udp_key->udp_src, is_mask); + SW_FLOW_KEY_PUT(match, tp.dst, udp_key->udp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_UDP); - - if (is_mask && exact_5tuple && *exact_5tuple && - (udp_key->udp_src != htons(0xffff) || - udp_key->udp_dst != htons(0xffff))) - *exact_5tuple = false; } if (attrs & (1 << OVS_KEY_ATTR_SCTP)) { const struct ovs_key_sctp *sctp_key; sctp_key = nla_data(a[OVS_KEY_ATTR_SCTP]); - if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) { - SW_FLOW_KEY_PUT(match, ipv4.tp.src, - sctp_key->sctp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv4.tp.dst, - sctp_key->sctp_dst, is_mask); - } else { - SW_FLOW_KEY_PUT(match, ipv6.tp.src, - sctp_key->sctp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv6.tp.dst, - sctp_key->sctp_dst, is_mask); - } + SW_FLOW_KEY_PUT(match, tp.src, sctp_key->sctp_src, is_mask); + SW_FLOW_KEY_PUT(match, tp.dst, sctp_key->sctp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_SCTP); } @@ -739,9 +670,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple const struct ovs_key_icmp *icmp_key; icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]); - SW_FLOW_KEY_PUT(match, ipv4.tp.src, + SW_FLOW_KEY_PUT(match, tp.src, htons(icmp_key->icmp_type), is_mask); - SW_FLOW_KEY_PUT(match, ipv4.tp.dst, + SW_FLOW_KEY_PUT(match, tp.dst, htons(icmp_key->icmp_code), is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ICMP); } @@ -750,9 +681,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple const struct ovs_key_icmpv6 *icmpv6_key; icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]); - SW_FLOW_KEY_PUT(match, ipv6.tp.src, + SW_FLOW_KEY_PUT(match, tp.src, htons(icmpv6_key->icmpv6_type), is_mask); - SW_FLOW_KEY_PUT(match, ipv6.tp.dst, + SW_FLOW_KEY_PUT(match, tp.dst, htons(icmpv6_key->icmpv6_code), is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6); } @@ -800,7 +731,6 @@ static void sw_flow_mask_set(struct sw_flow_mask *mask, * attribute specifies the mask field of the wildcarded flow. */ int ovs_nla_get_match(struct sw_flow_match *match, - bool *exact_5tuple, const struct nlattr *key, const struct nlattr *mask) { @@ -848,13 +778,10 @@ int ovs_nla_get_match(struct sw_flow_match *match, } } - err = ovs_key_from_nlattrs(match, NULL, key_attrs, a, false); + err = ovs_key_from_nlattrs(match, key_attrs, a, false); if (err) return err; - if (exact_5tuple) - *exact_5tuple = true; - if (mask) { err = parse_flow_mask_nlattrs(mask, a, &mask_attrs); if (err) @@ -892,7 +819,7 @@ int ovs_nla_get_match(struct sw_flow_match *match, } } - err = ovs_key_from_nlattrs(match, exact_5tuple, mask_attrs, a, true); + err = ovs_key_from_nlattrs(match, mask_attrs, a, true); if (err) return err; } else { @@ -982,8 +909,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, goto nla_put_failure; eth_key = nla_data(nla); - memcpy(eth_key->eth_src, output->eth.src, ETH_ALEN); - memcpy(eth_key->eth_dst, output->eth.dst, ETH_ALEN); + ether_addr_copy(eth_key->eth_src, output->eth.src); + ether_addr_copy(eth_key->eth_dst, output->eth.dst); if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) { __be16 eth_type; @@ -1055,8 +982,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, arp_key->arp_sip = output->ipv4.addr.src; arp_key->arp_tip = output->ipv4.addr.dst; arp_key->arp_op = htons(output->ip.proto); - memcpy(arp_key->arp_sha, output->ipv4.arp.sha, ETH_ALEN); - memcpy(arp_key->arp_tha, output->ipv4.arp.tha, ETH_ALEN); + ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha); + ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha); } if ((swkey->eth.type == htons(ETH_P_IP) || @@ -1070,19 +997,11 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; tcp_key = nla_data(nla); - if (swkey->eth.type == htons(ETH_P_IP)) { - tcp_key->tcp_src = output->ipv4.tp.src; - tcp_key->tcp_dst = output->ipv4.tp.dst; - if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS, - output->ipv4.tp.flags)) - goto nla_put_failure; - } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - tcp_key->tcp_src = output->ipv6.tp.src; - tcp_key->tcp_dst = output->ipv6.tp.dst; - if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS, - output->ipv6.tp.flags)) - goto nla_put_failure; - } + tcp_key->tcp_src = output->tp.src; + tcp_key->tcp_dst = output->tp.dst; + if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS, + output->tp.flags)) + goto nla_put_failure; } else if (swkey->ip.proto == IPPROTO_UDP) { struct ovs_key_udp *udp_key; @@ -1090,13 +1009,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; udp_key = nla_data(nla); - if (swkey->eth.type == htons(ETH_P_IP)) { - udp_key->udp_src = output->ipv4.tp.src; - udp_key->udp_dst = output->ipv4.tp.dst; - } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - udp_key->udp_src = output->ipv6.tp.src; - udp_key->udp_dst = output->ipv6.tp.dst; - } + udp_key->udp_src = output->tp.src; + udp_key->udp_dst = output->tp.dst; } else if (swkey->ip.proto == IPPROTO_SCTP) { struct ovs_key_sctp *sctp_key; @@ -1104,13 +1018,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; sctp_key = nla_data(nla); - if (swkey->eth.type == htons(ETH_P_IP)) { - sctp_key->sctp_src = swkey->ipv4.tp.src; - sctp_key->sctp_dst = swkey->ipv4.tp.dst; - } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - sctp_key->sctp_src = swkey->ipv6.tp.src; - sctp_key->sctp_dst = swkey->ipv6.tp.dst; - } + sctp_key->sctp_src = output->tp.src; + sctp_key->sctp_dst = output->tp.dst; } else if (swkey->eth.type == htons(ETH_P_IP) && swkey->ip.proto == IPPROTO_ICMP) { struct ovs_key_icmp *icmp_key; @@ -1119,8 +1028,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; icmp_key = nla_data(nla); - icmp_key->icmp_type = ntohs(output->ipv4.tp.src); - icmp_key->icmp_code = ntohs(output->ipv4.tp.dst); + icmp_key->icmp_type = ntohs(output->tp.src); + icmp_key->icmp_code = ntohs(output->tp.dst); } else if (swkey->eth.type == htons(ETH_P_IPV6) && swkey->ip.proto == IPPROTO_ICMPV6) { struct ovs_key_icmpv6 *icmpv6_key; @@ -1130,8 +1039,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; icmpv6_key = nla_data(nla); - icmpv6_key->icmpv6_type = ntohs(output->ipv6.tp.src); - icmpv6_key->icmpv6_code = ntohs(output->ipv6.tp.dst); + icmpv6_key->icmpv6_type = ntohs(output->tp.src); + icmpv6_key->icmpv6_code = ntohs(output->tp.dst); if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION || icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) { @@ -1143,8 +1052,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, nd_key = nla_data(nla); memcpy(nd_key->nd_target, &output->ipv6.nd.target, sizeof(nd_key->nd_target)); - memcpy(nd_key->nd_sll, output->ipv6.nd.sll, ETH_ALEN); - memcpy(nd_key->nd_tll, output->ipv6.nd.tll, ETH_ALEN); + ether_addr_copy(nd_key->nd_sll, output->ipv6.nd.sll); + ether_addr_copy(nd_key->nd_tll, output->ipv6.nd.tll); } } } @@ -1309,13 +1218,10 @@ static int validate_and_copy_sample(const struct nlattr *attr, static int validate_tp_port(const struct sw_flow_key *flow_key) { - if (flow_key->eth.type == htons(ETH_P_IP)) { - if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst) - return 0; - } else if (flow_key->eth.type == htons(ETH_P_IPV6)) { - if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst) - return 0; - } + if ((flow_key->eth.type == htons(ETH_P_IP) || + flow_key->eth.type == htons(ETH_P_IPV6)) && + (flow_key->tp.src || flow_key->tp.dst)) + return 0; return -EINVAL; } diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index b31fbe2..4401510 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -45,7 +45,6 @@ int ovs_nla_put_flow(const struct sw_flow_key *, int ovs_nla_get_flow_metadata(struct sw_flow *flow, const struct nlattr *attr); int ovs_nla_get_match(struct sw_flow_match *match, - bool *exact_5tuple, const struct nlattr *, const struct nlattr *); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 3c268b3..574c3ab 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -48,6 +48,7 @@ #define REHASH_INTERVAL (10 * 60 * HZ) static struct kmem_cache *flow_cache; +struct kmem_cache *flow_stats_cache __read_mostly; static u16 range_n_bytes(const struct sw_flow_key_range *range) { @@ -57,8 +58,10 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range) void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, const struct sw_flow_mask *mask) { - const long *m = (long *)((u8 *)&mask->key + mask->range.start); - const long *s = (long *)((u8 *)src + mask->range.start); + const long *m = (const long *)((const u8 *)&mask->key + + mask->range.start); + const long *s = (const long *)((const u8 *)src + + mask->range.start); long *d = (long *)((u8 *)dst + mask->range.start); int i; @@ -70,10 +73,11 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, *d++ = *s++ & *m++; } -struct sw_flow *ovs_flow_alloc(bool percpu_stats) +struct sw_flow *ovs_flow_alloc(void) { struct sw_flow *flow; - int cpu; + struct flow_stats *stats; + int node; flow = kmem_cache_alloc(flow_cache, GFP_KERNEL); if (!flow) @@ -81,27 +85,22 @@ struct sw_flow *ovs_flow_alloc(bool percpu_stats) flow->sf_acts = NULL; flow->mask = NULL; + flow->stats_last_writer = NUMA_NO_NODE; - flow->stats.is_percpu = percpu_stats; + /* Initialize the default stat node. */ + stats = kmem_cache_alloc_node(flow_stats_cache, + GFP_KERNEL | __GFP_ZERO, 0); + if (!stats) + goto err; - if (!percpu_stats) { - flow->stats.stat = kzalloc(sizeof(*flow->stats.stat), GFP_KERNEL); - if (!flow->stats.stat) - goto err; + spin_lock_init(&stats->lock); - spin_lock_init(&flow->stats.stat->lock); - } else { - flow->stats.cpu_stats = alloc_percpu(struct flow_stats); - if (!flow->stats.cpu_stats) - goto err; + RCU_INIT_POINTER(flow->stats[0], stats); - for_each_possible_cpu(cpu) { - struct flow_stats *cpu_stats; + for_each_node(node) + if (node != 0) + RCU_INIT_POINTER(flow->stats[node], NULL); - cpu_stats = per_cpu_ptr(flow->stats.cpu_stats, cpu); - spin_lock_init(&cpu_stats->lock); - } - } return flow; err: kmem_cache_free(flow_cache, flow); @@ -138,11 +137,13 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets) static void flow_free(struct sw_flow *flow) { - kfree((struct sf_flow_acts __force *)flow->sf_acts); - if (flow->stats.is_percpu) - free_percpu(flow->stats.cpu_stats); - else - kfree(flow->stats.stat); + int node; + + kfree((struct sw_flow_actions __force *)flow->sf_acts); + for_each_node(node) + if (flow->stats[node]) + kmem_cache_free(flow_stats_cache, + (struct flow_stats __force *)flow->stats[node]); kmem_cache_free(flow_cache, flow); } @@ -158,25 +159,6 @@ void ovs_flow_free(struct sw_flow *flow, bool deferred) if (!flow) return; - if (flow->mask) { - struct sw_flow_mask *mask = flow->mask; - - /* ovs-lock is required to protect mask-refcount and - * mask list. - */ - ASSERT_OVSL(); - BUG_ON(!mask->ref_count); - mask->ref_count--; - - if (!mask->ref_count) { - list_del_rcu(&mask->list); - if (deferred) - kfree_rcu(mask, rcu); - else - kfree(mask); - } - } - if (deferred) call_rcu(&flow->rcu, rcu_free_flow_callback); else @@ -375,7 +357,7 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table) static u32 flow_hash(const struct sw_flow_key *key, int key_start, int key_end) { - u32 *hash_key = (u32 *)((u8 *)key + key_start); + const u32 *hash_key = (const u32 *)((const u8 *)key + key_start); int hash_u32s = (key_end - key_start) >> 2; /* Make sure number of hash bytes are multiple of u32. */ @@ -397,8 +379,8 @@ static bool cmp_key(const struct sw_flow_key *key1, const struct sw_flow_key *key2, int key_start, int key_end) { - const long *cp1 = (long *)((u8 *)key1 + key_start); - const long *cp2 = (long *)((u8 *)key2 + key_start); + const long *cp1 = (const long *)((const u8 *)key1 + key_start); + const long *cp2 = (const long *)((const u8 *)key2 + key_start); long diffs = 0; int i; @@ -490,6 +472,25 @@ static struct table_instance *table_instance_expand(struct table_instance *ti) return table_instance_rehash(ti, ti->n_buckets * 2); } +/* Remove 'mask' from the mask list, if it is not needed any more. */ +static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask) +{ + if (mask) { + /* ovs-lock is required to protect mask-refcount and + * mask list. + */ + ASSERT_OVSL(); + BUG_ON(!mask->ref_count); + mask->ref_count--; + + if (!mask->ref_count) { + list_del_rcu(&mask->list); + kfree_rcu(mask, rcu); + } + } +} + +/* Must be called with OVS mutex held. */ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) { struct table_instance *ti = ovsl_dereference(table->ti); @@ -497,6 +498,11 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) BUG_ON(table->count == 0); hlist_del_rcu(&flow->hash_node[ti->node_ver]); table->count--; + + /* RCU delete the mask. 'flow->mask' is not NULLed, as it should be + * accessible as long as the RCU read lock is held. + */ + flow_mask_remove(table, flow->mask); } static struct sw_flow_mask *mask_alloc(void) @@ -513,8 +519,8 @@ static struct sw_flow_mask *mask_alloc(void) static bool mask_equal(const struct sw_flow_mask *a, const struct sw_flow_mask *b) { - u8 *a_ = (u8 *)&a->key + a->range.start; - u8 *b_ = (u8 *)&b->key + b->range.start; + const u8 *a_ = (const u8 *)&a->key + a->range.start; + const u8 *b_ = (const u8 *)&b->key + b->range.start; return (a->range.end == b->range.end) && (a->range.start == b->range.start) @@ -559,6 +565,7 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow, return 0; } +/* Must be called with OVS mutex held. */ int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow, struct sw_flow_mask *mask) { @@ -597,16 +604,28 @@ int ovs_flow_init(void) BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long)); BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long)); - flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow), 0, - 0, NULL); + flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) + + (num_possible_nodes() + * sizeof(struct flow_stats *)), + 0, 0, NULL); if (flow_cache == NULL) return -ENOMEM; + flow_stats_cache + = kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (flow_stats_cache == NULL) { + kmem_cache_destroy(flow_cache); + flow_cache = NULL; + return -ENOMEM; + } + return 0; } /* Uninitializes the flow module. */ void ovs_flow_exit(void) { + kmem_cache_destroy(flow_stats_cache); kmem_cache_destroy(flow_cache); } diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index baaeb10..ca8a582 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -52,10 +52,12 @@ struct flow_table { unsigned int count; }; +extern struct kmem_cache *flow_stats_cache; + int ovs_flow_init(void); void ovs_flow_exit(void); -struct sw_flow *ovs_flow_alloc(bool percpu_stats); +struct sw_flow *ovs_flow_alloc(void); void ovs_flow_free(struct sw_flow *, bool deferred); int ovs_flow_tbl_init(struct flow_table *); diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 0856f01..35ec4fe 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -256,7 +256,7 @@ static void gre_tnl_destroy(struct vport *vport) ovs_net = net_generic(net, ovs_net_id); - rcu_assign_pointer(ovs_net->vport_net.gre_vport, NULL); + RCU_INIT_POINTER(ovs_net->vport_net.gre_vport, NULL); ovs_vport_deferred_free(vport); gre_exit(); } diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index d7e50a1..8d721e6 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -172,7 +172,7 @@ void ovs_vport_deferred_free(struct vport *vport); */ static inline void *vport_priv(const struct vport *vport) { - return (u8 *)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN); + return (u8 *)(uintptr_t)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN); } /** @@ -185,9 +185,9 @@ static inline void *vport_priv(const struct vport *vport) * the result of a hash table lookup. @priv must point to the start of the * private data area. */ -static inline struct vport *vport_from_priv(const void *priv) +static inline struct vport *vport_from_priv(void *priv) { - return (struct vport *)(priv - ALIGN(sizeof(struct vport), VPORT_ALIGN)); + return (struct vport *)((u8 *)priv - ALIGN(sizeof(struct vport), VPORT_ALIGN)); } void ovs_vport_receive(struct vport *, struct sk_buff *, diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 37be6e2..1dde91e 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -298,7 +298,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) rds_ib_stats_inc(s_ib_tx_cq_event); if (wc.wr_id == RDS_IB_ACK_WR_ID) { - if (ic->i_ack_queued + HZ/2 < jiffies) + if (time_after(jiffies, ic->i_ack_queued + HZ/2)) rds_ib_stats_inc(s_ib_tx_stalled); rds_ib_ack_send_complete(ic); continue; @@ -315,7 +315,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) rm = rds_ib_send_unmap_op(ic, send, wc.status); - if (send->s_queued + HZ/2 < jiffies) + if (time_after(jiffies, send->s_queued + HZ/2)) rds_ib_stats_inc(s_ib_tx_stalled); if (send->s_op) { diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index e40c3c5..9105ea0 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -232,7 +232,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context) } if (wc.wr_id == RDS_IW_ACK_WR_ID) { - if (ic->i_ack_queued + HZ/2 < jiffies) + if (time_after(jiffies, ic->i_ack_queued + HZ/2)) rds_iw_stats_inc(s_iw_tx_stalled); rds_iw_ack_send_complete(ic); continue; @@ -267,7 +267,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context) send->s_wr.opcode = 0xdead; send->s_wr.num_sge = 1; - if (send->s_queued + HZ/2 < jiffies) + if (time_after(jiffies, send->s_queued + HZ/2)) rds_iw_stats_inc(s_iw_tx_stalled); /* If a RDMA operation produced an error, signal this right diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index c2be901..6cd9d1d 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -168,7 +168,7 @@ static int rds_rdma_listen_init(void) return ret; } - sin.sin_family = AF_INET, + sin.sin_family = AF_INET; sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY); sin.sin_port = (__force u16)htons(RDS_PORT); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 4e638f8..23ab4dcd 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -153,7 +153,7 @@ int rds_tcp_listen_init(void) sock->sk->sk_data_ready = rds_tcp_listen_data_ready; write_unlock_bh(&sock->sk->sk_callback_lock); - sin.sin_family = PF_INET, + sin.sin_family = PF_INET; sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY); sin.sin_port = (__force u16)htons(RDS_TCP_PORT); diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index bd2a5b9..14c98e4 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -36,8 +36,6 @@ struct rfkill_gpio_data { struct gpio_desc *shutdown_gpio; struct rfkill *rfkill_dev; - char *reset_name; - char *shutdown_name; struct clk *clk; bool clk_enabled; @@ -47,17 +45,14 @@ static int rfkill_gpio_set_power(void *data, bool blocked) { struct rfkill_gpio_data *rfkill = data; - if (blocked) { - gpiod_set_value(rfkill->shutdown_gpio, 0); - gpiod_set_value(rfkill->reset_gpio, 0); - if (!IS_ERR(rfkill->clk) && rfkill->clk_enabled) - clk_disable(rfkill->clk); - } else { - if (!IS_ERR(rfkill->clk) && !rfkill->clk_enabled) - clk_enable(rfkill->clk); - gpiod_set_value(rfkill->reset_gpio, 1); - gpiod_set_value(rfkill->shutdown_gpio, 1); - } + if (!blocked && !IS_ERR(rfkill->clk) && !rfkill->clk_enabled) + clk_enable(rfkill->clk); + + gpiod_set_value_cansleep(rfkill->shutdown_gpio, !blocked); + gpiod_set_value_cansleep(rfkill->reset_gpio, !blocked); + + if (blocked && !IS_ERR(rfkill->clk) && rfkill->clk_enabled) + clk_disable(rfkill->clk); rfkill->clk_enabled = blocked; @@ -87,10 +82,8 @@ static int rfkill_gpio_probe(struct platform_device *pdev) { struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data; struct rfkill_gpio_data *rfkill; - const char *clk_name = NULL; struct gpio_desc *gpio; int ret; - int len; rfkill = devm_kzalloc(&pdev->dev, sizeof(*rfkill), GFP_KERNEL); if (!rfkill) @@ -101,28 +94,15 @@ static int rfkill_gpio_probe(struct platform_device *pdev) if (ret) return ret; } else if (pdata) { - clk_name = pdata->power_clk_name; rfkill->name = pdata->name; rfkill->type = pdata->type; } else { return -ENODEV; } - len = strlen(rfkill->name); - rfkill->reset_name = devm_kzalloc(&pdev->dev, len + 7, GFP_KERNEL); - if (!rfkill->reset_name) - return -ENOMEM; - - rfkill->shutdown_name = devm_kzalloc(&pdev->dev, len + 10, GFP_KERNEL); - if (!rfkill->shutdown_name) - return -ENOMEM; + rfkill->clk = devm_clk_get(&pdev->dev, NULL); - snprintf(rfkill->reset_name, len + 6 , "%s_reset", rfkill->name); - snprintf(rfkill->shutdown_name, len + 9, "%s_shutdown", rfkill->name); - - rfkill->clk = devm_clk_get(&pdev->dev, clk_name); - - gpio = devm_gpiod_get_index(&pdev->dev, rfkill->reset_name, 0); + gpio = devm_gpiod_get_index(&pdev->dev, "reset", 0); if (!IS_ERR(gpio)) { ret = gpiod_direction_output(gpio, 0); if (ret) @@ -130,7 +110,7 @@ static int rfkill_gpio_probe(struct platform_device *pdev) rfkill->reset_gpio = gpio; } - gpio = devm_gpiod_get_index(&pdev->dev, rfkill->shutdown_name, 1); + gpio = devm_gpiod_get_index(&pdev->dev, "shutdown", 1); if (!IS_ERR(gpio)) { ret = gpiod_direction_output(gpio, 0); if (ret) @@ -146,14 +126,6 @@ static int rfkill_gpio_probe(struct platform_device *pdev) return -EINVAL; } - if (pdata && pdata->gpio_runtime_setup) { - ret = pdata->gpio_runtime_setup(pdev); - if (ret) { - dev_err(&pdev->dev, "can't set up gpio\n"); - return ret; - } - } - rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev, rfkill->type, &rfkill_gpio_ops, rfkill); @@ -174,20 +146,23 @@ static int rfkill_gpio_probe(struct platform_device *pdev) static int rfkill_gpio_remove(struct platform_device *pdev) { struct rfkill_gpio_data *rfkill = platform_get_drvdata(pdev); - struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data; - if (pdata && pdata->gpio_runtime_close) - pdata->gpio_runtime_close(pdev); rfkill_unregister(rfkill->rfkill_dev); rfkill_destroy(rfkill->rfkill_dev); return 0; } +#ifdef CONFIG_ACPI static const struct acpi_device_id rfkill_acpi_match[] = { + { "BCM2E1A", RFKILL_TYPE_BLUETOOTH }, + { "BCM2E39", RFKILL_TYPE_BLUETOOTH }, + { "BCM2E3D", RFKILL_TYPE_BLUETOOTH }, { "BCM4752", RFKILL_TYPE_GPS }, + { "LNV4752", RFKILL_TYPE_GPS }, { }, }; +#endif static struct platform_driver rfkill_gpio_driver = { .probe = rfkill_gpio_probe, diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 7633a75..0ad0807 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -99,7 +99,7 @@ static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr, _debug("tktlen: %x", tktlen); if (tktlen > AFSTOKEN_RK_TIX_MAX) return -EKEYREJECTED; - if (8 * 4 + tktlen != toklen) + if (toklen < 8 * 4 + tktlen) return -EKEYREJECTED; plen = sizeof(*token) + sizeof(*token->kad) + tktlen; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 1618696..13f64df 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -160,7 +160,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, { struct sock_filter *bpf_ops, *bpf_old; struct tcf_exts exts; - struct sock_fprog tmp; + struct sock_fprog_kern tmp; struct sk_filter *fp, *fp_old; u16 bpf_size, bpf_len; u32 classid; @@ -191,7 +191,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size); tmp.len = bpf_len; - tmp.filter = (struct sock_filter __user *) bpf_ops; + tmp.filter = bpf_ops; ret = sk_unattached_filter_create(&fp, &tmp); if (ret) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index d11d0a4..c721cd4 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -188,6 +188,12 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 }, }; +static void tcindex_filter_result_init(struct tcindex_filter_result *r) +{ + memset(r, 0, sizeof(*r)); + tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); +} + static int tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, u32 handle, struct tcindex_data *p, @@ -207,15 +213,11 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, return err; memcpy(&cp, p, sizeof(cp)); - memset(&new_filter_result, 0, sizeof(new_filter_result)); - tcf_exts_init(&new_filter_result.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); + tcindex_filter_result_init(&new_filter_result); + tcindex_filter_result_init(&cr); if (old_r) - memcpy(&cr, r, sizeof(cr)); - else { - memset(&cr, 0, sizeof(cr)); - tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - } + cr.res = r->res; if (tb[TCA_TCINDEX_HASH]) cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); @@ -267,9 +269,14 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = -ENOMEM; if (!cp.perfect && !cp.h) { if (valid_perfect_hash(&cp)) { + int i; + cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL); if (!cp.perfect) goto errout; + for (i = 0; i < cp.hash; i++) + tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT, + TCA_TCINDEX_POLICE); balloc = 1; } else { cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL); @@ -295,14 +302,17 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, tcf_bind_filter(tp, &cr.res, base); } - tcf_exts_change(tp, &cr.exts, &e); + if (old_r) + tcf_exts_change(tp, &r->exts, &e); + else + tcf_exts_change(tp, &cr.exts, &e); tcf_tree_lock(tp); if (old_r && old_r != r) - memset(old_r, 0, sizeof(*old_r)); + tcindex_filter_result_init(old_r); memcpy(p, &cp, sizeof(cp)); - memcpy(r, &cr, sizeof(cr)); + r->res = cr.res; if (r == &new_filter_result) { struct tcindex_filter **fp; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 4dc5d9e..1999592 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -943,7 +943,6 @@ static struct inet_protosw sctpv6_seqpacket_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctpv6_prot, .ops = &inet6_seqpacket_ops, - .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; static struct inet_protosw sctpv6_stream_protosw = { @@ -951,7 +950,6 @@ static struct inet_protosw sctpv6_stream_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctpv6_prot, .ops = &inet6_seqpacket_ops, - .no_check = 0, .flags = SCTP_PROTOSW_FLAG, }; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index af5afca..6789d785 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1017,7 +1017,6 @@ static struct inet_protosw sctp_seqpacket_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, - .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; static struct inet_protosw sctp_stream_protosw = { @@ -1025,7 +1024,6 @@ static struct inet_protosw sctp_stream_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, - .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 2af76ea..4298996 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6946,7 +6946,8 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; newsk->sk_flags = sk->sk_flags; - newsk->sk_no_check = sk->sk_no_check; + newsk->sk_no_check_tx = sk->sk_no_check_tx; + newsk->sk_no_check_rx = sk->sk_no_check_rx; newsk->sk_reuse = sk->sk_reuse; newsk->sk_shutdown = sk->sk_shutdown; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 25a3dcf..1dec604 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -866,8 +866,6 @@ static void xs_reset_transport(struct sock_xprt *transport) xs_restore_old_callbacks(transport, sk); write_unlock_bh(&sk->sk_callback_lock); - sk->sk_no_check = 0; - trace_rpc_socket_close(&transport->xprt, sock); sock_release(sock); } @@ -2046,7 +2044,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; - sk->sk_no_check = UDP_CSUM_NORCV; sk->sk_allocation = GFP_ATOMIC; xprt_set_connected(xprt); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ac08966..08d87fc 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -985,10 +985,11 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, return 0; } -static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) +static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) { struct sock *sk = sock->sk; DEFINE_WAIT(wait); + long timeo = *timeop; int err; for (;;) { @@ -1013,6 +1014,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) break; } finish_wait(sk_sleep(sk), &wait); + *timeop = timeo; return err; } @@ -1056,7 +1058,7 @@ static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock, restart: /* Look for a message in receive queue; wait if necessary */ - res = tipc_wait_for_rcvmsg(sock, timeo); + res = tipc_wait_for_rcvmsg(sock, &timeo); if (res) goto exit; @@ -1154,7 +1156,7 @@ static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock, restart: /* Look for a message in receive queue; wait if necessary */ - res = tipc_wait_for_rcvmsg(sock, timeo); + res = tipc_wait_for_rcvmsg(sock, &timeo); if (res) goto exit; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index bb7e8ba..7b9114e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1492,10 +1492,14 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, if (len > sk->sk_sndbuf - 32) goto out; - if (len > SKB_MAX_ALLOC) + if (len > SKB_MAX_ALLOC) { data_len = min_t(size_t, len - SKB_MAX_ALLOC, MAX_SKB_FRAGS * PAGE_SIZE); + data_len = PAGE_ALIGN(data_len); + + BUILD_BUG_ON(SKB_MAX_ALLOC < PAGE_SIZE); + } skb = sock_alloc_send_pskb(sk, len - data_len, data_len, msg->msg_flags & MSG_DONTWAIT, &err, @@ -1670,6 +1674,8 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, data_len = max_t(int, 0, size - SKB_MAX_HEAD(0)); + data_len = min_t(size_t, size, PAGE_ALIGN(data_len)); + skb = sock_alloc_send_pskb(sk, size - data_len, data_len, msg->msg_flags & MSG_DONTWAIT, &err, get_order(UNIX_SKB_FRAGS_SZ)); diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 3e02ade..bdad1f9 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -6,8 +6,8 @@ #include "rdev-ops.h" -static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev, bool notify) +int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev, bool notify) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 84d686e..992b340 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -370,8 +370,8 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_P2P_DEVICE: - case NL80211_IFTYPE_UNSPECIFIED: break; + case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: WARN_ON(1); } @@ -796,8 +796,7 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy, !cfg80211_go_permissive_chan(rdev, chandef->chan)) prohibited_flags |= IEEE80211_CHAN_NO_IR; - if (cfg80211_chandef_dfs_required(wiphy, chandef, - NL80211_IFTYPE_UNSPECIFIED) > 0 && + if (cfg80211_chandef_dfs_required(wiphy, chandef, iftype) > 0 && cfg80211_chandef_dfs_available(wiphy, chandef)) { /* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */ prohibited_flags = IEEE80211_CHAN_DISABLED; diff --git a/net/wireless/core.c b/net/wireless/core.c index b3ff369..a1c4065 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -130,7 +130,7 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, newname)) pr_err("failed to rename debugfs dir to %s!\n", newname); - nl80211_notify_dev_rename(rdev); + nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); return 0; } @@ -210,15 +210,12 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, } } -static int cfg80211_rfkill_set_block(void *data, bool blocked) +void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) { - struct cfg80211_registered_device *rdev = data; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct wireless_dev *wdev; - if (!blocked) - return 0; - - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(wdev, &rdev->wdev_list, list) { if (wdev->netdev) { @@ -234,7 +231,18 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked) break; } } +} +EXPORT_SYMBOL_GPL(cfg80211_shutdown_all_interfaces); +static int cfg80211_rfkill_set_block(void *data, bool blocked) +{ + struct cfg80211_registered_device *rdev = data; + + if (!blocked) + return 0; + + rtnl_lock(); + cfg80211_shutdown_all_interfaces(&rdev->wiphy); rtnl_unlock(); return 0; @@ -394,6 +402,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) rdev->wiphy.rts_threshold = (u32) -1; rdev->wiphy.coverage_class = 0; + rdev->wiphy.max_num_csa_counters = 1; + return &rdev->wiphy; } EXPORT_SYMBOL(wiphy_new); @@ -650,6 +660,8 @@ int wiphy_register(struct wiphy *wiphy) return res; } + nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); + return 0; } EXPORT_SYMBOL(wiphy_register); @@ -688,9 +700,10 @@ void wiphy_unregister(struct wiphy *wiphy) rfkill_unregister(rdev->rfkill); rtnl_lock(); + nl80211_notify_wiphy(rdev, NL80211_CMD_DEL_WIPHY); rdev->wiphy.registered = false; - BUG_ON(!list_empty(&rdev->wdev_list)); + WARN_ON(!list_empty(&rdev->wdev_list)); /* * First remove the hardware from everywhere, this makes @@ -792,23 +805,23 @@ void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev, rdev->num_running_monitor_ifaces += num; } -void cfg80211_leave(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev) +void __cfg80211_leave(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) { struct net_device *dev = wdev->netdev; ASSERT_RTNL(); + ASSERT_WDEV_LOCK(wdev); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - cfg80211_leave_ibss(rdev, dev, true); + __cfg80211_leave_ibss(rdev, dev, true); break; case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: if (rdev->sched_scan_req && dev == rdev->sched_scan_req->dev) __cfg80211_stop_sched_scan(rdev, false); - wdev_lock(wdev); #ifdef CONFIG_CFG80211_WEXT kfree(wdev->wext.ie); wdev->wext.ie = NULL; @@ -817,20 +830,49 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, #endif cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, true); - wdev_unlock(wdev); break; case NL80211_IFTYPE_MESH_POINT: - cfg80211_leave_mesh(rdev, dev); + __cfg80211_leave_mesh(rdev, dev); break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: - cfg80211_stop_ap(rdev, dev, true); + __cfg80211_stop_ap(rdev, dev, true); break; default: break; } } +void cfg80211_leave(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + wdev_lock(wdev); + __cfg80211_leave(rdev, wdev); + wdev_unlock(wdev); +} + +void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev, + gfp_t gfp) +{ + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct cfg80211_event *ev; + unsigned long flags; + + trace_cfg80211_stop_iface(wiphy, wdev); + + ev = kzalloc(sizeof(*ev), gfp); + if (!ev) + return; + + ev->type = EVENT_STOPPED; + + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + queue_work(cfg80211_wq, &rdev->event_work); +} +EXPORT_SYMBOL(cfg80211_stop_iface); + static int cfg80211_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ptr) { diff --git a/net/wireless/core.h b/net/wireless/core.h index 681b8fa..e9afbf1 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -185,6 +185,7 @@ enum cfg80211_event_type { EVENT_ROAMED, EVENT_DISCONNECTED, EVENT_IBSS_JOINED, + EVENT_STOPPED, }; struct cfg80211_event { @@ -281,6 +282,8 @@ int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, struct mesh_setup *setup, const struct mesh_config *conf); +int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev); int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev); int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, @@ -288,6 +291,8 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef); /* AP */ +int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev, bool notify); int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, bool notify); @@ -441,6 +446,8 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype, int num); +void __cfg80211_leave(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev); void cfg80211_leave(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk index b35da8d..40c37fc 100644 --- a/net/wireless/genregdb.awk +++ b/net/wireless/genregdb.awk @@ -68,17 +68,7 @@ function parse_reg_rule() sub(/,/, "", units) dfs_cac = $9 if (units == "mW") { - if (power == 100) { - power = 20 - } else if (power == 200) { - power = 23 - } else if (power == 500) { - power = 27 - } else if (power == 1000) { - power = 30 - } else { - print "Unknown power value in database!" - } + power = 10 * log(power)/log(10) } else { dfs_cac = $8 } @@ -117,7 +107,7 @@ function parse_reg_rule() } flags = flags "0" - printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %d, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags + printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %.0f, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags rules++ } diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 6b50588..8f345da 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -420,8 +420,8 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev, if (len > 0 && ssid[len - 1] == '\0') len--; + memcpy(wdev->ssid, ssid, len); wdev->wext.ibss.ssid = wdev->ssid; - memcpy(wdev->wext.ibss.ssid, ssid, len); wdev->wext.ibss.ssid_len = len; wdev_lock(wdev); diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index 3ddfb7c..092300b 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -238,8 +238,8 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, return 0; } -static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, - struct net_device *dev) +int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0f1b18f2..ba4f172 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -371,8 +371,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 }, [NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG }, [NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED }, - [NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_U16 }, - [NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_U16 }, + [NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_BINARY }, + [NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_BINARY }, [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY }, [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY }, [NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG }, @@ -386,6 +386,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 }, [NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 }, [NL80211_ATTR_IFACE_SOCKET_OWNER] = { .type = NLA_FLAG }, + [NL80211_ATTR_CSA_C_OFFSETS_TX] = { .type = NLA_BINARY }, }; /* policy for the key attributes */ @@ -970,8 +971,10 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy, c->max_interfaces)) goto nla_put_failure; if (large && - nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS, - c->radar_detect_widths)) + (nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS, + c->radar_detect_widths) || + nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_REGIONS, + c->radar_detect_regions))) goto nla_put_failure; nla_nest_end(msg, nl_combi); @@ -1223,6 +1226,7 @@ struct nl80211_dump_wiphy_state { }; static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, + enum nl80211_commands cmd, struct sk_buff *msg, u32 portid, u32 seq, int flags, struct nl80211_dump_wiphy_state *state) { @@ -1237,7 +1241,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.mgmt_stypes; u32 features; - hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_WIPHY); + hdr = nl80211hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; @@ -1251,6 +1255,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, cfg80211_rdev_list_generation)) goto nla_put_failure; + if (cmd != NL80211_CMD_NEW_WIPHY) + goto finish; + switch (state->split_start) { case 0: if (nla_put_u8(msg, NL80211_ATTR_WIPHY_RETRY_SHORT, @@ -1667,11 +1674,19 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, } nla_nest_end(msg, nested); } + state->split_start++; + break; + case 12: + if (rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH && + nla_put_u8(msg, NL80211_ATTR_MAX_CSA_COUNTERS, + rdev->wiphy.max_num_csa_counters)) + goto nla_put_failure; /* done */ state->split_start = 0; break; } + finish: return genlmsg_end(msg, hdr); nla_put_failure: @@ -1746,7 +1761,8 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) continue; /* attempt to fit multiple wiphy data chunks into the skb */ do { - ret = nl80211_send_wiphy(rdev, skb, + ret = nl80211_send_wiphy(rdev, NL80211_CMD_NEW_WIPHY, + skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, state); @@ -1801,7 +1817,8 @@ static int nl80211_get_wiphy(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - if (nl80211_send_wiphy(rdev, msg, info->snd_portid, info->snd_seq, 0, + if (nl80211_send_wiphy(rdev, NL80211_CMD_NEW_WIPHY, msg, + info->snd_portid, info->snd_seq, 0, &state) < 0) { nlmsg_free(msg); return -ENOBUFS; @@ -3640,6 +3657,10 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq, nla_put_u32(msg, NL80211_STA_INFO_TX_FAILED, sinfo->tx_failed)) goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_EXPECTED_THROUGHPUT) && + nla_put_u32(msg, NL80211_STA_INFO_EXPECTED_THROUGHPUT, + sinfo->expected_throughput)) + goto nla_put_failure; if ((sinfo->filled & STATION_INFO_BEACON_LOSS_COUNT) && nla_put_u32(msg, NL80211_STA_INFO_BEACON_LOSS, sinfo->beacon_loss_count)) @@ -5820,7 +5841,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, return -EBUSY; err = cfg80211_chandef_dfs_required(wdev->wiphy, &chandef, - NL80211_IFTYPE_UNSPECIFIED); + wdev->iftype); if (err < 0) return err; @@ -5861,6 +5882,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) u8 radar_detect_width = 0; int err; bool need_new_beacon = false; + int len, i; if (!rdev->ops->channel_switch || !(rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)) @@ -5919,26 +5941,55 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) if (!csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]) return -EINVAL; - params.counter_offset_beacon = - nla_get_u16(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); - if (params.counter_offset_beacon >= params.beacon_csa.tail_len) + len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); + if (!len || (len % sizeof(u16))) return -EINVAL; - /* sanity check - counters should be the same */ - if (params.beacon_csa.tail[params.counter_offset_beacon] != - params.count) + params.n_counter_offsets_beacon = len / sizeof(u16); + if (rdev->wiphy.max_num_csa_counters && + (params.n_counter_offsets_beacon > + rdev->wiphy.max_num_csa_counters)) return -EINVAL; + params.counter_offsets_beacon = + nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); + + /* sanity checks - counters should fit and be the same */ + for (i = 0; i < params.n_counter_offsets_beacon; i++) { + u16 offset = params.counter_offsets_beacon[i]; + + if (offset >= params.beacon_csa.tail_len) + return -EINVAL; + + if (params.beacon_csa.tail[offset] != params.count) + return -EINVAL; + } + if (csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]) { - params.counter_offset_presp = - nla_get_u16(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); - if (params.counter_offset_presp >= - params.beacon_csa.probe_resp_len) + len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); + if (!len || (len % sizeof(u16))) return -EINVAL; - if (params.beacon_csa.probe_resp[params.counter_offset_presp] != - params.count) + params.n_counter_offsets_presp = len / sizeof(u16); + if (rdev->wiphy.max_num_csa_counters && + (params.n_counter_offsets_beacon > + rdev->wiphy.max_num_csa_counters)) return -EINVAL; + + params.counter_offsets_presp = + nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); + + /* sanity checks - counters should fit and be the same */ + for (i = 0; i < params.n_counter_offsets_presp; i++) { + u16 offset = params.counter_offsets_presp[i]; + + if (offset >= params.beacon_csa.probe_resp_len) + return -EINVAL; + + if (params.beacon_csa.probe_resp[offset] != + params.count) + return -EINVAL; + } } skip_beacons: @@ -7784,6 +7835,27 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) if (!chandef.chan && params.offchan) return -EINVAL; + params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]); + params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]); + + if (info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]) { + int len = nla_len(info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]); + int i; + + if (len % sizeof(u16)) + return -EINVAL; + + params.n_csa_offsets = len / sizeof(u16); + params.csa_offsets = + nla_data(info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]); + + /* check that all the offsets fit the frame */ + for (i = 0; i < params.n_csa_offsets; i++) { + if (params.csa_offsets[i] >= params.len) + return -EINVAL; + } + } + if (!params.dont_wait_for_ack) { msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -7797,8 +7869,6 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) } } - params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]); - params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]); params.chan = chandef.chan; err = cfg80211_mlme_mgmt_tx(rdev, wdev, ¶ms, &cookie); if (err) @@ -8495,6 +8565,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(pat, tb[NL80211_WOWLAN_TRIG_PKT_PATTERN], rem) { + u8 *mask_pat; + nla_parse(pat_tb, MAX_NL80211_PKTPAT, nla_data(pat), nla_len(pat), NULL); err = -EINVAL; @@ -8518,19 +8590,18 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) goto error; new_triggers.patterns[i].pkt_offset = pkt_offset; - new_triggers.patterns[i].mask = - kmalloc(mask_len + pat_len, GFP_KERNEL); - if (!new_triggers.patterns[i].mask) { + mask_pat = kmalloc(mask_len + pat_len, GFP_KERNEL); + if (!mask_pat) { err = -ENOMEM; goto error; } - new_triggers.patterns[i].pattern = - new_triggers.patterns[i].mask + mask_len; - memcpy(new_triggers.patterns[i].mask, - nla_data(pat_tb[NL80211_PKTPAT_MASK]), + new_triggers.patterns[i].mask = mask_pat; + memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_MASK]), mask_len); + mask_pat += mask_len; + new_triggers.patterns[i].pattern = mask_pat; new_triggers.patterns[i].pattern_len = pat_len; - memcpy(new_triggers.patterns[i].pattern, + memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_PATTERN]), pat_len); i++; @@ -8722,6 +8793,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, nla_for_each_nested(pat, tb[NL80211_ATTR_COALESCE_RULE_PKT_PATTERN], rem) { + u8 *mask_pat; + nla_parse(pat_tb, MAX_NL80211_PKTPAT, nla_data(pat), nla_len(pat), NULL); if (!pat_tb[NL80211_PKTPAT_MASK] || @@ -8743,17 +8816,19 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, return -EINVAL; new_rule->patterns[i].pkt_offset = pkt_offset; - new_rule->patterns[i].mask = - kmalloc(mask_len + pat_len, GFP_KERNEL); - if (!new_rule->patterns[i].mask) + mask_pat = kmalloc(mask_len + pat_len, GFP_KERNEL); + if (!mask_pat) return -ENOMEM; - new_rule->patterns[i].pattern = - new_rule->patterns[i].mask + mask_len; - memcpy(new_rule->patterns[i].mask, - nla_data(pat_tb[NL80211_PKTPAT_MASK]), mask_len); + + new_rule->patterns[i].mask = mask_pat; + memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_MASK]), + mask_len); + + mask_pat += mask_len; + new_rule->patterns[i].pattern = mask_pat; new_rule->patterns[i].pattern_len = pat_len; - memcpy(new_rule->patterns[i].pattern, - nla_data(pat_tb[NL80211_PKTPAT_PATTERN]), pat_len); + memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_PATTERN]), + pat_len); i++; } @@ -10033,16 +10108,20 @@ static const struct genl_ops nl80211_ops[] = { /* notification functions */ -void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev) +void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev, + enum nl80211_commands cmd) { struct sk_buff *msg; struct nl80211_dump_wiphy_state state = {}; + WARN_ON(cmd != NL80211_CMD_NEW_WIPHY && + cmd != NL80211_CMD_DEL_WIPHY); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - if (nl80211_send_wiphy(rdev, msg, 0, 0, 0, &state) < 0) { + if (nl80211_send_wiphy(rdev, cmd, msg, 0, 0, 0, &state) < 0) { nlmsg_free(msg); return; } diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 1e6df96..49c9a48 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -5,7 +5,8 @@ int nl80211_init(void); void nl80211_exit(void); -void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev); +void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev, + enum nl80211_commands cmd); void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 00cdf73..d95bbe3 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -199,7 +199,7 @@ static inline int rdev_change_station(struct cfg80211_registered_device *rdev, } static inline int rdev_get_station(struct cfg80211_registered_device *rdev, - struct net_device *dev, u8 *mac, + struct net_device *dev, const u8 *mac, struct station_info *sinfo) { int ret; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index e78f532..558b0e3 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1876,7 +1876,8 @@ static void reg_process_hint(struct regulatory_request *reg_request) case NL80211_REGDOM_SET_BY_USER: treatment = reg_process_hint_user(reg_request); if (treatment == REG_REQ_IGNORE || - treatment == REG_REQ_ALREADY_SET) + treatment == REG_REQ_ALREADY_SET || + treatment == REG_REQ_USER_HINT_HANDLED) return; queue_delayed_work(system_power_efficient_wq, ®_timeout, msecs_to_jiffies(3142)); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index e7329bb..0798c62 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -891,6 +891,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, struct cfg80211_bss_ies *ies; struct ieee80211_channel *channel; struct cfg80211_internal_bss tmp = {}, *res; + bool signal_valid; if (WARN_ON(!wiphy)) return NULL; @@ -927,8 +928,9 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, rcu_assign_pointer(tmp.pub.beacon_ies, ies); rcu_assign_pointer(tmp.pub.ies, ies); - res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, - rx_channel == channel); + signal_valid = abs(rx_channel->center_freq - channel->center_freq) <= + wiphy->max_adj_channel_rssi_comp; + res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid); if (!res) return NULL; @@ -952,6 +954,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, struct cfg80211_internal_bss tmp = {}, *res; struct cfg80211_bss_ies *ies; struct ieee80211_channel *channel; + bool signal_valid; size_t ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable); @@ -999,8 +1002,9 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); - res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, - rx_channel == channel); + signal_valid = abs(rx_channel->center_freq - channel->center_freq) <= + wiphy->max_adj_channel_rssi_comp; + res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid); if (!res) return NULL; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 0c0844b..8bbeeb3 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -149,7 +149,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) case CFG80211_CONN_SCAN_AGAIN: return cfg80211_conn_scan(wdev); case CFG80211_CONN_AUTHENTICATE_NEXT: - BUG_ON(!rdev->ops->auth); + if (WARN_ON(!rdev->ops->auth)) + return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_AUTHENTICATING; return cfg80211_mlme_auth(rdev, wdev->netdev, params->channel, params->auth_type, @@ -161,7 +162,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) case CFG80211_CONN_AUTH_FAILED: return -ENOTCONN; case CFG80211_CONN_ASSOCIATE_NEXT: - BUG_ON(!rdev->ops->assoc); + if (WARN_ON(!rdev->ops->assoc)) + return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_ASSOCIATING; if (wdev->conn->prev_bssid_valid) req.prev_bssid = wdev->conn->prev_bssid; @@ -877,7 +879,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, } void cfg80211_disconnected(struct net_device *dev, u16 reason, - u8 *ie, size_t ie_len, gfp_t gfp) + const u8 *ie, size_t ie_len, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index f3c13ff..560ed77 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1876,29 +1876,33 @@ TRACE_EVENT(rdev_channel_switch, WIPHY_ENTRY NETDEV_ENTRY CHAN_DEF_ENTRY - __field(u16, counter_offset_beacon) - __field(u16, counter_offset_presp) __field(bool, radar_required) __field(bool, block_tx) __field(u8, count) + __dynamic_array(u16, bcn_ofs, params->n_counter_offsets_beacon) + __dynamic_array(u16, pres_ofs, params->n_counter_offsets_presp) ), TP_fast_assign( WIPHY_ASSIGN; NETDEV_ASSIGN; CHAN_DEF_ASSIGN(¶ms->chandef); - __entry->counter_offset_beacon = params->counter_offset_beacon; - __entry->counter_offset_presp = params->counter_offset_presp; __entry->radar_required = params->radar_required; __entry->block_tx = params->block_tx; __entry->count = params->count; + memcpy(__get_dynamic_array(bcn_ofs), + params->counter_offsets_beacon, + params->n_counter_offsets_beacon * sizeof(u16)); + + /* probe response offsets are optional */ + if (params->n_counter_offsets_presp) + memcpy(__get_dynamic_array(pres_ofs), + params->counter_offsets_presp, + params->n_counter_offsets_presp * sizeof(u16)); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT - ", block_tx: %d, count: %u, radar_required: %d" - ", counter offsets (beacon/presp): %u/%u", + ", block_tx: %d, count: %u, radar_required: %d", WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG, - __entry->block_tx, __entry->count, __entry->radar_required, - __entry->counter_offset_beacon, - __entry->counter_offset_presp) + __entry->block_tx, __entry->count, __entry->radar_required) ); TRACE_EVENT(rdev_set_qos_map, @@ -2636,6 +2640,21 @@ TRACE_EVENT(cfg80211_ft_event, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(target_ap)) ); +TRACE_EVENT(cfg80211_stop_iface, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT, + WIPHY_PR_ARG, WDEV_PR_ARG) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/wireless/util.c b/net/wireless/util.c index 7c47fa0..728f1c0 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -476,7 +476,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, EXPORT_SYMBOL(ieee80211_data_to_8023); int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, - enum nl80211_iftype iftype, u8 *bssid, bool qos) + enum nl80211_iftype iftype, + const u8 *bssid, bool qos) { struct ieee80211_hdr hdr; u16 hdrlen, ethertype; @@ -839,6 +840,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid, ev->ij.channel); break; + case EVENT_STOPPED: + __cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); + break; } wdev_unlock(wdev); @@ -1271,10 +1275,20 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, void *data), void *data) { + const struct ieee80211_regdomain *regdom; + enum nl80211_dfs_regions region = 0; int i, j, iftype; int num_interfaces = 0; u32 used_iftypes = 0; + if (radar_detect) { + rcu_read_lock(); + regdom = rcu_dereference(cfg80211_regdomain); + if (regdom) + region = regdom->dfs_region; + rcu_read_unlock(); + } + for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { num_interfaces += iftype_num[iftype]; if (iftype_num[iftype] > 0 && @@ -1315,6 +1329,10 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, if (radar_detect != (c->radar_detect_widths & radar_detect)) goto cont; + if (radar_detect && c->radar_detect_regions && + !(c->radar_detect_regions & BIT(region))) + goto cont; + /* Finally check that all iftypes that we're currently * using are actually part of this combination. If they * aren't then we can't use this combination and have @@ -1528,6 +1546,24 @@ unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy) } EXPORT_SYMBOL(ieee80211_get_num_supported_channels); +int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, + struct station_info *sinfo) +{ + struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; + + wdev = dev->ieee80211_ptr; + if (!wdev) + return -EOPNOTSUPP; + + rdev = wiphy_to_rdev(wdev->wiphy); + if (!rdev->ops->get_station) + return -EOPNOTSUPP; + + return rdev_get_station(rdev, dev, mac_addr, sinfo); +} +EXPORT_SYMBOL(cfg80211_get_station); + /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ const unsigned char rfc1042_header[] __aligned(2) = diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 3bb2cdc..c51e8f7b 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -199,6 +199,7 @@ int xfrm_output(struct sk_buff *skb) return xfrm_output2(skb); } +EXPORT_SYMBOL_GPL(xfrm_output); int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) { @@ -213,6 +214,7 @@ int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) return -EAFNOSUPPORT; return inner_mode->afinfo->extract_output(x, skb); } +EXPORT_SYMBOL_GPL(xfrm_inner_extract_output); void xfrm_local_error(struct sk_buff *skb, int mtu) { @@ -233,7 +235,4 @@ void xfrm_local_error(struct sk_buff *skb, int mtu) afinfo->local_error(skb, mtu); xfrm_state_put_afinfo(afinfo); } - -EXPORT_SYMBOL_GPL(xfrm_output); -EXPORT_SYMBOL_GPL(xfrm_inner_extract_output); EXPORT_SYMBOL_GPL(xfrm_local_error); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e63f242..a8ef510 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -769,7 +769,7 @@ EXPORT_SYMBOL(xfrm_policy_byid); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int -xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info) +xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { int dir, err = 0; @@ -783,10 +783,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi continue; err = security_xfrm_policy_delete(pol->security); if (err) { - xfrm_audit_policy_delete(pol, 0, - audit_info->loginuid, - audit_info->sessionid, - audit_info->secid); + xfrm_audit_policy_delete(pol, 0, task_valid); return err; } } @@ -800,9 +797,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi pol->security); if (err) { xfrm_audit_policy_delete(pol, 0, - audit_info->loginuid, - audit_info->sessionid, - audit_info->secid); + task_valid); return err; } } @@ -812,19 +807,19 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi } #else static inline int -xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info) +xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { return 0; } #endif -int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) +int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) { int dir, err = 0, cnt = 0; write_lock_bh(&net->xfrm.xfrm_policy_lock); - err = xfrm_policy_flush_secctx_check(net, type, audit_info); + err = xfrm_policy_flush_secctx_check(net, type, task_valid); if (err) goto out; @@ -841,9 +836,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) write_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; - xfrm_audit_policy_delete(pol, 1, audit_info->loginuid, - audit_info->sessionid, - audit_info->secid); + xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); @@ -862,10 +855,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) write_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; - xfrm_audit_policy_delete(pol, 1, - audit_info->loginuid, - audit_info->sessionid, - audit_info->secid); + xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); write_lock_bh(&net->xfrm.xfrm_policy_lock); @@ -2860,21 +2850,14 @@ out_byidx: static void xfrm_policy_fini(struct net *net) { - struct xfrm_audit audit_info; unsigned int sz; int dir; flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY - audit_info.loginuid = INVALID_UID; - audit_info.sessionid = (unsigned int)-1; - audit_info.secid = 0; - xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, &audit_info); + xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); #endif - audit_info.loginuid = INVALID_UID; - audit_info.sessionid = (unsigned int)-1; - audit_info.secid = 0; - xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info); + xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false); WARN_ON(!list_empty(&net->xfrm.policy_all)); @@ -2989,15 +2972,14 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, } } -void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, - kuid_t auid, unsigned int sessionid, u32 secid) +void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-add"); if (audit_buf == NULL) return; - xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf); + xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); @@ -3005,14 +2987,14 @@ void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, EXPORT_SYMBOL_GPL(xfrm_audit_policy_add); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, - kuid_t auid, unsigned int sessionid, u32 secid) + bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-delete"); if (audit_buf == NULL) return; - xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf); + xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 8e9c781..0ab5413 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -463,9 +463,7 @@ expired: if (!err) km_state_expired(x, 1, 0); - xfrm_audit_state_delete(x, err ? 0 : 1, - audit_get_loginuid(current), - audit_get_sessionid(current), 0); + xfrm_audit_state_delete(x, err ? 0 : 1, true); out: spin_unlock(&x->lock); @@ -562,7 +560,7 @@ EXPORT_SYMBOL(xfrm_state_delete); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int -xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info) +xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { int i, err = 0; @@ -572,10 +570,7 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { - xfrm_audit_state_delete(x, 0, - audit_info->loginuid, - audit_info->sessionid, - audit_info->secid); + xfrm_audit_state_delete(x, 0, task_valid); return err; } } @@ -585,18 +580,18 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi } #else static inline int -xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info) +xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { return 0; } #endif -int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) { int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); - err = xfrm_state_flush_secctx_check(net, proto, audit_info); + err = xfrm_state_flush_secctx_check(net, proto, task_valid); if (err) goto out; @@ -612,9 +607,7 @@ restart: err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, - audit_info->loginuid, - audit_info->sessionid, - audit_info->secid); + task_valid); xfrm_state_put(x); if (!err) cnt++; @@ -2128,14 +2121,10 @@ out_bydst: void xfrm_state_fini(struct net *net) { - struct xfrm_audit audit_info; unsigned int sz; flush_work(&net->xfrm.state_hash_work); - audit_info.loginuid = INVALID_UID; - audit_info.sessionid = (unsigned int)-1; - audit_info.secid = 0; - xfrm_state_flush(net, IPSEC_PROTO_ANY, &audit_info); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&net->xfrm.state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); @@ -2198,30 +2187,28 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, } } -void xfrm_audit_state_add(struct xfrm_state *x, int result, - kuid_t auid, unsigned int sessionid, u32 secid) +void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-add"); if (audit_buf == NULL) return; - xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf); + xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_add); -void xfrm_audit_state_delete(struct xfrm_state *x, int result, - kuid_t auid, unsigned int sessionid, u32 secid) +void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-delete"); if (audit_buf == NULL) return; - xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf); + xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 51398ae..fd9a16a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -597,9 +597,6 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_state *x; int err; struct km_event c; - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; err = verify_newsa_info(p, attrs); if (err) @@ -615,8 +612,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, else err = xfrm_state_update(x); - security_task_getsecid(current, &sid); - xfrm_audit_state_add(x, err ? 0 : 1, loginuid, sessionid, sid); + xfrm_audit_state_add(x, err ? 0 : 1, true); if (err < 0) { x->km.state = XFRM_STATE_DEAD; @@ -676,9 +672,6 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, int err = -ESRCH; struct km_event c; struct xfrm_usersa_id *p = nlmsg_data(nlh); - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; x = xfrm_user_state_lookup(net, p, attrs, &err); if (x == NULL) @@ -703,8 +696,7 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, km_state_notify(x, &c); out: - security_task_getsecid(current, &sid); - xfrm_audit_state_delete(x, err ? 0 : 1, loginuid, sessionid, sid); + xfrm_audit_state_delete(x, err ? 0 : 1, true); xfrm_state_put(x); return err; } @@ -1414,9 +1406,6 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; int err; int excl; - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; err = verify_newpolicy_info(p); if (err) @@ -1435,8 +1424,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, * a type XFRM_MSG_UPDPOLICY - JHS */ excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY; err = xfrm_policy_insert(p->dir, xp, excl); - security_task_getsecid(current, &sid); - xfrm_audit_policy_add(xp, err ? 0 : 1, loginuid, sessionid, sid); + xfrm_audit_policy_add(xp, err ? 0 : 1, true); if (err) { security_xfrm_policy_free(xp->security); @@ -1673,13 +1661,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, NETLINK_CB(skb).portid); } } else { - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; - - security_task_getsecid(current, &sid); - xfrm_audit_policy_delete(xp, err ? 0 : 1, loginuid, sessionid, - sid); + xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err != 0) goto out; @@ -1704,13 +1686,9 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct km_event c; struct xfrm_usersa_flush *p = nlmsg_data(nlh); - struct xfrm_audit audit_info; int err; - audit_info.loginuid = audit_get_loginuid(current); - audit_info.sessionid = audit_get_sessionid(current); - security_task_getsecid(current, &audit_info.secid); - err = xfrm_state_flush(net, p->proto, &audit_info); + err = xfrm_state_flush(net, p->proto, true); if (err) { if (err == -ESRCH) /* empty table */ return 0; @@ -1894,16 +1872,12 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; u8 type = XFRM_POLICY_TYPE_MAIN; int err; - struct xfrm_audit audit_info; err = copy_from_user_policy_type(&type, attrs); if (err) return err; - audit_info.loginuid = audit_get_loginuid(current); - audit_info.sessionid = audit_get_sessionid(current); - security_task_getsecid(current, &audit_info.secid); - err = xfrm_policy_flush(net, type, &audit_info); + err = xfrm_policy_flush(net, type, true); if (err) { if (err == -ESRCH) /* empty table */ return 0; @@ -1969,14 +1943,8 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, err = 0; if (up->hard) { - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; - - security_task_getsecid(current, &sid); xfrm_policy_delete(xp, p->dir); - xfrm_audit_policy_delete(xp, 1, loginuid, sessionid, sid); - + xfrm_audit_policy_delete(xp, 1, true); } else { // reset the timers here? WARN(1, "Dont know what to do with soft policy expire\n"); @@ -2012,13 +1980,8 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh, km_state_expired(x, ue->hard, nlh->nlmsg_pid); if (ue->hard) { - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; - - security_task_getsecid(current, &sid); __xfrm_state_delete(x); - xfrm_audit_state_delete(x, 1, loginuid, sessionid, sid); + xfrm_audit_state_delete(x, 1, true); } err = 0; out: |
