diff options
Diffstat (limited to 'net')
178 files changed, 2118 insertions, 1439 deletions
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 71c20c1d4002..9f481cfdf77d 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -241,7 +241,7 @@ batadv_v_elp_wifi_neigh_probe(struct batadv_hardif_neigh_node *neigh) * the packet to be exactly of that size to make the link * throughput estimation effective. */ - skb_put(skb, probe_len - hard_iface->bat_v.elp_skb->len); + skb_put_zero(skb, probe_len - hard_iface->bat_v.elp_skb->len); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Sending unicast (probe) ELP packet on interface %s to %pM\n", @@ -268,6 +268,7 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) struct batadv_priv *bat_priv; struct sk_buff *skb; u32 elp_interval; + bool ret; bat_v = container_of(work, struct batadv_hard_iface_bat_v, elp_wq.work); hard_iface = container_of(bat_v, struct batadv_hard_iface, bat_v); @@ -329,8 +330,11 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) * may sleep and that is not allowed in an rcu protected * context. Therefore schedule a task for that. */ - queue_work(batadv_event_workqueue, - &hardif_neigh->bat_v.metric_work); + ret = queue_work(batadv_event_workqueue, + &hardif_neigh->bat_v.metric_work); + + if (!ret) + batadv_hardif_neigh_put(hardif_neigh); } rcu_read_unlock(); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ff9659af6b91..5f1aeeded0e3 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1772,6 +1772,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; + bool ret; ethhdr = eth_hdr(skb); @@ -1795,8 +1796,13 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, if (unlikely(!backbone_gw)) return true; - queue_work(batadv_event_workqueue, &backbone_gw->report_work); - /* backbone_gw is unreferenced in the report work function function */ + ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work); + + /* backbone_gw is unreferenced in the report work function function + * if queue_work() call was successful + */ + if (!ret) + batadv_backbone_gw_put(backbone_gw); return true; } diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 8b198ee798c9..140c61a3f1ec 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rculist.h> @@ -348,6 +349,9 @@ out: * @bat_priv: the bat priv with all the soft interface information * @orig_node: originator announcing gateway capabilities * @gateway: announced bandwidth information + * + * Has to be called with the appropriate locks being acquired + * (gw.list_lock). */ static void batadv_gw_node_add(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, @@ -355,6 +359,8 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, { struct batadv_gw_node *gw_node; + lockdep_assert_held(&bat_priv->gw.list_lock); + if (gateway->bandwidth_down == 0) return; @@ -369,10 +375,8 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, gw_node->bandwidth_down = ntohl(gateway->bandwidth_down); gw_node->bandwidth_up = ntohl(gateway->bandwidth_up); - spin_lock_bh(&bat_priv->gw.list_lock); kref_get(&gw_node->refcount); hlist_add_head_rcu(&gw_node->list, &bat_priv->gw.gateway_list); - spin_unlock_bh(&bat_priv->gw.list_lock); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Found new gateway %pM -> gw bandwidth: %u.%u/%u.%u MBit\n", @@ -428,11 +432,14 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, { struct batadv_gw_node *gw_node, *curr_gw = NULL; + spin_lock_bh(&bat_priv->gw.list_lock); gw_node = batadv_gw_node_get(bat_priv, orig_node); if (!gw_node) { batadv_gw_node_add(bat_priv, orig_node, gateway); + spin_unlock_bh(&bat_priv->gw.list_lock); goto out; } + spin_unlock_bh(&bat_priv->gw.list_lock); if (gw_node->bandwidth_down == ntohl(gateway->bandwidth_down) && gw_node->bandwidth_up == ntohl(gateway->bandwidth_up)) diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 8da3c9336111..3ccc75ee719c 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -25,7 +25,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2018.2" +#define BATADV_SOURCE_VERSION "2018.3" #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 c3578444f3cb..34caf129a9bf 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -854,16 +854,27 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv, spinlock_t *lock; /* Used to lock list selected by "int in_coding" */ struct list_head *list; + /* Select ingoing or outgoing coding node */ + if (in_coding) { + lock = &orig_neigh_node->in_coding_list_lock; + list = &orig_neigh_node->in_coding_list; + } else { + lock = &orig_neigh_node->out_coding_list_lock; + list = &orig_neigh_node->out_coding_list; + } + + spin_lock_bh(lock); + /* Check if nc_node is already added */ nc_node = batadv_nc_find_nc_node(orig_node, orig_neigh_node, in_coding); /* Node found */ if (nc_node) - return nc_node; + goto unlock; nc_node = kzalloc(sizeof(*nc_node), GFP_ATOMIC); if (!nc_node) - return NULL; + goto unlock; /* Initialize nc_node */ INIT_LIST_HEAD(&nc_node->list); @@ -872,22 +883,14 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv, kref_get(&orig_neigh_node->refcount); nc_node->orig_node = orig_neigh_node; - /* Select ingoing or outgoing coding node */ - if (in_coding) { - lock = &orig_neigh_node->in_coding_list_lock; - list = &orig_neigh_node->in_coding_list; - } else { - lock = &orig_neigh_node->out_coding_list_lock; - list = &orig_neigh_node->out_coding_list; - } - batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_node %pM -> %pM\n", nc_node->addr, nc_node->orig_node->orig); /* Add nc_node to orig_node */ - spin_lock_bh(lock); kref_get(&nc_node->refcount); list_add_tail_rcu(&nc_node->list, list); + +unlock: spin_unlock_bh(lock); return nc_node; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 1485263a348b..626ddca332db 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -574,15 +574,20 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) struct batadv_softif_vlan *vlan; int err; + spin_lock_bh(&bat_priv->softif_vlan_list_lock); + vlan = batadv_softif_vlan_get(bat_priv, vid); if (vlan) { batadv_softif_vlan_put(vlan); + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); return -EEXIST; } vlan = kzalloc(sizeof(*vlan), GFP_ATOMIC); - if (!vlan) + if (!vlan) { + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); return -ENOMEM; + } vlan->bat_priv = bat_priv; vlan->vid = vid; @@ -590,17 +595,23 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) atomic_set(&vlan->ap_isolation, 0); + kref_get(&vlan->refcount); + hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list); + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); + + /* batadv_sysfs_add_vlan cannot be in the spinlock section due to the + * sleeping behavior of the sysfs functions and the fs_reclaim lock + */ err = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan); if (err) { - kfree(vlan); + /* ref for the function */ + batadv_softif_vlan_put(vlan); + + /* ref for the list */ + batadv_softif_vlan_put(vlan); return err; } - spin_lock_bh(&bat_priv->softif_vlan_list_lock); - kref_get(&vlan->refcount); - hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list); - spin_unlock_bh(&bat_priv->softif_vlan_list_lock); - /* add a new TT local entry. This one will be marked with the NOPURGE * flag */ diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index f2eef43bd2ec..09427fc6494a 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -188,7 +188,8 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ \ return __batadv_store_uint_attr(buff, count, _min, _max, \ _post_func, attr, \ - &bat_priv->_var, net_dev); \ + &bat_priv->_var, net_dev, \ + NULL); \ } #define BATADV_ATTR_SIF_SHOW_UINT(_name, _var) \ @@ -262,7 +263,9 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ \ length = __batadv_store_uint_attr(buff, count, _min, _max, \ _post_func, attr, \ - &hard_iface->_var, net_dev); \ + &hard_iface->_var, \ + hard_iface->soft_iface, \ + net_dev); \ \ batadv_hardif_put(hard_iface); \ return length; \ @@ -356,10 +359,12 @@ __batadv_store_bool_attr(char *buff, size_t count, static int batadv_store_uint_attr(const char *buff, size_t count, struct net_device *net_dev, + struct net_device *slave_dev, const char *attr_name, unsigned int min, unsigned int max, atomic_t *attr) { + char ifname[IFNAMSIZ + 3] = ""; unsigned long uint_val; int ret; @@ -385,8 +390,11 @@ static int batadv_store_uint_attr(const char *buff, size_t count, if (atomic_read(attr) == uint_val) return count; - batadv_info(net_dev, "%s: Changing from: %i to: %lu\n", - attr_name, atomic_read(attr), uint_val); + if (slave_dev) + snprintf(ifname, sizeof(ifname), "%s: ", slave_dev->name); + + batadv_info(net_dev, "%s: %sChanging from: %i to: %lu\n", + attr_name, ifname, atomic_read(attr), uint_val); atomic_set(attr, uint_val); return count; @@ -397,12 +405,13 @@ static ssize_t __batadv_store_uint_attr(const char *buff, size_t count, void (*post_func)(struct net_device *), const struct attribute *attr, atomic_t *attr_store, - struct net_device *net_dev) + struct net_device *net_dev, + struct net_device *slave_dev) { int ret; - ret = batadv_store_uint_attr(buff, count, net_dev, attr->name, min, max, - attr_store); + ret = batadv_store_uint_attr(buff, count, net_dev, slave_dev, + attr->name, min, max, attr_store); if (post_func && ret) post_func(net_dev); @@ -571,7 +580,7 @@ static ssize_t batadv_store_gw_sel_class(struct kobject *kobj, return __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE, batadv_post_gw_reselect, attr, &bat_priv->gw.sel_class, - bat_priv->soft_iface); + bat_priv->soft_iface, NULL); } static ssize_t batadv_show_gw_bwidth(struct kobject *kobj, @@ -1090,8 +1099,9 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, if (old_tp_override == tp_override) goto out; - batadv_info(net_dev, "%s: Changing from: %u.%u MBit to: %u.%u MBit\n", - "throughput_override", + batadv_info(hard_iface->soft_iface, + "%s: %s: Changing from: %u.%u MBit to: %u.%u MBit\n", + "throughput_override", net_dev->name, old_tp_override / 10, old_tp_override % 10, tp_override / 10, tp_override % 10); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 12a2b7d21376..d21624c44665 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1613,6 +1613,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, { struct batadv_tt_orig_list_entry *orig_entry; + spin_lock_bh(&tt_global->list_lock); + orig_entry = batadv_tt_global_orig_entry_find(tt_global, orig_node); if (orig_entry) { /* refresh the ttvn: the current value could be a bogus one that @@ -1635,11 +1637,9 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, orig_entry->flags = flags; kref_init(&orig_entry->refcount); - spin_lock_bh(&tt_global->list_lock); kref_get(&orig_entry->refcount); hlist_add_head_rcu(&orig_entry->list, &tt_global->orig_list); - spin_unlock_bh(&tt_global->list_lock); atomic_inc(&tt_global->orig_list_count); sync_flags: @@ -1647,6 +1647,8 @@ sync_flags: out: if (orig_entry) batadv_tt_orig_list_entry_put(orig_entry); + + spin_unlock_bh(&tt_global->list_lock); } /** diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index a637458205d1..40e69c9346d2 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -529,15 +529,20 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, { struct batadv_tvlv_handler *tvlv_handler; + spin_lock_bh(&bat_priv->tvlv.handler_list_lock); + tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version); if (tvlv_handler) { + spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); batadv_tvlv_handler_put(tvlv_handler); return; } tvlv_handler = kzalloc(sizeof(*tvlv_handler), GFP_ATOMIC); - if (!tvlv_handler) + if (!tvlv_handler) { + spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); return; + } tvlv_handler->ogm_handler = optr; tvlv_handler->unicast_handler = uptr; @@ -547,7 +552,6 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, kref_init(&tvlv_handler->refcount); INIT_HLIST_NODE(&tvlv_handler->list); - spin_lock_bh(&bat_priv->tvlv.handler_list_lock); kref_get(&tvlv_handler->refcount); hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list); spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 3bdc8f3ca259..ccce954f8146 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2434,9 +2434,8 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, /* LE address type */ addr_type = le_addr_type(cp->addr.type); - hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type); - - err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type); + /* Abort any ongoing SMP pairing. Removes ltk and irk if they exist. */ + err = smp_cancel_and_remove_pairing(hdev, &cp->addr.bdaddr, addr_type); if (err < 0) { err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, MGMT_STATUS_NOT_PAIRED, &rp, @@ -2450,8 +2449,6 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, goto done; } - /* Abort any ongoing SMP pairing */ - smp_cancel_pairing(conn); /* Defer clearing up the connection parameters until closing to * give a chance of keeping them if a repairing happens. diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ae91e2d40056..73f7211d0431 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -83,6 +83,7 @@ enum { struct smp_dev { /* Secure Connections OOB data */ + bool local_oob; u8 local_pk[64]; u8 local_rand[16]; bool debug_key; @@ -599,6 +600,8 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) memcpy(rand, smp->local_rand, 16); + smp->local_oob = true; + return 0; } @@ -1785,7 +1788,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (req->oob_flag == SMP_OOB_PRESENT) + if (req->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); /* SMP over BR/EDR requires special treatment */ @@ -1967,7 +1970,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (rsp->oob_flag == SMP_OOB_PRESENT) + if (rsp->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); smp->prsp[0] = SMP_CMD_PAIRING_RSP; @@ -2419,30 +2422,51 @@ unlock: return ret; } -void smp_cancel_pairing(struct hci_conn *hcon) +int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type) { - struct l2cap_conn *conn = hcon->l2cap_data; + struct hci_conn *hcon; + struct l2cap_conn *conn; struct l2cap_chan *chan; struct smp_chan *smp; + int err; + + err = hci_remove_ltk(hdev, bdaddr, addr_type); + hci_remove_irk(hdev, bdaddr, addr_type); + + hcon = hci_conn_hash_lookup_le(hdev, bdaddr, addr_type); + if (!hcon) + goto done; + conn = hcon->l2cap_data; if (!conn) - return; + goto done; chan = conn->smp; if (!chan) - return; + goto done; l2cap_chan_lock(chan); smp = chan->data; if (smp) { + /* Set keys to NULL to make sure smp_failure() does not try to + * remove and free already invalidated rcu list entries. */ + smp->ltk = NULL; + smp->slave_ltk = NULL; + smp->remote_irk = NULL; + if (test_bit(SMP_FLAG_COMPLETE, &smp->flags)) smp_failure(conn, 0); else smp_failure(conn, SMP_UNSPECIFIED); + err = 0; } l2cap_chan_unlock(chan); + +done: + return err; } static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) @@ -2697,7 +2721,13 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) * key was set/generated. */ if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) { - struct smp_dev *smp_dev = chan->data; + struct l2cap_chan *hchan = hdev->smp_data; + struct smp_dev *smp_dev; + + if (!hchan || !hchan->data) + return SMP_UNSPECIFIED; + + smp_dev = hchan->data; tfm_ecdh = smp_dev->tfm_ecdh; } else { @@ -3230,6 +3260,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) return ERR_CAST(tfm_ecdh); } + smp->local_oob = false; smp->tfm_aes = tfm_aes; smp->tfm_cmac = tfm_cmac; smp->tfm_ecdh = tfm_ecdh; diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index 0ff6247eaa6c..121edadd5f8d 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -181,7 +181,8 @@ enum smp_key_pref { }; /* SMP Commands */ -void smp_cancel_pairing(struct hci_conn *hcon); +int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type); bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, enum smp_key_pref key_pref); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level); diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index f0fc182d3db7..b64e1649993b 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -59,7 +59,7 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, req.is_set = is_set; req.pid = current->pid; req.cmd = optname; - req.addr = (long)optval; + req.addr = (long __force __user)optval; req.len = optlen; mutex_lock(&bpfilter_lock); if (!info.pid) @@ -98,7 +98,7 @@ static int __init load_umh(void) pr_info("Loaded bpfilter_umh pid %d\n", info.pid); /* health check that usermode process started correctly */ - if (__bpfilter_process_sockopt(NULL, 0, 0, 0, 0) != 0) { + if (__bpfilter_process_sockopt(NULL, 0, NULL, 0, 0) != 0) { stop_umh(); return -EFAULT; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 6e0dc6bcd32a..37278dc280eb 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -835,7 +835,8 @@ static unsigned int ip_sabotage_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) { + if (skb->nf_bridge && !skb->nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev)) { state->okfn(state->net, state->sk, skb); return NF_STOLEN; } diff --git a/net/core/dev.c b/net/core/dev.c index 325fc5088370..93243479085f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -93,7 +93,6 @@ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> -#include <linux/notifier.h> #include <linux/skbuff.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> @@ -1753,6 +1752,28 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) } EXPORT_SYMBOL(call_netdevice_notifiers); +/** + * call_netdevice_notifiers_mtu - call all network notifier blocks + * @val: value passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function + * @arg: additional u32 argument passed to the notifier function + * + * Call all network notifier blocks. Parameters and return value + * are as for raw_notifier_call_chain(). + */ +static int call_netdevice_notifiers_mtu(unsigned long val, + struct net_device *dev, u32 arg) +{ + struct netdev_notifier_info_ext info = { + .info.dev = dev, + .ext.mtu = arg, + }; + + BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0); + + return call_netdevice_notifiers_info(val, &info.info); +} + #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); @@ -7575,14 +7596,16 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, err = __dev_set_mtu(dev, new_mtu); if (!err) { - err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, + orig_mtu); err = notifier_to_errno(err); if (err) { /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ __dev_set_mtu(dev, orig_mtu); - call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, + new_mtu); } } return err; diff --git a/net/core/devlink.c b/net/core/devlink.c index 65fc366a78a4..6bc42933be4a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2592,7 +2592,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(skb, info); @@ -2600,7 +2600,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_resource_put: -err_skb_send_alloc: nlmsg_free(skb); return err; } @@ -2996,6 +2995,8 @@ devlink_param_value_get_from_info(const struct devlink_param *param, struct genl_info *info, union devlink_param_value *value) { + int len; + if (param->type != DEVLINK_PARAM_TYPE_BOOL && !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) return -EINVAL; @@ -3011,10 +3012,13 @@ devlink_param_value_get_from_info(const struct devlink_param *param, value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); break; case DEVLINK_PARAM_TYPE_STRING: - if (nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) > - DEVLINK_PARAM_MAX_STRING_VALUE) + len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]), + nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); + if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) || + len >= __DEVLINK_PARAM_MAX_STRING_VALUE) return -EINVAL; - value->vstr = nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + strcpy(value->vstr, + nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); break; case DEVLINK_PARAM_TYPE_BOOL: value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ? @@ -3101,7 +3105,10 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, return -EOPNOTSUPP; if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) { - param_item->driverinit_value = value; + if (param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, value.vstr); + else + param_item->driverinit_value = value; param_item->driverinit_value_valid = true; } else { if (!param->set) @@ -4541,7 +4548,10 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, DEVLINK_PARAM_CMODE_DRIVERINIT)) return -EOPNOTSUPP; - *init_val = param_item->driverinit_value; + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(init_val->vstr, param_item->driverinit_value.vstr); + else + *init_val = param_item->driverinit_value; return 0; } @@ -4572,7 +4582,10 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, DEVLINK_PARAM_CMODE_DRIVERINIT)) return -EOPNOTSUPP; - param_item->driverinit_value = init_val; + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; param_item->driverinit_value_valid = true; devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); @@ -4605,6 +4618,23 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) EXPORT_SYMBOL_GPL(devlink_param_value_changed); /** + * devlink_param_value_str_fill - Safely fill-up the string preventing + * from overflow of the preallocated buffer + * + * @dst_val: destination devlink_param_value + * @src: source buffer + */ +void devlink_param_value_str_fill(union devlink_param_value *dst_val, + const char *src) +{ + size_t len; + + len = strlcpy(dst_val->vstr, src, __DEVLINK_PARAM_MAX_STRING_VALUE); + WARN_ON(len >= __DEVLINK_PARAM_MAX_STRING_VALUE); +} +EXPORT_SYMBOL_GPL(devlink_param_value_str_fill); + +/** * devlink_region_create - create a new address region * * @devlink: devlink diff --git a/net/core/ethtool.c b/net/core/ethtool.c index c9993c6c2fd4..0762aaf8e964 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1483,6 +1483,7 @@ static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) { struct ethtool_wolinfo wol; + int ret; if (!dev->ethtool_ops->set_wol) return -EOPNOTSUPP; @@ -1490,7 +1491,13 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) if (copy_from_user(&wol, useraddr, sizeof(wol))) return -EFAULT; - return dev->ethtool_ops->set_wol(dev, &wol); + ret = dev->ethtool_ops->set_wol(dev, &wol); + if (ret) + return ret; + + dev->wol_enabled = !!wol.wolopts; + + return 0; } static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) @@ -2624,6 +2631,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GPHYSTATS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: + case ETHTOOL_GUFO: case ETHTOOL_GGSO: case ETHTOOL_GGRO: case ETHTOOL_GFLAGS: diff --git a/net/core/filter.c b/net/core/filter.c index c25eb36f1320..5e00f2b85a56 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2282,14 +2282,21 @@ static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .arg2_type = ARG_ANYTHING, }; +#define sk_msg_iter_var(var) \ + do { \ + var++; \ + if (var == MAX_SKB_FRAGS) \ + var = 0; \ + } while (0) + BPF_CALL_4(bpf_msg_pull_data, struct sk_msg_buff *, msg, u32, start, u32, end, u64, flags) { - unsigned int len = 0, offset = 0, copy = 0; + unsigned int len = 0, offset = 0, copy = 0, poffset = 0; + int bytes = end - start, bytes_sg_total; struct scatterlist *sg = msg->sg_data; int first_sg, last_sg, i, shift; unsigned char *p, *to, *from; - int bytes = end - start; struct page *page; if (unlikely(flags || end <= start)) @@ -2299,21 +2306,22 @@ BPF_CALL_4(bpf_msg_pull_data, i = msg->sg_start; do { len = sg[i].length; - offset += len; if (start < offset + len) break; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + offset += len; + sk_msg_iter_var(i); } while (i != msg->sg_end); if (unlikely(start >= offset + len)) return -EINVAL; - if (!msg->sg_copy[i] && bytes <= len) - goto out; - first_sg = i; + /* The start may point into the sg element so we need to also + * account for the headroom. + */ + bytes_sg_total = start - offset + bytes; + if (!msg->sg_copy[i] && bytes_sg_total <= len) + goto out; /* At this point we need to linearize multiple scatterlist * elements or a single shared page. Either way we need to @@ -2327,37 +2335,33 @@ BPF_CALL_4(bpf_msg_pull_data, */ do { copy += sg[i].length; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - if (bytes < copy) + sk_msg_iter_var(i); + if (bytes_sg_total <= copy) break; } while (i != msg->sg_end); last_sg = i; - if (unlikely(copy < end - start)) + if (unlikely(bytes_sg_total > copy)) return -EINVAL; - page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC, get_order(copy)); + page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, + get_order(copy)); if (unlikely(!page)) return -ENOMEM; p = page_address(page); - offset = 0; i = first_sg; do { from = sg_virt(&sg[i]); len = sg[i].length; - to = p + offset; + to = p + poffset; memcpy(to, from, len); - offset += len; + poffset += len; sg[i].length = 0; put_page(sg_page(&sg[i])); - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + sk_msg_iter_var(i); } while (i != last_sg); sg[first_sg].length = copy; @@ -2367,11 +2371,15 @@ BPF_CALL_4(bpf_msg_pull_data, * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ - shift = last_sg - first_sg - 1; + WARN_ON_ONCE(last_sg == first_sg); + shift = last_sg > first_sg ? + last_sg - first_sg - 1 : + MAX_SKB_FRAGS - first_sg + last_sg - 1; if (!shift) goto out; - i = first_sg + 1; + i = first_sg; + sk_msg_iter_var(i); do { int move_from; @@ -2388,15 +2396,13 @@ BPF_CALL_4(bpf_msg_pull_data, sg[move_from].page_link = 0; sg[move_from].offset = 0; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + sk_msg_iter_var(i); } while (1); msg->sg_end -= shift; if (msg->sg_end < 0) msg->sg_end += MAX_SKB_FRAGS; out: - msg->data = sg_virt(&sg[i]) + start - offset; + msg->data = sg_virt(&sg[first_sg]) + start - offset; msg->data_end = msg->data + bytes; return 0; @@ -7281,7 +7287,7 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_reuseport_md, ip_protocol): - BUILD_BUG_ON(hweight_long(SK_FL_PROTO_MASK) != BITS_PER_BYTE); + BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE); SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset, BPF_W, 0); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index aa19d86937af..91592fceeaad 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1180,6 +1180,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, lladdr = neigh->ha; } + /* Update confirmed timestamp for neighbour entry after we + * received ARP packet even if it doesn't change IP to MAC binding. + */ + if (new & NUD_CONNECTED) + neigh->confirmed = jiffies; + /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ @@ -1201,15 +1207,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } } - /* Update timestamps only once we know we will make a change to the + /* Update timestamp only once we know we will make a change to the * neighbour entry. Otherwise we risk to move the locktime window with * noop updates and ignore relevant ARP updates. */ - if (new != old || lladdr != neigh->ha) { - if (new & NUD_CONNECTED) - neigh->confirmed = jiffies; + if (new != old || lladdr != neigh->ha) neigh->updated = jiffies; - } if (new != old) { neigh_del_timer(neigh); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 57557a6a950c..de1d1ba92f2d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -135,27 +135,9 @@ static void queue_process(struct work_struct *work) } } -/* - * Check whether delayed processing was scheduled for our NIC. If so, - * we attempt to grab the poll lock and use ->poll() to pump the card. - * If this fails, either we've recursed in ->poll() or it's already - * running on another CPU. - * - * Note: we don't mask interrupts with this lock because we're using - * trylock here and interrupts are already disabled in the softirq - * case. Further, we test the poll_owner to avoid recursion on UP - * systems where the lock doesn't exist. - */ static void poll_one_napi(struct napi_struct *napi) { - int work = 0; - - /* net_rx_action's ->poll() invocations and our's are - * synchronized by this test which is only made while - * holding the napi->poll_lock. - */ - if (!test_bit(NAPI_STATE_SCHED, &napi->state)) - return; + int work; /* If we set this bit but see that it has already been set, * that indicates that napi has been disabled and we need @@ -187,16 +169,16 @@ static void poll_napi(struct net_device *dev) } } -static void netpoll_poll_dev(struct net_device *dev) +void netpoll_poll_dev(struct net_device *dev) { - const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); + const struct net_device_ops *ops; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity * while changing device state */ - if (down_trylock(&ni->dev_lock)) + if (!ni || down_trylock(&ni->dev_lock)) return; if (!netif_running(dev)) { @@ -205,13 +187,8 @@ static void netpoll_poll_dev(struct net_device *dev) } ops = dev->netdev_ops; - if (!ops->ndo_poll_controller) { - up(&ni->dev_lock); - return; - } - - /* Process pending work on NIC */ - ops->ndo_poll_controller(dev); + if (ops->ndo_poll_controller) + ops->ndo_poll_controller(dev); poll_napi(dev); @@ -219,6 +196,7 @@ static void netpoll_poll_dev(struct net_device *dev) zap_completion_queue(); } +EXPORT_SYMBOL(netpoll_poll_dev); void netpoll_poll_disable(struct net_device *dev) { @@ -334,6 +312,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo; + rcu_read_lock_bh(); lockdep_assert_irqs_disabled(); npinfo = rcu_dereference_bh(np->dev->npinfo); @@ -378,6 +357,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } + rcu_read_unlock_bh(); } EXPORT_SYMBOL(netpoll_send_skb_on_dev); @@ -613,8 +593,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) strlcpy(np->dev_name, ndev->name, IFNAMSIZ); INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); - if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || - !ndev->netdev_ops->ndo_poll_controller) { + if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", np->dev_name); err = -ENOTSUPP; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 24431e578310..37c7936124e6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -324,6 +324,10 @@ void rtnl_unregister_all(int protocol) rtnl_lock(); tab = rtnl_msg_handlers[protocol]; + if (!tab) { + rtnl_unlock(); + return; + } RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL); for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) { link = tab[msgindex]; @@ -1894,10 +1898,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (tb[IFLA_IF_NETNSID]) { netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); tgt_net = get_target_net(skb->sk, netnsid); - if (IS_ERR(tgt_net)) { - tgt_net = net; - netnsid = -1; - } + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); } if (tb[IFLA_EXT_MASK]) @@ -2806,7 +2808,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { - __dev_notify_flags(dev, old_flags, 0U); + __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags)); } else { dev->rtnl_link_state = RTNL_LINK_INITIALIZED; __dev_notify_flags(dev, old_flags, ~0U); @@ -2833,6 +2835,12 @@ struct net_device *rtnl_create_link(struct net *net, else if (ops->get_num_rx_queues) num_rx_queues = ops->get_num_rx_queues(); + if (num_tx_queues < 1 || num_tx_queues > 4096) + return ERR_PTR(-EINVAL); + + if (num_rx_queues < 1 || num_rx_queues > 4096) + return ERR_PTR(-EINVAL); + dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type, ops->setup, num_tx_queues, num_rx_queues); if (!dev) @@ -3740,16 +3748,27 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) int err = 0; int fidx = 0; - err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, - IFLA_MAX, ifla_policy, NULL); - if (err < 0) { - return -EINVAL; - } else if (err == 0) { - if (tb[IFLA_MASTER]) - br_idx = nla_get_u32(tb[IFLA_MASTER]); - } + /* A hack to preserve kernel<->userspace interface. + * Before Linux v4.12 this code accepted ndmsg since iproute2 v3.3.0. + * However, ndmsg is shorter than ifinfomsg thus nlmsg_parse() bails. + * So, check for ndmsg with an optional u32 attribute (not used here). + * Fortunately these sizes don't conflict with the size of ifinfomsg + * with an optional attribute. + */ + if (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) && + (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) + + nla_attr_size(sizeof(u32)))) { + err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, + IFLA_MAX, ifla_policy, NULL); + if (err < 0) { + return -EINVAL; + } else if (err == 0) { + if (tb[IFLA_MASTER]) + br_idx = nla_get_u32(tb[IFLA_MASTER]); + } - brport_idx = ifm->ifi_index; + brport_idx = ifm->ifi_index; + } if (br_idx) { br_dev = __dev_get_by_index(net, br_idx); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c996c09d095f..428094b577fc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -939,9 +939,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) WARN_ON_ONCE(!in_task()); - if (!sock_flag(sk, SOCK_ZEROCOPY)) - return NULL; - skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; @@ -4455,14 +4452,16 @@ EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { - if (unlikely(start > skb_headlen(skb)) || - unlikely((int)start + off > skb_headlen(skb) - 2)) { - net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n", - start, off, skb_headlen(skb)); + u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); + u32 csum_start = skb_headroom(skb) + (u32)start; + + if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) { + net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", + start, off, skb_headroom(skb), skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + start; + skb->csum_start = csum_start; skb->csum_offset = off; skb_set_transport_header(skb, start); return true; diff --git a/net/dccp/input.c b/net/dccp/input.c index d28d46bff6ab..85d6c879383d 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -606,11 +606,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (sk->sk_state == DCCP_LISTEN) { if (dh->dccph_type == DCCP_PKT_REQUEST) { /* It is possible that we process SYN packets from backlog, - * so we need to make sure to disable BH right there. + * so we need to make sure to disable BH and RCU right there. */ + rcu_read_lock(); local_bh_disable(); acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0; local_bh_enable(); + rcu_read_unlock(); if (!acceptable) return 1; consume_skb(skb); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b08feb219b44..8e08cea6f178 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -493,9 +493,11 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq_opt_deref(ireq)); + rcu_dereference(ireq->ireq_opt)); + rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index e63c554e0623..9f3209ff7ffd 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -19,12 +19,10 @@ #include <linux/of_mdio.h> #include <linux/of_platform.h> #include <linux/of_net.h> -#include <linux/of_gpio.h> #include <linux/netdevice.h> #include <linux/sysfs.h> #include <linux/phy_fixed.h> #include <linux/ptp_classify.h> -#include <linux/gpio/consumer.h> #include <linux/etherdevice.h> #include "dsa_priv.h" diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 962c4fd338ba..1c45c1d6d241 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -767,7 +767,6 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, const struct tc_action *a; struct dsa_port *to_dp; int err = -EOPNOTSUPP; - LIST_HEAD(actions); if (!ds->ops->port_mirror_add) return err; @@ -775,8 +774,7 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, if (!tcf_exts_has_one_action(cls->exts)) return err; - tcf_exts_to_list(cls->exts, &actions); - a = list_first_entry(&actions, struct tc_action, list); + a = tcf_exts_first_action(cls->exts); if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) { struct dsa_mall_mirror_tc_entry *mirror; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 20fda8fb8ffd..1fbe2f815474 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1377,6 +1377,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; + skb_reset_mac_len(skb); } while ((skb = skb->next)); out: diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 2998b0e47d4b..0113993e9b2c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1243,7 +1243,8 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct netdev_notifier_changeupper_info *info; + struct netdev_notifier_changeupper_info *upper_info = ptr; + struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); unsigned int flags; @@ -1278,16 +1279,19 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev, RTNH_F_LINKDOWN); else fib_sync_down_dev(dev, event, false); - /* fall through */ + rt_cache_flush(net); + break; case NETDEV_CHANGEMTU: + fib_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(net); break; case NETDEV_CHANGEUPPER: - info = ptr; + upper_info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ - if (info->upper_dev && netif_is_l3_master(info->upper_dev)) + if (upper_info->upper_dev && + netif_is_l3_master(upper_info->upper_dev)) fib_disable_ip(dev, NETDEV_DOWN, true); break; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f3c89ccf14c5..446204ca7406 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1470,6 +1470,56 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh, return NOTIFY_DONE; } +/* Update the PMTU of exceptions when: + * - the new MTU of the first hop becomes smaller than the PMTU + * - the old MTU was the same as the PMTU, and it limited discovery of + * larger MTUs on the path. With that limit raised, we can now + * discover larger MTUs + * A special case is locked exceptions, for which the PMTU is smaller + * than the minimal accepted PMTU: + * - if the new MTU is greater than the PMTU, don't make any change + * - otherwise, unlock and set PMTU + */ +static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig) +{ + struct fnhe_hash_bucket *bucket; + int i; + + bucket = rcu_dereference_protected(nh->nh_exceptions, 1); + if (!bucket) + return; + + for (i = 0; i < FNHE_HASH_SIZE; i++) { + struct fib_nh_exception *fnhe; + + for (fnhe = rcu_dereference_protected(bucket[i].chain, 1); + fnhe; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) { + if (fnhe->fnhe_mtu_locked) { + if (new <= fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + fnhe->fnhe_mtu_locked = false; + } + } else if (new < fnhe->fnhe_pmtu || + orig == fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + } + } + } +} + +void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) +{ + unsigned int hash = fib_devindex_hashfn(dev->ifindex); + struct hlist_head *head = &fib_info_devhash[hash]; + struct fib_nh *nh; + + hlist_for_each_entry(nh, head, nh_hash) { + if (nh->nh_dev == dev) + nh_update_mtu(nh, dev->mtu, orig_mtu); + } +} + /* Event force Flags Description * NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host * NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index cf75f8944b05..4da39446da2d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -820,10 +820,9 @@ static void igmp_timer_expire(struct timer_list *t) spin_lock(&im->lock); im->tm_running = 0; - if (im->unsolicit_count) { - im->unsolicit_count--; + if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); - } + im->reporter = 1; spin_unlock(&im->lock); @@ -1308,6 +1307,8 @@ static void igmp_group_added(struct ip_mc_list *im) if (in_dev->dead) return; + + im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); @@ -1391,9 +1392,6 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode) { struct ip_mc_list *im; -#ifdef CONFIG_IP_MULTICAST - struct net *net = dev_net(in_dev->dev); -#endif ASSERT_RTNL(); @@ -1420,7 +1418,6 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); - im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; #endif im->next_rcu = in_dev->mc_list; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index dfd5009f96ef..15e7f7915a21 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -544,7 +544,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, struct ip_options_rcu *opt; struct rtable *rt; - opt = ireq_opt_deref(ireq); + rcu_read_lock(); + opt = rcu_dereference(ireq->ireq_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, @@ -558,11 +559,13 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; + rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: + rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 88281fbce88c..e7227128df2c 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -599,6 +599,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, nextp = &fp->next; fp->prev = NULL; memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; head->data_len += fp->len; head->len += fp->len; if (head->ip_summed != fp->ip_summed) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 51a5d06085ac..8cce0e9ea08c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -178,6 +178,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info, if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); + else if (tpi->proto == htons(ETH_P_ERSPAN) || + tpi->proto == htons(ETH_P_ERSPAN2)) + itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); @@ -328,6 +331,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } + return PACKET_REJECT; + drop: kfree_skb(skb); return PACKET_RCVD; @@ -1508,11 +1513,14 @@ nla_put_failure: static void erspan_setup(struct net_device *dev) { + struct ip_tunnel *t = netdev_priv(dev); + ether_setup(dev); dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); + t->erspan_ver = 1; } static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index c0fe5ad996f2..26c36cccabdc 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -149,7 +149,6 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; - const struct iphdr *iph = ip_hdr(skb); __be16 *ports; int end; @@ -164,7 +163,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) ports = (__be16 *)skb_transport_header(skb); sin.sin_family = AF_INET; - sin.sin_addr.s_addr = iph->daddr; + sin.sin_addr.s_addr = ip_hdr(skb)->daddr; sin.sin_port = ports[1]; memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index c4f5602308ed..284a22154b4e 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -627,6 +627,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); + unsigned int inner_nhdr_len = 0; const struct iphdr *inner_iph; struct flowi4 fl4; u8 tos, ttl; @@ -636,6 +637,14 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, __be32 dst; bool connected; + /* ensure we can access the inner net header, for several users below */ + if (skb->protocol == htons(ETH_P_IP)) + inner_nhdr_len = sizeof(struct iphdr); + else if (skb->protocol == htons(ETH_P_IPV6)) + inner_nhdr_len = sizeof(struct ipv6hdr); + if (unlikely(!pskb_may_pull(skb, inner_nhdr_len))) + goto tx_error; + inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index d9504adc47b3..184bf2e0a1ed 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -106,6 +106,10 @@ config NF_NAT_IPV4 if NF_NAT_IPV4 +config NF_NAT_MASQUERADE_IPV4 + bool + +if NF_TABLES config NFT_CHAIN_NAT_IPV4 depends on NF_TABLES_IPV4 tristate "IPv4 nf_tables nat chain support" @@ -115,9 +119,6 @@ config NFT_CHAIN_NAT_IPV4 packet transformations such as the source, destination address and source and destination ports. -config NF_NAT_MASQUERADE_IPV4 - bool - config NFT_MASQ_IPV4 tristate "IPv4 masquerading support for nf_tables" depends on NF_TABLES_IPV4 @@ -135,6 +136,7 @@ config NFT_REDIR_IPV4 help This is the expression that provides IPv4 redirect support for nf_tables. +endif # NF_TABLES config NF_NAT_SNMP_BASIC tristate "Basic SNMP-ALG support" diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b678466da451..8501554e96a4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1001,21 +1001,22 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; + u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; if (ip_mtu_locked(dst)) return; - if (ipv4_mtu(dst) < mtu) + if (old_mtu < mtu) return; if (mtu < ip_rt_min_pmtu) { lock = true; - mtu = ip_rt_min_pmtu; + mtu = min(old_mtu, ip_rt_min_pmtu); } - if (rt->rt_pmtu == mtu && + if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) return; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index b92f422f2fa8..891ed2f91467 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -48,6 +48,7 @@ static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static int comp_sack_nr_max = 255; +static u32 u32_max_div_HZ = UINT_MAX / HZ; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -745,9 +746,10 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_probe_interval", .data = &init_net.ipv4.sysctl_tcp_probe_interval, - .maxlen = sizeof(int), + .maxlen = sizeof(u32), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_douintvec_minmax, + .extra2 = &u32_max_div_HZ, }, { .procname = "igmp_link_local_mcast_reports", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b8af2fec5ad5..10c6246396cc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1185,7 +1185,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; - if (flags & MSG_ZEROCOPY && size) { + if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { if (sk->sk_state != TCP_ESTABLISHED) { err = -EINVAL; goto out_err; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 13d34427ca3d..02ff2dde9609 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -95,11 +95,10 @@ struct bbr { u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ - restore_cwnd:1, /* decided to revert cwnd to old value */ round_start:1, /* start of packet-timed tx->ack round? */ idle_restart:1, /* restarting after idle? */ probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ - unused:12, + unused:13, lt_is_sampling:1, /* taking long-term ("LT") samples now? */ lt_rtt_cnt:7, /* round trips in long-term interval */ lt_use_bw:1; /* use lt_bw as our bw estimate? */ @@ -175,6 +174,8 @@ static const u32 bbr_lt_bw_diff = 4000 / 8; /* If we estimate we're policed, use lt_bw for this many round trips: */ static const u32 bbr_lt_bw_max_rtts = 48; +static void bbr_check_probe_rtt_done(struct sock *sk); + /* Do we estimate that STARTUP filled the pipe? */ static bool bbr_full_bw_reached(const struct sock *sk) { @@ -309,6 +310,8 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) */ if (bbr->mode == BBR_PROBE_BW) bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT); + else if (bbr->mode == BBR_PROBE_RTT) + bbr_check_probe_rtt_done(sk); } } @@ -396,17 +399,11 @@ static bool bbr_set_cwnd_to_recover_or_restore( cwnd = tcp_packets_in_flight(tp) + acked; } else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) { /* Exiting loss recovery; restore cwnd saved before recovery. */ - bbr->restore_cwnd = 1; + cwnd = max(cwnd, bbr->prior_cwnd); bbr->packet_conservation = 0; } bbr->prev_ca_state = state; - if (bbr->restore_cwnd) { - /* Restore cwnd after exiting loss recovery or PROBE_RTT. */ - cwnd = max(cwnd, bbr->prior_cwnd); - bbr->restore_cwnd = 0; - } - if (bbr->packet_conservation) { *new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked); return true; /* yes, using packet conservation */ @@ -423,10 +420,10 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u32 cwnd = 0, target_cwnd = 0; + u32 cwnd = tp->snd_cwnd, target_cwnd = 0; if (!acked) - return; + goto done; /* no packet fully ACKed; just apply caps */ if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) goto done; @@ -748,6 +745,20 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ } +static void bbr_check_probe_rtt_done(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (!(bbr->probe_rtt_done_stamp && + after(tcp_jiffies32, bbr->probe_rtt_done_stamp))) + return; + + bbr->min_rtt_stamp = tcp_jiffies32; /* wait a while until PROBE_RTT */ + tp->snd_cwnd = max(tp->snd_cwnd, bbr->prior_cwnd); + bbr_reset_mode(sk); +} + /* The goal of PROBE_RTT mode is to have BBR flows cooperatively and * periodically drain the bottleneck queue, to converge to measure the true * min_rtt (unloaded propagation delay). This allows the flows to keep queues @@ -806,12 +817,8 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) } else if (bbr->probe_rtt_done_stamp) { if (bbr->round_start) bbr->probe_rtt_round_done = 1; - if (bbr->probe_rtt_round_done && - after(tcp_jiffies32, bbr->probe_rtt_done_stamp)) { - bbr->min_rtt_stamp = tcp_jiffies32; - bbr->restore_cwnd = 1; /* snap to prior_cwnd */ - bbr_reset_mode(sk); - } + if (bbr->probe_rtt_round_done) + bbr_check_probe_rtt_done(sk); } } /* Restart after idle ends only once we process a new S/ACK for data */ @@ -862,7 +869,6 @@ static void bbr_init(struct sock *sk) bbr->has_seen_rtt = 0; bbr_init_pacing_rate_from_rtt(sk); - bbr->restore_cwnd = 0; bbr->round_start = 0; bbr->idle_restart = 0; bbr->full_bw_reached = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4c2dd9f863f7..47e08c1b5bc3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6009,11 +6009,13 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (th->fin) goto discard; /* It is possible that we process SYN packets from backlog, - * so we need to make sure to disable BH right there. + * so we need to make sure to disable BH and RCU right there. */ + rcu_read_lock(); local_bh_disable(); acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0; local_bh_enable(); + rcu_read_unlock(); if (!acceptable) return 1; @@ -6367,8 +6369,8 @@ static bool tcp_syn_flood_action(const struct sock *sk, if (!queue->synflood_warned && net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) - pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); + net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); return want_cookie; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9e041fa5c545..cd426313a298 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -943,9 +943,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq_opt_deref(ireq)); + rcu_dereference(ireq->ireq_opt)); + rcu_read_unlock(); err = net_xmit_eval(err); } @@ -2517,6 +2519,12 @@ static int __net_init tcp_sk_init(struct net *net) if (res) goto fail; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + /* Please enforce IP_DF and IPID==0 for RST and + * ACK sent in SYN-RECV and TIME-WAIT state. + */ + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 75ef332a7caf..12affb7864d9 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -184,8 +184,9 @@ kill: inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; } + } else { + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); } - inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f4e35b2ff8b8..c32a4c16b7ff 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1627,7 +1627,7 @@ busy_check: *err = error; return NULL; } -EXPORT_SYMBOL_GPL(__skb_recv_udp); +EXPORT_SYMBOL(__skb_recv_udp); /* * This should be easy, if there is something there we @@ -2124,6 +2124,28 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, inet_compute_pseudo); } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + inet_compute_pseudo); + + ret = udp_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + /* * All we need to do is get the socket, and then do a checksum. */ @@ -2170,14 +2192,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp_sk_rx_dst_set(sk, dst); - ret = udp_queue_rcv_skb(sk, skb); + ret = udp_unicast_rcv_skb(sk, skb, uh); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; + return ret; } if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) @@ -2185,22 +2202,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk) { - int ret; - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - inet_compute_pseudo); - - ret = udp_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; - } + if (sk) + return udp_unicast_rcv_skb(sk, skb, uh); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index bcfc00e88756..f8de2482a529 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -67,6 +67,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) if (xo && (xo->flags & XFRM_GRO)) { skb_mac_header_rebuild(skb); + skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c index 3d36644890bb..1ad2c2c4e250 100644 --- a/net/ipv4/xfrm4_mode_transport.c +++ b/net/ipv4/xfrm4_mode_transport.c @@ -46,7 +46,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) { int ihl = skb->data - skb_transport_header(skb); - struct xfrm_offload *xo = xfrm_offload(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), @@ -54,8 +53,7 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header = skb->transport_header; } ip_hdr(skb)->tot_len = htons(skb->len + ihl); - if (!xo || !(xo->flags & XFRM_GRO)) - skb_reset_transport_header(skb); + skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2fac4ad74867..c63ccce6425f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2398,7 +2398,7 @@ static void addrconf_add_mroute(struct net_device *dev) ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg, GFP_ATOMIC, NULL); + ip6_route_add(&cfg, GFP_KERNEL, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) @@ -3062,7 +3062,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) if (addr.s6_addr32[3]) { add_addr(idev, &addr, plen, scope); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, - GFP_ATOMIC); + GFP_KERNEL); return; } @@ -3087,7 +3087,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) add_addr(idev, &addr, plen, flag); addrconf_prefix_route(&addr, plen, 0, idev->dev, - 0, pflags, GFP_ATOMIC); + 0, pflags, GFP_KERNEL); } } } @@ -4201,7 +4201,6 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) p++; continue; } - state->offset++; return ifa; } @@ -4225,13 +4224,12 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, return ifa; } + state->offset = 0; while (++state->bucket < IN6_ADDR_HSIZE) { - state->offset = 0; hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; - state->offset++; return ifa; } } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 673bba31eb18..9a4261e50272 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -938,14 +938,14 @@ static int __init inet6_init(void) err = proto_register(&pingv6_prot, 1); if (err) - goto out_unregister_ping_proto; + goto out_unregister_raw_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. */ err = rawv6_init(); if (err) - goto out_unregister_raw_proto; + goto out_unregister_ping_proto; /* Register the family here so that the init calls below will * be able to create sockets. (?? is this dangerous ??) @@ -1113,11 +1113,11 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: - ip6_mr_cleanup(); + icmpv6_cleanup(); icmp_fail: - unregister_pernet_subsys(&inet6_net_ops); + ip6_mr_cleanup(); ipmr_fail: - icmpv6_cleanup(); + unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d212738e9d10..cbe46175bb59 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -196,8 +196,12 @@ void fib6_info_destroy_rcu(struct rcu_head *head) *ppcpu_rt = NULL; } } + + free_percpu(f6i->rt6i_pcpu); } + lwtstate_put(f6i->fib6_nh.nh_lwtstate); + if (f6i->fib6_nh.nh_dev) dev_put(f6i->fib6_nh.nh_dev); @@ -987,7 +991,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_clean_expires(iter); else fib6_set_expires(iter, rt->expires); - fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); + + if (rt->fib6_pmtu) + fib6_metric_set(iter, RTAX_MTU, + rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 18a3794b0f52..e493b041d4ac 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1778,6 +1778,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[], if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; + parms->erspan_ver = 1; if (data[IFLA_GRE_ERSPAN_VER]) parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 37ff4805b20c..c7e495f12011 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -115,6 +115,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, payload_len = skb->len - nhoff - sizeof(*ipv6h); ipv6h->payload_len = htons(payload_len); skb->network_header = (u8 *)ipv6h - skb->head; + skb_reset_mac_len(skb); if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 16f200f06500..f9f8f554d141 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -219,12 +219,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -ENOBUFS; } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); consume_skb(skb); skb = skb2; - /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically, - * it is safe to call in our context (socket lock not held) - */ - skb_set_owner_w(skb, (struct sock *)sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5df2a58d945c..a0b6932c3afd 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1188,7 +1188,15 @@ route_lookup: init_tel_txopt(&opt, encap_limit); ipv6_push_frag_opts(skb, &opt.ops, &proto); } - hop_limit = hop_limit ? : ip6_dst_hoplimit(dst); + + if (hop_limit == 0) { + if (skb->protocol == htons(ETH_P_IP)) + hop_limit = ip_hdr(skb)->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + hop_limit = ipv6_hdr(skb)->hop_limit; + else + hop_limit = ip6_dst_hoplimit(dst); + } /* Calculate max headroom for all the headers and adjust * needed_headroom if necessary. @@ -1226,7 +1234,7 @@ static inline int ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - const struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph; int encap_limit = -1; struct flowi6 fl6; __u8 dsfield; @@ -1234,6 +1242,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + /* ensure we can access the full inner ip header */ + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return -1; + + iph = ip_hdr(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); tproto = READ_ONCE(t->parms.proto); @@ -1298,7 +1311,7 @@ static inline int ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; int encap_limit = -1; __u16 offset; struct flowi6 fl6; @@ -1307,6 +1320,10 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + return -1; + + ipv6h = ipv6_hdr(skb); tproto = READ_ONCE(t->parms.proto); if ((tproto != IPPROTO_IPV6 && tproto != 0) || ip6_tnl_addr_conflict(t, ipv6h)) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 38dec9da90d3..eeaf7455d51e 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -481,7 +481,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } mtu = dst_mtu(dst); - if (!skb->ignore_df && skb->len > mtu) { + if (skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { @@ -1094,7 +1094,8 @@ static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n, } t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, list); + if (t) + unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 2a14d8b65924..8f68a518d9db 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -445,6 +445,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; + fp->sk = NULL; } sub_frag_mem_limit(fq->q.net, head->truesize); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 413d98bf24f4..5e0efd3954e9 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -651,8 +651,6 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb->tstamp = sockc->transmit_time; - skb_dst_set(skb, &rt->dst); - *dstp = NULL; skb_put(skb, length); skb_reset_network_header(skb); @@ -665,8 +663,14 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); - if (err) - goto error_fault; + if (err) { + err = -EFAULT; + kfree_skb(skb); + goto error; + } + + skb_dst_set(skb, &rt->dst); + *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -675,21 +679,28 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, if (unlikely(!skb)) return 0; + /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev + * in the error path. Since skb has been freed, the dst could + * have been queued for deletion. + */ + rcu_read_lock(); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); - if (err) - goto error; + if (err) { + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); + goto error_check; + } + rcu_read_unlock(); out: return 0; -error_fault: - err = -EFAULT; - kfree_skb(skb); error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); +error_check: if (err == -ENOBUFS && !np->recverr) err = 0; return err; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7208c16302f6..a366c05a239d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -364,11 +364,14 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); struct rt6_info *rt = (struct rt6_info *)dst; struct fib6_info *from; struct inet6_dev *idev; - dst_destroy_metrics_generic(dst); + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); + rt6_uncached_list_del(rt); idev = rt->rt6i_idev; @@ -946,8 +949,6 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort) static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) { - rt->dst.flags |= fib6_info_dst_flags(ort); - if (ort->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, ort); return; @@ -956,7 +957,7 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) rt->dst.error = 0; rt->dst.output = ip6_output; - if (ort->fib6_type == RTN_LOCAL) { + if (ort->fib6_type == RTN_LOCAL || ort->fib6_type == RTN_ANYCAST) { rt->dst.input = ip6_input; } else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; @@ -978,6 +979,10 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); + if (from->fib6_metrics != &dst_default_metrics) { + rt->dst._metrics |= DST_METRICS_REFCOUNTED; + refcount_inc(&from->fib6_metrics->refcnt); + } } /* Caller must already hold reference to @ort */ @@ -996,7 +1001,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) rt->rt6i_src = ort->fib6_src; #endif rt->rt6i_prefsrc = ort->fib6_prefsrc; - rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate); } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, @@ -4317,11 +4321,6 @@ static int ip6_route_info_append(struct net *net, if (!nh) return -ENOMEM; nh->fib6_info = rt; - err = ip6_convert_metrics(net, rt, r_cfg); - if (err) { - kfree(nh); - return err; - } memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); list_add_tail(&nh->next, rt6_nh_list); @@ -4671,20 +4670,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - struct rtmsg *rtm; + struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6key *rt6_dst, *rt6_src; + u32 *pmetrics, table, rt6_flags; struct nlmsghdr *nlh; + struct rtmsg *rtm; long expires = 0; - u32 *pmetrics; - u32 table; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; + if (rt6) { + rt6_dst = &rt6->rt6i_dst; + rt6_src = &rt6->rt6i_src; + rt6_flags = rt6->rt6i_flags; + } else { + rt6_dst = &rt->fib6_dst; + rt6_src = &rt->fib6_src; + rt6_flags = rt->fib6_flags; + } + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; - rtm->rtm_dst_len = rt->fib6_dst.plen; - rtm->rtm_src_len = rt->fib6_src.plen; + rtm->rtm_dst_len = rt6_dst->plen; + rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; @@ -4699,7 +4709,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; - if (rt->fib6_flags & RTF_CACHE) + if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { @@ -4707,7 +4717,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr)) + if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { @@ -4715,12 +4725,12 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && - nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr)) + nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE - if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) { + if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) @@ -4755,7 +4765,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ - if (rt->fib6_nsiblings) { + if (rt6) { + if (rt6_flags & RTF_GATEWAY && + nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) + goto nla_put_failure; + + if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) + goto nla_put_failure; + } else if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; struct nlattr *mp; @@ -4778,7 +4795,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; } - if (rt->fib6_flags & RTF_EXPIRES) { + if (rt6_flags & RTF_EXPIRES) { expires = dst ? dst->expires : rt->expires; expires -= jiffies; } @@ -4786,7 +4803,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; - if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags))) + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 83f4c77c79d8..28c4aa5078fc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -752,6 +752,28 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) } } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + ip6_compute_pseudo); + + ret = udpv6_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { @@ -803,13 +825,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp6_sk_rx_dst_set(sk, dst); - ret = udpv6_queue_rcv_skb(sk, skb); - sock_put(sk); + if (!uh->check && !udp_sk(sk)->no_check6_rx) { + sock_put(sk); + goto report_csum_error; + } - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - return 0; + ret = udp6_unicast_rcv_skb(sk, skb, uh); + sock_put(sk); + return ret; } /* @@ -822,30 +845,13 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { - int ret; - - if (!uh->check && !udp_sk(sk)->no_check6_rx) { - udp6_csum_zero_error(skb); - goto csum_error; - } - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - ip6_compute_pseudo); - - ret = udpv6_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - - return 0; + if (!uh->check && !udp_sk(sk)->no_check6_rx) + goto report_csum_error; + return udp6_unicast_rcv_skb(sk, skb, uh); } - if (!uh->check) { - udp6_csum_zero_error(skb); - goto csum_error; - } + if (!uh->check) + goto report_csum_error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; @@ -866,6 +872,9 @@ short_packet: ulen, skb->len, daddr, ntohs(uh->dest)); goto discard; + +report_csum_error: + udp6_csum_zero_error(skb); csum_error: __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 841f4a07438e..9ef490dddcea 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -59,6 +59,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) if (xo && (xo->flags & XFRM_GRO)) { skb_mac_header_rebuild(skb); + skb_reset_transport_header(skb); return -1; } diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c index 9ad07a91708e..3c29da5defe6 100644 --- a/net/ipv6/xfrm6_mode_transport.c +++ b/net/ipv6/xfrm6_mode_transport.c @@ -51,7 +51,6 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) { int ihl = skb->data - skb_transport_header(skb); - struct xfrm_offload *xo = xfrm_offload(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), @@ -60,8 +59,7 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) } ipv6_hdr(skb)->payload_len = htons(skb->len + ihl - sizeof(struct ipv6hdr)); - if (!xo || !(xo->flags & XFRM_GRO)) - skb_reset_transport_header(skb); + skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 5959ce9620eb..6a74080005cf 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -170,9 +170,11 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (toobig && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); + kfree_skb(skb); return -EMSGSIZE; } else if (!skb->ignore_df && toobig && skb->sk) { xfrm_local_error(skb, mtu); + kfree_skb(skb); return -EMSGSIZE; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index a21d8ed0a325..e2f16a0173a9 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -351,20 +351,28 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, memcpy(&phs_hdr->iucv_hdr, imsg, sizeof(struct iucv_message)); skb->dev = iucv->hs_dev; - if (!skb->dev) - return -ENODEV; - if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) - return -ENETDOWN; + if (!skb->dev) { + err = -ENODEV; + goto err_free; + } + if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) { + err = -ENETDOWN; + goto err_free; + } if (skb->len > skb->dev->mtu) { - if (sock->sk_type == SOCK_SEQPACKET) - return -EMSGSIZE; - else - skb_trim(skb, skb->dev->mtu); + if (sock->sk_type == SOCK_SEQPACKET) { + err = -EMSGSIZE; + goto err_free; + } + skb_trim(skb, skb->dev->mtu); } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); nskb = skb_clone(skb, GFP_ATOMIC); - if (!nskb) - return -ENOMEM; + if (!nskb) { + err = -ENOMEM; + goto err_free; + } + skb_queue_tail(&iucv->send_skb_q, nskb); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { @@ -375,6 +383,10 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, WARN_ON(atomic_read(&iucv->msg_recv) < 0); } return net_xmit_eval(err); + +err_free: + kfree_skb(skb); + return err; } static struct sock *__iucv_get_sock_by_name(char *nm) @@ -1167,7 +1179,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, err = afiucv_hs_send(&txmsg, sk, skb, 0); if (err) { atomic_dec(&iucv->msg_sent); - goto fail; + goto out; } } else { /* Classic VM IUCV transport */ skb_queue_tail(&iucv->send_skb_q, skb); @@ -2155,8 +2167,8 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, struct sock *sk; struct iucv_sock *iucv; struct af_iucv_trans_hdr *trans_hdr; + int err = NET_RX_SUCCESS; char nullstring[8]; - int err = 0; if (skb->len < (ETH_HLEN + sizeof(struct af_iucv_trans_hdr))) { WARN_ONCE(1, "AF_IUCV too short skb, len=%d, min=%d", @@ -2254,7 +2266,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, err = afiucv_hs_callback_rx(sk, skb); break; default: - ; + kfree_skb(skb); } return err; diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 8f7ef167c45a..eb502c6290c2 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1874,7 +1874,7 @@ static void iucv_pm_complete(struct device *dev) * Returns 0 if there are still iucv pathes defined * 1 if there are no iucv pathes defined */ -int iucv_path_table_empty(void) +static int iucv_path_table_empty(void) { int i; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index d25da0e66da1..5d22eda8a6b1 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -427,7 +427,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ - if (key->sta && test_sta_flag(key->sta, WLAN_STA_MFP)) + if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 6449a1c2283b..f0f5fedb8caa 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -947,8 +947,8 @@ static void ieee80211_rx_mgmt_deauth_ibss(struct ieee80211_sub_if_data *sdata, if (len < IEEE80211_DEAUTH_FRAME_LEN) return; - ibss_dbg(sdata, "RX DeAuth SA=%pM DA=%pM BSSID=%pM (reason: %d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, reason); + ibss_dbg(sdata, "RX DeAuth SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (reason: %d)\n", mgmt->bssid, reason); sta_info_destroy_addr(sdata, mgmt->sa); } @@ -966,9 +966,9 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg); auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction); - ibss_dbg(sdata, - "RX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=%d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, auth_transaction); + ibss_dbg(sdata, "RX Auth SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (auth_transaction=%d)\n", + mgmt->bssid, auth_transaction); if (auth_alg != WLAN_AUTH_OPEN || auth_transaction != 1) return; @@ -1175,10 +1175,10 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, rx_timestamp = drv_get_tsf(local, sdata); } - ibss_dbg(sdata, - "RX beacon SA=%pM BSSID=%pM TSF=0x%llx BCN=0x%llx diff=%lld @%lu\n", + ibss_dbg(sdata, "RX beacon SA=%pM BSSID=%pM TSF=0x%llx\n", mgmt->sa, mgmt->bssid, - (unsigned long long)rx_timestamp, + (unsigned long long)rx_timestamp); + ibss_dbg(sdata, "\tBCN=0x%llx diff=%lld @%lu\n", (unsigned long long)beacon_timestamp, (unsigned long long)(rx_timestamp - beacon_timestamp), jiffies); @@ -1537,9 +1537,9 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, tx_last_beacon = drv_tx_last_beacon(local); - ibss_dbg(sdata, - "RX ProbeReq SA=%pM DA=%pM BSSID=%pM (tx_last_beacon=%d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, tx_last_beacon); + ibss_dbg(sdata, "RX ProbeReq SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (tx_last_beacon=%d)\n", + mgmt->bssid, tx_last_beacon); if (!tx_last_beacon && is_multicast_ether_addr(mgmt->da)) return; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 5e6cf2cee965..5836ddeac9e3 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1756,7 +1756,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, if (local->ops->wake_tx_queue && type != NL80211_IFTYPE_AP_VLAN && - type != NL80211_IFTYPE_MONITOR) + (type != NL80211_IFTYPE_MONITOR || + (params->flags & MONITOR_FLAG_ACTIVE))) txq_size += sizeof(struct txq_info) + local->hw.txq_data_size; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4fb2709cb527..513627896204 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -256,8 +256,27 @@ static void ieee80211_restart_work(struct work_struct *work) flush_work(&local->radar_detected_work); rtnl_lock(); - list_for_each_entry(sdata, &local->interfaces, list) + list_for_each_entry(sdata, &local->interfaces, list) { + /* + * XXX: there may be more work for other vif types and even + * for station mode: a good thing would be to run most of + * the iface type's dependent _stop (ieee80211_mg_stop, + * ieee80211_ibss_stop) etc... + * For now, fix only the specific bug that was seen: race + * between csa_connection_drop_work and us. + */ + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + /* + * This worker is scheduled from the iface worker that + * runs on mac80211's workqueue, so we can't be + * scheduling this worker after the cancel right here. + * The exception is ieee80211_chswitch_done. + * Then we can have a race... + */ + cancel_work_sync(&sdata->u.mgd.csa_connection_drop_work); + } flush_delayed_work(&sdata->dec_tailroom_needed_wk); + } ieee80211_scan_cancel(local); /* make sure any new ROC will consider local->in_reconfig */ @@ -471,10 +490,7 @@ static const struct ieee80211_vht_cap mac80211_vht_capa_mod_mask = { cpu_to_le32(IEEE80211_VHT_CAP_RXLDPC | IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_SHORT_GI_160 | - IEEE80211_VHT_CAP_RXSTBC_1 | - IEEE80211_VHT_CAP_RXSTBC_2 | - IEEE80211_VHT_CAP_RXSTBC_3 | - IEEE80211_VHT_CAP_RXSTBC_4 | + IEEE80211_VHT_CAP_RXSTBC_MASK | IEEE80211_VHT_CAP_TXSTBC | IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE | IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE | @@ -1208,6 +1224,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&local->ifa6_notifier); #endif + ieee80211_txq_teardown_flows(local); rtnl_lock(); @@ -1236,7 +1253,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) skb_queue_purge(&local->skb_queue); skb_queue_purge(&local->skb_queue_unreliable); skb_queue_purge(&local->skb_queue_tdls_chsw); - ieee80211_txq_teardown_flows(local); destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index ee56f18cad3f..21526630bf65 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -217,7 +217,8 @@ void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); void ieee80211s_update_metric(struct ieee80211_local *local, - struct sta_info *sta, struct sk_buff *skb); + struct sta_info *sta, + struct ieee80211_tx_status *st); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata); int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 35ad3983ae4b..6950cd0bf594 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -295,15 +295,12 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, } void ieee80211s_update_metric(struct ieee80211_local *local, - struct sta_info *sta, struct sk_buff *skb) + struct sta_info *sta, + struct ieee80211_tx_status *st) { - struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_tx_info *txinfo = st->info; int failed; - if (!ieee80211_is_data(hdr->frame_control)) - return; - failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK); /* moving average, scaled to 100. @@ -572,6 +569,10 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, forward = false; reply = true; target_metric = 0; + + if (SN_GT(target_sn, ifmsh->sn)) + ifmsh->sn = target_sn; + if (time_after(jiffies, ifmsh->last_sn_update + net_traversal_jiffies(sdata)) || time_before(jiffies, ifmsh->last_sn_update)) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 7fb9957359a3..3dbecae4be73 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1073,6 +1073,10 @@ static void ieee80211_chswitch_work(struct work_struct *work) */ if (sdata->reserved_chanctx) { + struct ieee80211_supported_band *sband = NULL; + struct sta_info *mgd_sta = NULL; + enum ieee80211_sta_rx_bandwidth bw = IEEE80211_STA_RX_BW_20; + /* * with multi-vif csa driver may call ieee80211_csa_finish() * many times while waiting for other interfaces to use their @@ -1081,6 +1085,48 @@ static void ieee80211_chswitch_work(struct work_struct *work) if (sdata->reserved_ready) goto out; + if (sdata->vif.bss_conf.chandef.width != + sdata->csa_chandef.width) { + /* + * For managed interface, we need to also update the AP + * station bandwidth and align the rate scale algorithm + * on the bandwidth change. Here we only consider the + * bandwidth of the new channel definition (as channel + * switch flow does not have the full HT/VHT/HE + * information), assuming that if additional changes are + * required they would be done as part of the processing + * of the next beacon from the AP. + */ + switch (sdata->csa_chandef.width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + default: + bw = IEEE80211_STA_RX_BW_20; + break; + case NL80211_CHAN_WIDTH_40: + bw = IEEE80211_STA_RX_BW_40; + break; + case NL80211_CHAN_WIDTH_80: + bw = IEEE80211_STA_RX_BW_80; + break; + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + bw = IEEE80211_STA_RX_BW_160; + break; + } + + mgd_sta = sta_info_get(sdata, ifmgd->bssid); + sband = + local->hw.wiphy->bands[sdata->csa_chandef.chan->band]; + } + + if (sdata->vif.bss_conf.chandef.width > + sdata->csa_chandef.width) { + mgd_sta->sta.bandwidth = bw; + rate_control_rate_update(local, sband, mgd_sta, + IEEE80211_RC_BW_CHANGED); + } + ret = ieee80211_vif_use_reserved_context(sdata); if (ret) { sdata_info(sdata, @@ -1091,6 +1137,13 @@ static void ieee80211_chswitch_work(struct work_struct *work) goto out; } + if (sdata->vif.bss_conf.chandef.width < + sdata->csa_chandef.width) { + mgd_sta->sta.bandwidth = bw; + rate_control_rate_update(local, sband, mgd_sta, + IEEE80211_RC_BW_CHANGED); + } + goto out; } @@ -1312,6 +1365,16 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, cbss->beacon_interval)); return; drop_connection: + /* + * This is just so that the disconnect flow will know that + * we were trying to switch channel and failed. In case the + * mode is 1 (we are not allowed to Tx), we will know not to + * send a deauthentication frame. Those two fields will be + * reset when the disconnection worker runs. + */ + sdata->vif.csa_active = true; + sdata->csa_block_tx = csa_ie.mode; + ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work); mutex_unlock(&local->chanctx_mtx); mutex_unlock(&local->mtx); @@ -2522,6 +2585,7 @@ 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]; + bool tx; sdata_lock(sdata); if (!ifmgd->associated) { @@ -2529,6 +2593,8 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) return; } + tx = !sdata->csa_block_tx; + /* AP is probably out of range (or not reachable for another reason) so * remove the bss struct for that AP. */ @@ -2536,7 +2602,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, - true, frame_buf); + tx, frame_buf); mutex_lock(&local->mtx); sdata->vif.csa_active = false; ifmgd->csa_waiting_bcn = false; @@ -2547,7 +2613,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) } mutex_unlock(&local->mtx); - ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, + ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); sdata_unlock(sdata); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 64742f2765c4..96611d5dfadb 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1728,6 +1728,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) */ if (!ieee80211_hw_check(&sta->local->hw, AP_LINK_PS) && !ieee80211_has_morefrags(hdr->frame_control) && + !is_multicast_ether_addr(hdr->addr1) && (ieee80211_is_mgmt(hdr->frame_control) || ieee80211_is_data(hdr->frame_control)) && !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 9a6d7208bf4f..91d7c0cd1882 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -479,11 +479,6 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, if (!skb) return; - if (dropped) { - dev_kfree_skb_any(skb); - return; - } - if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie; struct ieee80211_sub_if_data *sdata; @@ -507,6 +502,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, rcu_read_unlock(); dev_kfree_skb_any(skb); + } else if (dropped) { + dev_kfree_skb_any(skb); } else { /* consumes skb */ skb_complete_wifi_ack(skb, acked); @@ -811,7 +808,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, rate_control_tx_status(local, sband, status); if (ieee80211_vif_is_mesh(&sta->sdata->vif)) - ieee80211s_update_metric(local, sta, skb); + ieee80211s_update_metric(local, sta, status); if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked) ieee80211_frame_acked(sta, skb); @@ -972,6 +969,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, } rate_control_tx_status(local, sband, status); + if (ieee80211_vif_is_mesh(&sta->sdata->vif)) + ieee80211s_update_metric(local, sta, status); } if (acked || noack_success) { diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 5cd5e6e5834e..6c647f425e05 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -16,6 +16,7 @@ #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" +#include "wme.h" /* give usermode some time for retries in setting up the TDLS session */ #define TDLS_PEER_SETUP_TIMEOUT (15 * HZ) @@ -1010,14 +1011,13 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: case WLAN_TDLS_SETUP_RESPONSE: - skb_set_queue_mapping(skb, IEEE80211_AC_BK); - skb->priority = 2; + skb->priority = 256 + 2; break; default: - skb_set_queue_mapping(skb, IEEE80211_AC_VI); - skb->priority = 5; + skb->priority = 256 + 5; break; } + skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, skb)); /* * Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress. diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index cd332e3e1134..25ba24bef8f5 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -214,6 +214,7 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) { struct ieee80211_local *local = tx->local; struct ieee80211_if_managed *ifmgd; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); /* driver doesn't support power save */ if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS)) @@ -242,6 +243,9 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) if (tx->sdata->vif.type != NL80211_IFTYPE_STATION) return TX_CONTINUE; + if (unlikely(info->flags & IEEE80211_TX_INTFL_OFFCHAN_TX_OK)) + return TX_CONTINUE; + ifmgd = &tx->sdata->u.mgd; /* @@ -1890,7 +1894,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; if (invoke_tx_handlers_early(&tx)) - return false; + return true; if (ieee80211_queue_skb(local, sdata, tx.sta, tx.skb)) return true; @@ -3078,27 +3082,18 @@ void ieee80211_clear_fast_xmit(struct sta_info *sta) } static bool ieee80211_amsdu_realloc_pad(struct ieee80211_local *local, - struct sk_buff *skb, int headroom, - int *subframe_len) + struct sk_buff *skb, int headroom) { - int amsdu_len = *subframe_len + sizeof(struct ethhdr); - int padding = (4 - amsdu_len) & 3; - - if (skb_headroom(skb) < headroom || skb_tailroom(skb) < padding) { + if (skb_headroom(skb) < headroom) { I802_DEBUG_INC(local->tx_expand_skb_head); - if (pskb_expand_head(skb, headroom, padding, GFP_ATOMIC)) { + if (pskb_expand_head(skb, headroom, 0, GFP_ATOMIC)) { wiphy_debug(local->hw.wiphy, "failed to reallocate TX buffer\n"); return false; } } - if (padding) { - *subframe_len += padding; - skb_put_zero(skb, padding); - } - return true; } @@ -3122,8 +3117,7 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata, if (info->control.flags & IEEE80211_TX_CTRL_AMSDU) return true; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr), - &subframe_len)) + if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr))) return false; data = skb_push(skb, sizeof(*amsdu_hdr)); @@ -3189,7 +3183,8 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, void *data; bool ret = false; unsigned int orig_len; - int n = 1, nfrags; + int n = 2, nfrags, pad = 0; + u16 hdrlen; if (!ieee80211_hw_check(&local->hw, TX_AMSDU)) return false; @@ -3222,9 +3217,6 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (skb->len + head->len > max_amsdu_len) goto out; - if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) - goto out; - nfrags = 1 + skb_shinfo(skb)->nr_frags; nfrags += 1 + skb_shinfo(head)->nr_frags; frag_tail = &skb_shinfo(head)->frag_list; @@ -3240,10 +3232,24 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (max_frags && nfrags > max_frags) goto out; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) + 2, - &subframe_len)) + if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) goto out; + /* + * Pad out the previous subframe to a multiple of 4 by adding the + * padding to the next one, that's being added. Note that head->len + * is the length of the full A-MSDU, but that works since each time + * we add a new subframe we pad out the previous one to a multiple + * of 4 and thus it no longer matters in the next round. + */ + hdrlen = fast_tx->hdr_len - sizeof(rfc1042_header); + if ((head->len - hdrlen) & 3) + pad = 4 - ((head->len - hdrlen) & 3); + + if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) + + 2 + pad)) + goto out_recalc; + ret = true; data = skb_push(skb, ETH_ALEN + 2); memmove(data, data + ETH_ALEN + 2, 2 * ETH_ALEN); @@ -3253,15 +3259,19 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, memcpy(data, &len, 2); memcpy(data + 2, rfc1042_header, sizeof(rfc1042_header)); + memset(skb_push(skb, pad), 0, pad); + head->len += skb->len; head->data_len += skb->len; *frag_tail = skb; - flow->backlog += head->len - orig_len; - tin->backlog_bytes += head->len - orig_len; - - fq_recalc_backlog(fq, tin, flow); +out_recalc: + if (head->len != orig_len) { + flow->backlog += head->len - orig_len; + tin->backlog_bytes += head->len - orig_len; + fq_recalc_backlog(fq, tin, flow); + } out: spin_unlock_bh(&fq->lock); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 88efda7c9f8a..716cd6442d86 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1135,7 +1135,7 @@ void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, { struct ieee80211_chanctx_conf *chanctx_conf; const struct ieee80211_reg_rule *rrule; - struct ieee80211_wmm_ac *wmm_ac; + const struct ieee80211_wmm_ac *wmm_ac; u16 center_freq = 0; if (sdata->vif.type != NL80211_IFTYPE_AP && @@ -1154,20 +1154,19 @@ void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, rrule = freq_reg_info(sdata->wdev.wiphy, MHZ_TO_KHZ(center_freq)); - if (IS_ERR_OR_NULL(rrule) || !rrule->wmm_rule) { + if (IS_ERR_OR_NULL(rrule) || !rrule->has_wmm) { rcu_read_unlock(); return; } if (sdata->vif.type == NL80211_IFTYPE_AP) - wmm_ac = &rrule->wmm_rule->ap[ac]; + wmm_ac = &rrule->wmm_rule.ap[ac]; else - wmm_ac = &rrule->wmm_rule->client[ac]; + wmm_ac = &rrule->wmm_rule.client[ac]; qparam->cw_min = max_t(u16, qparam->cw_min, wmm_ac->cw_min); qparam->cw_max = max_t(u16, qparam->cw_max, wmm_ac->cw_max); qparam->aifs = max_t(u8, qparam->aifs, wmm_ac->aifsn); - qparam->txop = !qparam->txop ? wmm_ac->cot / 32 : - min_t(u16, qparam->txop, wmm_ac->cot / 32); + qparam->txop = min_t(u16, qparam->txop, wmm_ac->cot / 32); rcu_read_unlock(); } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 7a4de6d618b1..8fbe6cdbe255 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1533,10 +1533,14 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, unsigned int flags; if (event == NETDEV_REGISTER) { - /* For now just support Ethernet, IPGRE, SIT and IPIP devices */ + + /* For now just support Ethernet, IPGRE, IP6GRE, SIT and + * IPIP devices + */ if (dev->type == ARPHRD_ETHER || dev->type == ARPHRD_LOOPBACK || dev->type == ARPHRD_IPGRE || + dev->type == ARPHRD_IP6GRE || dev->type == ARPHRD_SIT || dev->type == ARPHRD_TUNNEL) { mdev = mpls_add_dev(dev); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 82e6edf9c5d9..45f33d6dedf7 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -100,7 +100,7 @@ static int ncsi_write_package_info(struct sk_buff *skb, bool found; int rc; - if (id > ndp->package_num) { + if (id > ndp->package_num - 1) { netdev_info(ndp->ndev.dev, "NCSI: No package with id %u\n", id); return -ENODEV; } @@ -240,7 +240,7 @@ static int ncsi_pkg_info_all_nl(struct sk_buff *skb, return 0; /* done */ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - &ncsi_genl_family, 0, NCSI_CMD_PKG_INFO); + &ncsi_genl_family, NLM_F_MULTI, NCSI_CMD_PKG_INFO); if (!hdr) { rc = -EMSGSIZE; goto err; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 71709c104081..f61c306de1d0 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -771,13 +771,13 @@ config NETFILTER_XT_TARGET_CHECKSUM depends on NETFILTER_ADVANCED ---help--- This option adds a `CHECKSUM' target, which can be used in the iptables mangle - table. + table to work around buggy DHCP clients in virtualized environments. - You can use this target to compute and fill in the checksum in - a packet that lacks a checksum. This is particularly useful, - if you need to work around old applications such as dhcp clients, - that do not work well with checksum offloads, but don't want to disable - checksum offload in your device. + Some old DHCP clients drop packets because they are not aware + that the checksum would normally be offloaded to hardware and + thus should be considered valid. + This target can be used to fill in the checksum using iptables + when such packets are sent via a virtual network device. To compile it as a module, choose M here. If unsure, say N. diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 9f14b0df6960..51c5d7eec0a3 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -776,9 +776,26 @@ static const struct nf_hook_ops ipv6_conntrack_ops[] = { }; #endif +static int nf_ct_tcp_fixup(struct nf_conn *ct, void *_nfproto) +{ + u8 nfproto = (unsigned long)_nfproto; + + if (nf_ct_l3num(ct) != nfproto) + return 0; + + if (nf_ct_protonum(ct) == IPPROTO_TCP && + ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED) { + ct->proto.tcp.seen[0].td_maxwin = 0; + ct->proto.tcp.seen[1].td_maxwin = 0; + } + + return 0; +} + static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + bool fixup_needed = false; int err = 0; mutex_lock(&nf_ct_proto_mutex); @@ -798,6 +815,8 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) ARRAY_SIZE(ipv4_conntrack_ops)); if (err) cnet->users4 = 0; + else + fixup_needed = true; break; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: @@ -814,6 +833,8 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) ARRAY_SIZE(ipv6_conntrack_ops)); if (err) cnet->users6 = 0; + else + fixup_needed = true; break; #endif default: @@ -822,6 +843,11 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) } out_unlock: mutex_unlock(&nf_ct_proto_mutex); + + if (fixup_needed) + nf_ct_iterate_cleanup_net(net, nf_ct_tcp_fixup, + (void *)(unsigned long)nfproto, 0, 0); + return err; } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 8c58f96b59e7..f3f91ed2c21a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -675,7 +675,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -697,6 +697,8 @@ static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } + + timeouts[CTA_TIMEOUT_DCCP_UNSPEC] = timeouts[CTA_TIMEOUT_DCCP_REQUEST]; return 0; } @@ -726,7 +728,7 @@ dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { [CTA_TIMEOUT_DCCP_CLOSING] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_TIMEWAIT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL /* template, data assigned later */ @@ -827,6 +829,11 @@ static int dccp_init_net(struct net *net, u_int16_t proto) dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; + + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; } return dccp_kmemdup_sysctl_table(net, pn, dn); @@ -856,7 +863,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, @@ -864,7 +871,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = dccp_init_net, .get_net_proto = dccp_get_net_proto, }; @@ -889,7 +896,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, @@ -897,7 +904,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = dccp_init_net, .get_net_proto = dccp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index ac4a0b296dcd..1df3244ecd07 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -70,7 +70,7 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, return ret; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -113,7 +113,7 @@ static const struct nla_policy generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { [CTA_TIMEOUT_GENERIC_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table generic_sysctl_table[] = { @@ -164,7 +164,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .pkt_to_tuple = generic_pkt_to_tuple, .packet = generic_packet, .new = generic_new, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = generic_timeout_nlattr_to_obj, .obj_to_nlattr = generic_timeout_obj_to_nlattr, @@ -172,7 +172,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .obj_size = sizeof(unsigned int), .nla_policy = generic_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = generic_init_net, .get_net_proto = generic_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index d1632252bf5b..650eb4fba2c5 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -285,7 +285,7 @@ static void gre_destroy(struct nf_conn *ct) nf_ct_gre_keymap_destroy(master); } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -334,7 +334,7 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { [CTA_TIMEOUT_GRE_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_GRE_REPLIED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ static int gre_init_net(struct net *net, u_int16_t proto) { @@ -367,7 +367,7 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = gre_timeout_nlattr_to_obj, .obj_to_nlattr = gre_timeout_obj_to_nlattr, @@ -375,7 +375,7 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .obj_size = sizeof(unsigned int) * GRE_CT_MAX, .nla_policy = gre_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .net_id = &proto_gre_net_id, .init_net = gre_init_net, }; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 036670b38282..43c7e1a217b9 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -273,7 +273,7 @@ static unsigned int icmp_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -313,7 +313,7 @@ static const struct nla_policy icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table icmp_sysctl_table[] = { @@ -374,7 +374,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmp_timeout_nlattr_to_obj, .obj_to_nlattr = icmp_timeout_obj_to_nlattr, @@ -382,7 +382,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .obj_size = sizeof(unsigned int), .nla_policy = icmp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = icmp_init_net, .get_net_proto = icmp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index bed07b998a10..97e40f77d678 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -274,7 +274,7 @@ static unsigned int icmpv6_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -314,7 +314,7 @@ static const struct nla_policy icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table icmpv6_sysctl_table[] = { @@ -373,7 +373,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, @@ -381,7 +381,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .obj_size = sizeof(unsigned int), .nla_policy = icmpv6_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = icmpv6_init_net, .get_net_proto = icmpv6_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 8d1e085fc14a..e4d738d34cd0 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -591,7 +591,7 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -613,6 +613,8 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } + + timeouts[CTA_TIMEOUT_SCTP_UNSPEC] = timeouts[CTA_TIMEOUT_SCTP_CLOSED]; return 0; } @@ -644,7 +646,7 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL @@ -743,6 +745,11 @@ static int sctp_init_net(struct net *net, u_int16_t proto) for (i = 0; i < SCTP_CONNTRACK_MAX; i++) sn->timeouts[i] = sctp_timeouts[i]; + + /* timeouts[0] is unused, init it so ->timeouts[0] contains + * 'new' timeout, like udp or icmp. + */ + sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; } return sctp_kmemdup_sysctl_table(pn, sn); @@ -773,7 +780,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, @@ -781,7 +788,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = sctp_init_net, .get_net_proto = sctp_get_net_proto, }; @@ -806,7 +813,8 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, @@ -814,8 +822,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#endif +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = sctp_init_net, .get_net_proto = sctp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d80d322b9d8b..247b89784a6f 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1213,8 +1213,8 @@ static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = { #define TCP_NLATTR_SIZE ( \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + 1) + \ - NLA_ALIGN(NLA_HDRLEN + sizeof(sizeof(struct nf_ct_tcp_flags))) + \ - NLA_ALIGN(NLA_HDRLEN + sizeof(sizeof(struct nf_ct_tcp_flags)))) + NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags)) + \ + NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags))) static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) { @@ -1279,7 +1279,7 @@ static unsigned int tcp_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -1301,6 +1301,7 @@ static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[TCP_CONNTRACK_SYN_SENT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ; } + if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) { timeouts[TCP_CONNTRACK_SYN_RECV] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ; @@ -1341,6 +1342,8 @@ static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[TCP_CONNTRACK_UNACK] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ; } + + timeouts[CTA_TIMEOUT_TCP_UNSPEC] = timeouts[CTA_TIMEOUT_TCP_SYN_SENT]; return 0; } @@ -1391,7 +1394,7 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { [CTA_TIMEOUT_TCP_RETRANS] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_UNACK] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table tcp_sysctl_table[] = { @@ -1518,6 +1521,10 @@ static int tcp_init_net(struct net *net, u_int16_t proto) for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) tn->timeouts[i] = tcp_timeouts[i]; + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; tn->tcp_loose = nf_ct_tcp_loose; tn->tcp_be_liberal = nf_ct_tcp_be_liberal; tn->tcp_max_retrans = nf_ct_tcp_max_retrans; @@ -1551,7 +1558,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = .nlattr_size = TCP_NLATTR_SIZE, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, @@ -1560,7 +1567,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = tcp_init_net, .get_net_proto = tcp_get_net_proto, }; @@ -1586,7 +1593,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, @@ -1595,7 +1602,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = tcp_init_net, .get_net_proto = tcp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7a1b8988a931..3065fb8ef91b 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -171,7 +171,7 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, return NF_ACCEPT; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -221,7 +221,7 @@ udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { [CTA_TIMEOUT_UDP_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_UDP_REPLIED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table udp_sysctl_table[] = { @@ -292,7 +292,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -300,7 +300,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -321,7 +321,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -329,7 +329,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -350,7 +350,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -358,7 +358,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -379,7 +379,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -387,10 +387,9 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6); #endif -#include <net/netfilter/nf_conntrack_timeout.h> diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1dca5683f59f..2cfb173cd0b2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4637,6 +4637,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; + nft_set_elem_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index d46a236cdf31..a30f8ba4b89a 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -489,8 +489,8 @@ err: return err; } -static struct ctnl_timeout * -ctnl_timeout_find_get(struct net *net, const char *name) +static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net, + const char *name) { struct ctnl_timeout *timeout, *matching = NULL; @@ -509,7 +509,7 @@ ctnl_timeout_find_get(struct net *net, const char *name) break; } err: - return matching; + return matching ? &matching->timeout : NULL; } static void ctnl_timeout_put(struct nf_ct_timeout *t) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea4ba551abb2..d33094f4ec41 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -233,6 +233,7 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) int err; if (verdict == NF_ACCEPT || + verdict == NF_REPEAT || verdict == NF_STOP) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 26a8baebd072..5dd87748afa8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -799,7 +799,7 @@ err: } struct nft_ct_timeout_obj { - struct nf_conn *tmpl; + struct nf_ct_timeout *timeout; u8 l4proto; }; @@ -809,26 +809,42 @@ static void nft_ct_timeout_obj_eval(struct nft_object *obj, { const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb); - struct sk_buff *skb = pkt->skb; + struct nf_conn_timeout *timeout; + const unsigned int *values; + + if (priv->l4proto != pkt->tprot) + return; - if (ct || - priv->l4proto != pkt->tprot) + if (!ct || nf_ct_is_template(ct) || nf_ct_is_confirmed(ct)) return; - nf_ct_set(skb, priv->tmpl, IP_CT_NEW); + timeout = nf_ct_timeout_find(ct); + if (!timeout) { + timeout = nf_ct_timeout_ext_add(ct, priv->timeout, GFP_ATOMIC); + if (!timeout) { + regs->verdict.code = NF_DROP; + return; + } + } + + rcu_assign_pointer(timeout->timeout, priv->timeout); + + /* adjust the timeout as per 'new' state. ct is unconfirmed, + * so the current timestamp must not be added. + */ + values = nf_ct_timeout_data(timeout); + if (values) + nf_ct_refresh(ct, pkt->skb, values[0]); } static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) { - const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; struct nft_ct_timeout_obj *priv = nft_obj_data(obj); const struct nf_conntrack_l4proto *l4proto; - struct nf_conn_timeout *timeout_ext; struct nf_ct_timeout *timeout; int l3num = ctx->family; - struct nf_conn *tmpl; __u8 l4num; int ret; @@ -863,28 +879,14 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, timeout->l3num = l3num; timeout->l4proto = l4proto; - tmpl = nf_ct_tmpl_alloc(ctx->net, zone, GFP_ATOMIC); - if (!tmpl) { - ret = -ENOMEM; - goto err_free_timeout; - } - - timeout_ext = nf_ct_timeout_ext_add(tmpl, timeout, GFP_ATOMIC); - if (!timeout_ext) { - ret = -ENOMEM; - goto err_free_tmpl; - } ret = nf_ct_netns_get(ctx->net, ctx->family); if (ret < 0) - goto err_free_tmpl; - - priv->tmpl = tmpl; + goto err_free_timeout; + priv->timeout = timeout; return 0; -err_free_tmpl: - nf_ct_tmpl_free(tmpl); err_free_timeout: kfree(timeout); err_proto_put: @@ -896,22 +898,19 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { struct nft_ct_timeout_obj *priv = nft_obj_data(obj); - struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); - struct nf_ct_timeout *timeout; + struct nf_ct_timeout *timeout = priv->timeout; - timeout = rcu_dereference_raw(t->timeout); nf_ct_untimeout(ctx->net, timeout); nf_ct_l4proto_put(timeout->l4proto); nf_ct_netns_put(ctx->net, ctx->family); - nf_ct_tmpl_free(priv->tmpl); + kfree(priv->timeout); } static int nft_ct_timeout_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); - const struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); - const struct nf_ct_timeout *timeout = rcu_dereference_raw(t->timeout); + const struct nf_ct_timeout *timeout = priv->timeout; struct nlattr *nest_params; int ret; diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 5af74b37f423..a35fb59ace73 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -49,7 +49,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFTA_DATA_VALUE, NFT_OSF_MAXGENRELEN); + NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN); if (err < 0) return err; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 55e2d9215c0d..0e5ec126f6ad 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -355,12 +355,11 @@ cont: static void nft_rbtree_gc(struct work_struct *work) { + struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL; struct nft_set_gc_batch *gcb = NULL; - struct rb_node *node, *prev = NULL; - struct nft_rbtree_elem *rbe; struct nft_rbtree *priv; + struct rb_node *node; struct nft_set *set; - int i; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); @@ -371,7 +370,7 @@ static void nft_rbtree_gc(struct work_struct *work) rbe = rb_entry(node, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe)) { - prev = node; + rbe_end = rbe; continue; } if (!nft_set_elem_expired(&rbe->ext)) @@ -379,29 +378,30 @@ static void nft_rbtree_gc(struct work_struct *work) if (nft_set_elem_mark_busy(&rbe->ext)) continue; + if (rbe_prev) { + rb_erase(&rbe_prev->node, &priv->root); + rbe_prev = NULL; + } gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (!gcb) break; atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); + rbe_prev = rbe; - if (prev) { - rbe = rb_entry(prev, struct nft_rbtree_elem, node); + if (rbe_end) { atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe); - prev = NULL; + nft_set_gc_batch_add(gcb, rbe_end); + rb_erase(&rbe_end->node, &priv->root); + rbe_end = NULL; } node = rb_next(node); if (!node) break; } - if (gcb) { - for (i = 0; i < gcb->head.cnt; i++) { - rbe = gcb->elems[i]; - rb_erase(&rbe->node, &priv->root); - } - } + if (rbe_prev) + rb_erase(&rbe_prev->node, &priv->root); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); diff --git a/net/netfilter/xt_CHECKSUM.c b/net/netfilter/xt_CHECKSUM.c index 9f4151ec3e06..6c7aa6a0a0d2 100644 --- a/net/netfilter/xt_CHECKSUM.c +++ b/net/netfilter/xt_CHECKSUM.c @@ -16,6 +16,9 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_CHECKSUM.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michael S. Tsirkin <mst@redhat.com>"); MODULE_DESCRIPTION("Xtables: checksum modification"); @@ -25,7 +28,7 @@ MODULE_ALIAS("ip6t_CHECKSUM"); static unsigned int checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) { - if (skb->ip_summed == CHECKSUM_PARTIAL) + if (skb->ip_summed == CHECKSUM_PARTIAL && !skb_is_gso(skb)) skb_checksum_help(skb); return XT_CONTINUE; @@ -34,6 +37,8 @@ checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) static int checksum_tg_check(const struct xt_tgchk_param *par) { const struct xt_CHECKSUM_info *einfo = par->targinfo; + const struct ip6t_ip6 *i6 = par->entryinfo; + const struct ipt_ip *i4 = par->entryinfo; if (einfo->operation & ~XT_CHECKSUM_OP_FILL) { pr_info_ratelimited("unsupported CHECKSUM operation %x\n", @@ -43,6 +48,21 @@ static int checksum_tg_check(const struct xt_tgchk_param *par) if (!einfo->operation) return -EINVAL; + switch (par->family) { + case NFPROTO_IPV4: + if (i4->proto == IPPROTO_UDP && + (i4->invflags & XT_INV_PROTO) == 0) + return 0; + break; + case NFPROTO_IPV6: + if ((i6->flags & IP6T_F_PROTO) && + i6->proto == IPPROTO_UDP && + (i6->invflags & XT_INV_PROTO) == 0) + return 0; + break; + } + + pr_warn_once("CHECKSUM should be avoided. If really needed, restrict with \"-p udp\" and only use in OUTPUT\n"); return 0; } diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index dfbdbb2fc0ed..51d0c257e7a5 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -125,6 +125,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par) static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) { struct xt_cluster_match_info *info = par->matchinfo; + int ret; if (info->total_nodes > XT_CLUSTER_NODES_MAX) { pr_info_ratelimited("you have exceeded the maximum number of cluster nodes (%u > %u)\n", @@ -135,7 +136,17 @@ static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) pr_info_ratelimited("node mask cannot exceed total number of nodes\n"); return -EDOM; } - return 0; + + ret = nf_ct_netns_get(par->net, par->family); + if (ret < 0) + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); + return ret; +} + +static void xt_cluster_mt_destroy(const struct xt_mtdtor_param *par) +{ + nf_ct_netns_put(par->net, par->family); } static struct xt_match xt_cluster_match __read_mostly = { @@ -144,6 +155,7 @@ static struct xt_match xt_cluster_match __read_mostly = { .match = xt_cluster_mt, .checkentry = xt_cluster_mt_checkentry, .matchsize = sizeof(struct xt_cluster_match_info), + .destroy = xt_cluster_mt_destroy, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 9b16402f29af..3e7d259e5d8d 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -1057,7 +1057,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket; spin_lock_bh(&htable->lock); @@ -1074,7 +1074,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos) static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; *pos = ++(*bucket); @@ -1088,7 +1088,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; if (!IS_ERR(bucket)) @@ -1130,7 +1130,7 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1145,7 +1145,7 @@ static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1160,7 +1160,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1174,7 +1174,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_show_v2(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; @@ -1188,7 +1188,7 @@ static int dl_seq_show_v2(struct seq_file *s, void *v) static int dl_seq_show_v1(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; @@ -1202,7 +1202,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v) static int dl_seq_show(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 0472f3472842..ada144e5645b 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -56,7 +56,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; - if (!net_eq(xt_net(par), sock_net(sk))) + if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) @@ -117,7 +117,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; - if (!net_eq(xt_net(par), sock_net(sk))) + if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index c070dfc0190a..c92894c3e40a 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -781,7 +781,8 @@ static int netlbl_unlabel_addrinfo_get(struct genl_info *info, { u32 addr_len; - if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR]) { + if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR] && + info->attrs[NLBL_UNLABEL_A_IPV4MASK]) { addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]); if (addr_len != sizeof(struct in_addr) && addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV4MASK])) diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index ac8030c4bcf8..19cb2e473ea6 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -209,6 +209,11 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, } create_info = (struct hci_create_pipe_resp *)skb->data; + if (create_info->pipe >= NFC_HCI_MAX_PIPES) { + status = NFC_HCI_ANY_E_NOK; + goto exit; + } + /* Save the new created pipe and bind with local gate, * the description for skb->data[3] is destination gate id * but since we received this cmd from host controller, we @@ -232,6 +237,11 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, } delete_info = (struct hci_delete_pipe_noti *)skb->data; + if (delete_info->pipe >= NFC_HCI_MAX_PIPES) { + status = NFC_HCI_ANY_E_NOK; + goto exit; + } + hdev->pipes[delete_info->pipe].gate = NFC_HCI_INVALID_GATE; hdev->pipes[delete_info->pipe].dest_host = NFC_HCI_INVALID_HOST; break; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 86a75105af1a..35ae64cbef33 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1312,6 +1312,10 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, rcu_assign_pointer(help->helper, helper); info->helper = helper; + + if (info->nat) + request_module("ip_nat_%s", name); + return 0; } @@ -1624,10 +1628,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, OVS_NLERR(log, "Failed to allocate conntrack template"); return -ENOMEM; } - - __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); - nf_conntrack_get(&ct_info.ct->ct_general); - if (helper) { err = ovs_ct_add_helper(&ct_info, helper, key, log); if (err) @@ -1639,6 +1639,8 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (err) goto err_free_ct; + __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); + nf_conntrack_get(&ct_info.ct->ct_general); return 0; err_free_ct: __ovs_ct_free_action(&ct_info); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5610061e7f2e..d6e94dc7e290 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2715,10 +2715,12 @@ tpacket_error: } } - if (po->has_vnet_hdr && virtio_net_hdr_to_skb(skb, vnet_hdr, - vio_le())) { - tp_len = -EINVAL; - goto tpacket_error; + if (po->has_vnet_hdr) { + if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { + tp_len = -EINVAL; + goto tpacket_error; + } + virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; @@ -2915,6 +2917,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (err) goto out_free; len += sizeof(vnet_hdr); + virtio_net_hdr_set_proto(skb, &vnet_hdr); } skb_probe_transport_header(skb, reserve); @@ -4137,36 +4140,52 @@ static const struct vm_operations_struct packet_mmap_ops = { .close = packet_mm_close, }; -static void free_pg_vec(struct pgv *pg_vec, unsigned int len) +static void free_pg_vec(struct pgv *pg_vec, unsigned int order, + unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { - kvfree(pg_vec[i].buffer); + if (is_vmalloc_addr(pg_vec[i].buffer)) + vfree(pg_vec[i].buffer); + else + free_pages((unsigned long)pg_vec[i].buffer, + order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } -static char *alloc_one_pg_vec_page(unsigned long size) +static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; + gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | + __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; - buffer = kvzalloc(size, GFP_KERNEL); + buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; - buffer = kvzalloc(size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + /* __get_free_pages failed, fall back to vmalloc */ + buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); + if (buffer) + return buffer; + + /* vmalloc failed, lets dig into swap here */ + gfp_flags &= ~__GFP_NORETRY; + buffer = (char *) __get_free_pages(gfp_flags, order); + if (buffer) + return buffer; - return buffer; + /* complete and utter failure */ + return NULL; } -static struct pgv *alloc_pg_vec(struct tpacket_req *req) +static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; - unsigned long size = req->tp_block_size; struct pgv *pg_vec; int i; @@ -4175,7 +4194,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req) goto out; for (i = 0; i < block_nr; i++) { - pg_vec[i].buffer = alloc_one_pg_vec_page(size); + pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } @@ -4184,7 +4203,7 @@ out: return pg_vec; out_free_pgvec: - free_pg_vec(pg_vec, block_nr); + free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } @@ -4194,9 +4213,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); + int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; - int was_running; __be16 num; int err = -EINVAL; /* Added to avoid minimal code churn */ @@ -4258,7 +4277,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; err = -ENOMEM; - pg_vec = alloc_pg_vec(req); + order = get_order(req->tp_block_size); + pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { @@ -4312,6 +4332,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); + swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; @@ -4337,7 +4358,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } if (pg_vec) - free_pg_vec(pg_vec, req->tp_block_nr); + free_pg_vec(pg_vec, order, req->tp_block_nr); out: return err; } diff --git a/net/packet/internal.h b/net/packet/internal.h index 8f50036f62f0..3bb7c5fb3bff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -64,6 +64,7 @@ struct packet_ring_buffer { unsigned int frame_size; unsigned int frame_max; + unsigned int pg_vec_order; unsigned int pg_vec_pages; unsigned int pg_vec_len; diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 01b3bd6a3708..b9092111bc45 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -1,6 +1,6 @@ config RDS - tristate "The RDS Protocol" + tristate "The Reliable Datagram Sockets Protocol" depends on INET ---help--- The RDS (Reliable Datagram Sockets) protocol provides reliable, diff --git a/net/rds/bind.c b/net/rds/bind.c index 3ab55784b637..762d2c6788a3 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -76,11 +76,13 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, struct rds_sock *rs; __rds_create_bind_key(key, addr, port, scope_id); - rs = rhashtable_lookup_fast(&bind_hash_table, key, ht_parms); + rcu_read_lock(); + rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) rds_sock_addref(rs); else rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, ntohs(port)); @@ -235,6 +237,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } + sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) goto out; diff --git a/net/rds/ib.c b/net/rds/ib.c index c1d97640c0be..eba75c1ba359 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -341,15 +341,10 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; - struct rdma_dev_addr *dev_addr; ic = conn->c_transport_data; - dev_addr = &ic->i_cm_id->route.addr.dev_addr; - rdma_addr_get_sgid(dev_addr, - (union ib_gid *)&iinfo6->src_gid); - rdma_addr_get_dgid(dev_addr, - (union ib_gid *)&iinfo6->dst_gid); - + rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo6->src_gid, + (union ib_gid *)&iinfo6->dst_gid); rds_ibdev = ic->rds_ibdev; iinfo6->max_send_wr = ic->i_send_ring.w_nr; iinfo6->max_recv_wr = ic->i_recv_ring.w_nr; diff --git a/net/rds/ib.h b/net/rds/ib.h index 73427ff439f9..71ff356ee702 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -443,7 +443,7 @@ int rds_ib_send_grab_credits(struct rds_ib_connection *ic, u32 wanted, int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op); /* ib_stats.c */ -DECLARE_PER_CPU(struct rds_ib_statistics, rds_ib_stats); +DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_ib_statistics, rds_ib_stats); #define rds_ib_stats_inc(member) rds_stats_inc_which(rds_ib_stats, member) #define rds_ib_stats_add(member, count) \ rds_stats_add_which(rds_ib_stats, member, count) diff --git a/net/rds/send.c b/net/rds/send.c index 57b3d5a8b2db..fe785ee819dd 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1007,7 +1007,8 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, return ret; } -static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn) +static int rds_send_mprds_hash(struct rds_sock *rs, + struct rds_connection *conn, int nonblock) { int hash; @@ -1023,10 +1024,16 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn) * used. But if we are interrupted, we have to use the zero * c_path in case the connection ends up being non-MP capable. */ - if (conn->c_npaths == 0) + if (conn->c_npaths == 0) { + /* Cannot wait for the connection be made, so just use + * the base c_path. + */ + if (nonblock) + return 0; if (wait_event_interruptible(conn->c_hs_waitq, conn->c_npaths != 0)) hash = 0; + } if (conn->c_npaths == 1) hash = 0; } @@ -1256,7 +1263,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) } if (conn->c_trans->t_mp_capable) - cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; + cpath = &conn->c_path[rds_send_mprds_hash(rs, conn, nonblock)]; else cpath = &conn->c_path[0]; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 2c7b7c352d3e..b9bbcf3d6c63 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -37,7 +37,6 @@ #include <net/tcp.h> #include <net/net_namespace.h> #include <net/netns/generic.h> -#include <net/tcp.h> #include <net/addrconf.h> #include "rds.h" diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 00192a996be0..0f8465852254 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/mod_devicetable.h> #include <linux/rfkill.h> #include <linux/platform_device.h> #include <linux/clk.h> diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c97558710421..a6e6cae82c30 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -40,17 +40,12 @@ struct rxrpc_crypt { struct rxrpc_connection; /* - * Mark applied to socket buffers. + * Mark applied to socket buffers in skb->mark. skb->priority is used + * to pass supplementary information. */ enum rxrpc_skb_mark { - RXRPC_SKB_MARK_DATA, /* data message */ - RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */ - RXRPC_SKB_MARK_BUSY, /* server busy message */ - RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */ - RXRPC_SKB_MARK_LOCAL_ABORT, /* local abort message */ - RXRPC_SKB_MARK_NET_ERROR, /* network error message */ - RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */ - RXRPC_SKB_MARK_NEW_CALL, /* local error message */ + RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ + RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ }; /* @@ -293,7 +288,6 @@ struct rxrpc_peer { struct hlist_node hash_link; struct rxrpc_local *local; struct hlist_head error_targets; /* targets for net error distribution */ - struct work_struct error_distributor; struct rb_root service_conns; /* Service connections */ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ time64_t last_tx_at; /* Last time packet sent here */ @@ -304,12 +298,11 @@ struct rxrpc_peer { unsigned int maxdata; /* data size (MTU - hdrsize) */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ int debug_id; /* debug ID for printks */ - int error_report; /* Net (+0) or local (+1000000) to distribute */ -#define RXRPC_LOCAL_ERROR_OFFSET 1000000 struct sockaddr_rxrpc srx; /* remote address */ /* calculated RTT cache */ #define RXRPC_RTT_CACHE_SIZE 32 + spinlock_t rtt_input_lock; /* RTT lock for input routine */ ktime_t rtt_last_req; /* Time of last RTT request */ u64 rtt; /* Current RTT estimate (in nS) */ u64 rtt_sum; /* Sum of cache contents */ @@ -450,19 +443,29 @@ struct rxrpc_connection { spinlock_t state_lock; /* state-change lock */ enum rxrpc_conn_cache_state cache_state; enum rxrpc_conn_proto_state state; /* current state of connection */ - u32 local_abort; /* local abort code */ - u32 remote_abort; /* remote abort code */ + u32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ atomic_t serial; /* packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ u32 security_nonce; /* response re-use preventer */ - u16 service_id; /* Service ID, possibly upgraded */ + u32 service_id; /* Service ID, possibly upgraded */ u8 size_align; /* data size alignment (for security) */ u8 security_size; /* security header size */ u8 security_ix; /* security type */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ + short error; /* Local error code */ }; +static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp) +{ + return sp->hdr.flags & RXRPC_CLIENT_INITIATED; +} + +static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp) +{ + return !rxrpc_to_server(sp); +} + /* * Flags in call->flags. */ @@ -633,6 +636,8 @@ struct rxrpc_call { bool tx_phase; /* T if transmission phase, F if receive phase */ u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */ + spinlock_t input_lock; /* Lock for packet input to this call */ + /* receive-phase ACK management */ u8 ackr_reason; /* reason to ACK */ u16 ackr_skew; /* skew on packet being ACK'd */ @@ -717,7 +722,7 @@ extern struct workqueue_struct *rxrpc_workqueue; int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, - struct rxrpc_connection *, + struct rxrpc_sock *, struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long, @@ -887,8 +892,9 @@ extern unsigned long rxrpc_conn_idle_client_fast_expiry; extern struct idr rxrpc_client_conn_ids; void rxrpc_destroy_client_conn_ids(void); -int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *, - struct sockaddr_rxrpc *, gfp_t); +int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, + struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, + gfp_t); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_call *); void rxrpc_put_client_conn(struct rxrpc_connection *); @@ -908,7 +914,8 @@ extern unsigned int rxrpc_closed_conn_expiry; struct rxrpc_connection *rxrpc_alloc_connection(gfp_t); struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, - struct sk_buff *); + struct sk_buff *, + struct rxrpc_peer **); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_connection(struct rxrpc_connection *); @@ -960,7 +967,7 @@ void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ -void rxrpc_data_ready(struct sock *); +int rxrpc_input_packet(struct sock *, struct sk_buff *); /* * insecure.c @@ -1031,7 +1038,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *); * peer_event.c */ void rxrpc_error_report(struct sock *); -void rxrpc_peer_error_distributor(struct work_struct *); void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); void rxrpc_peer_keepalive_worker(struct work_struct *); @@ -1041,16 +1047,15 @@ void rxrpc_peer_keepalive_worker(struct work_struct *); */ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); -struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *, +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *, struct sockaddr_rxrpc *, gfp_t); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); -struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *, - struct rxrpc_peer *); +void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *, + struct rxrpc_peer *); void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); -void __rxrpc_queue_peer_error(struct rxrpc_peer *); /* * proc.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 9d1e298b784c..652e314de38e 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -249,11 +249,11 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) */ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_local *local, + struct rxrpc_peer *peer, struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_backlog *b = rx->backlog; - struct rxrpc_peer *peer, *xpeer; struct rxrpc_call *call; unsigned short call_head, conn_head, peer_head; unsigned short call_tail, conn_tail, peer_tail; @@ -276,21 +276,18 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, return NULL; if (!conn) { - /* No connection. We're going to need a peer to start off - * with. If one doesn't yet exist, use a spare from the - * preallocation set. We dump the address into the spare in - * anticipation - and to save on stack space. - */ - xpeer = b->peer_backlog[peer_tail]; - if (rxrpc_extract_addr_from_skb(local, &xpeer->srx, skb) < 0) - return NULL; - - peer = rxrpc_lookup_incoming_peer(local, xpeer); - if (peer == xpeer) { + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (!peer) { + peer = b->peer_backlog[peer_tail]; + if (rxrpc_extract_addr_from_skb(local, &peer->srx, skb) < 0) + return NULL; b->peer_backlog[peer_tail] = NULL; smp_store_release(&b->peer_backlog_tail, (peer_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); + + rxrpc_new_incoming_peer(rx, local, peer); } /* Now allocate and set up the connection */ @@ -335,45 +332,38 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, * The call is returned with the user access mutex held. */ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, - struct rxrpc_connection *conn, + struct rxrpc_sock *rx, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_sock *rx; + struct rxrpc_connection *conn; + struct rxrpc_peer *peer; struct rxrpc_call *call; - u16 service_id = sp->hdr.serviceId; _enter(""); - /* Get the socket providing the service */ - rx = rcu_dereference(local->service); - if (rx && (service_id == rx->srx.srx_service || - service_id == rx->second_service)) - goto found_service; - - trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EOPNOTSUPP); - skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; - skb->priority = RX_INVALID_OPERATION; - _leave(" = NULL [service]"); - return NULL; - -found_service: spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); - skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; skb->priority = RX_INVALID_OPERATION; _leave(" = NULL [close]"); call = NULL; goto out; } - call = rxrpc_alloc_incoming_call(rx, local, conn, skb); + /* The peer, connection and call may all have sprung into existence due + * to a duplicate packet being handled on another CPU in parallel, so + * we have to recheck the routing. However, we're now holding + * rx->incoming_lock, so the values should remain stable. + */ + conn = rxrpc_find_connection_rcu(local, skb, &peer); + + call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb); if (!call) { - skb->mark = RXRPC_SKB_MARK_BUSY; + skb->mark = RXRPC_SKB_MARK_REJECT_BUSY; _leave(" = NULL [busy]"); call = NULL; goto out; @@ -413,20 +403,22 @@ found_service: case RXRPC_CONN_SERVICE: write_lock(&call->state_lock); - if (rx->discard_new_call) - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - else - call->state = RXRPC_CALL_SERVER_ACCEPTING; + if (call->state < RXRPC_CALL_COMPLETE) { + if (rx->discard_new_call) + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; + else + call->state = RXRPC_CALL_SERVER_ACCEPTING; + } write_unlock(&call->state_lock); break; case RXRPC_CONN_REMOTELY_ABORTED: rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, - conn->remote_abort, -ECONNABORTED); + conn->abort_code, conn->error); break; case RXRPC_CONN_LOCALLY_ABORTED: rxrpc_abort_call("CON", call, sp->hdr.seq, - conn->local_abort, -ECONNABORTED); + conn->abort_code, conn->error); break; default: BUG(); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 9486293fef5c..8f1a8f85b1f9 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -138,6 +138,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); spin_lock_init(&call->notify_lock); + spin_lock_init(&call->input_lock); rwlock_init(&call->state_lock); atomic_set(&call->usage, 1); call->debug_id = debug_id; @@ -287,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, /* Set up or get a connection record and set the protocol parameters, * including channel number and call ID. */ - ret = rxrpc_connect_call(call, cp, srx, gfp); + ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) goto error; @@ -339,7 +340,7 @@ int rxrpc_retry_client_call(struct rxrpc_sock *rx, /* Set up or get a connection record and set the protocol parameters, * including channel number and call ID. */ - ret = rxrpc_connect_call(call, cp, srx, gfp); + ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) goto error; @@ -400,7 +401,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, rcu_assign_pointer(conn->channels[chan].call, call); spin_lock(&conn->params.peer->lock); - hlist_add_head(&call->error_link, &conn->params.peer->error_targets); + hlist_add_head_rcu(&call->error_link, &conn->params.peer->error_targets); spin_unlock(&conn->params.peer->lock); _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index f8f37188a932..521189f4b666 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -276,7 +276,8 @@ dont_reuse: * If we return with a connection, the call will be on its waiting list. It's * left to the caller to assign a channel and wake up the call. */ -static int rxrpc_get_client_conn(struct rxrpc_call *call, +static int rxrpc_get_client_conn(struct rxrpc_sock *rx, + struct rxrpc_call *call, struct rxrpc_conn_parameters *cp, struct sockaddr_rxrpc *srx, gfp_t gfp) @@ -289,7 +290,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp); + cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp); if (!cp->peer) goto error; @@ -683,7 +684,8 @@ out: * find a connection for a call * - called in process context with IRQs enabled */ -int rxrpc_connect_call(struct rxrpc_call *call, +int rxrpc_connect_call(struct rxrpc_sock *rx, + struct rxrpc_call *call, struct rxrpc_conn_parameters *cp, struct sockaddr_rxrpc *srx, gfp_t gfp) @@ -696,7 +698,7 @@ int rxrpc_connect_call(struct rxrpc_call *call, rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper); rxrpc_cull_active_client_conns(rxnet); - ret = rxrpc_get_client_conn(call, cp, srx, gfp); + ret = rxrpc_get_client_conn(rx, call, cp, srx, gfp); if (ret < 0) goto out; @@ -710,8 +712,8 @@ int rxrpc_connect_call(struct rxrpc_call *call, } spin_lock_bh(&call->conn->params.peer->lock); - hlist_add_head(&call->error_link, - &call->conn->params.peer->error_targets); + hlist_add_head_rcu(&call->error_link, + &call->conn->params.peer->error_targets); spin_unlock_bh(&call->conn->params.peer->lock); out: diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 6df56ce68861..b6fca8ebb117 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -126,7 +126,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, switch (chan->last_type) { case RXRPC_PACKET_TYPE_ABORT: - _proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort); + _proto("Tx ABORT %%%u { %d } [re]", serial, conn->abort_code); break; case RXRPC_PACKET_TYPE_ACK: trace_rxrpc_tx_ack(chan->call_debug_id, serial, @@ -153,13 +153,12 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, * pass a connection-level abort onto all calls on that connection */ static void rxrpc_abort_calls(struct rxrpc_connection *conn, - enum rxrpc_call_completion compl, - u32 abort_code, int error) + enum rxrpc_call_completion compl) { struct rxrpc_call *call; int i; - _enter("{%d},%x", conn->debug_id, abort_code); + _enter("{%d},%x", conn->debug_id, conn->abort_code); spin_lock(&conn->channel_lock); @@ -172,9 +171,11 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, trace_rxrpc_abort(call->debug_id, "CON", call->cid, call->call_id, 0, - abort_code, error); + conn->abort_code, + conn->error); if (rxrpc_set_call_completion(call, compl, - abort_code, error)) + conn->abort_code, + conn->error)) rxrpc_notify_socket(call); } } @@ -207,10 +208,12 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, return 0; } + conn->error = error; + conn->abort_code = abort_code; conn->state = RXRPC_CONN_LOCALLY_ABORTED; spin_unlock_bh(&conn->state_lock); - rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code, error); + rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED); msg.msg_name = &conn->params.peer->srx.transport; msg.msg_namelen = conn->params.peer->srx.transport_len; @@ -229,7 +232,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, whdr._rsvd = 0; whdr.serviceId = htons(conn->service_id); - word = htonl(conn->local_abort); + word = htonl(conn->abort_code); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); @@ -240,7 +243,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); - _proto("Tx CONN ABORT %%%u { %d }", serial, conn->local_abort); + _proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { @@ -315,9 +318,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, abort_code = ntohl(wtmp); _proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code); + conn->error = -ECONNABORTED; + conn->abort_code = abort_code; conn->state = RXRPC_CONN_REMOTELY_ABORTED; - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, - abort_code, -ECONNABORTED); + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED); return -ECONNABORTED; case RXRPC_PACKET_TYPE_CHALLENGE: diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 77440a356b14..885dae829f4a 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -69,10 +69,14 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) * If successful, a pointer to the connection is returned, but no ref is taken. * NULL is returned if there is no match. * + * When searching for a service call, if we find a peer but no connection, we + * return that through *_peer in case we need to create a new service call. + * * The caller must be holding the RCU read lock. */ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, - struct sk_buff *skb) + struct sk_buff *skb, + struct rxrpc_peer **_peer) { struct rxrpc_connection *conn; struct rxrpc_conn_proto k; @@ -85,9 +89,6 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0) goto not_found; - k.epoch = sp->hdr.epoch; - k.cid = sp->hdr.cid & RXRPC_CIDMASK; - /* We may have to handle mixing IPv4 and IPv6 */ if (srx.transport.family != local->srx.transport.family) { pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n", @@ -99,7 +100,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, k.epoch = sp->hdr.epoch; k.cid = sp->hdr.cid & RXRPC_CIDMASK; - if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) { + if (rxrpc_to_server(sp)) { /* We need to look up service connections by the full protocol * parameter set. We look up the peer first as an intermediate * step and then the connection from the peer's tree. @@ -107,6 +108,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, peer = rxrpc_lookup_peer_rcu(local, &srx); if (!peer) goto not_found; + *_peer = peer; conn = rxrpc_find_service_conn_rcu(peer, skb); if (!conn || atomic_read(&conn->usage) == 0) goto not_found; @@ -214,7 +216,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_cwnd = call->cong_cwnd; spin_lock_bh(&conn->params.peer->lock); - hlist_del_init(&call->error_link); + hlist_del_rcu(&call->error_link); spin_unlock_bh(&conn->params.peer->lock); if (rxrpc_is_client_call(call)) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index cfdc199c6351..570b49d2da42 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -216,10 +216,11 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb, /* * Apply a hard ACK by advancing the Tx window. */ -static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, +static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, struct rxrpc_ack_summary *summary) { struct sk_buff *skb, *list = NULL; + bool rot_last = false; int ix; u8 annotation; @@ -243,15 +244,17 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, skb->next = list; list = skb; - if (annotation & RXRPC_TX_ANNO_LAST) + if (annotation & RXRPC_TX_ANNO_LAST) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); + rot_last = true; + } if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK) summary->nr_rot_new_acks++; } spin_unlock(&call->lock); - trace_rxrpc_transmit(call, (test_bit(RXRPC_CALL_TX_LAST, &call->flags) ? + trace_rxrpc_transmit(call, (rot_last ? rxrpc_transmit_rotate_last : rxrpc_transmit_rotate)); wake_up(&call->waitq); @@ -262,6 +265,8 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, skb->next = NULL; rxrpc_free_skb(skb, rxrpc_skb_tx_freed); } + + return rot_last; } /* @@ -273,23 +278,26 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, const char *abort_why) { + unsigned int state; ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); write_lock(&call->state_lock); - switch (call->state) { + state = call->state; + switch (state) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: if (reply_begun) - call->state = RXRPC_CALL_CLIENT_RECV_REPLY; + call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY; else - call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY; break; case RXRPC_CALL_SERVER_AWAIT_ACK: __rxrpc_call_completed(call); rxrpc_notify_socket(call); + state = call->state; break; default: @@ -297,11 +305,10 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, } write_unlock(&call->state_lock); - if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) { + if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); - } else { + else trace_rxrpc_transmit(call, rxrpc_transmit_end); - } _leave(" = ok"); return true; @@ -332,11 +339,11 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); } - if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) - rxrpc_rotate_tx_window(call, top, &summary); if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { - rxrpc_proto_abort("TXL", call, top); - return false; + if (!rxrpc_rotate_tx_window(call, top, &summary)) { + rxrpc_proto_abort("TXL", call, top); + return false; + } } if (!rxrpc_end_tx_phase(call, true, "ETD")) return false; @@ -452,13 +459,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, } } + spin_lock(&call->input_lock); + /* Received data implicitly ACKs all of the request packets we sent * when we're acting as a client. */ if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) - return; + goto unlock; call->ackr_prev_seq = seq; @@ -488,12 +497,16 @@ next_subpacket: if (flags & RXRPC_LAST_PACKET) { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) - return rxrpc_proto_abort("LSN", call, seq); + seq != call->rx_top) { + rxrpc_proto_abort("LSN", call, seq); + goto unlock; + } } else { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) - return rxrpc_proto_abort("LSA", call, seq); + after_eq(seq, call->rx_top)) { + rxrpc_proto_abort("LSA", call, seq); + goto unlock; + } } trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); @@ -560,8 +573,10 @@ next_subpacket: skip: offset += len; if (flags & RXRPC_JUMBO_PACKET) { - if (skb_copy_bits(skb, offset, &flags, 1) < 0) - return rxrpc_proto_abort("XJF", call, seq); + if (skb_copy_bits(skb, offset, &flags, 1) < 0) { + rxrpc_proto_abort("XJF", call, seq); + goto unlock; + } offset += sizeof(struct rxrpc_jumbo_header); seq++; serial++; @@ -601,6 +616,9 @@ ack: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); } + +unlock: + spin_unlock(&call->input_lock); _leave(" [queued]"); } @@ -622,13 +640,14 @@ static void rxrpc_input_requested_ack(struct rxrpc_call *call, if (!skb) continue; + sent_at = skb->tstamp; + smp_rmb(); /* Read timestamp before serial. */ sp = rxrpc_skb(skb); if (sp->hdr.serial != orig_serial) continue; - smp_rmb(); - sent_at = skb->tstamp; goto found; } + return; found: @@ -686,15 +705,14 @@ static void rxrpc_input_ping_response(struct rxrpc_call *call, ping_time = call->ping_time; smp_rmb(); - ping_serial = call->ping_serial; + ping_serial = READ_ONCE(call->ping_serial); if (orig_serial == call->acks_lost_ping) rxrpc_input_check_for_lost_ack(call); - if (!test_bit(RXRPC_CALL_PINGING, &call->flags) || - before(orig_serial, ping_serial)) + if (before(orig_serial, ping_serial) || + !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags)) return; - clear_bit(RXRPC_CALL_PINGING, &call->flags); if (after(orig_serial, ping_serial)) return; @@ -860,15 +878,32 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, rxrpc_propose_ack_respond_to_ack); } + /* Discard any out-of-order or duplicate ACKs. */ + if (before_eq(sp->hdr.serial, call->acks_latest)) + return; + + buf.info.rxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(buf.info)) { - if (skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); + if (skb->len >= ioffset + sizeof(buf.info) && + skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) + return rxrpc_proto_abort("XAI", call, 0); + + spin_lock(&call->input_lock); + + /* Discard any out-of-order or duplicate ACKs. */ + if (before_eq(sp->hdr.serial, call->acks_latest)) + goto out; + call->acks_latest_ts = skb->tstamp; + call->acks_latest = sp->hdr.serial; + + /* Parse rwind and mtu sizes if provided. */ + if (buf.info.rxMTU) rxrpc_input_ackinfo(call, skb, &buf.info); - } - if (first_soft_ack == 0) - return rxrpc_proto_abort("AK0", call, 0); + if (first_soft_ack == 0) { + rxrpc_proto_abort("AK0", call, 0); + goto out; + } /* Ignore ACKs unless we are or have just been transmitting. */ switch (READ_ONCE(call->state)) { @@ -878,39 +913,35 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, case RXRPC_CALL_SERVER_AWAIT_ACK: break; default: - return; - } - - /* Discard any out-of-order or duplicate ACKs. */ - if (before_eq(sp->hdr.serial, call->acks_latest)) { - _debug("discard ACK %d <= %d", - sp->hdr.serial, call->acks_latest); - return; + goto out; } - call->acks_latest_ts = skb->tstamp; - call->acks_latest = sp->hdr.serial; if (before(hard_ack, call->tx_hard_ack) || - after(hard_ack, call->tx_top)) - return rxrpc_proto_abort("AKW", call, 0); - if (nr_acks > call->tx_top - hard_ack) - return rxrpc_proto_abort("AKN", call, 0); + after(hard_ack, call->tx_top)) { + rxrpc_proto_abort("AKW", call, 0); + goto out; + } + if (nr_acks > call->tx_top - hard_ack) { + rxrpc_proto_abort("AKN", call, 0); + goto out; + } - if (after(hard_ack, call->tx_hard_ack)) - rxrpc_rotate_tx_window(call, hard_ack, &summary); + if (after(hard_ack, call->tx_hard_ack)) { + if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { + rxrpc_end_tx_phase(call, false, "ETA"); + goto out; + } + } if (nr_acks > 0) { - if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) - return rxrpc_proto_abort("XSA", call, 0); + if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) { + rxrpc_proto_abort("XSA", call, 0); + goto out; + } rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks, &summary); } - if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { - rxrpc_end_tx_phase(call, false, "ETA"); - return; - } - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && @@ -919,7 +950,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, false, true, rxrpc_propose_ack_ping_for_lost_reply); - return rxrpc_congestion_management(call, skb, &summary, acked_serial); + rxrpc_congestion_management(call, skb, &summary, acked_serial); +out: + spin_unlock(&call->input_lock); } /* @@ -932,9 +965,12 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) _proto("Rx ACKALL %%%u", sp->hdr.serial); - rxrpc_rotate_tx_window(call, call->tx_top, &summary); - if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + spin_lock(&call->input_lock); + + if (rxrpc_rotate_tx_window(call, call->tx_top, &summary)) rxrpc_end_tx_phase(call, false, "ETL"); + + spin_unlock(&call->input_lock); } /* @@ -1017,18 +1053,19 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, } /* - * Handle a new call on a channel implicitly completing the preceding call on - * that channel. + * Handle a new service call on a channel implicitly completing the preceding + * call on that channel. This does not apply to client conns. * * TODO: If callNumber > call_id + 1, renegotiate security. */ -static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, +static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx, + struct rxrpc_connection *conn, struct rxrpc_call *call) { switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); - break; + /* Fall through */ case RXRPC_CALL_COMPLETE: break; default: @@ -1036,11 +1073,13 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, set_bit(RXRPC_CALL_EV_ABORT, &call->events); rxrpc_queue_call(call); } + trace_rxrpc_improper_term(call); break; } - trace_rxrpc_improper_term(call); + spin_lock(&rx->incoming_lock); __rxrpc_disconnect_call(conn, call); + spin_unlock(&rx->incoming_lock); rxrpc_notify_socket(call); } @@ -1119,43 +1158,29 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) * The socket is locked by the caller and this prevents the socket from being * shut down and the local endpoint from going away, thus sk_user_data will not * be cleared until this function returns. + * + * Called with the RCU read lock held from the IP layer via UDP. */ -void rxrpc_data_ready(struct sock *udp_sk) +int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) { struct rxrpc_connection *conn; struct rxrpc_channel *chan; - struct rxrpc_call *call; + struct rxrpc_call *call = NULL; struct rxrpc_skb_priv *sp; struct rxrpc_local *local = udp_sk->sk_user_data; - struct sk_buff *skb; + struct rxrpc_peer *peer = NULL; + struct rxrpc_sock *rx = NULL; unsigned int channel; - int ret, skew; + int skew = 0; _enter("%p", udp_sk); - ASSERT(!irqs_disabled()); - - skb = skb_recv_udp(udp_sk, 0, 1, &ret); - if (!skb) { - if (ret == -EAGAIN) - return; - _debug("UDP socket error %d", ret); - return; - } + if (skb->tstamp == 0) + skb->tstamp = ktime_get_real(); rxrpc_new_skb(skb, rxrpc_skb_rx_received); - _net("recv skb %p", skb); - - /* we'll probably need to checksum it (didn't call sock_recvmsg) */ - if (skb_checksum_complete(skb)) { - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); - __UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0); - _leave(" [CSUM failed]"); - return; - } - - __UDP_INC_STATS(&init_net, UDP_MIB_INDATAGRAMS, 0); + skb_pull(skb, sizeof(struct udphdr)); /* The UDP protocol already released all skb resources; * we are free to add our own data there. @@ -1170,69 +1195,104 @@ void rxrpc_data_ready(struct sock *udp_sk) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_lose_skb(skb, rxrpc_skb_rx_lost); - return; + rxrpc_free_skb(skb, rxrpc_skb_rx_lost); + return 0; } } + if (skb->tstamp == 0) + skb->tstamp = ktime_get_real(); trace_rxrpc_rx_packet(sp); - _net("Rx RxRPC %s ep=%x call=%x:%x", - sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient", - sp->hdr.epoch, sp->hdr.cid, sp->hdr.callNumber); - - if (sp->hdr.type >= RXRPC_N_PACKET_TYPES || - !((RXRPC_SUPPORTED_PACKET_TYPES >> sp->hdr.type) & 1)) { - _proto("Rx Bad Packet Type %u", sp->hdr.type); - goto bad_message; - } - switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: - if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) + if (rxrpc_to_client(sp)) goto discard; rxrpc_post_packet_to_local(local, skb); goto out; case RXRPC_PACKET_TYPE_BUSY: - if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) + if (rxrpc_to_server(sp)) goto discard; /* Fall through */ + case RXRPC_PACKET_TYPE_ACK: + case RXRPC_PACKET_TYPE_ACKALL: + if (sp->hdr.callNumber == 0) + goto bad_message; + /* Fall through */ + case RXRPC_PACKET_TYPE_ABORT: + break; case RXRPC_PACKET_TYPE_DATA: - if (sp->hdr.callNumber == 0) + if (sp->hdr.callNumber == 0 || + sp->hdr.seq == 0) goto bad_message; if (sp->hdr.flags & RXRPC_JUMBO_PACKET && !rxrpc_validate_jumbo(skb)) goto bad_message; break; + case RXRPC_PACKET_TYPE_CHALLENGE: + if (rxrpc_to_server(sp)) + goto discard; + break; + case RXRPC_PACKET_TYPE_RESPONSE: + if (rxrpc_to_client(sp)) + goto discard; + break; + /* Packet types 9-11 should just be ignored. */ case RXRPC_PACKET_TYPE_PARAMS: case RXRPC_PACKET_TYPE_10: case RXRPC_PACKET_TYPE_11: goto discard; + + default: + _proto("Rx Bad Packet Type %u", sp->hdr.type); + goto bad_message; } - rcu_read_lock(); + if (sp->hdr.serviceId == 0) + goto bad_message; + + if (rxrpc_to_server(sp)) { + /* Weed out packets to services we're not offering. Packets + * that would begin a call are explicitly rejected and the rest + * are just discarded. + */ + rx = rcu_dereference(local->service); + if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && + sp->hdr.serviceId != rx->second_service)) { + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && + sp->hdr.seq == 1) + goto unsupported_service; + goto discard; + } + } - conn = rxrpc_find_connection_rcu(local, skb); + conn = rxrpc_find_connection_rcu(local, skb, &peer); if (conn) { if (sp->hdr.securityIndex != conn->security_ix) goto wrong_security; if (sp->hdr.serviceId != conn->service_id) { - if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) || - conn->service_id != conn->params.service_id) + int old_id; + + if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) + goto reupgrade; + old_id = cmpxchg(&conn->service_id, conn->params.service_id, + sp->hdr.serviceId); + + if (old_id != conn->params.service_id && + old_id != sp->hdr.serviceId) goto reupgrade; - conn->service_id = sp->hdr.serviceId; } if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); rxrpc_post_packet_to_conn(conn, skb); - goto out_unlock; + goto out; } /* Note the serial number skew here */ @@ -1251,19 +1311,19 @@ void rxrpc_data_ready(struct sock *udp_sk) /* Ignore really old calls */ if (sp->hdr.callNumber < chan->last_call) - goto discard_unlock; + goto discard; if (sp->hdr.callNumber == chan->last_call) { if (chan->call || sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) - goto discard_unlock; + goto discard; /* For the previous service call, if completed * successfully, we discard all further packets. */ if (rxrpc_conn_is_service(conn) && chan->last_type == RXRPC_PACKET_TYPE_ACK) - goto discard_unlock; + goto discard; /* But otherwise we need to retransmit the final packet * from data cached in the connection record. @@ -1274,18 +1334,16 @@ void rxrpc_data_ready(struct sock *udp_sk) sp->hdr.serial, sp->hdr.flags, 0); rxrpc_post_packet_to_conn(conn, skb); - goto out_unlock; + goto out; } call = rcu_dereference(chan->call); if (sp->hdr.callNumber > chan->call_id) { - if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) { - rcu_read_unlock(); + if (rxrpc_to_client(sp)) goto reject_packet; - } if (call) - rxrpc_input_implicit_end_call(conn, call); + rxrpc_input_implicit_end_call(rx, conn, call); call = NULL; } @@ -1297,66 +1355,57 @@ void rxrpc_data_ready(struct sock *udp_sk) if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) set_bit(RXRPC_CALL_RX_HEARD, &call->flags); } - } else { - skew = 0; - call = NULL; } if (!call || atomic_read(&call->usage) == 0) { - if (!(sp->hdr.type & RXRPC_CLIENT_INITIATED) || - sp->hdr.callNumber == 0 || + if (rxrpc_to_client(sp) || sp->hdr.type != RXRPC_PACKET_TYPE_DATA) - goto bad_message_unlock; + goto bad_message; if (sp->hdr.seq != 1) - goto discard_unlock; - call = rxrpc_new_incoming_call(local, conn, skb); - if (!call) { - rcu_read_unlock(); + goto discard; + call = rxrpc_new_incoming_call(local, rx, skb); + if (!call) goto reject_packet; - } rxrpc_send_ping(call, skb, skew); mutex_unlock(&call->user_mutex); } rxrpc_input_call_packet(call, skb, skew); - goto discard_unlock; + goto discard; -discard_unlock: - rcu_read_unlock(); discard: rxrpc_free_skb(skb, rxrpc_skb_rx_freed); out: trace_rxrpc_rx_done(0, 0); - return; - -out_unlock: - rcu_read_unlock(); - goto out; + return 0; wrong_security: - rcu_read_unlock(); trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RXKADINCONSISTENCY, EBADMSG); skb->priority = RXKADINCONSISTENCY; goto post_abort; +unsupported_service: + trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EOPNOTSUPP); + skb->priority = RX_INVALID_OPERATION; + goto post_abort; + reupgrade: - rcu_read_unlock(); trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_PROTOCOL_ERROR, EBADMSG); goto protocol_error; -bad_message_unlock: - rcu_read_unlock(); bad_message: trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_PROTOCOL_ERROR, EBADMSG); protocol_error: skb->priority = RX_PROTOCOL_ERROR; post_abort: - skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; reject_packet: trace_rxrpc_rx_done(skb->mark, skb->priority); rxrpc_reject_packet(local, skb); _leave(" [badmsg]"); + return 0; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 777c3ed4cfc0..cad0691c2bb4 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -19,6 +19,7 @@ #include <linux/ip.h> #include <linux/hashtable.h> #include <net/sock.h> +#include <net/udp.h> #include <net/af_rxrpc.h> #include "ar-internal.h" @@ -108,7 +109,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, */ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) { - struct sock *sock; + struct sock *usk; int ret, opt; _enter("%p{%d,%d}", @@ -122,6 +123,28 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) return ret; } + /* set the socket up */ + usk = local->socket->sk; + inet_sk(usk)->mc_loop = 0; + + /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ + inet_inc_convert_csum(usk); + + rcu_assign_sk_user_data(usk, local); + + udp_sk(usk)->encap_type = UDP_ENCAP_RXRPC; + udp_sk(usk)->encap_rcv = rxrpc_input_packet; + udp_sk(usk)->encap_destroy = NULL; + udp_sk(usk)->gro_receive = NULL; + udp_sk(usk)->gro_complete = NULL; + + udp_encap_enable(); +#if IS_ENABLED(CONFIG_IPV6) + if (local->srx.transport.family == AF_INET6) + udpv6_encap_enable(); +#endif + usk->sk_error_report = rxrpc_error_report; + /* if a local address was supplied then bind it */ if (local->srx.transport_len > sizeof(sa_family_t)) { _debug("bind"); @@ -135,10 +158,10 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } switch (local->srx.transport.family) { - case AF_INET: - /* we want to receive ICMP errors */ + case AF_INET6: + /* we want to receive ICMPv6 errors */ opt = 1; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, + ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR, (char *) &opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); @@ -146,19 +169,22 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } /* we want to set the don't fragment bit */ - opt = IP_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, + opt = IPV6_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, (char *) &opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); goto error; } - break; - case AF_INET6: + /* Fall through and set IPv4 options too otherwise we don't get + * errors from IPv4 packets sent through the IPv6 socket. + */ + + case AF_INET: /* we want to receive ICMP errors */ opt = 1; - ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR, + ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, (char *) &opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); @@ -166,24 +192,28 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } /* we want to set the don't fragment bit */ - opt = IPV6_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, + opt = IP_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, (char *) &opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); goto error; } + + /* We want receive timestamps. */ + opt = 1; + ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS, + (char *)&opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } break; default: BUG(); } - /* set the socket up */ - sock = local->socket->sk; - sock->sk_user_data = local; - sock->sk_data_ready = rxrpc_data_ready; - sock->sk_error_report = rxrpc_error_report; _leave(" = 0"); return 0; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index ccf5de160444..e8fb8922bca8 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -124,7 +124,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, struct kvec iov[2]; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; - ktime_t now; size_t len, n; int ret; u8 reason; @@ -196,9 +195,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, /* We need to stick a time in before we send the packet in case * the reply gets back before kernel_sendmsg() completes - but * asking UDP to send the packet can take a relatively long - * time, so we update the time after, on the assumption that - * the packet transmission is more likely to happen towards the - * end of the kernel_sendmsg() call. + * time. */ call->ping_time = ktime_get_real(); set_bit(RXRPC_CALL_PINGING, &call->flags); @@ -206,9 +203,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, } ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - now = ktime_get_real(); - if (ping) - call->ping_time = now; conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, @@ -363,8 +357,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, /* If our RTT cache needs working on, request an ACK. Also request * ACKs if a DATA packet appears to have been lost. + * + * However, we mustn't request an ACK on the last reply packet of a + * service call, lest OpenAFS incorrectly send us an ACK with some + * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if (!(sp->hdr.flags & RXRPC_LAST_PACKET) && + if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) || + rxrpc_to_server(sp) + ) && (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) || retrans || call->cong_mode == RXRPC_CALL_SLOW_START || @@ -390,6 +390,11 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, goto send_fragmentable; down_read(&conn->params.local->defrag_sem); + + sp->hdr.serial = serial; + smp_wmb(); /* Set serial before timestamp */ + skb->tstamp = ktime_get_real(); + /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet * to go out of the interface @@ -413,12 +418,8 @@ done: trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, retrans, lost); if (ret >= 0) { - ktime_t now = ktime_get_real(); - skb->tstamp = now; - smp_wmb(); - sp->hdr.serial = serial; if (whdr.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = now; + call->peer->rtt_last_req = skb->tstamp; trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial); if (call->peer->rtt_usage > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -457,6 +458,10 @@ send_fragmentable: down_write(&conn->params.local->defrag_sem); + sp->hdr.serial = serial; + smp_wmb(); /* Set serial before timestamp */ + skb->tstamp = ktime_get_real(); + switch (conn->params.local->srx.transport.family) { case AF_INET: opt = IP_PMTUDISC_DONT; @@ -519,7 +524,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) struct kvec iov[2]; size_t size; __be32 code; - int ret; + int ret, ioc; _enter("%d", local->debug_id); @@ -527,7 +532,6 @@ void rxrpc_reject_packets(struct rxrpc_local *local) iov[0].iov_len = sizeof(whdr); iov[1].iov_base = &code; iov[1].iov_len = sizeof(code); - size = sizeof(whdr) + sizeof(code); msg.msg_name = &srx.transport; msg.msg_control = NULL; @@ -535,17 +539,31 @@ void rxrpc_reject_packets(struct rxrpc_local *local) msg.msg_flags = 0; memset(&whdr, 0, sizeof(whdr)); - whdr.type = RXRPC_PACKET_TYPE_ABORT; while ((skb = skb_dequeue(&local->reject_queue))) { rxrpc_see_skb(skb, rxrpc_skb_rx_seen); sp = rxrpc_skb(skb); + switch (skb->mark) { + case RXRPC_SKB_MARK_REJECT_BUSY: + whdr.type = RXRPC_PACKET_TYPE_BUSY; + size = sizeof(whdr); + ioc = 1; + break; + case RXRPC_SKB_MARK_REJECT_ABORT: + whdr.type = RXRPC_PACKET_TYPE_ABORT; + code = htonl(skb->priority); + size = sizeof(whdr) + sizeof(code); + ioc = 2; + break; + default: + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + continue; + } + if (rxrpc_extract_addr_from_skb(local, &srx, skb) == 0) { msg.msg_namelen = srx.transport_len; - code = htonl(skb->priority); - whdr.epoch = htonl(sp->hdr.epoch); whdr.cid = htonl(sp->hdr.cid); whdr.callNumber = htonl(sp->hdr.callNumber); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 4f9da2f51c69..05b51bdbdd41 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -23,6 +23,8 @@ #include "ar-internal.h" static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); +static void rxrpc_distribute_error(struct rxrpc_peer *, int, + enum rxrpc_call_completion); /* * Find the peer associated with an ICMP packet. @@ -194,8 +196,6 @@ void rxrpc_error_report(struct sock *sk) rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_rx_freed); - /* The ref we obtained is passed off to the work item */ - __rxrpc_queue_peer_error(peer); _leave(""); } @@ -205,6 +205,7 @@ void rxrpc_error_report(struct sock *sk) static void rxrpc_store_error(struct rxrpc_peer *peer, struct sock_exterr_skb *serr) { + enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR; struct sock_extended_err *ee; int err; @@ -255,7 +256,7 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, case SO_EE_ORIGIN_NONE: case SO_EE_ORIGIN_LOCAL: _proto("Rx Received local error { error=%d }", err); - err += RXRPC_LOCAL_ERROR_OFFSET; + compl = RXRPC_CALL_LOCAL_ERROR; break; case SO_EE_ORIGIN_ICMP6: @@ -264,48 +265,23 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, break; } - peer->error_report = err; + rxrpc_distribute_error(peer, err, compl); } /* - * Distribute an error that occurred on a peer + * Distribute an error that occurred on a peer. */ -void rxrpc_peer_error_distributor(struct work_struct *work) +static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, + enum rxrpc_call_completion compl) { - struct rxrpc_peer *peer = - container_of(work, struct rxrpc_peer, error_distributor); struct rxrpc_call *call; - enum rxrpc_call_completion compl; - int error; - - _enter(""); - - error = READ_ONCE(peer->error_report); - if (error < RXRPC_LOCAL_ERROR_OFFSET) { - compl = RXRPC_CALL_NETWORK_ERROR; - } else { - compl = RXRPC_CALL_LOCAL_ERROR; - error -= RXRPC_LOCAL_ERROR_OFFSET; - } - - _debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error); - spin_lock_bh(&peer->lock); - - while (!hlist_empty(&peer->error_targets)) { - call = hlist_entry(peer->error_targets.first, - struct rxrpc_call, error_link); - hlist_del_init(&call->error_link); + hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) { rxrpc_see_call(call); - - if (rxrpc_set_call_completion(call, compl, 0, -error)) + if (call->state < RXRPC_CALL_COMPLETE && + rxrpc_set_call_completion(call, compl, 0, -error)) rxrpc_notify_socket(call); } - - spin_unlock_bh(&peer->lock); - - rxrpc_put_peer(peer); - _leave(""); } /* @@ -325,6 +301,8 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, if (rtt < 0) return; + spin_lock(&peer->rtt_input_lock); + /* Replace the oldest datum in the RTT buffer */ sum -= peer->rtt_cache[cursor]; sum += rtt; @@ -336,6 +314,8 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, peer->rtt_usage = usage; } + spin_unlock(&peer->rtt_input_lock); + /* Now recalculate the average */ if (usage == RXRPC_RTT_CACHE_SIZE) { avg = sum / RXRPC_RTT_CACHE_SIZE; @@ -344,6 +324,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, do_div(avg, usage); } + /* Don't need to update this under lock */ peer->rtt = avg; trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt, usage, avg); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 1dc7648e3eff..5691b7d266ca 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -124,11 +124,9 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu( struct rxrpc_net *rxnet = local->rxnet; hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) { - if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) { - if (atomic_read(&peer->usage) == 0) - return NULL; + if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 && + atomic_read(&peer->usage) > 0) return peer; - } } return NULL; @@ -155,8 +153,10 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, * assess the MTU size for the network interface through which this peer is * reached */ -static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) +static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx, + struct rxrpc_peer *peer) { + struct net *net = sock_net(&rx->sk); struct dst_entry *dst; struct rtable *rt; struct flowi fl; @@ -171,7 +171,7 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) switch (peer->srx.transport.family) { case AF_INET: rt = ip_route_output_ports( - &init_net, fl4, NULL, + net, fl4, NULL, peer->srx.transport.sin.sin_addr.s_addr, 0, htons(7000), htons(7001), IPPROTO_UDP, 0, 0); if (IS_ERR(rt)) { @@ -190,7 +190,7 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) sizeof(struct in6_addr)); fl6->fl6_dport = htons(7001); fl6->fl6_sport = htons(7000); - dst = ip6_route_output(&init_net, NULL, fl6); + dst = ip6_route_output(net, NULL, fl6); if (dst->error) { _leave(" [route err %d]", dst->error); return; @@ -222,11 +222,10 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) atomic_set(&peer->usage, 1); peer->local = local; INIT_HLIST_HEAD(&peer->error_targets); - INIT_WORK(&peer->error_distributor, - &rxrpc_peer_error_distributor); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); + spin_lock_init(&peer->rtt_input_lock); peer->debug_id = atomic_inc_return(&rxrpc_debug_id); if (RXRPC_TX_SMSS > 2190) @@ -244,10 +243,11 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) /* * Initialise peer record. */ -static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key) +static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer, + unsigned long hash_key) { peer->hash_key = hash_key; - rxrpc_assess_MTU_size(peer); + rxrpc_assess_MTU_size(rx, peer); peer->mtu = peer->if_mtu; peer->rtt_last_req = ktime_get_real(); @@ -279,7 +279,8 @@ static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key) /* * Set up a new peer. */ -static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, +static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, + struct rxrpc_local *local, struct sockaddr_rxrpc *srx, unsigned long hash_key, gfp_t gfp) @@ -291,7 +292,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, peer = rxrpc_alloc_peer(local, gfp); if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); - rxrpc_init_peer(peer, hash_key); + rxrpc_init_peer(rx, peer, hash_key); } _leave(" = %p", peer); @@ -299,40 +300,31 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, } /* - * Set up a new incoming peer. The address is prestored in the preallocated - * peer. + * Set up a new incoming peer. There shouldn't be any other matching peers + * since we've already done a search in the list from the non-reentrant context + * (the data_ready handler) that is the only place we can add new peers. */ -struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, - struct rxrpc_peer *prealloc) +void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, + struct rxrpc_peer *peer) { - struct rxrpc_peer *peer; struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key; - hash_key = rxrpc_peer_hash_key(local, &prealloc->srx); - prealloc->local = local; - rxrpc_init_peer(prealloc, hash_key); + hash_key = rxrpc_peer_hash_key(local, &peer->srx); + peer->local = local; + rxrpc_init_peer(rx, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); - - /* Need to check that we aren't racing with someone else */ - peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key); - if (peer && !rxrpc_get_peer_maybe(peer)) - peer = NULL; - if (!peer) { - peer = prealloc; - hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); - list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); - } - + hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); + list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); spin_unlock(&rxnet->peer_hash_lock); - return peer; } /* * obtain a remote transport endpoint for the specified address */ -struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, + struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp) { struct rxrpc_peer *peer, *candidate; @@ -352,7 +344,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, /* The peer is not yet present in hash - create a candidate * for a new record and then redo the search. */ - candidate = rxrpc_create_peer(local, srx, hash_key, gfp); + candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp); if (!candidate) { _leave(" = NULL [nomem]"); return NULL; @@ -416,21 +408,6 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) } /* - * Queue a peer record. This passes the caller's ref to the workqueue. - */ -void __rxrpc_queue_peer_error(struct rxrpc_peer *peer) -{ - const void *here = __builtin_return_address(0); - int n; - - n = atomic_read(&peer->usage); - if (rxrpc_queue_work(&peer->error_distributor)) - trace_rxrpc_peer(peer, rxrpc_peer_queued_error, n, here); - else - rxrpc_put_peer(peer); -} - -/* * Discard a peer record. */ static void __rxrpc_put_peer(struct rxrpc_peer *peer) diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index 93da73bf7098..f9cb83c938f3 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -50,7 +50,6 @@ struct rxrpc_wire_header { #define RXRPC_PACKET_TYPE_10 10 /* Ignored */ #define RXRPC_PACKET_TYPE_11 11 /* Ignored */ #define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */ -#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */ uint8_t flags; /* packet flags */ #define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */ @@ -72,20 +71,6 @@ struct rxrpc_wire_header { } __packed; -#define RXRPC_SUPPORTED_PACKET_TYPES ( \ - (1 << RXRPC_PACKET_TYPE_DATA) | \ - (1 << RXRPC_PACKET_TYPE_ACK) | \ - (1 << RXRPC_PACKET_TYPE_BUSY) | \ - (1 << RXRPC_PACKET_TYPE_ABORT) | \ - (1 << RXRPC_PACKET_TYPE_ACKALL) | \ - (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \ - (1 << RXRPC_PACKET_TYPE_RESPONSE) | \ - /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \ - (1 << RXRPC_PACKET_TYPE_PARAMS) | \ - (1 << RXRPC_PACKET_TYPE_10) | \ - (1 << RXRPC_PACKET_TYPE_11) | \ - (1 << RXRPC_PACKET_TYPE_VERSION)) - /*****************************************************************************/ /* * jumbo packet secondary header diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 229d63c99be2..e12f8ef7baa4 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -300,21 +300,17 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, } EXPORT_SYMBOL(tcf_generic_walker); -static bool __tcf_idr_check(struct tc_action_net *tn, u32 index, - struct tc_action **a, int bind) +int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) { struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; spin_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); - if (IS_ERR(p)) { + if (IS_ERR(p)) p = NULL; - } else if (p) { + else if (p) refcount_inc(&p->tcfa_refcnt); - if (bind) - atomic_inc(&p->tcfa_bindcnt); - } spin_unlock(&idrinfo->lock); if (p) { @@ -323,23 +319,10 @@ static bool __tcf_idr_check(struct tc_action_net *tn, u32 index, } return false; } - -int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) -{ - return __tcf_idr_check(tn, index, a, 0); -} EXPORT_SYMBOL(tcf_idr_search); -bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a, - int bind) +static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) { - return __tcf_idr_check(tn, index, a, bind); -} -EXPORT_SYMBOL(tcf_idr_check); - -int tcf_idr_delete_index(struct tc_action_net *tn, u32 index) -{ - struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; int ret = 0; @@ -370,7 +353,6 @@ int tcf_idr_delete_index(struct tc_action_net *tn, u32 index) spin_unlock(&idrinfo->lock); return ret; } -EXPORT_SYMBOL(tcf_idr_delete_index); int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, @@ -409,7 +391,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, p->idrinfo = idrinfo; p->ops = ops; - INIT_LIST_HEAD(&p->list); *a = p; return 0; err3: @@ -681,19 +662,30 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) return ret; } +static int tcf_action_destroy_1(struct tc_action *a, int bind) +{ + struct tc_action *actions[] = { a, NULL }; + + return tcf_action_destroy(actions, bind); +} + static int tcf_action_put(struct tc_action *p) { return __tcf_action_put(p, false); } +/* Put all actions in this array, skip those NULL's. */ static void tcf_action_put_many(struct tc_action *actions[]) { int i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { struct tc_action *a = actions[i]; - const struct tc_action_ops *ops = a->ops; + const struct tc_action_ops *ops; + if (!a) + continue; + ops = a->ops; if (tcf_action_put(a)) module_put(ops->owner); } @@ -896,17 +888,16 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { err = tcf_action_goto_chain_init(a, tp); if (err) { - struct tc_action *actions[] = { a, NULL }; - - tcf_action_destroy(actions, bind); + tcf_action_destroy_1(a, bind); NL_SET_ERR_MSG(extack, "Failed to init TC action chain"); return ERR_PTR(err); } } if (!tcf_action_valid(a->tcfa_action)) { - NL_SET_ERR_MSG(extack, "invalid action value, using TC_ACT_UNSPEC instead"); - a->tcfa_action = TC_ACT_UNSPEC; + tcf_action_destroy_1(a, bind); + NL_SET_ERR_MSG(extack, "Invalid control action value"); + return ERR_PTR(-EINVAL); } return a; @@ -1175,41 +1166,38 @@ err_out: return err; } -static int tcf_action_delete(struct net *net, struct tc_action *actions[], - int *acts_deleted, struct netlink_ext_ack *extack) +static int tcf_action_delete(struct net *net, struct tc_action *actions[]) { - u32 act_index; - int ret, i; + int i; for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { struct tc_action *a = actions[i]; const struct tc_action_ops *ops = a->ops; - /* Actions can be deleted concurrently so we must save their * type and id to search again after reference is released. */ - act_index = a->tcfa_index; + struct tcf_idrinfo *idrinfo = a->idrinfo; + u32 act_index = a->tcfa_index; + actions[i] = NULL; if (tcf_action_put(a)) { /* last reference, action was deleted concurrently */ module_put(ops->owner); } else { + int ret; + /* now do the delete */ - ret = ops->delete(net, act_index); - if (ret < 0) { - *acts_deleted = i + 1; + ret = tcf_idr_delete_index(idrinfo, act_index); + if (ret < 0) return ret; - } } } - *acts_deleted = i; return 0; } static int tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], - int *acts_deleted, u32 portid, size_t attr_size, - struct netlink_ext_ack *extack) + u32 portid, size_t attr_size, struct netlink_ext_ack *extack) { int ret; struct sk_buff *skb; @@ -1227,7 +1215,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], } /* now do the delete */ - ret = tcf_action_delete(net, actions, acts_deleted, extack); + ret = tcf_action_delete(net, actions); if (ret < 0) { NL_SET_ERR_MSG(extack, "Failed to delete TC action"); kfree_skb(skb); @@ -1249,8 +1237,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; size_t attr_size = 0; - struct tc_action *actions[TCA_ACT_MAX_PRIO + 1] = {}; - int acts_deleted = 0; + struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); if (ret < 0) @@ -1280,14 +1267,13 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, if (event == RTM_GETACTION) ret = tcf_get_notify(net, portid, n, actions, event, extack); else { /* delete */ - ret = tcf_del_notify(net, n, actions, &acts_deleted, portid, - attr_size, extack); + ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) goto err; - return ret; + return 0; } err: - tcf_action_put_many(&actions[acts_deleted]); + tcf_action_put_many(actions); return ret; } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index d30b23e42436..0c68bc9cf0b4 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -395,13 +395,6 @@ static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_bpf_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, bpf_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", .type = TCA_ACT_BPF, @@ -412,7 +405,6 @@ static struct tc_action_ops act_bpf_ops __read_mostly = { .init = tcf_bpf_init, .walk = tcf_bpf_walker, .lookup = tcf_bpf_search, - .delete = tcf_bpf_delete, .size = sizeof(struct tcf_bpf), }; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 54c0bf54f2ac..6f0f273f1139 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -198,13 +198,6 @@ static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_connmark_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, connmark_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_connmark_ops = { .kind = "connmark", .type = TCA_ACT_CONNMARK, @@ -214,7 +207,6 @@ static struct tc_action_ops act_connmark_ops = { .init = tcf_connmark_init, .walk = tcf_connmark_walker, .lookup = tcf_connmark_search, - .delete = tcf_connmark_delete, .size = sizeof(struct tcf_connmark_info), }; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index e698d3fe2080..b8a67ae3105a 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -659,13 +659,6 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act) return nla_total_size(sizeof(struct tc_csum)); } -static int tcf_csum_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, csum_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_csum_ops = { .kind = "csum", .type = TCA_ACT_CSUM, @@ -677,7 +670,6 @@ static struct tc_action_ops act_csum_ops = { .walk = tcf_csum_walker, .lookup = tcf_csum_search, .get_fill_size = tcf_csum_get_fill_size, - .delete = tcf_csum_delete, .size = sizeof(struct tcf_csum), }; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 6a3f25a8ffb3..cd1d9bd32ef9 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -243,13 +243,6 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act) return sz; } -static int tcf_gact_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, gact_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_gact_ops = { .kind = "gact", .type = TCA_ACT_GACT, @@ -261,7 +254,6 @@ static struct tc_action_ops act_gact_ops = { .walk = tcf_gact_walker, .lookup = tcf_gact_search, .get_fill_size = tcf_gact_get_fill_size, - .delete = tcf_gact_delete, .size = sizeof(struct tcf_gact), }; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index d1081bdf1bdb..06a3d4801878 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -167,16 +167,16 @@ static struct tcf_meta_ops *find_ife_oplist(u16 metaid) { struct tcf_meta_ops *o; - read_lock_bh(&ife_mod_lock); + read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { if (o->metaid == metaid) { if (!try_module_get(o->owner)) o = NULL; - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); return o; } } - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); return NULL; } @@ -190,12 +190,12 @@ int register_ife_op(struct tcf_meta_ops *mops) !mops->get || !mops->alloc) return -EINVAL; - write_lock_bh(&ife_mod_lock); + write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid || (strcmp(mops->name, m->name) == 0)) { - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return -EEXIST; } } @@ -204,7 +204,7 @@ int register_ife_op(struct tcf_meta_ops *mops) mops->release = ife_release_meta_gen; list_add_tail(&mops->list, &ifeoplist); - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return 0; } EXPORT_SYMBOL_GPL(unregister_ife_op); @@ -214,7 +214,7 @@ int unregister_ife_op(struct tcf_meta_ops *mops) struct tcf_meta_ops *m; int err = -ENOENT; - write_lock_bh(&ife_mod_lock); + write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid) { list_del(&mops->list); @@ -222,7 +222,7 @@ int unregister_ife_op(struct tcf_meta_ops *mops) break; } } - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return err; } @@ -265,11 +265,8 @@ static const char *ife_meta_id2name(u32 metaid) #endif /* called when adding new meta information - * under ife->tcf_lock for existing action */ -static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, - void *val, int len, bool exists, - bool rtnl_held) +static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) { struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; @@ -277,15 +274,11 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (!ops) { ret = -ENOENT; #ifdef CONFIG_MODULES - if (exists) - spin_unlock_bh(&ife->tcf_lock); if (rtnl_held) rtnl_unlock(); request_module("ife-meta-%s", ife_meta_id2name(metaid)); if (rtnl_held) rtnl_lock(); - if (exists) - spin_lock_bh(&ife->tcf_lock); ops = find_ife_oplist(metaid); #endif } @@ -302,24 +295,17 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, } /* called when adding new meta information - * under ife->tcf_lock for existing action */ -static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool atomic) +static int __add_metainfo(const struct tcf_meta_ops *ops, + struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len, bool atomic, bool exists) { struct tcf_meta_info *mi = NULL; - struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; - if (!ops) - return -ENOENT; - mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL); - if (!mi) { - /*put back what find_ife_oplist took */ - module_put(ops->owner); + if (!mi) return -ENOMEM; - } mi->metaid = metaid; mi->ops = ops; @@ -327,29 +313,61 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL); if (ret != 0) { kfree(mi); - module_put(ops->owner); return ret; } } + if (exists) + spin_lock_bh(&ife->tcf_lock); list_add_tail(&mi->metalist, &ife->metalist); + if (exists) + spin_unlock_bh(&ife->tcf_lock); + + return ret; +} + +static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, + struct tcf_ife_info *ife, u32 metaid, + bool exists) +{ + int ret; + + if (!try_module_get(ops->owner)) + return -ENOENT; + ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); + if (ret) + module_put(ops->owner); + return ret; +} + +static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len, bool exists) +{ + const struct tcf_meta_ops *ops = find_ife_oplist(metaid); + int ret; + if (!ops) + return -ENOENT; + ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); + if (ret) + /*put back what find_ife_oplist took */ + module_put(ops->owner); return ret; } -static int use_all_metadata(struct tcf_ife_info *ife) +static int use_all_metadata(struct tcf_ife_info *ife, bool exists) { struct tcf_meta_ops *o; int rc = 0; int installed = 0; - read_lock_bh(&ife_mod_lock); + read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo(ife, o->metaid, NULL, 0, true); + rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); if (rc == 0) installed += 1; } - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); if (installed) return 0; @@ -396,7 +414,6 @@ static void _tcf_ife_cleanup(struct tc_action *a) struct tcf_meta_info *e, *n; list_for_each_entry_safe(e, n, &ife->metalist, metalist) { - module_put(e->ops->owner); list_del(&e->metalist); if (e->metaval) { if (e->ops->release) @@ -404,6 +421,7 @@ static void _tcf_ife_cleanup(struct tc_action *a) else kfree(e->metaval); } + module_put(e->ops->owner); kfree(e); } } @@ -422,7 +440,6 @@ static void tcf_ife_cleanup(struct tc_action *a) kfree_rcu(p, rcu); } -/* under ife->tcf_lock for existing action */ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { @@ -436,8 +453,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(ife, i, val, len, exists, - rtnl_held); + rc = load_metaops_and_vet(i, val, len, rtnl_held); if (rc != 0) return rc; @@ -540,8 +556,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p->eth_type = ife_type; } - if (exists) - spin_lock_bh(&ife->tcf_lock); if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); @@ -551,10 +565,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, NULL, NULL); if (err) { metadata_parse_err: - if (exists) - spin_unlock_bh(&ife->tcf_lock); tcf_idr_release(*a, bind); - kfree(p); return err; } @@ -569,17 +580,16 @@ metadata_parse_err: * as we can. You better have at least one else we are * going to bail out */ - err = use_all_metadata(ife); + err = use_all_metadata(ife, exists); if (err) { - if (exists) - spin_unlock_bh(&ife->tcf_lock); tcf_idr_release(*a, bind); - kfree(p); return err; } } + if (exists) + spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; /* protected by tcf_lock when modifying existing action */ rcu_swap_protected(ife->params, p, 1); @@ -853,13 +863,6 @@ static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_ife_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, ife_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_ife_ops = { .kind = "ife", .type = TCA_ACT_IFE, @@ -870,7 +873,6 @@ static struct tc_action_ops act_ife_ops = { .init = tcf_ife_init, .walk = tcf_ife_walker, .lookup = tcf_ife_search, - .delete = tcf_ife_delete, .size = sizeof(struct tcf_ife_info), }; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 51f235bbeb5b..8525de811616 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -135,7 +135,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, } td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]); - if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) { + if (nla_len(tb[TCA_IPT_TARG]) != td->u.target_size) { if (exists) tcf_idr_release(*a, bind); else @@ -337,13 +337,6 @@ static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_ipt_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_ipt_ops = { .kind = "ipt", .type = TCA_ACT_IPT, @@ -354,7 +347,6 @@ static struct tc_action_ops act_ipt_ops = { .init = tcf_ipt_init, .walk = tcf_ipt_walker, .lookup = tcf_ipt_search, - .delete = tcf_ipt_delete, .size = sizeof(struct tcf_ipt), }; @@ -395,13 +387,6 @@ static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_xt_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_xt_ops = { .kind = "xt", .type = TCA_ACT_XT, @@ -412,7 +397,6 @@ static struct tc_action_ops act_xt_ops = { .init = tcf_xt_init, .walk = tcf_xt_walker, .lookup = tcf_xt_search, - .delete = tcf_xt_delete, .size = sizeof(struct tcf_ipt), }; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 38fd20f10f67..8bf66d0a6800 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -395,13 +395,6 @@ static void tcf_mirred_put_dev(struct net_device *dev) dev_put(dev); } -static int tcf_mirred_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, mirred_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .type = TCA_ACT_MIRRED, @@ -416,7 +409,6 @@ static struct tc_action_ops act_mirred_ops = { .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, .put_dev = tcf_mirred_put_dev, - .delete = tcf_mirred_delete, }; static __net_init int mirred_init_net(struct net *net) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 822e903bfc25..4313aa102440 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -300,13 +300,6 @@ static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_nat_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, nat_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_nat_ops = { .kind = "nat", .type = TCA_ACT_NAT, @@ -316,7 +309,6 @@ static struct tc_action_ops act_nat_ops = { .init = tcf_nat_init, .walk = tcf_nat_walker, .lookup = tcf_nat_search, - .delete = tcf_nat_delete, .size = sizeof(struct tcf_nat), }; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 8a7a7cb94e83..ad99a99f11f6 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -109,16 +109,18 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, { struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX); + if (!keys_start) + goto nla_failure; for (; n > 0; n--) { struct nlattr *key_start; key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX); + if (!key_start) + goto nla_failure; if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) || - nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) { - nlmsg_trim(skb, keys_start); - return -EINVAL; - } + nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) + goto nla_failure; nla_nest_end(skb, key_start); @@ -128,6 +130,9 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, nla_nest_end(skb, keys_start); return 0; +nla_failure: + nla_nest_cancel(skb, keys_start); + return -EINVAL; } static int tcf_pedit_init(struct net *net, struct nlattr *nla, @@ -418,7 +423,10 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind; if (p->tcfp_keys_ex) { - tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys); + if (tcf_pedit_key_ex_dump(skb, + p->tcfp_keys_ex, + p->tcfp_nkeys)) + goto nla_put_failure; if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt)) goto nla_put_failure; @@ -460,13 +468,6 @@ static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_pedit_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, pedit_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_pedit_ops = { .kind = "pedit", .type = TCA_ACT_PEDIT, @@ -477,7 +478,6 @@ static struct tc_action_ops act_pedit_ops = { .init = tcf_pedit_init, .walk = tcf_pedit_walker, .lookup = tcf_pedit_search, - .delete = tcf_pedit_delete, .size = sizeof(struct tcf_pedit), }; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 06f0742db593..5d8bfa878477 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -320,13 +320,6 @@ static int tcf_police_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_police_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, police_net_id); - - return tcf_idr_delete_index(tn, index); -} - MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); @@ -340,7 +333,6 @@ static struct tc_action_ops act_police_ops = { .init = tcf_police_init, .walk = tcf_police_walker, .lookup = tcf_police_search, - .delete = tcf_police_delete, .size = sizeof(struct tcf_police), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 207b4132d1b0..6b67aa13d2dd 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, - &act_sample_ops, bind, false); + &act_sample_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; @@ -232,13 +232,6 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_sample_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, sample_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_sample_ops = { .kind = "sample", .type = TCA_ACT_SAMPLE, @@ -249,7 +242,6 @@ static struct tc_action_ops act_sample_ops = { .cleanup = tcf_sample_cleanup, .walk = tcf_sample_walker, .lookup = tcf_sample_search, - .delete = tcf_sample_delete, .size = sizeof(struct tcf_sample), }; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index e616523ba3c1..52400d49f81f 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -196,13 +196,6 @@ static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_simp_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, simp_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_simp_ops = { .kind = "simple", .type = TCA_ACT_SIMP, @@ -213,7 +206,6 @@ static struct tc_action_ops act_simp_ops = { .init = tcf_simp_init, .walk = tcf_simp_walker, .lookup = tcf_simp_search, - .delete = tcf_simp_delete, .size = sizeof(struct tcf_defact), }; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 926d7bc4a89d..73e44ce2a883 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -299,13 +299,6 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_skbedit_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, skbedit_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .type = TCA_ACT_SKBEDIT, @@ -316,7 +309,6 @@ static struct tc_action_ops act_skbedit_ops = { .cleanup = tcf_skbedit_cleanup, .walk = tcf_skbedit_walker, .lookup = tcf_skbedit_search, - .delete = tcf_skbedit_delete, .size = sizeof(struct tcf_skbedit), }; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index d6a1af0c4171..588077fafd6c 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -259,13 +259,6 @@ static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_skbmod_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, skbmod_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", .type = TCA_ACT_SKBMOD, @@ -276,7 +269,6 @@ static struct tc_action_ops act_skbmod_ops = { .cleanup = tcf_skbmod_cleanup, .walk = tcf_skbmod_walker, .lookup = tcf_skbmod_search, - .delete = tcf_skbmod_delete, .size = sizeof(struct tcf_skbmod), }; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 8f09cf08d8fe..681f6f04e7da 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -317,7 +317,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &metadata->u.tun_info, opts_len, extack); if (ret < 0) - goto err_out; + goto release_tun_meta; } metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; @@ -333,23 +333,24 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); - goto err_out; + goto release_tun_meta; } ret = ACT_P_CREATED; } else if (!ovr) { - tcf_idr_release(*a, bind); NL_SET_ERR_MSG(extack, "TC IDR already exists"); - return -EEXIST; + ret = -EEXIST; + goto release_tun_meta; } t = to_tunnel_key(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - tcf_idr_release(*a, bind); NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); - return -ENOMEM; + ret = -ENOMEM; + exists = true; + goto release_tun_meta; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -367,6 +368,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, return ret; +release_tun_meta: + dst_release(&metadata->dst); + err_out: if (exists) tcf_idr_release(*a, bind); @@ -408,8 +412,10 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, opt->type) || nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, - opt->length * 4, opt + 1)) + opt->length * 4, opt + 1)) { + nla_nest_cancel(skb, start); return -EMSGSIZE; + } len -= sizeof(struct geneve_opt) + opt->length * 4; src += sizeof(struct geneve_opt) + opt->length * 4; @@ -423,7 +429,7 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { struct nlattr *start; - int err; + int err = -EINVAL; if (!info->options_len) return 0; @@ -435,9 +441,11 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) - return err; + goto err_out; } else { - return -EINVAL; +err_out: + nla_nest_cancel(skb, start); + return err; } nla_nest_end(skb, start); @@ -548,13 +556,6 @@ static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tunnel_key_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", .type = TCA_ACT_TUNNEL_KEY, @@ -565,7 +566,6 @@ static struct tc_action_ops act_tunnel_key_ops = { .cleanup = tunnel_key_release, .walk = tunnel_key_walker, .lookup = tunnel_key_search, - .delete = tunnel_key_delete, .size = sizeof(struct tcf_tunnel_key), }; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 209e70ad2c09..033d273afe50 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -296,13 +296,6 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_vlan_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, vlan_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .type = TCA_ACT_VLAN, @@ -313,7 +306,6 @@ static struct tc_action_ops act_vlan_ops = { .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, .lookup = tcf_vlan_search, - .delete = tcf_vlan_delete, .size = sizeof(struct tcf_vlan), }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 31bd1439cf60..0a75cb2e5e7b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1252,7 +1252,7 @@ replay: } chain = tcf_chain_get(block, chain_index, true); if (!chain) { - NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + NL_SET_ERR_MSG(extack, "Cannot create specified filter chain"); err = -ENOMEM; goto errout; } @@ -1399,7 +1399,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, goto errout; } NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); - err = -EINVAL; + err = -ENOENT; goto errout; } @@ -1902,6 +1902,8 @@ replay: RTM_NEWCHAIN, false); break; case RTM_DELCHAIN: + tfilter_notify_chain(net, skb, block, q, parent, n, + chain, RTM_DELTFILTER); /* Flush the chain first as the user requested chain removal. */ tcf_chain_flush(chain); /* In case the chain was successfully deleted, put a reference diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d5d2a6dc3921..b2c3406a2cf2 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -398,6 +398,7 @@ static int u32_init(struct tcf_proto *tp) rcu_assign_pointer(tp_c->hlist, root_ht); root_ht->tp_c = tp_c; + root_ht->refcnt++; rcu_assign_pointer(tp->root, root_ht); tp->data = tp_c; return 0; @@ -610,7 +611,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, struct tc_u_hnode __rcu **hn; struct tc_u_hnode *phn; - WARN_ON(ht->refcnt); + WARN_ON(--ht->refcnt); u32_clear_hnode(tp, ht, extack); @@ -649,7 +650,7 @@ static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) WARN_ON(root_ht == NULL); - if (root_ht && --root_ht->refcnt == 0) + if (root_ht && --root_ht->refcnt == 1) u32_destroy_hnode(tp, root_ht, extack); if (--tp_c->refcnt == 0) { @@ -698,7 +699,6 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, } if (ht->refcnt == 1) { - ht->refcnt--; u32_destroy_hnode(tp, ht, extack); } else { NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); @@ -708,11 +708,11 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, out: *last = true; if (root_ht) { - if (root_ht->refcnt > 1) { + if (root_ht->refcnt > 2) { *last = false; goto ret; } - if (root_ht->refcnt == 1) { + if (root_ht->refcnt == 2) { if (!ht_empty(root_ht)) { *last = false; goto ret; @@ -914,6 +914,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_U32_MAX + 1]; u32 htid, flags = 0; + size_t sel_size; int err; #ifdef CONFIG_CLS_U32_PERF size_t size; @@ -1076,8 +1077,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } s = nla_data(tb[TCA_U32_SEL]); + sel_size = struct_size(s, keys, s->nkeys); + if (nla_len(tb[TCA_U32_SEL]) < sel_size) { + err = -EINVAL; + goto erridr; + } - n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); + n = kzalloc(offsetof(typeof(*n), sel) + sel_size, GFP_KERNEL); if (n == NULL) { err = -ENOBUFS; goto erridr; @@ -1092,7 +1098,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key)); + memcpy(&n->sel, s, sel_size); RCU_INIT_POINTER(n->ht_up, ht); n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 98541c6399db..85e73f48e48f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1311,6 +1311,18 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) * Delete/get qdisc. */ +const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { + [TCA_KIND] = { .type = NLA_STRING }, + [TCA_OPTIONS] = { .type = NLA_NESTED }, + [TCA_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct tc_estimator) }, + [TCA_STAB] = { .type = NLA_NESTED }, + [TCA_DUMP_INVISIBLE] = { .type = NLA_FLAG }, + [TCA_CHAIN] = { .type = NLA_U32 }, + [TCA_INGRESS_BLOCK] = { .type = NLA_U32 }, + [TCA_EGRESS_BLOCK] = { .type = NLA_U32 }, +}; + static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -1327,7 +1339,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); + err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, + extack); if (err < 0) return err; @@ -1411,7 +1424,8 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, replay: /* Reinit, just in case something touches this. */ - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); + err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, + extack); if (err < 0) return err; @@ -1645,7 +1659,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; ASSERT_RTNL(); - err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, NULL, NULL); + err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, + rtm_tca_policy, NULL); if (err < 0) return err; @@ -1864,7 +1879,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); + err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, + extack); if (err < 0) return err; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 35fc7252187c..793016d722ec 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -64,7 +64,6 @@ #include <linux/vmalloc.h> #include <linux/reciprocal_div.h> #include <net/netlink.h> -#include <linux/version.h> #include <linux/if_vlan.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -621,15 +620,20 @@ static bool cake_ddst(int flow_mode) } static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, - int flow_mode) + int flow_mode, u16 flow_override, u16 host_override) { - u32 flow_hash = 0, srchost_hash, dsthost_hash; + u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0; u16 reduced_hash, srchost_idx, dsthost_idx; struct flow_keys keys, host_keys; if (unlikely(flow_mode == CAKE_FLOW_NONE)) return 0; + /* If both overrides are set we can skip packet dissection entirely */ + if ((flow_override || !(flow_mode & CAKE_FLOW_FLOWS)) && + (host_override || !(flow_mode & CAKE_FLOW_HOSTS))) + goto skip_hash; + skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); @@ -676,6 +680,14 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, if (flow_mode & CAKE_FLOW_FLOWS) flow_hash = flow_hash_from_keys(&keys); +skip_hash: + if (flow_override) + flow_hash = flow_override - 1; + if (host_override) { + dsthost_hash = host_override - 1; + srchost_hash = host_override - 1; + } + if (!(flow_mode & CAKE_FLOW_FLOWS)) { if (flow_mode & CAKE_FLOW_SRC_IP) flow_hash ^= srchost_hash; @@ -1571,7 +1583,7 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, struct cake_sched_data *q = qdisc_priv(sch); struct tcf_proto *filter; struct tcf_result res; - u32 flow = 0; + u16 flow = 0, host = 0; int result; filter = rcu_dereference_bh(q->filter_list); @@ -1595,10 +1607,12 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, #endif if (TC_H_MIN(res.classid) <= CAKE_QUEUES) flow = TC_H_MIN(res.classid); + if (TC_H_MAJ(res.classid) <= (CAKE_QUEUES << 16)) + host = TC_H_MAJ(res.classid) >> 16; } hash: *t = cake_select_tin(sch, skb); - return flow ?: cake_hash(*t, skb, flow_mode) + 1; + return cake_hash(*t, skb, flow_mode, flow, host) + 1; } static void cake_reconfigure(struct Qdisc *sch); @@ -2630,7 +2644,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, for (i = 1; i <= CAKE_QUEUES; i++) quantum_div[i] = 65535 / i; - q->tins = kvzalloc(CAKE_MAX_TINS * sizeof(struct cake_tin_data), + q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) goto nomem; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index d74d00b29942..42191ed9902b 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1048,7 +1048,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, if (!ctx->packet || !ctx->packet->has_cookie_echo) return; - /* fallthru */ + /* fall through */ case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: diff --git a/net/sctp/proc.c b/net/sctp/proc.c index ef5c9a82d4e8..a644292f9faf 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -215,7 +215,6 @@ static const struct seq_operations sctp_eps_ops = { struct sctp_ht_iter { struct seq_net_private p; struct rhashtable_iter hti; - int start_fail; }; static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) @@ -224,7 +223,6 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) sctp_transport_walk_start(&iter->hti); - iter->start_fail = 0; return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos); } @@ -232,8 +230,6 @@ static void sctp_transport_seq_stop(struct seq_file *seq, void *v) { struct sctp_ht_iter *iter = seq->private; - if (iter->start_fail) - return; sctp_transport_walk_stop(&iter->hti); } @@ -264,8 +260,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) } transport = (struct sctp_transport *)v; - if (!sctp_transport_hold(transport)) - return 0; assoc = transport->asoc; epb = &assoc->base; sk = epb->sk; @@ -322,8 +316,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) } transport = (struct sctp_transport *)v; - if (!sctp_transport_hold(transport)) - return 0; assoc = transport->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e96b15a66aba..f73e9d38d5ba 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2658,20 +2658,23 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } if (params->spp_flags & SPP_IPV6_FLOWLABEL) { - if (trans && trans->ipaddr.sa.sa_family == AF_INET6) { - trans->flowlabel = params->spp_ipv6_flowlabel & - SCTP_FLOWLABEL_VAL_MASK; - trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; - } else if (asoc) { - list_for_each_entry(trans, - &asoc->peer.transport_addr_list, - transports) { - if (trans->ipaddr.sa.sa_family != AF_INET6) - continue; + if (trans) { + if (trans->ipaddr.sa.sa_family == AF_INET6) { trans->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } + } else if (asoc) { + struct sctp_transport *t; + + list_for_each_entry(t, &asoc->peer.transport_addr_list, + transports) { + if (t->ipaddr.sa.sa_family != AF_INET6) + continue; + t->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + t->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } asoc->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK; @@ -2687,12 +2690,13 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; trans->dscp |= SCTP_DSCP_SET_MASK; } else if (asoc) { - list_for_each_entry(trans, - &asoc->peer.transport_addr_list, + struct sctp_transport *t; + + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { - trans->dscp = params->spp_dscp & - SCTP_DSCP_VAL_MASK; - trans->dscp |= SCTP_DSCP_SET_MASK; + t->dscp = params->spp_dscp & + SCTP_DSCP_VAL_MASK; + t->dscp |= SCTP_DSCP_SET_MASK; } asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; asoc->dscp |= SCTP_DSCP_SET_MASK; @@ -5005,9 +5009,14 @@ struct sctp_transport *sctp_transport_get_next(struct net *net, break; } + if (!sctp_transport_hold(t)) + continue; + if (net_eq(sock_net(t->asoc->base.sk), net) && t->asoc->peer.primary_path == t) break; + + sctp_transport_put(t); } return t; @@ -5017,13 +5026,18 @@ struct sctp_transport *sctp_transport_get_idx(struct net *net, struct rhashtable_iter *iter, int pos) { - void *obj = SEQ_START_TOKEN; + struct sctp_transport *t; - while (pos && (obj = sctp_transport_get_next(net, iter)) && - !IS_ERR(obj)) - pos--; + if (!pos) + return SEQ_START_TOKEN; - return obj; + while ((t = sctp_transport_get_next(net, iter)) && !IS_ERR(t)) { + if (!--pos) + break; + sctp_transport_put(t); + } + + return t; } int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), @@ -5082,8 +5096,6 @@ again: tsp = sctp_transport_get_idx(net, &hti, *pos + 1); for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) { - if (!sctp_transport_hold(tsp)) - continue; ret = cb(tsp, p); if (ret) break; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 12cac85da994..033696e6f74f 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -260,6 +260,7 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { struct dst_entry *dst = sctp_transport_dst_check(t); + struct sock *sk = t->asoc->base.sk; bool change = true; if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { @@ -271,12 +272,19 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) pmtu = SCTP_TRUNC4(pmtu); if (dst) { - dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu); + struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family); + union sctp_addr addr; + + pf->af->from_sk(&addr, sk); + pf->to_sk_daddr(&t->ipaddr, sk); + dst->ops->update_pmtu(dst, sk, NULL, pmtu); + pf->to_sk_daddr(&addr, sk); + dst = sctp_transport_dst_check(t); } if (!dst) { - t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk); + t->af_specific->get_dst(t, &t->saddr, &t->fl, sk); dst = t->dst; } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 2d8a1e15e4f9..015231789ed2 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -742,7 +742,10 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_err = -rc; out: - smc->sk.sk_state_change(&smc->sk); + if (smc->sk.sk_err) + smc->sk.sk_state_change(&smc->sk); + else + smc->sk.sk_write_space(&smc->sk); kfree(smc->connect_info); smc->connect_info = NULL; release_sock(&smc->sk); @@ -1150,9 +1153,9 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) } /* listen worker: finish RDMA setup */ -static void smc_listen_rdma_finish(struct smc_sock *new_smc, - struct smc_clc_msg_accept_confirm *cclc, - int local_contact) +static int smc_listen_rdma_finish(struct smc_sock *new_smc, + struct smc_clc_msg_accept_confirm *cclc, + int local_contact) { struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK]; int reason_code = 0; @@ -1175,11 +1178,12 @@ static void smc_listen_rdma_finish(struct smc_sock *new_smc, if (reason_code) goto decline; } - return; + return 0; decline: mutex_unlock(&smc_create_lgr_pending); smc_listen_decline(new_smc, reason_code, local_contact); + return reason_code; } /* setup for RDMA connection of server */ @@ -1276,8 +1280,10 @@ static void smc_listen_work(struct work_struct *work) } /* finish worker */ - if (!ism_supported) - smc_listen_rdma_finish(new_smc, &cclc, local_contact); + if (!ism_supported) { + if (smc_listen_rdma_finish(new_smc, &cclc, local_contact)) + return; + } smc_conn_save_peer_info(new_smc, &cclc); mutex_unlock(&smc_create_lgr_pending); smc_listen_out_connected(new_smc); @@ -1529,7 +1535,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, return EPOLLNVAL; smc = smc_sk(sock->sk); - if ((sk->sk_state == SMC_INIT) || smc->use_fallback) { + if (smc->use_fallback) { /* delegate to CLC child sock */ mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); sk->sk_err = smc->clcsock->sk->sk_err; @@ -1560,9 +1566,9 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (sk->sk_state == SMC_APPCLOSEWAIT1) mask |= EPOLLIN; + if (smc->conn.urg_state == SMC_URG_VALID) + mask |= EPOLLPRI; } - if (smc->conn.urg_state == SMC_URG_VALID) - mask |= EPOLLPRI; } return mask; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 83aba9ade060..52241d679cc9 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -446,14 +446,12 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, vec[i++].iov_len = sizeof(trl); /* due to the few bytes needed for clc-handshake this cannot block */ len = kernel_sendmsg(smc->clcsock, &msg, vec, i, plen); - if (len < sizeof(pclc)) { - if (len >= 0) { - reason_code = -ENETUNREACH; - smc->sk.sk_err = -reason_code; - } else { - smc->sk.sk_err = smc->clcsock->sk->sk_err; - reason_code = -smc->sk.sk_err; - } + if (len < 0) { + smc->sk.sk_err = smc->clcsock->sk->sk_err; + reason_code = -smc->sk.sk_err; + } else if (len < (int)sizeof(pclc)) { + reason_code = -ENETUNREACH; + smc->sk.sk_err = -reason_code; } return reason_code; diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index ac961dfb1ea1..ea2b87f29469 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -100,15 +100,14 @@ static void smc_close_active_abort(struct smc_sock *smc) struct smc_cdc_conn_state_flags *txflags = &smc->conn.local_tx_ctrl.conn_state_flags; - sk->sk_err = ECONNABORTED; - if (smc->clcsock && smc->clcsock->sk) { - smc->clcsock->sk->sk_err = ECONNABORTED; - smc->clcsock->sk->sk_state_change(smc->clcsock->sk); + if (sk->sk_state != SMC_INIT && smc->clcsock && smc->clcsock->sk) { + sk->sk_err = ECONNABORTED; + if (smc->clcsock && smc->clcsock->sk) { + smc->clcsock->sk->sk_err = ECONNABORTED; + smc->clcsock->sk->sk_state_change(smc->clcsock->sk); + } } switch (sk->sk_state) { - case SMC_INIT: - sk->sk_state = SMC_PEERABORTWAIT; - break; case SMC_ACTIVE: sk->sk_state = SMC_PEERABORTWAIT; release_sock(sk); @@ -143,6 +142,7 @@ static void smc_close_active_abort(struct smc_sock *smc) case SMC_PEERFINCLOSEWAIT: sock_put(sk); /* passive closing */ break; + case SMC_INIT: case SMC_PEERABORTWAIT: case SMC_CLOSED: break; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 01c6ce042a1c..7cb3e4f07c10 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -461,7 +461,7 @@ static const struct genl_ops smc_pnet_ops[] = { }; /* SMC_PNETID family definition */ -static struct genl_family smc_pnet_nl_family = { +static struct genl_family smc_pnet_nl_family __ro_after_init = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, diff --git a/net/socket.c b/net/socket.c index e6945e318f02..01f3f8f32d6f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -941,7 +941,8 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg, + unsigned int ifreq_size) { int err; void __user *argp = (void __user *)arg; @@ -967,11 +968,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (copy_from_user(&ifr, argp, ifreq_size)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (copy_to_user(argp, &ifr, ifreq_size)) return -EFAULT; } return err; @@ -1070,7 +1071,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg); + err = sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct ifreq)); break; } return err; @@ -2750,7 +2752,8 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2766,7 +2769,8 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -3072,7 +3076,8 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, + sizeof(struct compat_ifreq)); set_fs(old_fs); out: @@ -3185,7 +3190,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg); + return sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct compat_ifreq)); } return -ENOIOCTLCMD; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 9ee6cfea56dd..d8026543bf4c 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -51,12 +51,12 @@ const char tipc_bclink_name[] = "broadcast-link"; * struct tipc_bc_base - base structure for keeping broadcast send state * @link: broadcast send link structure * @inputq: data input queue; will only carry SOCK_WAKEUP messages - * @dest: array keeping number of reachable destinations per bearer + * @dests: array keeping number of reachable destinations per bearer * @primary_bearer: a bearer having links to all broadcast destinations, if any * @bcast_support: indicates if primary bearer, if any, supports broadcast * @rcast_support: indicates if all peer nodes support replicast * @rc_ratio: dest count as percentage of cluster size where send method changes - * @bc_threshold: calculated drom rc_ratio; if dests > threshold use broadcast + * @bc_threshold: calculated from rc_ratio; if dests > threshold use broadcast */ struct tipc_bc_base { struct tipc_link *link; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 418f03d0be90..645c16052052 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -609,16 +609,18 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, switch (evt) { case NETDEV_CHANGE: - if (netif_carrier_ok(dev)) + if (netif_carrier_ok(dev) && netif_oper_up(dev)) { + test_and_set_bit_lock(0, &b->up); break; - /* else: fall through */ - case NETDEV_UP: - test_and_set_bit_lock(0, &b->up); - break; + } + /* fall through */ case NETDEV_GOING_DOWN: clear_bit_unlock(0, &b->up); tipc_reset_bearer(net, b); break; + case NETDEV_UP: + test_and_set_bit_lock(0, &b->up); + break; case NETDEV_CHANGEMTU: if (tipc_mtu_bad(dev, 0)) { bearer_disable(net, b); diff --git a/net/tipc/diag.c b/net/tipc/diag.c index aaabb0b776dd..73137f4aeb68 100644 --- a/net/tipc/diag.c +++ b/net/tipc/diag.c @@ -84,7 +84,9 @@ static int tipc_sock_diag_handler_dump(struct sk_buff *skb, if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = tipc_dump_start, .dump = tipc_diag_dump, + .done = tipc_dump_done, }; netlink_dump_start(net->diag_nlsk, skb, h, &c); return 0; diff --git a/net/tipc/link.c b/net/tipc/link.c index b1f0bee54eac..f6552e4f4b43 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -410,6 +410,11 @@ char *tipc_link_name(struct tipc_link *l) return l->name; } +u32 tipc_link_state(struct tipc_link *l) +{ + return l->state; +} + /** * tipc_link_create - create a new link * @n: pointer to associated node @@ -472,6 +477,8 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, l->in_session = false; l->bearer_id = bearer_id; l->tolerance = tolerance; + if (bc_rcvlink) + bc_rcvlink->tolerance = tolerance; l->net_plane = net_plane; l->advertised_mtu = mtu; l->mtu = mtu; @@ -838,12 +845,24 @@ static void link_prepare_wakeup(struct tipc_link *l) void tipc_link_reset(struct tipc_link *l) { + struct sk_buff_head list; + + __skb_queue_head_init(&list); + l->in_session = false; l->session++; l->mtu = l->advertised_mtu; + + spin_lock_bh(&l->wakeupq.lock); + skb_queue_splice_init(&l->wakeupq, &list); + spin_unlock_bh(&l->wakeupq.lock); + + spin_lock_bh(&l->inputq->lock); + skb_queue_splice_init(&list, l->inputq); + spin_unlock_bh(&l->inputq->lock); + __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); - skb_queue_splice_init(&l->wakeupq, l->inputq); __skb_queue_purge(&l->backlogq); l->backlog[TIPC_LOW_IMPORTANCE].len = 0; l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; @@ -1021,7 +1040,7 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r, /* Detect repeated retransmit failures on same packet */ if (r->last_retransm != buf_seqno(skb)) { r->last_retransm = buf_seqno(skb); - r->stale_limit = jiffies + msecs_to_jiffies(l->tolerance); + r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance); } else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) { link_retransmit_failure(l, skb); if (link_is_bc_sndlink(l)) @@ -1380,6 +1399,36 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, __skb_queue_tail(xmitq, skb); } +void tipc_link_create_dummy_tnl_msg(struct tipc_link *l, + struct sk_buff_head *xmitq) +{ + u32 onode = tipc_own_addr(l->net); + struct tipc_msg *hdr, *ihdr; + struct sk_buff_head tnlq; + struct sk_buff *skb; + u32 dnode = l->addr; + + skb_queue_head_init(&tnlq); + skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG, + INT_H_SIZE, BASIC_H_SIZE, + dnode, onode, 0, 0, 0); + if (!skb) { + pr_warn("%sunable to create tunnel packet\n", link_co_err); + return; + } + + hdr = buf_msg(skb); + msg_set_msgcnt(hdr, 1); + msg_set_bearer_id(hdr, l->peer_bearer_id); + + ihdr = (struct tipc_msg *)msg_data(hdr); + tipc_msg_init(onode, ihdr, TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, + BASIC_H_SIZE, dnode); + msg_set_errcode(ihdr, TIPC_ERR_NO_PORT); + __skb_queue_tail(&tnlq, skb); + tipc_link_xmit(l, &tnlq, xmitq); +} + /* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets * with contents of the link's transmit and backlog queues. */ @@ -1476,6 +1525,9 @@ bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr) return false; if (session != curr_session) return false; + /* Extra sanity check */ + if (!link_is_up(l) && msg_ack(hdr)) + return false; if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO)) return true; /* Accept only STATE with new sequence number */ @@ -1533,9 +1585,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, strncpy(if_name, data, TIPC_MAX_IF_NAME); /* Update own tolerance if peer indicates a non-zero value */ - if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; - + l->bc_rcvlink->tolerance = peers_tol; + } /* Update own priority if peer's priority is higher */ if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; @@ -1561,9 +1614,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->rcv_nxt_state = msg_seqno(hdr) + 1; /* Update own tolerance if peer indicates a non-zero value */ - if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; - + l->bc_rcvlink->tolerance = peers_tol; + } /* Update own prio if peer indicates a different value */ if ((peers_prio != l->priority) && in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) { @@ -2180,6 +2234,8 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, struct sk_buff_head *xmitq) { l->tolerance = tol; + if (l->bc_rcvlink) + l->bc_rcvlink->tolerance = tol; if (link_is_up(l)) tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } diff --git a/net/tipc/link.h b/net/tipc/link.h index 7bc494a33fdf..90488c538a4e 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -88,6 +88,8 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, struct tipc_link **link); void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq); +void tipc_link_create_dummy_tnl_msg(struct tipc_link *tnl, + struct sk_buff_head *xmitq); void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq); int tipc_link_fsm_evt(struct tipc_link *l, int evt); bool tipc_link_is_up(struct tipc_link *l); @@ -107,6 +109,7 @@ u16 tipc_link_rcv_nxt(struct tipc_link *l); u16 tipc_link_acked(struct tipc_link *l); u32 tipc_link_id(struct tipc_link *l); char *tipc_link_name(struct tipc_link *l); +u32 tipc_link_state(struct tipc_link *l); char tipc_link_plane(struct tipc_link *l); int tipc_link_prio(struct tipc_link *l); int tipc_link_window(struct tipc_link *l); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 88f027b502f6..66d5b2c5987a 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -980,20 +980,17 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port) { - u64 value = (u64)node << 32 | port; struct tipc_dest *dst; list_for_each_entry(dst, l, list) { - if (dst->value != value) - continue; - return dst; + if (dst->node == node && dst->port == port) + return dst; } return NULL; } bool tipc_dest_push(struct list_head *l, u32 node, u32 port) { - u64 value = (u64)node << 32 | port; struct tipc_dest *dst; if (tipc_dest_find(l, node, port)) @@ -1002,7 +999,8 @@ bool tipc_dest_push(struct list_head *l, u32 node, u32 port) dst = kmalloc(sizeof(*dst), GFP_ATOMIC); if (unlikely(!dst)) return false; - dst->value = value; + dst->node = node; + dst->port = port; list_add(&dst->list, l); return true; } diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 0febba41da86..892bd750b85f 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -133,13 +133,8 @@ void tipc_nametbl_stop(struct net *net); struct tipc_dest { struct list_head list; - union { - struct { - u32 port; - u32 node; - }; - u64 value; - }; + u32 port; + u32 node; }; struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 6ff2254088f6..99ee419210ba 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -167,7 +167,9 @@ static const struct genl_ops tipc_genl_v2_ops[] = { }, { .cmd = TIPC_NL_SOCK_GET, + .start = tipc_dump_start, .dumpit = tipc_nl_sk_dump, + .done = tipc_dump_done, .policy = tipc_nl_policy, }, { diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index a2f76743c73a..6376467e78f8 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -185,6 +185,10 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; buf->sk = msg->dst_sk; + if (__tipc_dump_start(&cb, msg->net)) { + kfree_skb(buf); + return -ENOMEM; + } do { int rem; @@ -216,6 +220,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, err = 0; err_out: + tipc_dump_done(&cb); kfree_skb(buf); if (err == -EMSGSIZE) { diff --git a/net/tipc/node.c b/net/tipc/node.c index 68014f1b6976..2afc4f8c37a7 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -111,6 +111,7 @@ struct tipc_node { int action_flags; struct list_head list; int state; + bool failover_sent; u16 sync_point; int link_cnt; u16 working_links; @@ -680,6 +681,7 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id, *slot0 = bearer_id; *slot1 = bearer_id; tipc_node_fsm_evt(n, SELF_ESTABL_CONTACT_EVT); + n->failover_sent = false; n->action_flags |= TIPC_NOTIFY_NODE_UP; tipc_link_set_active(nl, true); tipc_bcast_add_peer(n->net, nl, xmitq); @@ -911,6 +913,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, bool reset = true; char *if_name; unsigned long intv; + u16 session; *dupl_addr = false; *respond = false; @@ -997,9 +1000,10 @@ void tipc_node_check_dest(struct net *net, u32 addr, goto exit; if_name = strchr(b->name, ':') + 1; + get_random_bytes(&session, sizeof(u16)); if (!tipc_link_create(net, if_name, b->identity, b->tolerance, b->net_plane, b->mtu, b->priority, - b->window, mod(tipc_net(net)->random), + b->window, session, tipc_own_addr(net), addr, peer_id, n->capabilities, tipc_bc_sndlink(n->net), n->bc_entry.link, @@ -1615,6 +1619,14 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, tipc_skb_queue_splice_tail_init(tipc_link_inputq(pl), tipc_link_inputq(l)); } + /* If parallel link was already down, and this happened before + * the tunnel link came up, FAILOVER was never sent. Ensure that + * FAILOVER is sent to get peer out of NODE_FAILINGOVER state. + */ + if (n->state != NODE_FAILINGOVER && !n->failover_sent) { + tipc_link_create_dummy_tnl_msg(l, xmitq); + n->failover_sent = true; + } /* If pkts arrive out of order, use lowest calculated syncpt */ if (less(syncpt, n->sync_point)) n->sync_point = syncpt; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c1e93c9515bc..49810fdff4c5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -576,6 +576,7 @@ static int tipc_release(struct socket *sock) sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); + sock_orphan(sk); /* Reject any messages that accumulated in backlog queue */ release_sock(sk); tipc_dest_list_purge(&tsk->cong_links); @@ -1195,6 +1196,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, * @skb: pointer to message buffer. */ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); @@ -1212,7 +1214,16 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk), tsk_peer_port(tsk)); sk->sk_state_change(sk); - goto exit; + + /* State change is ignored if socket already awake, + * - convert msg to abort msg and add to inqueue + */ + msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE); + msg_set_type(hdr, TIPC_CONN_MSG); + msg_set_size(hdr, BASIC_H_SIZE); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); + __skb_queue_tail(inputq, skb); + return; } tsk->probe_unacked = false; @@ -1418,8 +1429,10 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) /* Handle implicit connection setup */ if (unlikely(dest)) { rc = __tipc_sendmsg(sock, m, dlen); - if (dlen && (dlen == rc)) + if (dlen && dlen == rc) { + tsk->peer_caps = tipc_node_get_capabilities(net, dnode); tsk->snt_unacked = tsk_inc(tsk, dlen + msg_hdr_sz(hdr)); + } return rc; } @@ -1933,7 +1946,7 @@ static void tipc_sk_proto_rcv(struct sock *sk, switch (msg_user(hdr)) { case CONN_MANAGER: - tipc_sk_conn_proto_rcv(tsk, skb, xmitq); + tipc_sk_conn_proto_rcv(tsk, skb, inputq, xmitq); return; case SOCK_WAKEUP: tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); @@ -2672,6 +2685,8 @@ void tipc_sk_reinit(struct net *net) rhashtable_walk_stop(&iter); } while (tsk == ERR_PTR(-EAGAIN)); + + rhashtable_walk_exit(&iter); } static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid) @@ -3227,45 +3242,74 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, struct netlink_callback *cb, struct tipc_sock *tsk)) { - struct net *net = sock_net(skb->sk); - struct tipc_net *tn = tipc_net(net); - const struct bucket_table *tbl; - u32 prev_portid = cb->args[1]; - u32 tbl_id = cb->args[0]; - struct rhash_head *pos; + struct rhashtable_iter *iter = (void *)cb->args[4]; struct tipc_sock *tsk; int err; - rcu_read_lock(); - tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht); - for (; tbl_id < tbl->size; tbl_id++) { - rht_for_each_entry_rcu(tsk, pos, tbl, tbl_id, node) { - spin_lock_bh(&tsk->sk.sk_lock.slock); - if (prev_portid && prev_portid != tsk->portid) { - spin_unlock_bh(&tsk->sk.sk_lock.slock); + rhashtable_walk_start(iter); + while ((tsk = rhashtable_walk_next(iter)) != NULL) { + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + if (err == -EAGAIN) { + err = 0; continue; } + break; + } - err = skb_handler(skb, cb, tsk); - if (err) { - prev_portid = tsk->portid; - spin_unlock_bh(&tsk->sk.sk_lock.slock); - goto out; - } - - prev_portid = 0; - spin_unlock_bh(&tsk->sk.sk_lock.slock); + sock_hold(&tsk->sk); + rhashtable_walk_stop(iter); + lock_sock(&tsk->sk); + err = skb_handler(skb, cb, tsk); + if (err) { + release_sock(&tsk->sk); + sock_put(&tsk->sk); + goto out; } + release_sock(&tsk->sk); + rhashtable_walk_start(iter); + sock_put(&tsk->sk); } + rhashtable_walk_stop(iter); out: - rcu_read_unlock(); - cb->args[0] = tbl_id; - cb->args[1] = prev_portid; - return skb->len; } EXPORT_SYMBOL(tipc_nl_sk_walk); +int tipc_dump_start(struct netlink_callback *cb) +{ + return __tipc_dump_start(cb, sock_net(cb->skb->sk)); +} +EXPORT_SYMBOL(tipc_dump_start); + +int __tipc_dump_start(struct netlink_callback *cb, struct net *net) +{ + /* tipc_nl_name_table_dump() uses cb->args[0...3]. */ + struct rhashtable_iter *iter = (void *)cb->args[4]; + struct tipc_net *tn = tipc_net(net); + + if (!iter) { + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + cb->args[4] = (long)iter; + } + + rhashtable_walk_enter(&tn->sk_rht, iter); + return 0; +} + +int tipc_dump_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *hti = (void *)cb->args[4]; + + rhashtable_walk_exit(hti); + kfree(hti); + return 0; +} +EXPORT_SYMBOL(tipc_dump_done); + int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, struct tipc_sock *tsk, u32 sk_filter_state, u64 (*tipc_diag_gen_cookie)(struct sock *sk)) diff --git a/net/tipc/socket.h b/net/tipc/socket.h index aff9b2ae5a1f..5e575f205afe 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -68,4 +68,7 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, int (*skb_handler)(struct sk_buff *skb, struct netlink_callback *cb, struct tipc_sock *tsk)); +int tipc_dump_start(struct netlink_callback *cb); +int __tipc_dump_start(struct netlink_callback *cb, struct net *net); +int tipc_dump_done(struct netlink_callback *cb); #endif diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index c8e34ef22c30..2627b5d812e9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -313,8 +313,8 @@ static void tipc_conn_send_work(struct work_struct *work) conn_put(con); } -/* tipc_conn_queue_evt() - interrupt level call from a subscription instance - * The queued work is launched into tipc_send_work()->tipc_send_to_sock() +/* tipc_topsrv_queue_evt() - interrupt level call from a subscription instance + * The queued work is launched into tipc_conn_send_work()->tipc_conn_send_to_sock() */ void tipc_topsrv_queue_evt(struct net *net, int conid, u32 event, struct tipc_event *evt) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 292742e50bfa..961b07d4d41c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -686,7 +686,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) goto free_marker_record; } - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; @@ -780,7 +780,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) ctx->priv_ctx_tx = offload_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, - &ctx->crypto_send, + &ctx->crypto_send.info, tcp_sk(sk)->write_seq); if (rc) goto release_netdev; @@ -862,7 +862,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, - &ctx->crypto_recv, + &ctx->crypto_recv.info, tcp_sk(sk)->copied_seq); if (rc) { pr_err_ratelimited("%s: The netdev has refused to offload this socket\n", diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 6102169239d1..450a6dbc5a88 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -320,7 +320,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, goto free_req; iv = buf; - memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt, + memcpy(iv, tls_ctx->crypto_send.aes_gcm_128.salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 93c0c225ab34..523622dc74f8 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -213,9 +213,14 @@ static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); - /* We are already sending pages, ignore notification */ - if (ctx->in_tcp_sendpages) + /* If in_tcp_sendpages call lower protocol write space handler + * to ensure we wake up any waiting operations there. For example + * if do_tcp_sendpages where to call sk_wait_event. + */ + if (ctx->in_tcp_sendpages) { + ctx->sk_write_space(sk); return; + } if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; @@ -236,6 +241,16 @@ static void tls_write_space(struct sock *sk) ctx->sk_write_space(sk); } +static void tls_ctx_free(struct tls_context *ctx) +{ + if (!ctx) + return; + + memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); + memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + kfree(ctx); +} + static void tls_sk_proto_close(struct sock *sk, long timeout) { struct tls_context *ctx = tls_get_ctx(sk); @@ -289,7 +304,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) #else { #endif - kfree(ctx); + tls_ctx_free(ctx); ctx = NULL; } @@ -300,7 +315,7 @@ skip_tx_cleanup: * for sk->sk_prot->unhash [tls_hw_unhash] */ if (free_ctx) - kfree(ctx); + tls_ctx_free(ctx); } static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, @@ -325,7 +340,7 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } /* get user crypto info */ - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; @@ -412,9 +427,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } if (tx) - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; else - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; /* Currently we don't support set crypto info more than one time */ if (TLS_CRYPTO_INFO_READY(crypto_info)) { @@ -494,7 +509,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, goto out; err_crypto_info: - memset(crypto_info, 0, sizeof(*crypto_info)); + memzero_explicit(crypto_info, sizeof(union tls_crypto_context)); out: return rc; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 52fbe727d7c1..b9c6ecfbcfea 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -125,6 +125,9 @@ static int alloc_encrypted_sg(struct sock *sk, int len) &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size, 0); + if (rc == -ENOSPC) + ctx->sg_encrypted_num_elem = ARRAY_SIZE(ctx->sg_encrypted_data); + return rc; } @@ -138,6 +141,9 @@ static int alloc_plaintext_sg(struct sock *sk, int len) &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size, tls_ctx->pending_open_record_frags); + if (rc == -ENOSPC) + ctx->sg_plaintext_num_elem = ARRAY_SIZE(ctx->sg_plaintext_data); + return rc; } @@ -925,7 +931,15 @@ int tls_sw_recvmsg(struct sock *sk, if (control != TLS_RECORD_TYPE_DATA) goto recv_end; } + } else { + /* MSG_PEEK right now cannot look beyond current skb + * from strparser, meaning we cannot advance skb here + * and thus unpause strparser since we'd loose original + * one. + */ + break; } + /* If we have a new message from strparser, continue now. */ if (copied >= target && !ctx->recv_pkt) break; @@ -1049,8 +1063,8 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } - if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) || - header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) { + if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) || + header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) { ret = -EINVAL; goto read_failure; } @@ -1130,7 +1144,6 @@ void tls_sw_free_resources_rx(struct sock *sk) int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { - char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; @@ -1175,12 +1188,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (tx) { crypto_init_wait(&sw_ctx_tx->async_wait); - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; } else { crypto_init_wait(&sw_ctx_rx->async_wait); - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; aead = &sw_ctx_rx->aead_recv; } @@ -1259,9 +1272,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ctx->push_pending_record = tls_sw_push_pending_record; - memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); - - rc = crypto_aead_setkey(*aead, keyval, + rc = crypto_aead_setkey(*aead, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); if (rc) goto free_aead; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5fb9b7dd9831..176edfefcbaa 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -669,13 +669,13 @@ static int nl80211_msg_put_wmm_rules(struct sk_buff *msg, goto nla_put_failure; if (nla_put_u16(msg, NL80211_WMMR_CW_MIN, - rule->wmm_rule->client[j].cw_min) || + rule->wmm_rule.client[j].cw_min) || nla_put_u16(msg, NL80211_WMMR_CW_MAX, - rule->wmm_rule->client[j].cw_max) || + rule->wmm_rule.client[j].cw_max) || nla_put_u8(msg, NL80211_WMMR_AIFSN, - rule->wmm_rule->client[j].aifsn) || - nla_put_u8(msg, NL80211_WMMR_TXOP, - rule->wmm_rule->client[j].cot)) + rule->wmm_rule.client[j].aifsn) || + nla_put_u16(msg, NL80211_WMMR_TXOP, + rule->wmm_rule.client[j].cot)) goto nla_put_failure; nla_nest_end(msg, nl_wmm_rule); @@ -766,9 +766,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if (large) { const struct ieee80211_reg_rule *rule = - freq_reg_info(wiphy, chan->center_freq); + freq_reg_info(wiphy, MHZ_TO_KHZ(chan->center_freq)); - if (!IS_ERR(rule) && rule->wmm_rule) { + if (!IS_ERR_OR_NULL(rule) && rule->has_wmm) { if (nl80211_msg_put_wmm_rules(msg, rule)) goto nla_put_failure; } @@ -3756,6 +3756,7 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband, return false; /* check availability */ + ridx = array_index_nospec(ridx, IEEE80211_HT_MCS_MASK_LEN); if (sband->ht_cap.mcs.rx_mask[ridx] & rbit) mcs[ridx] |= rbit; else @@ -10230,7 +10231,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev = dev->ieee80211_ptr; s32 last, low, high; u32 hyst; - int i, n; + int i, n, low_index; int err; /* RSSI reporting disabled? */ @@ -10267,10 +10268,19 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, if (last < wdev->cqm_config->rssi_thresholds[i]) break; - low = i > 0 ? - (wdev->cqm_config->rssi_thresholds[i - 1] - hyst) : S32_MIN; - high = i < n ? - (wdev->cqm_config->rssi_thresholds[i] + hyst - 1) : S32_MAX; + low_index = i - 1; + if (low_index >= 0) { + low_index = array_index_nospec(low_index, n); + low = wdev->cqm_config->rssi_thresholds[low_index] - hyst; + } else { + low = S32_MIN; + } + if (i < n) { + i = array_index_nospec(i, n); + high = wdev->cqm_config->rssi_thresholds[i] + hyst - 1; + } else { + high = S32_MAX; + } return rdev_set_cqm_rssi_range_config(rdev, dev, low, high); } @@ -12205,6 +12215,7 @@ static int nl80211_update_ft_ies(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; if (!info->attrs[NL80211_ATTR_MDID] || + !info->attrs[NL80211_ATTR_IE] || !is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 4fc66a117b7d..24cfa2776f50 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -425,36 +425,23 @@ static const struct ieee80211_regdomain * reg_copy_regd(const struct ieee80211_regdomain *src_regd) { struct ieee80211_regdomain *regd; - int size_of_regd, size_of_wmms; + int size_of_regd; unsigned int i; - struct ieee80211_wmm_rule *d_wmm, *s_wmm; size_of_regd = sizeof(struct ieee80211_regdomain) + src_regd->n_reg_rules * sizeof(struct ieee80211_reg_rule); - size_of_wmms = src_regd->n_wmm_rules * - sizeof(struct ieee80211_wmm_rule); - regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL); + regd = kzalloc(size_of_regd, GFP_KERNEL); if (!regd) return ERR_PTR(-ENOMEM); memcpy(regd, src_regd, sizeof(struct ieee80211_regdomain)); - d_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd); - s_wmm = (struct ieee80211_wmm_rule *)((u8 *)src_regd + size_of_regd); - memcpy(d_wmm, s_wmm, size_of_wmms); - - for (i = 0; i < src_regd->n_reg_rules; i++) { + for (i = 0; i < src_regd->n_reg_rules; i++) memcpy(®d->reg_rules[i], &src_regd->reg_rules[i], sizeof(struct ieee80211_reg_rule)); - if (!src_regd->reg_rules[i].wmm_rule) - continue; - regd->reg_rules[i].wmm_rule = d_wmm + - (src_regd->reg_rules[i].wmm_rule - s_wmm) / - sizeof(struct ieee80211_wmm_rule); - } return regd; } @@ -860,9 +847,10 @@ static bool valid_regdb(const u8 *data, unsigned int size) return true; } -static void set_wmm_rule(struct ieee80211_wmm_rule *rule, +static void set_wmm_rule(struct ieee80211_reg_rule *rrule, struct fwdb_wmm_rule *wmm) { + struct ieee80211_wmm_rule *rule = &rrule->wmm_rule; unsigned int i; for (i = 0; i < IEEE80211_NUM_ACS; i++) { @@ -876,11 +864,13 @@ static void set_wmm_rule(struct ieee80211_wmm_rule *rule, rule->ap[i].aifsn = wmm->ap[i].aifsn; rule->ap[i].cot = 1000 * be16_to_cpu(wmm->ap[i].cot); } + + rrule->has_wmm = true; } static int __regdb_query_wmm(const struct fwdb_header *db, const struct fwdb_country *country, int freq, - u32 *dbptr, struct ieee80211_wmm_rule *rule) + struct ieee80211_reg_rule *rule) { unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; struct fwdb_collection *coll = (void *)((u8 *)db + ptr); @@ -901,8 +891,6 @@ static int __regdb_query_wmm(const struct fwdb_header *db, wmm_ptr = be16_to_cpu(rrule->wmm_ptr) << 2; wmm = (void *)((u8 *)db + wmm_ptr); set_wmm_rule(rule, wmm); - if (dbptr) - *dbptr = wmm_ptr; return 0; } } @@ -910,8 +898,7 @@ static int __regdb_query_wmm(const struct fwdb_header *db, return -ENODATA; } -int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, - struct ieee80211_wmm_rule *rule) +int reg_query_regdb_wmm(char *alpha2, int freq, struct ieee80211_reg_rule *rule) { const struct fwdb_header *hdr = regdb; const struct fwdb_country *country; @@ -925,8 +912,7 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, country = &hdr->country[0]; while (country->coll_ptr) { if (alpha2_equal(alpha2, country->alpha2)) - return __regdb_query_wmm(regdb, country, freq, dbptr, - rule); + return __regdb_query_wmm(regdb, country, freq, rule); country++; } @@ -935,32 +921,13 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, } EXPORT_SYMBOL(reg_query_regdb_wmm); -struct wmm_ptrs { - struct ieee80211_wmm_rule *rule; - u32 ptr; -}; - -static struct ieee80211_wmm_rule *find_wmm_ptr(struct wmm_ptrs *wmm_ptrs, - u32 wmm_ptr, int n_wmms) -{ - int i; - - for (i = 0; i < n_wmms; i++) { - if (wmm_ptrs[i].ptr == wmm_ptr) - return wmm_ptrs[i].rule; - } - return NULL; -} - static int regdb_query_country(const struct fwdb_header *db, const struct fwdb_country *country) { unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; struct fwdb_collection *coll = (void *)((u8 *)db + ptr); struct ieee80211_regdomain *regdom; - struct ieee80211_regdomain *tmp_rd; - unsigned int size_of_regd, i, n_wmms = 0; - struct wmm_ptrs *wmm_ptrs; + unsigned int size_of_regd, i; size_of_regd = sizeof(struct ieee80211_regdomain) + coll->n_rules * sizeof(struct ieee80211_reg_rule); @@ -969,12 +936,6 @@ static int regdb_query_country(const struct fwdb_header *db, if (!regdom) return -ENOMEM; - wmm_ptrs = kcalloc(coll->n_rules, sizeof(*wmm_ptrs), GFP_KERNEL); - if (!wmm_ptrs) { - kfree(regdom); - return -ENOMEM; - } - regdom->n_reg_rules = coll->n_rules; regdom->alpha2[0] = country->alpha2[0]; regdom->alpha2[1] = country->alpha2[1]; @@ -1013,37 +974,11 @@ static int regdb_query_country(const struct fwdb_header *db, 1000 * be16_to_cpu(rule->cac_timeout); if (rule->len >= offsetofend(struct fwdb_rule, wmm_ptr)) { u32 wmm_ptr = be16_to_cpu(rule->wmm_ptr) << 2; - struct ieee80211_wmm_rule *wmm_pos = - find_wmm_ptr(wmm_ptrs, wmm_ptr, n_wmms); - struct fwdb_wmm_rule *wmm; - struct ieee80211_wmm_rule *wmm_rule; - - if (wmm_pos) { - rrule->wmm_rule = wmm_pos; - continue; - } - wmm = (void *)((u8 *)db + wmm_ptr); - tmp_rd = krealloc(regdom, size_of_regd + (n_wmms + 1) * - sizeof(struct ieee80211_wmm_rule), - GFP_KERNEL); - - if (!tmp_rd) { - kfree(regdom); - kfree(wmm_ptrs); - return -ENOMEM; - } - regdom = tmp_rd; - - wmm_rule = (struct ieee80211_wmm_rule *) - ((u8 *)regdom + size_of_regd + n_wmms * - sizeof(struct ieee80211_wmm_rule)); + struct fwdb_wmm_rule *wmm = (void *)((u8 *)db + wmm_ptr); - set_wmm_rule(wmm_rule, wmm); - wmm_ptrs[n_wmms].ptr = wmm_ptr; - wmm_ptrs[n_wmms++].rule = wmm_rule; + set_wmm_rule(rrule, wmm); } } - kfree(wmm_ptrs); return reg_schedule_apply(regdom); } @@ -2726,11 +2661,12 @@ static void reg_process_hint(struct regulatory_request *reg_request) { struct wiphy *wiphy = NULL; enum reg_request_treatment treatment; + enum nl80211_reg_initiator initiator = reg_request->initiator; if (reg_request->wiphy_idx != WIPHY_IDX_INVALID) wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx); - switch (reg_request->initiator) { + switch (initiator) { case NL80211_REGDOM_SET_BY_CORE: treatment = reg_process_hint_core(reg_request); break; @@ -2748,7 +2684,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) treatment = reg_process_hint_country_ie(wiphy, reg_request); break; default: - WARN(1, "invalid initiator %d\n", reg_request->initiator); + WARN(1, "invalid initiator %d\n", initiator); goto out_free; } @@ -2763,7 +2699,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) */ if (treatment == REG_REQ_ALREADY_SET && wiphy && wiphy->regulatory_flags & REGULATORY_STRICT_REG) { - wiphy_update_regulatory(wiphy, reg_request->initiator); + wiphy_update_regulatory(wiphy, initiator); wiphy_all_share_dfs_chan_state(wiphy); reg_check_channels(); } @@ -2932,6 +2868,7 @@ static int regulatory_hint_core(const char *alpha2) request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_CORE; + request->wiphy_idx = WIPHY_IDX_INVALID; queue_regulatory_request(request); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d36c3eb7b931..d0e7472dd9fd 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1058,13 +1058,23 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, return NULL; } +/* + * Update RX channel information based on the available frame payload + * information. This is mainly for the 2.4 GHz band where frames can be received + * from neighboring channels and the Beacon frames use the DSSS Parameter Set + * element to indicate the current (transmitting) channel, but this might also + * be needed on other bands if RX frequency does not match with the actual + * operating channel of a BSS. + */ static struct ieee80211_channel * cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, - struct ieee80211_channel *channel) + struct ieee80211_channel *channel, + enum nl80211_bss_scan_width scan_width) { const u8 *tmp; u32 freq; int channel_number = -1; + struct ieee80211_channel *alt_channel; tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen); if (tmp && tmp[1] == 1) { @@ -1078,16 +1088,45 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, } } - if (channel_number < 0) + if (channel_number < 0) { + /* No channel information in frame payload */ return channel; + } freq = ieee80211_channel_to_frequency(channel_number, channel->band); - channel = ieee80211_get_channel(wiphy, freq); - if (!channel) - return NULL; - if (channel->flags & IEEE80211_CHAN_DISABLED) + alt_channel = ieee80211_get_channel(wiphy, freq); + if (!alt_channel) { + if (channel->band == NL80211_BAND_2GHZ) { + /* + * Better not allow unexpected channels when that could + * be going beyond the 1-11 range (e.g., discovering + * BSS on channel 12 when radio is configured for + * channel 11. + */ + return NULL; + } + + /* No match for the payload channel number - ignore it */ + return channel; + } + + if (scan_width == NL80211_BSS_CHAN_WIDTH_10 || + scan_width == NL80211_BSS_CHAN_WIDTH_5) { + /* + * Ignore channel number in 5 and 10 MHz channels where there + * may not be an n:1 or 1:n mapping between frequencies and + * channel numbers. + */ + return channel; + } + + /* + * Use the channel determined through the payload channel number + * instead of the RX channel reported by the driver. + */ + if (alt_channel->flags & IEEE80211_CHAN_DISABLED) return NULL; - return channel; + return alt_channel; } /* Returned bss is reference counted and must be cleaned up appropriately. */ @@ -1112,7 +1151,8 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, (data->signal < 0 || data->signal > 100))) return NULL; - channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan); + channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan, + data->scan_width); if (!channel) return NULL; @@ -1210,7 +1250,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, return NULL; channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, - ielen, data->chan); + ielen, data->chan, data->scan_width); if (!channel) return NULL; diff --git a/net/wireless/util.c b/net/wireless/util.c index e0825a019e9f..959ed3acd240 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1456,7 +1456,7 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class) { u8 vht_opclass; - u16 freq = chandef->center_freq1; + u32 freq = chandef->center_freq1; if (freq >= 2412 && freq <= 2472) { if (chandef->width > NL80211_CHAN_WIDTH_40) diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 167f7025ac98..06943d9c9835 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1278,12 +1278,16 @@ static int cfg80211_wext_giwrate(struct net_device *dev, if (err) return err; - if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) - return -EOPNOTSUPP; + if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) { + err = -EOPNOTSUPP; + goto free; + } rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); - return 0; +free: + cfg80211_sinfo_release_content(&sinfo); + return err; } /* Get wireless statistics. Called by /proc/net/wireless and by SIOCGIWSTATS */ @@ -1293,7 +1297,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); /* we are under RTNL - globally locked - so can use static structs */ static struct iw_statistics wstats; - static struct station_info sinfo; + static struct station_info sinfo = {}; u8 bssid[ETH_ALEN]; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) @@ -1352,6 +1356,8 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED)) wstats.discard.retries = sinfo.tx_failed; + cfg80211_sinfo_release_content(&sinfo); + return &wstats; } diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 911ca6d3cb5a..bfe2dbea480b 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -74,14 +74,14 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, return 0; if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit) - return force_zc ? -ENOTSUPP : 0; /* fail or fallback */ + return force_zc ? -EOPNOTSUPP : 0; /* fail or fallback */ bpf.command = XDP_QUERY_XSK_UMEM; rtnl_lock(); err = xdp_umem_query(dev, queue_id); if (err) { - err = err < 0 ? -ENOTSUPP : -EBUSY; + err = err < 0 ? -EOPNOTSUPP : -EBUSY; goto err_rtnl_unlock; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index b89c9c7f8c5c..be3520e429c9 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -458,6 +458,7 @@ resume: XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } + crypto_done = false; } while (!err); err = xfrm_rcv_cb(skb, family, x->type->proto, 0); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 45ba07ab3e4f..261995d37ced 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -100,6 +100,10 @@ static int xfrm_output_one(struct sk_buff *skb, int err) spin_unlock_bh(&x->lock); skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + goto error_nolock; + } if (xfrm_offload(skb)) { x->type_offload->encap(x, skb); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 3110c3fbee20..f094d4b3520d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2491,6 +2491,10 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) } skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); + return 0; + } dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4791aa8b8185..df7ca2dabc48 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -151,10 +151,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, err = -EINVAL; switch (p->family) { case AF_INET: + if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) + goto out; + break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) + if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) + goto out; + break; #else err = -EAFNOSUPPORT; @@ -1396,10 +1402,16 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) switch (p->sel.family) { case AF_INET: + if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) + return -EINVAL; + break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) + if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) + return -EINVAL; + break; #else return -EAFNOSUPPORT; @@ -1480,6 +1492,9 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) (ut[i].family != prev_family)) return -EINVAL; + if (ut[i].mode >= XFRM_MODE_MAX) + return -EINVAL; + prev_family = ut[i].family; switch (ut[i].family) { |