diff options
author | Stefan Agner <stefan.agner@toradex.com> | 2016-03-29 13:02:23 -0700 |
---|---|---|
committer | Stefan Agner <stefan.agner@toradex.com> | 2016-03-29 13:02:23 -0700 |
commit | 1df133c0db64d633bbb9b238aa0e1588e2c5e7d6 (patch) | |
tree | c68d76907c523e81b5d0e8a924728f9e1aed1844 /net | |
parent | 2b7d39d1a28cb478627fc22fdc8dd77ed89ffe92 (diff) | |
parent | 62e21959dc6f25c5fce0c1a0934e4a9d982bf99b (diff) |
Merge tag 'v4.4.5' into toradex_vf_4.4-next
This is the 4.4.5 stable release
Diffstat (limited to 'net')
69 files changed, 601 insertions, 406 deletions
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 191a70290dca..f5d2fe5e31cc 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -127,21 +127,17 @@ batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw) } /* finally deinitialize the claim */ -static void batadv_claim_free_rcu(struct rcu_head *rcu) +static void batadv_claim_release(struct batadv_bla_claim *claim) { - struct batadv_bla_claim *claim; - - claim = container_of(rcu, struct batadv_bla_claim, rcu); - batadv_backbone_gw_free_ref(claim->backbone_gw); - kfree(claim); + kfree_rcu(claim, rcu); } /* free a claim, call claim_free_rcu if its the last reference */ static void batadv_claim_free_ref(struct batadv_bla_claim *claim) { if (atomic_dec_and_test(&claim->refcount)) - call_rcu(&claim->rcu, batadv_claim_free_rcu); + batadv_claim_release(claim); } /** diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 5a31420513e1..7b12ea8ea29d 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -75,18 +75,6 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu); } -/** - * batadv_hardif_free_ref_now - decrement the hard interface refcounter and - * possibly free it (without rcu callback) - * @hard_iface: the hard interface to free - */ -static inline void -batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface) -{ - if (atomic_dec_and_test(&hard_iface->refcount)) - batadv_hardif_free_rcu(&hard_iface->rcu); -} - static inline struct batadv_hard_iface * batadv_primary_if_get_selected(struct batadv_priv *bat_priv) { diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index f5276be2c77c..d0956f726547 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -203,28 +203,25 @@ void batadv_nc_init_orig(struct batadv_orig_node *orig_node) } /** - * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove - * its refcount on the orig_node - * @rcu: rcu pointer of the nc node + * batadv_nc_node_release - release nc_node from lists and queue for free after + * rcu grace period + * @nc_node: the nc node to free */ -static void batadv_nc_node_free_rcu(struct rcu_head *rcu) +static void batadv_nc_node_release(struct batadv_nc_node *nc_node) { - struct batadv_nc_node *nc_node; - - nc_node = container_of(rcu, struct batadv_nc_node, rcu); batadv_orig_node_free_ref(nc_node->orig_node); - kfree(nc_node); + kfree_rcu(nc_node, rcu); } /** - * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly - * frees it + * batadv_nc_node_free_ref - decrement the nc node refcounter and possibly + * release it * @nc_node: the nc node to free */ static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node) { if (atomic_dec_and_test(&nc_node->refcount)) - call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu); + batadv_nc_node_release(nc_node); } /** diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 7486df9ed48d..17851d3aaf22 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -163,92 +163,66 @@ err: } /** - * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object - * @rcu: rcu pointer of the neigh_ifinfo object - */ -static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu) -{ - struct batadv_neigh_ifinfo *neigh_ifinfo; - - neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu); - - if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) - batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing); - - kfree(neigh_ifinfo); -} - -/** - * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free - * the neigh_ifinfo (without rcu callback) + * batadv_neigh_ifinfo_release - release neigh_ifinfo from lists and queue for + * free after rcu grace period * @neigh_ifinfo: the neigh_ifinfo object to release */ static void -batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo) +batadv_neigh_ifinfo_release(struct batadv_neigh_ifinfo *neigh_ifinfo) { - if (atomic_dec_and_test(&neigh_ifinfo->refcount)) - batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu); + if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) + batadv_hardif_free_ref(neigh_ifinfo->if_outgoing); + + kfree_rcu(neigh_ifinfo, rcu); } /** - * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free + * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly release * the neigh_ifinfo * @neigh_ifinfo: the neigh_ifinfo object to release */ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo) { if (atomic_dec_and_test(&neigh_ifinfo->refcount)) - call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu); + batadv_neigh_ifinfo_release(neigh_ifinfo); } /** * batadv_neigh_node_free_rcu - free the neigh_node - * @rcu: rcu pointer of the neigh_node + * batadv_neigh_node_release - release neigh_node from lists and queue for + * free after rcu grace period + * @neigh_node: neigh neighbor to free */ -static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) +static void batadv_neigh_node_release(struct batadv_neigh_node *neigh_node) { struct hlist_node *node_tmp; - struct batadv_neigh_node *neigh_node; struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_algo_ops *bao; - neigh_node = container_of(rcu, struct batadv_neigh_node, rcu); bao = neigh_node->orig_node->bat_priv->bat_algo_ops; hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, &neigh_node->ifinfo_list, list) { - batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo); + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); } if (bao->bat_neigh_free) bao->bat_neigh_free(neigh_node); - batadv_hardif_free_ref_now(neigh_node->if_incoming); + batadv_hardif_free_ref(neigh_node->if_incoming); - kfree(neigh_node); -} - -/** - * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter - * and possibly free it (without rcu callback) - * @neigh_node: neigh neighbor to free - */ -static void -batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node) -{ - if (atomic_dec_and_test(&neigh_node->refcount)) - batadv_neigh_node_free_rcu(&neigh_node->rcu); + kfree_rcu(neigh_node, rcu); } /** * batadv_neigh_node_free_ref - decrement the neighbors refcounter - * and possibly free it + * and possibly release it * @neigh_node: neigh neighbor to free */ void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node) { if (atomic_dec_and_test(&neigh_node->refcount)) - call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu); + batadv_neigh_node_release(neigh_node); } /** @@ -532,108 +506,99 @@ out: } /** - * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object - * @rcu: rcu pointer of the orig_ifinfo object + * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for + * free after rcu grace period + * @orig_ifinfo: the orig_ifinfo object to release */ -static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) +static void batadv_orig_ifinfo_release(struct batadv_orig_ifinfo *orig_ifinfo) { - struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router; - orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); - if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) - batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + batadv_hardif_free_ref(orig_ifinfo->if_outgoing); /* this is the last reference to this object */ router = rcu_dereference_protected(orig_ifinfo->router, true); if (router) - batadv_neigh_node_free_ref_now(router); - kfree(orig_ifinfo); + batadv_neigh_node_free_ref(router); + + kfree_rcu(orig_ifinfo, rcu); } /** - * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free - * the orig_ifinfo (without rcu callback) + * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly release + * the orig_ifinfo * @orig_ifinfo: the orig_ifinfo object to release */ -static void -batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo) +void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) { if (atomic_dec_and_test(&orig_ifinfo->refcount)) - batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu); + batadv_orig_ifinfo_release(orig_ifinfo); } /** - * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free - * the orig_ifinfo - * @orig_ifinfo: the orig_ifinfo object to release + * batadv_orig_node_free_rcu - free the orig_node + * @rcu: rcu pointer of the orig_node */ -void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) +static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { - if (atomic_dec_and_test(&orig_ifinfo->refcount)) - call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu); + struct batadv_orig_node *orig_node; + + orig_node = container_of(rcu, struct batadv_orig_node, rcu); + + batadv_mcast_purge_orig(orig_node); + + batadv_frag_purge_orig(orig_node, NULL); + + if (orig_node->bat_priv->bat_algo_ops->bat_orig_free) + orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node); + + kfree(orig_node->tt_buff); + kfree(orig_node); } -static void batadv_orig_node_free_rcu(struct rcu_head *rcu) +/** + * batadv_orig_node_release - release orig_node from lists and queue for + * free after rcu grace period + * @orig_node: the orig node to free + */ +static void batadv_orig_node_release(struct batadv_orig_node *orig_node) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; - struct batadv_orig_node *orig_node; struct batadv_orig_ifinfo *orig_ifinfo; - orig_node = container_of(rcu, struct batadv_orig_node, rcu); - spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); - batadv_neigh_node_free_ref_now(neigh_node); + batadv_neigh_node_free_ref(neigh_node); } hlist_for_each_entry_safe(orig_ifinfo, node_tmp, &orig_node->ifinfo_list, list) { hlist_del_rcu(&orig_ifinfo->list); - batadv_orig_ifinfo_free_ref_now(orig_ifinfo); + batadv_orig_ifinfo_free_ref(orig_ifinfo); } spin_unlock_bh(&orig_node->neigh_list_lock); - batadv_mcast_purge_orig(orig_node); - /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); - batadv_frag_purge_orig(orig_node, NULL); - - if (orig_node->bat_priv->bat_algo_ops->bat_orig_free) - orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node); - - kfree(orig_node->tt_buff); - kfree(orig_node); + call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); } /** * batadv_orig_node_free_ref - decrement the orig node refcounter and possibly - * schedule an rcu callback for freeing it + * release it * @orig_node: the orig node to free */ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node) { if (atomic_dec_and_test(&orig_node->refcount)) - call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); -} - -/** - * batadv_orig_node_free_ref_now - decrement the orig node refcounter and - * possibly free it (without rcu callback) - * @orig_node: the orig node to free - */ -void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node) -{ - if (atomic_dec_and_test(&orig_node->refcount)) - batadv_orig_node_free_rcu(&orig_node->rcu); + batadv_orig_node_release(orig_node); } void batadv_originator_free(struct batadv_priv *bat_priv) diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index fa18f9bf266b..a5c37882b409 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -38,7 +38,6 @@ int batadv_originator_init(struct batadv_priv *bat_priv); void batadv_originator_free(struct batadv_priv *bat_priv); void batadv_purge_orig_ref(struct batadv_priv *bat_priv); void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node); -void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr); struct batadv_neigh_node * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 76f19ba62462..83b0ca27a45e 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -240,20 +240,6 @@ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, return count; } -static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) -{ - struct batadv_tt_orig_list_entry *orig_entry; - - orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); - - /* We are in an rcu callback here, therefore we cannot use - * batadv_orig_node_free_ref() and its call_rcu(): - * An rcu_barrier() wouldn't wait for that to finish - */ - batadv_orig_node_free_ref_now(orig_entry->orig_node); - kfree(orig_entry); -} - /** * batadv_tt_local_size_mod - change the size by v of the local table identified * by vid @@ -349,13 +335,25 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node, batadv_tt_global_size_mod(orig_node, vid, -1); } +/** + * batadv_tt_orig_list_entry_release - release tt orig entry from lists and + * queue for free after rcu grace period + * @orig_entry: tt orig entry to be free'd + */ +static void +batadv_tt_orig_list_entry_release(struct batadv_tt_orig_list_entry *orig_entry) +{ + batadv_orig_node_free_ref(orig_entry->orig_node); + kfree_rcu(orig_entry, rcu); +} + static void batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry) { if (!atomic_dec_and_test(&orig_entry->refcount)) return; - call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); + batadv_tt_orig_list_entry_release(orig_entry); } /** diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 9e9cca3689a0..795ddd8b2f77 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -307,6 +307,9 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, /* check that it's our buffer */ if (lowpan_is_ipv6(*skb_network_header(skb))) { + /* Pull off the 1-byte of 6lowpan header. */ + skb_pull(skb, 1); + /* Copy the packet so that the IPv6 header is * properly aligned. */ @@ -317,6 +320,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; + local_skb->dev = dev; skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); @@ -335,6 +339,8 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, if (!local_skb) goto drop; + local_skb->dev = dev; + ret = iphc_decompress(local_skb, dev, chan); if (ret < 0) { kfree_skb(local_skb); @@ -343,7 +349,6 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; - local_skb->dev = dev; if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 85b82f7adbd2..24e9410923d0 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -722,8 +722,12 @@ static void hci_req_add_le_create_conn(struct hci_request *req, if (hci_update_random_address(req, false, &own_addr_type)) return; + /* Set window to be the same value as the interval to enable + * continuous scanning. + */ cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); - cp.scan_window = cpu_to_le16(hdev->le_scan_window); + cp.scan_window = cp.scan_interval; + bacpy(&cp.peer_addr, &conn->dst); cp.peer_addr_type = conn->dst_type; cp.own_address_type = own_addr_type; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 981f8a202c27..02778c5bc149 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -175,21 +175,29 @@ static u8 update_white_list(struct hci_request *req) * command to remove it from the controller. */ list_for_each_entry(b, &hdev->le_white_list, list) { - struct hci_cp_le_del_from_white_list cp; + /* If the device is neither in pend_le_conns nor + * pend_le_reports then remove it from the whitelist. + */ + if (!hci_pend_le_action_lookup(&hdev->pend_le_conns, + &b->bdaddr, b->bdaddr_type) && + !hci_pend_le_action_lookup(&hdev->pend_le_reports, + &b->bdaddr, b->bdaddr_type)) { + struct hci_cp_le_del_from_white_list cp; + + cp.bdaddr_type = b->bdaddr_type; + bacpy(&cp.bdaddr, &b->bdaddr); - if (hci_pend_le_action_lookup(&hdev->pend_le_conns, - &b->bdaddr, b->bdaddr_type) || - hci_pend_le_action_lookup(&hdev->pend_le_reports, - &b->bdaddr, b->bdaddr_type)) { - white_list_entries++; + hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, + sizeof(cp), &cp); continue; } - cp.bdaddr_type = b->bdaddr_type; - bacpy(&cp.bdaddr, &b->bdaddr); + if (hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) { + /* White list can not be used with RPAs */ + return 0x00; + } - hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, - sizeof(cp), &cp); + white_list_entries++; } /* Since all no longer valid white list entries have been diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ffed8a1d4f27..4b175df35184 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1072,22 +1072,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) hcon->dst_type = smp->remote_irk->addr_type; queue_work(hdev->workqueue, &conn->id_addr_update_work); } - - /* When receiving an indentity resolving key for - * a remote device that does not use a resolvable - * private address, just remove the key so that - * it is possible to use the controller white - * list for scanning. - * - * Userspace will have been told to not store - * this key at this point. So it is safe to - * just remove it. - */ - if (!bacmp(&smp->remote_irk->rpa, BDADDR_ANY)) { - list_del_rcu(&smp->remote_irk->list); - kfree_rcu(smp->remote_irk, rcu); - smp->remote_irk = NULL; - } } if (smp->csrk) { diff --git a/net/bridge/br.c b/net/bridge/br.c index a1abe4936fe1..3addc05b9a16 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,6 +121,7 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; +/* called with RTNL */ static int br_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -130,7 +131,6 @@ static int br_switchdev_event(struct notifier_block *unused, struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; - rtnl_lock(); p = br_port_get_rtnl(dev); if (!p) goto out; @@ -155,7 +155,6 @@ static int br_switchdev_event(struct notifier_block *unused, } out: - rtnl_unlock(); return err; } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 5e88d3e17546..2c8095a5d824 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -28,6 +28,8 @@ const struct nf_br_ops __rcu *nf_br_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_br_ops); +static struct lock_class_key bridge_netdev_addr_lock_key; + /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -87,6 +89,11 @@ out: return NETDEV_TX_OK; } +static void br_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); +} + static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -99,6 +106,7 @@ static int br_dev_init(struct net_device *dev) err = br_vlan_init(br); if (err) free_percpu(br->stats); + br_set_lockdep_class(dev); return err; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9981039ef4ff..63ae5dd24fc5 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -672,6 +672,8 @@ static void reset_connection(struct ceph_connection *con) } con->in_seq = 0; con->in_seq_acked = 0; + + con->out_skip = 0; } /* @@ -771,6 +773,8 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt) static void con_out_kvec_reset(struct ceph_connection *con) { + BUG_ON(con->out_skip); + con->out_kvec_left = 0; con->out_kvec_bytes = 0; con->out_kvec_cur = &con->out_kvec[0]; @@ -779,9 +783,9 @@ static void con_out_kvec_reset(struct ceph_connection *con) static void con_out_kvec_add(struct ceph_connection *con, size_t size, void *data) { - int index; + int index = con->out_kvec_left; - index = con->out_kvec_left; + BUG_ON(con->out_skip); BUG_ON(index >= ARRAY_SIZE(con->out_kvec)); con->out_kvec[index].iov_len = size; @@ -790,6 +794,27 @@ static void con_out_kvec_add(struct ceph_connection *con, con->out_kvec_bytes += size; } +/* + * Chop off a kvec from the end. Return residual number of bytes for + * that kvec, i.e. how many bytes would have been written if the kvec + * hadn't been nuked. + */ +static int con_out_kvec_skip(struct ceph_connection *con) +{ + int off = con->out_kvec_cur - con->out_kvec; + int skip = 0; + + if (con->out_kvec_bytes > 0) { + skip = con->out_kvec[off + con->out_kvec_left - 1].iov_len; + BUG_ON(con->out_kvec_bytes < skip); + BUG_ON(!con->out_kvec_left); + con->out_kvec_bytes -= skip; + con->out_kvec_left--; + } + + return skip; +} + #ifdef CONFIG_BLOCK /* @@ -1175,6 +1200,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, return new_piece; } +static size_t sizeof_footer(struct ceph_connection *con) +{ + return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ? + sizeof(struct ceph_msg_footer) : + sizeof(struct ceph_msg_footer_old); +} + static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { BUG_ON(!msg); @@ -1197,7 +1229,6 @@ static void prepare_write_message_footer(struct ceph_connection *con) m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE; dout("prepare_write_message_footer %p\n", con); - con->out_kvec_is_msg = true; con->out_kvec[v].iov_base = &m->footer; if (con->peer_features & CEPH_FEATURE_MSG_AUTH) { if (con->ops->sign_message) @@ -1225,7 +1256,6 @@ static void prepare_write_message(struct ceph_connection *con) u32 crc; con_out_kvec_reset(con); - con->out_kvec_is_msg = true; con->out_msg_done = false; /* Sneak an ack in there first? If we can get it into the same @@ -1265,18 +1295,19 @@ static void prepare_write_message(struct ceph_connection *con) /* tag + hdr + front + middle */ con_out_kvec_add(con, sizeof (tag_msg), &tag_msg); - con_out_kvec_add(con, sizeof (m->hdr), &m->hdr); + con_out_kvec_add(con, sizeof(con->out_hdr), &con->out_hdr); con_out_kvec_add(con, m->front.iov_len, m->front.iov_base); if (m->middle) con_out_kvec_add(con, m->middle->vec.iov_len, m->middle->vec.iov_base); - /* fill in crc (except data pages), footer */ + /* fill in hdr crc and finalize hdr */ crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc)); con->out_msg->hdr.crc = cpu_to_le32(crc); - con->out_msg->footer.flags = 0; + memcpy(&con->out_hdr, &con->out_msg->hdr, sizeof(con->out_hdr)); + /* fill in front and middle crc, footer */ crc = crc32c(0, m->front.iov_base, m->front.iov_len); con->out_msg->footer.front_crc = cpu_to_le32(crc); if (m->middle) { @@ -1288,6 +1319,7 @@ static void prepare_write_message(struct ceph_connection *con) dout("%s front_crc %u middle_crc %u\n", __func__, le32_to_cpu(con->out_msg->footer.front_crc), le32_to_cpu(con->out_msg->footer.middle_crc)); + con->out_msg->footer.flags = 0; /* is there a data payload? */ con->out_msg->footer.data_crc = 0; @@ -1492,7 +1524,6 @@ static int write_partial_kvec(struct ceph_connection *con) } } con->out_kvec_left = 0; - con->out_kvec_is_msg = false; ret = 1; out: dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con, @@ -1584,6 +1615,7 @@ static int write_partial_skip(struct ceph_connection *con) { int ret; + dout("%s %p %d left\n", __func__, con, con->out_skip); while (con->out_skip > 0) { size_t size = min(con->out_skip, (int) PAGE_CACHE_SIZE); @@ -2313,9 +2345,9 @@ static int read_partial_message(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), seq, con->in_seq + 1); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; - return 0; + return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { pr_err("read_partial_message bad seq %lld expected %lld\n", seq, con->in_seq + 1); @@ -2338,10 +2370,10 @@ static int read_partial_message(struct ceph_connection *con) /* skip this message */ dout("alloc_msg said skip message\n"); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; - return 0; + return 1; } BUG_ON(!con->in_msg); @@ -2506,13 +2538,13 @@ more: more_kvec: /* kvec data queued? */ - if (con->out_skip) { - ret = write_partial_skip(con); + if (con->out_kvec_left) { + ret = write_partial_kvec(con); if (ret <= 0) goto out; } - if (con->out_kvec_left) { - ret = write_partial_kvec(con); + if (con->out_skip) { + ret = write_partial_skip(con); if (ret <= 0) goto out; } @@ -3050,16 +3082,31 @@ void ceph_msg_revoke(struct ceph_msg *msg) ceph_msg_put(msg); } if (con->out_msg == msg) { - dout("%s %p msg %p - was sending\n", __func__, con, msg); - con->out_msg = NULL; - if (con->out_kvec_is_msg) { - con->out_skip = con->out_kvec_bytes; - con->out_kvec_is_msg = false; + BUG_ON(con->out_skip); + /* footer */ + if (con->out_msg_done) { + con->out_skip += con_out_kvec_skip(con); + } else { + BUG_ON(!msg->data_length); + if (con->peer_features & CEPH_FEATURE_MSG_AUTH) + con->out_skip += sizeof(msg->footer); + else + con->out_skip += sizeof(msg->old_footer); } + /* data, middle, front */ + if (msg->data_length) + con->out_skip += msg->cursor.total_resid; + if (msg->middle) + con->out_skip += con_out_kvec_skip(con); + con->out_skip += con_out_kvec_skip(con); + + dout("%s %p msg %p - was sending, will write %d skip %d\n", + __func__, con, msg, con->out_kvec_bytes, con->out_skip); msg->hdr.seq = 0; - + con->out_msg = NULL; ceph_msg_put(msg); } + mutex_unlock(&con->mutex); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index f8f235930d88..a28e47ff1b1b 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2843,8 +2843,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); if (!req) { - pr_warn("%s osd%d tid %llu unknown, skipping\n", - __func__, osd->o_osd, tid); + dout("%s osd%d tid %llu unknown, skipping\n", __func__, + osd->o_osd, tid); m = NULL; *skip = 1; goto out; diff --git a/net/core/dev.c b/net/core/dev.c index ae00b894e675..9efbdb3ff78a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2542,6 +2542,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. + * + * Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) @@ -2556,6 +2558,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return ERR_PTR(err); } + BUILD_BUG_ON(SKB_SGO_CB_OFFSET + + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); SKB_GSO_CB(skb)->encap_level = 0; @@ -4140,6 +4145,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; + diffs |= skb_metadata_dst_cmp(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); @@ -4337,10 +4343,12 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) break; case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { + skb_dst_drop(skb); kmem_cache_free(skbuff_head_cache, skb); - else + } else { __kfree_skb(skb); + } break; case GRO_HELD: @@ -7120,8 +7128,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); - if (!dev->tx_queue_len) + if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; + dev->tx_queue_len = 1; + } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; diff --git a/net/core/filter.c b/net/core/filter.c index 672eefbfbe99..37157c4c1a78 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -777,6 +777,11 @@ static int bpf_check_classic(const struct sock_filter *filter, if (ftest->k == 0) return -EINVAL; break; + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + if (ftest->k >= 32) + return -EINVAL; + break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d79699c9d1b9..12e700332010 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -208,7 +208,6 @@ ip: case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; - __be32 flow_label; ipv6: iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); @@ -230,8 +229,12 @@ ipv6: key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - flow_label = ip6_flowlabel(iph); - if (flow_label) { + if ((dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL) || + (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) && + ip6_flowlabel(iph)) { + __be32 flow_label = ip6_flowlabel(iph); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, @@ -396,6 +399,13 @@ ip_proto_again: goto out_bad; proto = eth->h_proto; nhoff += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + hlen = nhoff; } key_control->flags |= FLOW_DIS_ENCAPSULATION; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index de8d5cc5eb24..4da4d51a2ccf 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2787,7 +2787,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, } else { skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); } - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + + if (likely(skb)) + skb_reserve(skb, LL_RESERVED_SPACE(dev)); return skb; } diff --git a/net/core/scm.c b/net/core/scm.c index 8a1741b14302..dce0acb929f1 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fplp = fpl; fpl->count = 0; fpl->max = SCM_MAX_FD; + fpl->user = NULL; } fpp = &fpl->fp[fpl->count]; @@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fpp++ = file; fpl->count++; } + + if (!fpl->user) + fpl->user = get_uid(current_user()); + return num; } @@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm) scm->fp = NULL; for (i=fpl->count-1; i>=0; i--) fput(fpl->fp[i]); + free_uid(fpl->user); kfree(fpl); } } @@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); new_fpl->max = new_fpl->count; + new_fpl->user = get_uid(fpl->user); } return new_fpl; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b2df375ec9c2..5bf88f58bee7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -79,6 +79,8 @@ struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; +int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; +EXPORT_SYMBOL(sysctl_max_skb_frags); /** * skb_panic - private function for out-of-line support diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 95b6139d710c..a6beb7b6ae55 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -26,6 +26,7 @@ static int zero = 0; static int one = 1; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; +static int max_skb_frags = MAX_SKB_FRAGS; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "max_skb_frags", + .data = &sysctl_max_skb_frags, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &max_skb_frags, + }, { } }; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5684e14932bd..902d606324a0 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -824,26 +824,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v4_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c6d0508e63a..b8608b71a66d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -691,26 +691,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v6_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cebd9d31e65a..f6303b17546b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 46b9c887bede..64148914803a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, reqsk_put(req); } -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child) +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; spin_lock(&queue->rskq_lock); if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_child_forget(sk, req, child); + child = NULL; } else { req->sk = child; req->dl_next = NULL; @@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, sk_acceptq_added(sk); } spin_unlock(&queue->rskq_lock); + return child; } EXPORT_SYMBOL(inet_csk_reqsk_queue_add); @@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, if (own_req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - inet_csk_reqsk_queue_add(sk, req, child); - /* Warning: caller must not call reqsk_put(req); - * child stole last reference on it. - */ - return child; + if (inet_csk_reqsk_queue_add(sk, req, child)) + return child; } /* Too bad, another child took ownership of the request, undo. */ bh_unlock_sock(child); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 1fe55ae81781..b8a0607dab96 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -661,6 +661,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); + skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4233cbe47052..49f02856304d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -240,6 +240,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, * from host network stack. */ features = netif_skb_features(skb); + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); @@ -921,7 +922,7 @@ static int __ip_append_data(struct sock *sk, if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && - (sk->sk_type == SOCK_DGRAM)) { + (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5f73a7c03e27..a50124260f5a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); + + /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); if (err) diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 6fb869f646bf..a04dee536b8e 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -27,8 +27,6 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, { int err; - skb_orphan(skb); - local_bh_disable(); err = ip_defrag(net, skb, user); local_bh_enable(); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index e89094ab5ddb..aa67e0e64b69 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bc35f1842512..7113bae4e6a0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(net, msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); goto out; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 85f184e429c6..02c62299d717 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; +static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ @@ -755,7 +756,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, 0); + 0, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1556,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1609,11 +1640,20 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) + if (fnhe) { rth = rcu_dereference(fnhe->fnhe_rth_input); - else - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(&FIB_RES_NH(*res), daddr); + fnhe = NULL; + } else { + goto rt_cache; + } + } + + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); +rt_cache: if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -2014,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); - if (fnhe) + if (fnhe) { prth = &fnhe->fnhe_rth_output; - else { - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; + rth = rcu_dereference(*prth); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(nh, fl4->daddr); + fnhe = NULL; + } else { + goto rt_cache; } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } + + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; + } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); + +rt_cache: if (rt_cache_valid(rth)) { dst_hold(&rth->dst); return rth; @@ -2569,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev) } #ifdef CONFIG_SYSCTL -static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c82cca18c90f..036a76ba2ac2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include <asm/uaccess.h> #include <asm/ioctls.h> +#include <asm/unaligned.h> #include <net/busy_poll.h> int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; @@ -938,7 +939,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= MAX_SKB_FRAGS) { + if (!can_coalesce && i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1211,7 +1212,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == MAX_SKB_FRAGS || !sg) { + if (i == sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } @@ -2637,6 +2638,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; unsigned int start; + u64 rate64; u32 rate; memset(info, 0, sizeof(*info)); @@ -2702,15 +2704,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_retrans = tp->total_retrans; rate = READ_ONCE(sk->sk_pacing_rate); - info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_pacing_rate); rate = READ_ONCE(sk->sk_max_pacing_rate); - info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_max_pacing_rate); do { start = u64_stats_fetch_begin_irq(&tp->syncp); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; + put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked); + put_unaligned(tp->bytes_received, &info->tcpi_bytes_received); } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); info->tcpi_segs_out = tp->segs_out; info->tcpi_segs_in = tp->segs_in; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d8841a2f1569..8c7e63163e92 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -312,7 +312,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk) /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ -void tcp_req_err(struct sock *sk, u32 seq) +void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); @@ -324,7 +324,7 @@ void tcp_req_err(struct sock *sk, u32 seq) if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - } else { + } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly @@ -384,7 +384,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, + type == ICMP_PARAMETERPROB || + type == ICMP_TIME_EXCEEDED || + (type == ICMP_DEST_UNREACH && + (code == ICMP_NET_UNREACH || + code == ICMP_HOST_UNREACH))); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy @@ -705,7 +710,8 @@ release_sk1: outside socket context is ugly, certainly. What can I do? */ -static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, +static void tcp_v4_send_ack(struct net *net, + struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) @@ -720,7 +726,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, ]; } rep; struct ip_reply_arg arg; - struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -782,7 +787,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v4_send_ack(sock_net(sk), skb, + tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, @@ -801,8 +807,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? - tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : + tcp_sk(sk)->snd_nxt; + + tcp_v4_send_ack(sock_net(sk), skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, tcp_time_stamp, req->ts_recent, @@ -1586,28 +1594,30 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (tcp_v4_inbound_md5_hash(sk, skb)) - goto discard_and_relse; - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { + reqsk_put(req); + goto discard_it; + } + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 17d35662930d..3e6a472e6b88 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) yeah->fast_count = 0; yeah->reno_count = max(yeah->reno_count>>1, 2U); - return tp->snd_cwnd - reduction; + return max_t(int, tp->snd_cwnd - reduction, 2); } static struct tcp_congestion_ops tcp_yeah __read_mostly = { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c43890848641..7f8ab46adf61 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -966,8 +966,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, sk->sk_family == AF_INET6); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; connected = 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1f21087accab..e8d3da0817d3 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -583,7 +583,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; @@ -3506,6 +3506,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; + bool notify = false; addrconf_join_solict(dev, &ifp->addr); @@ -3551,7 +3552,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ - ipv6_ifa_notify(RTM_NEWADDR, ifp); + notify = true; } } @@ -3559,6 +3560,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) out: spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); + if (notify) + ipv6_ifa_notify(RTM_NEWADDR, ifp); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 517c55b01ba8..428162155280 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -162,6 +162,9 @@ ipv4_connected: fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) fl6.flowi6_oif = np->mcast_oif; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 1f9ebe3cbb4a..dc2db4f7b182 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; - (sfl = rcu_dereference(*sflp)) != NULL; + (sfl = rcu_dereference_protected(*sflp, + lockdep_is_held(&ip6_sk_fl_lock))) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = rcu_dereference(sfl->next); + *sflp = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e6a7bd15b9b7..31144c486c52 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -909,6 +909,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct rt6_info *rt; #endif int err; + int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, @@ -940,10 +941,13 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, dst_release(*dst); *dst = NULL; } + + if (fl6->flowi6_oif) + flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) - *dst = ip6_route_output(net, sk, fl6); + *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) @@ -1353,7 +1357,7 @@ emsgsize: (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && - (sk->sk_type == SOCK_DGRAM)) { + (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, fl6); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 826e6aa44f8d..3f164d3aaee2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1174,11 +1174,10 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); } -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6) +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags) { struct dst_entry *dst; - int flags = 0; bool any_src; dst = l3mdev_rt6_dst_by_oif(net, fl6); @@ -1199,7 +1198,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); } -EXPORT_SYMBOL(ip6_route_output); +EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6b8a8a9091fa..b8d405623f4f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -328,6 +328,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; + bool fatal; int err; sk = __inet6_lookup_established(net, &tcp_hashinfo, @@ -346,8 +347,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; } seq = ntohl(th->seq); + fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, fatal); bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) @@ -401,7 +403,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; } - icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { @@ -462,8 +463,10 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + rcu_read_lock(); err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass); + rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1385,7 +1388,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; tcp_v6_fill_cb(skb, hdr, th); @@ -1393,24 +1396,24 @@ process: reqsk_put(req); goto discard_it; } - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); tcp_v6_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index f7fbdbabe50e..372855eeaf42 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -23,7 +23,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) struct ipv6hdr *inner_iph = ipipv6_hdr(skb); if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) - IP6_ECN_set_ce(inner_iph); + IP6_ECN_set_ce(skb, inner_iph); } /* Add encapsulation header. diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 435608c4306d..20ab7b2ec463 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -708,6 +708,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, if (!addr || addr->sa_family != AF_IUCV) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_iucv)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != IUCV_OPEN) { err = -EBADFD; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index f93c5be612a7..2caaa84ce92d 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family, ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, tunnel, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); @@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family, ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, session, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 337bb5d78003..6a12b0f5cac8 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1732,7 +1732,6 @@ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local) if (sdata->vif.type != NL80211_IFTYPE_ADHOC) continue; sdata->u.ibss.last_scan_completed = jiffies; - ieee80211_queue_work(&local->hw, &sdata->work); } mutex_unlock(&local->iflist_mtx); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index fa28500f28fd..6f85b6ab8e51 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1370,17 +1370,6 @@ out: sdata_unlock(sdata); } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - if (ieee80211_vif_is_mesh(&sdata->vif) && - ieee80211_sdata_running(sdata)) - ieee80211_queue_work(&local->hw, &sdata->work); - rcu_read_unlock(); -} void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) { diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index a1596344c3ba..4a8019f79fb2 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -362,14 +362,10 @@ static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP; } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local); - void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata); void ieee80211s_stop(void); #else -static inline void -ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) {} static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3aa04344942b..83097c3832d1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4003,8 +4003,6 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) if (!ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR)) ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.monitor_work); - /* and do all the other regular work too */ - ieee80211_queue_work(&sdata->local->hw, &sdata->work); } } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index a413e52f7691..acbe182b75d1 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -314,6 +314,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) bool was_scanning = local->scanning; struct cfg80211_scan_request *scan_req; struct ieee80211_sub_if_data *scan_sdata; + struct ieee80211_sub_if_data *sdata; lockdep_assert_held(&local->mtx); @@ -373,7 +374,16 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); - ieee80211_mesh_notify_scan_completed(local); + + /* Requeue all the work that might have been ignored while + * the scan was in progress; if there was none this will + * just be a no-op for the particular interface. + */ + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (ieee80211_sdata_running(sdata)) + ieee80211_queue_work(&sdata->local->hw, &sdata->work); + } + if (was_scanning) ieee80211_start_next_roc(local); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 91a8b004dc51..deadfdab1bc3 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -336,12 +336,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, unsigned short gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; struct sk_buff *segs, *nskb; - struct ovs_skb_cb ovs_cb; int err; - ovs_cb = *OVS_CB(skb); + BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET); segs = __skb_gso_segment(skb, NETIF_F_SG, false); - *OVS_CB(skb) = ovs_cb; if (IS_ERR(segs)) return PTR_ERR(segs); if (segs == NULL) @@ -359,7 +357,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, /* Queue all of the segments. */ skb = segs; do { - *OVS_CB(skb) = ovs_cb; if (gso_type & SKB_GSO_UDP && skb != segs) key = &later_key; diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 1605691d9414..d933cb89efac 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -90,7 +90,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) int err; struct vxlan_config conf = { .no_share = true, - .flags = VXLAN_F_COLLECT_METADATA, + .flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX, }; if (!options) { diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 10d42f3220ab..f925753668a7 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -377,6 +377,10 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, struct sockaddr_pn sa; u16 len; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; + /* check we have at least a full Phonet header */ if (!pskb_pull(skb, sizeof(struct phonethdr))) goto out; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f53bf3b6558b..cf5b69ab1829 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1095,17 +1095,6 @@ static unsigned int rfkill_fop_poll(struct file *file, poll_table *wait) return res; } -static bool rfkill_readable(struct rfkill_data *data) -{ - bool r; - - mutex_lock(&data->mtx); - r = !list_empty(&data->events); - mutex_unlock(&data->mtx); - - return r; -} - static ssize_t rfkill_fop_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { @@ -1122,8 +1111,11 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, goto out; } mutex_unlock(&data->mtx); + /* since we re-check and it just compares pointers, + * using !list_empty() without locking isn't a problem + */ ret = wait_event_interruptible(data->read_wait, - rfkill_readable(data)); + !list_empty(&data->events)); mutex_lock(&data->mtx); if (ret) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 57692947ebbe..95b021243233 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -252,23 +252,28 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC, mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, sizeof(key->eth.src)); + fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE, &mask->basic.n_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.n_proto)); + if (key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) { fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.ip_proto)); } - if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + + if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) { + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, sizeof(key->ipv4.src)); fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST, &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK, sizeof(key->ipv4.dst)); - } else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + } else if (tb[TCA_FLOWER_KEY_IPV6_SRC] || tb[TCA_FLOWER_KEY_IPV6_DST]) { + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC, &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK, sizeof(key->ipv6.src)); @@ -276,6 +281,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK, sizeof(key->ipv6.dst)); } + if (key->basic.ip_proto == IPPROTO_TCP) { fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, &mask->tp.src, TCA_FLOWER_UNSPEC, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b5c2cf2aa6d4..af1acf009866 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1852,6 +1852,7 @@ reset: } tp = old_tp; + protocol = tc_skb_protocol(skb); goto reclassify; #endif } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 3d9ea9a48289..8b4ff315695e 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -60,6 +60,8 @@ #include <net/inet_common.h> #include <net/inet_ecn.h> +#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) + /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; @@ -1352,6 +1354,8 @@ static __init int sctp_init(void) unsigned long limit; int max_share; int order; + int num_entries; + int max_entry_order; sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); @@ -1404,14 +1408,24 @@ static __init int sctp_init(void) /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. + * Though not identical. Start by getting a goal size */ if (totalram_pages >= (128 * 1024)) goal = totalram_pages >> (22 - PAGE_SHIFT); else goal = totalram_pages >> (24 - PAGE_SHIFT); - for (order = 0; (1UL << order) < goal; order++) - ; + /* Then compute the page order for said goal */ + order = get_order(goal); + + /* Now compute the required page order for the maximum sized table we + * want to create + */ + max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES * + sizeof(struct sctp_bind_hashbucket)); + + /* Limit the page order by that maximum hash table size */ + order = min(order, max_entry_order); do { sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE / @@ -1445,20 +1459,35 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } - /* Allocate and initialize the SCTP port hash table. */ + /* Allocate and initialize the SCTP port hash table. + * Note that order is initalized to start at the max sized + * table we want to support. If we can't get that many pages + * reduce the order and try again + */ do { - sctp_port_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_bind_hashbucket); - if ((sctp_port_hashsize > (64 * 1024)) && order > 0) - continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); + if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); status = -ENOMEM; goto err_bhash_alloc; } + + /* Now compute the number of entries that will fit in the + * port hash space we allocated + */ + num_entries = (1UL << order) * PAGE_SIZE / + sizeof(struct sctp_bind_hashbucket); + + /* And finish by rounding it down to the nearest power of two + * this wastes some memory of course, but its needed because + * the hash function operates based on the assumption that + * that the number of entries is a power of two + */ + sctp_port_hashsize = rounddown_pow_of_two(num_entries); + for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ef1d90fdc773..be1489fc3234 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5542,6 +5542,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; + int i; if (!ep->auth_enable) return -EACCES; @@ -5559,8 +5560,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, return -EFAULT; if (put_user(num_idents, &p->shmac_num_idents)) return -EFAULT; - if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len)) - return -EFAULT; + for (i = 0; i < num_idents; i++) { + __u16 hmacid = ntohs(hmacs->hmac_ids[i]); + + if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16))) + return -EFAULT; + } return 0; } @@ -6640,6 +6645,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -6663,6 +6669,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 26d50c565f54..3e0fc5127225 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -320,7 +320,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, struct ctl_table tbl; bool changed = false; char *none = "none"; - char tmp[8]; + char tmp[8] = {0}; int ret; memset(&tbl, 0, sizeof(struct ctl_table)); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 5e4f815c2b34..21e20353178e 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1225,7 +1225,7 @@ int qword_get(char **bpp, char *dest, int bufsize) if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; - while (len < bufsize) { + while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2ffaf6a79499..027c9ef8a263 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -398,7 +398,6 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (unlikely(!sock)) return -ENOTSOCK; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags); if (base != 0) { addr = NULL; addrlen = 0; @@ -442,7 +441,6 @@ static void xs_nospace_callback(struct rpc_task *task) struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); transport->inet->sk_write_pending--; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } /** @@ -467,20 +465,11 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { - if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) { - /* - * Notify TCP that we're limited by the application - * window size - */ - set_bit(SOCK_NOSPACE, &transport->sock->flags); - sk->sk_write_pending++; - /* ...and wait for more buffer space */ - xprt_wait_for_buffer_space(task, xs_nospace_callback); - } - } else { - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + /* wait for more buffer space */ + sk->sk_write_pending++; + xprt_wait_for_buffer_space(task, xs_nospace_callback); + } else ret = -ENOTCONN; - } spin_unlock_bh(&xprt->transport_lock); @@ -616,9 +605,6 @@ process_status: case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ENETUNREACH: case -ENOBUFS: case -EPIPE: @@ -626,7 +612,10 @@ process_status: case -EPERM: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -706,16 +695,16 @@ static int xs_tcp_send_request(struct rpc_task *task) case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ECONNRESET: case -ECONNREFUSED: case -ENOTCONN: case -EADDRINUSE: case -ENOBUFS: case -EPIPE: - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -1609,19 +1598,23 @@ static void xs_tcp_state_change(struct sock *sk) static void xs_write_space(struct sock *sk) { - struct socket *sock; + struct socket_wq *wq; struct rpc_xprt *xprt; - if (unlikely(!(sock = sk->sk_socket))) + if (!sk->sk_socket) return; - clear_bit(SOCK_NOSPACE, &sock->flags); + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); if (unlikely(!(xprt = xprt_from_sock(sk)))) return; - if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0) - return; + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) + goto out; xprt_write_space(xprt); +out: + rcu_read_unlock(); } /** diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index f34e535e93bd..d5d7132ac847 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -20,6 +20,7 @@ #include <linux/list.h> #include <linux/workqueue.h> #include <linux/if_vlan.h> +#include <linux/rtnetlink.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -565,7 +566,6 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, } EXPORT_SYMBOL_GPL(switchdev_port_obj_dump); -static DEFINE_MUTEX(switchdev_mutex); static RAW_NOTIFIER_HEAD(switchdev_notif_chain); /** @@ -580,9 +580,9 @@ int register_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&switchdev_mutex); + rtnl_lock(); err = raw_notifier_chain_register(&switchdev_notif_chain, nb); - mutex_unlock(&switchdev_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(register_switchdev_notifier); @@ -598,9 +598,9 @@ int unregister_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&switchdev_mutex); + rtnl_lock(); err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb); - mutex_unlock(&switchdev_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); @@ -614,16 +614,17 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * Call all network notifier blocks. This should be called by driver * when it needs to propagate hardware event. * Return values are same as for atomic_notifier_call_chain(). + * rtnl_lock must be held. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info) { int err; + ASSERT_RTNL(); + info->dev = dev; - mutex_lock(&switchdev_mutex); err = raw_notifier_call_chain(&switchdev_notif_chain, val, info); - mutex_unlock(&switchdev_mutex); return err; } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 9dc239dfe192..92e367a0a5ce 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -399,8 +399,10 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_LINK_GET); - if (!hdr) + if (!hdr) { + tipc_bcast_unlock(net); return -EMSGSIZE; + } attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK); if (!attrs) diff --git a/net/tipc/node.c b/net/tipc/node.c index 20cddec0a43c..3926b561f873 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -168,12 +168,6 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) skb_queue_head_init(&n_ptr->bc_entry.inputq1); __skb_queue_head_init(&n_ptr->bc_entry.arrvq); skb_queue_head_init(&n_ptr->bc_entry.inputq2); - hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); - list_for_each_entry_rcu(temp_node, &tn->node_list, list) { - if (n_ptr->addr < temp_node->addr) - break; - } - list_add_tail_rcu(&n_ptr->list, &temp_node->list); n_ptr->state = SELF_DOWN_PEER_LEAVING; n_ptr->signature = INVALID_NODE_SIG; n_ptr->active_links[0] = INVALID_BEARER_ID; @@ -193,6 +187,12 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) tipc_node_get(n_ptr); setup_timer(&n_ptr->timer, tipc_node_timeout, (unsigned long)n_ptr); n_ptr->keepalive_intv = U32_MAX; + hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { + if (n_ptr->addr < temp_node->addr) + break; + } + list_add_tail_rcu(&n_ptr->list, &temp_node->list); exit: spin_unlock_bh(&tn->node_list_lock); return n_ptr; diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 350cca33ee0a..69ee2eeef968 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -289,15 +289,14 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid, struct sockaddr_tipc *addr, void *usr_data, void *buf, size_t len) { - struct tipc_subscriber *subscriber = usr_data; + struct tipc_subscriber *subscrb = usr_data; struct tipc_subscription *sub = NULL; struct tipc_net *tn = net_generic(net, tipc_net_id); - tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscriber, &sub); - if (sub) - tipc_nametbl_subscribe(sub); - else - tipc_conn_terminate(tn->topsrv, subscriber->conid); + if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub)) + return tipc_conn_terminate(tn->topsrv, subscrb->conid); + + tipc_nametbl_subscribe(sub); } /* Handle one request to establish a new subscriber */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ef05cd9403d4..898a53a562b8 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1496,7 +1496,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) UNIXCB(skb).fp = NULL; for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->fp[i]); + unix_notinflight(scm->fp->user, scm->fp->fp[i]); } static void unix_destruct_scm(struct sk_buff *skb) @@ -1513,6 +1513,21 @@ static void unix_destruct_scm(struct sk_buff *skb) sock_wfree(skb); } +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + #define MAX_RECURSION_LEVEL 4 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) @@ -1521,6 +1536,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) unsigned char max_level = 0; int unix_sock_count = 0; + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + for (i = scm->fp->count - 1; i >= 0; i--) { struct sock *sk = unix_get_socket(scm->fp->fp[i]); @@ -1542,10 +1560,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) if (!UNIXCB(skb).fp) return -ENOMEM; - if (unix_sock_count) { - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); - } + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); return max_level; } @@ -1765,7 +1781,12 @@ restart_locked: goto out_unlock; } - if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + /* other == sk && unix_peer(other) != sk if + * - unix_peer(sk) == NULL, destination address bound to sk + * - unix_peer(sk) == sk by time of get but disconnected before lock + */ + if (other != sk && + unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); @@ -2254,13 +2275,15 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) size_t size = state->size; unsigned int last_len; - err = -EINVAL; - if (sk->sk_state != TCP_ESTABLISHED) + if (unlikely(sk->sk_state != TCP_ESTABLISHED)) { + err = -EINVAL; goto out; + } - err = -EOPNOTSUPP; - if (flags & MSG_OOB) + if (unlikely(flags & MSG_OOB)) { + err = -EOPNOTSUPP; goto out; + } target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, noblock); @@ -2306,9 +2329,11 @@ again: goto unlock; unix_state_unlock(sk); - err = -EAGAIN; - if (!timeo) + if (!timeo) { + err = -EAGAIN; break; + } + mutex_unlock(&u->readlock); timeo = unix_stream_data_wait(sk, timeo, last, @@ -2316,6 +2341,7 @@ again: if (signal_pending(current)) { err = sock_intr_errno(timeo); + scm_destroy(&scm); goto out; } diff --git a/net/unix/diag.c b/net/unix/diag.c index c512f64d5287..4d9679701a6d 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -220,7 +220,7 @@ done: return skb->len; } -static struct sock *unix_lookup_by_ino(int ino) +static struct sock *unix_lookup_by_ino(unsigned int ino) { int i; struct sock *sk; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index a73a226f2d33..6a0d48525fcf 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -116,15 +116,15 @@ struct sock *unix_get_socket(struct file *filp) * descriptor if it is for an AF_UNIX socket. */ -void unix_inflight(struct file *fp) +void unix_inflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); - if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); @@ -132,25 +132,28 @@ void unix_inflight(struct file *fp) BUG_ON(list_empty(&u->link)); } unix_tot_inflight++; - spin_unlock(&unix_gc_lock); } + user->unix_inflight++; + spin_unlock(&unix_gc_lock); } -void unix_notinflight(struct file *fp) +void unix_notinflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; - spin_unlock(&unix_gc_lock); } + user->unix_inflight--; + spin_unlock(&unix_gc_lock); } static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index cc3676eb6239..ff4a91fcab9f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -167,6 +167,8 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb { struct sk_buff *segs; + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); + BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, 0); kfree_skb(skb); if (IS_ERR(segs)) |