diff options
author | Ingo Molnar <mingo@kernel.org> | 2016-03-04 12:12:08 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2016-03-04 12:12:08 +0100 |
commit | bc94b99636dc7bcccce439a9fb9c00065e2e2627 (patch) | |
tree | bddbd29a5fd7b2d270d039efc1d6858791a2c98f /net | |
parent | 4650bac1fc45d64aef62ab99aa4db93d41dedbd9 (diff) | |
parent | fc77dbd34c5c99bce46d40a2491937c3bcbd10af (diff) | |
download | blackbird-obmc-linux-bc94b99636dc7bcccce439a9fb9c00065e2e2627.tar.gz blackbird-obmc-linux-bc94b99636dc7bcccce439a9fb9c00065e2e2627.zip |
Merge tag 'v4.5-rc6' into core/resources, to resolve conflict
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'net')
105 files changed, 842 insertions, 407 deletions
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index d5871ac493eb..f066781be3c8 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1625,7 +1625,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) rt = atrtr_find(&at_hint); } - err = ENETUNREACH; + err = -ENETUNREACH; if (!rt) goto out; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index e6c8382c79ba..ccf70bed0d0c 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -527,11 +527,12 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, * gets dereferenced. */ spin_lock_bh(&bat_priv->gw.list_lock); - hlist_del_init_rcu(&gw_node->list); + if (!hlist_unhashed(&gw_node->list)) { + hlist_del_init_rcu(&gw_node->list); + batadv_gw_node_free_ref(gw_node); + } spin_unlock_bh(&bat_priv->gw.list_lock); - batadv_gw_node_free_ref(gw_node); - curr_gw = batadv_gw_get_selected_gw_node(bat_priv); if (gw_node == curr_gw) batadv_gw_reselect(bat_priv); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 01acccc4d218..57f7107169f5 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -76,6 +76,28 @@ out: } /** + * batadv_mutual_parents - check if two devices are each others parent + * @dev1: 1st net_device + * @dev2: 2nd net_device + * + * veth devices come in pairs and each is the parent of the other! + * + * Return: true if the devices are each others parent, otherwise false + */ +static bool batadv_mutual_parents(const struct net_device *dev1, + const struct net_device *dev2) +{ + int dev1_parent_iflink = dev_get_iflink(dev1); + int dev2_parent_iflink = dev_get_iflink(dev2); + + if (!dev1_parent_iflink || !dev2_parent_iflink) + return false; + + return (dev1_parent_iflink == dev2->ifindex) && + (dev2_parent_iflink == dev1->ifindex); +} + +/** * batadv_is_on_batman_iface - check if a device is a batman iface descendant * @net_dev: the device to check * @@ -108,6 +130,9 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) if (WARN(!parent_dev, "Cannot find parent device")) return false; + if (batadv_mutual_parents(net_dev, parent_dev)) + return false; + ret = batadv_is_on_batman_iface(parent_dev); return ret; diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index cdfc85fa2743..0e80fd1461ab 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -303,9 +303,11 @@ static void batadv_tt_global_size_mod(struct batadv_orig_node *orig_node, if (atomic_add_return(v, &vlan->tt.num_entries) == 0) { spin_lock_bh(&orig_node->vlan_list_lock); - hlist_del_init_rcu(&vlan->list); + if (!hlist_unhashed(&vlan->list)) { + hlist_del_init_rcu(&vlan->list); + batadv_orig_node_vlan_free_ref(vlan); + } spin_unlock_bh(&orig_node->vlan_list_lock); - batadv_orig_node_vlan_free_ref(vlan); } batadv_orig_node_vlan_free_ref(vlan); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index d040365ba98e..8a4cc2f7f0db 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_core.c b/net/bluetooth/hci_core.c index 47bcef754796..883c821a9e78 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4112,8 +4112,10 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, break; } - *req_complete = bt_cb(skb)->hci.req_complete; - *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; + if (bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) + *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; + else + *req_complete = bt_cb(skb)->hci.req_complete; kfree_skb(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 41b5f3813f02..c78ee2dc9323 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -688,21 +688,29 @@ 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/l2cap_core.c b/net/bluetooth/l2cap_core.c index 39a5149f3010..eb4f5f24cbe3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -197,10 +197,20 @@ int l2cap_add_psm(struct l2cap_chan *chan, bdaddr_t *src, __le16 psm) chan->sport = psm; err = 0; } else { - u16 p; + u16 p, start, end, incr; + + if (chan->src_type == BDADDR_BREDR) { + start = L2CAP_PSM_DYN_START; + end = L2CAP_PSM_AUTO_END; + incr = 2; + } else { + start = L2CAP_PSM_LE_DYN_START; + end = L2CAP_PSM_LE_DYN_END; + incr = 1; + } err = -EINVAL; - for (p = 0x1001; p < 0x1100; p += 2) + for (p = start; p <= end; p += incr) if (!__l2cap_global_chan_by_addr(cpu_to_le16(p), src)) { chan->psm = cpu_to_le16(p); chan->sport = cpu_to_le16(p); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 1bb551527044..e4cae72895a7 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -58,7 +58,7 @@ static int l2cap_validate_bredr_psm(u16 psm) return -EINVAL; /* Restrict usage of well-known PSMs */ - if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) + if (psm < L2CAP_PSM_DYN_START && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; return 0; @@ -67,11 +67,11 @@ static int l2cap_validate_bredr_psm(u16 psm) static int l2cap_validate_le_psm(u16 psm) { /* Valid LE_PSM ranges are defined only until 0x00ff */ - if (psm > 0x00ff) + if (psm > L2CAP_PSM_LE_DYN_END) return -EINVAL; /* Restrict fixed, SIG assigned PSM values to CAP_NET_BIND_SERVICE */ - if (psm <= 0x007f && !capable(CAP_NET_BIND_SERVICE)) + if (psm < L2CAP_PSM_LE_DYN_START && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; return 0; @@ -125,6 +125,9 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) goto done; } + bacpy(&chan->src, &la.l2_bdaddr); + chan->src_type = la.l2_bdaddr_type; + if (la.l2_cid) err = l2cap_add_scid(chan, __le16_to_cpu(la.l2_cid)); else @@ -156,9 +159,6 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) break; } - bacpy(&chan->src, &la.l2_bdaddr); - chan->src_type = la.l2_bdaddr_type; - if (chan->psm && bdaddr_type_is_le(chan->src_type)) chan->mode = L2CAP_MODE_LE_FLOWCTL; 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_mdb.c b/net/bridge/br_mdb.c index 30e105f57f0d..74c278e00225 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -425,8 +425,8 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, mp = br_mdb_ip_get(mdb, group); if (!mp) { mp = br_multicast_new_group(br, port, group); - err = PTR_ERR(mp); - if (IS_ERR(mp)) + err = PTR_ERR_OR_ZERO(mp); + if (err) return err; } diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index 61d7617d9249..b82440e1fcb4 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -159,7 +159,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt) tmppkt = NULL; /* Verify that length is correct */ - err = EPROTO; + err = -EPROTO; if (rfml->pdu_size != cfpkt_getlen(pkt) - RFM_HEAD_SIZE + 1) goto out; } diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 393bfb22d5bb..5fcfb98f309e 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -403,6 +403,7 @@ static int is_out(const struct crush_map *map, * @local_retries: localized retries * @local_fallback_retries: localized fallback retries * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose) + * @stable: stable mode starts rep=0 in the recursive call for all replicas * @vary_r: pass r to recursive calls * @out2: second output vector for leaf items (if @recurse_to_leaf) * @parent_r: r value passed from the parent @@ -419,6 +420,7 @@ static int crush_choose_firstn(const struct crush_map *map, unsigned int local_fallback_retries, int recurse_to_leaf, unsigned int vary_r, + unsigned int stable, int *out2, int parent_r) { @@ -433,13 +435,13 @@ static int crush_choose_firstn(const struct crush_map *map, int collide, reject; int count = out_size; - dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n", + dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d stable %d\n", recurse_to_leaf ? "_LEAF" : "", bucket->id, x, outpos, numrep, tries, recurse_tries, local_retries, local_fallback_retries, - parent_r); + parent_r, stable); - for (rep = outpos; rep < numrep && count > 0 ; rep++) { + for (rep = stable ? 0 : outpos; rep < numrep && count > 0 ; rep++) { /* keep trying until we get a non-out, non-colliding item */ ftotal = 0; skip_rep = 0; @@ -512,13 +514,14 @@ static int crush_choose_firstn(const struct crush_map *map, if (crush_choose_firstn(map, map->buckets[-1-item], weight, weight_max, - x, outpos+1, 0, + x, stable ? 1 : outpos+1, 0, out2, outpos, count, recurse_tries, 0, local_retries, local_fallback_retries, 0, vary_r, + stable, NULL, sub_r) <= outpos) /* didn't get leaf */ @@ -816,6 +819,7 @@ int crush_do_rule(const struct crush_map *map, int choose_local_fallback_retries = map->choose_local_fallback_tries; int vary_r = map->chooseleaf_vary_r; + int stable = map->chooseleaf_stable; if ((__u32)ruleno >= map->max_rules) { dprintk(" bad ruleno %d\n", ruleno); @@ -835,7 +839,8 @@ int crush_do_rule(const struct crush_map *map, case CRUSH_RULE_TAKE: if ((curstep->arg1 >= 0 && curstep->arg1 < map->max_devices) || - (-1-curstep->arg1 < map->max_buckets && + (-1-curstep->arg1 >= 0 && + -1-curstep->arg1 < map->max_buckets && map->buckets[-1-curstep->arg1])) { w[0] = curstep->arg1; wsize = 1; @@ -869,6 +874,11 @@ int crush_do_rule(const struct crush_map *map, vary_r = curstep->arg1; break; + case CRUSH_RULE_SET_CHOOSELEAF_STABLE: + if (curstep->arg1 >= 0) + stable = curstep->arg1; + break; + case CRUSH_RULE_CHOOSELEAF_FIRSTN: case CRUSH_RULE_CHOOSE_FIRSTN: firstn = 1; @@ -888,6 +898,7 @@ int crush_do_rule(const struct crush_map *map, osize = 0; for (i = 0; i < wsize; i++) { + int bno; /* * see CRUSH_N, CRUSH_N_MINUS macros. * basically, numrep <= 0 means relative to @@ -900,6 +911,13 @@ int crush_do_rule(const struct crush_map *map, continue; } j = 0; + /* make sure bucket id is valid */ + bno = -1 - w[i]; + if (bno < 0 || bno >= map->max_buckets) { + /* w[i] is probably CRUSH_ITEM_NONE */ + dprintk(" bad w[i] %d\n", w[i]); + continue; + } if (firstn) { int recurse_tries; if (choose_leaf_tries) @@ -911,7 +929,7 @@ int crush_do_rule(const struct crush_map *map, recurse_tries = choose_tries; osize += crush_choose_firstn( map, - map->buckets[-1-w[i]], + map->buckets[bno], weight, weight_max, x, numrep, curstep->arg2, @@ -923,6 +941,7 @@ int crush_do_rule(const struct crush_map *map, choose_local_fallback_retries, recurse_to_leaf, vary_r, + stable, c+osize, 0); } else { @@ -930,7 +949,7 @@ int crush_do_rule(const struct crush_map *map, numrep : (result_max-osize)); crush_choose_indep( map, - map->buckets[-1-w[i]], + map->buckets[bno], weight, weight_max, x, out_size, numrep, curstep->arg2, diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9cfedf565f5b..9382619a405b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1197,6 +1197,13 @@ 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); @@ -2335,9 +2342,9 @@ 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); @@ -2360,10 +2367,10 @@ 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); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index f8f235930d88..5bc053778fed 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1770,6 +1770,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) u32 osdmap_epoch; int already_completed; u32 bytes; + u8 decode_redir; unsigned int i; tid = le64_to_cpu(msg->hdr.tid); @@ -1841,6 +1842,15 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) p += 8 + 4; /* skip replay_version */ p += 8; /* skip user_version */ + if (le16_to_cpu(msg->hdr.version) >= 7) + ceph_decode_8_safe(&p, end, decode_redir, bad_put); + else + decode_redir = 1; + } else { + decode_redir = 0; + } + + if (decode_redir) { err = ceph_redirect_decode(&p, end, &redir); if (err) goto bad_put; @@ -2843,8 +2853,8 @@ 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/ceph/osdmap.c b/net/ceph/osdmap.c index 7d8f581d9f1f..243574c8cf33 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -342,23 +342,32 @@ static struct crush_map *crush_decode(void *pbyval, void *end) c->choose_local_tries = ceph_decode_32(p); c->choose_local_fallback_tries = ceph_decode_32(p); c->choose_total_tries = ceph_decode_32(p); - dout("crush decode tunable choose_local_tries = %d", + dout("crush decode tunable choose_local_tries = %d\n", c->choose_local_tries); - dout("crush decode tunable choose_local_fallback_tries = %d", + dout("crush decode tunable choose_local_fallback_tries = %d\n", c->choose_local_fallback_tries); - dout("crush decode tunable choose_total_tries = %d", + dout("crush decode tunable choose_total_tries = %d\n", c->choose_total_tries); ceph_decode_need(p, end, sizeof(u32), done); c->chooseleaf_descend_once = ceph_decode_32(p); - dout("crush decode tunable chooseleaf_descend_once = %d", + dout("crush decode tunable chooseleaf_descend_once = %d\n", c->chooseleaf_descend_once); ceph_decode_need(p, end, sizeof(u8), done); c->chooseleaf_vary_r = ceph_decode_8(p); - dout("crush decode tunable chooseleaf_vary_r = %d", + dout("crush decode tunable chooseleaf_vary_r = %d\n", c->chooseleaf_vary_r); + /* skip straw_calc_version, allowed_bucket_algs */ + ceph_decode_need(p, end, sizeof(u8) + sizeof(u32), done); + *p += sizeof(u8) + sizeof(u32); + + ceph_decode_need(p, end, sizeof(u8), done); + c->chooseleaf_stable = ceph_decode_8(p); + dout("crush decode tunable chooseleaf_stable = %d\n", + c->chooseleaf_stable); + done: dout("crush_decode success\n"); return c; diff --git a/net/core/dev.c b/net/core/dev.c index cc9e3652cf93..0ef061b2badc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4351,6 +4351,7 @@ 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)); @@ -4548,10 +4549,12 @@ 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: @@ -5376,12 +5379,12 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; - lower = list_entry((*iter)->next, struct netdev_adjacent, list); + lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; - *iter = &lower->list; + *iter = lower->list.next; return lower->dev; } @@ -7419,8 +7422,10 @@ 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/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/scm.c b/net/core/scm.c index 14596fb37172..2696aefdc148 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/sock_reuseport.c b/net/core/sock_reuseport.c index 1df98c557440..e92b759d906c 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -93,10 +93,17 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) * @sk2: Socket belonging to the existing reuseport group. * May return ENOMEM and not add socket to group under memory pressure. */ -int reuseport_add_sock(struct sock *sk, const struct sock *sk2) +int reuseport_add_sock(struct sock *sk, struct sock *sk2) { struct sock_reuseport *reuse; + if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { + int err = reuseport_alloc(sk2); + + if (err) + return err; + } + spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)), 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/dsa/slave.c b/net/dsa/slave.c index 40b9ca72aae3..ab24521beb4d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1194,7 +1194,6 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, if (ret) { netdev_err(master, "error %d registering interface %s\n", ret, slave_dev->name); - phy_disconnect(p->phy); ds->ports[port] = NULL; free_netdev(slave_dev); return ret; @@ -1205,6 +1204,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, ret = dsa_slave_phy_setup(p, slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); + unregister_netdev(slave_dev); free_netdev(slave_dev); return ret; } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index c22920525e5d..775824720b6b 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -353,6 +353,7 @@ config INET_ESP select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES + select CRYPTO_ECHAINIV ---help--- Support for IPsec ESP. 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/fib_trie.c b/net/ipv4/fib_trie.c index 7aea0ccb6be6..d07fc076bea0 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1394,9 +1394,10 @@ found: struct fib_info *fi = fa->fa_info; int nhsel, err; - if ((index >= (1ul << fa->fa_slen)) && - ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH))) - continue; + if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { + if (index >= (1ul << fa->fa_slen)) + continue; + } if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) continue; if (fi->fib_dead) 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/inet_diag.c b/net/ipv4/inet_diag.c index 8bb8e7ad8548..6029157a19ed 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -361,13 +361,20 @@ struct sock *inet_diag_find_one_icsk(struct net *net, req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) - else if (req->sdiag_family == AF_INET6) - sk = inet6_lookup(net, hashinfo, - (struct in6_addr *)req->id.idiag_dst, - req->id.idiag_dport, - (struct in6_addr *)req->id.idiag_src, - req->id.idiag_sport, - req->id.idiag_if); + else if (req->sdiag_family == AF_INET6) { + if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && + ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) + sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3], + req->id.idiag_dport, req->id.idiag_src[3], + req->id.idiag_sport, req->id.idiag_if); + else + sk = inet6_lookup(net, hashinfo, + (struct in6_addr *)req->id.idiag_dst, + req->id.idiag_dport, + (struct in6_addr *)req->id.idiag_src, + req->id.idiag_sport, + req->id.idiag_if); + } #endif else return ERR_PTR(-EINVAL); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 3f00810b7288..187c6fcc3027 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_gre.c b/net/ipv4/ip_gre.c index 7c51c4e1661f..41ba68de46d8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1054,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = { static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); - dev->netdev_ops = &gre_tap_netdev_ops; - dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->netdev_ops = &gre_tap_netdev_ops; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } @@ -1240,6 +1241,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, err = ipgre_newlink(net, dev, tb, NULL); if (err < 0) goto out; + + /* openvswitch users expect packet sizes to be unrestricted, + * so set the largest MTU we can. + */ + err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); + if (err) + goto out; + return dev; out: free_netdev(dev); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index b1209b63381f..d77eb0c3b684 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -316,7 +316,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) { + if (sysctl_ip_early_demux && + !skb_dst(skb) && + !skb->sk && + !ip_is_fragment(iph)) { const struct net_protocol *ipprot; int protocol = iph->protocol; 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/ip_tunnel.c b/net/ipv4/ip_tunnel.c index c7bd72e9b544..89e8861e05fc 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -943,17 +943,31 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ioctl); -int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; - if (new_mtu < 68 || - new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen) + if (new_mtu < 68) return -EINVAL; + + if (new_mtu > max_mtu) { + if (strict) + return -EINVAL; + + new_mtu = max_mtu; + } + dev->mtu = new_mtu; return 0; } +EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); + +int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + return __ip_tunnel_change_mtu(dev, new_mtu, true); +} EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 67f7c9de0b16..2ed9dd2b5f2f 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -143,7 +143,11 @@ static char dhcp_client_identifier[253] __initdata; /* Persistent data: */ +#ifdef IPCONFIG_DYNAMIC static int ic_proto_used; /* Protocol used, if any */ +#else +#define ic_proto_used 0 +#endif static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */ static u8 ic_domain[64]; /* DNS (not NIS) domain name */ 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 c117b21b937d..d3a27165f9cc 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 fd17eec93525..483ffdf5aa4d 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; @@ -939,7 +940,7 @@ 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; } @@ -1212,7 +1213,7 @@ 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; } @@ -2638,6 +2639,7 @@ 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)); @@ -2703,15 +2705,17 @@ 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; @@ -2946,7 +2950,7 @@ static void __tcp_alloc_md5sig_pool(void) struct crypto_hash *hash; hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(hash)) + if (IS_ERR(hash)) return; per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0003d409fec5..3b2c8e90a475 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2164,8 +2164,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int cnt, oldcnt; - int err; + int cnt, oldcnt, lost; unsigned int mss; /* Use SACK to deduce losses of new sequences sent during recovery */ const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; @@ -2205,9 +2204,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; mss = tcp_skb_mss(skb); - err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, - mss, GFP_ATOMIC); - if (err < 0) + /* If needed, chop off the prefix to mark as lost. */ + lost = (packets - oldcnt) * mss; + if (lost < skb->len && + tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2366,8 +2366,6 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) tp->snd_ssthresh = tp->prior_ssthresh; tcp_ecn_withdraw_cwr(tp); } - } else { - tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh); } tp->snd_cwnd_stamp = tcp_time_stamp; tp->undo_marker = 0; @@ -2898,7 +2896,10 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; struct rtt_meas *m = tcp_sk(sk)->rtt_min; - struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now }; + struct rtt_meas rttm = { + .rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1), + .ts = now, + }; u32 elapsed; /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5ced3e4013e3..487ac67059e2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -311,7 +311,7 @@ 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); @@ -323,7 +323,7 @@ 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 @@ -383,7 +383,12 @@ 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 @@ -707,7 +712,8 @@ 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) @@ -722,7 +728,6 @@ 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)); @@ -784,7 +789,8 @@ 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, @@ -803,8 +809,10 @@ 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, @@ -1589,28 +1597,30 @@ 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/udp.c b/net/ipv4/udp.c index dc45b538e237..95d2f198017e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -499,6 +499,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -512,14 +513,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -563,6 +568,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -601,14 +607,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -1038,8 +1048,10 @@ 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/Kconfig b/net/ipv6/Kconfig index bb7dabe2ebbf..40c897515ddc 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -69,6 +69,7 @@ config INET6_ESP select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES + select CRYPTO_ECHAINIV ---help--- Support for IPsec ESP. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 38eeddedfc21..bdd7eac4307a 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; @@ -3538,6 +3538,7 @@ 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); @@ -3583,7 +3584,7 @@ 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; } } @@ -3591,6 +3592,8 @@ 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_gre.c b/net/ipv6/ip6_gre.c index f37f18b6b40c..a69aad1e29d1 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1512,6 +1512,7 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->destructor = ip6gre_dev_free; dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 23de98f976d5..a163102f1803 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) diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 31ba7ca19757..051b6a6bfff6 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -21,6 +21,10 @@ #include <net/ipv6.h> #include <net/netfilter/ipv6/nf_nat_masquerade.h> +#define MAX_WORK_COUNT 16 + +static atomic_t v6_worker_count; + unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, const struct net_device *out) @@ -78,14 +82,78 @@ static struct notifier_block masq_dev_notifier = { .notifier_call = masq_device_event, }; +struct masq_dev_work { + struct work_struct work; + struct net *net; + int ifindex; +}; + +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + long index; + + w = container_of(work, struct masq_dev_work, work); + + index = w->ifindex; + nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&v6_worker_count); + module_put(THIS_MODULE); +} + +/* ipv6 inet notifier is an atomic notifier, i.e. we cannot + * schedule. + * + * Unfortunately, nf_ct_iterate_cleanup can run for a long + * time if there are lots of conntracks and the system + * handles high softirq load, so it frequently calls cond_resched + * while iterating the conntrack table. + * + * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * + * As we can have 'a lot' of inet_events (depending on amount + * of ipv6 addresses being deleted), we also need to add an upper + * limit to the number of queued work items. + */ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; - struct netdev_notifier_info info; + const struct net_device *dev; + struct masq_dev_work *w; + struct net *net; + + if (event != NETDEV_DOWN || + atomic_read(&v6_worker_count) >= MAX_WORK_COUNT) + return NOTIFY_DONE; + + dev = ifa->idev->dev; + net = maybe_get_net(dev_net(dev)); + if (!net) + return NOTIFY_DONE; - netdev_notifier_info_init(&info, ifa->idev->dev); - return masq_device_event(this, event, &info); + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (w) { + atomic_inc(&v6_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = dev->ifindex; + w->net = net; + schedule_work(&w->work); + + return NOTIFY_DONE; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); + return NOTIFY_DONE; } static struct notifier_block masq_inet_notifier = { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3c8834bc822d..ed446639219c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1183,11 +1183,10 @@ 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); @@ -1208,7 +1207,7 @@ 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/sit.c b/net/ipv6/sit.c index e794ef66a401..2066d1c25a11 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -201,14 +201,14 @@ static int ipip6_tunnel_create(struct net_device *dev) if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; + dev->rtnl_link_ops = &sit_link_ops; + err = register_netdevice(dev); if (err < 0) goto out; ipip6_tunnel_clone_6rd(dev, sitn); - dev->rtnl_link_ops = &sit_link_ops; - dev_hold(dev); ipip6_tunnel_link(sitn, t); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 006396e31cb0..5c8c84273028 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -327,6 +327,7 @@ 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, @@ -345,8 +346,9 @@ 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) @@ -400,7 +402,6 @@ 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) { @@ -1386,7 +1387,7 @@ 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); @@ -1394,24 +1395,24 @@ 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/udp.c b/net/ipv6/udp.c index 5d2c2afffe7b..22e28a44e3c8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -257,6 +257,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -270,14 +271,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -321,6 +326,7 @@ struct sock *__udp6_lib_lookup(struct net *net, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -358,14 +364,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c index 3c4caa60c926..5728e76ca6d5 100644 --- a/net/irda/ircomm/ircomm_param.c +++ b/net/irda/ircomm/ircomm_param.c @@ -134,11 +134,10 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush) return -1; } skb_put(skb, count); + pr_debug("%s(), skb->len=%d\n", __func__, skb->len); spin_unlock_irqrestore(&self->spinlock, flags); - pr_debug("%s(), skb->len=%d\n", __func__ , skb->len); - if (flush) { /* ircomm_tty_do_softint will take care of the rest */ schedule_work(&self->tqueue); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ef50a94d3eb7..fc3598a922b0 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 f7fc0e00497f..978d3bc31df7 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1733,7 +1733,6 @@ 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/main.c b/net/mac80211/main.c index 6bcf0faa4a89..8190bf27ebff 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -248,6 +248,7 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for scan work complete */ flush_workqueue(local->workqueue); + flush_work(&local->sched_scan_stopped_work); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), "%s called with hardware scan in progress\n", __func__); @@ -256,6 +257,11 @@ static void ieee80211_restart_work(struct work_struct *work) list_for_each_entry(sdata, &local->interfaces, list) flush_delayed_work(&sdata->dec_tailroom_needed_wk); ieee80211_scan_cancel(local); + + /* make sure any new ROC will consider local->in_reconfig */ + flush_delayed_work(&local->roc_work); + flush_work(&local->hw_roc_done); + ieee80211_reconfig(local); rtnl_unlock(); } 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 1c342e2592c4..bfbb1acafdd1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4005,8 +4005,6 @@ 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/offchannel.c b/net/mac80211/offchannel.c index 8b2f4eaac2ba..55a9c5b94ce1 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -252,14 +252,11 @@ static bool ieee80211_recalc_sw_work(struct ieee80211_local *local, static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc, unsigned long start_time) { - struct ieee80211_local *local = roc->sdata->local; - if (WARN_ON(roc->notified)) return; roc->start_time = start_time; roc->started = true; - roc->hw_begun = true; if (roc->mgmt_tx_cookie) { if (!WARN_ON(!roc->frame)) { @@ -274,9 +271,6 @@ static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc, } roc->notified = true; - - if (!local->ops->remain_on_channel) - ieee80211_recalc_sw_work(local, start_time); } static void ieee80211_hw_roc_start(struct work_struct *work) @@ -291,6 +285,7 @@ static void ieee80211_hw_roc_start(struct work_struct *work) if (!roc->started) break; + roc->hw_begun = true; ieee80211_handle_roc_started(roc, local->hw_roc_start_time); } @@ -413,6 +408,10 @@ void ieee80211_start_next_roc(struct ieee80211_local *local) return; } + /* defer roc if driver is not started (i.e. during reconfig) */ + if (local->in_reconfig) + return; + roc = list_first_entry(&local->roc_list, struct ieee80211_roc_work, list); @@ -534,8 +533,10 @@ ieee80211_coalesce_hw_started_roc(struct ieee80211_local *local, * begin, otherwise they'll both be marked properly by the work * struct that runs once the driver notifies us of the beginning */ - if (cur_roc->hw_begun) + if (cur_roc->hw_begun) { + new_roc->hw_begun = true; ieee80211_handle_roc_started(new_roc, now); + } return true; } @@ -658,6 +659,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, queued = true; roc->on_channel = tmp->on_channel; ieee80211_handle_roc_started(roc, now); + ieee80211_recalc_sw_work(local, now); break; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index a413e52f7691..ae980ce8daff 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); } @@ -1213,6 +1223,14 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw) trace_api_sched_scan_stopped(local); + /* + * this shouldn't really happen, so for simplicity + * simply ignore it, and let mac80211 reconfigure + * the sched scan later on. + */ + if (local->in_reconfig) + return; + schedule_work(&local->sched_scan_stopped_work); } EXPORT_SYMBOL(ieee80211_sched_scan_stopped); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4402ad5b27d1..a4a4f89d3ba0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1453,7 +1453,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, more_data = ieee80211_sta_ps_more_data(sta, ignored_acs, reason, driver_release_tids); - if (reason == IEEE80211_FRAME_RELEASE_PSPOLL) + if (driver_release_tids && reason == IEEE80211_FRAME_RELEASE_PSPOLL) driver_release_tids = BIT(find_highest_prio_tid(driver_release_tids)); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 5bad05e9af90..6101deb805a8 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -51,6 +51,11 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct ieee80211_hdr *hdr = (void *)skb->data; int ac; + if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) { + ieee80211_free_txskb(&local->hw, skb); + return; + } + /* * This skb 'survived' a round-trip through the driver, and * hopefully the driver didn't mangle it too badly. However, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 3943d4bf289c..58f58bd5202f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2043,16 +2043,26 @@ int ieee80211_reconfig(struct ieee80211_local *local) */ if (sched_scan_req->n_scan_plans > 1 || __ieee80211_request_sched_scan_start(sched_scan_sdata, - sched_scan_req)) + sched_scan_req)) { + RCU_INIT_POINTER(local->sched_scan_sdata, NULL); + RCU_INIT_POINTER(local->sched_scan_req, NULL); sched_scan_stopped = true; + } mutex_unlock(&local->mtx); if (sched_scan_stopped) cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy); wake_up: - local->in_reconfig = false; - barrier(); + if (local->in_reconfig) { + local->in_reconfig = false; + barrier(); + + /* Restart deferred ROCs */ + mutex_lock(&local->mtx); + ieee80211_start_next_roc(local); + mutex_unlock(&local->mtx); + } if (local->monitors == local->open_count && local->monitors > 0) ieee80211_add_virtual_monitor(local); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 8c067e6663a1..95e757c377f9 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -891,7 +891,7 @@ config NETFILTER_XT_TARGET_TEE depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV4 - select NF_DUP_IPV6 if IP6_NF_IPTABLES != n + select NF_DUP_IPV6 if IPV6 ---help--- This option adds a "TEE" target with which a packet can be cloned and this clone be rerouted to another nexthop. diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 43d8c9896fa3..f0f688db6213 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -164,8 +164,6 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - if (e.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) e.cidr = HOST_MASK; @@ -377,8 +375,6 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - if (e.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) e.cidr = HOST_MASK; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3cb3cb831591..f60b4fdeeb8c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -66,6 +66,21 @@ EXPORT_SYMBOL_GPL(nf_conntrack_locks); __cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock); EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock); +static __read_mostly spinlock_t nf_conntrack_locks_all_lock; +static __read_mostly bool nf_conntrack_locks_all; + +void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) +{ + spin_lock(lock); + while (unlikely(nf_conntrack_locks_all)) { + spin_unlock(lock); + spin_lock(&nf_conntrack_locks_all_lock); + spin_unlock(&nf_conntrack_locks_all_lock); + spin_lock(lock); + } +} +EXPORT_SYMBOL_GPL(nf_conntrack_lock); + static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2) { h1 %= CONNTRACK_LOCKS; @@ -82,12 +97,12 @@ static bool nf_conntrack_double_lock(struct net *net, unsigned int h1, h1 %= CONNTRACK_LOCKS; h2 %= CONNTRACK_LOCKS; if (h1 <= h2) { - spin_lock(&nf_conntrack_locks[h1]); + nf_conntrack_lock(&nf_conntrack_locks[h1]); if (h1 != h2) spin_lock_nested(&nf_conntrack_locks[h2], SINGLE_DEPTH_NESTING); } else { - spin_lock(&nf_conntrack_locks[h2]); + nf_conntrack_lock(&nf_conntrack_locks[h2]); spin_lock_nested(&nf_conntrack_locks[h1], SINGLE_DEPTH_NESTING); } @@ -102,16 +117,19 @@ static void nf_conntrack_all_lock(void) { int i; - for (i = 0; i < CONNTRACK_LOCKS; i++) - spin_lock_nested(&nf_conntrack_locks[i], i); + spin_lock(&nf_conntrack_locks_all_lock); + nf_conntrack_locks_all = true; + + for (i = 0; i < CONNTRACK_LOCKS; i++) { + spin_lock(&nf_conntrack_locks[i]); + spin_unlock(&nf_conntrack_locks[i]); + } } static void nf_conntrack_all_unlock(void) { - int i; - - for (i = 0; i < CONNTRACK_LOCKS; i++) - spin_unlock(&nf_conntrack_locks[i]); + nf_conntrack_locks_all = false; + spin_unlock(&nf_conntrack_locks_all_lock); } unsigned int nf_conntrack_htable_size __read_mostly; @@ -757,7 +775,7 @@ restart: hash = hash_bucket(_hash, net); for (; i < net->ct.htable_size; i++) { lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS]; - spin_lock(lockp); + nf_conntrack_lock(lockp); if (read_seqcount_retry(&net->ct.generation, sequence)) { spin_unlock(lockp); goto restart; @@ -1382,7 +1400,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), for (; *bucket < net->ct.htable_size; (*bucket)++) { lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; local_bh_disable(); - spin_lock(lockp); + nf_conntrack_lock(lockp); if (*bucket < net->ct.htable_size) { hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) @@ -1394,6 +1412,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), } spin_unlock(lockp); local_bh_enable(); + cond_resched(); } for_each_possible_cpu(cpu) { @@ -1406,6 +1425,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), set_bit(IPS_DYING_BIT, &ct->status); } spin_unlock_bh(&pcpu->lock); + cond_resched(); } return NULL; found: @@ -1422,6 +1442,8 @@ void nf_ct_iterate_cleanup(struct net *net, struct nf_conn *ct; unsigned int bucket = 0; + might_sleep(); + while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { /* Time to push up daises... */ if (del_timer(&ct->timeout)) @@ -1430,6 +1452,7 @@ void nf_ct_iterate_cleanup(struct net *net, /* ... else the timer will get him soon. */ nf_ct_put(ct); + cond_resched(); } } EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index bd9d31537905..3b40ec575cd5 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -425,7 +425,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, } local_bh_disable(); for (i = 0; i < net->ct.htable_size; i++) { - spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); if (i < net->ct.htable_size) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) unhelp(h, me); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index dbb1bb3edb45..355e8552fd5b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -840,7 +840,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { restart: lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; - spin_lock(lockp); + nf_conntrack_lock(lockp); if (cb->args[0] >= net->ct.htable_size) { spin_unlock(lockp); goto out; diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index b6605e000801..5eefe4a355c6 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -224,12 +224,12 @@ static int __init nf_tables_netdev_init(void) nft_register_chain_type(&nft_filter_chain_netdev); ret = register_pernet_subsys(&nf_tables_netdev_net_ops); - if (ret < 0) + if (ret < 0) { nft_unregister_chain_type(&nft_filter_chain_netdev); - + return ret; + } register_netdevice_notifier(&nf_tables_netdev_notifier); - - return ret; + return 0; } static void __exit nf_tables_netdev_exit(void) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index a7ba23353dab..857ae89633af 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -311,14 +311,14 @@ replay: #endif { nfnl_unlock(subsys_id); - netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(oskb, nlh, -EOPNOTSUPP); return kfree_skb(skb); } } if (!ss->commit || !ss->abort) { nfnl_unlock(subsys_id); - netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(oskb, nlh, -EOPNOTSUPP); return kfree_skb(skb); } @@ -328,10 +328,12 @@ replay: nlh = nlmsg_hdr(skb); err = 0; - if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) || - skb->len < nlh->nlmsg_len) { - err = -EINVAL; - goto ack; + if (nlh->nlmsg_len < NLMSG_HDRLEN || + skb->len < nlh->nlmsg_len || + nlmsg_len(nlh) < sizeof(struct nfgenmsg)) { + nfnl_err_reset(&err_list); + status |= NFNL_BATCH_FAILURE; + goto done; } /* Only requests are handled by the kernel */ @@ -406,7 +408,7 @@ ack: * pointing to the batch header. */ nfnl_err_reset(&err_list); - netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM); + netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM); status |= NFNL_BATCH_FAILURE; goto done; } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 5d010f27ac01..2671b9deb103 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -307,7 +307,7 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) local_bh_disable(); for (i = 0; i < net->ct.htable_size; i++) { - spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); if (i < net->ct.htable_size) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) untimeout(h, timeout); diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 383c17138399..b78c28ba465f 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -46,16 +46,14 @@ static void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { - src64 = get_unaligned_be64(&src[i]); - src64 = be64_to_cpu((__force __be64)src64); + src64 = get_unaligned((u64 *)&src[i]); put_unaligned_be64(src64, &dst[i]); } break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 8; i++) { src64 = get_unaligned_be64(&src[i]); - src64 = (__force u64)cpu_to_be64(src64); - put_unaligned_be64(src64, &dst[i]); + put_unaligned(src64, (u64 *)&dst[i]); } break; } diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index c7808fc19719..c9743f78f219 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -100,7 +100,7 @@ static int nft_counter_init(const struct nft_ctx *ctx, cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu); if (cpu_stats == NULL) - return ENOMEM; + return -ENOMEM; preempt_disable(); this_cpu = this_cpu_ptr(cpu_stats); @@ -138,7 +138,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) cpu_stats = __netdev_alloc_pcpu_stats(struct nft_counter_percpu, GFP_ATOMIC); if (cpu_stats == NULL) - return ENOMEM; + return -ENOMEM; preempt_disable(); this_cpu = this_cpu_ptr(cpu_stats); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a0eb2161e3ef..d4a4619fcebc 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -127,6 +127,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, NF_CT_LABELS_MAX_SIZE - size); return; } +#endif case NFT_CT_BYTES: /* fallthrough */ case NFT_CT_PKTS: { const struct nf_conn_acct *acct = nf_conn_acct_find(ct); @@ -138,7 +139,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, memcpy(dest, &count, sizeof(count)); return; } -#endif default: break; } diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index b7c43def0dc6..e118397254af 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -228,7 +228,7 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); u8 nexthdr; - __be16 frag_off; + __be16 frag_off, oldlen, newlen; int tcphoff; int ret; @@ -244,7 +244,12 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) return NF_DROP; if (ret > 0) { ipv6h = ipv6_hdr(skb); - ipv6h->payload_len = htons(ntohs(ipv6h->payload_len) + ret); + oldlen = ipv6h->payload_len; + newlen = htons(ntohs(oldlen) + ret); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, oldlen), + newlen); + ipv6h->payload_len = newlen; } return XT_CONTINUE; } diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 3eff7b67cdf2..6e57a3966dc5 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -38,7 +38,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -#if IS_ENABLED(CONFIG_NF_DUP_IPV6) +#if IS_ENABLED(CONFIG_IPV6) static unsigned int tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { @@ -131,7 +131,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = { .destroy = tee_tg_destroy, .me = THIS_MODULE, }, -#if IS_ENABLED(CONFIG_NF_DUP_IPV6) +#if IS_ENABLED(CONFIG_IPV6) { .name = "TEE", .revision = 1, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 81dc1bb6e016..f1ffb34e253f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2831,7 +2831,8 @@ static int netlink_dump(struct sock *sk) * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ - skb_reserve(skb, skb_tailroom(skb) - alloc_size); + if (!netlink_rx_is_mmaped(sk)) + skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); len = cb->dump(skb, cb); diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 1605691d9414..5eb7694348b5 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -90,7 +90,9 @@ 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, + /* Don't restrict the packets that can be sent by MTU */ + .mtu = IP_MAX_MTU, }; if (!options) { 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/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/sched/sch_drr.c b/net/sched/sch_drr.c index f26bdea875c1..a1cd778240cd 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -403,6 +403,8 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch) if (len <= cl->deficit) { cl->deficit -= len; skb = qdisc_dequeue_peeked(cl->qdisc); + if (unlikely(skb == NULL)) + goto out; if (cl->qdisc->q.qlen == 0) list_del(&cl->alist); diff --git a/net/sctp/input.c b/net/sctp/input.c index bf61dfb8e09e..49d2cc751386 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -935,15 +935,22 @@ static struct sctp_association *__sctp_lookup_association( struct sctp_transport **pt) { struct sctp_transport *t; + struct sctp_association *asoc = NULL; + rcu_read_lock(); t = sctp_addrs_lookup_transport(net, local, peer); - if (!t || t->dead) - return NULL; + if (!t || !sctp_transport_hold(t)) + goto out; - sctp_association_hold(t->asoc); + asoc = t->asoc; + sctp_association_hold(asoc); *pt = t; - return t->asoc; + sctp_transport_put(t); + +out: + rcu_read_unlock(); + return asoc; } /* Look up an association. protected by RCU read lock */ @@ -955,9 +962,7 @@ struct sctp_association *sctp_lookup_association(struct net *net, { struct sctp_association *asoc; - rcu_read_lock(); asoc = __sctp_lookup_association(net, laddr, paddr, transportp); - rcu_read_unlock(); return asoc; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 684c5b31563b..ded7d931a6a5 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -165,8 +165,6 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa list_for_each_entry_rcu(transport, &assoc->peer.transport_addr_list, transports) { addr = &transport->ipaddr; - if (transport->dead) - continue; af = sctp_get_af_specific(addr->sa.sa_family); if (af->cmp_addr(addr, primary)) { @@ -380,6 +378,8 @@ 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; @@ -412,6 +412,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) sk->sk_rcvbuf); seq_printf(seq, "\n"); + sctp_transport_put(transport); + return 0; } @@ -489,12 +491,12 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) } tsp = (struct sctp_transport *)v; + if (!sctp_transport_hold(tsp)) + return 0; assoc = tsp->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, transports) { - if (tsp->dead) - continue; /* * The remote address (ADDR) */ @@ -544,6 +546,8 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } + sctp_transport_put(tsp); + return 0; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index ab0d538a74ed..1099e99a53c4 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; @@ -1355,6 +1357,8 @@ 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)); @@ -1407,14 +1411,24 @@ 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); /* Allocate and initialize the endpoint hash table. */ sctp_ep_hashsize = 64; @@ -1430,20 +1444,35 @@ 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_KERNEL | __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); @@ -1452,7 +1481,8 @@ static __init int sctp_init(void) if (sctp_transport_hashtable_init()) goto err_thash_alloc; - pr_info("Hash tables configured (bind %d)\n", sctp_port_hashsize); + pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize, + num_entries); sctp_sysctl_register(); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 2e21384697c2..b5327bb77458 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -259,12 +259,6 @@ void sctp_generate_t3_rtx_event(unsigned long peer) goto out_unlock; } - /* Is this transport really dead and just waiting around for - * the timer to let go of the reference? - */ - if (transport->dead) - goto out_unlock; - /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_T3_RTX), @@ -380,12 +374,6 @@ void sctp_generate_heartbeat_event(unsigned long data) goto out_unlock; } - /* Is this structure just waiting around for us to actually - * get destroyed? - */ - if (transport->dead) - goto out_unlock; - error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_HEARTBEAT), asoc->state, asoc->ep, asoc, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9bb80ec4c08f..e878da0949db 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5538,6 +5538,7 @@ 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; @@ -5555,8 +5556,12 @@ 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; } @@ -6636,6 +6641,7 @@ 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; @@ -6659,6 +6665,7 @@ 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/transport.c b/net/sctp/transport.c index aab9e3f29755..a431c14044a4 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -132,8 +132,6 @@ fail: */ void sctp_transport_free(struct sctp_transport *transport) { - transport->dead = 1; - /* Try to delete the heartbeat timer. */ if (del_timer(&transport->hb_timer)) sctp_transport_put(transport); @@ -169,7 +167,7 @@ static void sctp_transport_destroy_rcu(struct rcu_head *head) */ static void sctp_transport_destroy(struct sctp_transport *transport) { - if (unlikely(!transport->dead)) { + if (unlikely(atomic_read(&transport->refcnt))) { WARN(1, "Attempt to destroy undead transport %p!\n", transport); return; } @@ -296,9 +294,9 @@ void sctp_transport_route(struct sctp_transport *transport, } /* Hold a reference to a transport. */ -void sctp_transport_hold(struct sctp_transport *transport) +int sctp_transport_hold(struct sctp_transport *transport) { - atomic_inc(&transport->refcnt); + return atomic_add_unless(&transport->refcnt, 1, 0); } /* Release a reference to a transport and clean up diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 799e65b944b9..cabf586f47d7 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -740,7 +740,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) default: printk(KERN_CRIT "%s: bad return from " "gss_fill_context: %zd\n", __func__, err); - BUG(); + gss_msg->msg.errno = -EIO; } goto err_release_msg; } diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2b32fd602669..273bc3a35425 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/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index cc1251d07297..2dcd7640eeb5 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -341,6 +341,8 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, rqst->rq_reply_bytes_recvd = 0; rqst->rq_bytes_sent = 0; rqst->rq_xid = headerp->rm_xid; + + rqst->rq_private_buf.len = size; set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state); buf = &rqst->rq_rcv_buf; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index ebc661d3b6e3..47f7da58a7f0 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> @@ -567,7 +568,6 @@ 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); /** @@ -582,9 +582,9 @@ 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); @@ -600,9 +600,9 @@ 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); @@ -616,16 +616,17 @@ 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/link.c b/net/tipc/link.c index 0c2944fb9ae0..347cdc99ed09 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1973,8 +1973,10 @@ 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 fa97d9649a28..9d7a16fc5ca4 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -346,12 +346,6 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) skb_queue_head_init(&n->bc_entry.inputq2); for (i = 0; i < MAX_BEARERS; i++) spin_lock_init(&n->links[i].lock); - hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]); - list_for_each_entry_rcu(temp_node, &tn->node_list, list) { - if (n->addr < temp_node->addr) - break; - } - list_add_tail_rcu(&n->list, &temp_node->list); n->state = SELF_DOWN_PEER_LEAVING; n->signature = INVALID_NODE_SIG; n->active_links[0] = INVALID_BEARER_ID; @@ -372,6 +366,12 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) tipc_node_get(n); setup_timer(&n->timer, tipc_node_timeout, (unsigned long)n); n->keepalive_intv = U32_MAX; + hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]); + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { + if (n->addr < temp_node->addr) + break; + } + list_add_tail_rcu(&n->list, &temp_node->list); exit: spin_unlock_bh(&tn->node_list_lock); return n; 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 c5bf5ef2bf89..f75f847e688d 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) @@ -1561,7 +1561,7 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) return -ENOMEM; for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); + unix_inflight(scm->fp->user, scm->fp->fp[i]); return max_level; } @@ -1781,7 +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); @@ -2277,13 +2282,15 @@ 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); @@ -2305,6 +2312,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) bool drop_skb; struct sk_buff *skb, *last; +redo: unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) { err = -ECONNRESET; @@ -2329,9 +2337,11 @@ 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, @@ -2339,11 +2349,12 @@ again: if (signal_pending(current)) { err = sock_intr_errno(timeo); + scm_destroy(&scm); goto out; } mutex_lock(&u->readlock); - continue; + goto redo; unlock: unix_state_unlock(sk); break; 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 8fcdc2283af5..6a0d48525fcf 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -116,7 +116,7 @@ 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); @@ -133,11 +133,11 @@ void unix_inflight(struct file *fp) } unix_tot_inflight++; } - fp->f_cred->user->unix_inflight++; + 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); @@ -152,7 +152,7 @@ void unix_notinflight(struct file *fp) list_del_init(&u->link); unix_tot_inflight--; } - fp->f_cred->user->unix_inflight--; + user->unix_inflight--; spin_unlock(&unix_gc_lock); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 7fd1220fbfa0..bbe65dcb9738 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1557,8 +1557,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) goto out; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - while (total_written < len) { ssize_t written; @@ -1578,7 +1576,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_wait; release_sock(sk); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); timeout = schedule_timeout(timeout); + finish_wait(sk_sleep(sk), &wait); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); @@ -1588,8 +1588,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_wait; } - prepare_to_wait(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); } /* These checks occur both as part of and after the loop @@ -1635,7 +1633,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, out_wait: if (total_written > 0) err = total_written; - finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; @@ -1716,7 +1713,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (err < 0) goto out; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (1) { s64 ready = vsock_stream_has_data(vsk); @@ -1727,7 +1723,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, */ err = -ENOMEM; - goto out_wait; + goto out; } else if (ready > 0) { ssize_t read; @@ -1750,7 +1746,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, vsk, target, read, !(flags & MSG_PEEK), &recv_data); if (err < 0) - goto out_wait; + goto out; if (read >= target || flags & MSG_PEEK) break; @@ -1773,7 +1769,9 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, break; release_sock(sk); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); timeout = schedule_timeout(timeout); + finish_wait(sk_sleep(sk), &wait); lock_sock(sk); if (signal_pending(current)) { @@ -1783,9 +1781,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = -EAGAIN; break; } - - prepare_to_wait(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); } } @@ -1816,8 +1811,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = copied; } -out_wait: - finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3b0ce1c484a3..547ceecc0523 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -231,20 +231,22 @@ static const struct ieee80211_regdomain world_regdom = { /* IEEE 802.11b/g, channels 1..11 */ REG_RULE(2412-10, 2462+10, 40, 6, 20, 0), /* IEEE 802.11b/g, channels 12..13. */ - REG_RULE(2467-10, 2472+10, 40, 6, 20, - NL80211_RRF_NO_IR), + REG_RULE(2467-10, 2472+10, 20, 6, 20, + NL80211_RRF_NO_IR | NL80211_RRF_AUTO_BW), /* IEEE 802.11 channel 14 - Only JP enables * this and for 802.11b only */ REG_RULE(2484-10, 2484+10, 20, 6, 20, NL80211_RRF_NO_IR | NL80211_RRF_NO_OFDM), /* IEEE 802.11a, channel 36..48 */ - REG_RULE(5180-10, 5240+10, 160, 6, 20, - NL80211_RRF_NO_IR), + REG_RULE(5180-10, 5240+10, 80, 6, 20, + NL80211_RRF_NO_IR | + NL80211_RRF_AUTO_BW), /* IEEE 802.11a, channel 52..64 - DFS required */ - REG_RULE(5260-10, 5320+10, 160, 6, 20, + REG_RULE(5260-10, 5320+10, 80, 6, 20, NL80211_RRF_NO_IR | + NL80211_RRF_AUTO_BW | NL80211_RRF_DFS), /* IEEE 802.11a, channel 100..144 - DFS required */ @@ -2745,7 +2747,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) const struct ieee80211_power_rule *power_rule = NULL; char bw[32], cac_time[32]; - pr_info(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n"); + pr_debug(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n"); for (i = 0; i < rd->n_reg_rules; i++) { reg_rule = &rd->reg_rules[i]; @@ -2772,7 +2774,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) * in certain regions */ if (power_rule->max_antenna_gain) - pr_info(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n", + pr_debug(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, bw, @@ -2780,7 +2782,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) power_rule->max_eirp, cac_time); else - pr_info(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n", + pr_debug(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, bw, @@ -2813,35 +2815,35 @@ static void print_regdomain(const struct ieee80211_regdomain *rd) struct cfg80211_registered_device *rdev; rdev = cfg80211_rdev_by_wiphy_idx(lr->wiphy_idx); if (rdev) { - pr_info("Current regulatory domain updated by AP to: %c%c\n", + pr_debug("Current regulatory domain updated by AP to: %c%c\n", rdev->country_ie_alpha2[0], rdev->country_ie_alpha2[1]); } else - pr_info("Current regulatory domain intersected:\n"); + pr_debug("Current regulatory domain intersected:\n"); } else - pr_info("Current regulatory domain intersected:\n"); + pr_debug("Current regulatory domain intersected:\n"); } else if (is_world_regdom(rd->alpha2)) { - pr_info("World regulatory domain updated:\n"); + pr_debug("World regulatory domain updated:\n"); } else { if (is_unknown_alpha2(rd->alpha2)) - pr_info("Regulatory domain changed to driver built-in settings (unknown country)\n"); + pr_debug("Regulatory domain changed to driver built-in settings (unknown country)\n"); else { if (reg_request_cell_base(lr)) - pr_info("Regulatory domain changed to country: %c%c by Cell Station\n", + pr_debug("Regulatory domain changed to country: %c%c by Cell Station\n", rd->alpha2[0], rd->alpha2[1]); else - pr_info("Regulatory domain changed to country: %c%c\n", + pr_debug("Regulatory domain changed to country: %c%c\n", rd->alpha2[0], rd->alpha2[1]); } } - pr_info(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region)); + pr_debug(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region)); print_rd_rules(rd); } static void print_regdomain_info(const struct ieee80211_regdomain *rd) { - pr_info("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]); + pr_debug("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]); print_rd_rules(rd); } @@ -2862,7 +2864,8 @@ static int reg_set_rd_user(const struct ieee80211_regdomain *rd, return -EALREADY; if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } @@ -2898,7 +2901,8 @@ static int reg_set_rd_driver(const struct ieee80211_regdomain *rd, return -EALREADY; if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } @@ -2956,7 +2960,8 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, */ if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } |