diff options
Diffstat (limited to 'net')
82 files changed, 951 insertions, 540 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index fda3a80e9340..2b74ed56eb16 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -193,6 +193,8 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, dev); grp->nr_vlan_devs++; + netdev_update_features(dev); + return 0; out_unregister_netdev: diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index c84420cb410d..a662408ad867 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -763,11 +763,16 @@ int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb) bat_priv = netdev_priv(mesh_iface); primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + if (!primary_if) { ret = -ENOENT; goto out_put_mesh_iface; } + if (primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out_put_primary_if; + } + hard_iface = batadv_netlink_get_hardif(bat_priv, cb); if (IS_ERR(hard_iface) && PTR_ERR(hard_iface) != -ENONET) { ret = PTR_ERR(hard_iface); @@ -1327,11 +1332,16 @@ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) bat_priv = netdev_priv(mesh_iface); primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + if (!primary_if) { ret = -ENOENT; goto out_put_mesh_iface; } + if (primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out_put_primary_if; + } + hard_iface = batadv_netlink_get_hardif(bat_priv, cb); if (IS_ERR(hard_iface) && PTR_ERR(hard_iface) != -ENONET) { ret = PTR_ERR(hard_iface); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index f0c862091bff..2c21ae8abadc 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -53,6 +53,11 @@ static bool enable_6lowpan; static struct l2cap_chan *listen_chan; static DEFINE_MUTEX(set_lock); +enum { + LOWPAN_PEER_CLOSING, + LOWPAN_PEER_MAXBITS +}; + struct lowpan_peer { struct list_head list; struct rcu_head rcu; @@ -61,6 +66,8 @@ struct lowpan_peer { /* peer addresses in various formats */ unsigned char lladdr[ETH_ALEN]; struct in6_addr peer_addr; + + DECLARE_BITMAP(flags, LOWPAN_PEER_MAXBITS); }; struct lowpan_btle_dev { @@ -289,6 +296,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->pkt_type = PACKET_HOST; local_skb->dev = dev; + skb_reset_mac_header(local_skb); skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { @@ -919,7 +927,9 @@ static int bt_6lowpan_disconnect(struct l2cap_conn *conn, u8 dst_type) BT_DBG("peer %p chan %p", peer, peer->chan); + l2cap_chan_lock(peer->chan); l2cap_chan_close(peer->chan, ENOENT); + l2cap_chan_unlock(peer->chan); return 0; } @@ -956,10 +966,11 @@ static struct l2cap_chan *bt_6lowpan_listen(void) } static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, - struct l2cap_conn **conn) + struct l2cap_conn **conn, bool disconnect) { struct hci_conn *hcon; struct hci_dev *hdev; + int le_addr_type; int n; n = sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", @@ -970,13 +981,32 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, if (n < 7) return -EINVAL; + if (disconnect) { + /* The "disconnect" debugfs command has used different address + * type constants than "connect" since 2015. Let's retain that + * for now even though it's obviously buggy... + */ + *addr_type += 1; + } + + switch (*addr_type) { + case BDADDR_LE_PUBLIC: + le_addr_type = ADDR_LE_DEV_PUBLIC; + break; + case BDADDR_LE_RANDOM: + le_addr_type = ADDR_LE_DEV_RANDOM; + break; + default: + return -EINVAL; + } + /* The LE_PUBLIC address type is ignored because of BDADDR_ANY */ hdev = hci_get_route(addr, BDADDR_ANY, BDADDR_LE_PUBLIC); if (!hdev) return -ENOENT; hci_dev_lock(hdev); - hcon = hci_conn_hash_lookup_le(hdev, addr, *addr_type); + hcon = hci_conn_hash_lookup_le(hdev, addr, le_addr_type); hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -993,41 +1023,52 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, static void disconnect_all_peers(void) { struct lowpan_btle_dev *entry; - struct lowpan_peer *peer, *tmp_peer, *new_peer; - struct list_head peers; - - INIT_LIST_HEAD(&peers); + struct lowpan_peer *peer; + int nchans; - /* We make a separate list of peers as the close_cb() will - * modify the device peers list so it is better not to mess - * with the same list at the same time. + /* l2cap_chan_close() cannot be called from RCU, and lock ordering + * chan->lock > devices_lock prevents taking write side lock, so copy + * then close. */ rcu_read_lock(); + list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) + list_for_each_entry_rcu(peer, &entry->peers, list) + clear_bit(LOWPAN_PEER_CLOSING, peer->flags); + rcu_read_unlock(); - list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { - list_for_each_entry_rcu(peer, &entry->peers, list) { - new_peer = kmalloc(sizeof(*new_peer), GFP_ATOMIC); - if (!new_peer) - break; + do { + struct l2cap_chan *chans[32]; + int i; - new_peer->chan = peer->chan; - INIT_LIST_HEAD(&new_peer->list); + nchans = 0; - list_add(&new_peer->list, &peers); - } - } + spin_lock(&devices_lock); - rcu_read_unlock(); + list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { + list_for_each_entry_rcu(peer, &entry->peers, list) { + if (test_and_set_bit(LOWPAN_PEER_CLOSING, + peer->flags)) + continue; - spin_lock(&devices_lock); - list_for_each_entry_safe(peer, tmp_peer, &peers, list) { - l2cap_chan_close(peer->chan, ENOENT); + l2cap_chan_hold(peer->chan); + chans[nchans++] = peer->chan; - list_del_rcu(&peer->list); - kfree_rcu(peer, rcu); - } - spin_unlock(&devices_lock); + if (nchans >= ARRAY_SIZE(chans)) + goto done; + } + } + +done: + spin_unlock(&devices_lock); + + for (i = 0; i < nchans; ++i) { + l2cap_chan_lock(chans[i]); + l2cap_chan_close(chans[i], ENOENT); + l2cap_chan_unlock(chans[i]); + l2cap_chan_put(chans[i]); + } + } while (nchans); } struct set_enable { @@ -1050,7 +1091,9 @@ static void do_enable_set(struct work_struct *work) mutex_lock(&set_lock); if (listen_chan) { + l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); + l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); } @@ -1103,13 +1146,15 @@ static ssize_t lowpan_control_write(struct file *fp, buf[buf_size] = '\0'; if (memcmp(buf, "connect ", 8) == 0) { - ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn); + ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn, false); if (ret == -EINVAL) return ret; mutex_lock(&set_lock); if (listen_chan) { + l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); + l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); listen_chan = NULL; } @@ -1140,7 +1185,7 @@ static ssize_t lowpan_control_write(struct file *fp, } if (memcmp(buf, "disconnect ", 11) == 0) { - ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn); + ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn, true); if (ret < 0) return ret; @@ -1271,7 +1316,9 @@ static void __exit bt_6lowpan_exit(void) debugfs_remove(lowpan_control_debugfs); if (listen_chan) { + l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); + l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 111f0e37b672..6fc0692abf05 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -769,21 +769,23 @@ static void find_bis(struct hci_conn *conn, void *data) d->count++; } -static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) +static int hci_le_big_terminate(struct hci_dev *hdev, struct hci_conn *conn) { struct iso_list_data *d; int ret; - bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, conn->sync_handle); + bt_dev_dbg(hdev, "hcon %p big 0x%2.2x sync_handle 0x%4.4x", conn, + conn->iso_qos.bcast.big, conn->sync_handle); d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; - d->big = big; + d->big = conn->iso_qos.bcast.big; d->sync_handle = conn->sync_handle; - if (test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { + if (conn->type == PA_LINK && + test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { hci_conn_hash_list_flag(hdev, find_bis, PA_LINK, HCI_CONN_PA_SYNC, d); @@ -801,6 +803,9 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c d->big_sync_term = true; } + if (!d->pa_sync_term && !d->big_sync_term) + return 0; + ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); if (ret) @@ -843,10 +848,16 @@ static void bis_cleanup(struct hci_conn *conn) if (bis) return; + bis = hci_conn_hash_lookup_big_state(hdev, + conn->iso_qos.bcast.big, + BT_OPEN, + HCI_ROLE_MASTER); + if (bis) + return; + hci_le_terminate_big(hdev, conn); } else { - hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, - conn); + hci_le_big_terminate(hdev, conn); } } @@ -987,19 +998,20 @@ static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t conn->mtu = hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; break; case CIS_LINK: - case BIS_LINK: - case PA_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type); - /* set proper cleanup function */ - if (!bacmp(dst, BDADDR_ANY)) - conn->cleanup = bis_cleanup; - else if (conn->role == HCI_ROLE_MASTER) + if (conn->role == HCI_ROLE_MASTER) conn->cleanup = cis_cleanup; - conn->mtu = hdev->iso_mtu ? hdev->iso_mtu : - hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; + conn->mtu = hdev->iso_mtu; + break; + case PA_LINK: + case BIS_LINK: + /* conn->src should reflect the local identity address */ + hci_copy_identity_address(hdev, &conn->src, &conn->src_type); + conn->cleanup = bis_cleanup; + conn->mtu = hdev->iso_mtu; break; case SCO_LINK: if (lmp_esco_capable(hdev)) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d790b0d4eb9a..3838b90343d9 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1607,8 +1607,10 @@ static u8 hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, void *data, hci_dev_set_flag(hdev, HCI_LE_ADV); - if (adv && !adv->periodic) + if (adv) adv->enabled = true; + else if (!set->handle) + hci_dev_set_flag(hdev, HCI_LE_ADV_0); conn = hci_lookup_le_connect(hdev); if (conn) @@ -1619,6 +1621,8 @@ static u8 hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, void *data, if (cp->num_of_sets) { if (adv) adv->enabled = false; + else if (!set->handle) + hci_dev_clear_flag(hdev, HCI_LE_ADV_0); /* If just one instance was disabled check if there are * any other instance enabled before clearing HCI_LE_ADV @@ -3959,8 +3963,11 @@ static u8 hci_cc_le_set_per_adv_enable(struct hci_dev *hdev, void *data, hci_dev_set_flag(hdev, HCI_LE_PER_ADV); if (adv) - adv->enabled = true; + adv->periodic_enabled = true; } else { + if (adv) + adv->periodic_enabled = false; + /* If just one instance was disabled check if there are * any other instance enabled before clearing HCI_LE_PER_ADV. * The current periodic adv instance will be marked as @@ -4211,6 +4218,13 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, void *data, } if (i == ARRAY_SIZE(hci_cc_table)) { + if (!skb->len) { + bt_dev_err(hdev, "Unexpected cc 0x%4.4x with no status", + *opcode); + *status = HCI_ERROR_UNSPECIFIED; + return; + } + /* Unknown opcode, assume byte 0 contains the status, so * that e.g. __hci_cmd_sync() properly returns errors * for vendor specific commands send by HCI drivers. @@ -5829,6 +5843,29 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, void *data, le16_to_cpu(ev->supervision_timeout)); } +static void hci_le_pa_sync_lost_evt(struct hci_dev *hdev, void *data, + struct sk_buff *skb) +{ + struct hci_ev_le_pa_sync_lost *ev = data; + u16 handle = le16_to_cpu(ev->handle); + struct hci_conn *conn; + + bt_dev_dbg(hdev, "sync handle 0x%4.4x", handle); + + hci_dev_lock(hdev); + + /* Delete the pa sync connection */ + conn = hci_conn_hash_lookup_pa_sync_handle(hdev, handle); + if (conn) { + clear_bit(HCI_CONN_BIG_SYNC, &conn->flags); + clear_bit(HCI_CONN_PA_SYNC, &conn->flags); + hci_disconn_cfm(conn, HCI_ERROR_REMOTE_USER_TERM); + hci_conn_del(conn); + } + + hci_dev_unlock(hdev); +} + static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -6987,14 +7024,9 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, continue; } - if (ev->status != 0x42) { + if (ev->status != 0x42) /* Mark PA sync as established */ set_bit(HCI_CONN_PA_SYNC, &bis->flags); - /* Reset cleanup callback of PA Sync so it doesn't - * terminate the sync when deleting the connection. - */ - conn->cleanup = NULL; - } bis->sync_handle = conn->sync_handle; bis->iso_qos.bcast.big = ev->handle; @@ -7037,29 +7069,24 @@ static void hci_le_big_sync_lost_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_big_sync_lost *ev = data; - struct hci_conn *bis, *conn; - bool mgmt_conn; + struct hci_conn *bis; + bool mgmt_conn = false; bt_dev_dbg(hdev, "big handle 0x%2.2x", ev->handle); hci_dev_lock(hdev); - /* Delete the pa sync connection */ - bis = hci_conn_hash_lookup_pa_sync_big_handle(hdev, ev->handle); - if (bis) { - conn = hci_conn_hash_lookup_pa_sync_handle(hdev, - bis->sync_handle); - if (conn) - hci_conn_del(conn); - } - /* Delete each bis connection */ while ((bis = hci_conn_hash_lookup_big_state(hdev, ev->handle, BT_CONNECTED, HCI_ROLE_SLAVE))) { - mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &bis->flags); - mgmt_device_disconnected(hdev, &bis->dst, bis->type, bis->dst_type, - ev->reason, mgmt_conn); + if (!mgmt_conn) { + mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, + &bis->flags); + mgmt_device_disconnected(hdev, &bis->dst, bis->type, + bis->dst_type, ev->reason, + mgmt_conn); + } clear_bit(HCI_CONN_BIG_SYNC, &bis->flags); hci_disconn_cfm(bis, ev->reason); @@ -7173,6 +7200,9 @@ static const struct hci_le_ev { hci_le_per_adv_report_evt, sizeof(struct hci_ev_le_per_adv_report), HCI_MAX_EVENT_SIZE), + /* [0x10 = HCI_EV_LE_PA_SYNC_LOST] */ + HCI_LE_EV(HCI_EV_LE_PA_SYNC_LOST, hci_le_pa_sync_lost_evt, + sizeof(struct hci_ev_le_pa_sync_lost)), /* [0x12 = HCI_EV_LE_EXT_ADV_SET_TERM] */ HCI_LE_EV(HCI_EV_LE_EXT_ADV_SET_TERM, hci_le_ext_adv_term_evt, sizeof(struct hci_evt_le_ext_adv_set_term)), diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index eefdb6134ca5..6e76798ec786 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -863,11 +863,17 @@ bool hci_cmd_sync_dequeue_once(struct hci_dev *hdev, { struct hci_cmd_sync_work_entry *entry; - entry = hci_cmd_sync_lookup_entry(hdev, func, data, destroy); - if (!entry) + mutex_lock(&hdev->cmd_sync_work_lock); + + entry = _hci_cmd_sync_lookup_entry(hdev, func, data, destroy); + if (!entry) { + mutex_unlock(&hdev->cmd_sync_work_lock); return false; + } - hci_cmd_sync_cancel_entry(hdev, entry); + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + + mutex_unlock(&hdev->cmd_sync_work_lock); return true; } @@ -1601,7 +1607,7 @@ int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance) /* If periodic advertising already disabled there is nothing to do. */ adv = hci_find_adv_instance(hdev, instance); - if (!adv || !adv->periodic || !adv->enabled) + if (!adv || !adv->periodic_enabled) return 0; memset(&cp, 0, sizeof(cp)); @@ -1666,7 +1672,7 @@ static int hci_enable_per_advertising_sync(struct hci_dev *hdev, u8 instance) /* If periodic advertising already enabled there is nothing to do. */ adv = hci_find_adv_instance(hdev, instance); - if (adv && adv->periodic && adv->enabled) + if (adv && adv->periodic_enabled) return 0; memset(&cp, 0, sizeof(cp)); @@ -2600,9 +2606,8 @@ static int hci_resume_advertising_sync(struct hci_dev *hdev) /* If current advertising instance is set to instance 0x00 * then we need to re-enable it. */ - if (!hdev->cur_adv_instance) - err = hci_enable_ext_advertising_sync(hdev, - hdev->cur_adv_instance); + if (hci_dev_test_and_clear_flag(hdev, HCI_LE_ADV_0)) + err = hci_enable_ext_advertising_sync(hdev, 0x00); } else { /* Schedule for most recent instance to be restarted and begin * the software rotation loop @@ -6994,7 +6999,7 @@ static void create_pa_complete(struct hci_dev *hdev, void *data, int err) hci_dev_lock(hdev); - if (!hci_conn_valid(hdev, conn)) + if (hci_conn_valid(hdev, conn)) clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags); if (!err) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 9b263d061e05..3d98cb6291da 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -2032,7 +2032,7 @@ static void iso_conn_ready(struct iso_conn *conn) */ if (!bacmp(&hcon->dst, BDADDR_ANY)) { bacpy(&hcon->dst, &iso_pi(parent)->dst); - hcon->dst_type = iso_pi(parent)->dst_type; + hcon->dst_type = le_addr_type(iso_pi(parent)->dst_type); } if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags)) { @@ -2046,7 +2046,13 @@ static void iso_conn_ready(struct iso_conn *conn) } bacpy(&iso_pi(sk)->dst, &hcon->dst); - iso_pi(sk)->dst_type = hcon->dst_type; + + /* Convert from HCI to three-value type */ + if (hcon->dst_type == ADDR_LE_DEV_PUBLIC) + iso_pi(sk)->dst_type = BDADDR_LE_PUBLIC; + else + iso_pi(sk)->dst_type = BDADDR_LE_RANDOM; + iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle; memcpy(iso_pi(sk)->base, iso_pi(parent)->base, iso_pi(parent)->base_len); iso_pi(sk)->base_len = iso_pi(parent)->base_len; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 805c752ac0a9..35c57657bcf4 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -282,7 +282,7 @@ static void __set_retrans_timer(struct l2cap_chan *chan) if (!delayed_work_pending(&chan->monitor_timer) && chan->retrans_timeout) { l2cap_set_timer(chan, &chan->retrans_timer, - secs_to_jiffies(chan->retrans_timeout)); + msecs_to_jiffies(chan->retrans_timeout)); } } @@ -291,7 +291,7 @@ static void __set_monitor_timer(struct l2cap_chan *chan) __clear_retrans_timer(chan); if (chan->monitor_timeout) { l2cap_set_timer(chan, &chan->monitor_timer, - secs_to_jiffies(chan->monitor_timeout)); + msecs_to_jiffies(chan->monitor_timeout)); } } @@ -497,6 +497,7 @@ void l2cap_chan_hold(struct l2cap_chan *c) kref_get(&c->kref); } +EXPORT_SYMBOL_GPL(l2cap_chan_hold); struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c) { diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index a3d16eece0d2..262bf984d2aa 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2175,19 +2175,24 @@ static void set_mesh_complete(struct hci_dev *hdev, void *data, int err) sk = cmd->sk; if (status) { + mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, + status); mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev, true, cmd_status_rsp, &status); - return; + goto done; } - mgmt_pending_remove(cmd); mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, 0, NULL, 0); + +done: + mgmt_pending_free(cmd); } static int set_mesh_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_cp_set_mesh cp; + DEFINE_FLEX(struct mgmt_cp_set_mesh, cp, ad_types, num_ad_types, + sizeof(hdev->mesh_ad_types)); size_t len; mutex_lock(&hdev->mgmt_pending_lock); @@ -2197,27 +2202,26 @@ static int set_mesh_sync(struct hci_dev *hdev, void *data) return -ECANCELED; } - memcpy(&cp, cmd->param, sizeof(cp)); + len = cmd->param_len; + memcpy(cp, cmd->param, min(__struct_size(cp), len)); mutex_unlock(&hdev->mgmt_pending_lock); - len = cmd->param_len; - memset(hdev->mesh_ad_types, 0, sizeof(hdev->mesh_ad_types)); - if (cp.enable) + if (cp->enable) hci_dev_set_flag(hdev, HCI_MESH); else hci_dev_clear_flag(hdev, HCI_MESH); - hdev->le_scan_interval = __le16_to_cpu(cp.period); - hdev->le_scan_window = __le16_to_cpu(cp.window); + hdev->le_scan_interval = __le16_to_cpu(cp->period); + hdev->le_scan_window = __le16_to_cpu(cp->window); - len -= sizeof(cp); + len -= sizeof(struct mgmt_cp_set_mesh); /* If filters don't fit, forward all adv pkts */ if (len <= sizeof(hdev->mesh_ad_types)) - memcpy(hdev->mesh_ad_types, cp.ad_types, len); + memcpy(hdev->mesh_ad_types, cp->ad_types, len); hci_update_passive_scan_sync(hdev); return 0; @@ -5391,9 +5395,9 @@ static u8 parse_adv_monitor_pattern(struct adv_monitor *m, u8 pattern_count, for (i = 0; i < pattern_count; i++) { offset = patterns[i].offset; length = patterns[i].length; - if (offset >= HCI_MAX_EXT_AD_LENGTH || - length > HCI_MAX_EXT_AD_LENGTH || - (offset + length) > HCI_MAX_EXT_AD_LENGTH) + if (offset >= HCI_MAX_AD_LENGTH || + length > HCI_MAX_AD_LENGTH || + (offset + length) > HCI_MAX_AD_LENGTH) return MGMT_STATUS_INVALID_PARAMS; p = kmalloc(sizeof(*p), GFP_KERNEL); @@ -9493,6 +9497,7 @@ void mgmt_index_removed(struct hci_dev *hdev) cancel_delayed_work_sync(&hdev->discov_off); cancel_delayed_work_sync(&hdev->service_cache); cancel_delayed_work_sync(&hdev->rpa_expired); + cancel_delayed_work_sync(&hdev->mesh_send_done); } void mgmt_power_on(struct hci_dev *hdev, int err) diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 376ce6de84be..b783526ab588 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -643,8 +643,8 @@ static void rfcomm_dev_modem_status(struct rfcomm_dlc *dlc, u8 v24_sig) tty_port_tty_hangup(&dev->port, true); dev->modem_status = - ((v24_sig & RFCOMM_V24_RTC) ? (TIOCM_DSR | TIOCM_DTR) : 0) | - ((v24_sig & RFCOMM_V24_RTR) ? (TIOCM_RTS | TIOCM_CTS) : 0) | + ((v24_sig & RFCOMM_V24_RTC) ? TIOCM_DSR : 0) | + ((v24_sig & RFCOMM_V24_RTR) ? TIOCM_CTS : 0) | ((v24_sig & RFCOMM_V24_IC) ? TIOCM_RI : 0) | ((v24_sig & RFCOMM_V24_DV) ? TIOCM_CD : 0); } @@ -1055,10 +1055,14 @@ static void rfcomm_tty_hangup(struct tty_struct *tty) static int rfcomm_tty_tiocmget(struct tty_struct *tty) { struct rfcomm_dev *dev = tty->driver_data; + struct rfcomm_dlc *dlc = dev->dlc; + u8 v24_sig; BT_DBG("tty %p dev %p", tty, dev); - return dev->modem_status; + rfcomm_dlc_get_modem_status(dlc, &v24_sig); + + return (v24_sig & (TIOCM_DTR | TIOCM_RTS)) | dev->modem_status; } static int rfcomm_tty_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) @@ -1071,23 +1075,15 @@ static int rfcomm_tty_tiocmset(struct tty_struct *tty, unsigned int set, unsigne rfcomm_dlc_get_modem_status(dlc, &v24_sig); - if (set & TIOCM_DSR || set & TIOCM_DTR) + if (set & TIOCM_DTR) v24_sig |= RFCOMM_V24_RTC; - if (set & TIOCM_RTS || set & TIOCM_CTS) + if (set & TIOCM_RTS) v24_sig |= RFCOMM_V24_RTR; - if (set & TIOCM_RI) - v24_sig |= RFCOMM_V24_IC; - if (set & TIOCM_CD) - v24_sig |= RFCOMM_V24_DV; - if (clear & TIOCM_DSR || clear & TIOCM_DTR) + if (clear & TIOCM_DTR) v24_sig &= ~RFCOMM_V24_RTC; - if (clear & TIOCM_RTS || clear & TIOCM_CTS) + if (clear & TIOCM_RTS) v24_sig &= ~RFCOMM_V24_RTR; - if (clear & TIOCM_RI) - v24_sig &= ~RFCOMM_V24_IC; - if (clear & TIOCM_CD) - v24_sig &= ~RFCOMM_V24_DV; rfcomm_dlc_set_modem_status(dlc, v24_sig); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 870bdf2e082c..dea09096ad0f 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -25,7 +25,7 @@ static inline int should_deliver(const struct net_bridge_port *p, vg = nbp_vlan_group_rcu(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - (br_mst_is_enabled(p->br) || p->state == BR_STATE_FORWARDING) && + (br_mst_is_enabled(p) || p->state == BR_STATE_FORWARDING) && br_allowed_egress(vg, skb) && nbp_switchdev_allowed_egress(p, skb) && !br_skb_isolated(p, skb); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 98c5b9c3145f..ca3a637d7cca 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -386,6 +386,7 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_mst_uninit(br); br_recalculate_neigh_suppress_enabled(br); br_fdb_delete_by_port(br, NULL, 0, 1); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 67b4c905e49a..777fa869c1a1 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -94,7 +94,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb br = p->br; - if (br_mst_is_enabled(br)) { + if (br_mst_is_enabled(p)) { state = BR_STATE_FORWARDING; } else { if (p->state == BR_STATE_DISABLED) { @@ -429,7 +429,7 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) return RX_HANDLER_PASS; forward: - if (br_mst_is_enabled(p->br)) + if (br_mst_is_enabled(p)) goto defer_stp_filtering; switch (p->state) { diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c index 3f24b4ee49c2..43a300ae6bfa 100644 --- a/net/bridge/br_mst.c +++ b/net/bridge/br_mst.c @@ -22,6 +22,12 @@ bool br_mst_enabled(const struct net_device *dev) } EXPORT_SYMBOL_GPL(br_mst_enabled); +void br_mst_uninit(struct net_bridge *br) +{ + if (br_opt_get(br, BROPT_MST_ENABLED)) + static_branch_dec(&br_mst_used); +} + int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids) { const struct net_bridge_vlan_group *vg; @@ -225,9 +231,9 @@ int br_mst_set_enabled(struct net_bridge *br, bool on, return err; if (on) - static_branch_enable(&br_mst_used); + static_branch_inc(&br_mst_used); else - static_branch_disable(&br_mst_used); + static_branch_dec(&br_mst_used); br_opt_toggle(br, BROPT_MST_ENABLED, on); return 0; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 16be5d250402..7280c4e9305f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1935,10 +1935,12 @@ static inline bool br_vlan_state_allowed(u8 state, bool learn_allow) /* br_mst.c */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING DECLARE_STATIC_KEY_FALSE(br_mst_used); -static inline bool br_mst_is_enabled(struct net_bridge *br) +static inline bool br_mst_is_enabled(const struct net_bridge_port *p) { + /* check the port's vlan group to avoid racing with port deletion */ return static_branch_unlikely(&br_mst_used) && - br_opt_get(br, BROPT_MST_ENABLED); + br_opt_get(p->br, BROPT_MST_ENABLED) && + rcu_access_pointer(p->vlgrp); } int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, @@ -1952,8 +1954,9 @@ int br_mst_fill_info(struct sk_buff *skb, const struct net_bridge_vlan_group *vg); int br_mst_process(struct net_bridge_port *p, const struct nlattr *mst_attr, struct netlink_ext_ack *extack); +void br_mst_uninit(struct net_bridge *br); #else -static inline bool br_mst_is_enabled(struct net_bridge *br) +static inline bool br_mst_is_enabled(const struct net_bridge_port *p) { return false; } @@ -1987,6 +1990,10 @@ static inline int br_mst_process(struct net_bridge_port *p, { return -EOPNOTSUPP; } + +static inline void br_mst_uninit(struct net_bridge *br) +{ +} #endif struct nf_br_ops { diff --git a/net/core/datagram.c b/net/core/datagram.c index cb4b9ef2e4e3..c285c6465923 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -920,21 +920,22 @@ fault: EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg); /** - * datagram_poll - generic datagram poll + * datagram_poll_queue - same as datagram_poll, but on a specific receive + * queue * @file: file struct * @sock: socket * @wait: poll table + * @rcv_queue: receive queue to poll * - * Datagram poll: Again totally generic. This also handles - * sequenced packet sockets providing the socket receive queue - * is only ever holding data ready to receive. + * Performs polling on the given receive queue, handling shutdown, error, + * and connection state. This is useful for protocols that deliver + * userspace-bound packets through a custom queue instead of + * sk->sk_receive_queue. * - * Note: when you *don't* use this routine for this protocol, - * and you use a different write policy from sock_writeable() - * then please supply your own write_space callback. + * Return: poll bitmask indicating the socket's current state */ -__poll_t datagram_poll(struct file *file, struct socket *sock, - poll_table *wait) +__poll_t datagram_poll_queue(struct file *file, struct socket *sock, + poll_table *wait, struct sk_buff_head *rcv_queue) { struct sock *sk = sock->sk; __poll_t mask; @@ -956,7 +957,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(rcv_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -978,4 +979,27 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, return mask; } +EXPORT_SYMBOL(datagram_poll_queue); + +/** + * datagram_poll - generic datagram poll + * @file: file struct + * @sock: socket + * @wait: poll table + * + * Datagram poll: Again totally generic. This also handles + * sequenced packet sockets providing the socket receive queue + * is only ever holding data ready to receive. + * + * Note: when you *don't* use this routine for this protocol, + * and you use a different write policy from sock_writeable() + * then please supply your own write_space callback. + * + * Return: poll bitmask indicating the socket's current state + */ +__poll_t datagram_poll(struct file *file, struct socket *sock, poll_table *wait) +{ + return datagram_poll_queue(file, sock, wait, + &sock->sk->sk_receive_queue); +} EXPORT_SYMBOL(datagram_poll); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index ad54b12d4b4c..8bb71a10dba0 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -443,6 +443,9 @@ static int generic_hwtstamp_ioctl_lower(struct net_device *dev, int cmd, struct ifreq ifrr; int err; + if (!kernel_cfg->ifr) + return -EINVAL; + strscpy_pad(ifrr.ifr_name, dev->name, IFNAMSIZ); ifrr.ifr_ifru = kernel_cfg->ifr->ifr_ifru; diff --git a/net/core/devmem.c b/net/core/devmem.c index d9de31a6cc7f..1d04754bc756 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -17,6 +17,7 @@ #include <net/page_pool/helpers.h> #include <net/page_pool/memory_provider.h> #include <net/sock.h> +#include <net/tcp.h> #include <trace/events/page_pool.h> #include "devmem.h" @@ -357,7 +358,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id) { struct net_devmem_dmabuf_binding *binding; - struct dst_entry *dst = __sk_dst_get(sk); + struct net_device *dst_dev; + struct dst_entry *dst; int err = 0; binding = net_devmem_lookup_dmabuf(dmabuf_id); @@ -366,16 +368,35 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk, goto out_err; } + rcu_read_lock(); + dst = __sk_dst_get(sk); + /* If dst is NULL (route expired), attempt to rebuild it. */ + if (unlikely(!dst)) { + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) { + err = -EHOSTUNREACH; + goto out_unlock; + } + dst = __sk_dst_get(sk); + if (unlikely(!dst)) { + err = -ENODEV; + goto out_unlock; + } + } + /* The dma-addrs in this binding are only reachable to the corresponding * net_device. */ - if (!dst || !dst->dev || dst->dev->ifindex != binding->dev->ifindex) { + dst_dev = dst_dev_rcu(dst); + if (unlikely(!dst_dev) || unlikely(dst_dev != binding->dev)) { err = -ENODEV; - goto out_err; + goto out_unlock; } + rcu_read_unlock(); return binding; +out_unlock: + rcu_read_unlock(); out_err: if (binding) net_devmem_dmabuf_binding_put(binding); diff --git a/net/core/filter.c b/net/core/filter.c index 76628df1fc82..fa06c5a08e22 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3877,7 +3877,8 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u32 new_len = skb->len + head_room; int ret; - if (unlikely(flags || (!skb_is_gso(skb) && new_len > max_len) || + if (unlikely(flags || (int)head_room < 0 || + (!skb_is_gso(skb) && new_len > max_len) || new_len < skb->len)) return -EINVAL; diff --git a/net/core/gro.c b/net/core/gro.c index 5ba4504cfd28..76f9c3712422 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -639,6 +639,8 @@ EXPORT_SYMBOL(gro_receive_skb); static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) { + struct skb_shared_info *shinfo; + if (unlikely(skb->pfmemalloc)) { consume_skb(skb); return; @@ -655,8 +657,12 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb->ip_summed = CHECKSUM_NONE; - skb_shinfo(skb)->gso_type = 0; - skb_shinfo(skb)->gso_size = 0; + + shinfo = skb_shinfo(skb); + shinfo->gso_type = 0; + shinfo->gso_size = 0; + shinfo->hwtstamps.hwtstamp = 0; + if (unlikely(skb->slow_gro)) { skb_orphan(skb); skb_ext_reset(skb); diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index b43911562f4d..a725d21159a6 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -43,12 +43,11 @@ drop: if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); - if (have_bh_lock) - local_unlock_nested_bh(&gcells->cells->bh_lock); - res = NET_RX_SUCCESS; unlock: + if (have_bh_lock) + local_unlock_nested_bh(&gcells->cells->bh_lock); rcu_read_unlock(); return res; } @@ -61,9 +60,10 @@ static int gro_cell_poll(struct napi_struct *napi, int budget) struct sk_buff *skb; int work_done = 0; - __local_lock_nested_bh(&cell->bh_lock); while (work_done < budget) { + __local_lock_nested_bh(&cell->bh_lock); skb = __skb_dequeue(&cell->napi_skbs); + __local_unlock_nested_bh(&cell->bh_lock); if (!skb) break; napi_gro_receive(napi, skb); @@ -72,7 +72,6 @@ static int gro_cell_poll(struct napi_struct *napi, int budget) if (work_done < budget) napi_complete_done(napi, work_done); - __local_unlock_nested_bh(&cell->bh_lock); return work_done; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 60a05d3b7c24..331764845e8f 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -228,19 +228,16 @@ static void refill_skbs(struct netpoll *np) { struct sk_buff_head *skb_pool; struct sk_buff *skb; - unsigned long flags; skb_pool = &np->skb_pool; - spin_lock_irqsave(&skb_pool->lock, flags); - while (skb_pool->qlen < MAX_SKBS) { + while (READ_ONCE(skb_pool->qlen) < MAX_SKBS) { skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC); if (!skb) break; - __skb_queue_tail(skb_pool, skb); + skb_queue_tail(skb_pool, skb); } - spin_unlock_irqrestore(&skb_pool->lock, flags); } static void zap_completion_queue(void) @@ -814,6 +811,10 @@ static void __netpoll_cleanup(struct netpoll *np) if (!npinfo) return; + /* At this point, there is a single npinfo instance per netdevice, and + * its refcnt tracks how many netpoll structures are linked to it. We + * only perform npinfo cleanup when the refcnt decrements to zero. + */ if (refcount_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; @@ -823,8 +824,7 @@ static void __netpoll_cleanup(struct netpoll *np) RCU_INIT_POINTER(np->dev->npinfo, NULL); call_rcu(&npinfo->rcu, rcu_cleanup_netpoll_info); - } else - RCU_INIT_POINTER(np->dev->npinfo, NULL); + } skb_pool_flush(np); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8040ff7c356e..576d5ec3bb36 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4715,9 +4715,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, int err; u16 vid; - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - if (!del_bulk) { err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack); diff --git a/net/devlink/rate.c b/net/devlink/rate.c index 264fb82cba19..d157a8419bca 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -828,13 +828,15 @@ void devl_rate_nodes_destroy(struct devlink *devlink) if (!devlink_rate->parent) continue; - refcount_dec(&devlink_rate->parent->refcnt); if (devlink_rate_is_leaf(devlink_rate)) ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, NULL); else if (devlink_rate_is_node(devlink_rate)) ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, NULL); + + refcount_dec(&devlink_rate->parent->refcnt); + devlink_rate->parent = NULL; } list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) { if (devlink_rate_is_node(devlink_rate)) { diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 26bb657ceac3..eadb358179ce 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -176,7 +176,8 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_TAG_LEN); - dsa_default_offload_fwd_mark(skb); + if (likely(!is_link_local_ether_addr(eth_hdr(skb)->h_dest))) + dsa_default_offload_fwd_mark(skb); return skb; } @@ -224,12 +225,14 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, { int len = BRCM_LEG_TAG_LEN; int source_port; + __be16 *proto; u8 *brcm_tag; if (unlikely(!pskb_may_pull(skb, BRCM_LEG_TAG_LEN + VLAN_HLEN))) return NULL; brcm_tag = dsa_etype_header_pos_rx(skb); + proto = (__be16 *)(brcm_tag + BRCM_LEG_TAG_LEN); source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; @@ -237,14 +240,19 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, if (!skb->dev) return NULL; - /* VLAN tag is added by BCM63xx internal switch */ - if (netdev_uses_dsa(skb->dev)) + /* The internal switch in BCM63XX SoCs always tags on egress on the CPU + * port. We use VID 0 internally for untagged traffic, so strip the tag + * if the TCI field is all 0, and keep it otherwise to also retain + * e.g. 802.1p tagged packets. + */ + if (proto[0] == htons(ETH_P_8021Q) && proto[1] == 0) len += VLAN_HLEN; /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, len); - dsa_default_offload_fwd_mark(skb); + if (likely(!is_link_local_ether_addr(eth_hdr(skb)->h_dest))) + dsa_default_offload_fwd_mark(skb); dsa_strip_etype_header(skb, len); diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index 081093dfd553..8f9532a15f43 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -259,6 +259,7 @@ static int tls_handshake_accept(struct handshake_req *req, out_cancel: genlmsg_cancel(msg, hdr); + nlmsg_free(msg); out: return ret; } diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index fbbc3ccf9df6..492cbc78ab75 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -320,6 +320,9 @@ static void send_hsr_supervision_frame(struct hsr_port *port, } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); + skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); + skb_reset_mac_len(skb); + set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); @@ -334,7 +337,7 @@ static void send_hsr_supervision_frame(struct hsr_port *port, } hsr_stag->tlv.HSR_TLV_type = type; - /* TODO: Why 12 in HSRv0? */ + /* HSRv0 has 6 unused bytes after the MAC */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index c67c0d35921d..339f0d220212 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -262,15 +262,23 @@ static struct sk_buff *prp_fill_rct(struct sk_buff *skb, return skb; } -static void hsr_set_path_id(struct hsr_ethhdr *hsr_ethhdr, +static void hsr_set_path_id(struct hsr_frame_info *frame, + struct hsr_ethhdr *hsr_ethhdr, struct hsr_port *port) { int path_id; - if (port->type == HSR_PT_SLAVE_A) - path_id = 0; - else - path_id = 1; + if (port->hsr->prot_version) { + if (port->type == HSR_PT_SLAVE_A) + path_id = 0; + else + path_id = 1; + } else { + if (frame->is_supervision) + path_id = 0xf; + else + path_id = 1; + } set_hsr_tag_path(&hsr_ethhdr->hsr_tag, path_id); } @@ -304,7 +312,7 @@ static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, else hsr_ethhdr = (struct hsr_ethhdr *)pc; - hsr_set_path_id(hsr_ethhdr, port); + hsr_set_path_id(frame, hsr_ethhdr, port); set_hsr_tag_LSDU_size(&hsr_ethhdr->hsr_tag, lsdu_size); hsr_ethhdr->hsr_tag.sequence_nr = htons(frame->sequence_nr); hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; @@ -330,7 +338,7 @@ struct sk_buff *hsr_create_tagged_frame(struct hsr_frame_info *frame, (struct hsr_ethhdr *)skb_mac_header(frame->skb_hsr); /* set the lane id properly */ - hsr_set_path_id(hsr_ethhdr, port); + hsr_set_path_id(frame, hsr_ethhdr, port); return skb_clone(frame->skb_hsr, GFP_ATOMIC); } else if (port->dev->features & NETIF_F_HW_HSR_TAG_INS) { return skb_clone(frame->skb_std, GFP_ATOMIC); diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index b120470246cc..c96b63adf96f 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -34,12 +34,18 @@ static int hsr_newlink(struct net_device *dev, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); + struct net_device *link[2], *interlink = NULL; struct nlattr **data = params->data; enum hsr_version proto_version; unsigned char multicast_spec; u8 proto = HSR_PROTOCOL_HSR; - struct net_device *link[2], *interlink = NULL; + if (!net_eq(link_net, dev_net(dev))) { + NL_SET_ERR_MSG_MOD(extack, + "HSR slaves/interlink must be on the same net namespace than HSR link"); + return -EINVAL; + } + if (!data) { NL_SET_ERR_MSG_MOD(extack, "No slave devices specified"); return -EINVAL; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index e0d94270da28..05828d4cb6cd 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -122,8 +122,10 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __be16 type = x->inner_mode.family == AF_INET6 ? htons(ETH_P_IPV6) - : htons(ETH_P_IP); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, + XFRM_MODE_SKB_CB(skb)->protocol); + __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6) + : htons(ETH_P_IP); return skb_eth_gso_segment(skb, features, type); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6d27d3610c1c..b549d6a57307 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -607,6 +607,11 @@ static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) oldest_p = fnhe_p; } } + + /* Clear oldest->fnhe_daddr to prevent this fnhe from being + * rebound with new dsts in rt_bind_exception(). + */ + oldest->fnhe_daddr = 0; fnhe_flush_routes(oldest); *oldest_p = oldest->fnhe_next; kfree_rcu(oldest, rcu); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 31ea5af49f2d..e4a979b75cc6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -891,18 +891,27 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, } } -void tcp_rcvbuf_grow(struct sock *sk) +void tcp_rcvbuf_grow(struct sock *sk, u32 newval) { const struct net *net = sock_net(sk); struct tcp_sock *tp = tcp_sk(sk); - int rcvwin, rcvbuf, cap; + u32 rcvwin, rcvbuf, cap, oldval; + u64 grow; + + oldval = tp->rcvq_space.space; + tp->rcvq_space.space = newval; if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) return; + /* DRS is always one RTT late. */ + rcvwin = newval << 1; + /* slow start: allow the sender to double its rate. */ - rcvwin = tp->rcvq_space.space << 1; + grow = (u64)rcvwin * (newval - oldval); + do_div(grow, oldval); + rcvwin += grow << 1; if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt; @@ -943,9 +952,7 @@ void tcp_rcv_space_adjust(struct sock *sk) trace_tcp_rcvbuf_grow(sk, time); - tp->rcvq_space.space = copied; - - tcp_rcvbuf_grow(sk); + tcp_rcvbuf_grow(sk, copied); new_measure: tp->rcvq_space.seq = tp->copied_seq; @@ -5270,7 +5277,7 @@ end: } /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ if (sk->sk_socket) - tcp_rcvbuf_grow(sk); + tcp_rcvbuf_grow(sk, tp->rcvq_space.space); } static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 7b41fb4f00b5..22410243ebe8 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -158,8 +158,10 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __be16 type = x->inner_mode.family == AF_INET ? htons(ETH_P_IP) - : htons(ETH_P_IPV6); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, + XFRM_MODE_SKB_CB(skb)->protocol); + __be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP) + : htons(ETH_P_IPV6); return skb_eth_gso_segment(skb, features, type); } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 369a2f2e459c..0710281dd95a 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1246,9 +1246,9 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns else l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); - /* Reset skb netfilter state */ - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); + /* Reset control buffer */ + memset(skb->cb, 0, sizeof(skb->cb)); + nf_reset_ct(skb); /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index d9aca1c3c097..c52b0456039d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1876,6 +1876,9 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, link_conf->nontransmitted = false; link_conf->ema_ap = false; link_conf->bssid_indicator = 0; + link_conf->fils_discovery.min_interval = 0; + link_conf->fils_discovery.max_interval = 0; + link_conf->unsol_bcast_probe_resp_interval = 0; __sta_info_flush(sdata, true, link_id, NULL); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 57065714cf8c..7f8799fd673e 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1290,7 +1290,7 @@ ieee80211_link_chanctx_reservation_complete(struct ieee80211_link_data *link) &link->csa.finalize_work); break; case NL80211_IFTYPE_STATION: - wiphy_delayed_work_queue(sdata->local->hw.wiphy, + wiphy_hrtimer_work_queue(sdata->local->hw.wiphy, &link->u.mgd.csa.switch_work, 0); break; case NL80211_IFTYPE_UNSPECIFIED: diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 73fd86ec1bce..878c3b14aeb8 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -612,11 +612,11 @@ struct ieee80211_if_managed { u8 *assoc_req_ies; size_t assoc_req_ies_len; - struct wiphy_delayed_work ml_reconf_work; + struct wiphy_hrtimer_work ml_reconf_work; u16 removed_links; /* TID-to-link mapping support */ - struct wiphy_delayed_work ttlm_work; + struct wiphy_hrtimer_work ttlm_work; struct ieee80211_adv_ttlm_info ttlm_info; struct wiphy_work teardown_ttlm_work; @@ -1017,10 +1017,10 @@ struct ieee80211_link_data_managed { bool operating_11g_mode; struct { - struct wiphy_delayed_work switch_work; + struct wiphy_hrtimer_work switch_work; struct cfg80211_chan_def ap_chandef; struct ieee80211_parsed_tpe tpe; - unsigned long time; + ktime_t time; bool waiting_bcn; bool ignored_same_chan; bool blocked_tx; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index a7873832d4fa..0ca55b9655a7 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -223,6 +223,10 @@ static int ieee80211_can_powered_addr_change(struct ieee80211_sub_if_data *sdata if (netif_carrier_ok(sdata->dev)) return -EBUSY; + /* if any stations are set known (so they know this vif too), reject */ + if (sta_info_get_by_idx(sdata, 0)) + return -EBUSY; + /* First check no ROC work is happening on this iface */ list_for_each_entry(roc, &local->roc_list, list) { if (roc->sdata != sdata) @@ -242,12 +246,16 @@ static int ieee80211_can_powered_addr_change(struct ieee80211_sub_if_data *sdata ret = -EBUSY; } + /* + * More interface types could be added here but changing the + * address while powered makes the most sense in client modes. + */ switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - /* More interface types could be added here but changing the - * address while powered makes the most sense in client modes. - */ + /* refuse while connecting */ + if (sdata->u.mgd.auth_data || sdata->u.mgd.assoc_data) + return -EBUSY; break; default: ret = -EOPNOTSUPP; diff --git a/net/mac80211/key.c b/net/mac80211/key.c index b14e9cd9713f..d5da7ccea66e 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -508,11 +508,16 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, ret = ieee80211_key_enable_hw_accel(new); } } else { - if (!new->local->wowlan) + if (!new->local->wowlan) { ret = ieee80211_key_enable_hw_accel(new); - else if (link_id < 0 || !sdata->vif.active_links || - BIT(link_id) & sdata->vif.active_links) + } else if (link_id < 0 || !sdata->vif.active_links || + BIT(link_id) & sdata->vif.active_links) { new->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; + if (!(new->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | + IEEE80211_KEY_FLAG_PUT_MIC_SPACE | + IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) + decrease_tailroom_need_count(sdata, 1); + } } if (ret) diff --git a/net/mac80211/link.c b/net/mac80211/link.c index d71eabe5abf8..4a19b765ccb6 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -472,10 +472,10 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, * from there. */ if (link->conf->csa_active) - wiphy_delayed_work_queue(local->hw.wiphy, + wiphy_hrtimer_work_queue(local->hw.wiphy, &link->u.mgd.csa.switch_work, link->u.mgd.csa.time - - jiffies); + ktime_get_boottime()); } for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3b5827ea438e..f3138d158535 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -45,7 +45,7 @@ #define IEEE80211_ASSOC_TIMEOUT_SHORT (HZ / 10) #define IEEE80211_ASSOC_MAX_TRIES 3 -#define IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS msecs_to_jiffies(100) +#define IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS (100 * USEC_PER_MSEC) #define IEEE80211_ADV_TTLM_ST_UNDERFLOW 0xff00 #define IEEE80211_NEG_TTLM_REQ_TIMEOUT (HZ / 5) @@ -2594,7 +2594,7 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, return; } - wiphy_delayed_work_queue(sdata->local->hw.wiphy, + wiphy_hrtimer_work_queue(sdata->local->hw.wiphy, &link->u.mgd.csa.switch_work, 0); } @@ -2753,7 +2753,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, .timestamp = timestamp, .device_timestamp = device_timestamp, }; - unsigned long now; + u32 csa_time_tu; + ktime_t now; int res; lockdep_assert_wiphy(local->hw.wiphy); @@ -2983,10 +2984,9 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, csa_ie.mode); /* we may have to handle timeout for deactivated link in software */ - now = jiffies; - link->u.mgd.csa.time = now + - TU_TO_JIFFIES((max_t(int, csa_ie.count, 1) - 1) * - link->conf->beacon_int); + now = ktime_get_boottime(); + csa_time_tu = (max_t(int, csa_ie.count, 1) - 1) * link->conf->beacon_int; + link->u.mgd.csa.time = now + us_to_ktime(ieee80211_tu_to_usec(csa_time_tu)); if (ieee80211_vif_link_active(&sdata->vif, link->link_id) && local->ops->channel_switch) { @@ -3001,7 +3001,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, } /* channel switch handled in software */ - wiphy_delayed_work_queue(local->hw.wiphy, + wiphy_hrtimer_work_queue(local->hw.wiphy, &link->u.mgd.csa.switch_work, link->u.mgd.csa.time - now); return; @@ -4242,14 +4242,14 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, memset(&sdata->u.mgd.ttlm_info, 0, sizeof(sdata->u.mgd.ttlm_info)); - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); memset(&sdata->vif.neg_ttlm, 0, sizeof(sdata->vif.neg_ttlm)); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->neg_ttlm_timeout_work); sdata->u.mgd.removed_links = 0; - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.ml_reconf_work); wiphy_work_cancel(sdata->local->hw.wiphy, @@ -6876,7 +6876,7 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, /* In case the removal was cancelled, abort it */ if (sdata->u.mgd.removed_links) { sdata->u.mgd.removed_links = 0; - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.ml_reconf_work); } return; @@ -6906,9 +6906,9 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, } sdata->u.mgd.removed_links = removed_links; - wiphy_delayed_work_queue(sdata->local->hw.wiphy, + wiphy_hrtimer_work_queue(sdata->local->hw.wiphy, &sdata->u.mgd.ml_reconf_work, - TU_TO_JIFFIES(delay)); + us_to_ktime(ieee80211_tu_to_usec(delay))); } static int ieee80211_ttlm_set_links(struct ieee80211_sub_if_data *sdata, @@ -7095,7 +7095,7 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, /* if a planned TID-to-link mapping was cancelled - * abort it */ - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.ttlm_work); } else if (sdata->u.mgd.ttlm_info.active) { /* if no TID-to-link element, set to default mapping in @@ -7130,7 +7130,7 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, if (ttlm_info.switch_time) { u16 beacon_ts_tu, st_tu, delay; - u32 delay_jiffies; + u64 delay_usec; u64 mask; /* The t2l map switch time is indicated with a partial @@ -7152,23 +7152,23 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, if (delay > IEEE80211_ADV_TTLM_ST_UNDERFLOW) return; - delay_jiffies = TU_TO_JIFFIES(delay); + delay_usec = ieee80211_tu_to_usec(delay); /* Link switching can take time, so schedule it * 100ms before to be ready on time */ - if (delay_jiffies > IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS) - delay_jiffies -= + if (delay_usec > IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS) + delay_usec -= IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS; else - delay_jiffies = 0; + delay_usec = 0; sdata->u.mgd.ttlm_info = ttlm_info; - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.ttlm_work); - wiphy_delayed_work_queue(sdata->local->hw.wiphy, + wiphy_hrtimer_work_queue(sdata->local->hw.wiphy, &sdata->u.mgd.ttlm_work, - delay_jiffies); + us_to_ktime(delay_usec)); return; } } @@ -8793,7 +8793,7 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) ieee80211_csa_connection_drop_work); wiphy_delayed_work_init(&ifmgd->tdls_peer_del_work, ieee80211_tdls_peer_del_work); - wiphy_delayed_work_init(&ifmgd->ml_reconf_work, + wiphy_hrtimer_work_init(&ifmgd->ml_reconf_work, ieee80211_ml_reconf_work); wiphy_delayed_work_init(&ifmgd->reconf.wk, ieee80211_ml_sta_reconf_timeout); @@ -8802,7 +8802,7 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) timer_setup(&ifmgd->conn_mon_timer, ieee80211_sta_conn_mon_timer, 0); wiphy_delayed_work_init(&ifmgd->tx_tspec_wk, ieee80211_sta_handle_tspec_ac_params_wk); - wiphy_delayed_work_init(&ifmgd->ttlm_work, + wiphy_hrtimer_work_init(&ifmgd->ttlm_work, ieee80211_tid_to_link_map_work); wiphy_delayed_work_init(&ifmgd->neg_ttlm_timeout_work, ieee80211_neg_ttlm_timeout_work); @@ -8849,7 +8849,7 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link) else link->u.mgd.req_smps = IEEE80211_SMPS_OFF; - wiphy_delayed_work_init(&link->u.mgd.csa.switch_work, + wiphy_hrtimer_work_init(&link->u.mgd.csa.switch_work, ieee80211_csa_switch_work); ieee80211_clear_tpe(&link->conf->tpe); @@ -10064,7 +10064,7 @@ void ieee80211_mgd_stop_link(struct ieee80211_link_data *link) &link->u.mgd.request_smps_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, &link->u.mgd.recalc_smps); - wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy, + wiphy_hrtimer_work_cancel(link->sdata->local->hw.wiphy, &link->u.mgd.csa.switch_work); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6af43dfefdd6..5b4c3fe9970a 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -5360,10 +5360,14 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, if (WARN_ON(!local->started)) goto drop; - if (likely(!(status->flag & RX_FLAG_FAILED_PLCP_CRC))) { + if (likely(!(status->flag & RX_FLAG_FAILED_PLCP_CRC) && + !(status->flag & RX_FLAG_NO_PSDU && + status->zero_length_psdu_type == + IEEE80211_RADIOTAP_ZERO_LEN_PSDU_NOT_CAPTURED))) { /* - * Validate the rate, unless a PLCP error means that - * we probably can't have a valid rate here anyway. + * Validate the rate, unless there was a PLCP error which may + * have an invalid rate or the PSDU was not capture and may be + * missing rate information. */ switch (status->encoding) { diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 6003e47c770a..171643815076 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -85,6 +85,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("DssFallback", MPTCP_MIB_DSSFALLBACK), SNMP_MIB_ITEM("SimultConnectFallback", MPTCP_MIB_SIMULTCONNFALLBACK), SNMP_MIB_ITEM("FallbackFailed", MPTCP_MIB_FALLBACKFAILED), + SNMP_MIB_ITEM("WinProbe", MPTCP_MIB_WINPROBE), }; /* mptcp_mib_alloc - allocate percpu mib counters diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 309bac6fea32..a1d3e9369fbb 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -88,6 +88,7 @@ enum linux_mptcp_mib_field { MPTCP_MIB_DSSFALLBACK, /* Bad or missing DSS */ MPTCP_MIB_SIMULTCONNFALLBACK, /* Simultaneous connect */ MPTCP_MIB_FALLBACKFAILED, /* Can't fallback due to msk status */ + MPTCP_MIB_WINPROBE, /* MPTCP-level zero window probe */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1103b3341a70..f24ae7d40e88 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -838,8 +838,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, opts->suboptions = 0; + /* Force later mptcp_write_options(), but do not use any actual + * option space. + */ if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb))) - return false; + return true; if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) { if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) || @@ -1041,6 +1044,31 @@ static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una) WRITE_ONCE(msk->snd_una, new_snd_una); } +static void rwin_update(struct mptcp_sock *msk, struct sock *ssk, + struct sk_buff *skb) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct tcp_sock *tp = tcp_sk(ssk); + u64 mptcp_rcv_wnd; + + /* Avoid touching extra cachelines if TCP is going to accept this + * skb without filling the TCP-level window even with a possibly + * outdated mptcp-level rwin. + */ + if (!skb->len || skb->len < tcp_receive_window(tp)) + return; + + mptcp_rcv_wnd = atomic64_read(&msk->rcv_wnd_sent); + if (!after64(mptcp_rcv_wnd, subflow->rcv_wnd_sent)) + return; + + /* Some other subflow grew the mptcp-level rwin since rcv_wup, + * resync. + */ + tp->rcv_wnd += mptcp_rcv_wnd - subflow->rcv_wnd_sent; + subflow->rcv_wnd_sent = mptcp_rcv_wnd; +} + static void ack_update_msk(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_options_received *mp_opt) @@ -1208,6 +1236,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) */ if (mp_opt.use_ack) ack_update_msk(msk, sk, &mp_opt); + rwin_update(msk, sk, skb); /* Zero-data-length packets are dropped by the caller and not * propagated to the MPTCP layer, so the skb extension does not @@ -1294,6 +1323,10 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) if (rcv_wnd_new != rcv_wnd_old) { raise_win: + /* The msk-level rcv wnd is after the tcp level one, + * sync the latter. + */ + rcv_wnd_new = rcv_wnd_old; win = rcv_wnd_old - ack_seq; tp->rcv_wnd = min_t(u64, win, U32_MAX); new_win = tp->rcv_wnd; @@ -1317,6 +1350,21 @@ raise_win: update_wspace: WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); + subflow->rcv_wnd_sent = rcv_wnd_new; +} + +static void mptcp_track_rwin(struct tcp_sock *tp) +{ + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk; + + if (!ssk) + return; + + subflow = mptcp_subflow_ctx(ssk); + msk = mptcp_sk(subflow->conn); + WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); } __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) @@ -1611,6 +1659,10 @@ mp_rst: opts->reset_transient, opts->reset_reason); return; + } else if (unlikely(!opts->suboptions)) { + /* Fallback to TCP */ + mptcp_track_rwin(tp); + return; } if (OPTION_MPTCP_PRIO & opts->suboptions) { diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 2ff1b9499568..9604b91902b8 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -18,6 +18,7 @@ struct mptcp_pm_add_entry { u8 retrans_times; struct timer_list add_timer; struct mptcp_sock *sock; + struct rcu_head rcu; }; static DEFINE_SPINLOCK(mptcp_pm_list_lock); @@ -155,7 +156,7 @@ bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, entry = mptcp_pm_del_add_timer(msk, addr, false); ret = entry; - kfree(entry); + kfree_rcu(entry, rcu); return ret; } @@ -345,22 +346,27 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; - struct timer_list *add_timer = NULL; + bool stop_timer = false; + + rcu_read_lock(); spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (entry && (!check_id || entry->addr.id == addr->id)) { entry->retrans_times = ADD_ADDR_RETRANS_MAX; - add_timer = &entry->add_timer; + stop_timer = true; } if (!check_id && entry) list_del(&entry->list); spin_unlock_bh(&msk->pm.lock); - /* no lock, because sk_stop_timer_sync() is calling timer_delete_sync() */ - if (add_timer) - sk_stop_timer_sync(sk, add_timer); + /* Note: entry might have been removed by another thread. + * We hold rcu_read_lock() to ensure it is not freed under us. + */ + if (stop_timer) + sk_stop_timer_sync(sk, &entry->add_timer); + rcu_read_unlock(); return entry; } @@ -415,7 +421,7 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk) list_for_each_entry_safe(entry, tmp, &free_list, list) { sk_stop_timer_sync(sk, &entry->add_timer); - kfree(entry); + kfree_rcu(entry, rcu); } } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index e0f44dc232aa..0a50fd5edc06 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -370,6 +370,10 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) } subflow: + /* No need to try establishing subflows to remote id0 if not allowed */ + if (mptcp_pm_add_addr_c_flag_case(msk)) + goto exit; + /* check if should create a new subflow */ while (msk->pm.local_addr_used < endp_subflow_max && msk->pm.extra_subflows < limit_extra_subflows) { @@ -401,6 +405,8 @@ subflow: __mptcp_subflow_connect(sk, &local, &addrs[i]); spin_lock_bh(&msk->pm.lock); } + +exit: mptcp_pm_nl_check_work_pending(msk); } @@ -666,7 +672,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id) { - if (rm_id && WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + if (rm_id && !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { u8 limit_add_addr_accepted = mptcp_pm_get_limit_add_addr_accepted(msk); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 0292162a14ee..33b5dce431c2 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -61,11 +61,13 @@ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk) { + unsigned short family = READ_ONCE(sk->sk_family); + #if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (sk->sk_prot == &tcpv6_prot) + if (family == AF_INET6) return &inet6_stream_ops; #endif - WARN_ON_ONCE(sk->sk_prot != &tcp_prot); + WARN_ON_ONCE(family != AF_INET); return &inet_stream_ops; } @@ -76,6 +78,13 @@ bool __mptcp_try_fallback(struct mptcp_sock *msk, int fb_mib) if (__mptcp_check_fallback(msk)) return true; + /* The caller possibly is not holding the msk socket lock, but + * in the fallback case only the current subflow is touching + * the OoO queue. + */ + if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) + return false; + spin_lock_bh(&msk->fallback_lock); if (!msk->allow_infinite_fallback) { spin_unlock_bh(&msk->fallback_lock); @@ -194,17 +203,26 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, * - mptcp does not maintain a msk-level window clamp * - returns true when the receive buffer is actually updated */ -static bool mptcp_rcvbuf_grow(struct sock *sk) +static bool mptcp_rcvbuf_grow(struct sock *sk, u32 newval) { struct mptcp_sock *msk = mptcp_sk(sk); const struct net *net = sock_net(sk); - int rcvwin, rcvbuf, cap; + u32 rcvwin, rcvbuf, cap, oldval; + u64 grow; + oldval = msk->rcvq_space.space; + msk->rcvq_space.space = newval; if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) return false; - rcvwin = msk->rcvq_space.space << 1; + /* DRS is always one RTT late. */ + rcvwin = newval << 1; + + /* slow start: allow the sender to double its rate. */ + grow = (u64)rcvwin * (newval - oldval); + do_div(grow, oldval); + rcvwin += grow << 1; if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq; @@ -334,7 +352,7 @@ end: skb_set_owner_r(skb, sk); /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ if (sk->sk_socket) - mptcp_rcvbuf_grow(sk); + mptcp_rcvbuf_grow(sk, msk->rcvq_space.space); } static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset, @@ -926,14 +944,19 @@ static void mptcp_reset_rtx_timer(struct sock *sk) bool mptcp_schedule_work(struct sock *sk) { - if (inet_sk_state_load(sk) != TCP_CLOSE && - schedule_work(&mptcp_sk(sk)->work)) { - /* each subflow already holds a reference to the sk, and the - * workqueue is invoked by a subflow, so sk can't go away here. - */ - sock_hold(sk); + if (inet_sk_state_load(sk) == TCP_CLOSE) + return false; + + /* Get a reference on this socket, mptcp_worker() will release it. + * As mptcp_worker() might complete before us, we can not avoid + * a sock_hold()/sock_put() if schedule_work() returns false. + */ + sock_hold(sk); + + if (schedule_work(&mptcp_sk(sk)->work)) return true; - } + + sock_put(sk); return false; } @@ -998,7 +1021,7 @@ static void __mptcp_clean_una(struct sock *sk) if (WARN_ON_ONCE(!msk->recovery)) break; - WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); + msk->first_pending = mptcp_send_next(sk); } dfrag_clear(sk, dfrag); @@ -1290,7 +1313,12 @@ alloc_skb: if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); - if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { + /* No need for zero probe if there are any data pending + * either at the msk or ssk level; skb is the current write + * queue tail and can be empty at this point. + */ + if (snd_una != msk->snd_nxt || skb->len || + skb != tcp_send_head(ssk)) { tcp_remove_empty_skb(ssk); return 0; } @@ -1341,6 +1369,7 @@ alloc_skb: mpext->dsn64); if (zero_window_probe) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_WINPROBE); mptcp_subflow_ctx(ssk)->rel_write_seq += copy; mpext->frozen = 1; if (READ_ONCE(msk->csum_enabled)) @@ -1543,7 +1572,7 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk, mptcp_update_post_push(msk, dfrag, ret); } - WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); + msk->first_pending = mptcp_send_next(sk); if (msk->snd_burst <= 0 || !sk_stream_memory_free(ssk) || @@ -1903,7 +1932,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) get_page(dfrag->page); list_add_tail(&dfrag->list, &msk->rtx_queue); if (!msk->first_pending) - WRITE_ONCE(msk->first_pending, dfrag); + msk->first_pending = dfrag; } pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk, dfrag->data_seq, dfrag->data_len, dfrag->already_sent, @@ -1936,22 +1965,36 @@ do_error: static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); -static int __mptcp_recvmsg_mskq(struct sock *sk, - struct msghdr *msg, - size_t len, int flags, +static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, + size_t len, int flags, int copied_total, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb, *tmp; + int total_data_len = 0; int copied = 0; skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) { - u32 offset = MPTCP_SKB_CB(skb)->offset; + u32 delta, offset = MPTCP_SKB_CB(skb)->offset; u32 data_len = skb->len - offset; - u32 count = min_t(size_t, len - copied, data_len); + u32 count; int err; + if (flags & MSG_PEEK) { + /* skip already peeked skbs */ + if (total_data_len + data_len <= copied_total) { + total_data_len += data_len; + continue; + } + + /* skip the already peeked data in the current skb */ + delta = copied_total - total_data_len; + offset += delta; + data_len -= delta; + } + + count = min_t(size_t, len - copied, data_len); if (!(flags & MSG_TRUNC)) { err = skb_copy_datagram_msg(skb, offset, msg, count); if (unlikely(err < 0)) { @@ -1968,16 +2011,14 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, copied += count; - if (count < data_len) { - if (!(flags & MSG_PEEK)) { + if (!(flags & MSG_PEEK)) { + msk->bytes_consumed += count; + if (count < data_len) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; - msk->bytes_consumed += count; + break; } - break; - } - if (!(flags & MSG_PEEK)) { /* avoid the indirect call, we know the destructor is sock_rfree */ skb->destructor = NULL; skb->sk = NULL; @@ -1985,7 +2026,6 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, sk_mem_uncharge(sk, skb->truesize); __skb_unlink(skb, &sk->sk_receive_queue); skb_attempt_defer_free(skb); - msk->bytes_consumed += count; } if (copied >= len) @@ -2049,9 +2089,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (msk->rcvq_space.copied <= msk->rcvq_space.space) goto new_measure; - msk->rcvq_space.space = msk->rcvq_space.copied; - if (mptcp_rcvbuf_grow(sk)) { - + if (mptcp_rcvbuf_grow(sk, msk->rcvq_space.copied)) { /* Make subflows follow along. If we do not do this, we * get drops at subflow level if skbs can't be moved to * the mptcp rx queue fast enough (announced rcv_win can @@ -2063,8 +2101,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); - tcp_sk(ssk)->rcvq_space.space = msk->rcvq_space.copied; - tcp_rcvbuf_grow(ssk); + /* subflows can be added before tcp_init_transfer() */ + if (tcp_sk(ssk)->rcvq_space.space) + tcp_rcvbuf_grow(ssk, msk->rcvq_space.copied); unlock_sock_fast(ssk, slow); } } @@ -2183,7 +2222,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, while (copied < len) { int err, bytes_read; - bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, &tss, &cmsg_flags); + bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, + copied, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; @@ -2371,7 +2411,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) /* flags for __mptcp_close_ssk() */ #define MPTCP_CF_PUSH BIT(1) -#define MPTCP_CF_FASTCLOSE BIT(2) /* be sure to send a reset only if the caller asked for it, also * clean completely the subflow status when the subflow reaches @@ -2382,7 +2421,7 @@ static void __mptcp_subflow_disconnect(struct sock *ssk, unsigned int flags) { if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - (flags & MPTCP_CF_FASTCLOSE)) { + subflow->send_fastclose) { /* The MPTCP code never wait on the subflow sockets, TCP-level * disconnect should never fail */ @@ -2429,14 +2468,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { - /* be sure to force the tcp_close path - * to generate the egress reset - */ - ssk->sk_lingertime = 0; - sock_set_flag(ssk, SOCK_LINGER); - subflow->send_fastclose = 1; - } + if (subflow->send_fastclose && ssk->sk_state != TCP_CLOSE) + tcp_set_state(ssk, TCP_CLOSE); need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { @@ -2532,7 +2565,8 @@ static void __mptcp_close_subflow(struct sock *sk) if (ssk_state != TCP_CLOSE && (ssk_state != TCP_CLOSE_WAIT || - inet_sk_state_load(sk) != TCP_ESTABLISHED)) + inet_sk_state_load(sk) != TCP_ESTABLISHED || + __mptcp_check_fallback(msk))) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ @@ -2740,9 +2774,26 @@ static void mptcp_do_fastclose(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); mptcp_set_state(sk, TCP_CLOSE); - mptcp_for_each_subflow_safe(msk, subflow, tmp) - __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), - subflow, MPTCP_CF_FASTCLOSE); + + /* Explicitly send the fastclose reset as need */ + if (__mptcp_check_fallback(msk)) + return; + + mptcp_for_each_subflow_safe(msk, subflow, tmp) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + lock_sock(ssk); + + /* Some subflow socket states don't allow/need a reset.*/ + if ((1 << ssk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + goto unlock; + + subflow->send_fastclose = 1; + tcp_send_active_reset(ssk, ssk->sk_allocation, + SK_RST_REASON_TCP_ABORT_ON_CLOSE); +unlock: + release_sock(ssk); + } } static void mptcp_worker(struct work_struct *work) @@ -2769,7 +2820,11 @@ static void mptcp_worker(struct work_struct *work) __mptcp_close_subflow(sk); if (mptcp_close_tout_expired(sk)) { + struct mptcp_subflow_context *subflow, *tmp; + mptcp_do_fastclose(sk); + mptcp_for_each_subflow_safe(msk, subflow, tmp) + __mptcp_close_ssk(sk, subflow->tcp_sock, subflow, 0); mptcp_close_wake_up(sk); } @@ -2874,7 +2929,7 @@ static void __mptcp_clear_xmit(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; - WRITE_ONCE(msk->first_pending, NULL); + msk->first_pending = NULL; list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); } @@ -3194,7 +3249,8 @@ static int mptcp_disconnect(struct sock *sk, int flags) /* msk->subflow is still intact, the following will not free the first * subflow */ - mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); + mptcp_do_fastclose(sk); + mptcp_destroy_common(msk); /* The first subflow is already in TCP_CLOSE status, the following * can't overlap with a fallback anymore @@ -3373,7 +3429,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; } -void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) +void mptcp_destroy_common(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; @@ -3382,7 +3438,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) /* join list will be eventually flushed (with rst) at sock lock release time */ mptcp_for_each_subflow_safe(msk, subflow, tmp) - __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags); + __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, 0); __skb_queue_purge(&sk->sk_receive_queue); skb_rbtree_purge(&msk->out_of_order_queue); @@ -3400,7 +3456,7 @@ static void mptcp_destroy(struct sock *sk) /* allow the following to close even the initial subflow */ msk->free_first = 1; - mptcp_destroy_common(msk, 0); + mptcp_destroy_common(msk); sk_sockets_allocated_dec(sk); } @@ -3414,9 +3470,6 @@ void __mptcp_data_acked(struct sock *sk) void __mptcp_check_push(struct sock *sk, struct sock *ssk) { - if (!mptcp_send_head(sk)) - return; - if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, false); else diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 52f9cfa4ce95..6ca97096607c 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -414,7 +414,7 @@ static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk) { const struct mptcp_sock *msk = mptcp_sk(sk); - return READ_ONCE(msk->first_pending); + return msk->first_pending; } static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk) @@ -509,6 +509,7 @@ struct mptcp_subflow_context { u64 remote_key; u64 idsn; u64 map_seq; + u64 rcv_wnd_sent; u32 snd_isn; u32 token; u32 rel_write_seq; @@ -976,7 +977,7 @@ static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) local_bh_enable(); } -void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags); +void mptcp_destroy_common(struct mptcp_sock *msk); #define MPTCP_TOKEN_MAX_RETRIES 4 diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e8325890a322..af707ce0f624 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -2144,6 +2144,10 @@ void __init mptcp_subflow_init(void) tcp_prot_override = tcp_prot; tcp_prot_override.release_cb = tcp_release_cb_override; tcp_prot_override.diag_destroy = tcp_abort_override; +#ifdef CONFIG_BPF_SYSCALL + /* Disable sockmap processing for subflows */ + tcp_prot_override.psock_update_sk_prot = NULL; +#endif #if IS_ENABLED(CONFIG_MPTCP_IPV6) /* In struct mptcp_subflow_request_sock, we assume the TCP request sock @@ -2180,6 +2184,10 @@ void __init mptcp_subflow_init(void) tcpv6_prot_override = tcpv6_prot; tcpv6_prot_override.release_cb = tcp_release_cb_override; tcpv6_prot_override.diag_destroy = tcp_abort_override; +#ifdef CONFIG_BPF_SYSCALL + /* Disable sockmap processing for subflows */ + tcpv6_prot_override.psock_update_sk_prot = NULL; +#endif #endif mptcp_diag_subflow_init(&subflow_ulp_ops); diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 92b984fa8175..fc35a11cdca2 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -48,7 +48,7 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, return; } - count = priv->list->count; + count = READ_ONCE(priv->list->count); if ((count > priv->limit) ^ priv->invert) { regs->verdict.code = NFT_BREAK; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index d526e69a2a2b..6f2ae7cad731 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -22,6 +22,7 @@ #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_conntrack_seqadj.h> struct nft_ct_helper_obj { struct nf_conntrack_helper *helper4; @@ -379,6 +380,14 @@ static bool nft_ct_tmpl_alloc_pcpu(void) } #endif +static void __nft_ct_get_destroy(const struct nft_ctx *ctx, struct nft_ct *priv) +{ +#ifdef CONFIG_NF_CONNTRACK_LABELS + if (priv->key == NFT_CT_LABELS) + nf_connlabels_put(ctx->net); +#endif +} + static int nft_ct_get_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -413,6 +422,10 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_DIRECTION] != NULL) return -EINVAL; len = NF_CT_LABELS_MAX_SIZE; + + err = nf_connlabels_get(ctx->net, (len * BITS_PER_BYTE) - 1); + if (err) + return err; break; #endif case NFT_CT_HELPER: @@ -494,7 +507,8 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, case IP_CT_DIR_REPLY: break; default: - return -EINVAL; + err = -EINVAL; + goto err; } } @@ -502,11 +516,11 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, err = nft_parse_register_store(ctx, tb[NFTA_CT_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); if (err < 0) - return err; + goto err; err = nf_ct_netns_get(ctx->net, ctx->family); if (err < 0) - return err; + goto err; if (priv->key == NFT_CT_BYTES || priv->key == NFT_CT_PKTS || @@ -514,6 +528,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, nf_ct_set_acct(ctx->net, true); return 0; +err: + __nft_ct_get_destroy(ctx, priv); + return err; } static void __nft_ct_set_destroy(const struct nft_ctx *ctx, struct nft_ct *priv) @@ -626,6 +643,9 @@ err1: static void nft_ct_get_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { + struct nft_ct *priv = nft_expr_priv(expr); + + __nft_ct_get_destroy(ctx, priv); nf_ct_netns_put(ctx->net, ctx->family); } @@ -1173,6 +1193,10 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj, if (help) { rcu_assign_pointer(help->helper, to_assign); set_bit(IPS_HELPER_BIT, &ct->status); + + if ((ct->status & IPS_NAT_MASK) && !nfct_seqadj(ct)) + if (!nfct_seqadj_ext_add(ct)) + regs->verdict.code = NF_DROP; } } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2832e0794197..792ca44a461d 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -572,69 +572,6 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, - const struct nlattr *a) -{ - struct nshhdr *nh; - size_t length; - int err; - u8 flags; - u8 ttl; - int i; - - struct ovs_key_nsh key; - struct ovs_key_nsh mask; - - err = nsh_key_from_nlattr(a, &key, &mask); - if (err) - return err; - - /* Make sure the NSH base header is there */ - if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN)) - return -ENOMEM; - - nh = nsh_hdr(skb); - length = nsh_hdr_len(nh); - - /* Make sure the whole NSH header is there */ - err = skb_ensure_writable(skb, skb_network_offset(skb) + - length); - if (unlikely(err)) - return err; - - nh = nsh_hdr(skb); - skb_postpull_rcsum(skb, nh, length); - flags = nsh_get_flags(nh); - flags = OVS_MASKED(flags, key.base.flags, mask.base.flags); - flow_key->nsh.base.flags = flags; - ttl = nsh_get_ttl(nh); - ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl); - flow_key->nsh.base.ttl = ttl; - nsh_set_flags_and_ttl(nh, flags, ttl); - nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr, - mask.base.path_hdr); - flow_key->nsh.base.path_hdr = nh->path_hdr; - switch (nh->mdtype) { - case NSH_M_TYPE1: - for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) { - nh->md1.context[i] = - OVS_MASKED(nh->md1.context[i], key.context[i], - mask.context[i]); - } - memcpy(flow_key->nsh.context, nh->md1.context, - sizeof(nh->md1.context)); - break; - case NSH_M_TYPE2: - memset(flow_key->nsh.context, 0, - sizeof(flow_key->nsh.context)); - break; - default: - return -EINVAL; - } - skb_postpush_rcsum(skb, nh, length); - return 0; -} - /* Must follow skb_ensure_writable() since that can move the skb data. */ static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) @@ -1130,10 +1067,6 @@ static int execute_masked_set_action(struct sk_buff *skb, get_mask(a, struct ovs_key_ethernet *)); break; - case OVS_KEY_ATTR_NSH: - err = set_nsh(skb, flow_key, a); - break; - case OVS_KEY_ATTR_IPV4: err = set_ipv4(skb, flow_key, nla_data(a), get_mask(a, struct ovs_key_ipv4 *)); @@ -1170,6 +1103,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_LABELS: case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4: case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6: + case OVS_KEY_ATTR_NSH: err = -EINVAL; break; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ad64bb9ab5e2..1cb4f97335d8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1305,6 +1305,11 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, return 0; } +/* + * Constructs NSH header 'nh' from attributes of OVS_ACTION_ATTR_PUSH_NSH, + * where 'nh' points to a memory block of 'size' bytes. It's assumed that + * attributes were previously validated with validate_push_nsh(). + */ int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size) { @@ -1314,8 +1319,6 @@ int nsh_hdr_from_nlattr(const struct nlattr *attr, u8 ttl = 0; int mdlen = 0; - /* validate_nsh has check this, so we needn't do duplicate check here - */ if (size < NSH_BASE_HDR_LEN) return -ENOBUFS; @@ -1359,46 +1362,6 @@ int nsh_hdr_from_nlattr(const struct nlattr *attr, return 0; } -int nsh_key_from_nlattr(const struct nlattr *attr, - struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask) -{ - struct nlattr *a; - int rem; - - /* validate_nsh has check this, so we needn't do duplicate check here - */ - nla_for_each_nested(a, attr, rem) { - int type = nla_type(a); - - switch (type) { - case OVS_NSH_KEY_ATTR_BASE: { - const struct ovs_nsh_key_base *base = nla_data(a); - const struct ovs_nsh_key_base *base_mask = base + 1; - - nsh->base = *base; - nsh_mask->base = *base_mask; - break; - } - case OVS_NSH_KEY_ATTR_MD1: { - const struct ovs_nsh_key_md1 *md1 = nla_data(a); - const struct ovs_nsh_key_md1 *md1_mask = md1 + 1; - - memcpy(nsh->context, md1->context, sizeof(*md1)); - memcpy(nsh_mask->context, md1_mask->context, - sizeof(*md1_mask)); - break; - } - case OVS_NSH_KEY_ATTR_MD2: - /* Not supported yet */ - return -ENOTSUPP; - default: - return -EINVAL; - } - } - - return 0; -} - static int nsh_key_put_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool is_push_nsh, bool log) @@ -2839,17 +2802,13 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } -static bool validate_nsh(const struct nlattr *attr, bool is_mask, - bool is_push_nsh, bool log) +static bool validate_push_nsh(const struct nlattr *attr, bool log) { struct sw_flow_match match; struct sw_flow_key key; - int ret = 0; ovs_match_init(&match, &key, true, NULL); - ret = nsh_key_put_from_nlattr(attr, &match, is_mask, - is_push_nsh, log); - return !ret; + return !nsh_key_put_from_nlattr(attr, &match, false, true, log); } /* Return false if there are any non-masked bits set. @@ -2997,13 +2956,6 @@ static int validate_set(const struct nlattr *a, break; - case OVS_KEY_ATTR_NSH: - if (eth_type != htons(ETH_P_NSH)) - return -EINVAL; - if (!validate_nsh(nla_data(a), masked, false, log)) - return -EINVAL; - break; - default: return -EINVAL; } @@ -3437,7 +3389,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; } mac_proto = MAC_PROTO_NONE; - if (!validate_nsh(nla_data(a), false, true, true)) + if (!validate_push_nsh(nla_data(a), log)) return -EINVAL; break; diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index fe7f77fc5f18..ff8cdecbe346 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -65,8 +65,6 @@ int ovs_nla_put_actions(const struct nlattr *attr, void ovs_nla_free_flow_actions(struct sw_flow_actions *); void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); -int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh, - struct ovs_key_nsh *nsh_mask); int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size); diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 396b576390d0..c2b5bc19e091 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -47,12 +47,10 @@ TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb, filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); - bpf_compute_data_pointers(skb); - filter_res = bpf_prog_run(filter, skb); + filter_res = bpf_prog_run_data_pointers(filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_pointers(skb); - filter_res = bpf_prog_run(filter, skb); + filter_res = bpf_prog_run_data_pointers(filter, skb); } if (unlikely(!skb->tstamp && skb->tstamp_type)) skb->tstamp_type = SKB_CLOCK_REALTIME; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 3e89927d7116..26ba8c2d20ab 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -195,13 +195,15 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, const struct tcf_connmark_info *ci = to_connmark(a); unsigned char *b = skb_tail_pointer(skb); const struct tcf_connmark_parms *parms; - struct tc_connmark opt = { - .index = ci->tcf_index, - .refcnt = refcount_read(&ci->tcf_refcnt) - ref, - .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, - }; + struct tc_connmark opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + + opt.index = ci->tcf_index; + opt.refcnt = refcount_read(&ci->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind; + rcu_read_lock(); parms = rcu_dereference(ci->parms); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 107c6d83dc5c..7c6975632fc2 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -644,13 +644,15 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; - struct tc_ife opt = { - .index = ife->tcf_index, - .refcnt = refcount_read(&ife->tcf_refcnt) - ref, - .bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, - }; + struct tc_ife opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + + opt.index = ife->tcf_index, + opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref, + opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, + spin_lock_bh(&ife->tcf_lock); opt.action = ife->tcf_action; p = rcu_dereference_protected(ife->params, diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 7fbe42f0e5c2..a32754a2658b 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -97,12 +97,10 @@ TC_INDIRECT_SCOPE int cls_bpf_classify(struct sk_buff *skb, } else if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); - bpf_compute_data_pointers(skb); - filter_res = bpf_prog_run(prog->filter, skb); + filter_res = bpf_prog_run_data_pointers(prog->filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_pointers(skb); - filter_res = bpf_prog_run(prog->filter, skb); + filter_res = bpf_prog_run_data_pointers(prog->filter, skb); } if (unlikely(!skb->tstamp && skb->tstamp_type)) skb->tstamp_type = SKB_CLOCK_REALTIME; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1e058b46d3e1..f56b18c8aebf 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1599,6 +1599,11 @@ static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } + if (p->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot add children to ingress/clsact qdisc"); + return -EOPNOTSUPP; + } q = qdisc_leaf(p, clid, extack); if (IS_ERR(q)) return PTR_ERR(q); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 1e008a228ebd..7dee9748a56b 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -180,9 +180,10 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) static void try_bulk_dequeue_skb(struct Qdisc *q, struct sk_buff *skb, const struct netdev_queue *txq, - int *packets) + int *packets, int budget) { int bytelimit = qdisc_avail_bulklimit(txq) - skb->len; + int cnt = 0; while (bytelimit > 0) { struct sk_buff *nskb = q->dequeue(q); @@ -193,8 +194,10 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, bytelimit -= nskb->len; /* covers GSO len */ skb->next = nskb; skb = nskb; - (*packets)++; /* GSO counts as one pkt */ + if (++cnt >= budget) + break; } + (*packets) += cnt; skb_mark_not_on_list(skb); } @@ -228,7 +231,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, * A requeued skb (via q->gso_skb) can also be a SKB list. */ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, - int *packets) + int *packets, int budget) { const struct netdev_queue *txq = q->dev_queue; struct sk_buff *skb = NULL; @@ -295,7 +298,7 @@ validate: if (skb) { bulk: if (qdisc_may_bulk(q)) - try_bulk_dequeue_skb(q, skb, txq, packets); + try_bulk_dequeue_skb(q, skb, txq, packets, budget); else try_bulk_dequeue_skb_slow(q, skb, packets); } @@ -387,7 +390,7 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, * >0 - queue is not empty. * */ -static inline bool qdisc_restart(struct Qdisc *q, int *packets) +static inline bool qdisc_restart(struct Qdisc *q, int *packets, int budget) { spinlock_t *root_lock = NULL; struct netdev_queue *txq; @@ -396,7 +399,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) bool validate; /* Dequeue packet */ - skb = dequeue_skb(q, &validate, packets); + skb = dequeue_skb(q, &validate, packets, budget); if (unlikely(!skb)) return false; @@ -414,7 +417,7 @@ void __qdisc_run(struct Qdisc *q) int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; - while (qdisc_restart(q, &packets)) { + while (qdisc_restart(q, &packets, quota)) { quota -= packets; if (quota <= 0) { if (q->flags & TCQ_F_NOLOCK) diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 996c2018f0e6..2afb376299fe 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -73,19 +73,26 @@ static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb, struct nlattr *attr; void *info = NULL; + rcu_read_lock(); list_for_each_entry_rcu(laddr, address_list, list) addrcnt++; + rcu_read_unlock(); attr = nla_reserve(skb, INET_DIAG_LOCALS, addrlen * addrcnt); if (!attr) return -EMSGSIZE; info = nla_data(attr); + rcu_read_lock(); list_for_each_entry_rcu(laddr, address_list, list) { memcpy(info, &laddr->a, sizeof(laddr->a)); memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a)); info += addrlen; + + if (!--addrcnt) + break; } + rcu_read_unlock(); return 0; } @@ -223,14 +230,15 @@ struct sctp_comm_param { bool net_admin; }; -static size_t inet_assoc_attr_size(struct sctp_association *asoc) +static size_t inet_assoc_attr_size(struct sock *sk, + struct sctp_association *asoc) { int addrlen = sizeof(struct sockaddr_storage); int addrcnt = 0; struct sctp_sockaddr_entry *laddr; list_for_each_entry_rcu(laddr, &asoc->base.bind_addr.address_list, - list) + list, lockdep_sock_is_held(sk)) addrcnt++; return nla_total_size(sizeof(struct sctp_info)) @@ -256,11 +264,14 @@ static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *t if (err) return err; - rep = nlmsg_new(inet_assoc_attr_size(assoc), GFP_KERNEL); - if (!rep) + lock_sock(sk); + + rep = nlmsg_new(inet_assoc_attr_size(sk, assoc), GFP_KERNEL); + if (!rep) { + release_sock(sk); return -ENOMEM; + } - lock_sock(sk); if (ep != assoc->ep) { err = -EAGAIN; goto out; diff --git a/net/sctp/input.c b/net/sctp/input.c index 7e99894778d4..e119e460ccde 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -190,7 +190,7 @@ int sctp_rcv(struct sk_buff *skb) goto discard_release; nf_reset_ct(skb); - if (sk_filter(sk, skb)) + if (sk_filter(sk, skb) || skb->len < sizeof(struct sctp_chunkhdr)) goto discard_release; /* Create an SCTP packet structure. */ diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 5c1652181805..f5a7d5a38755 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -169,13 +169,14 @@ next_chunk: chunk->head_skb = chunk->skb; /* skbs with "cover letter" */ - if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) + if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) { + if (WARN_ON(!skb_shinfo(chunk->skb)->frag_list)) { + __SCTP_INC_STATS(dev_net(chunk->skb->dev), + SCTP_MIB_IN_PKT_DISCARDS); + sctp_chunk_free(chunk); + goto next_chunk; + } chunk->skb = skb_shinfo(chunk->skb)->frag_list; - - if (WARN_ON(!chunk->skb)) { - __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); - sctp_chunk_free(chunk); - goto next_chunk; } } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 4d258a6e8033..0c56d9673cc1 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -37,10 +37,10 @@ /* 1st Level Abstractions. */ /* Initialize a new transport from provided memory. */ -static struct sctp_transport *sctp_transport_init(struct net *net, - struct sctp_transport *peer, - const union sctp_addr *addr, - gfp_t gfp) +static void sctp_transport_init(struct net *net, + struct sctp_transport *peer, + const union sctp_addr *addr, + gfp_t gfp) { /* Copy in the address. */ peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); @@ -83,8 +83,6 @@ static struct sctp_transport *sctp_transport_init(struct net *net, get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); refcount_set(&peer->refcnt, 1); - - return peer; } /* Allocate and initialize a new transport. */ @@ -96,20 +94,13 @@ struct sctp_transport *sctp_transport_new(struct net *net, transport = kzalloc(sizeof(*transport), gfp); if (!transport) - goto fail; + return NULL; - if (!sctp_transport_init(net, transport, addr, gfp)) - goto fail_init; + sctp_transport_init(net, transport, addr, gfp); SCTP_DBG_OBJCNT_INC(transport); return transport; - -fail_init: - kfree(transport); - -fail: - return NULL; } /* This transport is no longer needed. Free up if possible, or @@ -495,6 +486,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) if (tp->rttvar || tp->srtt) { struct net *net = tp->asoc->base.net; + unsigned int rto_beta, rto_alpha; /* 6.3.1 C3) When a new RTT measurement R' is made, set * RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'| * SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R' @@ -506,10 +498,14 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) * For example, assuming the default value of RTO.Alpha of * 1/8, rto_alpha would be expressed as 3. */ - tp->rttvar = tp->rttvar - (tp->rttvar >> net->sctp.rto_beta) - + (((__u32)abs((__s64)tp->srtt - (__s64)rtt)) >> net->sctp.rto_beta); - tp->srtt = tp->srtt - (tp->srtt >> net->sctp.rto_alpha) - + (rtt >> net->sctp.rto_alpha); + rto_beta = READ_ONCE(net->sctp.rto_beta); + if (rto_beta < 32) + tp->rttvar = tp->rttvar - (tp->rttvar >> rto_beta) + + (((__u32)abs((__s64)tp->srtt - (__s64)rtt)) >> rto_beta); + rto_alpha = READ_ONCE(net->sctp.rto_alpha); + if (rto_alpha < 32) + tp->srtt = tp->srtt - (tp->srtt >> rto_alpha) + + (rtt >> rto_alpha); } else { /* 6.3.1 C2) When the first RTT measurement R is made, set * SRTT <- R, RTTVAR <- R/2. diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 157aace169d4..87c87edadde7 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -890,6 +890,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) return SMC_CLC_DECL_CNFERR; } pclc_base->hdr.typev1 = SMC_TYPE_N; + ini->smc_type_v1 = SMC_TYPE_N; } else { pclc_base->iparea_offset = htons(sizeof(*pclc_smcd)); plen += sizeof(*pclc_prfx) + diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c index a944e7dcb8b9..a94084b4a498 100644 --- a/net/smc/smc_inet.c +++ b/net/smc/smc_inet.c @@ -56,7 +56,6 @@ static struct inet_protosw smc_inet_protosw = { .protocol = IPPROTO_SMC, .prot = &smc_inet_prot, .ops = &smc_inet_stream_ops, - .flags = INET_PROTOSW_ICSK, }; #if IS_ENABLED(CONFIG_IPV6) @@ -104,27 +103,15 @@ static struct inet_protosw smc_inet6_protosw = { .protocol = IPPROTO_SMC, .prot = &smc_inet6_prot, .ops = &smc_inet6_stream_ops, - .flags = INET_PROTOSW_ICSK, }; #endif /* CONFIG_IPV6 */ -static unsigned int smc_sync_mss(struct sock *sk, u32 pmtu) -{ - /* No need pass it through to clcsock, mss can always be set by - * sock_create_kern or smc_setsockopt. - */ - return 0; -} - static int smc_inet_init_sock(struct sock *sk) { struct net *net = sock_net(sk); /* init common smc sock */ smc_sk_init(net, sk, IPPROTO_SMC); - - inet_csk(sk)->icsk_sync_mss = smc_sync_mss; - /* create clcsock */ return smc_create_clcsk(net, sk, sk->sk_family); } diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 43b1f558b33d..e659fea2da70 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -238,7 +238,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, strp_parser_err(strp, -EMSGSIZE, desc); break; } else if (len <= (ssize_t)head->len - - skb->len - stm->strp.offset) { + (ssize_t)skb->len - stm->strp.offset) { /* Length must be into new skb (and also * greater than zero) */ diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 984e0cf9bf8a..a570e7adf270 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -18,10 +18,9 @@ config SUNRPC_SWAP config RPCSEC_GSS_KRB5 tristate "Secure RPC: Kerberos V mechanism" - depends on SUNRPC + depends on SUNRPC && CRYPTO default y select SUNRPC_GSS - select CRYPTO select CRYPTO_SKCIPHER select CRYPTO_HASH help diff --git a/net/tipc/net.c b/net/tipc/net.c index 0e95572e56b4..7e65d0b0c4a8 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -145,7 +145,9 @@ void tipc_net_finalize_work(struct work_struct *work) { struct tipc_net *tn = container_of(work, struct tipc_net, work); + rtnl_lock(); tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); + rtnl_unlock(); } void tipc_net_stop(struct net *net) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index a64ae15b1a60..71734411ff4c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -723,8 +723,10 @@ tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async, /* shouldn't get to wraparound: * too long in async stage, something bad happened */ - if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) + if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) { + tls_offload_rx_resync_async_request_cancel(resync_async); return false; + } /* asynchronous stage: log all headers seq such that * req_seq <= seq <= end_seq, and wait for real resync request diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 768098dec231..833c3616d2a2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2954,6 +2954,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, u = unix_sk(sk); +redo: /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ @@ -2965,7 +2966,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, struct sk_buff *skb, *last; int chunk; -redo: unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) { err = -ECONNRESET; @@ -3015,7 +3015,6 @@ again: goto out; } - mutex_lock(&u->iolock); goto redo; unlock: unix_state_unlock(sk); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 684ab03137b6..65396a4e1b07 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -145,6 +145,7 @@ enum unix_vertex_index { }; static unsigned long unix_vertex_unvisited_index = UNIX_VERTEX_INDEX_MARK1; +static unsigned long unix_vertex_max_scc_index = UNIX_VERTEX_INDEX_START; static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) { @@ -153,6 +154,7 @@ static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) if (!vertex) { vertex = list_first_entry(&fpl->vertices, typeof(*vertex), entry); vertex->index = unix_vertex_unvisited_index; + vertex->scc_index = ++unix_vertex_max_scc_index; vertex->out_degree = 0; INIT_LIST_HEAD(&vertex->edges); INIT_LIST_HEAD(&vertex->scc_entry); @@ -489,10 +491,15 @@ prev_vertex: scc_dead = unix_vertex_dead(v); } - if (scc_dead) + if (scc_dead) { unix_collect_skb(&scc, hitlist); - else if (!unix_graph_maybe_cyclic) - unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + } else { + if (unix_vertex_max_scc_index < vertex->scc_index) + unix_vertex_max_scc_index = vertex->scc_index; + + if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + } list_del(&scc); } @@ -507,6 +514,7 @@ static void unix_walk_scc(struct sk_buff_head *hitlist) unsigned long last_index = UNIX_VERTEX_INDEX_START; unix_graph_maybe_cyclic = false; + unix_vertex_max_scc_index = UNIX_VERTEX_INDEX_START; /* Visit every vertex exactly once. * __unix_walk_scc() moves visited vertices to unix_visited_vertices. diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4c2db6cca557..a9ca9c3b87b3 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -487,12 +487,26 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) goto err; } - if (vsk->transport) { - if (vsk->transport == new_transport) { - ret = 0; - goto err; - } + if (vsk->transport && vsk->transport == new_transport) { + ret = 0; + goto err; + } + + /* We increase the module refcnt to prevent the transport unloading + * while there are open sockets assigned to it. + */ + if (!new_transport || !try_module_get(new_transport->module)) { + ret = -ENODEV; + goto err; + } + /* It's safe to release the mutex after a successful try_module_get(). + * Whichever transport `new_transport` points at, it won't go away until + * the last module_put() below or in vsock_deassign_transport(). + */ + mutex_unlock(&vsock_register_mutex); + + if (vsk->transport) { /* transport->release() must be called with sock lock acquired. * This path can only be taken during vsock_connect(), where we * have already held the sock lock. In the other cases, this @@ -512,20 +526,6 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) vsk->peer_shutdown = 0; } - /* We increase the module refcnt to prevent the transport unloading - * while there are open sockets assigned to it. - */ - if (!new_transport || !try_module_get(new_transport->module)) { - ret = -ENODEV; - goto err; - } - - /* It's safe to release the mutex after a successful try_module_get(). - * Whichever transport `new_transport` points at, it won't go away until - * the last module_put() below or in vsock_deassign_transport(). - */ - mutex_unlock(&vsock_register_mutex); - if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || !new_transport->seqpacket_allow(remote_cid)) { @@ -1661,18 +1661,40 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, timeout = schedule_timeout(timeout); lock_sock(sk); - if (signal_pending(current)) { - err = sock_intr_errno(timeout); - sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; - sock->state = SS_UNCONNECTED; - vsock_transport_cancel_pkt(vsk); - vsock_remove_connected(vsk); - goto out_wait; - } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { - err = -ETIMEDOUT; + /* Connection established. Whatever happens to socket once we + * release it, that's not connect()'s concern. No need to go + * into signal and timeout handling. Call it a day. + * + * Note that allowing to "reset" an already established socket + * here is racy and insecure. + */ + if (sk->sk_state == TCP_ESTABLISHED) + break; + + /* If connection was _not_ established and a signal/timeout came + * to be, we want the socket's state reset. User space may want + * to retry. + * + * sk_state != TCP_ESTABLISHED implies that socket is not on + * vsock_connected_table. We keep the binding and the transport + * assigned. + */ + if (signal_pending(current) || timeout == 0) { + err = timeout == 0 ? -ETIMEDOUT : sock_intr_errno(timeout); + + /* Listener might have already responded with + * VIRTIO_VSOCK_OP_RESPONSE. Its handling expects our + * sk_state == TCP_SYN_SENT, which hereby we break. + * In such case VIRTIO_VSOCK_OP_RST will follow. + */ sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; + + /* Try to cancel VIRTIO_VSOCK_OP_REQUEST skb sent out by + * transport->connect(). + */ vsock_transport_cancel_pkt(vsk); + goto out_wait; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 797f9f2004a6..54a34d8d356e 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1787,6 +1787,62 @@ bool wiphy_delayed_work_pending(struct wiphy *wiphy, } EXPORT_SYMBOL_GPL(wiphy_delayed_work_pending); +enum hrtimer_restart wiphy_hrtimer_work_timer(struct hrtimer *t) +{ + struct wiphy_hrtimer_work *hrwork = + container_of(t, struct wiphy_hrtimer_work, timer); + + wiphy_work_queue(hrwork->wiphy, &hrwork->work); + + return HRTIMER_NORESTART; +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_timer); + +void wiphy_hrtimer_work_queue(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork, + ktime_t delay) +{ + trace_wiphy_hrtimer_work_queue(wiphy, &hrwork->work, delay); + + if (!delay) { + hrtimer_cancel(&hrwork->timer); + wiphy_work_queue(wiphy, &hrwork->work); + return; + } + + hrwork->wiphy = wiphy; + hrtimer_start_range_ns(&hrwork->timer, delay, + 1000 * NSEC_PER_USEC, HRTIMER_MODE_REL); +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_queue); + +void wiphy_hrtimer_work_cancel(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork) +{ + lockdep_assert_held(&wiphy->mtx); + + hrtimer_cancel(&hrwork->timer); + wiphy_work_cancel(wiphy, &hrwork->work); +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_cancel); + +void wiphy_hrtimer_work_flush(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork) +{ + lockdep_assert_held(&wiphy->mtx); + + hrtimer_cancel(&hrwork->timer); + wiphy_work_flush(wiphy, &hrwork->work); +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_flush); + +bool wiphy_hrtimer_work_pending(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork) +{ + return hrtimer_is_queued(&hrwork->timer); +} +EXPORT_SYMBOL_GPL(wiphy_hrtimer_work_pending); + static int __init cfg80211_init(void) { int err; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 346dfd2bd987..03d07b54359a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4136,8 +4136,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev->wiphy.txq_quantum = old_txq_quantum; } - if (old_rts_threshold) - kfree(old_radio_rts_threshold); + kfree(old_radio_rts_threshold); return result; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 8a4c34112eb5..2b71f1d867a0 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -304,6 +304,27 @@ TRACE_EVENT(wiphy_delayed_work_queue, __entry->delay) ); +TRACE_EVENT(wiphy_hrtimer_work_queue, + TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work, + ktime_t delay), + TP_ARGS(wiphy, work, delay), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(void *, instance) + __field(void *, func) + __field(ktime_t, delay) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->instance = work; + __entry->func = work->func; + __entry->delay = delay; + ), + TP_printk(WIPHY_PR_FMT " instance=%p func=%pS delay=%llu", + WIPHY_PR_ARG, __entry->instance, __entry->func, + __entry->delay) +); + TRACE_EVENT(wiphy_work_worker_start, TP_PROTO(struct wiphy *wiphy), TP_ARGS(wiphy), diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index fc7a603b04f1..bf744ac9d5a7 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -555,14 +555,10 @@ static void espintcp_close(struct sock *sk, long timeout) static __poll_t espintcp_poll(struct file *file, struct socket *sock, poll_table *wait) { - __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct espintcp_ctx *ctx = espintcp_getctx(sk); - if (!skb_queue_empty(&ctx->ike_queue)) - mask |= EPOLLIN | EPOLLRDNORM; - - return mask; + return datagram_poll_queue(file, sock, wait, &ctx->ike_queue); } static void build_protos(struct proto *espintcp_prot, diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 44b9de6e4e77..52ae0e034d29 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -438,7 +438,7 @@ ok: check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; - switch (x->inner_mode.family) { + switch (skb_dst(skb)->ops->family) { case AF_INET: /* Check for IPv4 options */ if (ip_hdr(skb)->ihl != 5) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9077730ff7d0..54222fcbd7fd 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -698,7 +698,7 @@ static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x) return; if (x->outer_mode.encap == XFRM_MODE_TUNNEL) { - switch (x->outer_mode.family) { + switch (skb_dst(skb)->ops->family) { case AF_INET: xo->inner_ipproto = ip_hdr(skb)->protocol; break; @@ -772,8 +772,12 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) /* Exclusive direct xmit for tunnel mode, as * some filtering or matching rules may apply * in transport mode. + * Locally generated packets also require + * the normal XFRM path for L2 header setup, + * as the hardware needs the L2 header to match + * for encryption, so skip direct output as well. */ - if (x->props.mode == XFRM_MODE_TUNNEL) + if (x->props.mode == XFRM_MODE_TUNNEL && !skb->sk) return xfrm_dev_direct_output(sk, x, skb); return xfrm_output_resume(sk, skb, 0); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d213ca3653a8..9e14e453b55c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -592,6 +592,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); +static void xfrm_state_delete_tunnel(struct xfrm_state *x); static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) @@ -607,6 +608,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) kfree(x->replay_esn); kfree(x->preplay_esn); xfrm_unset_type_offload(x); + xfrm_state_delete_tunnel(x); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); @@ -806,7 +808,6 @@ void __xfrm_state_destroy(struct xfrm_state *x) } EXPORT_SYMBOL(__xfrm_state_destroy); -static void xfrm_state_delete_tunnel(struct xfrm_state *x); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -2073,6 +2074,7 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, return x; error: + x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); out: return NULL; @@ -2157,11 +2159,15 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, xfrm_state_insert(xc); } else { if (xfrm_state_add(xc) < 0) - goto error; + goto error_add; } return xc; +error_add: + if (xuo) + xfrm_dev_state_delete(xc); error: + xc->km.state = XFRM_STATE_DEAD; xfrm_state_put(xc); return NULL; } @@ -2191,14 +2197,18 @@ int xfrm_state_update(struct xfrm_state *x) } if (x1->km.state == XFRM_STATE_ACQ) { - if (x->dir && x1->dir != x->dir) + if (x->dir && x1->dir != x->dir) { + to_put = x1; goto out; + } __xfrm_state_insert(x); x = NULL; } else { - if (x1->dir != x->dir) + if (x1->dir != x->dir) { + to_put = x1; goto out; + } } err = 0; @@ -3298,6 +3308,7 @@ out_bydst: void xfrm_state_fini(struct net *net) { unsigned int sz; + int i; flush_work(&net->xfrm.state_hash_work); xfrm_state_flush(net, 0, false); @@ -3305,14 +3316,17 @@ void xfrm_state_fini(struct net *net) WARN_ON(!list_empty(&net->xfrm.state_all)); + for (i = 0; i <= net->xfrm.state_hmask; i++) { + WARN_ON(!hlist_empty(net->xfrm.state_byseq + i)); + WARN_ON(!hlist_empty(net->xfrm.state_byspi + i)); + WARN_ON(!hlist_empty(net->xfrm.state_bysrc + i)); + WARN_ON(!hlist_empty(net->xfrm.state_bydst + i)); + } + sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); - WARN_ON(!hlist_empty(net->xfrm.state_byseq)); xfrm_hash_free(net->xfrm.state_byseq, sz); - WARN_ON(!hlist_empty(net->xfrm.state_byspi)); xfrm_hash_free(net->xfrm.state_byspi, sz); - WARN_ON(!hlist_empty(net->xfrm.state_bysrc)); xfrm_hash_free(net->xfrm.state_bysrc, sz); - WARN_ON(!hlist_empty(net->xfrm.state_bydst)); xfrm_hash_free(net->xfrm.state_bydst, sz); free_percpu(net->xfrm.state_cache_input); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 010c9e6638c0..403b5ecac2c5 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -947,8 +947,11 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_SA_PCPU]) { x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); - if (x->pcpu_num >= num_possible_cpus()) + if (x->pcpu_num >= num_possible_cpus()) { + err = -ERANGE; + NL_SET_ERR_MSG(extack, "pCPU number too big"); goto error; + } } err = __xfrm_init_state(x, extack); @@ -3035,6 +3038,9 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, } xfrm_state_free(x); + xfrm_dev_policy_delete(xp); + xfrm_dev_policy_free(xp); + security_xfrm_policy_free(xp->security); kfree(xp); return 0; |