diff options
Diffstat (limited to 'net')
93 files changed, 1436 insertions, 769 deletions
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 8e48ccd2af30..c82502e213a8 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -2952,5 +2952,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) return 0; } - return hci_cmd_sync_queue_once(hdev, abort_conn_sync, conn, NULL); + /* Run immediately if on cmd_sync_work since this may be called + * as a result to MGMT_OP_DISCONNECT/MGMT_OP_UNPAIR which does + * already queue its callback on cmd_sync_work. + */ + return hci_cmd_sync_run_once(hdev, abort_conn_sync, conn, NULL); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 8a4ebd93adfc..d6976db02c06 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -119,13 +119,6 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state) case DISCOVERY_STARTING: break; case DISCOVERY_FINDING: - /* If discovery was not started then it was initiated by the - * MGMT interface so no MGMT event shall be generated either - */ - if (old_state != DISCOVERY_STARTING) { - hdev->discovery.state = old_state; - return; - } mgmt_discovering(hdev, 1); break; case DISCOVERY_RESOLVING: @@ -2413,10 +2406,16 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, /* To avoid a potential race with hci_unregister_dev. */ hci_dev_hold(hdev); - if (action == PM_SUSPEND_PREPARE) + switch (action) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: ret = hci_suspend_dev(hdev); - else if (action == PM_POST_SUSPEND) + break; + case PM_POST_HIBERNATION: + case PM_POST_SUSPEND: ret = hci_resume_dev(hdev); + break; + } if (ret) bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", @@ -3671,19 +3670,19 @@ static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; - int quote, cnt, tmp; + int quote, *cnt, tmp; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, LE_LINK)) return; - cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; + cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; - __check_timeout(hdev, cnt, LE_LINK); + __check_timeout(hdev, *cnt, LE_LINK); - tmp = cnt; - while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { + tmp = *cnt; + while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, @@ -3698,7 +3697,7 @@ static void hci_sched_le(struct hci_dev *hdev) hci_send_frame(hdev, skb); hdev->le_last_tx = jiffies; - cnt--; + (*cnt)--; chan->sent++; chan->conn->sent++; @@ -3708,12 +3707,7 @@ static void hci_sched_le(struct hci_dev *hdev) } } - if (hdev->le_pkts) - hdev->le_cnt = cnt; - else - hdev->acl_cnt = cnt; - - if (cnt != tmp) + if (*cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index dce8035ca799..1c82dcdf6e8f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1721,9 +1721,10 @@ static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable) switch (enable) { case LE_SCAN_ENABLE: hci_dev_set_flag(hdev, HCI_LE_SCAN); - if (hdev->le_scan_type == LE_SCAN_ACTIVE) + if (hdev->le_scan_type == LE_SCAN_ACTIVE) { clear_pending_adv_report(hdev); - hci_discovery_set_state(hdev, DISCOVERY_FINDING); + hci_discovery_set_state(hdev, DISCOVERY_FINDING); + } break; case LE_SCAN_DISABLE: @@ -5919,7 +5920,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && - (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || + (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index cd2ed16da8a4..5533e6f561b3 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -112,7 +112,7 @@ static void hci_cmd_sync_add(struct hci_request *req, u16 opcode, u32 plen, skb_queue_tail(&req->cmd_q, skb); } -static int hci_cmd_sync_run(struct hci_request *req) +static int hci_req_sync_run(struct hci_request *req) { struct hci_dev *hdev = req->hdev; struct sk_buff *skb; @@ -169,7 +169,7 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, hdev->req_status = HCI_REQ_PEND; - err = hci_cmd_sync_run(&req); + err = hci_req_sync_run(&req); if (err < 0) return ERR_PTR(err); @@ -782,6 +782,44 @@ int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, } EXPORT_SYMBOL(hci_cmd_sync_queue_once); +/* Run HCI command: + * + * - hdev must be running + * - if on cmd_sync_work then run immediately otherwise queue + */ +int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + /* Only queue command if hdev is running which means it had been opened + * and is either on init phase or is already up. + */ + if (!test_bit(HCI_RUNNING, &hdev->flags)) + return -ENETDOWN; + + /* If on cmd_sync_work then run immediately otherwise queue */ + if (current_work() == &hdev->cmd_sync_work) + return func(hdev, data); + + return hci_cmd_sync_submit(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_run); + +/* Run HCI command entry once: + * + * - Lookup if an entry already exist and only if it doesn't creates a new entry + * and run it. + * - if on cmd_sync_work then run immediately otherwise queue + */ +int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy)) + return 0; + + return hci_cmd_sync_run(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_run_once); + /* Lookup HCI command entry: * * - Return first entry that matches by function callback or data or @@ -2976,6 +3014,27 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) */ filter_policy = hci_update_accept_list_sync(hdev); + /* If suspended and filter_policy set to 0x00 (no acceptlist) then + * passive scanning cannot be started since that would require the host + * to be woken up to process the reports. + */ + if (hdev->suspended && !filter_policy) { + /* Check if accept list is empty then there is no need to scan + * while suspended. + */ + if (list_empty(&hdev->le_accept_list)) + return 0; + + /* If there are devices is the accept_list that means some + * devices could not be programmed which in non-suspended case + * means filter_policy needs to be set to 0x00 so the host needs + * to filter, but since this is treating suspended case we + * can ignore device needing host to filter to allow devices in + * the acceptlist to be able to wakeup the system. + */ + filter_policy = 0x01; + } + /* When the controller is using random resolvable addresses and * with that having LE privacy enabled, then controllers with * Extended Scanner Filter Policies support can now enable support @@ -2998,6 +3057,20 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) } else if (hci_is_adv_monitoring(hdev)) { window = hdev->le_scan_window_adv_monitor; interval = hdev->le_scan_int_adv_monitor; + + /* Disable duplicates filter when scanning for advertisement + * monitor for the following reasons. + * + * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm + * controllers ignore RSSI_Sampling_Period when the duplicates + * filter is enabled. + * + * For SW pattern filtering, when we're not doing interleaved + * scanning, it is necessary to disable duplicates filter, + * otherwise hosts can only receive one advertisement and it's + * impossible to know if a peer is still in range. + */ + filter_dups = LE_SCAN_FILTER_DUP_DISABLE; } else { window = hdev->le_scan_window; interval = hdev->le_scan_interval; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index c3c26bbb5dda..9988ba382b68 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6774,6 +6774,7 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, bt_cb(skb)->l2cap.psm = psm; if (!chan->ops->recv(chan, skb)) { + l2cap_chan_unlock(chan); l2cap_chan_put(chan); return; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 40d4887c7f79..279902e8bd8a 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2830,16 +2830,6 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "debug_keys %u key_count %u", cp->debug_keys, key_count); - for (i = 0; i < key_count; i++) { - struct mgmt_link_key_info *key = &cp->keys[i]; - - /* Considering SMP over BREDR/LE, there is no need to check addr_type */ - if (key->type > 0x08) - return mgmt_cmd_status(sk, hdev->id, - MGMT_OP_LOAD_LINK_KEYS, - MGMT_STATUS_INVALID_PARAMS); - } - hci_dev_lock(hdev); hci_link_keys_clear(hdev); @@ -2864,6 +2854,19 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, continue; } + if (key->addr.type != BDADDR_BREDR) { + bt_dev_warn(hdev, + "Invalid link address type %u for %pMR", + key->addr.type, &key->addr.bdaddr); + continue; + } + + if (key->type > 0x08) { + bt_dev_warn(hdev, "Invalid link key type %u for %pMR", + key->type, &key->addr.bdaddr); + continue; + } + /* Always ignore debug keys and require a new pairing if * the user wants to use them. */ @@ -2921,7 +2924,12 @@ static int unpair_device_sync(struct hci_dev *hdev, void *data) if (!conn) return 0; - return hci_abort_conn_sync(hdev, conn, HCI_ERROR_REMOTE_USER_TERM); + /* Disregard any possible error since the likes of hci_abort_conn_sync + * will clean up the connection no matter the error. + */ + hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); + + return 0; } static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, @@ -3053,13 +3061,44 @@ unlock: return err; } +static void disconnect_complete(struct hci_dev *hdev, void *data, int err) +{ + struct mgmt_pending_cmd *cmd = data; + + cmd->cmd_complete(cmd, mgmt_status(err)); + mgmt_pending_free(cmd); +} + +static int disconnect_sync(struct hci_dev *hdev, void *data) +{ + struct mgmt_pending_cmd *cmd = data; + struct mgmt_cp_disconnect *cp = cmd->param; + struct hci_conn *conn; + + if (cp->addr.type == BDADDR_BREDR) + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, + &cp->addr.bdaddr); + else + conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr, + le_addr_type(cp->addr.type)); + + if (!conn) + return -ENOTCONN; + + /* Disregard any possible error since the likes of hci_abort_conn_sync + * will clean up the connection no matter the error. + */ + hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); + + return 0; +} + static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_disconnect *cp = data; struct mgmt_rp_disconnect rp; struct mgmt_pending_cmd *cmd; - struct hci_conn *conn; int err; bt_dev_dbg(hdev, "sock %p", sk); @@ -3082,27 +3121,7 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - if (pending_find(MGMT_OP_DISCONNECT, hdev)) { - err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, - MGMT_STATUS_BUSY, &rp, sizeof(rp)); - goto failed; - } - - if (cp->addr.type == BDADDR_BREDR) - conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, - &cp->addr.bdaddr); - else - conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr, - le_addr_type(cp->addr.type)); - - if (!conn || conn->state == BT_OPEN || conn->state == BT_CLOSED) { - err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, - MGMT_STATUS_NOT_CONNECTED, &rp, - sizeof(rp)); - goto failed; - } - - cmd = mgmt_pending_add(sk, MGMT_OP_DISCONNECT, hdev, data, len); + cmd = mgmt_pending_new(sk, MGMT_OP_DISCONNECT, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@ -3110,9 +3129,10 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, cmd->cmd_complete = generic_cmd_complete; - err = hci_disconnect(conn, HCI_ERROR_REMOTE_USER_TERM); + err = hci_cmd_sync_queue(hdev, disconnect_sync, cmd, + disconnect_complete); if (err < 0) - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); failed: hci_dev_unlock(hdev); @@ -3456,6 +3476,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * will be kept and this function does nothing. */ p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + if (!p) { + err = -EIO; + goto unlock; + } if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) p->auto_connect = HCI_AUTO_CONN_DISABLED; @@ -7068,7 +7092,6 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, for (i = 0; i < irk_count; i++) { struct mgmt_irk_info *irk = &cp->irks[i]; - u8 addr_type = le_addr_type(irk->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, @@ -7078,12 +7101,8 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, continue; } - /* When using SMP over BR/EDR, the addr type should be set to BREDR */ - if (irk->addr.type == BDADDR_BREDR) - addr_type = BDADDR_BREDR; - hci_add_irk(hdev, &irk->addr.bdaddr, - addr_type, irk->val, + le_addr_type(irk->addr.type), irk->val, BDADDR_ANY); } @@ -7148,15 +7167,6 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, bt_dev_dbg(hdev, "key_count %u", key_count); - for (i = 0; i < key_count; i++) { - struct mgmt_ltk_info *key = &cp->keys[i]; - - if (!ltk_is_valid(key)) - return mgmt_cmd_status(sk, hdev->id, - MGMT_OP_LOAD_LONG_TERM_KEYS, - MGMT_STATUS_INVALID_PARAMS); - } - hci_dev_lock(hdev); hci_smp_ltks_clear(hdev); @@ -7164,7 +7174,6 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, for (i = 0; i < key_count; i++) { struct mgmt_ltk_info *key = &cp->keys[i]; u8 type, authenticated; - u8 addr_type = le_addr_type(key->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, @@ -7174,6 +7183,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, continue; } + if (!ltk_is_valid(key)) { + bt_dev_warn(hdev, "Invalid LTK for %pMR", + &key->addr.bdaddr); + continue; + } + switch (key->type) { case MGMT_LTK_UNAUTHENTICATED: authenticated = 0x00; @@ -7199,12 +7214,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, continue; } - /* When using SMP over BR/EDR, the addr type should be set to BREDR */ - if (key->addr.type == BDADDR_BREDR) - addr_type = BDADDR_BREDR; - hci_add_ltk(hdev, &key->addr.bdaddr, - addr_type, type, authenticated, + le_addr_type(key->addr.type), type, authenticated, key->val, key->enc_size, key->ediv, key->rand); } @@ -9498,7 +9509,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); + ev.key.addr.type = BDADDR_BREDR; ev.key.type = key->type; memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE); ev.key.pin_len = key->pin_len; @@ -9549,7 +9560,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); ev.key.type = mgmt_ltk_type(key); ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; @@ -9578,7 +9589,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent) bacpy(&ev.rpa, &irk->rpa); bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr); - ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type); + ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type); memcpy(ev.irk.val, irk->val, sizeof(irk->val)); mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL); @@ -9607,7 +9618,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr); - ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type); ev.key.type = csrk->type; memcpy(ev.key.val, csrk->val, sizeof(csrk->val)); @@ -9685,18 +9696,6 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, mgmt_event_skb(skb, NULL); } -static void disconnect_rsp(struct mgmt_pending_cmd *cmd, void *data) -{ - struct sock **sk = data; - - cmd->cmd_complete(cmd, 0); - - *sk = cmd->sk; - sock_hold(*sk); - - mgmt_pending_remove(cmd); -} - static void unpair_device_rsp(struct mgmt_pending_cmd *cmd, void *data) { struct hci_dev *hdev = data; @@ -9740,8 +9739,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, if (link_type != ACL_LINK && link_type != LE_LINK) return; - mgmt_pending_foreach(MGMT_OP_DISCONNECT, hdev, disconnect_rsp, &sk); - bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); ev.reason = reason; @@ -9754,9 +9751,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, if (sk) sock_put(sk); - - mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp, - hdev); } void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1e7ea3a4b7ef..8b9724fd752a 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, * Confirms and the responder Enters the passkey. */ if (smp->method == OVERLAP) { - if (hcon->role == HCI_ROLE_MASTER) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp->method = CFM_PASSKEY; else smp->method = REQ_PASSKEY; @@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp) smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); else SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp) int ret; bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn, - conn->hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, @@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp) return SMP_CONFIRM_FAILED; } - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 stk[16]; __le64 rand = 0; __le16 ediv = 0; @@ -1059,7 +1060,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->remote_irk) { - smp->remote_irk->link_type = hcon->type; mgmt_new_irk(hdev, smp->remote_irk, persistent); /* Now that user space can be considered to know the @@ -1079,28 +1079,24 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->csrk) { - smp->csrk->link_type = hcon->type; smp->csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->csrk, persistent); } if (smp->responder_csrk) { - smp->responder_csrk->link_type = hcon->type; smp->responder_csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->responder_csrk, persistent); } if (smp->ltk) { - smp->ltk->link_type = hcon->type; smp->ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->ltk, persistent); } if (smp->responder_ltk) { - smp->responder_ltk->link_type = hcon->type; smp->responder_ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->responder_ltk, persistent); @@ -1120,8 +1116,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst, smp->link_key, type, 0, &persistent); if (key) { - key->link_type = hcon->type; - key->bdaddr_type = hcon->dst_type; mgmt_new_link_key(hdev, key, persistent); /* Don't keep debug keys around if the relevant @@ -1256,14 +1250,15 @@ static void smp_distribute_keys(struct smp_chan *smp) rsp = (void *) &smp->prsp[1]; /* The responder sends its keys first */ - if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) && + (smp->remote_key_dist & KEY_DIST_MASK)) { smp_allow_key_dist(smp); return; } req = (void *) &smp->preq[1]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { keydist = &rsp->init_key_dist; *keydist &= req->init_key_dist; } else { @@ -1432,7 +1427,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16]) struct hci_conn *hcon = smp->conn->hcon; u8 *na, *nb, a[7], b[7]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { na = smp->prnd; nb = smp->rrnd; } else { @@ -1460,7 +1455,7 @@ static void sc_dhkey_check(struct smp_chan *smp) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->preq[1], 3); @@ -1539,7 +1534,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) /* The round is only complete when the initiator * receives pairing random. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); if (smp->passkey_round == 20) @@ -1567,7 +1562,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); return 0; @@ -1578,7 +1573,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) case SMP_CMD_PUBLIC_KEY: default: /* Initiating device starts the round */ - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; bt_dev_dbg(hdev, "Starting passkey round %u", @@ -1623,7 +1618,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey) } /* Initiator sends DHKey check first */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) { @@ -1746,7 +1741,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_cmd_pairing rsp, *req = (void *) skb->data; struct l2cap_chan *chan = conn->smp; struct hci_dev *hdev = conn->hcon->hdev; - struct smp_chan *smp; + struct smp_chan *smp = chan->data; u8 key_size, auth, sec_level; int ret; @@ -1755,16 +1750,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*req)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_SLAVE) + if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; - if (!chan->data) + if (!smp) { smp = smp_chan_create(conn); - else - smp = chan->data; - - if (!smp) - return SMP_UNSPECIFIED; + if (!smp) + return SMP_UNSPECIFIED; + } /* We didn't start the pairing, so match remote */ auth = req->auth_req & AUTH_REQ_MASK(hdev); @@ -1946,7 +1939,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rsp)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_MASTER) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; skb_pull(skb, sizeof(*rsp)); @@ -2041,7 +2034,7 @@ static u8 sc_check_confirm(struct smp_chan *smp) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM); - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2063,7 +2056,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) u8 auth; /* The issue is only observed when we're in responder role */ - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_UNSPECIFIED; if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { @@ -2099,7 +2092,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) struct hci_dev *hdev = hcon->hdev; bt_dev_dbg(hdev, "conn %p %s", conn, - hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); if (skb->len < sizeof(smp->pcnf)) return SMP_INVALID_PARAMS; @@ -2121,7 +2115,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) return ret; } - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2156,7 +2150,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (!test_bit(SMP_FLAG_SC, &smp->flags)) return smp_random(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { pkax = smp->local_pk; pkbx = smp->remote_pk; na = smp->prnd; @@ -2169,7 +2163,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); @@ -2180,7 +2174,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 cfm[16]; err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk, @@ -2221,7 +2215,7 @@ mackey_and_ltk: return SMP_UNSPECIFIED; if (smp->method == REQ_OOB) { - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } @@ -2295,10 +2289,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, return false; } +static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_pairing cp; + + if (smp->conn->hcon->type == ACL_LINK) + build_bredr_pairing_cmd(smp, &cp, NULL); + else + build_pairing_cmd(smp->conn, &cp, NULL, auth); + + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], &cp, sizeof(cp)); + + smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + + set_bit(SMP_FLAG_INITIATOR, &smp->flags); +} + static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_security_req *rp = (void *) skb->data; - struct smp_cmd_pairing cp; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; struct smp_chan *smp; @@ -2347,16 +2358,20 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) skb_pull(skb, sizeof(*rp)); - memset(&cp, 0, sizeof(cp)); - build_pairing_cmd(conn, &cp, NULL, auth); + smp_send_pairing_req(smp, auth); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); + return 0; +} - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); +static void smp_send_security_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_security_req cp; - return 0; + cp.auth_req = auth; + smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); + + clear_bit(SMP_FLAG_INITIATOR, &smp->flags); } int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) @@ -2427,23 +2442,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq |= SMP_AUTH_MITM; } - if (hcon->role == HCI_ROLE_MASTER) { - struct smp_cmd_pairing cp; - - build_pairing_cmd(conn, &cp, NULL, authreq); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); - } else { - struct smp_cmd_security_req cp; - cp.auth_req = authreq; - smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); - } + if (hcon->role == HCI_ROLE_MASTER) + smp_send_pairing_req(smp, authreq); + else + smp_send_security_req(smp, authreq); - set_bit(SMP_FLAG_INITIATOR, &smp->flags); ret = 0; unlock: @@ -2694,8 +2697,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb) static u8 sc_select_method(struct smp_chan *smp) { - struct l2cap_conn *conn = smp->conn; - struct hci_conn *hcon = conn->hcon; struct smp_cmd_pairing *local, *remote; u8 local_mitm, remote_mitm, local_io, remote_io, method; @@ -2708,7 +2709,7 @@ static u8 sc_select_method(struct smp_chan *smp) * the "struct smp_cmd_pairing" from them we need to skip the * first byte which contains the opcode. */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local = (void *) &smp->preq[1]; remote = (void *) &smp->prsp[1]; } else { @@ -2777,7 +2778,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* Non-initiating device sends its public key after receiving * the key from the initiating device. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { err = sc_send_public_key(smp); if (err) return err; @@ -2839,7 +2840,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); @@ -2848,7 +2849,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); if (smp->method == REQ_PASSKEY) { @@ -2863,7 +2864,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* The Initiating device waits for the non-initiating device to * send the confirm value. */ - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd, @@ -2897,7 +2898,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->prsp[1], 3); @@ -2922,7 +2923,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (crypto_memneq(check->e, e, 16)) return SMP_DHKEY_CHECK_FAILED; - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) { set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags); return 0; @@ -2934,7 +2935,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) sc_add_ltk(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size); hcon->enc_key_size = smp->enc_key_size; } @@ -3083,7 +3084,6 @@ static void bredr_pairing(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; - struct smp_cmd_pairing req; struct smp_chan *smp; bt_dev_dbg(hdev, "chan %p", chan); @@ -3135,14 +3135,7 @@ static void bredr_pairing(struct l2cap_chan *chan) bt_dev_dbg(hdev, "starting SMP over BR/EDR"); - /* Prepare and send the BR/EDR SMP Pairing Request */ - build_bredr_pairing_cmd(smp, &req, NULL); - - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &req, sizeof(req)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + smp_send_pairing_req(smp, 0x00); } static void smp_resume_cb(struct l2cap_chan *chan) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c77591e63841..ad7a42b505ef 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1469,12 +1469,10 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, modified = true; } - if (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) { + if (test_and_set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) { /* Refresh entry */ fdb->used = jiffies; - } else if (!test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags)) { - /* Take over SW learned entry */ - set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags); + } else { modified = true; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 9a1cb5079a7a..b2ae0d2434d2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2045,16 +2045,14 @@ void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; - HLIST_HEAD(deleted_head); struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_find_del_pg(br, pg); - hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); - br_multicast_gc(&deleted_head); + flush_work(&br->mcast_gc_work); br_multicast_port_ctx_deinit(&port->multicast_ctx); free_percpu(port->mcast_stats); } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 09f6a773a708..8f9c19d992ac 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -622,8 +622,12 @@ static unsigned int br_nf_local_in(void *priv, if (likely(nf_ct_is_confirmed(ct))) return NF_ACCEPT; + if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + WARN_ON_ONCE(skb_shared(skb)); - WARN_ON_ONCE(refcount_read(&nfct->use) != 1); /* We can't call nf_confirm here, it would create a dependency * on nf_conntrack module. diff --git a/net/can/bcm.c b/net/can/bcm.c index 27d5fcf0eac9..46d3ec3aa44b 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1470,6 +1470,10 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, /* remove device reference, if this is our bound device */ if (bo->bound && bo->ifindex == dev->ifindex) { +#if IS_ENABLED(CONFIG_PROC_FS) + if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read) + remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir); +#endif bo->bound = 0; bo->ifindex = 0; notify_enodev = 1; diff --git a/net/core/dev.c b/net/core/dev.c index 6ea1d20676fb..f66e61407883 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5150,6 +5150,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) bpf_net_ctx_clear(bpf_net_ctx); return XDP_DROP; } + bpf_net_ctx_clear(bpf_net_ctx); } return XDP_PASS; out_redir: @@ -9911,6 +9912,15 @@ static void netdev_sync_lower_features(struct net_device *upper, } } +static bool netdev_has_ip_or_hw_csum(netdev_features_t features) +{ + netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + bool ip_csum = (features & ip_csum_mask) == ip_csum_mask; + bool hw_csum = features & NETIF_F_HW_CSUM; + + return ip_csum || hw_csum; +} + static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { @@ -9992,15 +10002,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_LRO; } - if (features & NETIF_F_HW_TLS_TX) { - bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) == - (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - bool hw_csum = features & NETIF_F_HW_CSUM; - - if (!ip_csum && !hw_csum) { - netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); - features &= ~NETIF_F_HW_TLS_TX; - } + if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); + features &= ~NETIF_F_HW_TLS_TX; } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { @@ -10008,6 +10012,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_HW_TLS_RX; } + if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n"); + features &= ~NETIF_F_GSO_UDP_L4; + } + return features; } diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 8ec35194bfcb..ab150641142a 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -148,9 +148,9 @@ static void linkwatch_schedule_work(int urgent) * override the existing timer. */ if (test_bit(LW_URGENT, &linkwatch_flags)) - mod_delayed_work(system_wq, &linkwatch_work, 0); + mod_delayed_work(system_unbound_wq, &linkwatch_work, 0); else - schedule_delayed_work(&linkwatch_work, delay); + queue_delayed_work(system_unbound_wq, &linkwatch_work, delay); } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 0e2084ce7b75..291fdf4a328b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -235,7 +235,7 @@ static ssize_t speed_show(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && netif_device_present(netdev)) { + if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) @@ -1524,7 +1524,7 @@ static const struct attribute_group dql_group = { }; #else /* Fake declaration, all the code using it should be dead */ -extern const struct attribute_group dql_group; +static const struct attribute_group dql_group = {}; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 55bcacf67df3..d657b042d5a0 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -228,7 +228,6 @@ void netpoll_poll_disable(struct net_device *dev) down(&ni->dev_lock); srcu_read_unlock(&netpoll_srcu, idx); } -EXPORT_SYMBOL(netpoll_poll_disable); void netpoll_poll_enable(struct net_device *dev) { @@ -239,7 +238,6 @@ void netpoll_poll_enable(struct net_device *dev) up(&ni->dev_lock); rcu_read_unlock(); } -EXPORT_SYMBOL(netpoll_poll_enable); static void refill_skbs(void) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index ea55a758a475..197a50ef8e2e 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3654,7 +3654,7 @@ static int pktgen_thread_worker(void *arg) struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; - WARN_ON(smp_processor_id() != cpu); + WARN_ON_ONCE(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); complete(&t->start_done); @@ -3989,6 +3989,7 @@ static int __net_init pg_net_init(struct net *net) goto remove; } + cpus_read_lock(); for_each_online_cpu(cpu) { int err; @@ -3997,6 +3998,7 @@ static int __net_init pg_net_init(struct net *net) pr_warn("Cannot create thread for cpu %d (%d)\n", cpu, err); } + cpus_read_unlock(); if (list_empty(&pn->pktgen_threads)) { pr_err("Initialization failed for all threads\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 87e67194f240..73fd7f543fd0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3288,7 +3288,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (ifm->ifi_index > 0) dev = __dev_get_by_index(tgt_net, ifm->ifi_index); else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) - dev = rtnl_dev_get(net, tb); + dev = rtnl_dev_get(tgt_net, tb); else if (tb[IFLA_GROUP]) err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP])); else diff --git a/net/dsa/tag.c b/net/dsa/tag.c index 6e402d49afd3..79ad105902d9 100644 --- a/net/dsa/tag.c +++ b/net/dsa/tag.c @@ -105,8 +105,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, p = netdev_priv(skb->dev); - if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { - nskb = dsa_untag_bridge_pvid(skb); + if (unlikely(cpu_dp->ds->untag_bridge_pvid || + cpu_dp->ds->untag_vlan_aware_bridge_pvid)) { + nskb = dsa_software_vlan_untag(skb); if (!nskb) { kfree_skb(skb); return 0; diff --git a/net/dsa/tag.h b/net/dsa/tag.h index f6b9c73718df..d5707870906b 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -44,46 +44,81 @@ static inline struct net_device *dsa_conduit_find_user(struct net_device *dev, return NULL; } -/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged - * frames as untagged, since the bridge will not untag them. +/** + * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge can process tagged packets. Software like STP/PTP may not. The + * bridge can also process untagged packets, to the same effect as if they were + * tagged with the PVID of the ingress port. So packets tagged with the PVID of + * the bridge port must be software-untagged, to support both use cases. */ -static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) +static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) { - struct dsa_port *dp = dsa_user_to_port(skb->dev); - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct net_device *dev = skb->dev; - struct net_device *upper_dev; - u16 vid, pvid, proto; + u16 pvid, proto; int err; - if (!br || br_vlan_enabled(br)) - return skb; - err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { - skb = skb_vlan_untag(skb); - if (!skb) - return NULL; - } + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; - if (!skb_vlan_tag_present(skb)) - return skb; + if (vid == pvid && skb->vlan_proto == htons(proto)) + __vlan_hwaccel_clear_tag(skb); +} - vid = skb_vlan_tag_get_id(skb); +/** + * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run + * on the plain port, or on a VLAN upper interface). Maybe packets are coming + * to software as tagged with a driver-defined VID which is NOT equal to the + * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration + * should NOT be committed to hardware). DSA needs a method for this private + * VID to be communicated by software to it, and if packets are tagged with it, + * software-untag them. Note: the private VID may be different per bridge, to + * support the FDB isolation use case. + * + * FIXME: this is currently implemented based on the broken assumption that + * the "private VID" used by the driver in VLAN-unaware mode is equal to the + * bridge PVID. It should not be, except for a coincidence; the bridge PVID is + * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that + * this function removes is wrong. + * + * All users of ds->untag_bridge_pvid should fix their drivers, if necessary, + * to make the two independent. Only then, if there still remains a need to + * strip the private VID from packets, then a new ds->ops->get_private_vid() + * API shall be introduced to communicate to DSA what this VID is, which needs + * to be stripped here. + */ +static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) +{ + struct net_device *upper_dev; + u16 pvid, proto; + int err; - /* We already run under an RCU read-side critical section since - * we are called from netif_receive_skb_list_internal(). - */ - err = br_vlan_get_pvid_rcu(dev, &pvid); + err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - if (vid != pvid) - return skb; + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; + + if (vid != pvid || skb->vlan_proto != htons(proto)) + return; /* The sad part about attempting to untag from DSA is that we * don't know, unless we check, if the skb will end up in @@ -95,10 +130,50 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) * definitely keep the tag, to make sure it keeps working. */ upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); - if (upper_dev) + if (!upper_dev) + __vlan_hwaccel_clear_tag(skb); +} + +/** + * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path + * @skb: Pointer to socket buffer (packet) + * + * Receive path method for switches which cannot avoid tagging all packets + * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or + * ds->untag_vlan_aware_bridge_pvid is set to true. + * + * As a side effect of this method, any VLAN tag from the skb head is moved + * to hwaccel. + */ +static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_user_to_port(skb->dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + u16 vid; + + /* software untagging for standalone ports not yet necessary */ + if (!br) return skb; - __vlan_hwaccel_clear_tag(skb); + /* Move VLAN tag from data to hwaccel */ + if (!skb_vlan_tag_present(skb)) { + skb = skb_vlan_untag(skb); + if (!skb) + return NULL; + } + + if (!skb_vlan_tag_present(skb)) + return skb; + + vid = skb_vlan_tag_get_id(skb); + + if (br_vlan_enabled(br)) { + if (dp->ds->untag_vlan_aware_bridge_pvid) + dsa_software_untag_vlan_aware_bridge(skb, br, vid); + } else { + if (dp->ds->untag_bridge_pvid) + dsa_software_untag_vlan_unaware_bridge(skb, br, vid); + } return skb; } diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3..bf6608fc6be7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville" -/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class; - ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type); qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c index ae4b4b28a601..655ff5224ffa 100644 --- a/net/ethtool/cmis_fw_update.c +++ b/net/ethtool/cmis_fw_update.c @@ -35,7 +35,10 @@ struct cmis_cdb_fw_mng_features_rpl { __be16 resv7; }; -#define CMIS_CDB_FW_WRITE_MECHANISM_LPL 0x01 +enum cmis_cdb_fw_write_mechanism { + CMIS_CDB_FW_WRITE_MECHANISM_LPL = 0x01, + CMIS_CDB_FW_WRITE_MECHANISM_BOTH = 0x11, +}; static int cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb, @@ -64,7 +67,8 @@ cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb, } rpl = (struct cmis_cdb_fw_mng_features_rpl *)args.req.payload; - if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL)) { + if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL || + rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_BOTH)) { ethnl_module_fw_flash_ntf_err(dev, ntf_params, "Write LPL is not supported", NULL); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 983fee76f5cf..ae041f51cd2d 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -442,6 +442,9 @@ int __ethtool_get_link_ksettings(struct net_device *dev, if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + memset(link_ksettings, 0, sizeof(*link_ksettings)); return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } @@ -1331,13 +1334,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); const struct ethtool_ops *ops = dev->ethtool_ops; u32 dev_indir_size = 0, dev_key_size = 0, i; + u32 user_indir_len = 0, indir_bytes = 0; struct ethtool_rxfh_param rxfh_dev = {}; struct ethtool_rxfh_context *ctx = NULL; struct netlink_ext_ack *extack = NULL; struct ethtool_rxnfc rx_rings; struct ethtool_rxfh rxfh; bool locked = false; /* dev->ethtool->rss_lock taken */ - u32 indir_bytes = 0; bool create = false; u8 *rss_config; int ret; @@ -1369,23 +1372,25 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, return -EOPNOTSUPP; create = rxfh.rss_context == ETH_RXFH_CONTEXT_ALLOC; - /* If either indir, hash key or function is valid, proceed further. - * Must request at least one change: indir size, hash key, function - * or input transformation. - */ if ((rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE && rxfh.indir_size != dev_indir_size) || - (rxfh.key_size && (rxfh.key_size != dev_key_size)) || + (rxfh.key_size && rxfh.key_size != dev_key_size)) + return -EINVAL; + + /* Must request at least one change: indir size, hash key, function + * or input transformation. + * There's no need for any of it in case of context creation. + */ + if (!create && (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE && rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE && rxfh.input_xfrm == RXH_XFRM_NO_CHANGE)) return -EINVAL; - if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) - indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); + indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); - rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER); + rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER); if (!rss_config) return -ENOMEM; @@ -1400,6 +1405,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, */ if (rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) { + user_indir_len = indir_bytes; rxfh_dev.indir = (u32 *)rss_config; rxfh_dev.indir_size = dev_indir_size; ret = ethtool_copy_validate_indir(rxfh_dev.indir, @@ -1426,7 +1432,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh_dev.key_size = dev_key_size; rxfh_dev.key = rss_config + indir_bytes; if (copy_from_user(rxfh_dev.key, - useraddr + rss_cfg_offset + indir_bytes, + useraddr + rss_cfg_offset + user_indir_len, rxfh.key_size)) { ret = -EFAULT; goto out; @@ -1449,12 +1455,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, } if (ops->create_rxfh_context) { - u32 limit = ops->rxfh_max_context_id ?: U32_MAX; + u32 limit = ops->rxfh_max_num_contexts ?: U32_MAX; u32 ctx_id; /* driver uses new API, core allocates ID */ ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx, - XA_LIMIT(1, limit), GFP_KERNEL_ACCOUNT); + XA_LIMIT(1, limit - 1), + GFP_KERNEL_ACCOUNT); if (ret < 0) { kfree(ctx); goto out; @@ -1474,16 +1481,21 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh_dev.input_xfrm = rxfh.input_xfrm; if (rxfh.rss_context && ops->create_rxfh_context) { - if (create) + if (create) { ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev, extack); - else if (rxfh_dev.rss_delete) + /* Make sure driver populates defaults */ + WARN_ON_ONCE(!ret && !rxfh_dev.key && + !memchr_inv(ethtool_rxfh_context_key(ctx), + 0, ctx->key_size)); + } else if (rxfh_dev.rss_delete) { ret = ops->remove_rxfh_context(dev, ctx, rxfh.rss_context, extack); - else + } else { ret = ops->modify_rxfh_context(dev, ctx, &rxfh_dev, extack); + } } else { ret = ops->set_rxfh(dev, &rxfh_dev, extack); } @@ -1522,6 +1534,22 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, kfree(ctx); goto out; } + + /* Fetch the defaults for the old API, in the new API drivers + * should write defaults into ctx themselves. + */ + rxfh_dev.indir = (u32 *)rss_config; + rxfh_dev.indir_size = dev_indir_size; + + rxfh_dev.key = rss_config + indir_bytes; + rxfh_dev.key_size = dev_key_size; + + ret = ops->get_rxfh(dev, &rxfh_dev); + if (WARN_ON(ret)) { + xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context); + kfree(ctx); + goto out; + } } if (rxfh_dev.rss_delete) { WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context) != ctx); @@ -1530,12 +1558,14 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (rxfh_dev.indir) { for (i = 0; i < dev_indir_size; i++) ethtool_rxfh_context_indir(ctx)[i] = rxfh_dev.indir[i]; - ctx->indir_configured = 1; + ctx->indir_configured = + rxfh.indir_size && + rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE; } if (rxfh_dev.key) { memcpy(ethtool_rxfh_context_key(ctx), rxfh_dev.key, dev_key_size); - ctx->key_configured = 1; + ctx->key_configured = !!rxfh.key_size; } if (rxfh_dev.hfunc != ETH_RSS_HASH_NO_CHANGE) ctx->hfunc = rxfh_dev.hfunc; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 71679137eff2..5c4c4505ab9a 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -111,7 +111,8 @@ rss_reply_size(const struct ethnl_req_info *req_base, const struct rss_reply_data *data = RSS_REPDATA(reply_base); int len; - len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ + len = nla_total_size(sizeof(u32)) + /* _RSS_CONTEXT */ + nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */ nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */ nla_total_size(data->hkey_size); /* _RSS_HKEY */ @@ -124,6 +125,11 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + + if (request->rss_context && + nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context)) + return -EMSGSIZE; if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index e4cc6b78dcfc..049e22bdaafb 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -231,9 +231,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); - spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); - spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); @@ -314,14 +312,10 @@ static void send_hsr_supervision_frame(struct hsr_port *port, set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ - spin_lock_bh(&hsr->seqnr_lock); - if (hsr->prot_version > 0) { - hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); - hsr->sup_sequence_nr++; - } else { - hsr_stag->sequence_nr = htons(hsr->sequence_nr); - hsr->sequence_nr++; - } + if (hsr->prot_version > 0) + hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sup_sequence_nr)); + else + hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sequence_nr)); hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ @@ -343,13 +337,11 @@ static void send_hsr_supervision_frame(struct hsr_port *port, ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } - if (skb_put_padto(skb, ETH_ZLEN)) { - spin_unlock_bh(&hsr->seqnr_lock); + if (skb_put_padto(skb, ETH_ZLEN)) return; - } hsr_forward_skb(skb, port); - spin_unlock_bh(&hsr->seqnr_lock); + return; } @@ -374,9 +366,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ - spin_lock_bh(&hsr->seqnr_lock); - hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); - hsr->sup_sequence_nr++; + hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sup_sequence_nr)); hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); @@ -384,13 +374,10 @@ static void send_prp_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); - if (skb_put_padto(skb, ETH_ZLEN)) { - spin_unlock_bh(&hsr->seqnr_lock); + if (skb_put_padto(skb, ETH_ZLEN)) return; - } hsr_forward_skb(skb, master); - spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function @@ -427,6 +414,9 @@ static void hsr_proxy_announce(struct timer_list *t) * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); + if (!interlink) + goto done; + list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; @@ -441,6 +431,7 @@ static void hsr_proxy_announce(struct timer_list *t) mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } +done: rcu_read_unlock(); } @@ -621,11 +612,9 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], if (res < 0) return res; - spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ - hsr->sequence_nr = HSR_SEQNR_START; - hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; - hsr->interlink_sequence_nr = HSR_SEQNR_START; + atomic_set(&hsr->sequence_nr, HSR_SEQNR_START); + atomic_set(&hsr->sup_sequence_nr, HSR_SUP_SEQNR_START); timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index b38060246e62..6f63c8a775c4 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -599,9 +599,7 @@ static void handle_std_frame(struct sk_buff *skb, if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) { /* Sequence nr for the master/interlink node */ - lockdep_assert_held(&hsr->seqnr_lock); - frame->sequence_nr = hsr->sequence_nr; - hsr->sequence_nr++; + frame->sequence_nr = atomic_inc_return(&hsr->sequence_nr); } } diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index ab1f8d35d9dc..6f7bbf01f3e4 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -202,11 +202,9 @@ struct hsr_priv { struct timer_list prune_timer; struct timer_list prune_proxy_timer; int announce_count; - u16 sequence_nr; - u16 interlink_sequence_nr; /* Interlink port seq_nr */ - u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ + atomic_t sequence_nr; + atomic_t sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ enum hsr_version prot_version; /* Indicate if HSRv0, HSRv1 or PRPv1 */ - spinlock_t seqnr_lock; /* locking for sequence_nr */ spinlock_t list_lock; /* locking for node list */ struct hsr_proto_ops *proto_ops; #define PRP_LAN_ID 0x5 /* 0x1010 for A and 0x1011 for B. Bit 0 is set diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index f6ff0b61e08a..8aea4ff5f49e 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -163,7 +163,7 @@ static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN, hsr->sup_multicast_addr) || - nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr->sequence_nr)) + nla_put_u16(skb, IFLA_HSR_SEQ_NR, atomic_read(&hsr->sequence_nr))) goto nla_put_failure; if (hsr->prot_version == PRP_V1) proto = HSR_PROTOCOL_PRP; diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index 0abbc413e0fe..3e30745e2c09 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -50,7 +50,7 @@ struct fou_net { static inline struct fou *fou_from_sock(struct sock *sk) { - return sk->sk_user_data; + return rcu_dereference_sk_user_data(sk); } static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len) @@ -233,9 +233,15 @@ static struct sk_buff *fou_gro_receive(struct sock *sk, struct sk_buff *skb) { const struct net_offload __rcu **offloads; - u8 proto = fou_from_sock(sk)->protocol; + struct fou *fou = fou_from_sock(sk); const struct net_offload *ops; struct sk_buff *pp = NULL; + u8 proto; + + if (!fou) + goto out; + + proto = fou->protocol; /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel @@ -263,14 +269,24 @@ static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { const struct net_offload __rcu **offloads; - u8 proto = fou_from_sock(sk)->protocol; + struct fou *fou = fou_from_sock(sk); const struct net_offload *ops; - int err = -ENOSYS; + u8 proto; + int err; + + if (!fou) { + err = -ENOENT; + goto out; + } + + proto = fou->protocol; offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); - if (WARN_ON(!ops || !ops->callbacks.gro_complete)) + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) { + err = -ENOSYS; goto out; + } err = ops->callbacks.gro_complete(skb, nhoff); @@ -322,6 +338,9 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, skb_gro_remcsum_init(&grc); + if (!fou) + goto out; + off = skb_gro_offset(skb); len = off + sizeof(*guehdr); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 4d42d0756fd7..a5db7c67d61b 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -145,25 +145,27 @@ static struct pernet_operations iptable_nat_net_ops = { static int __init iptable_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv4_table, - iptable_nat_table_init); + int ret; + /* net->gen->ptr[iptable_nat_net_id] must be allocated + * before calling iptable_nat_table_init(). + */ + ret = register_pernet_subsys(&iptable_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&iptable_nat_net_ops); - if (ret < 0) { - xt_unregister_template(&nf_nat_ipv4_table); - return ret; - } + ret = xt_register_template(&nf_nat_ipv4_table, + iptable_nat_table_init); + if (ret < 0) + unregister_pernet_subsys(&iptable_nat_net_ops); return ret; } static void __exit iptable_nat_exit(void) { - unregister_pernet_subsys(&iptable_nat_net_ops); xt_unregister_template(&nf_nat_ipv4_table); + unregister_pernet_subsys(&iptable_nat_net_ops); } module_init(iptable_nat_init); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e03a342c9162..831a18dc7aa6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4637,6 +4637,13 @@ int tcp_abort(struct sock *sk, int err) /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); + /* Avoid closing the same socket twice. */ + if (sk->sk_state == TCP_CLOSE) { + if (!has_current_bpf_ctx()) + release_sock(sk); + return -ENOENT; + } + if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); @@ -4646,16 +4653,13 @@ int tcp_abort(struct sock *sk, int err) local_bh_disable(); bh_lock_sock(sk); - if (!sock_flag(sk, SOCK_DEAD)) { - if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); - tcp_done_with_error(sk, err); - } + if (tcp_need_reset(sk->sk_state)) + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); + tcp_done_with_error(sk, err); bh_unlock_sock(sk); local_bh_enable(); - tcp_write_queue_purge(sk); if (!has_current_bpf_ctx()) release_sock(sk); return 0; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 85531437890c..db6516092daf 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -267,32 +267,49 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head) kfree_sensitive(key); } -void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +static void tcp_ao_info_free_rcu(struct rcu_head *head) { - struct tcp_ao_info *ao; + struct tcp_ao_info *ao = container_of(head, struct tcp_ao_info, rcu); struct tcp_ao_key *key; struct hlist_node *n; + hlist_for_each_entry_safe(key, n, &ao->head, node) { + hlist_del(&key->node); + tcp_sigpool_release(key->tcp_sigpool_id); + kfree_sensitive(key); + } + kfree(ao); + static_branch_slow_dec_deferred(&tcp_ao_needed); +} + +static void tcp_ao_sk_omem_free(struct sock *sk, struct tcp_ao_info *ao) +{ + size_t total_ao_sk_mem = 0; + struct tcp_ao_key *key; + + hlist_for_each_entry(key, &ao->head, node) + total_ao_sk_mem += tcp_ao_sizeof_key(key); + atomic_sub(total_ao_sk_mem, &sk->sk_omem_alloc); +} + +void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +{ + struct tcp_ao_info *ao; + if (twsk) { ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1); - tcp_twsk(sk)->ao_info = NULL; + rcu_assign_pointer(tcp_twsk(sk)->ao_info, NULL); } else { ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1); - tcp_sk(sk)->ao_info = NULL; + rcu_assign_pointer(tcp_sk(sk)->ao_info, NULL); } if (!ao || !refcount_dec_and_test(&ao->refcnt)) return; - hlist_for_each_entry_safe(key, n, &ao->head, node) { - hlist_del_rcu(&key->node); - if (!twsk) - atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); - call_rcu(&key->rcu, tcp_ao_key_free_rcu); - } - - kfree_rcu(ao, rcu); - static_branch_slow_dec_deferred(&tcp_ao_needed); + if (!twsk) + tcp_ao_sk_omem_free(sk, ao); + call_rcu(&ao->rcu, tcp_ao_info_free_rcu); } void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 53b0d62fd2c2..fe6178715ba0 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -577,7 +577,7 @@ out_err: err = sk_stream_error(sk, msg->msg_flags, err); release_sock(sk); sk_psock_put(sk, psock); - return copied ? copied : err; + return copied > 0 ? copied : err; } enum { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 454362e359da..e37488d3453f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ if (unlikely(len != icsk->icsk_ack.rcv_mss)) { u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE; + u8 old_ratio = tcp_sk(sk)->scaling_ratio; do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; + + if (old_ratio != tcp_sk(sk)->scaling_ratio) + WRITE_ONCE(tcp_sk(sk)->window_clamp, + tcp_win_from_space(sk, sk->sk_rcvbuf)); } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd17f25ff288..a4e510846905 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -97,6 +97,8 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; +static DEFINE_MUTEX(tcp_exit_batch_mutex); + static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -3514,6 +3516,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; + /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work + * and failed setup_net error unwinding path are serialized. + * + * tcp_twsk_purge() handles twsk in any dead netns, not just those in + * net_exit_list, the thread that dismantles a particular twsk must + * do so without other thread progressing to refcount_dec_and_test() of + * tcp_death_row.tw_refcount. + */ + mutex_lock(&tcp_exit_batch_mutex); + tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { @@ -3521,6 +3533,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); } + + mutex_unlock(&tcp_exit_batch_mutex); } static struct pernet_operations __net_initdata tcp_sk_ops = { diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 4b791e74529e..e4ad3311e148 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (thlen < sizeof(*th)) goto out; + if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) + goto out; + if (!pskb_may_pull(skb, thlen)) goto out; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index aa2e0a28ca61..d842303587af 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,17 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) + return ERR_PTR(-EINVAL); + + /* We don't know if egress device can segment and checksum the packet + * when IPv6 extension headers are present. Fall back to software GSO. + */ + if (gso_skb->ip_summed != CHECKSUM_PARTIAL) + features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h index ad5f6f6ba333..85b92917849b 100644 --- a/net/ipv6/ila/ila.h +++ b/net/ipv6/ila/ila.h @@ -108,6 +108,7 @@ int ila_lwt_init(void); void ila_lwt_fini(void); int ila_xlat_init_net(struct net *net); +void ila_xlat_pre_exit_net(struct net *net); void ila_xlat_exit_net(struct net *net); int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c index 69caed07315f..976c78efbae1 100644 --- a/net/ipv6/ila/ila_main.c +++ b/net/ipv6/ila/ila_main.c @@ -71,6 +71,11 @@ ila_xlat_init_fail: return err; } +static __net_exit void ila_pre_exit_net(struct net *net) +{ + ila_xlat_pre_exit_net(net); +} + static __net_exit void ila_exit_net(struct net *net) { ila_xlat_exit_net(net); @@ -78,6 +83,7 @@ static __net_exit void ila_exit_net(struct net *net) static struct pernet_operations ila_net_ops = { .init = ila_init_net, + .pre_exit = ila_pre_exit_net, .exit = ila_exit_net, .id = &ila_net_id, .size = sizeof(struct ila_net), diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 67e8c9440977..534a4498e280 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -619,6 +619,15 @@ int ila_xlat_init_net(struct net *net) return 0; } +void ila_xlat_pre_exit_net(struct net *net) +{ + struct ila_net *ilan = net_generic(net, ila_net_id); + + if (ilan->xlat.hooks_registered) + nf_unregister_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); +} + void ila_xlat_exit_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); @@ -626,10 +635,6 @@ void ila_xlat_exit_net(struct net *net) rhashtable_free_and_destroy(&ilan->xlat.rhash_table, ila_free_cb, NULL); free_bucket_spinlocks(ilan->xlat.locks); - - if (ilan->xlat.hooks_registered) - nf_unregister_net_hooks(net, ila_nf_hook_ops, - ARRAY_SIZE(ila_nf_hook_ops)); } static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ab504d31f0cd..f26841f1490f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOMEM; } + rcu_read_unlock(); } hdr = ipv6_hdr(skb); @@ -283,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOBUFS; } + rcu_read_unlock(); } if (opt) { @@ -1956,6 +1964,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; + rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) @@ -1965,6 +1974,7 @@ int ip6_send_skb(struct sk_buff *skb) IPSTATS_MIB_OUTDISCARDS); } + rcu_read_unlock(); return err; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9dee0c127955..87dfb565a9f8 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1507,7 +1507,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { - dev->hard_header_len = tdev->hard_header_len + t_hlen; + dev->needed_headroom = tdev->hard_header_len + + tdev->needed_headroom + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; @@ -1731,7 +1732,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); + int t_hlen; + t_hlen = tnl->hlen + sizeof(struct ipv6hdr); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; @@ -1740,10 +1743,10 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { - if (new_mtu > IP6_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } else { - if (new_mtu > IP_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); @@ -1887,12 +1890,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t_hlen = t->hlen + sizeof(struct ipv6hdr); dev->type = ARPHRD_TUNNEL6; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; + dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 70a0b2ad6bd7..b8eec1b6cc2c 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -227,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { + bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; @@ -262,22 +263,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, break; #endif default: - if (ndisc_is_useropt(dev, nd_opt)) { - ndopts->nd_useropts_end = nd_opt; - if (!ndopts->nd_useropts) - ndopts->nd_useropts = nd_opt; - } else { - /* - * Unknown options must be silently ignored, - * to accommodate future extension to the - * protocol. - */ - ND_PRINTK(2, notice, - "%s: ignored unsupported option; type=%d, len=%d\n", - __func__, - nd_opt->nd_opt_type, - nd_opt->nd_opt_len); - } + unknown = true; + } + if (ndisc_is_useropt(dev, nd_opt)) { + ndopts->nd_useropts_end = nd_opt; + if (!ndopts->nd_useropts) + ndopts->nd_useropts = nd_opt; + } else if (unknown) { + /* + * Unknown options must be silently ignored, + * to accommodate future extension to the + * protocol. + */ + ND_PRINTK(2, notice, + "%s: ignored unsupported option; type=%d, len=%d\n", + __func__, + nd_opt->nd_opt_type, + nd_opt->nd_opt_len); } next_opt: opt_len -= l; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 52cf104e3478..e119d4f090cc 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -147,23 +147,27 @@ static struct pernet_operations ip6table_nat_net_ops = { static int __init ip6table_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv6_table, - ip6table_nat_table_init); + int ret; + /* net->gen->ptr[ip6table_nat_net_id] must be allocated + * before calling ip6t_nat_register_lookups(). + */ + ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&ip6table_nat_net_ops); + ret = xt_register_template(&nf_nat_ipv6_table, + ip6table_nat_table_init); if (ret) - xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); return ret; } static void __exit ip6table_nat_exit(void) { - unregister_pernet_subsys(&ip6table_nat_net_ops); xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); } module_init(ip6table_nat_init); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6f0844c9315d..4120e67a8ce6 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, }; struct inet_frag_queue *q; + if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))) + key.iif = 0; + q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index c3b0b610b0aa..c00323fa9eb6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -335,8 +335,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data) struct iucv_sock *iucv = iucv_sk(sk); struct iucv_path *path = iucv->path; - if (iucv->path) { - iucv->path = NULL; + /* Whoever resets the path pointer, must sever and free it. */ + if (xchg(&iucv->path, NULL)) { if (with_user_data) { low_nmcpy(user_data, iucv->src_name); high_nmcpy(user_data, iucv->dst_name); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 1e42e13ad24e..d3e9efab7f4b 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -86,13 +86,15 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs, { struct device *dev; va_list vargs; + char buf[20]; int rc; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) goto out_error; va_start(vargs, fmt); - rc = dev_set_name(dev, fmt, vargs); + vsnprintf(buf, sizeof(buf), fmt, vargs); + rc = dev_set_name(dev, "%s", buf); va_end(vargs); if (rc) goto out_error; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 2f191e50d4fc..d4118c796290 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -926,6 +927,7 @@ partial_message: KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -951,6 +953,7 @@ out_error: sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index c80ab3f26084..2e86f520f799 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -86,6 +86,11 @@ /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 +#define L2TP_DEPTH_NESTING 2 +#if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING +#error "L2TP requires its own lockdep subclass" +#endif + /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { @@ -1124,7 +1129,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); - bh_lock_sock_nested(sk); + /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by + * nested socket calls on the same lockdep socket class. This can + * happen when data from a user socket is routed over l2tp, which uses + * another userspace socket. + */ + spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); + if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; @@ -1176,7 +1187,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: - bh_unlock_sock(sk); + spin_unlock(&sk->sk_lock.slock); return ret; } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 85cb71de370f..b02b84ce2130 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -114,7 +114,7 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, /* apply all changes now - no failures allowed */ - if (monitor_sdata) + if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { @@ -3053,6 +3053,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { + if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return -EOPNOTSUPP; + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!sdata) @@ -3115,7 +3118,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, if (has_monitor) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 4779a18ab75d..f9526bbc3633 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -6664,7 +6664,7 @@ static bool ieee80211_mgd_ssid_mismatch(struct ieee80211_sub_if_data *sdata, return true; /* hidden SSID: zeroed out */ - if (memcmp(elems->ssid, zero_ssid, elems->ssid_len)) + if (!memcmp(elems->ssid, zero_ssid, elems->ssid_len)) return false; return memcmp(elems->ssid, cfg->ssid, cfg->ssid_len); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 72a9ba8bc5fd..bca7b341dd77 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1768,7 +1768,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local, break; } sdata = rcu_dereference(local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; @@ -3957,7 +3957,8 @@ begin: break; } tx.sdata = rcu_dereference(local->monitor_sdata); - if (tx.sdata) { + if (tx.sdata && + ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &tx.sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; @@ -5347,8 +5348,10 @@ ieee80211_beacon_get_ap(struct ieee80211_hw *hw, if (beacon->tail) skb_put_data(skb, beacon->tail, beacon->tail_len); - if (ieee80211_beacon_protect(skb, local, sdata, link) < 0) + if (ieee80211_beacon_protect(skb, local, sdata, link) < 0) { + dev_kfree_skb(skb); return NULL; + } ieee80211_beacon_get_finish(hw, vif, link, offs, beacon, skb, chanctx_conf, csa_off_base); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index ced19ce7c51a..c7ad9bc5973a 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -776,7 +776,7 @@ static void __iterate_interfaces(struct ieee80211_local *local, sdata = rcu_dereference_check(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx) || lockdep_is_held(&local->hw.wiphy->mtx)); - if (sdata && + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) && (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 77e5dd422258..8551dab1d1e6 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test) skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2); - KUNIT_EXPECT_EQ(test, skb->len, 1); + KUNIT_EXPECT_EQ(test, skb2->len, 1); skb_free_datagram(sock->sk, skb2); diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 3ae46b545d2c..2d3efb405437 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk) nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */ - nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ + nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */ diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index ad28da655f8b..a29ff901df75 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -68,12 +68,12 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo skb = skb_peek_tail(&sk->sk_receive_queue); if (skb) { WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); - pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk, + pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk, MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq, MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq); MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq; MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq; } - pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq); + pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq); } diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index c30405e76833..7884217f33eb 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), + SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), + SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 2704afd0dfe4..66aa67f49d03 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -14,7 +14,9 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */ + MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8e8dcfbc2993..370c3836b771 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -117,7 +117,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } - pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u", + pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u\n", version, flags, opsize, mp_opt->sndr_key, mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum); break; @@ -131,7 +131,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 4; mp_opt->nonce = get_unaligned_be32(ptr); ptr += 4; - pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u", + pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u\n", mp_opt->backup, mp_opt->join_id, mp_opt->token, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) { @@ -142,19 +142,19 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 8; mp_opt->nonce = get_unaligned_be32(ptr); ptr += 4; - pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u", + pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u\n", mp_opt->backup, mp_opt->join_id, mp_opt->thmac, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK; ptr += 2; memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); - pr_debug("MP_JOIN hmac"); + pr_debug("MP_JOIN hmac\n"); } break; case MPTCPOPT_DSS: - pr_debug("DSS"); + pr_debug("DSS\n"); ptr++; /* we must clear 'mpc_map' be able to detect MP_CAPABLE @@ -169,7 +169,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0; mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK); - pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d", + pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n", mp_opt->data_fin, mp_opt->dsn64, mp_opt->use_map, mp_opt->ack64, mp_opt->use_ack); @@ -207,7 +207,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 4; } - pr_debug("data_ack=%llu", mp_opt->data_ack); + pr_debug("data_ack=%llu\n", mp_opt->data_ack); } if (mp_opt->use_map) { @@ -231,7 +231,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; } - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n", mp_opt->data_seq, mp_opt->subflow_seq, mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD), mp_opt->csum); @@ -293,7 +293,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->ahmac = get_unaligned_be64(ptr); ptr += 8; } - pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d", + pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d\n", (mp_opt->addr.family == AF_INET6) ? "6" : "", mp_opt->addr.id, mp_opt->ahmac, mp_opt->echo, ntohs(mp_opt->addr.port)); break; @@ -309,7 +309,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE; for (i = 0; i < mp_opt->rm_list.nr; i++) mp_opt->rm_list.ids[i] = *ptr++; - pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr); + pr_debug("RM_ADDR: rm_list_nr=%d\n", mp_opt->rm_list.nr); break; case MPTCPOPT_MP_PRIO: @@ -318,7 +318,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_PRIO; mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP; - pr_debug("MP_PRIO: prio=%d", mp_opt->backup); + pr_debug("MP_PRIO: prio=%d\n", mp_opt->backup); break; case MPTCPOPT_MP_FASTCLOSE: @@ -329,7 +329,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE; - pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key); + pr_debug("MP_FASTCLOSE: recv_key=%llu\n", mp_opt->rcvr_key); break; case MPTCPOPT_RST: @@ -343,7 +343,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, flags = *ptr++; mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT; mp_opt->reset_reason = *ptr; - pr_debug("MP_RST: transient=%u reason=%u", + pr_debug("MP_RST: transient=%u reason=%u\n", mp_opt->reset_transient, mp_opt->reset_reason); break; @@ -354,7 +354,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; mp_opt->suboptions |= OPTION_MPTCP_FAIL; mp_opt->fail_seq = get_unaligned_be64(ptr); - pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq); + pr_debug("MP_FAIL: data_seq=%llu\n", mp_opt->fail_seq); break; default: @@ -417,7 +417,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { - pr_debug("remote_token=%u, nonce=%u", subflow->remote_token, + pr_debug("remote_token=%u, nonce=%u\n", subflow->remote_token, subflow->local_nonce); opts->suboptions = OPTION_MPTCP_MPJ_SYN; opts->join_id = subflow->local_id; @@ -500,7 +500,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPC_ACK; } - pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d", + pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d\n", subflow, subflow->local_key, subflow->remote_key, data_len); @@ -509,7 +509,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, opts->suboptions = OPTION_MPTCP_MPJ_ACK; memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN); *size = TCPOLEN_MPTCP_MPJ_ACK; - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); /* we can use the full delegate action helper only from BH context * If we are in process context - sk is flushing the backlog at @@ -675,7 +675,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * *size = len; if (drop_other_suboptions) { - pr_debug("drop other suboptions"); + pr_debug("drop other suboptions\n"); opts->suboptions = 0; /* note that e.g. DSS could have written into the memory @@ -695,7 +695,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * } else { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); } - pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d", + pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n", opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port)); return true; @@ -726,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk, opts->rm_list = rm_list; for (i = 0; i < opts->rm_list.nr; i++) - pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]); + pr_debug("rm_list_ids[%d]=%d\n", i, opts->rm_list.ids[i]); MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr); return true; } @@ -752,7 +752,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, opts->suboptions |= OPTION_MPTCP_PRIO; opts->backup = subflow->request_bkup; - pr_debug("prio=%d", opts->backup); + pr_debug("prio=%d\n", opts->backup); return true; } @@ -794,7 +794,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk, opts->suboptions |= OPTION_MPTCP_FASTCLOSE; opts->rcvr_key = READ_ONCE(msk->remote_key); - pr_debug("FASTCLOSE key=%llu", opts->rcvr_key); + pr_debug("FASTCLOSE key=%llu\n", opts->rcvr_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); return true; } @@ -816,7 +816,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk, opts->suboptions |= OPTION_MPTCP_FAIL; opts->fail_seq = subflow->map_seq; - pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq); + pr_debug("MP_FAIL fail_seq=%llu\n", opts->fail_seq); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX); return true; @@ -904,16 +904,16 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, opts->csum_reqd = subflow_req->csum_reqd; opts->allow_join_id0 = subflow_req->allow_join_id0; *size = TCPOLEN_MPTCP_MPC_SYNACK; - pr_debug("subflow_req=%p, local_key=%llu", + pr_debug("subflow_req=%p, local_key=%llu\n", subflow_req, subflow_req->local_key); return true; } else if (subflow_req->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_SYNACK; - opts->backup = subflow_req->backup; + opts->backup = subflow_req->request_bkup; opts->join_id = subflow_req->local_id; opts->thmac = subflow_req->thmac; opts->nonce = subflow_req->local_nonce; - pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u", + pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u\n", subflow_req, opts->backup, opts->join_id, opts->thmac, opts->nonce); *size = TCPOLEN_MPTCP_MPJ_SYNACK; @@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (subflow->remote_key_valid && (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || - ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) { + ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && + (!mp_opt->echo || subflow->mp_join)))) { /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 55406720c607..37f6dbcd8434 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -19,7 +19,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, { u8 add_addr = READ_ONCE(msk->pm.addr_signal); - pr_debug("msk=%p, local_id=%d, echo=%d", msk, addr->id, echo); + pr_debug("msk=%p, local_id=%d, echo=%d\n", msk, addr->id, echo); lockdep_assert_held(&msk->pm.lock); @@ -45,7 +45,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ { u8 rm_addr = READ_ONCE(msk->pm.addr_signal); - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); + pr_debug("msk=%p, rm_list_nr=%d\n", msk, rm_list->nr); if (rm_addr) { MPTCP_ADD_STATS(sock_net((struct sock *)msk), @@ -60,23 +60,13 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ return 0; } -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) -{ - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); - - spin_lock_bh(&msk->pm.lock); - mptcp_pm_nl_rm_subflow_received(msk, rm_list); - spin_unlock_bh(&msk->pm.lock); - return 0; -} - /* path manager event handlers */ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side) { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p, token=%u side=%d", msk, READ_ONCE(msk->token), server_side); + pr_debug("msk=%p, token=%u side=%d\n", msk, READ_ONCE(msk->token), server_side); WRITE_ONCE(pm->server_side, server_side); mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC); @@ -100,7 +90,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) subflows_max = mptcp_pm_get_subflows_max(msk); - pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows, + pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk, pm->subflows, subflows_max, READ_ONCE(pm->accept_subflow)); /* try to avoid acquiring the lock below */ @@ -124,7 +114,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) static bool mptcp_pm_schedule_work(struct mptcp_sock *msk, enum mptcp_pm_status new_status) { - pr_debug("msk=%p status=%x new=%lx", msk, msk->pm.status, + pr_debug("msk=%p status=%x new=%lx\n", msk, msk->pm.status, BIT(new_status)); if (msk->pm.status & BIT(new_status)) return false; @@ -139,7 +129,7 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk) struct mptcp_pm_data *pm = &msk->pm; bool announce = false; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&pm->lock); @@ -163,14 +153,14 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk) void mptcp_pm_connection_closed(struct mptcp_sock *msk) { - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); } void mptcp_pm_subflow_established(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (!READ_ONCE(pm->work_pending)) return; @@ -222,7 +212,7 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id, + pr_debug("msk=%p remote_id=%d accept=%d\n", msk, addr->id, READ_ONCE(pm->accept_addr)); mptcp_event_addr_announced(ssk, addr); @@ -236,7 +226,9 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, } else { __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP); } - } else if (!READ_ONCE(pm->accept_addr)) { + /* id0 should not have a different address */ + } else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) || + (addr->id > 0 && !READ_ONCE(pm->accept_addr))) { mptcp_pm_announce_addr(msk, addr, true); mptcp_pm_add_addr_send_ack(msk); } else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) { @@ -253,7 +245,7 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&pm->lock); @@ -277,7 +269,7 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, struct mptcp_pm_data *pm = &msk->pm; u8 i; - pr_debug("msk=%p remote_ids_nr=%d", msk, rm_list->nr); + pr_debug("msk=%p remote_ids_nr=%d\n", msk, rm_list->nr); for (i = 0; i < rm_list->nr; i++) mptcp_event_addr_removed(msk, rm_list->ids[i]); @@ -309,19 +301,19 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - pr_debug("fail_seq=%llu", fail_seq); + pr_debug("fail_seq=%llu\n", fail_seq); if (!READ_ONCE(msk->allow_infinite_fallback)) return; if (!subflow->fail_tout) { - pr_debug("send MP_FAIL response and infinite map"); + pr_debug("send MP_FAIL response and infinite map\n"); subflow->send_mp_fail = 1; subflow->send_infinite_map = 1; tcp_send_ack(sk); } else { - pr_debug("MP_FAIL response received"); + pr_debug("MP_FAIL response received\n"); WRITE_ONCE(subflow->fail_tout, 0); } } @@ -426,15 +418,24 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, &skc_local); } +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc) +{ + struct mptcp_addr_info skc_local; + + mptcp_local_address((struct sock_common *)skc, &skc_local); + + if (mptcp_pm_is_userspace(msk)) + return mptcp_userspace_pm_is_backup(msk, &skc_local); + + return mptcp_pm_nl_is_backup(msk, &skc_local); +} + int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) { *flags = 0; *ifindex = 0; - if (!id) - return 0; - if (mptcp_pm_is_userspace(msk)) return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index ea9e5817b9e9..ad935d34c973 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -130,12 +130,15 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; - struct sock_common *skc; list_for_each_entry(subflow, list, node) { - skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - remote_address(skc, &cur); + if (!((1 << inet_sk_state_load(ssk)) & + (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV))) + continue; + + remote_address((struct sock_common *)ssk, &cur); if (mptcp_addresses_equal(&cur, daddr, daddr->port)) return true; } @@ -143,11 +146,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, return false; } -static struct mptcp_pm_addr_entry * +static bool select_local_address(const struct pm_nl_pernet *pernet, - const struct mptcp_sock *msk) + const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; msk_owned_by_me(msk); @@ -159,17 +164,21 @@ select_local_address(const struct pm_nl_pernet *pernet, if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; - ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } -static struct mptcp_pm_addr_entry * -select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) +static bool +select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; rcu_read_lock(); /* do not keep any additional per socket state, just signal @@ -184,11 +193,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue; - ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) @@ -279,7 +290,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (!msk) return; @@ -298,7 +309,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) spin_lock_bh(&msk->pm.lock); if (!mptcp_pm_should_add_signal_addr(msk)) { - pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id); + pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id); mptcp_pm_announce_addr(msk, &entry->addr, false); mptcp_pm_add_addr_send_ack(msk); entry->retrans_times++; @@ -323,15 +334,21 @@ 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; spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); - if (entry && (!check_id || entry->addr.id == addr->id)) + if (entry && (!check_id || entry->addr.id == addr->id)) { entry->retrans_times = ADD_ADDR_RETRANS_MAX; + add_timer = &entry->add_timer; + } + if (!check_id && entry) + list_del(&entry->list); spin_unlock_bh(&msk->pm.lock); - if (entry && (!check_id || entry->addr.id == addr->id)) - sk_stop_timer_sync(sk, &entry->add_timer); + /* no lock, because sk_stop_timer_sync() is calling del_timer_sync() */ + if (add_timer) + sk_stop_timer_sync(sk, add_timer); return entry; } @@ -348,7 +365,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (add_entry) { - if (mptcp_pm_is_kernel(msk)) + if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; sk_reset_timer(sk, &add_entry->add_timer, @@ -379,7 +396,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) struct sock *sk = (struct sock *)msk; LIST_HEAD(free_list); - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&msk->pm.lock); list_splice_init(&msk->pm.anno_list, &free_list); @@ -465,13 +482,12 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow; - pr_debug("send ack for %s", + pr_debug("send ack for %s\n", prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr")); slow = lock_sock_fast(ssk); if (prio) { subflow->send_mp_prio = 1; - subflow->backup = backup; subflow->request_bkup = backup; } @@ -514,8 +530,9 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - struct mptcp_pm_addr_entry *local; + struct mptcp_pm_addr_entry local; unsigned int add_addr_signal_max; + bool signal_and_subflow = false; unsigned int local_addr_max; struct pm_nl_pernet *pernet; unsigned int subflows_max; @@ -556,8 +573,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check first for announce */ if (msk->pm.add_addr_signaled < add_addr_signal_max) { - local = select_signal_address(pernet, msk); - /* due to racing events on both ends we can reach here while * previous add address is still running: if we invoke now * mptcp_pm_announce_addr(), that will fail and the @@ -568,16 +583,30 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; - if (local) { - if (mptcp_pm_alloc_anno_list(msk, &local->addr)) { - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr, false); - mptcp_pm_nl_addr_send_ack(msk); - } - } + if (!select_signal_address(pernet, msk, &local)) + goto subflow; + + /* If the alloc fails, we are on memory pressure, not worth + * continuing, and trying to create subflows. + */ + if (!mptcp_pm_alloc_anno_list(msk, &local.addr)) + return; + + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled++; + + /* Special case for ID0: set the correct ID */ + if (local.addr.id == msk->mpc_endpoint_id) + local.addr.id = 0; + + mptcp_pm_announce_addr(msk, &local.addr, false); + mptcp_pm_nl_addr_send_ack(msk); + + if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + signal_and_subflow = true; } +subflow: /* check if should create a new subflow */ while (msk->pm.local_addr_used < local_addr_max && msk->pm.subflows < subflows_max) { @@ -585,21 +614,28 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) bool fullmesh; int i, nr; - local = select_local_address(pernet, msk); - if (!local) + if (signal_and_subflow) + signal_and_subflow = false; + else if (!select_local_address(pernet, msk, &local)) break; - fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); + fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH); - msk->pm.local_addr_used++; - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + + /* Special case for ID0: set the correct ID */ + if (local.addr.id == msk->mpc_endpoint_id) + local.addr.id = 0; + else /* local_addr_used is not decr for ID 0 */ + msk->pm.local_addr_used++; + + nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs); if (nr == 0) continue; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - __mptcp_subflow_connect(sk, &local->addr, &addrs[i]); + __mptcp_subflow_connect(sk, &local.addr, &addrs[i]); spin_lock_bh(&msk->pm.lock); } mptcp_pm_nl_check_work_pending(msk); @@ -624,6 +660,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; + struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; unsigned int subflows_max; int i = 0; @@ -631,6 +668,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, pernet = pm_nl_get_pernet_from_msk(msk); subflows_max = mptcp_pm_get_subflows_max(msk); + mptcp_local_address((struct sock_common *)msk, &mpc_addr); + rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) @@ -641,7 +680,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, if (msk->pm.subflows < subflows_max) { msk->pm.subflows++; - addrs[i++] = entry->addr; + addrs[i] = entry->addr; + + /* Special case for ID0: set the correct ID */ + if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port)) + addrs[i].id = 0; + + i++; } } rcu_read_unlock(); @@ -683,7 +728,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); subflows_max = mptcp_pm_get_subflows_max(msk); - pr_debug("accepted %d:%d remote family %d", + pr_debug("accepted %d:%d remote family %d\n", msk->pm.add_addr_accepted, add_addr_accept_max, msk->pm.remote.family); @@ -712,13 +757,24 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) spin_lock_bh(&msk->pm.lock); if (sf_created) { - msk->pm.add_addr_accepted++; + /* add_addr_accepted is not decr for ID 0 */ + if (remote.id) + msk->pm.add_addr_accepted++; if (msk->pm.add_addr_accepted >= add_addr_accept_max || msk->pm.subflows >= subflows_max) WRITE_ONCE(msk->pm.accept_addr, false); } } +bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk, + const struct mptcp_addr_info *remote) +{ + struct mptcp_addr_info mpc_remote; + + remote_address((struct sock_common *)msk, &mpc_remote); + return mptcp_addresses_equal(&mpc_remote, remote, remote->port); +} + void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; @@ -730,9 +786,12 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) !mptcp_pm_should_rm_signal(msk)) return; - subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node); - if (subflow) - mptcp_pm_send_ack(msk, subflow, false, false); + mptcp_for_each_subflow(msk, subflow) { + if (__mptcp_subflow_active(subflow)) { + mptcp_pm_send_ack(msk, subflow, false, false); + break; + } + } } int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, @@ -742,7 +801,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, { struct mptcp_subflow_context *subflow; - pr_debug("bkup=%d", bkup); + pr_debug("bkup=%d\n", bkup); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -765,11 +824,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, return -EINVAL; } -static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id) -{ - return local_id == id || (!local_id && msk->mpc_endpoint_id == id); -} - static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list, enum linux_mptcp_mib_field rm_type) @@ -778,7 +832,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, struct sock *sk = (struct sock *)msk; u8 i; - pr_debug("%s rm_list_nr %d", + pr_debug("%s rm_list_nr %d\n", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr); msk_owned_by_me(msk); @@ -802,12 +856,14 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, int how = RCV_SHUTDOWN | SEND_SHUTDOWN; u8 id = subflow_get_local_id(subflow); + if (inet_sk_state_load(ssk) == TCP_CLOSE) + continue; if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; - if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) + if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id) continue; - pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", + pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); @@ -817,25 +873,27 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock); - removed = true; + removed |= subflow->request_join; if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } - if (rm_type == MPTCP_MIB_RMSUBFLOW) - __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap); - else if (rm_type == MPTCP_MIB_RMADDR) + + if (rm_type == MPTCP_MIB_RMADDR) __MPTCP_INC_STATS(sock_net(sk), rm_type); + if (!removed) continue; if (!mptcp_pm_is_kernel(msk)) continue; - if (rm_type == MPTCP_MIB_RMADDR) { - msk->pm.add_addr_accepted--; - WRITE_ONCE(msk->pm.accept_addr, true); - } else if (rm_type == MPTCP_MIB_RMSUBFLOW) { - msk->pm.local_addr_used--; + if (rm_type == MPTCP_MIB_RMADDR && rm_id && + !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + /* Note: if the subflow has been closed before, this + * add_addr_accepted counter will not be decremented. + */ + if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk)) + WRITE_ONCE(msk->pm.accept_addr, true); } } } @@ -845,8 +903,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR); } -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list) +static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW); } @@ -862,7 +920,7 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk) spin_lock_bh(&msk->pm.lock); - pr_debug("msk=%p status=%x", msk, pm->status); + pr_debug("msk=%p status=%x\n", msk, pm->status); if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); mptcp_pm_nl_add_addr_received(msk); @@ -1102,6 +1160,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc return ret; } +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) +{ + struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + rcu_read_unlock(); + + return backup; +} + #define MPTCP_PM_CMD_GRP_OFFSET 0 #define MPTCP_PM_EV_GRP_OFFSET 1 @@ -1262,20 +1338,27 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info) return pm_nl_get_pernet(genl_info_net(info)); } -static int mptcp_nl_add_subflow_or_signal_addr(struct net *net) +static int mptcp_nl_add_subflow_or_signal_addr(struct net *net, + struct mptcp_addr_info *addr) { struct mptcp_sock *msk; long s_slot = 0, s_num = 0; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; + struct mptcp_addr_info mpc_addr; if (!READ_ONCE(msk->fully_established) || mptcp_pm_is_userspace(msk)) goto next; + /* if the endp linked to the init sf is re-added with a != ID */ + mptcp_local_address((struct sock_common *)msk, &mpc_addr); + lock_sock(sk); spin_lock_bh(&msk->pm.lock); + if (mptcp_addresses_equal(addr, &mpc_addr, addr->port)) + msk->mpc_endpoint_id = addr->id; mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1311,8 +1394,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; - if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { - GENL_SET_ERR_MSG(info, "flags must have signal when using port"); + if (addr.addr.port && !address_use_port(&addr)) { + GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port"); return -EINVAL; } @@ -1348,7 +1431,7 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } - mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk)); + mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr); return 0; out_free: @@ -1363,6 +1446,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); + /* No entries with ID 0 */ + if (id == 0) + return 0; + rcu_read_lock(); entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id); if (entry) { @@ -1381,7 +1468,6 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, entry = mptcp_pm_del_add_timer(msk, addr, false); if (entry) { - list_del(&entry->list); kfree(entry); return true; } @@ -1389,6 +1475,12 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, return false; } +static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) +{ + return msk->mpc_endpoint_id == addr->id ? 0 : addr->id; +} + static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool force) @@ -1396,28 +1488,38 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, struct mptcp_rm_list list = { .nr = 0 }; bool ret; - list.ids[list.nr++] = addr->id; + list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); + if (ret) { + __set_bit(addr->id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled--; + } mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } return ret; } +static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id) +{ + /* If it was marked as used, and not ID 0, decrement local_addr_used */ + if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) && + id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0)) + msk->pm.local_addr_used--; +} + static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, const struct mptcp_pm_addr_entry *entry) { const struct mptcp_addr_info *addr = &entry->addr; - struct mptcp_rm_list list = { .nr = 0 }; + struct mptcp_rm_list list = { .nr = 1 }; long s_slot = 0, s_num = 0; struct mptcp_sock *msk; - pr_debug("remove_id=%d", addr->id); - - list.ids[list.nr++] = addr->id; + pr_debug("remove_id=%d\n", addr->id); while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; @@ -1435,8 +1537,22 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); - if (remove_subflow) - mptcp_pm_remove_subflow(msk, &list); + + list.ids[0] = mptcp_endp_get_local_id(msk, addr); + if (remove_subflow) { + spin_lock_bh(&msk->pm.lock); + mptcp_pm_nl_rm_subflow_received(msk, &list); + spin_unlock_bh(&msk->pm.lock); + } + + if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + spin_lock_bh(&msk->pm.lock); + __mark_subflow_endp_available(msk, list.ids[0]); + spin_unlock_bh(&msk->pm.lock); + } + + if (msk->mpc_endpoint_id == entry->addr.id) + msk->mpc_endpoint_id = 0; release_sock(sk); next: @@ -1471,6 +1587,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, spin_lock_bh(&msk->pm.lock); mptcp_pm_remove_addr(msk, &list); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, 0); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1530,25 +1647,36 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) return ret; } +/* Called from the userspace PM only */ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; + int anno_nr = 0; list_for_each_entry(entry, rm_list, list) { - if ((remove_anno_list_by_saddr(msk, &entry->addr) || - lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr >= MPTCP_RM_IDS_MAX) + break; + + /* only delete if either announced or matching a subflow */ + if (remove_anno_list_by_saddr(msk, &entry->addr)) + anno_nr++; + else if (!lookup_subflow_by_saddr(&msk->conn_list, + &entry->addr)) + continue; + + alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= anno_nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } } +/* Called from the in-kernel PM only */ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list) { @@ -1556,22 +1684,26 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { - if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && - slist.nr < MPTCP_RM_IDS_MAX) - slist.ids[slist.nr++] = entry->addr.id; + if (slist.nr < MPTCP_RM_IDS_MAX && + lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) + slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); - if (remove_anno_list_by_saddr(msk, &entry->addr) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr < MPTCP_RM_IDS_MAX && + remove_anno_list_by_saddr(msk, &entry->addr)) + alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); } + spin_lock_bh(&msk->pm.lock); if (alist.nr) { - spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); - spin_unlock_bh(&msk->pm.lock); } if (slist.nr) - mptcp_pm_remove_subflow(msk, &slist); + mptcp_pm_nl_rm_subflow_received(msk, &slist); + /* Reset counters: maybe some subflows have been removed before */ + bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); + msk->pm.local_addr_used = 0; + spin_unlock_bh(&msk->pm.lock); } static void mptcp_nl_remove_addrs_list(struct net *net, @@ -1855,10 +1987,11 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, { struct mptcp_rm_list list = { .nr = 0 }; - list.ids[list.nr++] = addr->id; + list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, list.ids[0]); mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); } diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index f0a4590506c6..8eaa9fbe3e34 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -165,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, + struct mptcp_addr_info *skc) +{ + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, false)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + spin_unlock_bh(&msk->pm.lock); + + return backup; +} + int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a26c2c840fd9..37ebcb7640eb 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -139,7 +139,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; - pr_debug("colesced seq %llx into %llx new len %d new end seq %llx", + pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n", MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, to->len, MPTCP_SKB_CB(from)->end_seq); MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; @@ -217,7 +217,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) end_seq = MPTCP_SKB_CB(skb)->end_seq; max_seq = atomic64_read(&msk->rcv_wnd_sent); - pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq, + pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq, RB_EMPTY_ROOT(&msk->out_of_order_queue)); if (after64(end_seq, max_seq)) { /* out of window */ @@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_orphan(skb); /* try to fetch required memory from subflow */ - if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) + if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); goto drop; + } has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; @@ -641,7 +643,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } - pr_debug("msk=%p ssk=%p", msk, ssk); + pr_debug("msk=%p ssk=%p\n", msk, ssk); tp = tcp_sk(ssk); do { u32 map_remaining, offset; @@ -722,7 +724,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) u64 end_seq; p = rb_first(&msk->out_of_order_queue); - pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); + pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); while (p) { skb = rb_to_skb(p); if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) @@ -744,7 +746,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; /* skip overlapping data, if any */ - pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d", + pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n", MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq, delta); MPTCP_SKB_CB(skb)->offset += delta; @@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (__mptcp_rmem(sk) > sk_rbuf) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); + if (__mptcp_rmem(sk) > sk_rbuf) return; - } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); @@ -1240,7 +1240,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, size_t copy; int i; - pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u", + pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n", msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent); if (WARN_ON_ONCE(info->sent > info->limit || @@ -1341,7 +1341,7 @@ alloc_skb: mpext->use_map = 1; mpext->dsn64 = 1; - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d", + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n", mpext->data_seq, mpext->subflow_seq, mpext->data_len, mpext->dsn64); @@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } mptcp_for_each_subflow(msk, subflow) { + bool backup = subflow->backup || subflow->request_bkup; + trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); - nr_active += !subflow->backup; + nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ @@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); - if (linger_time < send_info[subflow->backup].linger_time) { - send_info[subflow->backup].ssk = ssk; - send_info[subflow->backup].linger_time = linger_time; + if (linger_time < send_info[backup].linger_time) { + send_info[backup].ssk = ssk; + send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); @@ -1890,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!msk->first_pending) WRITE_ONCE(msk->first_pending, dfrag); } - pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk, + 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, !dfrag_collapsed); @@ -2246,7 +2248,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - pr_debug("block timeout %ld", timeo); + pr_debug("block timeout %ld\n", timeo); sk_wait_data(sk, &timeo, NULL); } @@ -2262,7 +2264,7 @@ out_err: } } - pr_debug("msk=%p rx queue empty=%d:%d copied=%d", + pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n", msk, skb_queue_empty_lockless(&sk->sk_receive_queue), skb_queue_empty(&msk->receive_queue), copied); if (!(flags & MSG_PEEK)) @@ -2324,7 +2326,7 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) continue; } - if (subflow->backup) { + if (subflow->backup || subflow->request_bkup) { if (!backup) backup = ssk; continue; @@ -2506,6 +2508,12 @@ out: void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { + /* The first subflow can already be closed and still in the list */ + if (subflow->close_event_done) + return; + + subflow->close_event_done = true; + if (sk->sk_state == TCP_ESTABLISHED) mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); @@ -2531,8 +2539,11 @@ static void __mptcp_close_subflow(struct sock *sk) mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int ssk_state = inet_sk_state_load(ssk); - if (inet_sk_state_load(ssk) != TCP_CLOSE) + if (ssk_state != TCP_CLOSE && + (ssk_state != TCP_CLOSE_WAIT || + inet_sk_state_load(sk) != TCP_ESTABLISHED)) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ @@ -2712,7 +2723,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) if (!ssk) return; - pr_debug("MP_FAIL doesn't respond, reset the subflow"); + pr_debug("MP_FAIL doesn't respond, reset the subflow\n"); slow = lock_sock_fast(ssk); mptcp_subflow_reset(ssk); @@ -2886,7 +2897,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) break; default: if (__mptcp_check_fallback(mptcp_sk(sk))) { - pr_debug("Fallback"); + pr_debug("Fallback\n"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); @@ -2896,7 +2907,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); mptcp_schedule_work(sk); } else { - pr_debug("Sending DATA_FIN on subflow %p", ssk); + pr_debug("Sending DATA_FIN on subflow %p\n", ssk); tcp_send_ack(ssk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); @@ -2962,7 +2973,7 @@ static void mptcp_check_send_data_fin(struct sock *sk) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu", + pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n", msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk), msk->snd_nxt, msk->write_seq); @@ -2986,7 +2997,7 @@ static void __mptcp_wr_shutdown(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d", + pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n", msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state, !!mptcp_send_head(sk)); @@ -3001,7 +3012,7 @@ static void __mptcp_destroy_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); might_sleep(); @@ -3109,7 +3120,7 @@ cleanup: mptcp_set_state(sk, TCP_CLOSE); sock_hold(sk); - pr_debug("msk=%p state=%d", sk, sk->sk_state); + pr_debug("msk=%p state=%d\n", sk, sk->sk_state); if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); @@ -3541,7 +3552,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p, ssk=%p", msk, msk->first); + pr_debug("msk=%p, ssk=%p\n", msk, msk->first); if (WARN_ON_ONCE(!msk->first)) return -EINVAL; @@ -3558,7 +3569,7 @@ void mptcp_finish_connect(struct sock *ssk) sk = subflow->conn; msk = mptcp_sk(sk); - pr_debug("msk=%p, token=%u", sk, subflow->token); + pr_debug("msk=%p, token=%u\n", sk, subflow->token); subflow->map_seq = subflow->iasn; subflow->map_subflow_seq = 1; @@ -3587,7 +3598,7 @@ bool mptcp_finish_join(struct sock *ssk) struct sock *parent = (void *)msk; bool ret = true; - pr_debug("msk=%p, subflow=%p", msk, subflow); + pr_debug("msk=%p, subflow=%p\n", msk, subflow); /* mptcp socket already closing? */ if (!mptcp_is_fully_established(parent)) { @@ -3633,7 +3644,7 @@ err_prohibited: static void mptcp_shutdown(struct sock *sk, int how) { - pr_debug("sk=%p, how=%d", sk, how); + pr_debug("sk=%p, how=%d\n", sk, how); if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk)) __mptcp_wr_shutdown(sk); @@ -3854,7 +3865,7 @@ static int mptcp_listen(struct socket *sock, int backlog) struct sock *ssk; int err; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); lock_sock(sk); @@ -3893,7 +3904,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *newsk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. @@ -3902,12 +3913,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk) return -EINVAL; - pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk)); + pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk)); newsk = inet_csk_accept(ssk, arg); if (!newsk) return arg->err; - pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk)); + pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk)); if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; struct sock *new_mptcp_sock; @@ -4000,7 +4011,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); - pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); + pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags); if (state == TCP_LISTEN) { struct sock *ssk = READ_ONCE(msk->first); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index b11a4e50d52b..3b22313d1b86 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -448,6 +448,7 @@ struct mptcp_subflow_request_sock { u16 mp_capable : 1, mp_join : 1, backup : 1, + request_bkup : 1, csum_reqd : 1, allow_join_id0 : 1; u8 local_id; @@ -523,7 +524,8 @@ struct mptcp_subflow_context { stale : 1, /* unable to snd/rcv data, do not use for xmit */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 10; + close_event_done : 1, /* has done the post-closed part */ + __unused : 9; bool data_avail; bool scheduled; u32 remote_nonce; @@ -991,6 +993,8 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk); +bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk, + const struct mptcp_addr_info *remote); void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); @@ -1025,7 +1029,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); @@ -1108,6 +1111,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc); +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); int mptcp_pm_nl_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); @@ -1129,8 +1135,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list); unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); @@ -1176,7 +1180,7 @@ static inline bool mptcp_check_fallback(const struct sock *sk) static inline void __mptcp_do_fallback(struct mptcp_sock *msk) { if (__mptcp_check_fallback(msk)) { - pr_debug("TCP fallback already done (msk=%p)", msk); + pr_debug("TCP fallback already done (msk=%p)\n", msk); return; } set_bit(MPTCP_FALLBACK_DONE, &msk->flags); @@ -1212,7 +1216,7 @@ static inline void mptcp_do_fallback(struct sock *ssk) } } -#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a) +#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a) static inline bool mptcp_check_infinite_map(struct sk_buff *skb) { diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c index 4a7fd0508ad2..78ed508ebc1b 100644 --- a/net/mptcp/sched.c +++ b/net/mptcp/sched.c @@ -86,7 +86,7 @@ int mptcp_register_scheduler(struct mptcp_sched_ops *sched) list_add_tail_rcu(&sched->list, &mptcp_sched_list); spin_unlock(&mptcp_sched_list_lock); - pr_debug("%s registered", sched->name); + pr_debug("%s registered\n", sched->name); return 0; } @@ -118,7 +118,7 @@ int mptcp_init_sched(struct mptcp_sock *msk, if (msk->sched->init) msk->sched->init(msk); - pr_debug("sched=%s", msk->sched->name); + pr_debug("sched=%s\n", msk->sched->name); return 0; } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 2026a9a36f80..505445a9598f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -873,7 +873,7 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname, struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (level == SOL_SOCKET) return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen); @@ -1453,7 +1453,7 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname, struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); /* @@ the meaning of setsockopt() when the socket is connected and * there are multiple subflows is not yet defined. It is up to the diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 39e2cbdf3801..064ab3235893 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -39,7 +39,7 @@ static void subflow_req_destructor(struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - pr_debug("subflow_req=%p", subflow_req); + pr_debug("subflow_req=%p\n", subflow_req); if (subflow_req->msk) sock_put((struct sock *)subflow_req->msk); @@ -100,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) return NULL; } subflow_req->local_id = local_id; + subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req); return msk; } @@ -145,7 +146,7 @@ static int subflow_check_req(struct request_sock *req, struct mptcp_options_received mp_opt; bool opt_mp_capable, opt_mp_join; - pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); + pr_debug("subflow_req=%p, listener=%p\n", subflow_req, listener); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of @@ -168,6 +169,9 @@ static int subflow_check_req(struct request_sock *req, return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); + + if (mp_opt.backup) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); } if (opt_mp_capable && listener->request_mptcp) { @@ -217,7 +221,7 @@ again: } if (subflow_use_different_sport(subflow_req->msk, sk_listener)) { - pr_debug("syn inet_sport=%d %d", + pr_debug("syn inet_sport=%d %d\n", ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { @@ -239,7 +243,7 @@ again: subflow_init_req_cookie_join_save(subflow_req, skb); } - pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, + pr_debug("token=%u, remote_nonce=%u msk=%p\n", subflow_req->token, subflow_req->remote_nonce, subflow_req->msk); } @@ -523,7 +527,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; - pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); + pr_debug("subflow=%p synack seq=%x\n", subflow, subflow->ssn_offset); mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { @@ -555,7 +559,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; WRITE_ONCE(subflow->remote_id, mp_opt.join_id); - pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", + pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d\n", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -577,8 +581,11 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + if (subflow->backup) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX); + if (subflow_use_different_dport(msk, sk)) { - pr_debug("synack inet_dport=%d %d", + pr_debug("synack inet_dport=%d %d\n", ntohs(inet_sk(sk)->inet_dport), ntohs(inet_sk(parent)->inet_dport)); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX); @@ -614,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk) return err; subflow_set_local_id(subflow, err); + subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk); + return 0; } @@ -646,7 +655,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); /* Never answer to SYNs sent to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -677,7 +686,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); if (skb->protocol == htons(ETH_P_IP)) return subflow_v4_conn_request(sk, skb); @@ -798,7 +807,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_sock *owner; struct sock *child; - pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); + pr_debug("listener=%p, req=%p, conn=%p\n", listener, req, listener->conn); /* After child creation we must look for MPC even when options * are not parsed @@ -889,7 +898,7 @@ create_child: ctx->conn = (struct sock *)owner; if (subflow_use_different_sport(owner, sk)) { - pr_debug("ack inet_sport=%d %d", + pr_debug("ack inet_sport=%d %d\n", ntohs(inet_sk(sk)->inet_sport), ntohs(inet_sk((struct sock *)owner)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(owner, sk)) { @@ -952,7 +961,7 @@ enum mapping_status { static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d\n", ssn, subflow->map_subflow_seq, subflow->map_data_len); } @@ -1112,7 +1121,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len = mpext->data_len; if (data_len == 0) { - pr_debug("infinite mapping received"); + pr_debug("infinite mapping received\n"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); subflow->map_data_len = 0; return MAPPING_INVALID; @@ -1124,7 +1133,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (data_len == 1) { bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq, mpext->dsn64); - pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq); + pr_debug("DATA_FIN with no payload seq=%llu\n", mpext->data_seq); if (subflow->map_valid) { /* A DATA_FIN might arrive in a DSS * option before the previous mapping @@ -1150,7 +1159,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_fin_seq &= GENMASK_ULL(31, 0); mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); - pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d", + pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d\n", data_fin_seq, mpext->dsn64); /* Adjust for DATA_FIN using 1 byte of sequence space */ @@ -1196,7 +1205,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (unlikely(subflow->map_csum_reqd != csum_reqd)) return MAPPING_INVALID; - pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", + pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n", subflow->map_seq, subflow->map_subflow_seq, subflow->map_data_len, subflow->map_csum_reqd, subflow->map_data_csum); @@ -1221,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - u32 incr; + struct tcp_sock *tp = tcp_sk(ssk); + u32 offset, incr, avail_len; + + offset = tp->copied_seq - TCP_SKB_CB(skb)->seq; + if (WARN_ON_ONCE(offset > skb->len)) + goto out; - incr = limit >= skb->len ? skb->len + fin : limit; + avail_len = skb->len - offset; + incr = limit >= avail_len ? avail_len + fin : limit; - pr_debug("discarding=%d len=%d seq=%d", incr, skb->len, - subflow->map_subflow_seq); + pr_debug("discarding=%d len=%d offset=%d seq=%d\n", incr, skb->len, + offset, subflow->map_subflow_seq); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); tcp_sk(ssk)->copied_seq += incr; + +out: if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) sk_eat_skb(ssk, skb); if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) @@ -1238,12 +1255,16 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, /* sched mptcp worker to remove the subflow if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { - if (likely(ssk->sk_state != TCP_CLOSE)) + struct sock *sk = (struct sock *)msk; + + if (likely(ssk->sk_state != TCP_CLOSE && + (ssk->sk_state != TCP_CLOSE_WAIT || + inet_sk_state_load(sk) != TCP_ESTABLISHED))) return; if (skb_queue_empty(&ssk->sk_receive_queue) && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) - mptcp_schedule_work((struct sock *)msk); + mptcp_schedule_work(sk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) @@ -1320,7 +1341,7 @@ static bool subflow_check_data_avail(struct sock *ssk) old_ack = READ_ONCE(msk->ack_seq); ack_seq = mptcp_subflow_get_mapped_dsn(subflow); - pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, + pr_debug("msk ack_seq=%llx subflow ack_seq=%llx\n", old_ack, ack_seq); if (unlikely(before64(ack_seq, old_ack))) { mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); @@ -1392,7 +1413,7 @@ bool mptcp_subflow_data_available(struct sock *sk) subflow->map_valid = 0; WRITE_ONCE(subflow->data_avail, false); - pr_debug("Done with mapping: seq=%u data_len=%u", + pr_debug("Done with mapping: seq=%u data_len=%u\n", subflow->map_subflow_seq, subflow->map_data_len); } @@ -1502,7 +1523,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk); - pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d", + pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d\n", subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped); if (likely(icsk->icsk_af_ops == target)) @@ -1595,7 +1616,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, goto failed; mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL); - pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, + pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; WRITE_ONCE(subflow->remote_id, remote_id); @@ -1730,7 +1751,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid; subflow = mptcp_subflow_ctx(sf->sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); *new_sock = sf; sock_hold(sk); @@ -1759,7 +1780,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, INIT_LIST_HEAD(&ctx->node); INIT_LIST_HEAD(&ctx->delegated_node); - pr_debug("subflow=%p", ctx); + pr_debug("subflow=%p\n", ctx); ctx->tcp_sock = sk; WRITE_ONCE(ctx->local_id, -1); @@ -1910,7 +1931,7 @@ static int subflow_ulp_init(struct sock *sk) goto out; } - pr_debug("subflow=%p, family=%d", ctx, sk->sk_family); + pr_debug("subflow=%p, family=%d\n", ctx, sk->sk_family); tp->is_mptcp = 1; ctx->icsk_af_ops = icsk->icsk_af_ops; @@ -2005,6 +2026,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; + new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 5c1ff07eaee0..df72b0376970 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -670,8 +670,14 @@ static int __init nf_flow_table_module_init(void) if (ret) goto out_offload; + ret = nf_flow_register_bpf(); + if (ret) + goto out_bpf; + return 0; +out_bpf: + nf_flow_table_offload_exit(); out_offload: unregister_pernet_subsys(&nf_flow_table_net_ops); return ret; diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 88787b45e30d..b0f199171932 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return NF_ACCEPT; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); proto = veth->h_vlan_encapsulated_proto; break; @@ -98,7 +101,7 @@ static int __init nf_flow_inet_module_init(void) nft_register_flowtable_type(&flowtable_ipv6); nft_register_flowtable_type(&flowtable_inet); - return nf_flow_register_bpf(); + return 0; } static void __exit nf_flow_inet_module_exit(void) diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index c2c005234dcd..98edcaa37b38 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return false; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); if (veth->h_vlan_encapsulated_proto == proto) { *offset += VLAN_HLEN; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index ff1a4e36c2b5..e06bc36f49fe 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, struct list_head *block_cb_list) { struct flow_cls_offload cls_flow = {}; + struct netlink_ext_ack extack = {}; struct flow_block_cb *block_cb; - struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; int err, i = 0; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 481ee78e77bc..0a2f79346958 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8020,6 +8020,19 @@ cont: return skb->len; } +static int nf_tables_dumpreset_obj(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); + int ret; + + mutex_lock(&nft_net->commit_mutex); + ret = nf_tables_dump_obj(skb, cb); + mutex_unlock(&nft_net->commit_mutex); + + return ret; +} + static int nf_tables_dump_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -8036,12 +8049,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb) if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - ctx->reset = true; - return 0; } +static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb) +{ + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + + return nf_tables_dump_obj_start(cb); +} + static int nf_tables_dump_obj_done(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -8052,8 +8071,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); @@ -8062,72 +8082,109 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; - bool reset = false; u32 objtype; int err; - if (info->nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .start = nf_tables_dump_obj_start, - .dump = nf_tables_dump_obj, - .done = nf_tables_dump_obj_done, - .module = THIS_MODULE, - .data = (void *)nla, - }; - - return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); - } - if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) - return -EINVAL; + return ERR_PTR(-EINVAL); table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); - return PTR_ERR(table); + return ERR_CAST(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); - return PTR_ERR(obj); + return ERR_CAST(obj); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) - return -ENOMEM; + return ERR_PTR(-ENOMEM); - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - reset = true; + err = nf_tables_fill_obj_info(skb2, net, portid, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + family, table, obj, reset); + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + } - if (reset) { - const struct nftables_pernet *nft_net; - char *buf; + return skb2; +} - nft_net = nft_pernet(net); - buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + u32 portid = NETLINK_CB(skb).portid; + struct sk_buff *skb2; - audit_log_nfcfg(buf, - family, - 1, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, + .dump = nf_tables_dump_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, - family, table, obj, reset); - if (err < 0) - goto err_fill_obj_info; + skb2 = nf_tables_getobj_single(portid, info, nla, false); + if (IS_ERR(skb2)) + return PTR_ERR(skb2); - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, info->net, portid); +} -err_fill_obj_info: - kfree_skb(skb2); - return err; +static int nf_tables_getobj_reset(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dumpreset_obj_start, + .dump = nf_tables_dumpreset_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + rcu_read_unlock(); + mutex_lock(&nft_net->commit_mutex); + skb2 = nf_tables_getobj_single(portid, info, nla, true); + mutex_unlock(&nft_net->commit_mutex); + rcu_read_lock(); + module_put(THIS_MODULE); + + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + buf = kasprintf(GFP_ATOMIC, "%.*s:%u", + nla_len(nla[NFTA_OBJ_TABLE]), + (char *)nla_data(nla[NFTA_OBJ_TABLE]), + nft_net->base_seq); + audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); + + return nfnetlink_unicast(skb2, net, portid); } static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) @@ -9410,7 +9467,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call = nf_tables_getobj, + .call = nf_tables_getobj_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abf660c7baf..932b3ddb34f1 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -427,8 +427,10 @@ replay_abort: nfnl_unlock(subsys_id); - if (nlh->nlmsg_flags & NLM_F_ACK) + if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); + } while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -577,6 +579,7 @@ done: ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } else if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); } } else { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 55e28e1da66e..e0716da256bf 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; - const struct nf_conn *ct = (void *)skb_nfct(entry->skb); + struct nf_conn *ct = (void *)skb_nfct(entry->skb); + unsigned long status; + unsigned int use; - if (ct && ((ct->status & flags) == IPS_DYING)) + if (!ct) + return false; + + status = READ_ONCE(ct->status); + if ((status & flags) == IPS_DYING) return true; + + if (status & IPS_CONFIRMED) + return false; + + /* in some cases skb_clone() can occur after initial conntrack + * pickup, but conntrack assumes exclusive skb->_nfct ownership for + * unconfirmed entries. + * + * This happens for br_netfilter and with ip multicast routing. + * We can't be solved with serialization here because one clone could + * have been queued for local delivery. + */ + use = refcount_read(&ct->ct_general.use); + if (likely(use == 1)) + return false; + + /* Can't decrement further? Exclusive ownership. */ + if (!refcount_dec_not_one(&ct->ct_general.use)) + return false; + + skb_set_nfct(entry->skb, 0); + /* No nf_ct_put(): we already decremented .use and it cannot + * drop down to 0. + */ + return true; #endif return false; } diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 291ed2026367..eab0dc66bee6 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -107,11 +107,16 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv, struct nft_counter *total) { struct nft_counter *this_cpu; + seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); + myseq = this_cpu_ptr(&nft_counter_seq); + + write_seqcount_begin(myseq); this_cpu->packets -= total->packets; this_cpu->bytes -= total->bytes; + write_seqcount_end(myseq); local_bh_enable(); } @@ -265,7 +270,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, struct nft_counter *this_cpu; seqcount_t *myseq; - preempt_disable(); + local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); myseq = this_cpu_ptr(&nft_counter_seq); @@ -273,7 +278,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, this_cpu->packets += stats->pkts; this_cpu->bytes += stats->bytes; write_seqcount_end(myseq); - preempt_enable(); + local_bh_enable(); } void nft_counter_init_seqcount(void) diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index f30163e2ca62..12cdff640492 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -9,7 +9,8 @@ struct nft_socket { enum nft_socket_keys key:8; - u8 level; + u8 level; /* cgroupv2 level to extract */ + u8 level_user; /* cgroupv2 level provided by userspace */ u8 len; union { u8 dreg; @@ -53,6 +54,28 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo memcpy(dest, &cgid, sizeof(u64)); return true; } + +/* process context only, uses current->nsproxy. */ +static noinline int nft_socket_cgroup_subtree_level(void) +{ + struct cgroup *cgrp = cgroup_get_from_path("/"); + int level; + + if (!cgrp) + return -ENOENT; + + level = cgrp->level; + + cgroup_put(cgrp); + + if (WARN_ON_ONCE(level > 255)) + return -ERANGE; + + if (WARN_ON_ONCE(level < 0)) + return -EINVAL; + + return level; +} #endif static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) @@ -110,13 +133,13 @@ static void nft_socket_eval(const struct nft_expr *expr, *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; - return; + goto out_put_sk; } break; case NFT_SOCKET_WILDCARD: if (!sk_fullsock(sk)) { regs->verdict.code = NFT_BREAK; - return; + goto out_put_sk; } nft_socket_wildcard(pkt, regs, sk, dest); break; @@ -124,7 +147,7 @@ static void nft_socket_eval(const struct nft_expr *expr, case NFT_SOCKET_CGROUPV2: if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) { regs->verdict.code = NFT_BREAK; - return; + goto out_put_sk; } break; #endif @@ -133,6 +156,7 @@ static void nft_socket_eval(const struct nft_expr *expr, regs->verdict.code = NFT_BREAK; } +out_put_sk: if (sk != skb->sk) sock_gen_put(sk); } @@ -173,9 +197,10 @@ static int nft_socket_init(const struct nft_ctx *ctx, case NFT_SOCKET_MARK: len = sizeof(u32); break; -#ifdef CONFIG_CGROUPS +#ifdef CONFIG_SOCK_CGROUP_DATA case NFT_SOCKET_CGROUPV2: { unsigned int level; + int err; if (!tb[NFTA_SOCKET_LEVEL]) return -EINVAL; @@ -184,6 +209,17 @@ static int nft_socket_init(const struct nft_ctx *ctx, if (level > 255) return -EOPNOTSUPP; + err = nft_socket_cgroup_subtree_level(); + if (err < 0) + return err; + + priv->level_user = level; + + level += err; + /* Implies a giant cgroup tree */ + if (WARN_ON_ONCE(level > 255)) + return -EOPNOTSUPP; + priv->level = level; len = sizeof(u64); break; @@ -208,7 +244,7 @@ static int nft_socket_dump(struct sk_buff *skb, if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg)) return -1; if (priv->key == NFT_SOCKET_CGROUPV2 && - nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level))) + nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level_user))) return -1; return 0; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 99d72543abd3..78d9961fcd44 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2706,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = { }; static const char * const ovs_drop_reasons[] = { -#define S(x) (#x), +#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x), OVS_DROP_REASONS(S) #undef S }; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 113b907da0f7..3ba8e7e739b5 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -44,6 +44,8 @@ static DEFINE_MUTEX(zones_mutex); struct zones_ht_key { struct net *net; u16 zone; + /* Note : pad[] must be the last field. */ + u8 pad[]; }; struct tcf_ct_flow_table { @@ -60,7 +62,7 @@ struct tcf_ct_flow_table { static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), - .key_len = sizeof_field(struct tcf_ct_flow_table, key), + .key_len = offsetof(struct zones_ht_key, pad), .automatic_shrinking = true, }; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 9602dafe32e6..d2f49db70523 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -786,12 +786,15 @@ skip_hash: * queue, accept the collision, update the host tags. */ q->way_collisions++; - if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { - q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; - q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; - } allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); + + if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { + if (allocate_src) + q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; + if (allocate_dst) + q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; + } found: /* reserve queue for future packets in same flow */ reduced_hash = outer_hash + k; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 238974725679..19a49af5a9e5 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -663,7 +663,9 @@ begin: pband = &q->band_flows[q->band_nr]; pband->credit = min(pband->credit + pband->quantum, pband->quantum); - goto begin; + if (pband->credit > 0) + goto begin; + retry = 0; } if (q->time_next_delayed_flow != ~0ULL) qdisc_watchdog_schedule_range_ns(&q->watchdog, diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index edc72962ae63..39382ee1e331 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; - struct sk_buff *skb2; + struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; - int rc = NET_XMIT_SUCCESS; - int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_orphan_partial(skb); /* - * If we need to duplicate packet, then re-insert at top of the - * qdisc tree, since parent queuer expects that only one - * skb will be queued. + * If we need to duplicate packet, then clone it before + * original is modified. */ - if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root_bh(sch); - u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - - q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); - q->duplicate = dupsave; - rc_drop = NET_XMIT_SUCCESS; - } + if (count > 1) + skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. @@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) - return rc_drop; + goto finish_segs; + segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; @@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); - return rc_drop; + if (skb2) + __qdisc_drop(skb2, to_free); + return NET_XMIT_DROP; + } + + /* + * If doing duplication then re-insert at top of the + * qdisc tree, since parent queuer expects that only one + * skb will be queued. + */ + if (skb2) { + struct Qdisc *rootq = qdisc_root_bh(sch); + u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ + + q->duplicate = 0; + rootq->enqueue(skb2, rootq, to_free); + q->duplicate = dupsave; + skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); @@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } finish_segs: + if (skb2) + __qdisc_drop(skb2, to_free); + if (segs) { unsigned int len, last_len; - int nb; + int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; @@ -731,11 +742,10 @@ deliver: err = qdisc_enqueue(skb, q->qdisc, &to_free); kfree_skb_list(to_free); - if (err != NET_XMIT_SUCCESS && - net_xmit_drop_count(err)) { - qdisc_qstats_drop(sch); - qdisc_tree_reduce_backlog(sch, 1, - pkt_len); + if (err != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(err)) + qdisc_qstats_drop(sch); + qdisc_tree_reduce_backlog(sch, 1, pkt_len); } goto tfifo_dequeue; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 17fcaa9b0df9..a8a254a5008e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -735,15 +735,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; + int err = 0; ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); struct sctp_endpoint *ep2; struct list_head *list; - int cnt = 0, err = 1; + int cnt = 0; + + err = 1; list_for_each(list, &ep->base.bind_addr.address_list) cnt++; @@ -761,24 +765,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) if (!err) { err = reuseport_add_sock(sk, sk2, any); if (err) - return err; + goto out; break; } else if (err < 0) { - return err; + goto out; } } if (err) { err = reuseport_alloc(sk, any); if (err) - return err; + goto out; } } - write_lock(&head->lock); hlist_add_head(&ep->node, &head->chain); +out: write_unlock(&head->lock); - return 0; + return err; } /* Add an endpoint to the hash. Local BH-safe. */ @@ -803,10 +807,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - - write_lock(&head->lock); hlist_del_init(&ep->node); write_unlock(&head->lock); } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 5adf0c0a6c1a..7d315a18612b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2260,12 +2260,6 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } } - /* Update socket peer label if first association. */ - if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - /* Set temp so that it won't be added into hashtable */ new_asoc->temp = 1; @@ -2274,6 +2268,22 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( */ action = sctp_tietags_compare(new_asoc, asoc); + /* In cases C and E the association doesn't enter the ESTABLISHED + * state, so there is no need to call security_sctp_assoc_request(). + */ + switch (action) { + case 'A': /* Association restart. */ + case 'B': /* Collision case B. */ + case 'D': /* Collision case D. */ + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request((struct sctp_association *)asoc, + chunk->head_skb ?: chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + break; + } + switch (action) { case 'A': /* Association restart. */ retval = sctp_sf_do_dupcook_a(net, ep, asoc, chunk, commands, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 73a875573e7a..8e3093938cd2 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3319,10 +3319,8 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family) rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); - if (rc) { - sk_common_release(sk); + if (rc) return rc; - } /* smc_clcsock_release() does not wait smc->clcsock->sk's * destruction; its sk_state might not be TCP_CLOSE after @@ -3368,6 +3366,9 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, smc->clcsock = clcsock; else rc = smc_create_clcsk(net, sk, family); + + if (rc) + sk_common_release(sk); out: return rc; } diff --git a/net/smc/smc.h b/net/smc/smc.h index 34b781e463c4..ad77d6b6b8d3 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -284,6 +284,9 @@ struct smc_connection { struct smc_sock { /* smc sock container */ struct sock sk; +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6_pinfo *pinet6; +#endif struct socket *clcsock; /* internal tcp socket */ void (*clcsk_state_change)(struct sock *sk); /* original stat_change fct. */ diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c index bece346dd8e9..a5b2041600f9 100644 --- a/net/smc/smc_inet.c +++ b/net/smc/smc_inet.c @@ -60,6 +60,11 @@ static struct inet_protosw smc_inet_protosw = { }; #if IS_ENABLED(CONFIG_IPV6) +struct smc6_sock { + struct smc_sock smc; + struct ipv6_pinfo inet6; +}; + static struct proto smc_inet6_prot = { .name = "INET6_SMC", .owner = THIS_MODULE, @@ -67,9 +72,10 @@ static struct proto smc_inet6_prot = { .hash = smc_hash_sk, .unhash = smc_unhash_sk, .release_cb = smc_release_cb, - .obj_size = sizeof(struct smc_sock), + .obj_size = sizeof(struct smc6_sock), .h.smc_hash = &smc_v6_hashinfo, .slab_flags = SLAB_TYPESAFE_BY_RCU, + .ipv6_pinfo_offset = offsetof(struct smc6_sock, inet6), }; static const struct proto_ops smc_inet6_stream_ops = { diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h index 9d32058db2b5..e19177ce4092 100644 --- a/net/smc/smc_stats.h +++ b/net/smc/smc_stats.h @@ -19,7 +19,7 @@ #include "smc_clc.h" -#define SMC_MAX_FBACK_RSN_CNT 30 +#define SMC_MAX_FBACK_RSN_CNT 36 enum { SMC_BUF_8K, diff --git a/net/socket.c b/net/socket.c index fcbdd5bc47ac..0a2bd22ec105 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2362,7 +2362,7 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen) { - int max_optlen __maybe_unused; + int max_optlen __maybe_unused = 0; const struct proto_ops *ops; int err; @@ -2371,7 +2371,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level, return err; if (!compat) - max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + copy_from_sockptr(&max_optlen, optlen, sizeof(int)); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index e03f14024e47..88a59cfa5583 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -161,7 +161,7 @@ param_get_pool_mode(char *buf, const struct kernel_param *kp) str[len] = '\n'; str[len + 1] = '\0'; - return sysfs_emit(buf, str); + return sysfs_emit(buf, "%s", str); } module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode, diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c index a938c19c3490..8507cd4d8921 100644 --- a/net/sunrpc/xprtrdma/ib_client.c +++ b/net/sunrpc/xprtrdma/ib_client.c @@ -62,10 +62,11 @@ int rpcrdma_rn_register(struct ib_device *device, if (!rd || test_bit(RPCRDMA_RD_F_REMOVING, &rd->rd_flags)) return -ENETUNREACH; - kref_get(&rd->rd_kref); if (xa_alloc(&rd->rd_xa, &rn->rn_index, rn, xa_limit_32b, GFP_KERNEL) < 0) return -ENOMEM; + kref_get(&rd->rd_kref); rn->rn_done = done; + trace_rpcrdma_client_register(device, rn); return 0; } @@ -91,6 +92,7 @@ void rpcrdma_rn_unregister(struct ib_device *device, if (!rd) return; + trace_rpcrdma_client_unregister(device, rn); xa_erase(&rd->rd_xa, rn->rn_index); kref_put(&rd->rd_kref, rpcrdma_rn_release); } @@ -111,7 +113,7 @@ static int rpcrdma_add_one(struct ib_device *device) return -ENOMEM; kref_init(&rd->rd_kref); - xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC1); + xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC); rd->rd_device = device; init_completion(&rd->rd_done); ib_set_client_data(device, &rpcrdma_ib_client, rd); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4b040285aa78..0ff9b2dd86ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1270,25 +1270,28 @@ out: return err; } +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk; - sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif - return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); @@ -2174,15 +2177,12 @@ out: } int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err; sk = sock->sk; @@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } -#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2250,6 +2242,22 @@ out: release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84..c42c5cc18f32 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d99319d82205..64eeed82d43d 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -3178,8 +3178,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, gfp_t gfp) { - size_t min_hdr_len = offsetof(struct ieee80211_mgmt, - u.probe_resp.variable); + size_t min_hdr_len; struct ieee80211_ext *ext = NULL; enum cfg80211_bss_frame_type ftype; u16 beacon_interval; @@ -3202,10 +3201,16 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { ext = (void *) mgmt; - min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon); if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_short_beacon.variable); + else + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon.variable); + } else { + /* same for beacons */ + min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); } if (WARN_ON(len < min_hdr_len)) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index e419aa8c4a5a..d9d7bf8bb5c1 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1045,6 +1045,7 @@ void cfg80211_connect_done(struct net_device *dev, cfg80211_hold_bss( bss_from_pub(params->links[link].bss)); ev->cr.links[link].bss = params->links[link].bss; + ev->cr.links[link].status = params->links[link].status; if (params->links[link].addr) { ev->cr.links[link].addr = next; |