diff options
Diffstat (limited to 'net')
58 files changed, 785 insertions, 272 deletions
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 7a2174851857..fe49e8a7969f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3087,8 +3087,18 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); + /* Check for existing connection: + * + * 1. If it doesn't exist then it must be receiver/slave role. + * 2. If it does exist confirm that it is connecting/BT_CONNECT in case + * of initiator/master role since there could be a collision where + * either side is attempting to connect or something like a fuzzing + * testing is trying to play tricks to destroy the hcon object before + * it even attempts to connect (e.g. hcon->state == BT_OPEN). + */ conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); - if (!conn) { + if (!conn || + (conn->role == HCI_ROLE_MASTER && conn->state != BT_CONNECT)) { /* In case of error status and there is no connection pending * just unlock as there is nothing to cleanup. */ @@ -4391,6 +4401,8 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "num %d", ev->num); + hci_dev_lock(hdev); + for (i = 0; i < ev->num; i++) { struct hci_comp_pkts_info *info = &ev->handles[i]; struct hci_conn *conn; @@ -4472,6 +4484,8 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data, } queue_work(hdev->workqueue, &hdev->tx_work); + + hci_dev_unlock(hdev); } static void hci_mode_change_evt(struct hci_dev *hdev, void *data, @@ -5634,8 +5648,18 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, */ hci_dev_clear_flag(hdev, HCI_LE_ADV); - conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, bdaddr); - if (!conn) { + /* Check for existing connection: + * + * 1. If it doesn't exist then use the role to create a new object. + * 2. If it does exist confirm that it is connecting/BT_CONNECT in case + * of initiator/master role since there could be a collision where + * either side is attempting to connect or something like a fuzzing + * testing is trying to play tricks to destroy the hcon object before + * it even attempts to connect (e.g. hcon->state == BT_OPEN). + */ + conn = hci_conn_hash_lookup_role(hdev, LE_LINK, role, bdaddr); + if (!conn || + (conn->role == HCI_ROLE_MASTER && conn->state != BT_CONNECT)) { /* In case of error status and there is no connection pending * just unlock as there is nothing to cleanup. */ diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index b6f888d8354e..7a7d49890858 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2594,6 +2594,13 @@ static int hci_resume_advertising_sync(struct hci_dev *hdev) hci_remove_ext_adv_instance_sync(hdev, adv->instance, NULL); } + + /* If current advertising instance is set to instance 0x00 + * then we need to re-enable it. + */ + if (!hdev->cur_adv_instance) + err = hci_enable_ext_advertising_sync(hdev, + hdev->cur_adv_instance); } else { /* Schedule for most recent instance to be restarted and begin * the software rotation loop diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 50634ef5c8b7..225140fcb3d6 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1323,8 +1323,7 @@ static void mgmt_set_powered_complete(struct hci_dev *hdev, void *data, int err) struct mgmt_mode *cp; /* Make sure cmd still outstanding. */ - if (err == -ECANCELED || - cmd != pending_find(MGMT_OP_SET_POWERED, hdev)) + if (err == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; cp = cmd->param; @@ -1351,23 +1350,29 @@ static void mgmt_set_powered_complete(struct hci_dev *hdev, void *data, int err) mgmt_status(err)); } - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); } static int set_powered_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_mode *cp; + struct mgmt_mode cp; + + mutex_lock(&hdev->mgmt_pending_lock); /* Make sure cmd still outstanding. */ - if (cmd != pending_find(MGMT_OP_SET_POWERED, hdev)) + if (!__mgmt_pending_listed(hdev, cmd)) { + mutex_unlock(&hdev->mgmt_pending_lock); return -ECANCELED; + } - cp = cmd->param; + memcpy(&cp, cmd->param, sizeof(cp)); + + mutex_unlock(&hdev->mgmt_pending_lock); BT_DBG("%s", hdev->name); - return hci_set_powered_sync(hdev, cp->val); + return hci_set_powered_sync(hdev, cp.val); } static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, @@ -1516,8 +1521,7 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "err %d", err); /* Make sure cmd still outstanding. */ - if (err == -ECANCELED || - cmd != pending_find(MGMT_OP_SET_DISCOVERABLE, hdev)) + if (err == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; hci_dev_lock(hdev); @@ -1539,12 +1543,15 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data, new_settings(hdev, cmd->sk); done: - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); hci_dev_unlock(hdev); } static int set_discoverable_sync(struct hci_dev *hdev, void *data) { + if (!mgmt_pending_listed(hdev, data)) + return -ECANCELED; + BT_DBG("%s", hdev->name); return hci_update_discoverable_sync(hdev); @@ -1691,8 +1698,7 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "err %d", err); /* Make sure cmd still outstanding. */ - if (err == -ECANCELED || - cmd != pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) + if (err == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; hci_dev_lock(hdev); @@ -1707,7 +1713,7 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data, new_settings(hdev, cmd->sk); done: - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); hci_dev_unlock(hdev); } @@ -1743,6 +1749,9 @@ static int set_connectable_update_settings(struct hci_dev *hdev, static int set_connectable_sync(struct hci_dev *hdev, void *data) { + if (!mgmt_pending_listed(hdev, data)) + return -ECANCELED; + BT_DBG("%s", hdev->name); return hci_update_connectable_sync(hdev); @@ -1919,14 +1928,17 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) { struct cmd_lookup match = { NULL, hdev }; struct mgmt_pending_cmd *cmd = data; - struct mgmt_mode *cp = cmd->param; - u8 enable = cp->val; + struct mgmt_mode *cp; + u8 enable; bool changed; /* Make sure cmd still outstanding. */ - if (err == -ECANCELED || cmd != pending_find(MGMT_OP_SET_SSP, hdev)) + if (err == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; + cp = cmd->param; + enable = cp->val; + if (err) { u8 mgmt_err = mgmt_status(err); @@ -1935,8 +1947,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) new_settings(hdev, NULL); } - mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, true, - cmd_status_rsp, &mgmt_err); + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err); return; } @@ -1946,7 +1957,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED); } - mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, true, settings_rsp, &match); + settings_rsp(cmd, &match); if (changed) new_settings(hdev, match.sk); @@ -1960,14 +1971,25 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) static int set_ssp_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_mode *cp = cmd->param; + struct mgmt_mode cp; bool changed = false; int err; - if (cp->val) + mutex_lock(&hdev->mgmt_pending_lock); + + if (!__mgmt_pending_listed(hdev, cmd)) { + mutex_unlock(&hdev->mgmt_pending_lock); + return -ECANCELED; + } + + memcpy(&cp, cmd->param, sizeof(cp)); + + mutex_unlock(&hdev->mgmt_pending_lock); + + if (cp.val) changed = !hci_dev_test_and_set_flag(hdev, HCI_SSP_ENABLED); - err = hci_write_ssp_mode_sync(hdev, cp->val); + err = hci_write_ssp_mode_sync(hdev, cp.val); if (!err && changed) hci_dev_clear_flag(hdev, HCI_SSP_ENABLED); @@ -2060,32 +2082,50 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) static void set_le_complete(struct hci_dev *hdev, void *data, int err) { + struct mgmt_pending_cmd *cmd = data; struct cmd_lookup match = { NULL, hdev }; u8 status = mgmt_status(err); bt_dev_dbg(hdev, "err %d", err); - if (status) { - mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, true, cmd_status_rsp, - &status); + if (err == -ECANCELED || !mgmt_pending_valid(hdev, data)) return; + + if (status) { + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, status); + goto done; } - mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, true, settings_rsp, &match); + settings_rsp(cmd, &match); new_settings(hdev, match.sk); if (match.sk) sock_put(match.sk); + +done: + mgmt_pending_free(cmd); } static int set_le_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_mode *cp = cmd->param; - u8 val = !!cp->val; + struct mgmt_mode cp; + u8 val; int err; + mutex_lock(&hdev->mgmt_pending_lock); + + if (!__mgmt_pending_listed(hdev, cmd)) { + mutex_unlock(&hdev->mgmt_pending_lock); + return -ECANCELED; + } + + memcpy(&cp, cmd->param, sizeof(cp)); + val = !!cp.val; + + mutex_unlock(&hdev->mgmt_pending_lock); + if (!val) { hci_clear_adv_instance_sync(hdev, NULL, 0x00, true); @@ -2127,7 +2167,12 @@ static void set_mesh_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; u8 status = mgmt_status(err); - struct sock *sk = cmd->sk; + struct sock *sk; + + if (err == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) + return; + + sk = cmd->sk; if (status) { mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev, true, @@ -2142,24 +2187,37 @@ static void set_mesh_complete(struct hci_dev *hdev, void *data, int err) static int set_mesh_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_cp_set_mesh *cp = cmd->param; - size_t len = cmd->param_len; + struct mgmt_cp_set_mesh cp; + size_t len; + + mutex_lock(&hdev->mgmt_pending_lock); + + if (!__mgmt_pending_listed(hdev, cmd)) { + mutex_unlock(&hdev->mgmt_pending_lock); + return -ECANCELED; + } + + memcpy(&cp, cmd->param, sizeof(cp)); + + mutex_unlock(&hdev->mgmt_pending_lock); + + len = cmd->param_len; memset(hdev->mesh_ad_types, 0, sizeof(hdev->mesh_ad_types)); - if (cp->enable) + if (cp.enable) hci_dev_set_flag(hdev, HCI_MESH); else hci_dev_clear_flag(hdev, HCI_MESH); - hdev->le_scan_interval = __le16_to_cpu(cp->period); - hdev->le_scan_window = __le16_to_cpu(cp->window); + hdev->le_scan_interval = __le16_to_cpu(cp.period); + hdev->le_scan_window = __le16_to_cpu(cp.window); - len -= sizeof(*cp); + len -= sizeof(cp); /* If filters don't fit, forward all adv pkts */ if (len <= sizeof(hdev->mesh_ad_types)) - memcpy(hdev->mesh_ad_types, cp->ad_types, len); + memcpy(hdev->mesh_ad_types, cp.ad_types, len); hci_update_passive_scan_sync(hdev); return 0; @@ -3867,15 +3925,16 @@ static int name_changed_sync(struct hci_dev *hdev, void *data) static void set_name_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_cp_set_local_name *cp = cmd->param; + struct mgmt_cp_set_local_name *cp; u8 status = mgmt_status(err); bt_dev_dbg(hdev, "err %d", err); - if (err == -ECANCELED || - cmd != pending_find(MGMT_OP_SET_LOCAL_NAME, hdev)) + if (err == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; + cp = cmd->param; + if (status) { mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, status); @@ -3887,16 +3946,27 @@ static void set_name_complete(struct hci_dev *hdev, void *data, int err) hci_cmd_sync_queue(hdev, name_changed_sync, NULL, NULL); } - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); } static int set_name_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_cp_set_local_name *cp = cmd->param; + struct mgmt_cp_set_local_name cp; + + mutex_lock(&hdev->mgmt_pending_lock); + + if (!__mgmt_pending_listed(hdev, cmd)) { + mutex_unlock(&hdev->mgmt_pending_lock); + return -ECANCELED; + } + + memcpy(&cp, cmd->param, sizeof(cp)); + + mutex_unlock(&hdev->mgmt_pending_lock); if (lmp_bredr_capable(hdev)) { - hci_update_name_sync(hdev, cp->name); + hci_update_name_sync(hdev, cp.name); hci_update_eir_sync(hdev); } @@ -4048,12 +4118,10 @@ int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip) static void set_default_phy_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; - struct sk_buff *skb = cmd->skb; + struct sk_buff *skb; u8 status = mgmt_status(err); - if (err == -ECANCELED || - cmd != pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev)) - return; + skb = cmd->skb; if (!status) { if (!skb) @@ -4080,7 +4148,7 @@ static void set_default_phy_complete(struct hci_dev *hdev, void *data, int err) if (skb && !IS_ERR(skb)) kfree_skb(skb); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); } static int set_default_phy_sync(struct hci_dev *hdev, void *data) @@ -4088,7 +4156,9 @@ static int set_default_phy_sync(struct hci_dev *hdev, void *data) struct mgmt_pending_cmd *cmd = data; struct mgmt_cp_set_phy_configuration *cp = cmd->param; struct hci_cp_le_set_default_phy cp_phy; - u32 selected_phys = __le32_to_cpu(cp->selected_phys); + u32 selected_phys; + + selected_phys = __le32_to_cpu(cp->selected_phys); memset(&cp_phy, 0, sizeof(cp_phy)); @@ -4228,7 +4298,7 @@ static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev, goto unlock; } - cmd = mgmt_pending_add(sk, MGMT_OP_SET_PHY_CONFIGURATION, hdev, data, + cmd = mgmt_pending_new(sk, MGMT_OP_SET_PHY_CONFIGURATION, hdev, data, len); if (!cmd) err = -ENOMEM; @@ -5189,7 +5259,17 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, { struct mgmt_rp_add_adv_patterns_monitor rp; struct mgmt_pending_cmd *cmd = data; - struct adv_monitor *monitor = cmd->user_data; + struct adv_monitor *monitor; + + /* This is likely the result of hdev being closed and mgmt_index_removed + * is attempting to clean up any pending command so + * hci_adv_monitors_clear is about to be called which will take care of + * freeing the adv_monitor instances. + */ + if (status == -ECANCELED && !mgmt_pending_valid(hdev, cmd)) + return; + + monitor = cmd->user_data; hci_dev_lock(hdev); @@ -5215,9 +5295,20 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, static int mgmt_add_adv_patterns_monitor_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - struct adv_monitor *monitor = cmd->user_data; + struct adv_monitor *mon; + + mutex_lock(&hdev->mgmt_pending_lock); + + if (!__mgmt_pending_listed(hdev, cmd)) { + mutex_unlock(&hdev->mgmt_pending_lock); + return -ECANCELED; + } + + mon = cmd->user_data; + + mutex_unlock(&hdev->mgmt_pending_lock); - return hci_add_adv_monitor(hdev, monitor); + return hci_add_adv_monitor(hdev, mon); } static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev, @@ -5484,7 +5575,8 @@ unlock: status); } -static void read_local_oob_data_complete(struct hci_dev *hdev, void *data, int err) +static void read_local_oob_data_complete(struct hci_dev *hdev, void *data, + int err) { struct mgmt_rp_read_local_oob_data mgmt_rp; size_t rp_size = sizeof(mgmt_rp); @@ -5504,7 +5596,8 @@ static void read_local_oob_data_complete(struct hci_dev *hdev, void *data, int e bt_dev_dbg(hdev, "status %d", status); if (status) { - mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, status); + mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, + status); goto remove; } @@ -5786,17 +5879,12 @@ static void start_discovery_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - if (err == -ECANCELED) - return; - - if (cmd != pending_find(MGMT_OP_START_DISCOVERY, hdev) && - cmd != pending_find(MGMT_OP_START_LIMITED_DISCOVERY, hdev) && - cmd != pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev)) + if (err == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err), cmd->param, 1); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); hci_discovery_set_state(hdev, err ? DISCOVERY_STOPPED: DISCOVERY_FINDING); @@ -5804,6 +5892,9 @@ static void start_discovery_complete(struct hci_dev *hdev, void *data, int err) static int start_discovery_sync(struct hci_dev *hdev, void *data) { + if (!mgmt_pending_listed(hdev, data)) + return -ECANCELED; + return hci_start_discovery_sync(hdev); } @@ -6009,15 +6100,14 @@ static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; - if (err == -ECANCELED || - cmd != pending_find(MGMT_OP_STOP_DISCOVERY, hdev)) + if (err == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; bt_dev_dbg(hdev, "err %d", err); mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err), cmd->param, 1); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); if (!err) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); @@ -6025,6 +6115,9 @@ static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err) static int stop_discovery_sync(struct hci_dev *hdev, void *data) { + if (!mgmt_pending_listed(hdev, data)) + return -ECANCELED; + return hci_stop_discovery_sync(hdev); } @@ -6234,14 +6327,18 @@ static void enable_advertising_instance(struct hci_dev *hdev, int err) static void set_advertising_complete(struct hci_dev *hdev, void *data, int err) { + struct mgmt_pending_cmd *cmd = data; struct cmd_lookup match = { NULL, hdev }; u8 instance; struct adv_info *adv_instance; u8 status = mgmt_status(err); + if (err == -ECANCELED || !mgmt_pending_valid(hdev, data)) + return; + if (status) { - mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, true, - cmd_status_rsp, &status); + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, status); + mgmt_pending_free(cmd); return; } @@ -6250,8 +6347,7 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err) else hci_dev_clear_flag(hdev, HCI_ADVERTISING); - mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, true, settings_rsp, - &match); + settings_rsp(cmd, &match); new_settings(hdev, match.sk); @@ -6283,10 +6379,23 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err) static int set_adv_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_mode *cp = cmd->param; - u8 val = !!cp->val; + struct mgmt_mode cp; + u8 val; - if (cp->val == 0x02) + mutex_lock(&hdev->mgmt_pending_lock); + + if (!__mgmt_pending_listed(hdev, cmd)) { + mutex_unlock(&hdev->mgmt_pending_lock); + return -ECANCELED; + } + + memcpy(&cp, cmd->param, sizeof(cp)); + + mutex_unlock(&hdev->mgmt_pending_lock); + + val = !!cp.val; + + if (cp.val == 0x02) hci_dev_set_flag(hdev, HCI_ADVERTISING_CONNECTABLE); else hci_dev_clear_flag(hdev, HCI_ADVERTISING_CONNECTABLE); @@ -8039,10 +8148,6 @@ static void read_local_oob_ext_data_complete(struct hci_dev *hdev, void *data, u8 status = mgmt_status(err); u16 eir_len; - if (err == -ECANCELED || - cmd != pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev)) - return; - if (!status) { if (!skb) status = MGMT_STATUS_FAILED; @@ -8149,7 +8254,7 @@ done: kfree_skb(skb); kfree(mgmt_rp); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); } static int read_local_ssp_oob_req(struct hci_dev *hdev, struct sock *sk, @@ -8158,7 +8263,7 @@ static int read_local_ssp_oob_req(struct hci_dev *hdev, struct sock *sk, struct mgmt_pending_cmd *cmd; int err; - cmd = mgmt_pending_add(sk, MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev, + cmd = mgmt_pending_new(sk, MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev, cp, sizeof(*cp)); if (!cmd) return -ENOMEM; diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c index a88a07da3947..aa7b5585cb26 100644 --- a/net/bluetooth/mgmt_util.c +++ b/net/bluetooth/mgmt_util.c @@ -320,6 +320,52 @@ void mgmt_pending_remove(struct mgmt_pending_cmd *cmd) mgmt_pending_free(cmd); } +bool __mgmt_pending_listed(struct hci_dev *hdev, struct mgmt_pending_cmd *cmd) +{ + struct mgmt_pending_cmd *tmp; + + lockdep_assert_held(&hdev->mgmt_pending_lock); + + if (!cmd) + return false; + + list_for_each_entry(tmp, &hdev->mgmt_pending, list) { + if (cmd == tmp) + return true; + } + + return false; +} + +bool mgmt_pending_listed(struct hci_dev *hdev, struct mgmt_pending_cmd *cmd) +{ + bool listed; + + mutex_lock(&hdev->mgmt_pending_lock); + listed = __mgmt_pending_listed(hdev, cmd); + mutex_unlock(&hdev->mgmt_pending_lock); + + return listed; +} + +bool mgmt_pending_valid(struct hci_dev *hdev, struct mgmt_pending_cmd *cmd) +{ + bool listed; + + if (!cmd) + return false; + + mutex_lock(&hdev->mgmt_pending_lock); + + listed = __mgmt_pending_listed(hdev, cmd); + if (listed) + list_del(&cmd->list); + + mutex_unlock(&hdev->mgmt_pending_lock); + + return listed; +} + void mgmt_mesh_foreach(struct hci_dev *hdev, void (*cb)(struct mgmt_mesh_tx *mesh_tx, void *data), void *data, struct sock *sk) diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h index 024e51dd6937..bcba8c9d8952 100644 --- a/net/bluetooth/mgmt_util.h +++ b/net/bluetooth/mgmt_util.h @@ -65,6 +65,9 @@ struct mgmt_pending_cmd *mgmt_pending_new(struct sock *sk, u16 opcode, void *data, u16 len); void mgmt_pending_free(struct mgmt_pending_cmd *cmd); void mgmt_pending_remove(struct mgmt_pending_cmd *cmd); +bool __mgmt_pending_listed(struct hci_dev *hdev, struct mgmt_pending_cmd *cmd); +bool mgmt_pending_listed(struct hci_dev *hdev, struct mgmt_pending_cmd *cmd); +bool mgmt_pending_valid(struct hci_dev *hdev, struct mgmt_pending_cmd *cmd); void mgmt_mesh_foreach(struct hci_dev *hdev, void (*cb)(struct mgmt_mesh_tx *mesh_tx, void *data), void *data, struct sock *sk); diff --git a/net/bridge/br.c b/net/bridge/br.c index 1885d0c315f0..c683baa3847f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -324,6 +324,13 @@ int br_boolopt_multi_toggle(struct net_bridge *br, int err = 0; int opt_id; + opt_id = find_next_bit(&bitmap, BITS_PER_LONG, BR_BOOLOPT_MAX); + if (opt_id != BITS_PER_LONG) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Unknown boolean option %d", + opt_id); + return -EINVAL; + } + for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) { bool on = !!(bm->optval & BIT(opt_id)); diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c index 39844f14eed8..797719cb227e 100644 --- a/net/can/j1939/bus.c +++ b/net/can/j1939/bus.c @@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) if (!ecu) ecu = j1939_ecu_create_locked(priv, name); err = PTR_ERR_OR_ZERO(ecu); - if (err) + if (err) { + if (j1939_address_is_unicast(sa)) + priv->ents[sa].nusers--; goto done; + } ecu->nusers++; /* TODO: do we care if ecu->addr != sa? */ diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 31a93cae5111..81f58924b4ac 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -212,6 +212,7 @@ void j1939_priv_get(struct j1939_priv *priv); /* notify/alert all j1939 sockets bound to ifindex */ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv); +void j1939_sk_netdev_event_unregister(struct j1939_priv *priv); int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk); void j1939_tp_init(struct j1939_priv *priv); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 7e8a20f2fc42..3706a872ecaf 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -377,6 +377,9 @@ static int j1939_netdev_notify(struct notifier_block *nb, j1939_sk_netdev_event_netdown(priv); j1939_ecu_unmap_all(priv); break; + case NETDEV_UNREGISTER: + j1939_sk_netdev_event_unregister(priv); + break; } j1939_priv_put(priv); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 3d8b588822f9..88e7160d4248 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -521,6 +521,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa); if (ret) { j1939_netdev_stop(priv); + jsk->priv = NULL; + synchronize_rcu(); + j1939_priv_put(priv); goto out_release_sock; } @@ -1300,6 +1303,55 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) read_unlock_bh(&priv->j1939_socks_lock); } +void j1939_sk_netdev_event_unregister(struct j1939_priv *priv) +{ + struct sock *sk; + struct j1939_sock *jsk; + bool wait_rcu = false; + +rescan: /* The caller is holding a ref on this "priv" via j1939_priv_get_by_ndev(). */ + read_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + /* Skip if j1939_jsk_add() is not called on this socket. */ + if (!(jsk->state & J1939_SOCK_BOUND)) + continue; + sk = &jsk->sk; + sock_hold(sk); + read_unlock_bh(&priv->j1939_socks_lock); + /* Check if j1939_jsk_del() is not yet called on this socket after holding + * socket's lock, for both j1939_sk_bind() and j1939_sk_release() call + * j1939_jsk_del() with socket's lock held. + */ + lock_sock(sk); + if (jsk->state & J1939_SOCK_BOUND) { + /* Neither j1939_sk_bind() nor j1939_sk_release() called j1939_jsk_del(). + * Make this socket no longer bound, by pretending as if j1939_sk_bind() + * dropped old references but did not get new references. + */ + j1939_jsk_del(priv, jsk); + j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); + j1939_netdev_stop(priv); + /* Call j1939_priv_put() now and prevent j1939_sk_sock_destruct() from + * calling the corresponding j1939_priv_put(). + * + * j1939_sk_sock_destruct() is supposed to call j1939_priv_put() after + * an RCU grace period. But since the caller is holding a ref on this + * "priv", we can defer synchronize_rcu() until immediately before + * the caller calls j1939_priv_put(). + */ + j1939_priv_put(priv); + jsk->priv = NULL; + wait_rcu = true; + } + release_sock(sk); + sock_put(sk); + goto rescan; + } + read_unlock_bh(&priv->j1939_socks_lock); + if (wait_rcu) + synchronize_rcu(); +} + static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index d1b5705dc0c6..9f6d860411cb 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1524,7 +1524,7 @@ static void con_fault_finish(struct ceph_connection *con) * in case we faulted due to authentication, invalidate our * current tickets so that we can get new ones. */ - if (con->v1.auth_retry) { + if (!ceph_msgr2(from_msgr(con->msgr)) && con->v1.auth_retry) { dout("auth_retry %d, invalidating\n", con->v1.auth_retry); if (con->ops->invalidate_authorizer) con->ops->invalidate_authorizer(con); @@ -1714,9 +1714,10 @@ static void clear_standby(struct ceph_connection *con) { /* come back from STANDBY? */ if (con->state == CEPH_CON_S_STANDBY) { - dout("clear_standby %p and ++connect_seq\n", con); + dout("clear_standby %p\n", con); con->state = CEPH_CON_S_PREOPEN; - con->v1.connect_seq++; + if (!ceph_msgr2(from_msgr(con->msgr))) + con->v1.connect_seq++; WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING)); WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)); } diff --git a/net/core/dev.c b/net/core/dev.c index 93a25d87b86b..8d49b2198d07 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6965,7 +6965,7 @@ static void napi_stop_kthread(struct napi_struct *napi) * the kthread. */ while (true) { - if (!test_bit(NAPIF_STATE_SCHED_THREADED, &napi->state)) + if (!test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) break; msleep(20); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 9c0ad7f4b5d8..ad54b12d4b4c 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -464,8 +464,15 @@ int generic_hwtstamp_get_lower(struct net_device *dev, if (!netif_device_present(dev)) return -ENODEV; - if (ops->ndo_hwtstamp_get) - return dev_get_hwtstamp_phylib(dev, kernel_cfg); + if (ops->ndo_hwtstamp_get) { + int err; + + netdev_lock_ops(dev); + err = dev_get_hwtstamp_phylib(dev, kernel_cfg); + netdev_unlock_ops(dev); + + return err; + } /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg); @@ -481,8 +488,15 @@ int generic_hwtstamp_set_lower(struct net_device *dev, if (!netif_device_present(dev)) return -ENODEV; - if (ops->ndo_hwtstamp_set) - return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack); + if (ops->ndo_hwtstamp_set) { + int err; + + netdev_lock_ops(dev); + err = dev_set_hwtstamp_phylib(dev, kernel_cfg, extack); + netdev_unlock_ops(dev); + + return err; + } /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index c28cd6665444..3c2dc4c5e683 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1328,7 +1328,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) struct netdev_rx_queue *queue = &dev->_rx[i]; struct kobject *kobj = &queue->kobj; - if (!refcount_read(&dev_net(dev)->ns.count)) + if (!check_net(dev_net(dev))) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); @@ -2061,7 +2061,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; - if (!refcount_read(&dev_net(dev)->ns.count)) + if (!check_net(dev_net(dev))) queue->kobj.uevent_suppress = 1; if (netdev_uses_bql(dev)) @@ -2315,7 +2315,7 @@ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; - if (!refcount_read(&dev_net(ndev)->ns.count)) + if (!check_net(dev_net(ndev))) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 1b6f3826dd0e..b0e0f22d7b21 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -20,6 +20,7 @@ #include <linux/sched/task.h> #include <linux/uidgid.h> #include <linux/proc_fs.h> +#include <linux/nstree.h> #include <net/aligned_data.h> #include <net/sock.h> @@ -314,7 +315,7 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { int id; - if (refcount_read(&net->ns.count) == 0) + if (!check_net(net)) return NETNSA_NSID_NOT_ASSIGNED; spin_lock(&net->nsid_lock); @@ -397,10 +398,15 @@ static __net_init void preinit_net_sysctl(struct net *net) } /* init code that must occur even if setup_net() is not called. */ -static __net_init void preinit_net(struct net *net, struct user_namespace *user_ns) +static __net_init int preinit_net(struct net *net, struct user_namespace *user_ns) { + int ret; + + ret = ns_common_init(net); + if (ret) + return ret; + refcount_set(&net->passive, 1); - refcount_set(&net->ns.count, 1); ref_tracker_dir_init(&net->refcnt_tracker, 128, "net_refcnt"); ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net_notrefcnt"); @@ -420,6 +426,7 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_ INIT_LIST_HEAD(&net->ptype_all); INIT_LIST_HEAD(&net->ptype_specific); preinit_net_sysctl(net); + return 0; } /* @@ -432,7 +439,7 @@ static __net_init int setup_net(struct net *net) LIST_HEAD(net_exit_list); int error = 0; - net->net_cookie = atomic64_inc_return(&net_aligned_data.net_cookie); + net->net_cookie = ns_tree_gen_id(&net->ns); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); @@ -442,6 +449,7 @@ static __net_init int setup_net(struct net *net) down_write(&net_rwsem); list_add_tail_rcu(&net->list, &net_namespace_list); up_write(&net_rwsem); + ns_tree_add_raw(net); out: return error; @@ -539,7 +547,7 @@ void net_drop_ns(void *p) net_passive_dec(net); } -struct net *copy_net_ns(unsigned long flags, +struct net *copy_net_ns(u64 flags, struct user_namespace *user_ns, struct net *old_net) { struct ucounts *ucounts; @@ -559,7 +567,9 @@ struct net *copy_net_ns(unsigned long flags, goto dec_ucounts; } - preinit_net(net, user_ns); + rv = preinit_net(net, user_ns); + if (rv < 0) + goto dec_ucounts; net->ucounts = ucounts; get_user_ns(user_ns); @@ -573,6 +583,7 @@ struct net *copy_net_ns(unsigned long flags, if (rv < 0) { put_userns: + ns_common_free(net); #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif @@ -659,8 +670,10 @@ static void cleanup_net(struct work_struct *work) /* Don't let anyone else find us. */ down_write(&net_rwsem); - llist_for_each_entry(net, net_kill_list, cleanup_list) + llist_for_each_entry(net, net_kill_list, cleanup_list) { + ns_tree_remove(net); list_del_rcu(&net->list); + } /* Cache last net. After we unlock rtnl, no one new net * added to net_namespace_list can assign nsid pointer * to a net from net_kill_list (see peernet2id_alloc()). @@ -693,6 +706,7 @@ static void cleanup_net(struct work_struct *work) /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); + ns_common_free(net); dec_net_namespaces(net->ucounts); #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); @@ -812,31 +826,12 @@ static void net_ns_net_debugfs(struct net *net) static __net_init int net_ns_net_init(struct net *net) { -#ifdef CONFIG_NET_NS - net->ns.ops = &netns_operations; -#endif - net->ns.inum = PROC_NET_INIT_INO; - if (net != &init_net) { - int ret = ns_alloc_inum(&net->ns); - if (ret) - return ret; - } net_ns_net_debugfs(net); return 0; } -static __net_exit void net_ns_net_exit(struct net *net) -{ - /* - * Initial network namespace doesn't exit so we don't need any - * special checks here. - */ - ns_free_inum(&net->ns); -} - static struct pernet_operations __net_initdata net_ns_ops = { .init = net_ns_net_init, - .exit = net_ns_net_exit, }; static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { @@ -1282,7 +1277,12 @@ void __init net_ns_init(void) #ifdef CONFIG_KEYS init_net.key_domain = &init_net_key_domain; #endif - preinit_net(&init_net, &init_user_ns); + /* + * This currently cannot fail as the initial network namespace + * has a static inode number. + */ + if (preinit_net(&init_net, &init_user_ns)) + panic("Could not preinitialize the initial network namespace"); down_write(&pernet_ops_rwsem); if (setup_net(&init_net)) @@ -1517,11 +1517,6 @@ static struct ns_common *netns_get(struct task_struct *task) return net ? &net->ns : NULL; } -static inline struct net *to_net_ns(struct ns_common *ns) -{ - return container_of(ns, struct net, ns); -} - static void netns_put(struct ns_common *ns) { put_net(to_net_ns(ns)); @@ -1548,7 +1543,6 @@ static struct user_namespace *netns_owner(struct ns_common *ns) const struct proc_ns_operations netns_operations = { .name = "net", - .type = CLONE_NEWNET, .get = netns_get, .put = netns_put, .install = netns_install, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ee0274417948..1c0279b9cb9f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6667,7 +6667,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, return NULL; while (data_len) { - if (nr_frags == MAX_SKB_FRAGS - 1) + if (nr_frags == MAX_SKB_FRAGS) goto failure; while (order && PAGE_ALIGN(data_len) < (PAGE_SIZE << order)) order--; diff --git a/net/devlink/rate.c b/net/devlink/rate.c index 110b3fa8a0b1..264fb82cba19 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -34,7 +34,7 @@ devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info) static struct devlink_rate * devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name) { - static struct devlink_rate *devlink_rate; + struct devlink_rate *devlink_rate; list_for_each_entry(devlink_rate, &devlink->rate_list, list) { if (devlink_rate_is_node(devlink_rate) && @@ -819,8 +819,8 @@ EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy); */ void devl_rate_nodes_destroy(struct devlink *devlink) { - static struct devlink_rate *devlink_rate, *tmp; const struct devlink_ops *ops = devlink->ops; + struct devlink_rate *devlink_rate, *tmp; devl_assert_locked(devlink); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 4f58648a27ad..92e6a681c797 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -905,7 +905,7 @@ int ethtool_net_get_ts_info_by_phc(struct net_device *dev, int err; if (!ops->get_ts_info) - return -ENODEV; + return -EOPNOTSUPP; /* Does ptp comes from netdev */ ethtool_init_tsinfo(info); @@ -973,7 +973,7 @@ int ethtool_get_ts_info_by_phc(struct net_device *dev, int err; err = ethtool_net_get_ts_info_by_phc(dev, info, hwprov_desc); - if (err == -ENODEV) { + if (err == -ENODEV || err == -EOPNOTSUPP) { struct phy_device *phy; phy = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 88657255fec1..fbbc3ccf9df6 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -49,7 +49,7 @@ static bool hsr_check_carrier(struct hsr_port *master) ASSERT_RTNL(); - hsr_for_each_port(master->hsr, port) { + hsr_for_each_port_rtnl(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; @@ -105,7 +105,7 @@ int hsr_get_max_mtu(struct hsr_priv *hsr) struct hsr_port *port; mtu_max = ETH_DATA_LEN; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); @@ -139,7 +139,7 @@ static int hsr_dev_open(struct net_device *dev) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -172,7 +172,7 @@ static int hsr_dev_close(struct net_device *dev) struct hsr_priv *hsr; hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -205,7 +205,7 @@ static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); @@ -226,6 +226,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; + rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; @@ -238,6 +239,8 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } + rcu_read_unlock(); + return NETDEV_TX_OK; } @@ -484,7 +487,7 @@ static void hsr_set_rx_mode(struct net_device *dev) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -506,7 +509,7 @@ static void hsr_change_rx_flags(struct net_device *dev, int change) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -534,7 +537,7 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; @@ -580,7 +583,7 @@ static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: @@ -672,9 +675,14 @@ struct net_device *hsr_get_port_ndev(struct net_device *ndev, struct hsr_priv *hsr = netdev_priv(ndev); struct hsr_port *port; + rcu_read_lock(); hsr_for_each_port(hsr, port) - if (port->type == pt) + if (port->type == pt) { + dev_hold(port->dev); + rcu_read_unlock(); return port->dev; + } + rcu_read_unlock(); return NULL; } EXPORT_SYMBOL(hsr_get_port_ndev); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 192893c3f2ec..bc94b07101d8 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -22,7 +22,7 @@ static bool hsr_slave_empty(struct hsr_priv *hsr) { struct hsr_port *port; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) return false; return true; @@ -134,7 +134,7 @@ struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) { struct hsr_port *port; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type == pt) return port; return NULL; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 135ec5fce019..33b0d2460c9b 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -224,6 +224,9 @@ struct hsr_priv { #define hsr_for_each_port(hsr, port) \ list_for_each_entry_rcu((port), &(hsr)->ports, port_list) +#define hsr_for_each_port_rtnl(hsr, port) \ + list_for_each_entry_rcu((port), &(hsr)->ports, port_list, lockdep_rtnl_is_held()) + struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt); /* Caller must ensure skb is a valid HSR frame */ diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 875ff923a8ed..56a117560c0c 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -329,13 +329,13 @@ restart: TCPF_NEW_SYN_RECV)) continue; - if (refcount_read(&sock_net(sk)->ns.count)) + if (check_net(sock_net(sk))) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (refcount_read(&sock_net(sk)->ns.count)) { + if (check_net(sock_net(sk))) { sock_gen_put(sk); goto restart; } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index cc9915543637..2e61ac137128 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -206,6 +206,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) return -EINVAL; + if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); @@ -300,6 +303,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) return -EINVAL; + if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 29118c43ebf5..34137768e7f9 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2399,6 +2399,13 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, return -EINVAL; } + if (!list_empty(&old->grp_list) && + rtnl_dereference(new->nh_info)->fdb_nh != + rtnl_dereference(old->nh_info)->fdb_nh) { + NL_SET_ERR_MSG(extack, "Cannot change nexthop FDB status while in a group"); + return -EINVAL; + } + err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); if (err) return err; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 71a956fbfc55..ad76556800f2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3327,6 +3327,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + struct request_sock *req; u32 seq; if (old_state != TCP_CLOSE) @@ -3442,6 +3443,10 @@ int tcp_disconnect(struct sock *sk, int flags) /* Clean up fastopen related fields */ + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) + reqsk_fastopen_remove(sk, req, false); tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index bbb8d5f0eae7..3338b6cc85c4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1178,7 +1178,9 @@ void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb) if (!ao) return; - WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); + /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ + if (skb) + WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); ao->rcv_sne = 0; hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ba581785adb4..a268e1595b22 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -408,8 +408,11 @@ more_data: if (!psock->cork) { psock->cork = kzalloc(sizeof(*psock->cork), GFP_ATOMIC | __GFP_NOWARN); - if (!psock->cork) + if (!psock->cork) { + sk_msg_free(sk, msg); + *copied = 0; return -ENOMEM; + } } memcpy(psock->cork, msg, sizeof(*msg)); return 0; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 03c068ea27b6..b67f94c60f9f 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -912,7 +912,7 @@ static void tcp_metrics_flush_all(struct net *net) spin_lock_bh(&tcp_metrics_lock); for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { match = net ? net_eq(tm_net(tm), net) : - !refcount_read(&tm_net(tm)->ns.count); + !check_net(tm_net(tm)); if (match) { rcu_assign_pointer(*pp, tm->tcpm_next); kfree_rcu(tm, rcu_head); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2a8ea28442b2..1103b3341a70 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -985,13 +985,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return false; } - if (mp_opt->deny_join_id0) - WRITE_ONCE(msk->pm.remote_deny_join_id0, true); - if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); set_fully_established: + if (mp_opt->deny_join_id0) + WRITE_ONCE(msk->pm.remote_deny_join_id0, true); + mptcp_data_lock((struct sock *)msk); __mptcp_subflow_fully_established(msk, subflow, mp_opt); mptcp_data_unlock((struct sock *)msk); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 50aaf259959a..ce7d42d3bd00 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -408,6 +408,7 @@ static int mptcp_event_created(struct sk_buff *skb, const struct sock *ssk) { int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)); + u16 flags = 0; if (err) return err; @@ -415,6 +416,12 @@ static int mptcp_event_created(struct sk_buff *skb, if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side))) return -EMSGSIZE; + if (READ_ONCE(msk->pm.remote_deny_join_id0)) + flags |= MPTCP_PM_EV_FLAG_DENY_JOIN_ID0; + + if (flags && nla_put_u16(skb, MPTCP_ATTR_FLAGS, flags)) + return -EMSGSIZE; + return mptcp_event_add_subflow(skb, ssk); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e6fd97b21e9e..5e497a83e967 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -371,6 +371,20 @@ static void mptcp_close_wake_up(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } +static void mptcp_shutdown_subflows(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + + slow = lock_sock_fast(ssk); + tcp_shutdown(ssk, SEND_SHUTDOWN); + unlock_sock_fast(ssk, slow); + } +} + /* called under the msk socket lock */ static bool mptcp_pending_data_fin_ack(struct sock *sk) { @@ -395,6 +409,7 @@ static void mptcp_check_data_fin_ack(struct sock *sk) break; case TCP_CLOSING: case TCP_LAST_ACK: + mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; } @@ -563,6 +578,7 @@ static bool mptcp_check_data_fin(struct sock *sk) mptcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: + mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; default: diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 2c267aff95be..2abe6f1e9940 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1532,13 +1532,12 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) { static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK; struct sock *sk = (struct sock *)msk; + bool keep_open; - if (ssk->sk_prot->keepalive) { - if (sock_flag(sk, SOCK_KEEPOPEN)) - ssk->sk_prot->keepalive(ssk, 1); - else - ssk->sk_prot->keepalive(ssk, 0); - } + keep_open = sock_flag(sk, SOCK_KEEPOPEN); + if (ssk->sk_prot->keepalive) + ssk->sk_prot->keepalive(ssk, keep_open); + sock_valbool_flag(ssk, SOCK_KEEPOPEN, keep_open); ssk->sk_priority = sk->sk_priority; ssk->sk_bound_dev_if = sk->sk_bound_dev_if; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3f1b62a9fe88..f31a3a79531a 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -883,6 +883,10 @@ create_child: ctx->subflow_id = 1; owner = mptcp_sk(ctx->conn); + + if (mp_opt.deny_join_id0) + WRITE_ONCE(owner->pm.remote_deny_join_id0, true); + mptcp_pm_new_connection(owner, child, 1); /* with OoO packets we can reach here without ingress diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c1082de09656..c3c73411c40c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1131,11 +1131,14 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, return ERR_PTR(-ENOENT); } -static __be16 nft_base_seq(const struct net *net) +static unsigned int nft_base_seq(const struct net *net) { - struct nftables_pernet *nft_net = nft_pernet(net); + return READ_ONCE(net->nft.base_seq); +} - return htons(nft_net->base_seq & 0xffff); +static __be16 nft_base_seq_be16(const struct net *net) +{ + return htons(nft_base_seq(net) & 0xffff); } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { @@ -1155,7 +1158,7 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -1248,7 +1251,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -2030,7 +2033,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -2133,7 +2136,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -3671,7 +3674,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0, - nft_base_seq(net)); + nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -3839,7 +3842,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -4050,7 +4053,7 @@ static int nf_tables_getrule_reset(struct sk_buff *skb, buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_RULE_TABLE]), (char *)nla_data(nla[NFTA_RULE_TABLE]), - nft_net->base_seq); + nft_base_seq(net)); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); kfree(buf); @@ -4887,7 +4890,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), flags, ctx->family, NFNETLINK_V0, - nft_base_seq(ctx->net)); + nft_base_seq_be16(ctx->net)); if (!nlh) goto nla_put_failure; @@ -5032,7 +5035,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && @@ -6209,7 +6212,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && @@ -6238,7 +6241,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) seq = cb->nlh->nlmsg_seq; nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI, - table->family, NFNETLINK_V0, nft_base_seq(net)); + table->family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -6331,7 +6334,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, - NFNETLINK_V0, nft_base_seq(ctx->net)); + NFNETLINK_V0, nft_base_seq_be16(ctx->net)); if (!nlh) goto nla_put_failure; @@ -6630,7 +6633,7 @@ static int nf_tables_getsetelem_reset(struct sk_buff *skb, } nelems++; } - audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems); + audit_log_nft_set_reset(dump_ctx.ctx.table, nft_base_seq(info->net), nelems); out_unlock: rcu_read_unlock(); @@ -8381,7 +8384,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -8446,7 +8449,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -8480,7 +8483,7 @@ cont: idx++; } if (ctx->reset && entries) - audit_log_obj_reset(table, nft_net->base_seq, entries); + audit_log_obj_reset(table, nft_base_seq(net), entries); if (rc < 0) break; } @@ -8649,7 +8652,7 @@ static int nf_tables_getobj_reset(struct sk_buff *skb, buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_OBJ_TABLE]), (char *)nla_data(nla[NFTA_OBJ_TABLE]), - nft_net->base_seq); + nft_base_seq(net)); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); @@ -8754,9 +8757,8 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp) { - struct nftables_pernet *nft_net = nft_pernet(net); char *buf = kasprintf(gfp, "%s:%u", - table->name, nft_net->base_seq); + table->name, nft_base_seq(net)); audit_log_nfcfg(buf, family, @@ -9442,7 +9444,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -9511,7 +9513,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -9696,17 +9698,16 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { - struct nftables_pernet *nft_net = nft_pernet(net); struct nlmsghdr *nlh; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC, - NFNETLINK_V0, nft_base_seq(net)); + NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_base_seq(net))) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; @@ -10968,11 +10969,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - base_seq = READ_ONCE(nft_net->base_seq); + base_seq = nft_base_seq(net); while (++base_seq == 0) ; - WRITE_ONCE(nft_net->base_seq, base_seq); + /* pairs with smp_load_acquire in nft_lookup_eval */ + smp_store_release(&net->nft.base_seq, base_seq); gc_seq = nft_gc_seq_begin(nft_net); @@ -11181,7 +11183,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); - nf_tables_commit_audit_log(&adl, nft_net->base_seq); + nf_tables_commit_audit_log(&adl, nft_base_seq(net)); nft_gc_seq_end(nft_net, gc_seq); nft_net->validate_state = NFT_VALIDATE_SKIP; @@ -11506,7 +11508,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid) mutex_lock(&nft_net->commit_mutex); nft_net->tstamp = get_jiffies_64(); - genid_ok = genid == 0 || nft_net->base_seq == genid; + genid_ok = genid == 0 || nft_base_seq(net) == genid; if (!genid_ok) mutex_unlock(&nft_net->commit_mutex); @@ -12143,7 +12145,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); - nft_net->base_seq = 1; + net->nft.base_seq = 1; nft_net->gc_seq = 0; nft_net->validate_state = NFT_VALIDATE_SKIP; INIT_WORK(&nft_net->destroy_work, nf_tables_trans_destroy_work); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 40c602ffbcba..58c5b14889c4 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -24,11 +24,11 @@ struct nft_lookup { struct nft_set_binding binding; }; -#ifdef CONFIG_MITIGATION_RETPOLINE -const struct nft_set_ext * -nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key) +static const struct nft_set_ext * +__nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { +#ifdef CONFIG_MITIGATION_RETPOLINE if (set->ops == &nft_set_hash_fast_type.ops) return nft_hash_lookup_fast(net, set, key); if (set->ops == &nft_set_hash_type.ops) @@ -51,10 +51,46 @@ nft_set_do_lookup(const struct net *net, const struct nft_set *set, return nft_rbtree_lookup(net, set, key); WARN_ON_ONCE(1); +#endif return set->ops->lookup(net, set, key); } + +static unsigned int nft_base_seq(const struct net *net) +{ + /* pairs with smp_store_release() in nf_tables_commit() */ + return smp_load_acquire(&net->nft.base_seq); +} + +static bool nft_lookup_should_retry(const struct net *net, unsigned int seq) +{ + return unlikely(seq != nft_base_seq(net)); +} + +const struct nft_set_ext * +nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) +{ + const struct nft_set_ext *ext; + unsigned int base_seq; + + do { + base_seq = nft_base_seq(net); + + ext = __nft_set_do_lookup(net, set, key); + if (ext) + break; + /* No match? There is a small chance that lookup was + * performed in the old generation, but nf_tables_commit() + * already unlinked a (matching) element. + * + * We need to repeat the lookup to make sure that we didn't + * miss a matching element in the new generation. + */ + } while (nft_lookup_should_retry(net, base_seq)); + + return ext; +} EXPORT_SYMBOL_GPL(nft_set_do_lookup); -#endif void nft_lookup_eval(const struct nft_expr *expr, struct nft_regs *regs, diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index c24c922f895d..8d3f040a904a 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -226,7 +226,8 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, const struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be; - list_for_each_entry_rcu(be, &priv->list, head) { + list_for_each_entry_rcu(be, &priv->list, head, + lockdep_is_held(&nft_pernet(ctx->net)->commit_mutex)) { if (iter->count < iter->skip) goto cont; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9a10251228fd..793790d79d13 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -510,6 +510,23 @@ out: * * This function is called from the data path. It will search for * an element matching the given key in the current active copy. + * Unlike other set types, this uses NFT_GENMASK_ANY instead of + * nft_genmask_cur(). + * + * This is because new (future) elements are not reachable from + * priv->match, they get added to priv->clone instead. + * When the commit phase flips the generation bitmask, the + * 'now old' entries are skipped but without the 'now current' + * elements becoming visible. Using nft_genmask_cur() thus creates + * inconsistent state: matching old entries get skipped but thew + * newly matching entries are unreachable. + * + * GENMASK will still find the 'now old' entries which ensures consistent + * priv->match view. + * + * nft_pipapo_commit swaps ->clone and ->match shortly after the + * genbit flip. As ->clone doesn't contain the old entries in the first + * place, lookup will only find the now-current ones. * * Return: ntables API extension pointer or NULL if no match. */ @@ -518,12 +535,11 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { struct nft_pipapo *priv = nft_set_priv(set); - u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_elem *e; m = rcu_dereference(priv->match); - e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64()); + e = pipapo_get(m, (const u8 *)key, NFT_GENMASK_ANY, get_jiffies_64()); return e ? &e->ext : NULL; } diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 2f090e253caf..c0884fa68c79 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1152,7 +1152,6 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); const struct nft_set_ext *ext = NULL; struct nft_pipapo_scratch *scratch; - u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; @@ -1248,8 +1247,7 @@ next_match: if (last) { const struct nft_set_ext *e = &f->mt[ret].e->ext; - if (unlikely(nft_set_elem_expired(e) || - !nft_set_elem_active(e, genmask))) + if (unlikely(nft_set_elem_expired(e))) goto next_match; ext = e; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 938a257c069e..b1f04168ec93 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -77,7 +77,9 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; - interval = rbe; + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_rbtree_elem_expired(rbe)) + interval = rbe; } else if (d > 0) parent = rcu_dereference_raw(parent->rb_right); else { @@ -102,8 +104,6 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } if (set->flags & NFT_SET_INTERVAL && interval != NULL && - nft_set_elem_active(&interval->ext, genmask) && - !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) return &interval->ext; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 104732d34543..978c129c6095 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1836,6 +1836,9 @@ static int genl_bind(struct net *net, int group) !ns_capable(net->user_ns, CAP_SYS_ADMIN)) ret = -EPERM; + if (ret) + break; + if (family->bind) family->bind(i); diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 28c1b0022178..bd861191157b 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -133,12 +133,15 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len, &off, PAGE_SIZE); - if (unlikely(ret != ibmr->sg_dma_len)) - return ret < 0 ? ret : -EINVAL; + if (unlikely(ret != ibmr->sg_dma_len)) { + ret = ret < 0 ? ret : -EINVAL; + goto out_inc; + } - if (cmpxchg(&frmr->fr_state, - FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) - return -EBUSY; + if (cmpxchg(&frmr->fr_state, FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) { + ret = -EBUSY; + goto out_inc; + } atomic_inc(&ibmr->ic->i_fastreg_inuse_count); @@ -166,11 +169,10 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) /* Failure here can be because of -ENOMEM as well */ rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); - atomic_inc(&ibmr->ic->i_fastreg_wrs); if (printk_ratelimit()) pr_warn("RDS/IB: %s returned error(%d)\n", __func__, ret); - goto out; + goto out_inc; } /* Wait for the registration to complete in order to prevent an invalid @@ -179,8 +181,10 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) */ wait_event(frmr->fr_reg_done, !frmr->fr_reg); -out: + return ret; +out_inc: + atomic_inc(&ibmr->ic->i_fastreg_wrs); return ret; } diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 41e657e97761..cf2dcec6ce5a 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -94,10 +94,10 @@ static const struct dmi_system_id rfkill_gpio_deny_table[] = { static int rfkill_gpio_probe(struct platform_device *pdev) { struct rfkill_gpio_data *rfkill; - struct gpio_desc *gpio; + const char *type_name = NULL; const char *name_property; const char *type_property; - const char *type_name; + struct gpio_desc *gpio; int ret; if (dmi_check_system(rfkill_gpio_deny_table)) diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index 1e19c605bcc8..dce5a3d8a964 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -475,7 +475,7 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, struct krb5_buffer metadata; unsigned int offset = sp->offset, len = sp->len; size_t data_offset = 0, data_len = len; - u32 ac; + u32 ac = 0; int ret = -ENOMEM; _enter(""); @@ -499,9 +499,10 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, ret = rxgk_verify_mic_skb(gk->krb5, gk->rx_Kc, &metadata, skb, &offset, &len, &ac); kfree(hdr); - if (ret == -EPROTO) { - rxrpc_abort_eproto(call, skb, ac, - rxgk_abort_1_verify_mic_eproto); + if (ret < 0) { + if (ret != -ENOMEM) + rxrpc_abort_eproto(call, skb, ac, + rxgk_abort_1_verify_mic_eproto); } else { sp->offset = offset; sp->len = len; @@ -524,15 +525,16 @@ static int rxgk_verify_packet_encrypted(struct rxrpc_call *call, struct rxgk_header hdr; unsigned int offset = sp->offset, len = sp->len; int ret; - u32 ac; + u32 ac = 0; _enter(""); ret = rxgk_decrypt_skb(gk->krb5, gk->rx_enc, skb, &offset, &len, &ac); - if (ret == -EPROTO) - rxrpc_abort_eproto(call, skb, ac, rxgk_abort_2_decrypt_eproto); - if (ret < 0) + if (ret < 0) { + if (ret != -ENOMEM) + rxrpc_abort_eproto(call, skb, ac, rxgk_abort_2_decrypt_eproto); goto error; + } if (len < sizeof(hdr)) { ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, diff --git a/net/rxrpc/rxgk_app.c b/net/rxrpc/rxgk_app.c index b94b77a1c317..30275cb5ba3e 100644 --- a/net/rxrpc/rxgk_app.c +++ b/net/rxrpc/rxgk_app.c @@ -54,6 +54,10 @@ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, _enter(""); + if (ticket_len < 10 * sizeof(__be32)) + return rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO, + rxgk_abort_resp_short_yfs_tkt); + /* Get the session key length */ ret = skb_copy_bits(skb, ticket_offset, tmp, sizeof(tmp)); if (ret < 0) @@ -187,7 +191,7 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, struct key *server_key; unsigned int ticket_offset, ticket_len; u32 kvno, enctype; - int ret, ec; + int ret, ec = 0; struct { __be32 kvno; @@ -195,22 +199,23 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, __be32 token_len; } container; + if (token_len < sizeof(container)) + goto short_packet; + /* Decode the RXGK_TokenContainer object. This tells us which server * key we should be using. We can then fetch the key, get the secret * and set up the crypto to extract the token. */ if (skb_copy_bits(skb, token_offset, &container, sizeof(container)) < 0) - return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, - rxgk_abort_resp_tok_short); + goto short_packet; kvno = ntohl(container.kvno); enctype = ntohl(container.enctype); ticket_len = ntohl(container.token_len); ticket_offset = token_offset + sizeof(container); - if (xdr_round_up(ticket_len) > token_len - 3 * 4) - return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, - rxgk_abort_resp_tok_short); + if (xdr_round_up(ticket_len) > token_len - sizeof(container)) + goto short_packet; _debug("KVNO %u", kvno); _debug("ENC %u", enctype); @@ -236,9 +241,11 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, &ticket_offset, &ticket_len, &ec); crypto_free_aead(token_enc); token_enc = NULL; - if (ret < 0) - return rxrpc_abort_conn(conn, skb, ec, ret, - rxgk_abort_resp_tok_dec); + if (ret < 0) { + if (ret != -ENOMEM) + return rxrpc_abort_conn(conn, skb, ec, ret, + rxgk_abort_resp_tok_dec); + } ret = conn->security->default_decode_ticket(conn, skb, ticket_offset, ticket_len, _key); @@ -283,4 +290,8 @@ temporary_error: * also come out this way if the ticket decryption fails. */ return ret; + +short_packet: + return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, + rxgk_abort_resp_tok_short); } diff --git a/net/rxrpc/rxgk_common.h b/net/rxrpc/rxgk_common.h index 7370a5655985..80164d89e19c 100644 --- a/net/rxrpc/rxgk_common.h +++ b/net/rxrpc/rxgk_common.h @@ -88,11 +88,16 @@ int rxgk_decrypt_skb(const struct krb5_enctype *krb5, *_offset += offset; *_len = len; break; + case -EBADMSG: /* Checksum mismatch. */ case -EPROTO: - case -EBADMSG: *_error_code = RXGK_SEALEDINCON; break; + case -EMSGSIZE: + *_error_code = RXGK_PACKETSHORT; + break; + case -ENOPKG: /* Would prefer RXGK_BADETYPE, but not available for YFS. */ default: + *_error_code = RXGK_INCONSISTENCY; break; } @@ -127,11 +132,16 @@ int rxgk_verify_mic_skb(const struct krb5_enctype *krb5, *_offset += offset; *_len = len; break; + case -EBADMSG: /* Checksum mismatch */ case -EPROTO: - case -EBADMSG: *_error_code = RXGK_SEALEDINCON; break; + case -EMSGSIZE: + *_error_code = RXGK_PACKETSHORT; + break; + case -ENOPKG: /* Would prefer RXGK_BADETYPE, but not available for YFS. */ default: + *_error_code = RXGK_INCONSISTENCY; break; } diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c index 0eb00bbefd17..77cc1c6dc3e9 100644 --- a/net/smc/smc_loopback.c +++ b/net/smc/smc_loopback.c @@ -56,6 +56,7 @@ static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb, { struct smc_lo_dmb_node *dmb_node, *tmp_node; struct smc_lo_dev *ldev = smcd->priv; + struct folio *folio; int sba_idx, rc; /* check space for new dmb */ @@ -74,13 +75,16 @@ static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb, dmb_node->sba_idx = sba_idx; dmb_node->len = dmb->dmb_len; - dmb_node->cpu_addr = kzalloc(dmb_node->len, GFP_KERNEL | - __GFP_NOWARN | __GFP_NORETRY | - __GFP_NOMEMALLOC); - if (!dmb_node->cpu_addr) { + + /* not critical; fail under memory pressure and fallback to TCP */ + folio = folio_alloc(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | + __GFP_NORETRY | __GFP_ZERO, + get_order(dmb_node->len)); + if (!folio) { rc = -ENOMEM; goto err_node; } + dmb_node->cpu_addr = folio_address(folio); dmb_node->dma_addr = SMC_DMA_ADDR_INVALID; refcount_set(&dmb_node->refcnt, 1); @@ -122,7 +126,7 @@ static void __smc_lo_unregister_dmb(struct smc_lo_dev *ldev, write_unlock_bh(&ldev->dmb_ht_lock); clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask); - kvfree(dmb_node->cpu_addr); + folio_put(virt_to_folio(dmb_node->cpu_addr)); kfree(dmb_node); if (atomic_dec_and_test(&ldev->dmb_cnt)) diff --git a/net/socket.c b/net/socket.c index 682969deaed3..bac335ecee4c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1176,6 +1176,9 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; + if (iocb->ki_flags & IOCB_NOSIGNAL) + msg.msg_flags |= MSG_NOSIGNAL; + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 73bc39281ef5..9b45fbdc90ca 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -276,8 +276,6 @@ EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (unlikely(current->flags & PF_EXITING)) - return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c5f7bbf5775f..3aa987e7f072 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -407,9 +407,9 @@ xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags) iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, alert_kvec.iov_len); ret = sock_recvmsg(sock, &msg, flags); - if (ret > 0 && - tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { - iov_iter_revert(&msg.msg_iter, ret); + if (ret > 0) { + if (tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) + iov_iter_revert(&msg.msg_iter, ret); ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg, -EAGAIN); } diff --git a/net/tls/tls.h b/net/tls/tls.h index 4e077068e6d9..e4c42731ce39 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -141,6 +141,7 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx); int wait_on_pending_writer(struct sock *sk, long *timeo); void tls_err_abort(struct sock *sk, int err); +void tls_strp_abort_strp(struct tls_strparser *strp, int err); int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index d71643b494a1..98e12f0ff57e 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -13,7 +13,7 @@ static struct workqueue_struct *tls_strp_wq; -static void tls_strp_abort_strp(struct tls_strparser *strp, int err) +void tls_strp_abort_strp(struct tls_strparser *strp, int err) { if (strp->stopped) return; @@ -211,11 +211,17 @@ static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb, struct sk_buff *in_skb, unsigned int offset, size_t in_len) { + unsigned int nfrag = skb->len / PAGE_SIZE; size_t len, chunk; skb_frag_t *frag; int sz; - frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE]; + if (unlikely(nfrag >= skb_shinfo(skb)->nr_frags)) { + DEBUG_NET_WARN_ON_ONCE(1); + return -EMSGSIZE; + } + + frag = &skb_shinfo(skb)->frags[nfrag]; len = in_len; /* First make sure we got the header */ @@ -520,10 +526,8 @@ static int tls_strp_read_sock(struct tls_strparser *strp) tls_strp_load_anchor_with_queue(strp, inq); if (!strp->stm.full_len) { sz = tls_rx_msg_size(strp, strp->anchor); - if (sz < 0) { - tls_strp_abort_strp(strp, sz); + if (sz < 0) return sz; - } strp->stm.full_len = sz; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bac65d0d4e3e..daac9fd4be7e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2474,8 +2474,7 @@ int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb) return data_len + TLS_HEADER_SIZE; read_failure: - tls_err_abort(strp->sk, ret); - + tls_strp_abort_strp(strp, ret); return ret; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6d7c110814ff..768098dec231 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1387,7 +1387,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, * Get the parent directory, calculate the hash for last * component. */ - dentry = kern_path_create(AT_FDCWD, addr->name->sun_path, &parent, 0); + dentry = start_creating_path(AT_FDCWD, addr->name->sun_path, &parent, 0); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out; @@ -1417,7 +1417,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, unix_table_double_unlock(net, old_hash, new_hash); unix_insert_bsd_socket(sk); mutex_unlock(&u->bindlock); - done_path_create(&parent, dentry); + end_creating_path(&parent, dentry); return 0; out_unlock: @@ -1427,7 +1427,7 @@ out_unlink: /* failed after successful mknod? unlink what we'd created... */ vfs_unlink(idmap, d_inode(parent.dentry), dentry, NULL); out_path: - done_path_create(&parent, dentry); + end_creating_path(&parent, dentry); out: unix_release_addr(addr); return err == -EEXIST ? -EADDRINUSE : err; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 89519aa52893..852573423e52 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7062,7 +7062,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg80211_registered_device *rdev, struct net_device *dev, - const u8 *mac_addr, struct station_info *sinfo) + const u8 *mac_addr, struct station_info *sinfo, + bool link_stats) { void *hdr; struct nlattr *sinfoattr, *bss_param; @@ -7283,7 +7284,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, goto nla_put_failure; } - if (sinfo->valid_links) { + if (link_stats && sinfo->valid_links) { links = nla_nest_start(msg, NL80211_ATTR_MLO_LINKS); if (!links) goto nla_put_failure; @@ -7574,7 +7575,7 @@ static int nl80211_dump_station(struct sk_buff *skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev->netdev, mac_addr, - &sinfo) < 0) + &sinfo, false) < 0) goto out; sta_idx++; @@ -7635,7 +7636,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, info->snd_portid, info->snd_seq, 0, - rdev, dev, mac_addr, &sinfo) < 0) { + rdev, dev, mac_addr, &sinfo, false) < 0) { nlmsg_free(msg); return -ENOBUFS; } @@ -19680,7 +19681,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, return; if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, 0, 0, 0, - rdev, dev, mac_addr, sinfo) < 0) { + rdev, dev, mac_addr, sinfo, false) < 0) { nlmsg_free(msg); return; } @@ -19710,7 +19711,7 @@ void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr, } if (nl80211_send_station(msg, NL80211_CMD_DEL_STATION, 0, 0, 0, - rdev, dev, mac_addr, sinfo) < 0) { + rdev, dev, mac_addr, sinfo, false) < 0) { nlmsg_free(msg); return; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9c3acecc14b1..72e34bd2d925 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -36,6 +36,20 @@ #define TX_BATCH_SIZE 32 #define MAX_PER_SOCKET_BUDGET 32 +struct xsk_addr_node { + u64 addr; + struct list_head addr_node; +}; + +struct xsk_addr_head { + u32 num_descs; + struct list_head addrs_list; +}; + +static struct kmem_cache *xsk_tx_generic_cache; + +#define XSKCB(skb) ((struct xsk_addr_head *)((skb)->cb)) + void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { if (pool->cached_need_wakeup & XDP_WAKEUP_RX) @@ -532,24 +546,43 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags) return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); } -static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr) +static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool) { unsigned long flags; int ret; spin_lock_irqsave(&pool->cq_lock, flags); - ret = xskq_prod_reserve_addr(pool->cq, addr); + ret = xskq_prod_reserve(pool->cq); spin_unlock_irqrestore(&pool->cq_lock, flags); return ret; } -static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n) +static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, + struct sk_buff *skb) { + struct xsk_addr_node *pos, *tmp; + u32 descs_processed = 0; unsigned long flags; + u32 idx; spin_lock_irqsave(&pool->cq_lock, flags); - xskq_prod_submit_n(pool->cq, n); + idx = xskq_get_prod(pool->cq); + + xskq_prod_write_addr(pool->cq, idx, + (u64)(uintptr_t)skb_shinfo(skb)->destructor_arg); + descs_processed++; + + if (unlikely(XSKCB(skb)->num_descs > 1)) { + list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) { + xskq_prod_write_addr(pool->cq, idx + descs_processed, + pos->addr); + descs_processed++; + list_del(&pos->addr_node); + kmem_cache_free(xsk_tx_generic_cache, pos); + } + } + xskq_prod_submit_n(pool->cq, descs_processed); spin_unlock_irqrestore(&pool->cq_lock, flags); } @@ -562,9 +595,14 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n) spin_unlock_irqrestore(&pool->cq_lock, flags); } +static void xsk_inc_num_desc(struct sk_buff *skb) +{ + XSKCB(skb)->num_descs++; +} + static u32 xsk_get_num_desc(struct sk_buff *skb) { - return skb ? (long)skb_shinfo(skb)->destructor_arg : 0; + return XSKCB(skb)->num_descs; } static void xsk_destruct_skb(struct sk_buff *skb) @@ -576,23 +614,33 @@ static void xsk_destruct_skb(struct sk_buff *skb) *compl->tx_timestamp = ktime_get_tai_fast_ns(); } - xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb)); + xsk_cq_submit_addr_locked(xdp_sk(skb->sk)->pool, skb); sock_wfree(skb); } -static void xsk_set_destructor_arg(struct sk_buff *skb) +static void xsk_set_destructor_arg(struct sk_buff *skb, u64 addr) { - long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1; - - skb_shinfo(skb)->destructor_arg = (void *)num; + BUILD_BUG_ON(sizeof(struct xsk_addr_head) > sizeof(skb->cb)); + INIT_LIST_HEAD(&XSKCB(skb)->addrs_list); + XSKCB(skb)->num_descs = 0; + skb_shinfo(skb)->destructor_arg = (void *)(uintptr_t)addr; } static void xsk_consume_skb(struct sk_buff *skb) { struct xdp_sock *xs = xdp_sk(skb->sk); + u32 num_descs = xsk_get_num_desc(skb); + struct xsk_addr_node *pos, *tmp; + + if (unlikely(num_descs > 1)) { + list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) { + list_del(&pos->addr_node); + kmem_cache_free(xsk_tx_generic_cache, pos); + } + } skb->destructor = sock_wfree; - xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb)); + xsk_cq_cancel_locked(xs->pool, num_descs); /* Free skb without triggering the perf drop trace */ consume_skb(skb); xs->skb = NULL; @@ -609,6 +657,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, { struct xsk_buff_pool *pool = xs->pool; u32 hr, len, ts, offset, copy, copied; + struct xsk_addr_node *xsk_addr; struct sk_buff *skb = xs->skb; struct page *page; void *buffer; @@ -623,6 +672,19 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, return ERR_PTR(err); skb_reserve(skb, hr); + + xsk_set_destructor_arg(skb, desc->addr); + } else { + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); + if (!xsk_addr) + return ERR_PTR(-ENOMEM); + + /* in case of -EOVERFLOW that could happen below, + * xsk_consume_skb() will release this node as whole skb + * would be dropped, which implies freeing all list elements + */ + xsk_addr->addr = desc->addr; + list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list); } addr = desc->addr; @@ -694,8 +756,11 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, err = skb_store_bits(skb, 0, buffer, len); if (unlikely(err)) goto free_err; + + xsk_set_destructor_arg(skb, desc->addr); } else { int nr_frags = skb_shinfo(skb)->nr_frags; + struct xsk_addr_node *xsk_addr; struct page *page; u8 *vaddr; @@ -710,12 +775,22 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, goto free_err; } + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); + if (!xsk_addr) { + __free_page(page); + err = -ENOMEM; + goto free_err; + } + vaddr = kmap_local_page(page); memcpy(vaddr, buffer, len); kunmap_local(vaddr); skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); + + xsk_addr->addr = desc->addr; + list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list); } if (first_frag && desc->options & XDP_TX_METADATA) { @@ -759,7 +834,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->mark = READ_ONCE(xs->sk.sk_mark); skb->destructor = xsk_destruct_skb; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); - xsk_set_destructor_arg(skb); + xsk_inc_num_desc(skb); return skb; @@ -769,7 +844,7 @@ free_err: if (err == -EOVERFLOW) { /* Drop the packet */ - xsk_set_destructor_arg(xs->skb); + xsk_inc_num_desc(xs->skb); xsk_drop_skb(xs->skb); xskq_cons_release(xs->tx); } else { @@ -812,7 +887,7 @@ static int __xsk_generic_xmit(struct sock *sk) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr); + err = xsk_cq_reserve_locked(xs->pool); if (err) { err = -EAGAIN; goto out; @@ -1815,8 +1890,18 @@ static int __init xsk_init(void) if (err) goto out_pernet; + xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache", + sizeof(struct xsk_addr_node), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (!xsk_tx_generic_cache) { + err = -ENOMEM; + goto out_unreg_notif; + } + return 0; +out_unreg_notif: + unregister_netdevice_notifier(&xsk_netdev_notifier); out_pernet: unregister_pernet_subsys(&xsk_net_ops); out_sk: diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 46d87e961ad6..f16f390370dc 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -344,6 +344,11 @@ static inline u32 xskq_cons_present_entries(struct xsk_queue *q) /* Functions for producers */ +static inline u32 xskq_get_prod(struct xsk_queue *q) +{ + return READ_ONCE(q->ring->producer); +} + static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max) { u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons); @@ -390,6 +395,13 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr) return 0; } +static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr) +{ + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + + ring->desc[idx & q->ring_mask] = addr; +} + static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs, u32 nb_entries) { diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index c7a1f080d2de..44b9de6e4e77 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -438,7 +438,7 @@ ok: check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; - switch (x->props.family) { + switch (x->inner_mode.family) { case AF_INET: /* Check for IPv4 options */ if (ip_hdr(skb)->ihl != 5) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 78fcbb89cf32..d213ca3653a8 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2583,6 +2583,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, for (h = 0; h < range; h++) { u32 spi = (low == high) ? low : get_random_u32_inclusive(low, high); + if (spi == 0) + goto next; newspi = htonl(spi); spin_lock_bh(&net->xfrm.xfrm_state_lock); @@ -2598,6 +2600,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, xfrm_state_put(x0); spin_unlock_bh(&net->xfrm.xfrm_state_lock); +next: if (signal_pending(current)) { err = -ERESTARTSYS; goto unlock; |