diff options
Diffstat (limited to 'net')
75 files changed, 1135 insertions, 946 deletions
diff --git a/net/Makefile b/net/Makefile index 428c523296e3..cedc19be7ada 100644 --- a/net/Makefile +++ b/net/Makefile @@ -17,7 +17,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ -obj-$(CONFIG_UNIX_SCM) += unix/ +obj-$(CONFIG_UNIX) += unix/ obj-y += ipv6/ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c index 1bc51e2b05a3..3e1713673ecc 100644 --- a/net/bluetooth/eir.c +++ b/net/bluetooth/eir.c @@ -366,17 +366,19 @@ u8 eir_create_scan_rsp(struct hci_dev *hdev, u8 instance, u8 *ptr) void *eir_get_service_data(u8 *eir, size_t eir_len, u16 uuid, size_t *len) { - while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, len))) { + size_t dlen; + + while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, &dlen))) { u16 value = get_unaligned_le16(eir); if (uuid == value) { if (len) - *len -= 2; + *len = dlen - 2; return &eir[2]; } - eir += *len; - eir_len -= *len; + eir += dlen; + eir_len -= dlen; } return NULL; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 70be66cd6036..f3596cfdffc2 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1862,10 +1862,8 @@ void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) if (monitor->handle) idr_remove(&hdev->adv_monitors_idr, monitor->handle); - if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) { + if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) hdev->adv_monitors_cnt--; - mgmt_adv_monitor_removed(hdev, monitor->handle); - } kfree(monitor); } @@ -2492,6 +2490,7 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); + mutex_init(&hdev->mgmt_pending_lock); ida_init(&hdev->unset_handle_ida); @@ -3380,23 +3379,18 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) bt_dev_err(hdev, "link tx timeout"); - rcu_read_lock(); + hci_dev_lock(hdev); /* Kill stalled connections */ - list_for_each_entry_rcu(c, &h->list, list) { + list_for_each_entry(c, &h->list, list) { if (c->type == type && c->sent) { bt_dev_err(hdev, "killing stalled connection %pMR", &c->dst); - /* hci_disconnect might sleep, so, we have to release - * the RCU read lock before calling it. - */ - rcu_read_unlock(); hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM); - rcu_read_lock(); } } - rcu_read_unlock(); + hci_dev_unlock(hdev); } static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index d6f40806ee51..e92bc4ceb5ad 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1586,7 +1586,8 @@ static int hci_enable_per_advertising_sync(struct hci_dev *hdev, u8 instance) static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv) { u8 bid[3]; - u8 ad[4 + 3]; + u8 ad[HCI_MAX_EXT_AD_LENGTH]; + u8 len; /* Skip if NULL adv as instance 0x00 is used for general purpose * advertising so it cannot used for the likes of Broadcast Announcement @@ -1612,8 +1613,10 @@ static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv) /* Generate Broadcast ID */ get_random_bytes(bid, sizeof(bid)); - eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid)); - hci_set_adv_instance_data(hdev, adv->instance, sizeof(ad), ad, 0, NULL); + len = eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid)); + memcpy(ad + len, adv->adv_data, adv->adv_data_len); + hci_set_adv_instance_data(hdev, adv->instance, len + adv->adv_data_len, + ad, 0, NULL); return hci_update_adv_data_sync(hdev, adv->instance); } @@ -1630,8 +1633,15 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len, if (instance) { adv = hci_find_adv_instance(hdev, instance); - /* Create an instance if that could not be found */ - if (!adv) { + if (adv) { + /* Turn it into periodic advertising */ + adv->periodic = true; + adv->per_adv_data_len = data_len; + if (data) + memcpy(adv->per_adv_data, data, data_len); + adv->flags = flags; + } else if (!adv) { + /* Create an instance if that could not be found */ adv = hci_add_per_instance(hdev, instance, flags, data_len, data, sync_interval, diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 72ee41b894a5..2744ad11687c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1411,7 +1411,8 @@ static void l2cap_request_info(struct l2cap_conn *conn) sizeof(req), &req); } -static bool l2cap_check_enc_key_size(struct hci_conn *hcon) +static bool l2cap_check_enc_key_size(struct hci_conn *hcon, + struct l2cap_chan *chan) { /* The minimum encryption key size needs to be enforced by the * host stack before establishing any L2CAP connections. The @@ -1425,7 +1426,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon) int min_key_size = hcon->hdev->min_enc_key_size; /* On FIPS security level, key size must be 16 bytes */ - if (hcon->sec_level == BT_SECURITY_FIPS) + if (chan->sec_level == BT_SECURITY_FIPS) min_key_size = 16; return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) || @@ -1453,7 +1454,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) !__l2cap_no_conn_pending(chan)) return; - if (l2cap_check_enc_key_size(conn->hcon)) + if (l2cap_check_enc_key_size(conn->hcon, chan)) l2cap_start_connection(chan); else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); @@ -1528,7 +1529,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn) continue; } - if (l2cap_check_enc_key_size(conn->hcon)) + if (l2cap_check_enc_key_size(conn->hcon, chan)) l2cap_start_connection(chan); else l2cap_chan_close(chan, ECONNREFUSED); @@ -3955,7 +3956,7 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, /* Check if the ACL is secure enough (if not SDP) */ if (psm != cpu_to_le16(L2CAP_PSM_SDP) && (!hci_conn_check_link_mode(conn->hcon) || - !l2cap_check_enc_key_size(conn->hcon))) { + !l2cap_check_enc_key_size(conn->hcon, pchan))) { conn->disc_reason = HCI_ERROR_AUTH_FAILURE; result = L2CAP_CR_SEC_BLOCK; goto response; @@ -4832,7 +4833,8 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, if (!smp_sufficient_security(conn->hcon, pchan->sec_level, SMP_ALLOW_STK)) { - result = L2CAP_CR_LE_AUTHENTICATION; + result = pchan->sec_level == BT_SECURITY_MEDIUM ? + L2CAP_CR_LE_ENCRYPTION : L2CAP_CR_LE_AUTHENTICATION; chan = NULL; goto response_unlock; } @@ -7323,7 +7325,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } if (chan->state == BT_CONNECT) { - if (!status && l2cap_check_enc_key_size(hcon)) + if (!status && l2cap_check_enc_key_size(hcon, chan)) l2cap_start_connection(chan); else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); @@ -7333,7 +7335,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) struct l2cap_conn_rsp rsp; __u16 res, stat; - if (!status && l2cap_check_enc_key_size(hcon)) { + if (!status && l2cap_check_enc_key_size(hcon, chan)) { if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { res = L2CAP_CR_PEND; stat = L2CAP_CS_AUTHOR_PEND; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 29e420e9754b..853d217cabc9 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1433,22 +1433,17 @@ static void settings_rsp(struct mgmt_pending_cmd *cmd, void *data) send_settings_rsp(cmd->sk, cmd->opcode, match->hdev); - list_del(&cmd->list); - if (match->sk == NULL) { match->sk = cmd->sk; sock_hold(match->sk); } - - mgmt_pending_free(cmd); } static void cmd_status_rsp(struct mgmt_pending_cmd *cmd, void *data) { u8 *status = data; - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, *status); - mgmt_pending_remove(cmd); + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, *status); } static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data) @@ -1462,8 +1457,6 @@ static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data) if (cmd->cmd_complete) { cmd->cmd_complete(cmd, match->mgmt_status); - mgmt_pending_remove(cmd); - return; } @@ -1472,13 +1465,13 @@ static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data) static int generic_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status) { - return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, + return mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status, cmd->param, cmd->param_len); } static int addr_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status) { - return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, + return mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status, cmd->param, sizeof(struct mgmt_addr_info)); } @@ -1518,7 +1511,7 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data, if (err) { u8 mgmt_err = mgmt_status(err); - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err); hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); goto done; } @@ -1693,7 +1686,7 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data, if (err) { u8 mgmt_err = mgmt_status(err); - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err); goto done; } @@ -1930,8 +1923,8 @@ 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, cmd_status_rsp, - &mgmt_err); + mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, true, + cmd_status_rsp, &mgmt_err); return; } @@ -1941,7 +1934,7 @@ 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, settings_rsp, &match); + mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, true, settings_rsp, &match); if (changed) new_settings(hdev, match.sk); @@ -2061,12 +2054,12 @@ static void set_le_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); if (status) { - mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, cmd_status_rsp, - &status); + mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, true, cmd_status_rsp, + &status); return; } - mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, settings_rsp, &match); + mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, true, settings_rsp, &match); new_settings(hdev, match.sk); @@ -2125,7 +2118,7 @@ static void set_mesh_complete(struct hci_dev *hdev, void *data, int err) struct sock *sk = cmd->sk; if (status) { - mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev, + mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev, true, cmd_status_rsp, &status); return; } @@ -2566,7 +2559,7 @@ static void mgmt_class_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err), hdev->dev_class, 3); mgmt_pending_free(cmd); @@ -3354,7 +3347,7 @@ static int pairing_complete(struct mgmt_pending_cmd *cmd, u8 status) bacpy(&rp.addr.bdaddr, &conn->dst); rp.addr.type = link_to_bdaddr(conn->type, conn->dst_type); - err = mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_PAIR_DEVICE, + err = mgmt_cmd_complete(cmd->sk, cmd->hdev->id, MGMT_OP_PAIR_DEVICE, status, &rp, sizeof(rp)); /* So we don't get further callbacks for this connection */ @@ -5165,24 +5158,14 @@ static void mgmt_adv_monitor_added(struct sock *sk, struct hci_dev *hdev, mgmt_event(MGMT_EV_ADV_MONITOR_ADDED, hdev, &ev, sizeof(ev), sk); } -void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle) +static void mgmt_adv_monitor_removed(struct sock *sk, struct hci_dev *hdev, + __le16 handle) { struct mgmt_ev_adv_monitor_removed ev; - struct mgmt_pending_cmd *cmd; - struct sock *sk_skip = NULL; - struct mgmt_cp_remove_adv_monitor *cp; - cmd = pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev); - if (cmd) { - cp = cmd->param; + ev.monitor_handle = handle; - if (cp->monitor_handle) - sk_skip = cmd->sk; - } - - ev.monitor_handle = cpu_to_le16(handle); - - mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk_skip); + mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk); } static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, @@ -5253,7 +5236,7 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, hci_update_passive_scan(hdev); } - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(status), &rp, sizeof(rp)); mgmt_pending_remove(cmd); @@ -5284,8 +5267,7 @@ static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev, if (pending_find(MGMT_OP_SET_LE, hdev) || pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) || - pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev) || - pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) { + pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) { status = MGMT_STATUS_BUSY; goto unlock; } @@ -5455,8 +5437,7 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, struct mgmt_pending_cmd *cmd = data; struct mgmt_cp_remove_adv_monitor *cp; - if (status == -ECANCELED || - cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) + if (status == -ECANCELED) return; hci_dev_lock(hdev); @@ -5465,12 +5446,14 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, rp.monitor_handle = cp->monitor_handle; - if (!status) + if (!status) { + mgmt_adv_monitor_removed(cmd->sk, hdev, cp->monitor_handle); hci_update_passive_scan(hdev); + } - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(status), &rp, sizeof(rp)); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); hci_dev_unlock(hdev); bt_dev_dbg(hdev, "remove monitor %d complete, status %d", @@ -5480,10 +5463,6 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, static int mgmt_remove_adv_monitor_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - - if (cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) - return -ECANCELED; - struct mgmt_cp_remove_adv_monitor *cp = cmd->param; u16 handle = __le16_to_cpu(cp->monitor_handle); @@ -5502,14 +5481,13 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, hci_dev_lock(hdev); if (pending_find(MGMT_OP_SET_LE, hdev) || - pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev) || pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) || pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) { status = MGMT_STATUS_BUSY; goto unlock; } - cmd = mgmt_pending_add(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len); + cmd = mgmt_pending_new(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len); if (!cmd) { status = MGMT_STATUS_NO_RESOURCES; goto unlock; @@ -5519,7 +5497,7 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, mgmt_remove_adv_monitor_complete); if (err) { - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); if (err == -ENOMEM) status = MGMT_STATUS_NO_RESOURCES; @@ -5872,7 +5850,7 @@ static void start_discovery_complete(struct hci_dev *hdev, void *data, int err) cmd != pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev)) return; - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err), + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err), cmd->param, 1); mgmt_pending_remove(cmd); @@ -6110,7 +6088,7 @@ static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err), + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err), cmd->param, 1); mgmt_pending_remove(cmd); @@ -6335,7 +6313,7 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err) u8 status = mgmt_status(err); if (status) { - mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, + mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, true, cmd_status_rsp, &status); return; } @@ -6345,7 +6323,7 @@ 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, settings_rsp, + mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, true, settings_rsp, &match); new_settings(hdev, match.sk); @@ -6689,7 +6667,7 @@ static void set_bredr_complete(struct hci_dev *hdev, void *data, int err) */ hci_dev_clear_flag(hdev, HCI_BREDR_ENABLED); - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err); } else { send_settings_rsp(cmd->sk, MGMT_OP_SET_BREDR, hdev); new_settings(hdev, cmd->sk); @@ -6826,7 +6804,7 @@ static void set_secure_conn_complete(struct hci_dev *hdev, void *data, int err) if (err) { u8 mgmt_err = mgmt_status(err); - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err); goto done; } @@ -7273,7 +7251,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) rp.max_tx_power = HCI_TX_POWER_INVALID; } - mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO, status, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, MGMT_OP_GET_CONN_INFO, status, &rp, sizeof(rp)); mgmt_pending_free(cmd); @@ -7433,7 +7411,7 @@ static void get_clock_info_complete(struct hci_dev *hdev, void *data, int err) } complete: - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, &rp, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status, &rp, sizeof(rp)); mgmt_pending_free(cmd); @@ -7605,11 +7583,16 @@ static void add_device_complete(struct hci_dev *hdev, void *data, int err) struct mgmt_cp_add_device *cp = cmd->param; if (!err) { + struct hci_conn_params *params; + + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, + le_addr_type(cp->addr.type)); + device_added(cmd->sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); device_flags_changed(NULL, hdev, &cp->addr.bdaddr, cp->addr.type, hdev->conn_flags, - PTR_UINT(cmd->user_data)); + params ? params->flags : 0); } mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE, @@ -7712,8 +7695,6 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - cmd->user_data = UINT_PTR(current_flags); - err = hci_cmd_sync_queue(hdev, add_device_sync, cmd, add_device_complete); if (err < 0) { @@ -8634,10 +8615,10 @@ static void add_advertising_complete(struct hci_dev *hdev, void *data, int err) rp.instance = cp->instance; if (err) - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err)); else - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err), &rp, sizeof(rp)); add_adv_complete(hdev, cmd->sk, cp->instance, err); @@ -8825,10 +8806,10 @@ static void add_ext_adv_params_complete(struct hci_dev *hdev, void *data, hci_remove_adv_instance(hdev, cp->instance); - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err)); } else { - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err), &rp, sizeof(rp)); } @@ -8976,10 +8957,10 @@ static void add_ext_adv_data_complete(struct hci_dev *hdev, void *data, int err) rp.instance = cp->instance; if (err) - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err)); else - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err), &rp, sizeof(rp)); mgmt_pending_free(cmd); @@ -9138,10 +9119,10 @@ static void remove_advertising_complete(struct hci_dev *hdev, void *data, rp.instance = cp->instance; if (err) - mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err)); else - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); mgmt_pending_free(cmd); @@ -9412,7 +9393,7 @@ void mgmt_index_removed(struct hci_dev *hdev) if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) return; - mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &match); + mgmt_pending_foreach(0, hdev, true, cmd_complete_rsp, &match); if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, NULL, 0, @@ -9450,7 +9431,8 @@ void mgmt_power_on(struct hci_dev *hdev, int err) hci_update_passive_scan(hdev); } - mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); + mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, true, settings_rsp, + &match); new_settings(hdev, match.sk); @@ -9465,7 +9447,8 @@ void __mgmt_power_off(struct hci_dev *hdev) struct cmd_lookup match = { NULL, hdev }; u8 zero_cod[] = { 0, 0, 0 }; - mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); + mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, true, settings_rsp, + &match); /* If the power off is because of hdev unregistration let * use the appropriate INVALID_INDEX status. Otherwise use @@ -9479,7 +9462,7 @@ void __mgmt_power_off(struct hci_dev *hdev) else match.mgmt_status = MGMT_STATUS_NOT_POWERED; - mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &match); + mgmt_pending_foreach(0, hdev, true, cmd_complete_rsp, &match); if (memcmp(hdev->dev_class, zero_cod, sizeof(zero_cod)) != 0) { mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, @@ -9720,7 +9703,6 @@ static void unpair_device_rsp(struct mgmt_pending_cmd *cmd, void *data) device_unpaired(hdev, &cp->addr.bdaddr, cp->addr.type, cmd->sk); cmd->cmd_complete(cmd, 0); - mgmt_pending_remove(cmd); } bool mgmt_powering_down(struct hci_dev *hdev) @@ -9773,8 +9755,8 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, struct mgmt_cp_disconnect *cp; struct mgmt_pending_cmd *cmd; - mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp, - hdev); + mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, true, + unpair_device_rsp, hdev); cmd = pending_find(MGMT_OP_DISCONNECT, hdev); if (!cmd) @@ -9967,7 +9949,7 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status) if (status) { u8 mgmt_err = mgmt_status(status); - mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, + mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, true, cmd_status_rsp, &mgmt_err); return; } @@ -9977,8 +9959,8 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status) else changed = hci_dev_test_and_clear_flag(hdev, HCI_LINK_SECURITY); - mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, settings_rsp, - &match); + mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, true, + settings_rsp, &match); if (changed) new_settings(hdev, match.sk); @@ -10002,9 +9984,12 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, { struct cmd_lookup match = { NULL, hdev, mgmt_status(status) }; - mgmt_pending_foreach(MGMT_OP_SET_DEV_CLASS, hdev, sk_lookup, &match); - mgmt_pending_foreach(MGMT_OP_ADD_UUID, hdev, sk_lookup, &match); - mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, sk_lookup, &match); + mgmt_pending_foreach(MGMT_OP_SET_DEV_CLASS, hdev, false, sk_lookup, + &match); + mgmt_pending_foreach(MGMT_OP_ADD_UUID, hdev, false, sk_lookup, + &match); + mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, false, sk_lookup, + &match); if (!status) { mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, dev_class, diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c index 0115f783bde8..4ba500c377a4 100644 --- a/net/bluetooth/mgmt_util.c +++ b/net/bluetooth/mgmt_util.c @@ -217,47 +217,47 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode, struct hci_dev *hdev) { - struct mgmt_pending_cmd *cmd; + struct mgmt_pending_cmd *cmd, *tmp; + + mutex_lock(&hdev->mgmt_pending_lock); - list_for_each_entry(cmd, &hdev->mgmt_pending, list) { + list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) { if (hci_sock_get_channel(cmd->sk) != channel) continue; - if (cmd->opcode == opcode) - return cmd; - } - return NULL; -} - -struct mgmt_pending_cmd *mgmt_pending_find_data(unsigned short channel, - u16 opcode, - struct hci_dev *hdev, - const void *data) -{ - struct mgmt_pending_cmd *cmd; - - list_for_each_entry(cmd, &hdev->mgmt_pending, list) { - if (cmd->user_data != data) - continue; - if (cmd->opcode == opcode) + if (cmd->opcode == opcode) { + mutex_unlock(&hdev->mgmt_pending_lock); return cmd; + } } + mutex_unlock(&hdev->mgmt_pending_lock); + return NULL; } -void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, +void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, bool remove, void (*cb)(struct mgmt_pending_cmd *cmd, void *data), void *data) { struct mgmt_pending_cmd *cmd, *tmp; + mutex_lock(&hdev->mgmt_pending_lock); + list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) { if (opcode > 0 && cmd->opcode != opcode) continue; + if (remove) + list_del(&cmd->list); + cb(cmd, data); + + if (remove) + mgmt_pending_free(cmd); } + + mutex_unlock(&hdev->mgmt_pending_lock); } struct mgmt_pending_cmd *mgmt_pending_new(struct sock *sk, u16 opcode, @@ -271,7 +271,7 @@ struct mgmt_pending_cmd *mgmt_pending_new(struct sock *sk, u16 opcode, return NULL; cmd->opcode = opcode; - cmd->index = hdev->id; + cmd->hdev = hdev; cmd->param = kmemdup(data, len, GFP_KERNEL); if (!cmd->param) { @@ -297,7 +297,9 @@ struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode, if (!cmd) return NULL; + mutex_lock(&hdev->mgmt_pending_lock); list_add_tail(&cmd->list, &hdev->mgmt_pending); + mutex_unlock(&hdev->mgmt_pending_lock); return cmd; } @@ -311,7 +313,10 @@ void mgmt_pending_free(struct mgmt_pending_cmd *cmd) void mgmt_pending_remove(struct mgmt_pending_cmd *cmd) { + mutex_lock(&cmd->hdev->mgmt_pending_lock); list_del(&cmd->list); + mutex_unlock(&cmd->hdev->mgmt_pending_lock); + mgmt_pending_free(cmd); } @@ -321,7 +326,7 @@ void mgmt_mesh_foreach(struct hci_dev *hdev, { struct mgmt_mesh_tx *mesh_tx, *tmp; - list_for_each_entry_safe(mesh_tx, tmp, &hdev->mgmt_pending, list) { + list_for_each_entry_safe(mesh_tx, tmp, &hdev->mesh_pending, list) { if (!sk || mesh_tx->sk == sk) cb(mesh_tx, data); } diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h index bdf978605d5a..024e51dd6937 100644 --- a/net/bluetooth/mgmt_util.h +++ b/net/bluetooth/mgmt_util.h @@ -33,7 +33,7 @@ struct mgmt_mesh_tx { struct mgmt_pending_cmd { struct list_head list; u16 opcode; - int index; + struct hci_dev *hdev; void *param; size_t param_len; struct sock *sk; @@ -54,11 +54,7 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode, struct hci_dev *hdev); -struct mgmt_pending_cmd *mgmt_pending_find_data(unsigned short channel, - u16 opcode, - struct hci_dev *hdev, - const void *data); -void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, +void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, bool remove, void (*cb)(struct mgmt_pending_cmd *cmd, void *data), void *data); struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode, diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 7305f5f8215c..96bea0c8408f 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -1030,7 +1030,7 @@ static int br_mdb_add_group(const struct br_mdb_config *cfg, /* host join */ if (!port) { - if (mp->host_joined) { + if (mp->host_joined && !(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host"); return -EEXIST; } diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 98aea5485aae..a8c67035e23c 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -65,17 +65,14 @@ static struct dst_ops fake_dst_ops = { * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ -static const u32 br_dst_default_metrics[RTAX_MAX] = { - [RTAX_MTU - 1] = 1500, -}; - void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; rcuref_init(&rt->dst.__rcuref, 1); rt->dst.dev = br->dev; - dst_init_metrics(&rt->dst, br_dst_default_metrics, true); + dst_init_metrics(&rt->dst, br->metrics, false); + dst_metric_set(&rt->dst, RTAX_MTU, br->dev->mtu); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 72d80fd943a8..9197b511e459 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -502,6 +502,7 @@ struct net_bridge { struct rtable fake_rtable; struct rt6_info fake_rt6_info; }; + u32 metrics[RTAX_MAX]; #endif u16 group_fwd_mask; u16 group_fwd_mask_required; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 4fbfbafdfa02..4b4a396d9722 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -60,19 +60,19 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, struct ip_fraglist_iter iter; struct sk_buff *frag; - if (first_len - hlen > mtu || - skb_headroom(skb) < ll_rs) + if (first_len - hlen > mtu) goto blackhole; - if (skb_cloned(skb)) + if (skb_cloned(skb) || + skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { - if (frag->len > mtu || - skb_headroom(frag) < hlen + ll_rs) + if (frag->len > mtu) goto blackhole; - if (skb_shared(frag)) + if (skb_shared(frag) || + skb_headroom(frag) < hlen + ll_rs) goto slow_path; } diff --git a/net/can/bcm.c b/net/can/bcm.c index a1f5db0fd5d4..75653584f31b 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -58,6 +58,7 @@ #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <net/sock.h> #include <net/net_namespace.h> @@ -120,6 +121,7 @@ struct bcm_op { struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; + spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */ }; struct bcm_sock { @@ -205,7 +207,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex)); seq_printf(m, " <<<\n"); - list_for_each_entry(op, &bo->rx_ops, list) { + rcu_read_lock(); + + list_for_each_entry_rcu(op, &bo->rx_ops, list) { unsigned long reduction; @@ -261,6 +265,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, "# sent %ld\n", op->frames_abs); } seq_putc(m, '\n'); + + rcu_read_unlock(); + return 0; } #endif /* CONFIG_PROC_FS */ @@ -273,13 +280,18 @@ static void bcm_can_tx(struct bcm_op *op) { struct sk_buff *skb; struct net_device *dev; - struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; + struct canfd_frame *cf; int err; /* no target device? => exit */ if (!op->ifindex) return; + /* read currframe under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + cf = op->frames + op->cfsiz * op->currframe; + spin_unlock_bh(&op->bcm_tx_lock); + dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { /* RFC: should this bcm_op remove itself here? */ @@ -300,6 +312,10 @@ static void bcm_can_tx(struct bcm_op *op) skb->dev = dev; can_skb_set_owner(skb, op->sk); err = can_send(skb, 1); + + /* update currframe and count under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + if (!err) op->frames_abs++; @@ -308,6 +324,11 @@ static void bcm_can_tx(struct bcm_op *op) /* reached last frame? */ if (op->currframe >= op->nframes) op->currframe = 0; + + if (op->count > 0) + op->count--; + + spin_unlock_bh(&op->bcm_tx_lock); out: dev_put(dev); } @@ -404,7 +425,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { - op->count--; + bcm_can_tx(op); if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ @@ -419,7 +440,6 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) bcm_send_to_user(op, &msg_head, NULL, 0); } - bcm_can_tx(op); } else if (op->kt_ival2) { bcm_can_tx(op); @@ -801,7 +821,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, REGMASK(op->can_id), bcm_rx_handler, op); - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } @@ -821,7 +841,7 @@ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh, list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } @@ -914,6 +934,27 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } op->flags = msg_head->flags; + /* only lock for unlikely count/nframes/currframe changes */ + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX || + op->flags & SETTIMER) { + + spin_lock_bh(&op->bcm_tx_lock); + + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX) { + /* potentially update changed nframes */ + op->nframes = msg_head->nframes; + /* restart multiple frame transmission */ + op->currframe = 0; + } + + if (op->flags & SETTIMER) + op->count = msg_head->count; + + spin_unlock_bh(&op->bcm_tx_lock); + } + } else { /* insert new BCM operation for the given can_id */ @@ -921,9 +962,14 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; + op->nframes = msg_head->nframes; + + if (op->flags & SETTIMER) + op->count = msg_head->count; /* create array for CAN frames and copy the data */ if (msg_head->nframes > 1) { @@ -982,22 +1028,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ - if (op->nframes != msg_head->nframes) { - op->nframes = msg_head->nframes; - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - - /* check flags */ - - if (op->flags & TX_RESET_MULTI_IDX) { - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - if (op->flags & SETTIMER) { /* set timer values */ - op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); @@ -1014,11 +1046,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->flags |= TX_ANNOUNCE; } - if (op->flags & TX_ANNOUNCE) { + if (op->flags & TX_ANNOUNCE) bcm_can_tx(op); - if (op->count) - op->count--; - } if (op->flags & STARTTIMER) bcm_tx_start_timer(op); @@ -1234,7 +1263,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_rx_handler, op, "bcm", sk); if (err) { /* this bcm rx op is broken -> remove it */ - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return err; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 359e24c3f22c..6afea369ca21 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -897,6 +897,10 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) pkt_dev->nr_labels = 0; do { __u32 tmp; + + if (n >= MAX_MPLS_LABELS) + return -E2BIG; + len = hex32_arg(&buffer[i], 8, &tmp); if (len <= 0) return len; @@ -908,8 +912,6 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) return -EFAULT; i++; n++; - if (n >= MAX_MPLS_LABELS) - return -E2BIG; } while (c == ','); pkt_dev->nr_labels = n; @@ -1875,8 +1877,8 @@ static ssize_t pktgen_thread_write(struct file *file, i = len; /* Read variable name */ - - len = strn_len(&user_buffer[i], sizeof(name) - 1); + max = min(sizeof(name) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1906,7 +1908,8 @@ static ssize_t pktgen_thread_write(struct file *file, if (!strcmp(name, "add_device")) { char f[32]; memset(f, 0, 32); - len = strn_len(&user_buffer[i], sizeof(f) - 1); + max = min(sizeof(f) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) { ret = len; goto out; diff --git a/net/core/scm.c b/net/core/scm.c index 737917c7ac62..431bfb3ea392 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -36,6 +36,7 @@ #include <net/compat.h> #include <net/scm.h> #include <net/cls_cgroup.h> +#include <net/af_unix.h> /* @@ -85,8 +86,15 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) return -ENOMEM; *fplp = fpl; fpl->count = 0; + fpl->count_unix = 0; fpl->max = SCM_MAX_FD; fpl->user = NULL; +#if IS_ENABLED(CONFIG_UNIX) + fpl->inflight = false; + fpl->dead = false; + fpl->edges = NULL; + INIT_LIST_HEAD(&fpl->vertices); +#endif } fpp = &fpl->fp[fpl->count]; @@ -109,6 +117,9 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) fput(file); return -EINVAL; } + if (unix_get_socket(file)) + fpl->count_unix++; + *fpp++ = file; fpl->count++; } @@ -371,8 +382,14 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) if (new_fpl) { for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); + new_fpl->max = new_fpl->count; new_fpl->user = get_uid(fpl->user); +#if IS_ENABLED(CONFIG_UNIX) + new_fpl->inflight = false; + new_fpl->edges = NULL; + INIT_LIST_HEAD(&new_fpl->vertices); +#endif } return new_fpl; } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index b9b941c487c8..2076db464e93 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -529,16 +529,22 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, u32 off, u32 len, struct sk_psock *psock, struct sock *sk, - struct sk_msg *msg) + struct sk_msg *msg, + bool take_ref) { int num_sge, copied; + /* skb_to_sgvec will fail when the total number of fragments in + * frag_list and frags exceeds MAX_MSG_FRAGS. For example, the + * caller may aggregate multiple skbs. + */ num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (num_sge < 0) { /* skb linearize may fail with ENOMEM, but lets simply try again * later if this happens. Under memory pressure we don't want to * drop the skb. We need to linearize the skb so that the mapping * in skb_to_sgvec can not error. + * Note that skb_linearize requires the skb not to be shared. */ if (skb_linearize(skb)) return -EAGAIN; @@ -555,7 +561,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, msg->sg.start = 0; msg->sg.size = copied; msg->sg.end = num_sge; - msg->skb = skb; + msg->skb = take_ref ? skb_get(skb) : skb; sk_psock_queue_msg(psock, msg); sk_psock_data_ready(sk, psock); @@ -563,7 +569,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, } static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, - u32 off, u32 len); + u32 off, u32 len, bool take_ref); static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len) @@ -577,7 +583,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * correctly. */ if (unlikely(skb->sk == sk)) - return sk_psock_skb_ingress_self(psock, skb, off, len); + return sk_psock_skb_ingress_self(psock, skb, off, len, true); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; @@ -589,7 +595,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * into user buffers. */ skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, true); if (err < 0) kfree(msg); return err; @@ -600,7 +606,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * because the skb is already accounted for here. */ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, - u32 off, u32 len) + u32 off, u32 len, bool take_ref) { struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC); struct sock *sk = psock->sk; @@ -609,7 +615,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb if (unlikely(!msg)) return -EAGAIN; skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, take_ref); if (err < 0) kfree(msg); return err; @@ -618,18 +624,13 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { - int err = 0; - if (!ingress) { if (!sock_writeable(psock->sk)) return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - skb_get(skb); - err = sk_psock_skb_ingress(psock, skb, off, len); - if (err < 0) - kfree_skb(skb); - return err; + + return sk_psock_skb_ingress(psock, skb, off, len); } static void sk_psock_skb_state(struct sk_psock *psock, @@ -654,12 +655,14 @@ static void sk_psock_backlog(struct work_struct *work) bool ingress; int ret; + /* Increment the psock refcnt to synchronize with close(fd) path in + * sock_map_close(), ensuring we wait for backlog thread completion + * before sk_socket freed. If refcnt increment fails, it indicates + * sock_map_close() completed with sk_socket potentially already freed. + */ + if (!sk_psock_get(psock->sk)) + return; mutex_lock(&psock->work_mutex); - if (unlikely(state->len)) { - len = state->len; - off = state->off; - } - while ((skb = skb_peek(&psock->ingress_skb))) { len = skb->len; off = 0; @@ -669,6 +672,13 @@ static void sk_psock_backlog(struct work_struct *work) off = stm->offset; len = stm->full_len; } + + /* Resume processing from previous partial state */ + if (unlikely(state->len)) { + len = state->len; + off = state->off; + } + ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); do { @@ -696,11 +706,14 @@ static void sk_psock_backlog(struct work_struct *work) len -= ret; } while (len); + /* The entire skb sent, clear state */ + sk_psock_skb_state(psock, state, 0, 0); skb = skb_dequeue(&psock->ingress_skb); kfree_skb(skb); } end: mutex_unlock(&psock->work_mutex); + sk_psock_put(psock->sk, psock); } struct sk_psock *sk_psock_init(struct sock *sk, int node) @@ -1013,7 +1026,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, off = stm->offset; len = stm->full_len; } - err = sk_psock_skb_ingress_self(psock, skb, off, len); + err = sk_psock_skb_ingress_self(psock, skb, off, len, false); } if (err < 0) { spin_lock_bh(&psock->ingress_lock); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index cacdafb41200..146c1dbd15a9 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -257,7 +257,7 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, int source_port; u8 *brcm_tag; - if (unlikely(!pskb_may_pull(skb, BRCM_LEG_PORT_ID))) + if (unlikely(!pskb_may_pull(skb, BRCM_LEG_TAG_LEN + VLAN_HLEN))) return NULL; brcm_tag = dsa_etype_header_pos_rx(skb); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index eeace9b509ce..49fd664f50fc 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -118,47 +118,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) } #ifdef CONFIG_INET_ESPINTCP -struct esp_tcp_sk { - struct sock *sk; - struct rcu_head rcu; -}; - -static void esp_free_tcp_sk(struct rcu_head *head) -{ - struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); - - sock_put(esk->sk); - kfree(esk); -} - static struct sock *esp_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; struct net *net = xs_net(x); - struct esp_tcp_sk *esk; __be16 sport, dport; - struct sock *nsk; struct sock *sk; - sk = rcu_dereference(x->encap_sk); - if (sk && sk->sk_state == TCP_ESTABLISHED) - return sk; - spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (sk && sk == nsk) { - esk = kmalloc(sizeof(*esk), GFP_ATOMIC); - if (!esk) { - spin_unlock_bh(&x->lock); - return ERR_PTR(-ENOMEM); - } - RCU_INIT_POINTER(x->encap_sk, NULL); - esk->sk = sk; - call_rcu(&esk->rcu, esp_free_tcp_sk); - } spin_unlock_bh(&x->lock); sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4, @@ -171,20 +140,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x) return ERR_PTR(-EINVAL); } - spin_lock_bh(&x->lock); - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (encap->encap_sport != sport || - encap->encap_dport != dport) { - sock_put(sk); - sk = nsk ?: ERR_PTR(-EREMCHG); - } else if (sk == nsk) { - sock_put(sk); - } else { - rcu_assign_pointer(x->encap_sk, sk); - } - spin_unlock_bh(&x->lock); - return sk; } @@ -207,6 +162,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) err = espintcp_push_skb(sk, skb); bh_unlock_sock(sk); + sock_put(sk); + out: rcu_read_unlock(); return err; @@ -391,6 +348,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, if (IS_ERR(sk)) return ERR_CAST(sk); + sock_put(sk); + *lenp = htons(len); esph = (struct ip_esp_hdr *)(lenp + 1); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 90ce87ffed46..7993ff46de23 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -829,19 +829,33 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, } } + if (cfg->fc_dst_len > 32) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + err = -EINVAL; + goto errout; + } + + if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) { + NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); + err = -EINVAL; + goto errout; + } + if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); - return -EINVAL; + err = -EINVAL; + goto errout; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); - return -EINVAL; + err = -EINVAL; + goto errout; } if (!cfg->fc_table) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 513f475c6a53..298a9944a3d1 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -222,9 +222,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct nlattr **tb, struct netlink_ext_ack *extack) { - struct net *net = sock_net(skb->sk); + struct fib4_rule *rule4 = (struct fib4_rule *)rule; + struct net *net = rule->fr_net; int err = -EINVAL; - struct fib4_rule *rule4 = (struct fib4_rule *) rule; if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 77b97c48da5e..fa54b36b241a 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1192,22 +1192,6 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, return 0; } -static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) -{ - if (plen > KEYLENGTH) { - NL_SET_ERR_MSG(extack, "Invalid prefix length"); - return false; - } - - if ((plen < KEYLENGTH) && (key << plen)) { - NL_SET_ERR_MSG(extack, - "Invalid prefix for given prefix length"); - return false; - } - - return true; -} - static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); @@ -1228,9 +1212,6 @@ int fib_table_insert(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen, extack)) - return -EINVAL; - pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); @@ -1723,9 +1704,6 @@ int fib_table_delete(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen, extack)) - return -EINVAL; - l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7967ff7e02f7..60e81f6b1c6d 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1231,22 +1231,37 @@ int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) { unsigned int locksz = sizeof(spinlock_t); unsigned int i, nblocks = 1; + spinlock_t *ptr = NULL; - if (locksz != 0) { - /* allocate 2 cache lines or at least one spinlock per cpu */ - nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U); - nblocks = roundup_pow_of_two(nblocks * num_possible_cpus()); + if (locksz == 0) + goto set_mask; - /* no more locks than number of hash buckets */ - nblocks = min(nblocks, hashinfo->ehash_mask + 1); + /* Allocate 2 cache lines or at least one spinlock per cpu. */ + nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U) * num_possible_cpus(); - hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL); - if (!hashinfo->ehash_locks) - return -ENOMEM; + /* At least one page per NUMA node. */ + nblocks = max(nblocks, num_online_nodes() * PAGE_SIZE / locksz); + + nblocks = roundup_pow_of_two(nblocks); + + /* No more locks than number of hash buckets. */ + nblocks = min(nblocks, hashinfo->ehash_mask + 1); - for (i = 0; i < nblocks; i++) - spin_lock_init(&hashinfo->ehash_locks[i]); + if (num_online_nodes() > 1) { + /* Use vmalloc() to allow NUMA policy to spread pages + * on all available nodes if desired. + */ + ptr = vmalloc_array(nblocks, locksz); + } + if (!ptr) { + ptr = kvmalloc_array(nblocks, locksz, GFP_KERNEL); + if (!ptr) + return -ENOMEM; } + for (i = 0; i < nblocks; i++) + spin_lock_init(&ptr[i]); + hashinfo->ehash_locks = ptr; +set_mask: hashinfo->ehash_locks_mask = nblocks - 1; return 0; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 890c15510b42..f261e29adc7c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -140,7 +140,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info, const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; - unsigned int data_len = 0; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) @@ -181,7 +180,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info, case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; - data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: @@ -189,10 +187,16 @@ static int ipgre_err(struct sk_buff *skb, u32 info, } #if IS_ENABLED(CONFIG_IPV6) - if (tpi->proto == htons(ETH_P_IPV6) && - !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, - type, data_len)) - return 0; + if (tpi->proto == htons(ETH_P_IPV6)) { + unsigned int data_len = 0; + + if (type == ICMP_TIME_EXCEEDED) + data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ + + if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, + type, data_len)) + return 0; + } #endif if (t->parms.iph.daddr == 0 || diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 10d38ec0ff5a..a172248b6678 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -425,6 +425,20 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr return false; } +static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count) +{ + tp->delivered_ce += ecn_count; +} + +/* Updates the delivered and delivered_ce counts */ +static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, + bool ece_ack) +{ + tp->delivered += delivered; + if (ece_ack) + tcp_count_delivered_ce(tp, delivered); +} + /* Buffer size and advertised window tuning. * * 1. Tuning sk->sk_sndbuf, when connection enters established state. @@ -1137,15 +1151,6 @@ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb) } } -/* Updates the delivered and delivered_ce counts */ -static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, - bool ece_ack) -{ - tp->delivered += delivered; - if (ece_ack) - tp->delivered_ce += delivered; -} - /* This procedure tags the retransmission queue when SACKs arrive. * * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L). @@ -3816,12 +3821,23 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) } } -static inline void tcp_in_ack_event(struct sock *sk, u32 flags) +static void tcp_in_ack_event(struct sock *sk, int flag) { const struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_ca_ops->in_ack_event) - icsk->icsk_ca_ops->in_ack_event(sk, flags); + if (icsk->icsk_ca_ops->in_ack_event) { + u32 ack_ev_flags = 0; + + if (flag & FLAG_WIN_UPDATE) + ack_ev_flags |= CA_ACK_WIN_UPDATE; + if (flag & FLAG_SLOWPATH) { + ack_ev_flags |= CA_ACK_SLOWPATH; + if (flag & FLAG_ECE) + ack_ev_flags |= CA_ACK_ECE; + } + + icsk->icsk_ca_ops->in_ack_event(sk, ack_ev_flags); + } } /* Congestion control has updated the cwnd already. So if we're in @@ -3938,12 +3954,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_snd_una_update(tp, ack); flag |= FLAG_WIN_UPDATE; - tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS); } else { - u32 ack_ev_flags = CA_ACK_SLOWPATH; - if (ack_seq != TCP_SKB_CB(skb)->end_seq) flag |= FLAG_DATA; else @@ -3955,19 +3967,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, &sack_state); - if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) { + if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; - ack_ev_flags |= CA_ACK_ECE; - } if (sack_state.sack_delivered) tcp_count_delivered(tp, sack_state.sack_delivered, flag & FLAG_ECE); - - if (flag & FLAG_WIN_UPDATE) - ack_ev_flags |= CA_ACK_WIN_UPDATE; - - tcp_in_ack_event(sk, ack_ev_flags); } /* This is a deviation from RFC3168 since it states that: @@ -3994,6 +3999,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_rack_update_reo_wnd(sk, &rs); + tcp_in_ack_event(sk, flag); + if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -4025,6 +4032,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) return 1; no_queue: + tcp_in_ack_event(sk, flag); /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) { tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 132cfc3b2c84..3870b59f5400 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -332,6 +332,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, bool copy_dtor; __sum16 check; __be16 newlen; + int ret = 0; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) @@ -354,6 +355,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); + ret = __skb_linearize(gso_skb); + if (ret) + return ERR_PTR(ret); + /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 62bb9651133c..7e4c8628cf98 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -135,47 +135,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) } #ifdef CONFIG_INET6_ESPINTCP -struct esp_tcp_sk { - struct sock *sk; - struct rcu_head rcu; -}; - -static void esp_free_tcp_sk(struct rcu_head *head) -{ - struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); - - sock_put(esk->sk); - kfree(esk); -} - static struct sock *esp6_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; struct net *net = xs_net(x); - struct esp_tcp_sk *esk; __be16 sport, dport; - struct sock *nsk; struct sock *sk; - sk = rcu_dereference(x->encap_sk); - if (sk && sk->sk_state == TCP_ESTABLISHED) - return sk; - spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (sk && sk == nsk) { - esk = kmalloc(sizeof(*esk), GFP_ATOMIC); - if (!esk) { - spin_unlock_bh(&x->lock); - return ERR_PTR(-ENOMEM); - } - RCU_INIT_POINTER(x->encap_sk, NULL); - esk->sk = sk; - call_rcu(&esk->rcu, esp_free_tcp_sk); - } spin_unlock_bh(&x->lock); sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6, @@ -188,20 +157,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x) return ERR_PTR(-EINVAL); } - spin_lock_bh(&x->lock); - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (encap->encap_sport != sport || - encap->encap_dport != dport) { - sock_put(sk); - sk = nsk ?: ERR_PTR(-EREMCHG); - } else if (sk == nsk) { - sock_put(sk); - } else { - rcu_assign_pointer(x->encap_sk, sk); - } - spin_unlock_bh(&x->lock); - return sk; } @@ -224,6 +179,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) err = espintcp_push_skb(sk, skb); bh_unlock_sock(sk); + sock_put(sk); + out: rcu_read_unlock(); return err; @@ -427,6 +384,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x, if (IS_ERR(sk)) return ERR_CAST(sk); + sock_put(sk); + *lenp = htons(len); esph = (struct ip_esp_hdr *)(lenp + 1); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 6eeab21512ba..e0f0c5f8cccd 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -350,9 +350,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct nlattr **tb, struct netlink_ext_ack *extack) { + struct fib6_rule *rule6 = (struct fib6_rule *)rule; + struct net *net = rule->fr_net; int err = -EINVAL; - struct net *net = sock_net(skb->sk); - struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c86d5dca29df..28777b142240 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1452,6 +1452,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, } v6_cork->hop_limit = ipc6->hlimit; v6_cork->tclass = ipc6->tclass; + v6_cork->dontfrag = ipc6->dontfrag; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst); @@ -1485,7 +1486,7 @@ static int __ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, - unsigned int flags, struct ipcm6_cookie *ipc6) + unsigned int flags) { struct sk_buff *skb, *skb_prev = NULL; struct inet_cork *cork = &cork_full->base; @@ -1541,7 +1542,7 @@ static int __ip6_append_data(struct sock *sk, if (headersize + transhdrlen > mtu) goto emsgsize; - if (cork->length + length > mtu - headersize && ipc6->dontfrag && + if (cork->length + length > mtu - headersize && v6_cork->dontfrag && (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_ICMPV6 || sk->sk_protocol == IPPROTO_RAW)) { @@ -1913,7 +1914,7 @@ int ip6_append_data(struct sock *sk, return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork, &np->cork, sk_page_frag(sk), getfrag, - from, length, transhdrlen, flags, ipc6); + from, length, transhdrlen, flags); } EXPORT_SYMBOL_GPL(ip6_append_data); @@ -2118,7 +2119,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, err = __ip6_append_data(sk, &queue, cork, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, - flags, ipc6); + flags); if (err) { __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork); return ERR_PTR(err); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 7c4af48d529e..606aae4e78a9 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -163,20 +163,20 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct ip6_fraglist_iter iter; struct sk_buff *frag2; - if (first_len - hlen > mtu || - skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) + if (first_len - hlen > mtu) goto blackhole; - if (skb_cloned(skb)) + if (skb_cloned(skb) || + skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) goto slow_path; skb_walk_frags(skb, frag2) { - if (frag2->len > mtu || - skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr))) + if (frag2->len > mtu) goto blackhole; /* Partially cloned skb? */ - if (skb_shared(frag2)) + if (skb_shared(frag2) || + skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr))) goto slow_path; } diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index c9f1634b3838..a89ce0fbfe4b 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -158,6 +158,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, { const struct nft_fib *priv = nft_expr_priv(expr); int noff = skb_network_offset(pkt->skb); + const struct net_device *found = NULL; const struct net_device *oif = NULL; u32 *dest = ®s->data[priv->dreg]; struct ipv6hdr *iph, _iph; @@ -202,11 +203,15 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev && - l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex) - goto put_rt_err; + if (!oif) { + found = rt->rt6i_idev->dev; + } else { + if (oif == rt->rt6i_idev->dev || + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == oif->ifindex) + found = oif; + } - nft_fib_store_result(dest, priv, rt->rt6i_idev->dev); + nft_fib_store_result(dest, priv, found); put_rt_err: ip6_rt_put(rt); } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index c434940131b1..7f295b9c1374 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -1638,10 +1638,8 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = { [SEG6_LOCAL_SRH] = { .type = NLA_BINARY }, [SEG6_LOCAL_TABLE] = { .type = NLA_U32 }, [SEG6_LOCAL_VRFTABLE] = { .type = NLA_U32 }, - [SEG6_LOCAL_NH4] = { .type = NLA_BINARY, - .len = sizeof(struct in_addr) }, - [SEG6_LOCAL_NH6] = { .type = NLA_BINARY, - .len = sizeof(struct in6_addr) }, + [SEG6_LOCAL_NH4] = NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)), + [SEG6_LOCAL_NH6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [SEG6_LOCAL_IIF] = { .type = NLA_U32 }, [SEG6_LOCAL_OIF] = { .type = NLA_U32 }, [SEG6_LOCAL_BPF] = { .type = NLA_NESTED }, diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index cc25fec44f85..19f3de3c24ef 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -888,15 +888,15 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (sk->sk_type != SOCK_STREAM) goto copy_uaddr; + /* Partial read */ + if (used + offset < skb_len) + continue; + if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } - - /* Partial read */ - if (used + offset < skb_len) - continue; } while (len > 0); out: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d1046f495e63..3a6fff98748b 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1186,10 +1186,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) return -EINVAL; } - local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) + - sizeof(void *) * channels, GFP_KERNEL); + local->int_scan_req = kzalloc(struct_size(local->int_scan_req, + channels, channels), + GFP_KERNEL); if (!local->int_scan_req) return -ENOMEM; + local->int_scan_req->n_channels = channels; eth_broadcast_addr(local->int_scan_req->bssid); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 42e2c84ed248..2c7e139efd53 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2959,7 +2959,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, if (tx) ieee80211_flush_queues(local, sdata, false); - drv_mgd_complete_tx(sdata->local, sdata, &info); + if (tx || frame_buf) + drv_mgd_complete_tx(sdata->local, sdata, &info); /* clear AP addr only after building the needed mgmt frames */ eth_zero_addr(sdata->deflink.u.mgd.bssid); @@ -7821,7 +7822,6 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); - drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } diff --git a/net/mctp/device.c b/net/mctp/device.c index 85cc5f31f1e7..8d1386601bbe 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -20,8 +20,7 @@ #include <net/sock.h> struct mctp_dump_cb { - int h; - int idx; + unsigned long ifindex; size_t a_idx; }; @@ -115,43 +114,36 @@ static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct mctp_dump_cb *mcb = (void *)cb->ctx; struct net *net = sock_net(skb->sk); - struct hlist_head *head; struct net_device *dev; struct ifaddrmsg *hdr; struct mctp_dev *mdev; - int ifindex; - int idx = 0, rc; - - hdr = nlmsg_data(cb->nlh); - // filter by ifindex if requested - ifindex = hdr->ifa_index; + int ifindex = 0, rc; + + /* Filter by ifindex if a header is provided */ + if (cb->nlh->nlmsg_len >= nlmsg_msg_size(sizeof(*hdr))) { + hdr = nlmsg_data(cb->nlh); + ifindex = hdr->ifa_index; + } else { + if (cb->strict_check) { + NL_SET_ERR_MSG(cb->extack, "mctp: Invalid header for addr dump request"); + return -EINVAL; + } + } rcu_read_lock(); - for (; mcb->h < NETDEV_HASHENTRIES; mcb->h++, mcb->idx = 0) { - idx = 0; - head = &net->dev_index_head[mcb->h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx >= mcb->idx && - (ifindex == 0 || ifindex == dev->ifindex)) { - mdev = __mctp_dev_get(dev); - if (mdev) { - rc = mctp_dump_dev_addrinfo(mdev, - skb, cb); - mctp_dev_put(mdev); - // Error indicates full buffer, this - // callback will get retried. - if (rc < 0) - goto out; - } - } - idx++; - // reset for next iteration - mcb->a_idx = 0; - } + for_each_netdev_dump(net, dev, mcb->ifindex) { + if (ifindex && ifindex != dev->ifindex) + continue; + mdev = __mctp_dev_get(dev); + if (!mdev) + continue; + rc = mctp_dump_dev_addrinfo(mdev, skb, cb); + mctp_dev_put(mdev); + if (rc < 0) + break; + mcb->a_idx = 0; } -out: rcu_read_unlock(); - mcb->idx = idx; return skb->len; } @@ -525,9 +517,12 @@ static struct notifier_block mctp_dev_nb = { }; static const struct rtnl_msg_handler mctp_device_rtnl_msg_handlers[] = { - {THIS_MODULE, PF_MCTP, RTM_NEWADDR, mctp_rtm_newaddr, NULL, 0}, - {THIS_MODULE, PF_MCTP, RTM_DELADDR, mctp_rtm_deladdr, NULL, 0}, - {THIS_MODULE, PF_MCTP, RTM_GETADDR, NULL, mctp_dump_addrinfo, 0}, + {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_NEWADDR, + .doit = mctp_rtm_newaddr}, + {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_DELADDR, + .doit = mctp_rtm_deladdr}, + {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_GETADDR, + .dumpit = mctp_dump_addrinfo}, }; int __init mctp_device_init(void) diff --git a/net/mctp/route.c b/net/mctp/route.c index d3c1f54386ef..009ba5edbd52 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -274,8 +274,10 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) key = flow->key; - if (WARN_ON(key->dev && key->dev != dev)) + if (key->dev) { + WARN_ON(key->dev != dev); return; + } mctp_dev_set_key(dev, key); } diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 4e0842df5234..2c260f33b55c 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -143,16 +143,15 @@ struct ncsi_channel_vlan_filter { }; struct ncsi_channel_stats { - u32 hnc_cnt_hi; /* Counter cleared */ - u32 hnc_cnt_lo; /* Counter cleared */ - u32 hnc_rx_bytes; /* Rx bytes */ - u32 hnc_tx_bytes; /* Tx bytes */ - u32 hnc_rx_uc_pkts; /* Rx UC packets */ - u32 hnc_rx_mc_pkts; /* Rx MC packets */ - u32 hnc_rx_bc_pkts; /* Rx BC packets */ - u32 hnc_tx_uc_pkts; /* Tx UC packets */ - u32 hnc_tx_mc_pkts; /* Tx MC packets */ - u32 hnc_tx_bc_pkts; /* Tx BC packets */ + u64 hnc_cnt; /* Counter cleared */ + u64 hnc_rx_bytes; /* Rx bytes */ + u64 hnc_tx_bytes; /* Tx bytes */ + u64 hnc_rx_uc_pkts; /* Rx UC packets */ + u64 hnc_rx_mc_pkts; /* Rx MC packets */ + u64 hnc_rx_bc_pkts; /* Rx BC packets */ + u64 hnc_tx_uc_pkts; /* Tx UC packets */ + u64 hnc_tx_mc_pkts; /* Tx MC packets */ + u64 hnc_tx_bc_pkts; /* Tx BC packets */ u32 hnc_fcs_err; /* FCS errors */ u32 hnc_align_err; /* Alignment errors */ u32 hnc_false_carrier; /* False carrier detection */ @@ -181,7 +180,7 @@ struct ncsi_channel_stats { u32 hnc_tx_1023_frames; /* Tx 512-1023 bytes frames */ u32 hnc_tx_1522_frames; /* Tx 1024-1522 bytes frames */ u32 hnc_tx_9022_frames; /* Tx 1523-9022 bytes frames */ - u32 hnc_rx_valid_bytes; /* Rx valid bytes */ + u64 hnc_rx_valid_bytes; /* Rx valid bytes */ u32 hnc_rx_runt_pkts; /* Rx error runt packets */ u32 hnc_rx_jabber_pkts; /* Rx error jabber packets */ u32 ncsi_rx_cmds; /* Rx NCSI commands */ diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h index f2f3b5c1b941..24edb2737972 100644 --- a/net/ncsi/ncsi-pkt.h +++ b/net/ncsi/ncsi-pkt.h @@ -252,16 +252,15 @@ struct ncsi_rsp_gp_pkt { /* Get Controller Packet Statistics */ struct ncsi_rsp_gcps_pkt { struct ncsi_rsp_pkt_hdr rsp; /* Response header */ - __be32 cnt_hi; /* Counter cleared */ - __be32 cnt_lo; /* Counter cleared */ - __be32 rx_bytes; /* Rx bytes */ - __be32 tx_bytes; /* Tx bytes */ - __be32 rx_uc_pkts; /* Rx UC packets */ - __be32 rx_mc_pkts; /* Rx MC packets */ - __be32 rx_bc_pkts; /* Rx BC packets */ - __be32 tx_uc_pkts; /* Tx UC packets */ - __be32 tx_mc_pkts; /* Tx MC packets */ - __be32 tx_bc_pkts; /* Tx BC packets */ + __be64 cnt; /* Counter cleared */ + __be64 rx_bytes; /* Rx bytes */ + __be64 tx_bytes; /* Tx bytes */ + __be64 rx_uc_pkts; /* Rx UC packets */ + __be64 rx_mc_pkts; /* Rx MC packets */ + __be64 rx_bc_pkts; /* Rx BC packets */ + __be64 tx_uc_pkts; /* Tx UC packets */ + __be64 tx_mc_pkts; /* Tx MC packets */ + __be64 tx_bc_pkts; /* Tx BC packets */ __be32 fcs_err; /* FCS errors */ __be32 align_err; /* Alignment errors */ __be32 false_carrier; /* False carrier detection */ @@ -290,11 +289,11 @@ struct ncsi_rsp_gcps_pkt { __be32 tx_1023_frames; /* Tx 512-1023 bytes frames */ __be32 tx_1522_frames; /* Tx 1024-1522 bytes frames */ __be32 tx_9022_frames; /* Tx 1523-9022 bytes frames */ - __be32 rx_valid_bytes; /* Rx valid bytes */ + __be64 rx_valid_bytes; /* Rx valid bytes */ __be32 rx_runt_pkts; /* Rx error runt packets */ __be32 rx_jabber_pkts; /* Rx error jabber packets */ __be32 checksum; /* Checksum */ -}; +} __packed __aligned(4); /* Get NCSI Statistics */ struct ncsi_rsp_gns_pkt { diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 4a8ce2949fae..8668888c5a2f 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -926,16 +926,15 @@ static int ncsi_rsp_handler_gcps(struct ncsi_request *nr) /* Update HNC's statistics */ ncs = &nc->stats; - ncs->hnc_cnt_hi = ntohl(rsp->cnt_hi); - ncs->hnc_cnt_lo = ntohl(rsp->cnt_lo); - ncs->hnc_rx_bytes = ntohl(rsp->rx_bytes); - ncs->hnc_tx_bytes = ntohl(rsp->tx_bytes); - ncs->hnc_rx_uc_pkts = ntohl(rsp->rx_uc_pkts); - ncs->hnc_rx_mc_pkts = ntohl(rsp->rx_mc_pkts); - ncs->hnc_rx_bc_pkts = ntohl(rsp->rx_bc_pkts); - ncs->hnc_tx_uc_pkts = ntohl(rsp->tx_uc_pkts); - ncs->hnc_tx_mc_pkts = ntohl(rsp->tx_mc_pkts); - ncs->hnc_tx_bc_pkts = ntohl(rsp->tx_bc_pkts); + ncs->hnc_cnt = be64_to_cpu(rsp->cnt); + ncs->hnc_rx_bytes = be64_to_cpu(rsp->rx_bytes); + ncs->hnc_tx_bytes = be64_to_cpu(rsp->tx_bytes); + ncs->hnc_rx_uc_pkts = be64_to_cpu(rsp->rx_uc_pkts); + ncs->hnc_rx_mc_pkts = be64_to_cpu(rsp->rx_mc_pkts); + ncs->hnc_rx_bc_pkts = be64_to_cpu(rsp->rx_bc_pkts); + ncs->hnc_tx_uc_pkts = be64_to_cpu(rsp->tx_uc_pkts); + ncs->hnc_tx_mc_pkts = be64_to_cpu(rsp->tx_mc_pkts); + ncs->hnc_tx_bc_pkts = be64_to_cpu(rsp->tx_bc_pkts); ncs->hnc_fcs_err = ntohl(rsp->fcs_err); ncs->hnc_align_err = ntohl(rsp->align_err); ncs->hnc_false_carrier = ntohl(rsp->false_carrier); @@ -964,7 +963,7 @@ static int ncsi_rsp_handler_gcps(struct ncsi_request *nr) ncs->hnc_tx_1023_frames = ntohl(rsp->tx_1023_frames); ncs->hnc_tx_1522_frames = ntohl(rsp->tx_1522_frames); ncs->hnc_tx_9022_frames = ntohl(rsp->tx_9022_frames); - ncs->hnc_rx_valid_bytes = ntohl(rsp->rx_valid_bytes); + ncs->hnc_rx_valid_bytes = be64_to_cpu(rsp->rx_valid_bytes); ncs->hnc_rx_runt_pkts = ntohl(rsp->rx_runt_pkts); ncs->hnc_rx_jabber_pkts = ntohl(rsp->rx_jabber_pkts); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 559665467b04..1d5de1d9f008 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -621,7 +621,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_COUNT] = { .procname = "nf_conntrack_count", @@ -657,7 +659,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { .data = &nf_ct_expect_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_ACCT] = { .procname = "nf_conntrack_acct", @@ -951,7 +955,9 @@ static struct ctl_table nf_ct_netfilter_table[] = { .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, }, { } }; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index ccca6e3848bc..9df883d79acc 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -248,7 +248,7 @@ static noinline bool nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_ct) { - static const unsigned long uses_nat = IPS_NAT_MASK | IPS_SEQ_ADJUST_BIT; + static const unsigned long uses_nat = IPS_NAT_MASK | IPS_SEQ_ADJUST; const struct nf_conntrack_tuple_hash *thash; const struct nf_conntrack_zone *zone; struct nf_conn *ct; @@ -287,8 +287,14 @@ nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple, zone = nf_ct_zone(ignored_ct); thash = nf_conntrack_find_get(net, zone, tuple); - if (unlikely(!thash)) /* clashing entry went away */ - return false; + if (unlikely(!thash)) { + struct nf_conntrack_tuple reply; + + nf_ct_invert_tuple(&reply, tuple); + thash = nf_conntrack_find_get(net, zone, &reply); + if (!thash) /* clashing entry went away */ + return false; + } ct = nf_ct_tuplehash_to_ctrack(thash); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 9b2d7463d3d3..df0798da2329 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -19,10 +19,16 @@ struct nft_quota { }; static inline bool nft_overquota(struct nft_quota *priv, - const struct sk_buff *skb) + const struct sk_buff *skb, + bool *report) { - return atomic64_add_return(skb->len, priv->consumed) >= - atomic64_read(&priv->quota); + u64 consumed = atomic64_add_return(skb->len, priv->consumed); + u64 quota = atomic64_read(&priv->quota); + + if (report) + *report = consumed >= quota; + + return consumed > quota; } static inline bool nft_quota_invert(struct nft_quota *priv) @@ -34,7 +40,7 @@ static inline void nft_quota_do_eval(struct nft_quota *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { - if (nft_overquota(priv, pkt->skb) ^ nft_quota_invert(priv)) + if (nft_overquota(priv, pkt->skb, NULL) ^ nft_quota_invert(priv)) regs->verdict.code = NFT_BREAK; } @@ -51,13 +57,13 @@ static void nft_quota_obj_eval(struct nft_object *obj, const struct nft_pktinfo *pkt) { struct nft_quota *priv = nft_obj_data(obj); - bool overquota; + bool overquota, report; - overquota = nft_overquota(priv, pkt->skb); + overquota = nft_overquota(priv, pkt->skb, &report); if (overquota ^ nft_quota_invert(priv)) regs->verdict.code = NFT_BREAK; - if (overquota && + if (report && !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) nft_obj_notify(nft_net(pkt), obj->key.table, obj, 0, 0, NFT_MSG_NEWOBJ, 0, nft_pf(pkt), 0, GFP_ATOMIC); diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index c15db28c5ebc..be7c16c79f71 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1114,6 +1114,25 @@ bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features, } /** + * pipapo_resmap_init_avx2() - Initialise result map before first use + * @m: Matching data, including mapping table + * @res_map: Result map + * + * Like pipapo_resmap_init() but do not set start map bits covered by the first field. + */ +static inline void pipapo_resmap_init_avx2(const struct nft_pipapo_match *m, unsigned long *res_map) +{ + const struct nft_pipapo_field *f = m->f; + int i; + + /* Starting map doesn't need to be set to all-ones for this implementation, + * but we do need to zero the remaining bits, if any. + */ + for (i = f->bsize; i < m->bsize_max; i++) + res_map[i] = 0ul; +} + +/** * nft_pipapo_avx2_lookup() - Lookup function for AVX2 implementation * @net: Network namespace * @set: nftables API set representation @@ -1171,7 +1190,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, res = scratch->map + (map_index ? m->bsize_max : 0); fill = scratch->map + (map_index ? 0 : m->bsize_max); - /* Starting map doesn't need to be set for this implementation */ + pipapo_resmap_init_avx2(m, res); nft_pipapo_avx2_prepare(); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index d499eb3f4f29..3e3ae29dde33 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -617,10 +617,10 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, struct geneve_opt *opt; int offset = 0; - inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_GENEVE); - if (!inner) - goto failure; while (opts->len > offset) { + inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_GENEVE); + if (!inner) + goto failure; opt = (struct geneve_opt *)(opts->u.data + offset); if (nla_put_be16(skb, NFTA_TUNNEL_KEY_GENEVE_CLASS, opt->opt_class) || @@ -630,8 +630,8 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, opt->length * 4, opt->opt_data)) goto inner_failure; offset += sizeof(*opt) + opt->length * 4; + nla_nest_end(skb, inner); } - nla_nest_end(skb, inner); } nla_nest_end(skb, nest); return 0; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 27511c90a26f..daef0eeaea2c 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -1140,6 +1140,11 @@ int netlbl_conn_setattr(struct sock *sk, break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: + if (sk->sk_family != AF_INET6) { + ret_val = -EAFNOSUPPORT; + goto conn_setattr_return; + } + addr6 = (struct sockaddr_in6 *)addr; entry = netlbl_domhsh_getentry_af6(secattr->domain, &addr6->sin6_addr); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 8a848ce72e29..b80bd3a90773 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -788,7 +788,7 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) memset(&key->ipv4, 0, sizeof(key->ipv4)); } } else if (eth_p_mpls(key->eth.type)) { - u8 label_count = 1; + size_t label_count = 1; memset(&key->mpls, 0, sizeof(key->mpls)); skb_set_inner_network_header(skb, skb->mac_len); diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 5f2e06815745..63c02040b426 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -168,7 +168,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 9da86db4d2c2..3ee46f6e005d 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -661,7 +661,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, for (i = q->nbands; i < oldbands; i++) { if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) list_del_init(&q->classes[i].alist); - qdisc_tree_flush_backlog(q->classes[i].qdisc); + qdisc_purge_queue(q->classes[i].qdisc); } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index f59a2cb2c803..91f5ef6be0f2 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -901,7 +901,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); } while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9330923a624c..47b5a056165c 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -431,7 +431,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit || q->memory_usage > q->memory_limit) { - struct sk_buff *skb = fq_codel_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); q->cstats.drop_len += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 68e6acd0f130..607c580d75e4 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -357,7 +357,7 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, /* Drop excess packets if new limit is lower */ while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_pie_qdisc_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); len_dropped += qdisc_pkt_len(skb); num_dropped += 1; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 5d9cccfac4a1..afcb83d469ff 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -175,6 +175,11 @@ struct hfsc_sched { #define HT_INFINITY 0xffffffffffffffffULL /* infinite time value */ +static bool cl_in_el_or_vttree(struct hfsc_class *cl) +{ + return ((cl->cl_flags & HFSC_FSC) && cl->cl_nactive) || + ((cl->cl_flags & HFSC_RSC) && !RB_EMPTY_NODE(&cl->el_node)); +} /* * eligible tree holds backlogged classes being sorted by their eligible times. @@ -1040,6 +1045,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + RB_CLEAR_NODE(&cl->el_node); + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); @@ -1570,7 +1577,10 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) return err; } - if (first && !cl->cl_nactive) { + sch->qstats.backlog += len; + sch->q.qlen++; + + if (first && !cl_in_el_or_vttree(cl)) { if (cl->cl_flags & HFSC_RSC) init_ed(cl, len); if (cl->cl_flags & HFSC_FSC) @@ -1585,9 +1595,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } - sch->qstats.backlog += len; - sch->q.qlen++; - return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index d26cd436cbe3..83fc44f20e31 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -560,7 +560,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, qlen = sch->q.qlen; prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = hhf_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); rtnl_kfree_skbs(skb, skb); } diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 2da6250ec346..48c5ab8ec143 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -190,7 +190,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, /* Drop excess packets if new limit is lower */ qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index fdc5ef52c3ee..fdd9caa41e80 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -211,7 +211,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); for (i = q->bands; i < oldbands; i++) - qdisc_tree_flush_backlog(q->queues[i]); + qdisc_purge_queue(q->queues[i]); for (i = oldbands; i < q->bands; i++) { q->queues[i] = queues[i]; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 16277b6a0238..3c6b4460cf2c 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -283,7 +283,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, q->userbits = userbits; q->limit = ctl->limit; if (child) { - qdisc_tree_flush_backlog(q->qdisc); + qdisc_purge_queue(q->qdisc); old_child = q->qdisc; q->qdisc = child; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 002941d35b64..d564675a8be4 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -310,7 +310,10 @@ drop: /* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */ x = q->tail->next; slot = &q->slots[x]; - q->tail->next = slot->next; + if (slot->next == x) + q->tail = NULL; /* no more active slots */ + else + q->tail->next = slot->next; q->ht[slot->hash] = SFQ_EMPTY_SLOT; goto drop; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index f92174008499..61dd5c8f2310 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -452,7 +452,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); if (child) { - qdisc_tree_flush_backlog(q->qdisc); + qdisc_purge_queue(q->qdisc); old = q->qdisc; q->qdisc = child; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index fd73be940f46..77a76634014a 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -529,6 +529,8 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write, return ret; } +static DEFINE_MUTEX(sctp_sysctl_mutex); + static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -553,6 +555,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, if (new_value > max || new_value < min) return -EINVAL; + mutex_lock(&sctp_sysctl_mutex); net->sctp.udp_port = new_value; sctp_udp_sock_stop(net); if (new_value) { @@ -565,6 +568,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, lock_sock(sk); sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); release_sock(sk); + mutex_unlock(&sctp_sysctl_mutex); } return ret; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index dbcc72b43d0c..d44d7f427fc9 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -1084,14 +1084,16 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; + struct net_device *base_ndev; struct net *net; - ndev = pnet_find_base_ndev(ndev); + base_ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); - if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, + if (smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid) && + smc_pnet_find_ndev_pnetid_by_table(base_ndev, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { - smc_pnet_find_rdma_dev(ndev, ini); + smc_pnet_find_rdma_dev(base_ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 142ee6554848..4ffb2bcaf364 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -275,9 +275,6 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, old = rcu_dereference_protected(clnt->cl_xprt, lockdep_is_held(&clnt->cl_lock)); - if (!xprt_bound(xprt)) - clnt->cl_autobind = 1; - clnt->cl_timeout = timeout; rcu_assign_pointer(clnt->cl_xprt, xprt); spin_unlock(&clnt->cl_lock); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 102c3818bc54..53bcca365fb1 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -820,9 +820,10 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) } trace_rpcb_setport(child, map->r_status, map->r_port); - xprt->ops->set_port(xprt, map->r_port); - if (map->r_port) + if (map->r_port) { + xprt->ops->set_port(xprt, map->r_port); xprt_set_bound(xprt); + } } /* diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 9b45fbdc90ca..73bc39281ef5 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -276,6 +276,8 @@ 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/tipc/crypto.c b/net/tipc/crypto.c index c524421ec652..79f91b6ca8c8 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -817,12 +817,20 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb, goto exit; } + /* Get net to avoid freed tipc_crypto when delete namespace */ + if (!maybe_get_net(aead->crypto->net)) { + tipc_bearer_put(b); + rc = -ENODEV; + goto exit; + } + /* Now, do encrypt */ rc = crypto_aead_encrypt(req); if (rc == -EINPROGRESS || rc == -EBUSY) return rc; tipc_bearer_put(b); + put_net(aead->crypto->net); exit: kfree(ctx); @@ -860,6 +868,7 @@ static void tipc_aead_encrypt_done(void *data, int err) kfree(tx_ctx); tipc_bearer_put(b); tipc_aead_put(aead); + put_net(net); } /** diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 5df08d848b5c..1852fac3e72b 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -395,7 +395,6 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; shinfo = skb_shinfo(strp->anchor); - shinfo->frag_list = NULL; /* If we don't know the length go max plus page for cipher overhead */ need_spc = strp->stm.full_len ?: TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; @@ -411,6 +410,8 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) page, 0, 0); } + shinfo->frag_list = NULL; + strp->copy_mode = 1; strp->stm.offset = 0; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 6e30fe879d53..4a9a3aed5d6d 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -908,6 +908,13 @@ more_data: &msg_redir, send, flags); lock_sock(sk); if (err < 0) { + /* Regardless of whether the data represented by + * msg_redir is sent successfully, we have already + * uncharged it via sk_msg_return_zero(). The + * msg->sg.size represents the remaining unprocessed + * data, which needs to be uncharged here. + */ + sk_mem_uncharge(sk, msg->sg.size); *copied -= sk_msg_free_nocharge(sk, &msg_redir); msg->sg.size = 0; } @@ -1120,9 +1127,13 @@ alloc_encrypted: num_async++; else if (ret == -ENOMEM) goto wait_for_memory; - else if (ctx->open_rec && ret == -ENOSPC) + else if (ctx->open_rec && ret == -ENOSPC) { + if (msg_pl->cork_bytes) { + ret = 0; + goto send_end; + } goto rollback_iter; - else if (ret != -EAGAIN) + } else if (ret != -EAGAIN) goto send_end; } continue; diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 28b232f281ab..8b5d04210d7c 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -16,11 +16,6 @@ config UNIX Say Y unless you know what you are doing. -config UNIX_SCM - bool - depends on UNIX - default y - config AF_UNIX_OOB bool depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index 20491825b4d0..4ddd125c4642 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -11,5 +11,3 @@ unix-$(CONFIG_BPF_SYSCALL) += unix_bpf.o obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o - -obj-$(CONFIG_UNIX_SCM) += scm.o diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ab23c8d72122..236a2cd2bc93 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -117,8 +117,6 @@ #include <linux/file.h> #include <linux/btf_ids.h> -#include "scm.h" - static atomic_long_t unix_nr_socks; static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2]; static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2]; @@ -980,11 +978,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; u = unix_sk(sk); - u->inflight = 0; + u->listener = NULL; + u->vertex = NULL; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); @@ -1583,6 +1581,7 @@ restart: newsk->sk_type = sk->sk_type; init_peercred(newsk); newu = unix_sk(newsk); + newu->listener = other; RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); @@ -1678,8 +1677,8 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk = sock->sk; - struct sock *tsk; struct sk_buff *skb; + struct sock *tsk; int err; err = -EOPNOTSUPP; @@ -1709,6 +1708,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, /* attach accepted sock to socket */ unix_state_lock(tsk); + unix_update_edges(unix_sk(tsk)); newsock->state = SS_CONNECTED; unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); @@ -1752,51 +1752,65 @@ out: return err; } +/* The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + /* Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + if (unix_prepare_fpl(UNIXCB(skb).fp)) + return -ENOMEM; + + return 0; +} + +static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + unix_destroy_fpl(scm->fp); +} + static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { scm->fp = scm_fp_dup(UNIXCB(skb).fp); +} - /* - * Garbage collection of unix sockets starts by selecting a set of - * candidate sockets which have reference only from being in flight - * (total_refs == inflight_refs). This condition is checked once during - * the candidate collection phase, and candidates are marked as such, so - * that non-candidates can later be ignored. While inflight_refs is - * protected by unix_gc_lock, total_refs (file count) is not, hence this - * is an instantaneous decision. - * - * Once a candidate, however, the socket must not be reinstalled into a - * file descriptor while the garbage collection is in progress. - * - * If the above conditions are met, then the directed graph of - * candidates (*) does not change while unix_gc_lock is held. - * - * Any operations that changes the file count through file descriptors - * (dup, close, sendmsg) does not change the graph since candidates are - * not installed in fds. - * - * Dequeing a candidate via recvmsg would install it into an fd, but - * that takes unix_gc_lock to decrement the inflight count, so it's - * serialized with garbage collection. - * - * MSG_PEEK is special in that it does not change the inflight count, - * yet does install the socket into an fd. The following lock/unlock - * pair is to ensure serialization with garbage collection. It must be - * done between incrementing the file count and installing the file into - * an fd. - * - * If garbage collection starts after the barrier provided by the - * lock/unlock, then it will see the elevated refcount and not mark this - * as a candidate. If a garbage collection is already in progress - * before the file count was incremented, then the lock/unlock pair will - * ensure that garbage collection is finished before progressing to - * installing the fd. - * - * (*) A -> B where B is on the queue of A or B is on the queue of C - * which is on the queue of listening socket A. - */ - spin_lock(&unix_gc_lock); - spin_unlock(&unix_gc_lock); +static void unix_destruct_scm(struct sk_buff *skb) +{ + struct scm_cookie scm; + + memset(&scm, 0, sizeof(scm)); + scm.pid = UNIXCB(skb).pid; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); + + /* Alas, it calls VFS */ + /* So fscking what? fput() had been SMP-safe since the last Summer */ + scm_destroy(&scm); + sock_wfree(skb); } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -1855,8 +1869,10 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_add(fp->count, &u->scm_stat.nr_fds); + unix_add_edges(fp, u); + } } static void scm_stat_del(struct sock *sk, struct sk_buff *skb) @@ -1864,8 +1880,10 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_sub(fp->count, &u->scm_stat.nr_fds); + unix_del_edges(fp); + } } /* @@ -1885,11 +1903,12 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, long timeo; int err; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags&MSG_OOB) goto out; @@ -2157,11 +2176,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, bool fds_sent = false; int data_len; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { #if IS_ENABLED(CONFIG_AF_UNIX_OOB) diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2a758531e102..23efb78fe9ef 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -81,278 +81,551 @@ #include <net/scm.h> #include <net/tcp_states.h> -#include "scm.h" +struct unix_sock *unix_get_socket(struct file *filp) +{ + struct inode *inode = file_inode(filp); + + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + const struct proto_ops *ops; + struct sock *sk = sock->sk; -/* Internal data structures and random procedures: */ + ops = READ_ONCE(sock->ops); -static LIST_HEAD(gc_candidates); -static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); + /* PF_UNIX ? */ + if (sk && ops && ops->family == PF_UNIX) + return unix_sk(sk); + } -static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), - struct sk_buff_head *hitlist) + return NULL; +} + +static struct unix_vertex *unix_edge_successor(struct unix_edge *edge) { - struct sk_buff *skb; - struct sk_buff *next; - - spin_lock(&x->sk_receive_queue.lock); - skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - /* Do we have file descriptors ? */ - if (UNIXCB(skb).fp) { - bool hit = false; - /* Process the descriptors of this socket */ - int nfd = UNIXCB(skb).fp->count; - struct file **fp = UNIXCB(skb).fp->fp; - - while (nfd--) { - /* Get the socket the fd matches if it indeed does so */ - struct sock *sk = unix_get_socket(*fp++); - - if (sk) { - struct unix_sock *u = unix_sk(sk); - - /* Ignore non-candidates, they could - * have been added to the queues after - * starting the garbage collection - */ - if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { - hit = true; - - func(u); - } - } - } - if (hit && hitlist != NULL) { - __skb_unlink(skb, &x->sk_receive_queue); - __skb_queue_tail(hitlist, skb); - } - } + /* If an embryo socket has a fd, + * the listener indirectly holds the fd's refcnt. + */ + if (edge->successor->listener) + return unix_sk(edge->successor->listener)->vertex; + + return edge->successor->vertex; +} + +static bool unix_graph_maybe_cyclic; +static bool unix_graph_grouped; + +static void unix_update_graph(struct unix_vertex *vertex) +{ + /* If the receiver socket is not inflight, no cyclic + * reference could be formed. + */ + if (!vertex) + return; + + unix_graph_maybe_cyclic = true; + unix_graph_grouped = false; +} + +static LIST_HEAD(unix_unvisited_vertices); + +enum unix_vertex_index { + UNIX_VERTEX_INDEX_MARK1, + UNIX_VERTEX_INDEX_MARK2, + UNIX_VERTEX_INDEX_START, +}; + +static unsigned long unix_vertex_unvisited_index = UNIX_VERTEX_INDEX_MARK1; + +static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) +{ + struct unix_vertex *vertex = edge->predecessor->vertex; + + if (!vertex) { + vertex = list_first_entry(&fpl->vertices, typeof(*vertex), entry); + vertex->index = unix_vertex_unvisited_index; + vertex->out_degree = 0; + INIT_LIST_HEAD(&vertex->edges); + INIT_LIST_HEAD(&vertex->scc_entry); + + list_move_tail(&vertex->entry, &unix_unvisited_vertices); + edge->predecessor->vertex = vertex; } - spin_unlock(&x->sk_receive_queue.lock); + + vertex->out_degree++; + list_add_tail(&edge->vertex_entry, &vertex->edges); + + unix_update_graph(unix_edge_successor(edge)); } -static void scan_children(struct sock *x, void (*func)(struct unix_sock *), - struct sk_buff_head *hitlist) +static void unix_del_edge(struct scm_fp_list *fpl, struct unix_edge *edge) { - if (x->sk_state != TCP_LISTEN) { - scan_inflight(x, func, hitlist); - } else { - struct sk_buff *skb; - struct sk_buff *next; - struct unix_sock *u; - LIST_HEAD(embryos); + struct unix_vertex *vertex = edge->predecessor->vertex; - /* For a listening socket collect the queued embryos - * and perform a scan on them as well. - */ - spin_lock(&x->sk_receive_queue.lock); - skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - u = unix_sk(skb->sk); + if (!fpl->dead) + unix_update_graph(unix_edge_successor(edge)); - /* An embryo cannot be in-flight, so it's safe - * to use the list link. - */ - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &embryos); - } - spin_unlock(&x->sk_receive_queue.lock); + list_del(&edge->vertex_entry); + vertex->out_degree--; - while (!list_empty(&embryos)) { - u = list_entry(embryos.next, struct unix_sock, link); - scan_inflight(&u->sk, func, hitlist); - list_del_init(&u->link); - } + if (!vertex->out_degree) { + edge->predecessor->vertex = NULL; + list_move_tail(&vertex->entry, &fpl->vertices); } } -static void dec_inflight(struct unix_sock *usk) +static void unix_free_vertices(struct scm_fp_list *fpl) { - usk->inflight--; + struct unix_vertex *vertex, *next_vertex; + + list_for_each_entry_safe(vertex, next_vertex, &fpl->vertices, entry) { + list_del(&vertex->entry); + kfree(vertex); + } } -static void inc_inflight(struct unix_sock *usk) +static DEFINE_SPINLOCK(unix_gc_lock); +unsigned int unix_tot_inflight; + +void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) { - usk->inflight++; + int i = 0, j = 0; + + spin_lock(&unix_gc_lock); + + if (!fpl->count_unix) + goto out; + + do { + struct unix_sock *inflight = unix_get_socket(fpl->fp[j++]); + struct unix_edge *edge; + + if (!inflight) + continue; + + edge = fpl->edges + i++; + edge->predecessor = inflight; + edge->successor = receiver; + + unix_add_edge(fpl, edge); + } while (i < fpl->count_unix); + + receiver->scm_stat.nr_unix_fds += fpl->count_unix; + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + fpl->count_unix); +out: + WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight + fpl->count); + + spin_unlock(&unix_gc_lock); + + fpl->inflight = true; + + unix_free_vertices(fpl); } -static void inc_inflight_move_tail(struct unix_sock *u) +void unix_del_edges(struct scm_fp_list *fpl) { - u->inflight++; + struct unix_sock *receiver; + int i = 0; + + spin_lock(&unix_gc_lock); - /* If this still might be part of a cycle, move it to the end - * of the list, so that it's checked even if it was already - * passed over + if (!fpl->count_unix) + goto out; + + do { + struct unix_edge *edge = fpl->edges + i++; + + unix_del_edge(fpl, edge); + } while (i < fpl->count_unix); + + if (!fpl->dead) { + receiver = fpl->edges[0].successor; + receiver->scm_stat.nr_unix_fds -= fpl->count_unix; + } + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - fpl->count_unix); +out: + WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight - fpl->count); + + spin_unlock(&unix_gc_lock); + + fpl->inflight = false; +} + +void unix_update_edges(struct unix_sock *receiver) +{ + /* nr_unix_fds is only updated under unix_state_lock(). + * If it's 0 here, the embryo socket is not part of the + * inflight graph, and GC will not see it, so no lock needed. */ - if (test_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags)) - list_move_tail(&u->link, &gc_candidates); + if (!receiver->scm_stat.nr_unix_fds) { + receiver->listener = NULL; + } else { + spin_lock(&unix_gc_lock); + unix_update_graph(unix_sk(receiver->listener)->vertex); + receiver->listener = NULL; + spin_unlock(&unix_gc_lock); + } } -static bool gc_in_progress; -#define UNIX_INFLIGHT_TRIGGER_GC 16000 +int unix_prepare_fpl(struct scm_fp_list *fpl) +{ + struct unix_vertex *vertex; + int i; + + if (!fpl->count_unix) + return 0; + + for (i = 0; i < fpl->count_unix; i++) { + vertex = kmalloc(sizeof(*vertex), GFP_KERNEL); + if (!vertex) + goto err; + + list_add(&vertex->entry, &fpl->vertices); + } + + fpl->edges = kvmalloc_array(fpl->count_unix, sizeof(*fpl->edges), + GFP_KERNEL_ACCOUNT); + if (!fpl->edges) + goto err; + + return 0; -void wait_for_unix_gc(void) +err: + unix_free_vertices(fpl); + return -ENOMEM; +} + +void unix_destroy_fpl(struct scm_fp_list *fpl) { - /* If number of inflight sockets is insane, - * force a garbage collect right now. - * Paired with the WRITE_ONCE() in unix_inflight(), - * unix_notinflight() and gc_in_progress(). - */ - if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && - !READ_ONCE(gc_in_progress)) - unix_gc(); - wait_event(unix_gc_wait, !READ_ONCE(gc_in_progress)); + if (fpl->inflight) + unix_del_edges(fpl); + + kvfree(fpl->edges); + unix_free_vertices(fpl); } -/* The external entry point: unix_gc() */ -void unix_gc(void) +static bool unix_vertex_dead(struct unix_vertex *vertex) { - struct sk_buff *next_skb, *skb; + struct unix_edge *edge; struct unix_sock *u; - struct unix_sock *next; - struct sk_buff_head hitlist; - struct list_head cursor; - LIST_HEAD(not_cycle_list); + long total_ref; - spin_lock(&unix_gc_lock); + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + struct unix_vertex *next_vertex = unix_edge_successor(edge); - /* Avoid a recursive GC. */ - if (gc_in_progress) - goto out; + /* The vertex's fd can be received by a non-inflight socket. */ + if (!next_vertex) + return false; - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ - WRITE_ONCE(gc_in_progress, true); + /* The vertex's fd can be received by an inflight socket in + * another SCC. + */ + if (next_vertex->scc_index != vertex->scc_index) + return false; + } - /* First, select candidates for garbage collection. Only - * in-flight sockets are considered, and from those only ones - * which don't have any external reference. - * - * Holding unix_gc_lock will protect these candidates from - * being detached, and hence from gaining an external - * reference. Since there are no possible receivers, all - * buffers currently on the candidates' queues stay there - * during the garbage collection. - * - * We also know that no new candidate can be added onto the - * receive queues. Other, non candidate sockets _can_ be - * added to queue, so we must make sure only to touch - * candidates. - * - * Embryos, though never candidates themselves, affect which - * candidates are reachable by the garbage collector. Before - * being added to a listener's queue, an embryo may already - * receive data carrying SCM_RIGHTS, potentially making the - * passed socket a candidate that is not yet reachable by the - * collector. It becomes reachable once the embryo is - * enqueued. Therefore, we must ensure that no SCM-laden - * embryo appears in a (candidate) listener's queue between - * consecutive scan_children() calls. - */ - list_for_each_entry_safe(u, next, &gc_inflight_list, link) { - struct sock *sk = &u->sk; - long total_refs; - - total_refs = file_count(sk->sk_socket->file); - - BUG_ON(!u->inflight); - BUG_ON(total_refs < u->inflight); - if (total_refs == u->inflight) { - list_move_tail(&u->link, &gc_candidates); - __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); - __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); - - if (sk->sk_state == TCP_LISTEN) { - unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); - unix_state_unlock(sk); + /* No receiver exists out of the same SCC. */ + + edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); + u = edge->predecessor; + total_ref = file_count(u->sk.sk_socket->file); + + /* If not close()d, total_ref > out_degree. */ + if (total_ref != vertex->out_degree) + return false; + + return true; +} + +enum unix_recv_queue_lock_class { + U_RECVQ_LOCK_NORMAL, + U_RECVQ_LOCK_EMBRYO, +}; + +static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist) +{ + skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist); + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + WARN_ON_ONCE(skb_unref(u->oob_skb)); + u->oob_skb = NULL; + } +#endif +} + +static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) +{ + struct unix_vertex *vertex; + + list_for_each_entry_reverse(vertex, scc, scc_entry) { + struct sk_buff_head *queue; + struct unix_edge *edge; + struct unix_sock *u; + + edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); + u = edge->predecessor; + queue = &u->sk.sk_receive_queue; + + spin_lock(&queue->lock); + + if (u->sk.sk_state == TCP_LISTEN) { + struct sk_buff *skb; + + skb_queue_walk(queue, skb) { + struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; + + /* listener -> embryo order, the inversion never happens. */ + spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO); + unix_collect_queue(unix_sk(skb->sk), hitlist); + spin_unlock(&embryo_queue->lock); } + } else { + unix_collect_queue(u, hitlist); } + + spin_unlock(&queue->lock); } +} - /* Now remove all internal in-flight reference to children of - * the candidates. - */ - list_for_each_entry(u, &gc_candidates, link) - scan_children(&u->sk, dec_inflight, NULL); +static bool unix_scc_cyclic(struct list_head *scc) +{ + struct unix_vertex *vertex; + struct unix_edge *edge; - /* Restore the references for children of all candidates, - * which have remaining references. Do this recursively, so - * only those remain, which form cyclic references. - * - * Use a "cursor" link, to make the list traversal safe, even - * though elements might be moved about. + /* SCC containing multiple vertices ? */ + if (!list_is_singular(scc)) + return true; + + vertex = list_first_entry(scc, typeof(*vertex), scc_entry); + + /* Self-reference or a embryo-listener circle ? */ + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + if (unix_edge_successor(edge) == vertex) + return true; + } + + return false; +} + +static LIST_HEAD(unix_visited_vertices); +static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; + +static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, + struct sk_buff_head *hitlist) +{ + LIST_HEAD(vertex_stack); + struct unix_edge *edge; + LIST_HEAD(edge_stack); + +next_vertex: + /* Push vertex to vertex_stack and mark it as on-stack + * (index >= UNIX_VERTEX_INDEX_START). + * The vertex will be popped when finalising SCC later. */ - list_add(&cursor, &gc_candidates); - while (cursor.next != &gc_candidates) { - u = list_entry(cursor.next, struct unix_sock, link); + list_add(&vertex->scc_entry, &vertex_stack); + + vertex->index = *last_index; + vertex->scc_index = *last_index; + (*last_index)++; + + /* Explore neighbour vertices (receivers of the current vertex's fd). */ + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + struct unix_vertex *next_vertex = unix_edge_successor(edge); + + if (!next_vertex) + continue; + + if (next_vertex->index == unix_vertex_unvisited_index) { + /* Iterative deepening depth first search + * + * 1. Push a forward edge to edge_stack and set + * the successor to vertex for the next iteration. + */ + list_add(&edge->stack_entry, &edge_stack); - /* Move cursor to after the current position. */ - list_move(&cursor, &u->link); + vertex = next_vertex; + goto next_vertex; - if (u->inflight) { - list_move_tail(&u->link, ¬_cycle_list); - __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); - scan_children(&u->sk, inc_inflight_move_tail, NULL); + /* 2. Pop the edge directed to the current vertex + * and restore the ancestor for backtracking. + */ +prev_vertex: + edge = list_first_entry(&edge_stack, typeof(*edge), stack_entry); + list_del_init(&edge->stack_entry); + + next_vertex = vertex; + vertex = edge->predecessor->vertex; + + /* If the successor has a smaller scc_index, two vertices + * are in the same SCC, so propagate the smaller scc_index + * to skip SCC finalisation. + */ + vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); + } else if (next_vertex->index != unix_vertex_grouped_index) { + /* Loop detected by a back/cross edge. + * + * The successor is on vertex_stack, so two vertices are in + * the same SCC. If the successor has a smaller *scc_index*, + * propagate it to skip SCC finalisation. + */ + vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); + } else { + /* The successor was already grouped as another SCC */ } } - list_del(&cursor); - /* Now gc_candidates contains only garbage. Restore original - * inflight counters for these as well, and remove the skbuffs - * which are creating the cycle(s). - */ - skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) { - scan_children(&u->sk, inc_inflight, &hitlist); + if (vertex->index == vertex->scc_index) { + struct unix_vertex *v; + struct list_head scc; + bool scc_dead = true; -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; + /* SCC finalised. + * + * If the scc_index was not updated, all the vertices above on + * vertex_stack are in the same SCC. Group them using scc_entry. + */ + __list_cut_position(&scc, &vertex_stack, &vertex->scc_entry); + + list_for_each_entry_reverse(v, &scc, scc_entry) { + /* Don't restart DFS from this vertex in unix_walk_scc(). */ + list_move_tail(&v->entry, &unix_visited_vertices); + + /* Mark vertex as off-stack. */ + v->index = unix_vertex_grouped_index; + + if (scc_dead) + scc_dead = unix_vertex_dead(v); } -#endif + + if (scc_dead) + unix_collect_skb(&scc, hitlist); + else if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + + list_del(&scc); } - /* not_cycle_list contains those sockets which do not make up a - * cycle. Restore these to the inflight list. + /* Need backtracking ? */ + if (!list_empty(&edge_stack)) + goto prev_vertex; +} + +static void unix_walk_scc(struct sk_buff_head *hitlist) +{ + unsigned long last_index = UNIX_VERTEX_INDEX_START; + + unix_graph_maybe_cyclic = false; + + /* Visit every vertex exactly once. + * __unix_walk_scc() moves visited vertices to unix_visited_vertices. */ - while (!list_empty(¬_cycle_list)) { - u = list_entry(not_cycle_list.next, struct unix_sock, link); - __clear_bit(UNIX_GC_CANDIDATE, &u->gc_flags); - list_move_tail(&u->link, &gc_inflight_list); + while (!list_empty(&unix_unvisited_vertices)) { + struct unix_vertex *vertex; + + vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); + __unix_walk_scc(vertex, &last_index, hitlist); } - spin_unlock(&unix_gc_lock); + list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); + swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); - /* We need io_uring to clean its registered files, ignore all io_uring - * originated skbs. It's fine as io_uring doesn't keep references to - * other io_uring instances and so killing all other files in the cycle - * will put all io_uring references forcing it to go through normal - * release.path eventually putting registered files. - */ - skb_queue_walk_safe(&hitlist, skb, next_skb) { - if (skb->destructor == io_uring_destruct_scm) { - __skb_unlink(skb, &hitlist); - skb_queue_tail(&skb->sk->sk_receive_queue, skb); + unix_graph_grouped = true; +} + +static void unix_walk_scc_fast(struct sk_buff_head *hitlist) +{ + unix_graph_maybe_cyclic = false; + + while (!list_empty(&unix_unvisited_vertices)) { + struct unix_vertex *vertex; + struct list_head scc; + bool scc_dead = true; + + vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); + list_add(&scc, &vertex->scc_entry); + + list_for_each_entry_reverse(vertex, &scc, scc_entry) { + list_move_tail(&vertex->entry, &unix_visited_vertices); + + if (scc_dead) + scc_dead = unix_vertex_dead(vertex); } + + if (scc_dead) + unix_collect_skb(&scc, hitlist); + else if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + + list_del(&scc); } - /* Here we are. Hitlist is filled. Die. */ - __skb_queue_purge(&hitlist); + list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); +} + +static bool gc_in_progress; + +static void __unix_gc(struct work_struct *work) +{ + struct sk_buff_head hitlist; + struct sk_buff *skb; spin_lock(&unix_gc_lock); - /* There could be io_uring registered files, just push them back to - * the inflight list - */ - list_for_each_entry_safe(u, next, &gc_candidates, link) - list_move_tail(&u->link, &gc_inflight_list); + if (!unix_graph_maybe_cyclic) { + spin_unlock(&unix_gc_lock); + goto skip_gc; + } + + __skb_queue_head_init(&hitlist); + + if (unix_graph_grouped) + unix_walk_scc_fast(&hitlist); + else + unix_walk_scc(&hitlist); - /* All candidates should have been detached by now. */ - BUG_ON(!list_empty(&gc_candidates)); + spin_unlock(&unix_gc_lock); + + skb_queue_walk(&hitlist, skb) { + if (UNIXCB(skb).fp) + UNIXCB(skb).fp->dead = true; + } - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ + __skb_queue_purge(&hitlist); +skip_gc: WRITE_ONCE(gc_in_progress, false); +} - wake_up(&unix_gc_wait); +static DECLARE_WORK(unix_gc_work, __unix_gc); - out: - spin_unlock(&unix_gc_lock); +void unix_gc(void) +{ + WRITE_ONCE(gc_in_progress, true); + queue_work(system_unbound_wq, &unix_gc_work); +} + +#define UNIX_INFLIGHT_TRIGGER_GC 16000 +#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) + +void wait_for_unix_gc(struct scm_fp_list *fpl) +{ + /* If number of inflight sockets is insane, + * force a garbage collect right now. + * + * Paired with the WRITE_ONCE() in unix_inflight(), + * unix_notinflight(), and __unix_gc(). + */ + if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && + !READ_ONCE(gc_in_progress)) + unix_gc(); + + /* Penalise users who want to send AF_UNIX sockets + * but whose sockets have not been received yet. + */ + if (!fpl || !fpl->count_unix || + READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) + return; + + if (READ_ONCE(gc_in_progress)) + flush_work(&unix_gc_work); } diff --git a/net/unix/scm.c b/net/unix/scm.c deleted file mode 100644 index e92f2fad6410..000000000000 --- a/net/unix/scm.c +++ /dev/null @@ -1,161 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/socket.h> -#include <linux/net.h> -#include <linux/fs.h> -#include <net/af_unix.h> -#include <net/scm.h> -#include <linux/init.h> -#include <linux/io_uring.h> - -#include "scm.h" - -unsigned int unix_tot_inflight; -EXPORT_SYMBOL(unix_tot_inflight); - -LIST_HEAD(gc_inflight_list); -EXPORT_SYMBOL(gc_inflight_list); - -DEFINE_SPINLOCK(unix_gc_lock); -EXPORT_SYMBOL(unix_gc_lock); - -struct sock *unix_get_socket(struct file *filp) -{ - struct sock *u_sock = NULL; - struct inode *inode = file_inode(filp); - - /* Socket ? */ - if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { - struct socket *sock = SOCKET_I(inode); - const struct proto_ops *ops = READ_ONCE(sock->ops); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && ops && ops->family == PF_UNIX) - u_sock = s; - } - - return u_sock; -} -EXPORT_SYMBOL(unix_get_socket); - -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ -void unix_inflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - if (!u->inflight) { - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - BUG_ON(list_empty(&u->link)); - } - u->inflight++; - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); - spin_unlock(&unix_gc_lock); -} - -void unix_notinflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - BUG_ON(!u->inflight); - BUG_ON(list_empty(&u->link)); - - u->inflight--; - if (!u->inflight) - list_del_init(&u->link); - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); - spin_unlock(&unix_gc_lock); -} - -/* - * The "user->unix_inflight" variable is protected by the garbage - * collection lock, and we just read it locklessly here. If you go - * over the limit, there might be a tiny race in actually noticing - * it across threads. Tough. - */ -static inline bool too_many_unix_fds(struct task_struct *p) -{ - struct user_struct *user = current_user(); - - if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. - */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return 0; -} -EXPORT_SYMBOL(unix_attach_fds); - -void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - scm->fp = UNIXCB(skb).fp; - UNIXCB(skb).fp = NULL; - - for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); -} -EXPORT_SYMBOL(unix_detach_fds); - -void unix_destruct_scm(struct sk_buff *skb) -{ - struct scm_cookie scm; - - memset(&scm, 0, sizeof(scm)); - scm.pid = UNIXCB(skb).pid; - if (UNIXCB(skb).fp) - unix_detach_fds(&scm, skb); - - /* Alas, it calls VFS */ - /* So fscking what? fput() had been SMP-safe since the last Summer */ - scm_destroy(&scm); - sock_wfree(skb); -} -EXPORT_SYMBOL(unix_destruct_scm); - -void io_uring_destruct_scm(struct sk_buff *skb) -{ - unix_destruct_scm(skb); -} -EXPORT_SYMBOL(io_uring_destruct_scm); diff --git a/net/unix/scm.h b/net/unix/scm.h deleted file mode 100644 index 5a255a477f16..000000000000 --- a/net/unix/scm.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef NET_UNIX_SCM_H -#define NET_UNIX_SCM_H - -extern struct list_head gc_inflight_list; -extern spinlock_t unix_gc_lock; - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb); -void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb); - -#endif diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 04dc0c8a8370..7188d3592dde 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -371,7 +371,6 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, xdo->dev = dev; netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC); - xdo->real_dev = dev; xdo->type = XFRM_DEV_OFFLOAD_PACKET; switch (dir) { case XFRM_POLICY_IN: @@ -393,7 +392,6 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack); if (err) { xdo->dev = NULL; - xdo->real_dev = NULL; xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xdo->dir = 0; netdev_put(dev, &xdo->dev_tracker); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 68b3f9e7edff..2edb0f868c57 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1603,6 +1603,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct xfrm_policy *delpol; struct hlist_head *chain; + /* Sanitize mark before store */ + policy->mark.v &= policy->mark.m; + spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (chain) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 8a6e8656d014..d2bd5bddfb05 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -754,9 +754,6 @@ int __xfrm_state_delete(struct xfrm_state *x) net->xfrm.state_num--; spin_unlock(&net->xfrm.xfrm_state_lock); - if (x->encap_sk) - sock_put(rcu_dereference_raw(x->encap_sk)); - xfrm_dev_state_delete(x); /* All xfrm_state objects are created by xfrm_state_alloc. @@ -1329,7 +1326,6 @@ found: xso->type = XFRM_DEV_OFFLOAD_PACKET; xso->dir = xdo->dir; xso->dev = xdo->dev; - xso->real_dev = xdo->real_dev; xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ; netdev_hold(xso->dev, &xso->dev_tracker, GFP_ATOMIC); error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL); @@ -1337,7 +1333,6 @@ found: xso->dir = 0; netdev_put(xso->dev, &xso->dev_tracker); xso->dev = NULL; - xso->real_dev = NULL; xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; x->km.state = XFRM_STATE_DEAD; to_put = x; @@ -1478,6 +1473,9 @@ static void __xfrm_state_insert(struct xfrm_state *x) list_add(&x->km.all, &net->xfrm.state_all); + /* Sanitize mark before store */ + x->mark.v &= x->mark.m; + h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, |