diff options
Diffstat (limited to 'net')
168 files changed, 4410 insertions, 3417 deletions
diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index 466353b3dde4..54e7fb1a4ee5 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -116,8 +116,6 @@ static int atm_uevent(const struct device *cdev, struct kobj_uevent_env *env) return -ENODEV; adev = to_atm_dev(cdev); - if (!adev) - return -ENODEV; if (add_uevent_var(env, "NAME=%s%d", adev->type, adev->number)) return -ENOMEM; diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index 2134f92bd7ac..5d698f19868c 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -109,7 +109,7 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon; u8 role = out ? HCI_ROLE_MASTER : HCI_ROLE_SLAVE; - hcon = hci_conn_add(hdev, AMP_LINK, dst, role); + hcon = hci_conn_add(hdev, AMP_LINK, dst, role, __next_handle(mgr)); if (!hcon) return NULL; @@ -117,7 +117,6 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, hcon->state = BT_CONNECT; hcon->attempt++; - hcon->handle = __next_handle(mgr); hcon->remote_id = remote_id; hcon->amp_mgr = amp_mgr_get(mgr); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7a6f20338db8..2cee330188ce 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -153,6 +153,9 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_conn_hash_del(hdev, conn); + if (HCI_CONN_HANDLE_UNSET(conn->handle)) + ida_free(&hdev->unset_handle_ida, conn->handle); + if (conn->cleanup) conn->cleanup(conn); @@ -169,13 +172,11 @@ static void hci_conn_cleanup(struct hci_conn *conn) hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); } - hci_conn_del_sysfs(conn); - debugfs_remove_recursive(conn->debugfs); - hci_dev_put(hdev); + hci_conn_del_sysfs(conn); - hci_conn_put(conn); + hci_dev_put(hdev); } static void hci_acl_create_connection(struct hci_conn *conn) @@ -759,6 +760,7 @@ static int terminate_big_sync(struct hci_dev *hdev, void *data) bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", d->big, d->bis); + hci_disable_per_advertising_sync(hdev, d->bis); hci_remove_ext_adv_instance_sync(hdev, d->bis, NULL); /* Only terminate BIG if it has been created */ @@ -814,6 +816,17 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data) return 0; } +static void find_bis(struct hci_conn *conn, void *data) +{ + struct iso_list_data *d = data; + + /* Ignore if BIG doesn't match */ + if (d->big != conn->iso_qos.bcast.big) + return; + + d->count++; +} + static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) { struct iso_list_data *d; @@ -825,10 +838,27 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c if (!d) return -ENOMEM; + memset(d, 0, sizeof(*d)); d->big = big; d->sync_handle = conn->sync_handle; - d->pa_sync_term = test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags); - d->big_sync_term = test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags); + + if (test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { + hci_conn_hash_list_flag(hdev, find_bis, ISO_LINK, + HCI_CONN_PA_SYNC, d); + + if (!d->count) + d->pa_sync_term = true; + + d->count = 0; + } + + if (test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags)) { + hci_conn_hash_list_flag(hdev, find_bis, ISO_LINK, + HCI_CONN_BIG_SYNC, d); + + if (!d->count) + d->big_sync_term = true; + } ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); @@ -864,12 +894,6 @@ static void bis_cleanup(struct hci_conn *conn) hci_le_terminate_big(hdev, conn); } else { - bis = hci_conn_hash_lookup_big_any_dst(hdev, - conn->iso_qos.bcast.big); - - if (bis) - return; - hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, conn); } @@ -928,31 +952,18 @@ static void cis_cleanup(struct hci_conn *conn) hci_le_remove_cig(hdev, conn->iso_qos.ucast.cig); } -static u16 hci_conn_hash_alloc_unset(struct hci_dev *hdev) +static int hci_conn_hash_alloc_unset(struct hci_dev *hdev) { - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c; - u16 handle = HCI_CONN_HANDLE_MAX + 1; - - rcu_read_lock(); - - list_for_each_entry_rcu(c, &h->list, list) { - /* Find the first unused handle */ - if (handle == 0xffff || c->handle != handle) - break; - handle++; - } - rcu_read_unlock(); - - return handle; + return ida_alloc_range(&hdev->unset_handle_ida, HCI_CONN_HANDLE_MAX + 1, + U16_MAX, GFP_ATOMIC); } struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, - u8 role) + u8 role, u16 handle) { struct hci_conn *conn; - BT_DBG("%s dst %pMR", hdev->name, dst); + bt_dev_dbg(hdev, "dst %pMR handle 0x%4.4x", dst, handle); conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) @@ -960,7 +971,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, bacpy(&conn->dst, dst); bacpy(&conn->src, &hdev->bdaddr); - conn->handle = hci_conn_hash_alloc_unset(hdev); + conn->handle = handle; conn->hdev = hdev; conn->type = type; conn->role = role; @@ -973,6 +984,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, conn->rssi = HCI_RSSI_INVALID; conn->tx_power = HCI_TX_POWER_INVALID; conn->max_tx_power = HCI_TX_POWER_INVALID; + conn->sync_handle = HCI_SYNC_HANDLE_INVALID; set_bit(HCI_CONN_POWER_SAVE, &conn->flags); conn->disc_timeout = HCI_DISCONN_TIMEOUT; @@ -1044,6 +1056,20 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, return conn; } +struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, + bdaddr_t *dst, u8 role) +{ + int handle; + + bt_dev_dbg(hdev, "dst %pMR", dst); + + handle = hci_conn_hash_alloc_unset(hdev); + if (unlikely(handle < 0)) + return NULL; + + return hci_conn_add(hdev, type, dst, role, handle); +} + static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason) { if (!reason) @@ -1247,6 +1273,12 @@ void hci_conn_failed(struct hci_conn *conn, u8 status) break; } + /* In case of BIG/PA sync failed, clear conn flags so that + * the conns will be correctly cleaned up by ISO layer + */ + test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags); + test_and_clear_bit(HCI_CONN_PA_SYNC_FAILED, &conn->flags); + conn->state = BT_CLOSED; hci_connect_cfm(conn, status); hci_conn_del(conn); @@ -1274,6 +1306,9 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) if (conn->abort_reason) return conn->abort_reason; + if (HCI_CONN_HANDLE_UNSET(conn->handle)) + ida_free(&hdev->unset_handle_ida, conn->handle); + conn->handle = handle; return 0; @@ -1381,7 +1416,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, if (conn) { bacpy(&conn->dst, dst); } else { - conn = hci_conn_add(hdev, LE_LINK, dst, role); + conn = hci_conn_add_unset(hdev, LE_LINK, dst, role); if (!conn) return ERR_PTR(-ENOMEM); hci_conn_hold(conn); @@ -1486,6 +1521,18 @@ static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos) /* Allocate BIS if not set */ if (qos->bcast.bis == BT_ISO_QOS_BIS_UNSET) { + if (qos->bcast.big != BT_ISO_QOS_BIG_UNSET) { + conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big); + + if (conn) { + /* If the BIG handle is already matched to an advertising + * handle, do not allocate a new one. + */ + qos->bcast.bis = conn->iso_qos.bcast.bis; + return 0; + } + } + /* Find an unused adv set to advertise BIS, skip instance 0x00 * since it is reserved as general purpose set. */ @@ -1546,7 +1593,7 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, memcmp(conn->le_per_adv_data, base, base_len))) return ERR_PTR(-EADDRINUSE); - conn = hci_conn_add(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); + conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); if (!conn) return ERR_PTR(-ENOMEM); @@ -1590,7 +1637,7 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, BT_DBG("requesting refresh of dst_addr"); - conn = hci_conn_add(hdev, LE_LINK, dst, HCI_ROLE_MASTER); + conn = hci_conn_add_unset(hdev, LE_LINK, dst, HCI_ROLE_MASTER); if (!conn) return ERR_PTR(-ENOMEM); @@ -1627,9 +1674,18 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-EOPNOTSUPP); } + /* Reject outgoing connection to device with same BD ADDR against + * CVE-2020-26555 + */ + if (!bacmp(&hdev->bdaddr, dst)) { + bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", + dst); + return ERR_PTR(-ECONNREFUSED); + } + acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { - acl = hci_conn_add(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); + acl = hci_conn_add_unset(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); if (!acl) return ERR_PTR(-ENOMEM); } @@ -1689,7 +1745,7 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, sco = hci_conn_hash_lookup_ba(hdev, type, dst); if (!sco) { - sco = hci_conn_add(hdev, type, dst, HCI_ROLE_MASTER); + sco = hci_conn_add_unset(hdev, type, dst, HCI_ROLE_MASTER); if (!sco) { hci_conn_drop(acl); return ERR_PTR(-ENOMEM); @@ -1881,7 +1937,7 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, cis = hci_conn_hash_lookup_cis(hdev, dst, dst_type, qos->ucast.cig, qos->ucast.cis); if (!cis) { - cis = hci_conn_add(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); + cis = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); if (!cis) return ERR_PTR(-ENOMEM); cis->cleanup = cis_cleanup; @@ -2130,7 +2186,7 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, } pdu; int err; - if (num_bis > sizeof(pdu.bis)) + if (num_bis < 0x01 || num_bis > sizeof(pdu.bis)) return -EINVAL; err = qos_set_big(hdev, qos); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 195aea2198a9..65601aa52e0d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2535,6 +2535,8 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); + ida_init(&hdev->unset_handle_ida); + INIT_LIST_HEAD(&hdev->mesh_pending); INIT_LIST_HEAD(&hdev->mgmt_pending); INIT_LIST_HEAD(&hdev->reject_list); @@ -2789,6 +2791,7 @@ void hci_release_dev(struct hci_dev *hdev) hci_codec_list_clear(&hdev->local_codecs); hci_dev_unlock(hdev); + ida_destroy(&hdev->unset_handle_ida); ida_simple_remove(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); kfree_skb(hdev->recv_event); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 31d02b54eea1..0849e0dafa95 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -26,6 +26,8 @@ /* Bluetooth HCI event handling. */ #include <asm/unaligned.h> +#include <linux/crypto.h> +#include <crypto/algapi.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -2333,8 +2335,8 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) } } else { if (!conn) { - conn = hci_conn_add(hdev, ACL_LINK, &cp->bdaddr, - HCI_ROLE_MASTER); + conn = hci_conn_add_unset(hdev, ACL_LINK, &cp->bdaddr, + HCI_ROLE_MASTER); if (!conn) bt_dev_err(hdev, "no memory for new connection"); } @@ -3149,8 +3151,8 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &ev->bdaddr, BDADDR_BREDR)) { - conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, - HCI_ROLE_SLAVE); + conn = hci_conn_add_unset(hdev, ev->link_type, + &ev->bdaddr, HCI_ROLE_SLAVE); if (!conn) { bt_dev_err(hdev, "no memory for new conn"); goto unlock; @@ -3268,6 +3270,16 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type); + /* Reject incoming connection from device with same BD ADDR against + * CVE-2020-26555 + */ + if (hdev && !bacmp(&hdev->bdaddr, &ev->bdaddr)) { + bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", + &ev->bdaddr); + hci_reject_conn(hdev, &ev->bdaddr); + return; + } + mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type, &flags); @@ -3305,8 +3317,8 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { - conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, - HCI_ROLE_SLAVE); + conn = hci_conn_add_unset(hdev, ev->link_type, &ev->bdaddr, + HCI_ROLE_SLAVE); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); goto unlock; @@ -4742,6 +4754,15 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, void *data, if (!conn) goto unlock; + /* Ignore NULL link key against CVE-2020-26555 */ + if (!crypto_memneq(ev->link_key, ZERO_KEY, HCI_LINK_KEY_SIZE)) { + bt_dev_dbg(hdev, "Ignore NULL link key (ZERO KEY) for %pMR", + &ev->bdaddr); + hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); + hci_conn_drop(conn); + goto unlock; + } + hci_conn_hold(conn); conn->disc_timeout = HCI_DISCONN_TIMEOUT; hci_conn_drop(conn); @@ -5274,8 +5295,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) * available, then do not declare that OOB data is * present. */ - if (!memcmp(data->rand256, ZERO_KEY, 16) || - !memcmp(data->hash256, ZERO_KEY, 16)) + if (!crypto_memneq(data->rand256, ZERO_KEY, 16) || + !crypto_memneq(data->hash256, ZERO_KEY, 16)) return 0x00; return 0x02; @@ -5285,8 +5306,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) * not supported by the hardware, then check that if * P-192 data values are present. */ - if (!memcmp(data->rand192, ZERO_KEY, 16) || - !memcmp(data->hash192, ZERO_KEY, 16)) + if (!crypto_memneq(data->rand192, ZERO_KEY, 16) || + !crypto_memneq(data->hash192, ZERO_KEY, 16)) return 0x00; return 0x01; @@ -5303,7 +5324,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn) + if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; hci_conn_hold(conn); @@ -5550,7 +5571,7 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn) + if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; /* Reset the authentication requirement to unknown */ @@ -5869,7 +5890,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, if (status) goto unlock; - conn = hci_conn_add(hdev, LE_LINK, bdaddr, role); + conn = hci_conn_add_unset(hdev, LE_LINK, bdaddr, role); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); goto unlock; @@ -5931,17 +5952,11 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = ev_bdaddr_type(hdev, conn->dst_type, NULL); - if (handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", handle, - HCI_CONN_HANDLE_MAX); - status = HCI_ERROR_INVALID_PARAMETERS; - } - /* All connection failure handling is taken care of by the * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ - if (status) + if (status || hci_conn_set_handle(conn, handle)) goto unlock; /* Drop the connection if it has been aborted */ @@ -5965,7 +5980,6 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, mgmt_device_connected(hdev, conn, NULL, 0); conn->sec_level = BT_SECURITY_LOW; - conn->handle = handle; conn->state = BT_CONFIG; /* Store current advertising instance as connection advertising instance @@ -6582,7 +6596,7 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data, struct hci_ev_le_pa_sync_established *ev = data; int mask = hdev->link_mode; __u8 flags = 0; - struct hci_conn *bis; + struct hci_conn *pa_sync; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -6599,20 +6613,19 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data, if (!(flags & HCI_PROTO_DEFER)) goto unlock; - /* Add connection to indicate the PA sync event */ - bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY, - HCI_ROLE_SLAVE); + if (ev->status) { + /* Add connection to indicate the failed PA sync event */ + pa_sync = hci_conn_add_unset(hdev, ISO_LINK, BDADDR_ANY, + HCI_ROLE_SLAVE); - if (!bis) - goto unlock; + if (!pa_sync) + goto unlock; - if (ev->status) - set_bit(HCI_CONN_PA_SYNC_FAILED, &bis->flags); - else - set_bit(HCI_CONN_PA_SYNC, &bis->flags); + set_bit(HCI_CONN_PA_SYNC_FAILED, &pa_sync->flags); - /* Notify connection to iso layer */ - hci_connect_cfm(bis, ev->status); + /* Notify iso layer */ + hci_connect_cfm(pa_sync, ev->status); + } unlock: hci_dev_unlock(hdev); @@ -6999,12 +7012,12 @@ static void hci_le_cis_req_evt(struct hci_dev *hdev, void *data, cis = hci_conn_hash_lookup_handle(hdev, cis_handle); if (!cis) { - cis = hci_conn_add(hdev, ISO_LINK, &acl->dst, HCI_ROLE_SLAVE); + cis = hci_conn_add(hdev, ISO_LINK, &acl->dst, HCI_ROLE_SLAVE, + cis_handle); if (!cis) { hci_le_reject_cis(hdev, ev->cis_handle); goto unlock; } - cis->handle = cis_handle; } cis->iso_qos.ucast.cig = ev->cig_id; @@ -7021,6 +7034,14 @@ unlock: hci_dev_unlock(hdev); } +static int hci_iso_term_big_sync(struct hci_dev *hdev, void *data) +{ + u8 handle = PTR_UINT(data); + + return hci_le_terminate_big_sync(hdev, handle, + HCI_ERROR_LOCAL_HOST_TERM); +} + static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -7065,16 +7086,17 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, rcu_read_lock(); } + rcu_read_unlock(); + if (!ev->status && !i) /* If no BISes have been connected for the BIG, * terminate. This is in case all bound connections * have been closed before the BIG creation * has completed. */ - hci_le_terminate_big_sync(hdev, ev->handle, - HCI_ERROR_LOCAL_HOST_TERM); + hci_cmd_sync_queue(hdev, hci_iso_term_big_sync, + UINT_PTR(ev->handle), NULL); - rcu_read_unlock(); hci_dev_unlock(hdev); } @@ -7083,7 +7105,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, { struct hci_evt_le_big_sync_estabilished *ev = data; struct hci_conn *bis; - struct hci_conn *pa_sync; int i; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -7094,15 +7115,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - if (!ev->status) { - pa_sync = hci_conn_hash_lookup_pa_sync(hdev, ev->handle); - if (pa_sync) - /* Also mark the BIG sync established event on the - * associated PA sync hcon - */ - set_bit(HCI_CONN_BIG_SYNC, &pa_sync->flags); - } - for (i = 0; i < ev->num_bis; i++) { u16 handle = le16_to_cpu(ev->bis[i]); __le32 interval; @@ -7110,10 +7122,9 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis = hci_conn_hash_lookup_handle(hdev, handle); if (!bis) { bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, handle); if (!bis) continue; - bis->handle = handle; } if (ev->status != 0x42) @@ -7156,15 +7167,42 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, struct hci_evt_le_big_info_adv_report *ev = data; int mask = hdev->link_mode; __u8 flags = 0; + struct hci_conn *pa_sync; bt_dev_dbg(hdev, "sync_handle 0x%4.4x", le16_to_cpu(ev->sync_handle)); hci_dev_lock(hdev); mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, ISO_LINK, &flags); - if (!(mask & HCI_LM_ACCEPT)) + if (!(mask & HCI_LM_ACCEPT)) { hci_le_pa_term_sync(hdev, ev->sync_handle); + goto unlock; + } + if (!(flags & HCI_PROTO_DEFER)) + goto unlock; + + pa_sync = hci_conn_hash_lookup_pa_sync_handle + (hdev, + le16_to_cpu(ev->sync_handle)); + + if (pa_sync) + goto unlock; + + /* Add connection to indicate the PA sync event */ + pa_sync = hci_conn_add_unset(hdev, ISO_LINK, BDADDR_ANY, + HCI_ROLE_SLAVE); + + if (!pa_sync) + goto unlock; + + pa_sync->sync_handle = le16_to_cpu(ev->sync_handle); + set_bit(HCI_CONN_PA_SYNC, &pa_sync->flags); + + /* Notify iso layer */ + hci_connect_cfm(pa_sync, 0x00); + +unlock: hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 5e4f718073b7..3e7cd330d731 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -488,7 +488,8 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) ni->type = hdev->dev_type; ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); - memcpy(ni->name, hdev->name, 8); + memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name, + strnlen(hdev->name, sizeof(ni->name)), '\0'); opcode = cpu_to_le16(HCI_MON_NEW_INDEX); break; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index d06e07a0ea5a..d85a7091a116 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -152,7 +152,7 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, struct sk_buff *skb; int err = 0; - bt_dev_dbg(hdev, "Opcode 0x%4x", opcode); + bt_dev_dbg(hdev, "Opcode 0x%4.4x", opcode); hci_req_init(&req, hdev); @@ -248,7 +248,7 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk); if (IS_ERR(skb)) { if (!event) - bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, + bt_dev_err(hdev, "Opcode 0x%4.4x failed: %ld", opcode, PTR_ERR(skb)); return PTR_ERR(skb); } @@ -1312,7 +1312,7 @@ int hci_start_ext_adv_sync(struct hci_dev *hdev, u8 instance) return hci_enable_ext_advertising_sync(hdev, instance); } -static int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance) +int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance) { struct hci_cp_le_set_per_adv_enable cp; struct adv_info *adv = NULL; @@ -4264,12 +4264,12 @@ static int hci_le_set_host_feature_sync(struct hci_dev *hdev) { struct hci_cp_le_set_host_feature cp; - if (!iso_capable(hdev)) + if (!cis_capable(hdev)) return 0; memset(&cp, 0, sizeof(cp)); - /* Isochronous Channels (Host Support) */ + /* Connected Isochronous Channels (Host Support) */ cp.bit_number = 32; cp.bit_value = 1; @@ -5232,6 +5232,17 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn, if (conn->type == AMP_LINK) return hci_disconnect_phy_link_sync(hdev, conn->handle, reason); + if (test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) { + /* This is a BIS connection, hci_conn_del will + * do the necessary cleanup. + */ + hci_dev_lock(hdev); + hci_conn_failed(conn, reason); + hci_dev_unlock(hdev); + + return 0; + } + memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); cp.reason = reason; @@ -5369,6 +5380,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { int err = 0; u16 handle = conn->handle; + bool disconnect = false; struct hci_conn *c; switch (conn->state) { @@ -5383,40 +5395,16 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) err = hci_reject_conn_sync(hdev, conn, reason); break; case BT_OPEN: - hci_dev_lock(hdev); - - /* Cleanup bis or pa sync connections */ - if (test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags) || - test_and_clear_bit(HCI_CONN_PA_SYNC_FAILED, &conn->flags)) { - hci_conn_failed(conn, reason); - } else if (test_bit(HCI_CONN_PA_SYNC, &conn->flags) || - test_bit(HCI_CONN_BIG_SYNC, &conn->flags)) { - conn->state = BT_CLOSED; - hci_disconn_cfm(conn, reason); - hci_conn_del(conn); - } - - hci_dev_unlock(hdev); - return 0; case BT_BOUND: - hci_dev_lock(hdev); - hci_conn_failed(conn, reason); - hci_dev_unlock(hdev); - return 0; + break; default: - hci_dev_lock(hdev); - conn->state = BT_CLOSED; - hci_disconn_cfm(conn, reason); - hci_conn_del(conn); - hci_dev_unlock(hdev); - return 0; + disconnect = true; + break; } hci_dev_lock(hdev); - /* Check if the connection hasn't been cleanup while waiting - * commands to complete. - */ + /* Check if the connection has been cleaned up concurrently */ c = hci_conn_hash_lookup_handle(hdev, handle); if (!c || c != conn) { err = 0; @@ -5428,7 +5416,13 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) * or in case of LE it was still scanning so it can be cleanup * safely. */ - hci_conn_failed(conn, reason); + if (disconnect) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, reason); + hci_conn_del(conn); + } else { + hci_conn_failed(conn, reason); + } unlock: hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 15b33579007c..367e32fe30eb 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -35,7 +35,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p", conn); + bt_dev_dbg(hdev, "conn %p", conn); conn->dev.type = &bt_link; conn->dev.class = &bt_class; @@ -48,27 +48,30 @@ void hci_conn_add_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p", conn); + bt_dev_dbg(hdev, "conn %p", conn); if (device_is_registered(&conn->dev)) return; dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); - if (device_add(&conn->dev) < 0) { + if (device_add(&conn->dev) < 0) bt_dev_err(hdev, "failed to register connection device"); - return; - } - - hci_dev_hold(hdev); } void hci_conn_del_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - if (!device_is_registered(&conn->dev)) + bt_dev_dbg(hdev, "conn %p", conn); + + if (!device_is_registered(&conn->dev)) { + /* If device_add() has *not* succeeded, use *only* put_device() + * to drop the reference count. + */ + put_device(&conn->dev); return; + } while (1) { struct device *dev; @@ -80,9 +83,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn) put_device(dev); } - device_del(&conn->dev); - - hci_dev_put(hdev); + device_unregister(&conn->dev); } static void bt_host_release(struct device *dev) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 71248163ce9a..07b80e97aead 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -14,6 +14,7 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/iso.h> +#include "eir.h" static const struct proto_ops iso_sock_ops; @@ -47,6 +48,7 @@ static void iso_sock_kill(struct sock *sk); #define EIR_SERVICE_DATA_LENGTH 4 #define BASE_MAX_LENGTH (HCI_MAX_PER_AD_LENGTH - EIR_SERVICE_DATA_LENGTH) +#define EIR_BAA_SERVICE_UUID 0x1851 /* iso_pinfo flags values */ enum { @@ -77,6 +79,7 @@ static struct bt_iso_qos default_qos; static bool check_ucast_qos(struct bt_iso_qos *qos); static bool check_bcast_qos(struct bt_iso_qos *qos); static bool iso_match_sid(struct sock *sk, void *data); +static bool iso_match_sync_handle(struct sock *sk, void *data); static void iso_sock_disconn(struct sock *sk); /* ---- ISO timers ---- */ @@ -789,8 +792,7 @@ static int iso_sock_bind_bc(struct socket *sock, struct sockaddr *addr, BT_DBG("sk %p bc_sid %u bc_num_bis %u", sk, sa->iso_bc->bc_sid, sa->iso_bc->bc_num_bis); - if (addr_len > sizeof(*sa) + sizeof(*sa->iso_bc) || - sa->iso_bc->bc_num_bis < 0x01 || sa->iso_bc->bc_num_bis > 0x1f) + if (addr_len > sizeof(*sa) + sizeof(*sa->iso_bc)) return -EINVAL; bacpy(&iso_pi(sk)->dst, &sa->iso_bc->bc_bdaddr); @@ -1202,7 +1204,6 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, test_bit(HCI_CONN_PA_SYNC, &pi->conn->hcon->flags)) { iso_conn_big_sync(sk); sk->sk_state = BT_LISTEN; - set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); } else { iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; @@ -1461,6 +1462,8 @@ static int iso_sock_getsockopt(struct socket *sock, int level, int optname, len = min_t(unsigned int, len, base_len); if (copy_to_user(optval, base, len)) err = -EFAULT; + if (put_user(len, optlen)) + err = -EFAULT; break; @@ -1579,6 +1582,7 @@ static void iso_conn_ready(struct iso_conn *conn) struct sock *sk = conn->sk; struct hci_ev_le_big_sync_estabilished *ev = NULL; struct hci_ev_le_pa_sync_established *ev2 = NULL; + struct hci_evt_le_big_info_adv_report *ev3 = NULL; struct hci_conn *hcon; BT_DBG("conn %p", conn); @@ -1603,14 +1607,20 @@ static void iso_conn_ready(struct iso_conn *conn) parent = iso_get_sock_listen(&hcon->src, &hcon->dst, iso_match_big, ev); - } else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags) || - test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { + } else if (test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { ev2 = hci_recv_event_data(hcon->hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev2) parent = iso_get_sock_listen(&hcon->src, &hcon->dst, iso_match_sid, ev2); + } else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags)) { + ev3 = hci_recv_event_data(hcon->hdev, + HCI_EVT_LE_BIG_INFO_ADV_REPORT); + if (ev3) + parent = iso_get_sock_listen(&hcon->src, + &hcon->dst, + iso_match_sync_handle, ev3); } if (!parent) @@ -1650,11 +1660,13 @@ static void iso_conn_ready(struct iso_conn *conn) hcon->sync_handle = iso_pi(parent)->sync_handle; } - if (ev2 && !ev2->status) { - iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle; + if (ev3) { iso_pi(sk)->qos = iso_pi(parent)->qos; + iso_pi(sk)->qos.bcast.encryption = ev3->encryption; + hcon->iso_qos = iso_pi(sk)->qos; iso_pi(sk)->bc_num_bis = iso_pi(parent)->bc_num_bis; memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis, ISO_MAX_NUM_BIS); + set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); } bacpy(&iso_pi(sk)->dst, &hcon->dst); @@ -1774,12 +1786,16 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) { + size_t base_len = ev3->length; + u8 *base; + sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, iso_match_sync_handle_pa_report, ev3); - - if (sk) { - memcpy(iso_pi(sk)->base, ev3->data, ev3->length); - iso_pi(sk)->base_len = ev3->length; + base = eir_get_service_data(ev3->data, ev3->length, + EIR_BAA_SERVICE_UUID, &base_len); + if (base && sk && base_len <= sizeof(iso_pi(sk)->base)) { + memcpy(iso_pi(sk)->base, base, base_len); + iso_pi(sk)->base_len = base_len; } } else { sk = iso_get_sock_listen(&hdev->bdaddr, BDADDR_ANY, NULL, NULL); diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index abbafa6194ca..630e3023273b 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -150,10 +150,7 @@ static bool read_supported_features(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { - if (!skb) - skb = ERR_PTR(-EIO); - + if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read MSFT supported features (%ld)", PTR_ERR(skb)); return false; @@ -353,7 +350,7 @@ static void msft_remove_addr_filters_sync(struct hci_dev *hdev, u8 handle) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { + if (IS_ERR(skb)) { kfree(address_filter); continue; } @@ -442,11 +439,8 @@ static int msft_remove_monitor_sync(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { - if (!skb) - return -EIO; + if (IS_ERR(skb)) return PTR_ERR(skb); - } return msft_le_cancel_monitor_advertisement_cb(hdev, hdev->msft_opcode, monitor, skb); @@ -559,7 +553,7 @@ static int msft_add_monitor_sync(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, hdev->msft_opcode, total_size, cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { + if (IS_ERR(skb)) { err = PTR_ERR(skb); goto out_free; } @@ -740,10 +734,10 @@ static int msft_cancel_address_filter_sync(struct hci_dev *hdev, void *data) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { + if (IS_ERR(skb)) { bt_dev_err(hdev, "MSFT: Failed to cancel address (%pMR) filter", &address_filter->bdaddr); - err = -EIO; + err = PTR_ERR(skb); goto done; } kfree_skb(skb); @@ -893,7 +887,7 @@ static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, size, cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { + if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to enable address %pMR filter", &address_filter->bdaddr); skb = NULL; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 033034d68f1f..6adcb45bca75 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -486,11 +486,11 @@ static unsigned int br_nf_pre_routing(void *priv, struct brnf_net *brnet; if (unlikely(!pskb_may_pull(skb, len))) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_PKT_TOO_SMALL, 0); p = br_port_get_rcu(state->in); if (p == NULL) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); br = p->br; brnet = net_generic(state->net, brnf_net_id); @@ -501,7 +501,7 @@ static unsigned int br_nf_pre_routing(void *priv, return NF_ACCEPT; if (!ipv6_mod_enabled()) { pr_warn_once("Module ipv6 is disabled, so call_ip6tables is not supported."); - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IPV6DISABLED, 0); } nf_bridge_pull_encap_header_rcsum(skb); @@ -518,12 +518,12 @@ static unsigned int br_nf_pre_routing(void *priv, nf_bridge_pull_encap_header_rcsum(skb); if (br_validate_ipv4(state->net, skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); if (!nf_bridge_alloc(skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); if (!setup_pre_routing(skb, state->net)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); nf_bridge = nf_bridge_info_get(skb); nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; @@ -570,18 +570,12 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff } -/* This is the 'purely bridged' case. For IP, we pass the packet to - * netfilter with indev and outdev set to the bridge device, - * but we are still able to filter on the 'real' indev/outdev - * because of the physdev module. For ARP, indev and outdev are the - * bridge ports. */ -static unsigned int br_nf_forward_ip(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) +static unsigned int br_nf_forward_ip(struct sk_buff *skb, + const struct nf_hook_state *state, + u8 pf) { struct nf_bridge_info *nf_bridge; struct net_device *parent; - u_int8_t pf; nf_bridge = nf_bridge_info_get(skb); if (!nf_bridge) @@ -590,24 +584,15 @@ static unsigned int br_nf_forward_ip(void *priv, /* Need exclusive nf_bridge_info since we might have multiple * different physoutdevs. */ if (!nf_bridge_unshare(skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); nf_bridge = nf_bridge_info_get(skb); if (!nf_bridge) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); parent = bridge_parent(state->out); if (!parent) - return NF_DROP; - - if (IS_IP(skb) || is_vlan_ip(skb, state->net) || - is_pppoe_ip(skb, state->net)) - pf = NFPROTO_IPV4; - else if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) || - is_pppoe_ipv6(skb, state->net)) - pf = NFPROTO_IPV6; - else - return NF_ACCEPT; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); nf_bridge_pull_encap_header(skb); @@ -618,21 +603,20 @@ static unsigned int br_nf_forward_ip(void *priv, if (pf == NFPROTO_IPV4) { if (br_validate_ipv4(state->net, skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; - } - - if (pf == NFPROTO_IPV6) { + skb->protocol = htons(ETH_P_IP); + } else if (pf == NFPROTO_IPV6) { if (br_validate_ipv6(state->net, skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; + skb->protocol = htons(ETH_P_IPV6); + } else { + WARN_ON_ONCE(1); + return NF_DROP; } nf_bridge->physoutdev = skb->dev; - if (pf == NFPROTO_IPV4) - skb->protocol = htons(ETH_P_IP); - else - skb->protocol = htons(ETH_P_IPV6); NF_HOOK(pf, NF_INET_FORWARD, state->net, NULL, skb, brnf_get_logical_dev(skb, state->in, state->net), @@ -641,8 +625,7 @@ static unsigned int br_nf_forward_ip(void *priv, return NF_STOLEN; } -static unsigned int br_nf_forward_arp(void *priv, - struct sk_buff *skb, +static unsigned int br_nf_forward_arp(struct sk_buff *skb, const struct nf_hook_state *state) { struct net_bridge_port *p; @@ -659,14 +642,11 @@ static unsigned int br_nf_forward_arp(void *priv, if (!brnet->call_arptables && !br_opt_get(br, BROPT_NF_CALL_ARPTABLES)) return NF_ACCEPT; - if (!IS_ARP(skb)) { - if (!is_vlan_arp(skb, state->net)) - return NF_ACCEPT; + if (is_vlan_arp(skb, state->net)) nf_bridge_pull_encap_header(skb); - } if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_PKT_TOO_SMALL, 0); if (arp_hdr(skb)->ar_pln != 4) { if (is_vlan_arp(skb, state->net)) @@ -680,6 +660,28 @@ static unsigned int br_nf_forward_arp(void *priv, return NF_STOLEN; } +/* This is the 'purely bridged' case. For IP, we pass the packet to + * netfilter with indev and outdev set to the bridge device, + * but we are still able to filter on the 'real' indev/outdev + * because of the physdev module. For ARP, indev and outdev are the + * bridge ports. + */ +static unsigned int br_nf_forward(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + if (IS_IP(skb) || is_vlan_ip(skb, state->net) || + is_pppoe_ip(skb, state->net)) + return br_nf_forward_ip(skb, state, NFPROTO_IPV4); + if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) || + is_pppoe_ipv6(skb, state->net)) + return br_nf_forward_ip(skb, state, NFPROTO_IPV6); + if (IS_ARP(skb) || is_vlan_arp(skb, state->net)) + return br_nf_forward_arp(skb, state); + + return NF_ACCEPT; +} + static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { struct brnf_frag_data *data; @@ -831,7 +833,7 @@ static unsigned int br_nf_post_routing(void *priv, return NF_ACCEPT; if (!realoutdev) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); if (IS_IP(skb) || is_vlan_ip(skb, state->net) || is_pppoe_ip(skb, state->net)) @@ -937,13 +939,7 @@ static const struct nf_hook_ops br_nf_ops[] = { .priority = NF_BR_PRI_BRNF, }, { - .hook = br_nf_forward_ip, - .pf = NFPROTO_BRIDGE, - .hooknum = NF_BR_FORWARD, - .priority = NF_BR_PRI_BRNF - 1, - }, - { - .hook = br_nf_forward_arp, + .hook = br_nf_forward, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF, diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 550039dfc31a..2e24a743f917 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -161,13 +161,13 @@ unsigned int br_nf_pre_routing_ipv6(void *priv, struct nf_bridge_info *nf_bridge; if (br_validate_ipv6(state->net, skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); nf_bridge = nf_bridge_alloc(skb); if (!nf_bridge) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); if (!setup_pre_routing(skb, state->net)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); nf_bridge = nf_bridge_info_get(skb); nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 10a41cd9c523..3c8b78d9c4d1 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -459,8 +459,8 @@ int ceph_tcp_connect(struct ceph_connection *con) set_sock_callbacks(sock, con); con_sock_state_connecting(con); - ret = sock->ops->connect(sock, (struct sockaddr *)&ss, sizeof(ss), - O_NONBLOCK); + ret = kernel_connect(sock, (struct sockaddr *)&ss, sizeof(ss), + O_NONBLOCK); if (ret == -EINPROGRESS) { dout("connect %s EINPROGRESS sk_state = %u\n", ceph_pr_addr(&con->peer_addr), diff --git a/net/core/dev.c b/net/core/dev.c index 97e7b9833db9..0d548431f3fa 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -345,7 +345,6 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { list_del(&name_node->list); - netdev_name_node_del(name_node); kfree(name_node->name); netdev_name_node_free(name_node); } @@ -364,6 +363,8 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; + netdev_name_node_del(name_node); + synchronize_rcu(); __netdev_name_node_alt_destroy(name_node); return 0; @@ -380,6 +381,7 @@ static void netdev_name_node_alt_flush(struct net_device *dev) /* Device list insertion */ static void list_netdevice(struct net_device *dev) { + struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); @@ -390,6 +392,10 @@ static void list_netdevice(struct net_device *dev) hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock(&dev_base_lock); + + netdev_for_each_altname(dev, name_node) + netdev_name_node_add(net, name_node); + /* We reserved the ifindex, this can't fail */ WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL)); @@ -401,12 +407,16 @@ static void list_netdevice(struct net_device *dev) */ static void unlist_netdevice(struct net_device *dev, bool lock) { + struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); xa_erase(&net->dev_by_index, dev->ifindex); + netdev_for_each_altname(dev, name_node) + netdev_name_node_del(name_node); + /* Unlink dev from the device chain */ if (lock) write_lock(&dev_base_lock); @@ -1047,7 +1057,7 @@ EXPORT_SYMBOL(dev_valid_name); * __dev_alloc_name - allocate a name for a device * @net: network namespace to allocate the device name in * @name: name format string - * @buf: scratch buffer and result name string + * @res: result name string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses @@ -1058,83 +1068,77 @@ EXPORT_SYMBOL(dev_valid_name); * Returns the number of the unit assigned or a negative errno code. */ -static int __dev_alloc_name(struct net *net, const char *name, char *buf) +static int __dev_alloc_name(struct net *net, const char *name, char *res) { int i = 0; const char *p; const int max_netdevices = 8*PAGE_SIZE; unsigned long *inuse; struct net_device *d; + char buf[IFNAMSIZ]; - if (!dev_valid_name(name)) - return -EINVAL; - + /* Verify the string as this thing may have come from the user. + * There must be one "%d" and no other "%" characters. + */ p = strchr(name, '%'); - if (p) { - /* - * Verify the string as this thing may have come from - * the user. There must be either one "%d" and no other "%" - * characters. - */ - if (p[1] != 'd' || strchr(p + 2, '%')) - return -EINVAL; + if (!p || p[1] != 'd' || strchr(p + 2, '%')) + return -EINVAL; - /* Use one page as a bit array of possible slots */ - inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); - if (!inuse) - return -ENOMEM; + /* Use one page as a bit array of possible slots */ + inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); + if (!inuse) + return -ENOMEM; - for_each_netdev(net, d) { - struct netdev_name_node *name_node; - list_for_each_entry(name_node, &d->name_node->list, list) { - if (!sscanf(name_node->name, name, &i)) - continue; - if (i < 0 || i >= max_netdevices) - continue; + for_each_netdev(net, d) { + struct netdev_name_node *name_node; - /* avoid cases where sscanf is not exact inverse of printf */ - snprintf(buf, IFNAMSIZ, name, i); - if (!strncmp(buf, name_node->name, IFNAMSIZ)) - __set_bit(i, inuse); - } - if (!sscanf(d->name, name, &i)) + netdev_for_each_altname(d, name_node) { + if (!sscanf(name_node->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; - /* avoid cases where sscanf is not exact inverse of printf */ + /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); - if (!strncmp(buf, d->name, IFNAMSIZ)) + if (!strncmp(buf, name_node->name, IFNAMSIZ)) __set_bit(i, inuse); } + if (!sscanf(d->name, name, &i)) + continue; + if (i < 0 || i >= max_netdevices) + continue; - i = find_first_zero_bit(inuse, max_netdevices); - bitmap_free(inuse); + /* avoid cases where sscanf is not exact inverse of printf */ + snprintf(buf, IFNAMSIZ, name, i); + if (!strncmp(buf, d->name, IFNAMSIZ)) + __set_bit(i, inuse); } - snprintf(buf, IFNAMSIZ, name, i); - if (!netdev_name_in_use(net, buf)) - return i; + i = find_first_zero_bit(inuse, max_netdevices); + bitmap_free(inuse); + if (i == max_netdevices) + return -ENFILE; - /* It is possible to run out of possible slots - * when the name is long and there isn't enough space left - * for the digits, or if all bits are used. - */ - return -ENFILE; + snprintf(res, IFNAMSIZ, name, i); + return i; } -static int dev_alloc_name_ns(struct net *net, - struct net_device *dev, - const char *name) +/* Returns negative errno or allocated unit id (see __dev_alloc_name()) */ +static int dev_prep_valid_name(struct net *net, struct net_device *dev, + const char *want_name, char *out_name, + int dup_errno) { - char buf[IFNAMSIZ]; - int ret; + if (!dev_valid_name(want_name)) + return -EINVAL; - BUG_ON(!net); - ret = __dev_alloc_name(net, name, buf); - if (ret >= 0) - strscpy(dev->name, buf, IFNAMSIZ); - return ret; + if (strchr(want_name, '%')) + return __dev_alloc_name(net, want_name, out_name); + + if (netdev_name_in_use(net, want_name)) + return -dup_errno; + if (out_name != want_name) + strscpy(out_name, want_name, IFNAMSIZ); + return 0; } /** @@ -1153,26 +1157,17 @@ static int dev_alloc_name_ns(struct net *net, int dev_alloc_name(struct net_device *dev, const char *name) { - return dev_alloc_name_ns(dev_net(dev), dev, name); + return dev_prep_valid_name(dev_net(dev), dev, name, dev->name, ENFILE); } EXPORT_SYMBOL(dev_alloc_name); static int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { - BUG_ON(!net); - - if (!dev_valid_name(name)) - return -EINVAL; - - if (strchr(name, '%')) - return dev_alloc_name_ns(net, dev, name); - else if (netdev_name_in_use(net, name)) - return -EEXIST; - else if (dev->name != name) - strscpy(dev->name, name, IFNAMSIZ); + int ret; - return 0; + ret = dev_prep_valid_name(net, dev, name, dev->name, EEXIST); + return ret < 0 ? ret : 0; } /** @@ -6532,9 +6527,11 @@ static int __napi_poll(struct napi_struct *n, bool *repoll) * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; - if (test_bit(NAPI_STATE_SCHED, &n->state)) { + if (napi_is_scheduled(n)) { work = n->poll(n, weight); trace_napi_poll(n, work, weight); + + xdp_do_check_flushed(n); } if (unlikely(work > weight)) @@ -11081,7 +11078,9 @@ EXPORT_SYMBOL(unregister_netdev); int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex) { + struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); + char new_name[IFNAMSIZ] = {}; int err, new_nsid; ASSERT_RTNL(); @@ -11108,10 +11107,15 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, /* We get here if we can't use the current device name */ if (!pat) goto out; - err = dev_get_valid_name(net, dev, pat); + err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST); if (err < 0) goto out; } + /* Check that none of the altnames conflicts. */ + err = -EEXIST; + netdev_for_each_altname(dev, name_node) + if (netdev_name_in_use(net, name_node->name)) + goto out; /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { @@ -11179,6 +11183,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, kobject_uevent(&dev->dev.kobj, KOBJ_ADD); netdev_adjacent_add_links(dev); + if (new_name[0]) /* Rename the netdev to prepared name */ + strscpy(dev->name, new_name, IFNAMSIZ); + /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); WARN_ON(err); diff --git a/net/core/dev.h b/net/core/dev.h index e075e198092c..5aa45f0fd4ae 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -62,6 +62,9 @@ struct netdev_name_node { int netdev_get_name(struct net *net, char *name, int ifindex); int dev_change_name(struct net_device *dev, const char *newname); +#define netdev_for_each_altname(dev, namenode) \ + list_for_each_entry((namenode), &(dev)->name_node->list, list) + int netdev_name_node_alt_create(struct net_device *dev, const char *name); int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); @@ -136,4 +139,10 @@ static inline void netif_set_gro_ipv4_max_size(struct net_device *dev, } int rps_cpumask_housekeeping(struct cpumask *mask); + +#if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) +void xdp_do_check_flushed(struct napi_struct *napi); +#else +static inline void xdp_do_check_flushed(struct napi_struct *napi) { } +#endif #endif diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index b46aedc36939..feeddf95f450 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -382,7 +382,7 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) if (err) return err; - err = dsa_master_hwtstamp_validate(dev, &kernel_cfg, &extack); + err = dsa_conduit_hwtstamp_validate(dev, &kernel_cfg, &extack); if (err) { if (extack._msg) netdev_err(dev, "%s\n", extack._msg); diff --git a/net/core/filter.c b/net/core/filter.c index cc2e4babc85f..21d75108c2e9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -83,6 +83,8 @@ #include <net/netfilter/nf_conntrack_bpf.h> #include <linux/un.h> +#include "dev.h" + static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id); @@ -4208,6 +4210,20 @@ void xdp_do_flush(void) } EXPORT_SYMBOL_GPL(xdp_do_flush); +#if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) +void xdp_do_check_flushed(struct napi_struct *napi) +{ + bool ret; + + ret = dev_check_flush(); + ret |= cpu_map_check_flush(); + ret |= xsk_map_check_flush(); + + WARN_ONCE(ret, "Missing xdp_do_flush() invocation after NAPI by %ps\n", + napi->poll); +} +#endif + void bpf_clear_redirect_map(struct bpf_map *map) { struct bpf_redirect_info *ri; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 9c09f091cbff..df81c1f0a570 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -251,7 +251,8 @@ bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) static int neigh_forced_gc(struct neigh_table *tbl) { - int max_clean = atomic_read(&tbl->gc_entries) - tbl->gc_thresh2; + int max_clean = atomic_read(&tbl->gc_entries) - + READ_ONCE(tbl->gc_thresh2); unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; @@ -280,7 +281,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) } } - tbl->last_flush = jiffies; + WRITE_ONCE(tbl->last_flush, jiffies); write_unlock_bh(&tbl->lock); @@ -464,17 +465,17 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, { struct neighbour *n = NULL; unsigned long now = jiffies; - int entries; + int entries, gc_thresh3; if (exempt_from_gc) goto do_alloc; entries = atomic_inc_return(&tbl->gc_entries) - 1; - if (entries >= tbl->gc_thresh3 || - (entries >= tbl->gc_thresh2 && - time_after(now, tbl->last_flush + 5 * HZ))) { - if (!neigh_forced_gc(tbl) && - entries >= tbl->gc_thresh3) { + gc_thresh3 = READ_ONCE(tbl->gc_thresh3); + if (entries >= gc_thresh3 || + (entries >= READ_ONCE(tbl->gc_thresh2) && + time_after(now, READ_ONCE(tbl->last_flush) + 5 * HZ))) { + if (!neigh_forced_gc(tbl) && entries >= gc_thresh3) { net_info_ratelimited("%s: neighbor table overflow!\n", tbl->id); NEIGH_CACHE_STAT_INC(tbl, table_fulls); @@ -955,13 +956,14 @@ static void neigh_periodic_work(struct work_struct *work) if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; - tbl->last_rand = jiffies; + + WRITE_ONCE(tbl->last_rand, jiffies); list_for_each_entry(p, &tbl->parms_list, list) p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } - if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + if (atomic_read(&tbl->entries) < READ_ONCE(tbl->gc_thresh1)) goto out; for (i = 0 ; i < (1 << nht->hash_shift); i++) { @@ -2167,15 +2169,16 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndtmsg->ndtm_pad2 = 0; if (nla_put_string(skb, NDTA_NAME, tbl->id) || - nla_put_msecs(skb, NDTA_GC_INTERVAL, tbl->gc_interval, NDTA_PAD) || - nla_put_u32(skb, NDTA_THRESH1, tbl->gc_thresh1) || - nla_put_u32(skb, NDTA_THRESH2, tbl->gc_thresh2) || - nla_put_u32(skb, NDTA_THRESH3, tbl->gc_thresh3)) + nla_put_msecs(skb, NDTA_GC_INTERVAL, READ_ONCE(tbl->gc_interval), + NDTA_PAD) || + nla_put_u32(skb, NDTA_THRESH1, READ_ONCE(tbl->gc_thresh1)) || + nla_put_u32(skb, NDTA_THRESH2, READ_ONCE(tbl->gc_thresh2)) || + nla_put_u32(skb, NDTA_THRESH3, READ_ONCE(tbl->gc_thresh3))) goto nla_put_failure; { unsigned long now = jiffies; - long flush_delta = now - tbl->last_flush; - long rand_delta = now - tbl->last_rand; + long flush_delta = now - READ_ONCE(tbl->last_flush); + long rand_delta = now - READ_ONCE(tbl->last_rand); struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, @@ -2183,7 +2186,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, .ndtc_entries = atomic_read(&tbl->entries), .ndtc_last_flush = jiffies_to_msecs(flush_delta), .ndtc_last_rand = jiffies_to_msecs(rand_delta), - .ndtc_proxy_qlen = tbl->proxy_queue.qlen, + .ndtc_proxy_qlen = READ_ONCE(tbl->proxy_queue.qlen), }; rcu_read_lock(); @@ -2206,17 +2209,17 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, struct neigh_statistics *st; st = per_cpu_ptr(tbl->stats, cpu); - ndst.ndts_allocs += st->allocs; - ndst.ndts_destroys += st->destroys; - ndst.ndts_hash_grows += st->hash_grows; - ndst.ndts_res_failed += st->res_failed; - ndst.ndts_lookups += st->lookups; - ndst.ndts_hits += st->hits; - ndst.ndts_rcv_probes_mcast += st->rcv_probes_mcast; - ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast; - ndst.ndts_periodic_gc_runs += st->periodic_gc_runs; - ndst.ndts_forced_gc_runs += st->forced_gc_runs; - ndst.ndts_table_fulls += st->table_fulls; + ndst.ndts_allocs += READ_ONCE(st->allocs); + ndst.ndts_destroys += READ_ONCE(st->destroys); + ndst.ndts_hash_grows += READ_ONCE(st->hash_grows); + ndst.ndts_res_failed += READ_ONCE(st->res_failed); + ndst.ndts_lookups += READ_ONCE(st->lookups); + ndst.ndts_hits += READ_ONCE(st->hits); + ndst.ndts_rcv_probes_mcast += READ_ONCE(st->rcv_probes_mcast); + ndst.ndts_rcv_probes_ucast += READ_ONCE(st->rcv_probes_ucast); + ndst.ndts_periodic_gc_runs += READ_ONCE(st->periodic_gc_runs); + ndst.ndts_forced_gc_runs += READ_ONCE(st->forced_gc_runs); + ndst.ndts_table_fulls += READ_ONCE(st->table_fulls); } if (nla_put_64bit(skb, NDTA_STATS, sizeof(ndst), &ndst, @@ -2445,16 +2448,16 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout_tbl_lock; if (tb[NDTA_THRESH1]) - tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); + WRITE_ONCE(tbl->gc_thresh1, nla_get_u32(tb[NDTA_THRESH1])); if (tb[NDTA_THRESH2]) - tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]); + WRITE_ONCE(tbl->gc_thresh2, nla_get_u32(tb[NDTA_THRESH2])); if (tb[NDTA_THRESH3]) - tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]); + WRITE_ONCE(tbl->gc_thresh3, nla_get_u32(tb[NDTA_THRESH3])); if (tb[NDTA_GC_INTERVAL]) - tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]); + WRITE_ONCE(tbl->gc_interval, nla_get_msecs(tb[NDTA_GC_INTERVAL])); err = 0; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8a9868ea5067..5e409b98aba0 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -376,6 +376,14 @@ static void page_pool_set_pp_info(struct page_pool *pool, { page->pp = pool; page->pp_magic |= PP_SIGNATURE; + + /* Ensuring all pages have been split into one fragment initially: + * page_pool_set_pp_info() is only called once for every page when it + * is allocated from the page allocator and page_pool_fragment_page() + * is dirtying the same cache line as the page->pp_magic above, so + * the overhead is negligible. + */ + page_pool_fragment_page(page, 1); if (pool->p.init_callback) pool->p.init_callback(page, pool->p.init_arg); } @@ -672,7 +680,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, struct page *page = virt_to_head_page(data[i]); /* It is not the last user for the page frag case */ - if (!page_pool_is_last_frag(pool, page)) + if (!page_pool_is_last_frag(page)) continue; page = __page_pool_put_page(pool, page, -1, false); @@ -748,8 +756,7 @@ struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int max_size = PAGE_SIZE << pool->p.order; struct page *page = pool->frag_page; - if (WARN_ON(!(pool->p.flags & PP_FLAG_PAGE_FRAG) || - size > max_size)) + if (WARN_ON(size > max_size)) return NULL; size = ALIGN(size, dma_get_cache_alignment()); @@ -802,7 +809,7 @@ static void page_pool_empty_ring(struct page_pool *pool) } } -static void page_pool_free(struct page_pool *pool) +static void __page_pool_destroy(struct page_pool *pool) { if (pool->disconnect) pool->disconnect(pool); @@ -853,7 +860,7 @@ static int page_pool_release(struct page_pool *pool) page_pool_scrub(pool); inflight = page_pool_inflight(pool); if (!inflight) - page_pool_free(pool); + __page_pool_destroy(pool); return inflight; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 5e865af82e5b..8afcfadf8d5a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -670,19 +670,19 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_puts(seq, " Flags: "); for (i = 0; i < NR_PKT_FLAGS; i++) { - if (i == F_FLOW_SEQ) + if (i == FLOW_SEQ_SHIFT) if (!pkt_dev->cflows) continue; - if (pkt_dev->flags & (1 << i)) + if (pkt_dev->flags & (1 << i)) { seq_printf(seq, "%s ", pkt_flag_names[i]); - else if (i == F_FLOW_SEQ) - seq_puts(seq, "FLOW_RND "); - #ifdef CONFIG_XFRM - if (i == F_IPSEC && pkt_dev->spi) - seq_printf(seq, "spi:%u", pkt_dev->spi); + if (i == IPSEC_SHIFT && pkt_dev->spi) + seq_printf(seq, "spi:%u ", pkt_dev->spi); #endif + } else if (i == FLOW_SEQ_SHIFT) { + seq_puts(seq, "FLOW_RND "); + } } seq_puts(seq, "\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eef7f7788996..f2753fd58881 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5532,13 +5532,11 @@ static unsigned int rtnl_offload_xstats_get_size_hw_s_info_one(const struct net_device *dev, enum netdev_offload_xstats_type type) { - bool enabled = netdev_offload_xstats_enabled(dev, type); - return nla_total_size(0) + /* IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST */ nla_total_size(sizeof(u8)) + /* IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED */ - (enabled ? nla_total_size(sizeof(u8)) : 0) + + nla_total_size(sizeof(u8)) + 0; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0401f40973a5..c52ddd6891d9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4267,6 +4267,7 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config) { + unsigned int patlen = config->ops->get_pattern_len(config); struct ts_state state; unsigned int ret; @@ -4278,7 +4279,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); ret = textsearch_find(config, &state); - return (ret <= to - from ? ret : UINT_MAX); + return (ret + patlen <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); @@ -5764,7 +5765,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, /* In general, avoid mixing page_pool and non-page_pool allocated * pages within the same SKB. Additionally avoid dealing with clones * with page_pool pages, in case the SKB is using page_pool fragment - * references (PP_FLAG_PAGE_FRAG). Since we only take full page + * references (page_pool_alloc_frag()). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. * In theory we could take full references if @from is cloned and diff --git a/net/core/sock.c b/net/core/sock.c index 290165954379..1d28e3e87970 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3035,21 +3035,29 @@ EXPORT_SYMBOL(sk_wait_data); * @amt: pages to allocate * @kind: allocation type * - * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc + * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc. + * + * Unlike the globally shared limits among the sockets under same protocol, + * consuming the budget of a memcg won't have direct effect on other ones. + * So be optimistic about memcg's tolerance, and leave the callers to decide + * whether or not to raise allocated through sk_under_memory_pressure() or + * its variants. */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { - bool memcg_charge = mem_cgroup_sockets_enabled && sk->sk_memcg; + struct mem_cgroup *memcg = mem_cgroup_sockets_enabled ? sk->sk_memcg : NULL; struct proto *prot = sk->sk_prot; - bool charged = true; + bool charged = false; long allocated; sk_memory_allocated_add(sk, amt); allocated = sk_memory_allocated(sk); - if (memcg_charge && - !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt, - gfp_memcg_charge()))) - goto suppress_allocation; + + if (memcg) { + if (!mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge())) + goto suppress_allocation; + charged = true; + } /* Under limit. */ if (allocated <= sk_prot_mem_limits(sk, 0)) { @@ -3065,7 +3073,14 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; - /* guarantee minimum buffer size under pressure */ + /* Guarantee minimum buffer size under pressure (either global + * or memcg) to make sure features described in RFC 7323 (TCP + * Extensions for High Performance) work properly. + * + * This rule does NOT stand when exceeds global or memcg's hard + * limit, or else a DoS attack can be taken place by spawning + * lots of sockets whose usage are under minimum buffer size. + */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot)) return 1; @@ -3084,8 +3099,17 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) if (sk_has_memory_pressure(sk)) { u64 alloc; - if (!sk_under_memory_pressure(sk)) + /* The following 'average' heuristic is within the + * scope of global accounting, so it only makes + * sense for global memory pressure. + */ + if (!sk_under_global_memory_pressure(sk)) return 1; + + /* Try to be fair among all the sockets under global + * pressure by allowing the ones that below average + * usage to raise. + */ alloc = sk_sockets_allocated_read_positive(sk); if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + @@ -3104,8 +3128,8 @@ suppress_allocation: */ if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { /* Force charge with __GFP_NOFAIL */ - if (memcg_charge && !charged) { - mem_cgroup_charge_skmem(sk->sk_memcg, amt, + if (memcg && !charged) { + mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge() | __GFP_NOFAIL); } return 1; @@ -3117,8 +3141,8 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); - if (memcg_charge && charged) - mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); + if (charged) + mem_cgroup_uncharge_skmem(memcg, amt); return 0; } diff --git a/net/core/stream.c b/net/core/stream.c index f5c4e47df165..96fbcb9bbb30 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -117,7 +117,7 @@ EXPORT_SYMBOL(sk_stream_wait_close); */ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) { - int err = 0; + int ret, err = 0; long vm_wait = 0; long current_timeo = *timeo_p; DEFINE_WAIT_FUNC(wait, woken_wake_function); @@ -142,11 +142,13 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || - (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || - (sk_stream_memory_free(sk) && - !vm_wait), &wait); + ret = sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || + (sk_stream_memory_free(sk) && !vm_wait), + &wait); sk->sk_write_pending--; + if (ret < 0) + goto do_error; if (vm_wait) { vm_wait -= current_timeo; diff --git a/net/devlink/core.c b/net/devlink/core.c index bcbbb952569f..6984877e9f10 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -168,6 +168,20 @@ int devlink_rel_nested_in_add(u32 *rel_index, u32 devlink_index, return 0; } +/** + * devlink_rel_nested_in_notify - Notify the object this devlink + * instance is nested in. + * @devlink: devlink + * + * This is called upon network namespace change of devlink instance. + * In case this devlink instance is nested in another devlink object, + * a notification of a change of this object should be sent + * over netlink. The parent devlink instance lock needs to be + * taken during the notification preparation. + * However, since the devlink lock of nested instance is held here, + * we would end with wrong devlink instance lock ordering and + * deadlock. Therefore the work is utilized to avoid that. + */ void devlink_rel_nested_in_notify(struct devlink *devlink) { struct devlink_rel *rel = devlink->rel; @@ -183,9 +197,8 @@ static struct devlink_rel *devlink_rel_find(unsigned long rel_index) DEVLINK_REL_IN_USE); } -static struct devlink *devlink_rel_devlink_get_lock(u32 rel_index) +static struct devlink *devlink_rel_devlink_get(u32 rel_index) { - struct devlink *devlink; struct devlink_rel *rel; u32 devlink_index; @@ -198,16 +211,7 @@ static struct devlink *devlink_rel_devlink_get_lock(u32 rel_index) xa_unlock(&devlink_rels); if (!rel) return NULL; - devlink = devlinks_xa_get(devlink_index); - if (!devlink) - return NULL; - devl_lock(devlink); - if (!devl_is_registered(devlink)) { - devl_unlock(devlink); - devlink_put(devlink); - return NULL; - } - return devlink; + return devlinks_xa_get(devlink_index); } int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink, @@ -218,11 +222,10 @@ int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink, struct devlink *rel_devlink; int err; - rel_devlink = devlink_rel_devlink_get_lock(rel_index); + rel_devlink = devlink_rel_devlink_get(rel_index); if (!rel_devlink) return 0; err = devlink_nl_put_nested_handle(msg, net, rel_devlink, attrtype); - devl_unlock(rel_devlink); devlink_put(rel_devlink); if (!err && msg_updated) *msg_updated = true; @@ -310,6 +313,7 @@ static void devlink_release(struct work_struct *work) mutex_destroy(&devlink->lock); lockdep_unregister_key(&devlink->lock_key); + put_device(devlink->dev); kfree(devlink); } @@ -425,7 +429,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, if (ret < 0) goto err_xa_alloc; - devlink->dev = dev; + devlink->dev = get_device(dev); devlink->ops = ops; xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); xa_init_flags(&devlink->params, XA_FLAGS_ALLOC); diff --git a/net/devlink/dev.c b/net/devlink/dev.c index dc8039ca2b38..4fc7adb32663 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -492,7 +492,7 @@ free_msg: return -EMSGSIZE; } -int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; enum devlink_reload_action action; @@ -658,7 +658,7 @@ nla_put_failure: return err; } -int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; @@ -679,7 +679,7 @@ int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) return genlmsg_reply(msg, info); } -int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; @@ -1108,7 +1108,7 @@ static int devlink_flash_component_get(struct devlink *devlink, return 0; } -int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_flash_update_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *nla_overwrite_mask, *nla_file_name; struct devlink_flash_update_params params = {}; @@ -1351,7 +1351,7 @@ static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, }; -int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; struct devlink *devlink = info->user_ptr[0]; diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index 741d1bf1bec8..183dbe3807ab 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -227,67 +227,3 @@ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, /* Linecards */ unsigned int devlink_linecard_index(struct devlink_linecard *linecard); - -/* Devlink nl cmds */ -int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_resource_dump(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb); -int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, - struct netlink_callback *cb); -int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, - struct netlink_callback *cb); -int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb, - struct genl_info *info); diff --git a/net/devlink/dpipe.c b/net/devlink/dpipe.c index 431227c412e5..a72a9292efc5 100644 --- a/net/devlink/dpipe.c +++ b/net/devlink/dpipe.c @@ -289,7 +289,7 @@ err_table_put: return err; } -int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_dpipe_table_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const char *table_name = NULL; @@ -562,8 +562,8 @@ send_done: return genlmsg_reply(dump_ctx.skb, info); } -int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_dpipe_entries_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_dpipe_table *table; @@ -712,8 +712,8 @@ err_table_put: return err; } -int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_dpipe_headers_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; @@ -746,8 +746,8 @@ static int devlink_dpipe_table_counters_set(struct devlink *devlink, return 0; } -int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_dpipe_table_counters_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const char *table_name; diff --git a/net/devlink/health.c b/net/devlink/health.c index 51e6e81e31bb..695df61f8ac2 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -19,6 +19,7 @@ struct devlink_fmsg_item { struct devlink_fmsg { struct list_head item_list; + int err; /* first error encountered on some devlink_fmsg_XXX() call */ bool putting_binary; /* This flag forces enclosing of binary data * in an array brackets. It forces using * of designated API: @@ -451,8 +452,8 @@ int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb, devlink_nl_health_reporter_get_dump_one); } -int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -562,21 +563,18 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, return 0; reporter->dump_fmsg = devlink_fmsg_alloc(); - if (!reporter->dump_fmsg) { - err = -ENOMEM; - return err; - } + if (!reporter->dump_fmsg) + return -ENOMEM; - err = devlink_fmsg_obj_nest_start(reporter->dump_fmsg); - if (err) - goto dump_err; + devlink_fmsg_obj_nest_start(reporter->dump_fmsg); err = reporter->ops->dump(reporter, reporter->dump_fmsg, priv_ctx, extack); if (err) goto dump_err; - err = devlink_fmsg_obj_nest_end(reporter->dump_fmsg); + devlink_fmsg_obj_nest_end(reporter->dump_fmsg); + err = reporter->dump_fmsg->err; if (err) goto dump_err; @@ -657,8 +655,8 @@ devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, } EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); -int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -670,373 +668,258 @@ int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, return devlink_health_reporter_recover(reporter, NULL, info->extack); } -static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, - int attrtype) +static void devlink_fmsg_err_if_binary(struct devlink_fmsg *fmsg) +{ + if (!fmsg->err && fmsg->putting_binary) + fmsg->err = -EINVAL; +} + +static void devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, int attrtype) { struct devlink_fmsg_item *item; + if (fmsg->err) + return; + item = kzalloc(sizeof(*item), GFP_KERNEL); - if (!item) - return -ENOMEM; + if (!item) { + fmsg->err = -ENOMEM; + return; + } item->attrtype = attrtype; list_add_tail(&item->list, &fmsg->item_list); - - return 0; } -int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) +void devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); -static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) +static void devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); } -int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) +void devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_end(fmsg); + devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); #define DEVLINK_FMSG_MAX_SIZE (GENLMSG_DEFAULT_SIZE - GENL_HDRLEN - NLA_HDRLEN) -static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) +static void devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) { struct devlink_fmsg_item *item; - if (fmsg->putting_binary) - return -EINVAL; + devlink_fmsg_err_if_binary(fmsg); + if (fmsg->err) + return; - if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) - return -EMSGSIZE; + if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) { + fmsg->err = -EMSGSIZE; + return; + } item = kzalloc(sizeof(*item) + strlen(name) + 1, GFP_KERNEL); - if (!item) - return -ENOMEM; + if (!item) { + fmsg->err = -ENOMEM; + return; + } item->nla_type = NLA_NUL_STRING; item->len = strlen(name) + 1; item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME; memcpy(&item->value, name, item->len); list_add_tail(&item->list, &fmsg->item_list); - - return 0; } -int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) +void devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) { - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); - if (err) - return err; - - err = devlink_fmsg_put_name(fmsg, name); - if (err) - return err; - - return 0; + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); + devlink_fmsg_put_name(fmsg, name); } EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); -int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) +void devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_end(fmsg); + devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); -int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name) +void devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) { - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); } EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_start); -int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) +void devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) { - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_nest_end(fmsg); + devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); -int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name) +void devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) { - int err; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, name); - if (err) - return err; - + devlink_fmsg_arr_pair_nest_start(fmsg, name); fmsg->putting_binary = true; - return err; } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_start); -int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) +void devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) { + if (fmsg->err) + return; + if (!fmsg->putting_binary) - return -EINVAL; + fmsg->err = -EINVAL; fmsg->putting_binary = false; - return devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_end); -static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, - const void *value, u16 value_len, - u8 value_nla_type) +static void devlink_fmsg_put_value(struct devlink_fmsg *fmsg, + const void *value, u16 value_len, + u8 value_nla_type) { struct devlink_fmsg_item *item; - if (value_len > DEVLINK_FMSG_MAX_SIZE) - return -EMSGSIZE; + if (fmsg->err) + return; + + if (value_len > DEVLINK_FMSG_MAX_SIZE) { + fmsg->err = -EMSGSIZE; + return; + } item = kzalloc(sizeof(*item) + value_len, GFP_KERNEL); - if (!item) - return -ENOMEM; + if (!item) { + fmsg->err = -ENOMEM; + return; + } item->nla_type = value_nla_type; item->len = value_len; item->attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; memcpy(&item->value, value, item->len); list_add_tail(&item->list, &fmsg->item_list); - - return 0; } -static int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) +static void devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); } -static int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) +static void devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); } -int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) +void devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); -static int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) +static void devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); } -int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) +void devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, - NLA_NUL_STRING); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, NLA_NUL_STRING); } EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); -int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) +void devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) { - if (!fmsg->putting_binary) - return -EINVAL; + if (!fmsg->err && !fmsg->putting_binary) + fmsg->err = -EINVAL; - return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); + devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); -int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, - bool value) +void devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, + bool value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_bool_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_bool_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_bool_pair_put); -int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, - u8 value) +void devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, + u8 value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u8_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_u8_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u8_pair_put); -int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, - u32 value) +void devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, + u32 value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u32_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_u32_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_pair_put); -int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, - u64 value) +void devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, + u64 value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u64_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_u64_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u64_pair_put); -int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, - const char *value) +void devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, + const char *value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_string_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_string_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); -int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u32 value_len) +void devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, + const void *value, u32 value_len) { u32 data_size; - int end_err; u32 offset; - int err; - err = devlink_fmsg_binary_pair_nest_start(fmsg, name); - if (err) - return err; + devlink_fmsg_binary_pair_nest_start(fmsg, name); for (offset = 0; offset < value_len; offset += data_size) { data_size = value_len - offset; if (data_size > DEVLINK_FMSG_MAX_SIZE) data_size = DEVLINK_FMSG_MAX_SIZE; - err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); - if (err) - break; - /* Exit from loop with a break (instead of - * return) to make sure putting_binary is turned off in - * devlink_fmsg_binary_pair_nest_end - */ - } - end_err = devlink_fmsg_binary_pair_nest_end(fmsg); - if (end_err) - err = end_err; + devlink_fmsg_binary_put(fmsg, value + offset, data_size); + } - return err; + devlink_fmsg_binary_pair_nest_end(fmsg); + fmsg->putting_binary = false; } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); @@ -1146,6 +1029,9 @@ static int devlink_fmsg_snd(struct devlink_fmsg *fmsg, void *hdr; int err; + if (fmsg->err) + return fmsg->err; + while (!last) { int tmp_index = index; @@ -1199,6 +1085,9 @@ static int devlink_fmsg_dumpit(struct devlink_fmsg *fmsg, struct sk_buff *skb, void *hdr; int err; + if (fmsg->err) + return fmsg->err; + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, cmd); if (!hdr) { @@ -1219,8 +1108,8 @@ nla_put_failure: return err; } -int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -1238,17 +1127,13 @@ int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, if (!fmsg) return -ENOMEM; - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - goto out; + devlink_fmsg_obj_nest_start(fmsg); err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) goto out; - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - goto out; + devlink_fmsg_obj_nest_end(fmsg); err = devlink_fmsg_snd(fmsg, info, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); @@ -1278,8 +1163,8 @@ devlink_health_reporter_get_from_cb_lock(struct netlink_callback *cb) return reporter; } -int devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, - struct netlink_callback *cb) +int devlink_nl_health_reporter_dump_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_health_reporter *reporter; @@ -1317,8 +1202,8 @@ unlock: return err; } -int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -1334,8 +1219,8 @@ int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, return 0; } -int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_test_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; diff --git a/net/devlink/linecard.c b/net/devlink/linecard.c index 9ff1813f88c5..2f1c317b64cd 100644 --- a/net/devlink/linecard.c +++ b/net/devlink/linecard.c @@ -369,8 +369,7 @@ out: return err; } -int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index 499304d9de49..d0b90ebc8b15 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -13,91 +13,28 @@ static const struct genl_multicast_group devlink_nl_mcgrps[] = { [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, }; -static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { - [DEVLINK_ATTR_UNSPEC] = { .strict_start_type = - DEVLINK_ATTR_TRAP_POLICER_ID }, - [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO, - DEVLINK_PORT_TYPE_IB), - [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY, - DEVLINK_ESWITCH_MODE_SWITCHDEV), - [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, - [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64}, - [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64}, - [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, - [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, - [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = - NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS), - [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, - [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, - [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8 }, - [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 }, - [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 }, - [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED }, - [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - DEVLINK_RELOAD_ACTION_MAX), - [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), - [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, - [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, - [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, - [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 }, - [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 }, - [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 }, - [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, - [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, - [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, - [DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG }, -}; - int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net, struct devlink *devlink, int attrtype) { struct nlattr *nested_attr; + struct net *devl_net; nested_attr = nla_nest_start(msg, attrtype); if (!nested_attr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; - if (!net_eq(net, devlink_net(devlink))) { - int id = peernet2id_alloc(net, devlink_net(devlink), - GFP_KERNEL); + rcu_read_lock(); + devl_net = read_pnet_rcu(&devlink->_net); + if (!net_eq(net, devl_net)) { + int id = peernet2id_alloc(net, devl_net, GFP_ATOMIC); + + rcu_read_unlock(); if (nla_put_s32(msg, DEVLINK_ATTR_NETNS_ID, id)) return -EMSGSIZE; + } else { + rcu_read_unlock(); } nla_nest_end(msg, nested_attr); @@ -185,7 +122,7 @@ unlock: int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { - return __devlink_nl_pre_doit(skb, info, ops->internal_flags); + return __devlink_nl_pre_doit(skb, info, 0); } int devlink_nl_pre_doit_port(const struct genl_split_ops *ops, @@ -281,269 +218,12 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, return devlink_nl_inst_iter_dumpit(msg, cb, flags, dump_one); } -static const struct genl_small_ops devlink_nl_small_ops[40] = { - { - .cmd = DEVLINK_CMD_PORT_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_RATE_SET, - .doit = devlink_nl_cmd_rate_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RATE_NEW, - .doit = devlink_nl_cmd_rate_new_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RATE_DEL, - .doit = devlink_nl_cmd_rate_del_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PORT_SPLIT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_split_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_PORT_UNSPLIT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_unsplit_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_PORT_NEW, - .doit = devlink_nl_cmd_port_new_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PORT_DEL, - .doit = devlink_nl_cmd_port_del_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - - { - .cmd = DEVLINK_CMD_LINECARD_SET, - .doit = devlink_nl_cmd_linecard_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SB_POOL_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_pool_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_port_pool_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_occ_snapshot_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_occ_max_clear_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_ESWITCH_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_eswitch_get_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_ESWITCH_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_eswitch_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_table_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_entries_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_headers_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_table_counters_set, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RESOURCE_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_resource_set, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RESOURCE_DUMP, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_resource_dump, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_RELOAD, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_reload, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PARAM_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_param_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PORT_PARAM_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_param_get_doit, - .dumpit = devlink_nl_cmd_port_param_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_PORT_PARAM_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_param_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_REGION_NEW, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_region_new, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_REGION_DEL, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_region_del, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_REGION_READ, - .validate = GENL_DONT_VALIDATE_STRICT | - GENL_DONT_VALIDATE_DUMP_STRICT, - .dumpit = devlink_nl_cmd_region_read_dumpit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_recover_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_diagnose_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - .validate = GENL_DONT_VALIDATE_STRICT | - GENL_DONT_VALIDATE_DUMP_STRICT, - .dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_test_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_FLASH_UPDATE, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_flash_update, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_SET, - .doit = devlink_nl_cmd_trap_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_GROUP_SET, - .doit = devlink_nl_cmd_trap_group_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_POLICER_SET, - .doit = devlink_nl_cmd_trap_policer_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SELFTESTS_RUN, - .doit = devlink_nl_cmd_selftests_run, - .flags = GENL_ADMIN_PERM, - }, - /* -- No new ops here! Use split ops going forward! -- */ -}; - struct genl_family devlink_nl_family __ro_after_init = { .name = DEVLINK_GENL_NAME, .version = DEVLINK_GENL_VERSION, - .maxattr = DEVLINK_ATTR_MAX, - .policy = devlink_nl_policy, .netnsok = true, .parallel_ops = true, - .pre_doit = devlink_nl_pre_doit, - .post_doit = devlink_nl_post_doit, .module = THIS_MODULE, - .small_ops = devlink_nl_small_ops, - .n_small_ops = ARRAY_SIZE(devlink_nl_small_ops), .split_ops = devlink_nl_ops, .n_split_ops = ARRAY_SIZE(devlink_nl_ops), .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index 467b7a431de1..9cbae0169249 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -10,6 +10,18 @@ #include <uapi/linux/devlink.h> +/* Common nested types */ +const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1] = { + [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY, }, + [DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_PORT_FN_ATTR_OPSTATE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(3), +}; + +const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = { + [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG, }, +}; + /* DEVLINK_CMD_GET - do */ static const struct nla_policy devlink_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -29,6 +41,48 @@ static const struct nla_policy devlink_port_get_dump_nl_policy[DEVLINK_ATTR_DEV_ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_PORT_SET - do */ +static const struct nla_policy devlink_port_set_nl_policy[DEVLINK_ATTR_PORT_FUNCTION + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_MAX(NLA_U16, 3), + [DEVLINK_ATTR_PORT_FUNCTION] = NLA_POLICY_NESTED(devlink_dl_port_function_nl_policy), +}; + +/* DEVLINK_CMD_PORT_NEW - do */ +static const struct nla_policy devlink_port_new_nl_policy[DEVLINK_ATTR_PORT_PCI_SF_NUMBER + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_PORT_FLAVOUR] = NLA_POLICY_MAX(NLA_U16, 7), + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16, }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32, }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_DEL - do */ +static const struct nla_policy devlink_port_del_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_SPLIT - do */ +static const struct nla_policy devlink_port_split_nl_policy[DEVLINK_ATTR_PORT_SPLIT_COUNT + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_UNSPLIT - do */ +static const struct nla_policy devlink_port_unsplit_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_SB_GET - do */ static const struct nla_policy devlink_sb_get_do_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -56,6 +110,16 @@ static const struct nla_policy devlink_sb_pool_get_dump_nl_policy[DEVLINK_ATTR_D [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_SB_POOL_SET - do */ +static const struct nla_policy devlink_sb_pool_set_nl_policy[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, }, + [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_SB_PORT_POOL_GET - do */ static const struct nla_policy devlink_sb_port_pool_get_do_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -71,6 +135,16 @@ static const struct nla_policy devlink_sb_port_pool_get_dump_nl_policy[DEVLINK_A [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_SB_PORT_POOL_SET - do */ +static const struct nla_policy devlink_sb_port_pool_set_nl_policy[DEVLINK_ATTR_SB_THRESHOLD + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, }, + [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ static const struct nla_policy devlink_sb_tc_pool_bind_get_do_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -87,6 +161,100 @@ static const struct nla_policy devlink_sb_tc_pool_bind_get_dump_nl_policy[DEVLIN [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */ +static const struct nla_policy devlink_sb_tc_pool_bind_set_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, }, + [DEVLINK_ATTR_SB_POOL_TYPE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16, }, + [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */ +static const struct nla_policy devlink_sb_occ_snapshot_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */ +static const struct nla_policy devlink_sb_occ_max_clear_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_ESWITCH_GET - do */ +static const struct nla_policy devlink_eswitch_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_ESWITCH_SET - do */ +static const struct nla_policy devlink_eswitch_set_nl_policy[DEVLINK_ATTR_ESWITCH_ENCAP_MODE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_MAX(NLA_U16, 1), + [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = NLA_POLICY_MAX(NLA_U16, 3), + [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = NLA_POLICY_MAX(NLA_U8, 1), +}; + +/* DEVLINK_CMD_DPIPE_TABLE_GET - do */ +static const struct nla_policy devlink_dpipe_table_get_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */ +static const struct nla_policy devlink_dpipe_entries_get_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */ +static const struct nla_policy devlink_dpipe_headers_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */ +static const struct nla_policy devlink_dpipe_table_counters_set_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8, }, +}; + +/* DEVLINK_CMD_RESOURCE_SET - do */ +static const struct nla_policy devlink_resource_set_nl_policy[DEVLINK_ATTR_RESOURCE_SIZE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64, }, +}; + +/* DEVLINK_CMD_RESOURCE_DUMP - do */ +static const struct nla_policy devlink_resource_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_RELOAD - do */ +static const struct nla_policy devlink_reload_nl_policy[DEVLINK_ATTR_RELOAD_LIMITS + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, 1, 2), + [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(6), + [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32, }, + [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32, }, + [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_PARAM_GET - do */ static const struct nla_policy devlink_param_get_do_nl_policy[DEVLINK_ATTR_PARAM_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -100,6 +268,15 @@ static const struct nla_policy devlink_param_get_dump_nl_policy[DEVLINK_ATTR_DEV [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_PARAM_SET - do */ +static const struct nla_policy devlink_param_set_nl_policy[DEVLINK_ATTR_PARAM_VALUE_CMODE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8, }, + [DEVLINK_ATTR_PARAM_VALUE_CMODE] = NLA_POLICY_MAX(NLA_U8, 2), +}; + /* DEVLINK_CMD_REGION_GET - do */ static const struct nla_policy devlink_region_get_do_nl_policy[DEVLINK_ATTR_REGION_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -114,6 +291,50 @@ static const struct nla_policy devlink_region_get_dump_nl_policy[DEVLINK_ATTR_DE [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_REGION_NEW - do */ +static const struct nla_policy devlink_region_new_nl_policy[DEVLINK_ATTR_REGION_SNAPSHOT_ID + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_REGION_DEL - do */ +static const struct nla_policy devlink_region_del_nl_policy[DEVLINK_ATTR_REGION_SNAPSHOT_ID + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_REGION_READ - dump */ +static const struct nla_policy devlink_region_read_nl_policy[DEVLINK_ATTR_REGION_DIRECT + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG, }, + [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64, }, + [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64, }, +}; + +/* DEVLINK_CMD_PORT_PARAM_GET - do */ +static const struct nla_policy devlink_port_param_get_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_PARAM_SET - do */ +static const struct nla_policy devlink_port_param_set_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_INFO_GET - do */ static const struct nla_policy devlink_info_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -135,6 +356,58 @@ static const struct nla_policy devlink_health_reporter_get_dump_nl_policy[DEVLIN [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, }; +/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */ +static const struct nla_policy devlink_health_reporter_set_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64, }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8, }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */ +static const struct nla_policy devlink_health_reporter_recover_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */ +static const struct nla_policy devlink_health_reporter_diagnose_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */ +static const struct nla_policy devlink_health_reporter_dump_get_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */ +static const struct nla_policy devlink_health_reporter_dump_clear_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_FLASH_UPDATE - do */ +static const struct nla_policy devlink_flash_update_nl_policy[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = NLA_POLICY_BITFIELD32(3), +}; + /* DEVLINK_CMD_TRAP_GET - do */ static const struct nla_policy devlink_trap_get_do_nl_policy[DEVLINK_ATTR_TRAP_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -148,6 +421,14 @@ static const struct nla_policy devlink_trap_get_dump_nl_policy[DEVLINK_ATTR_DEV_ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_TRAP_SET - do */ +static const struct nla_policy devlink_trap_set_nl_policy[DEVLINK_ATTR_TRAP_ACTION + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_ACTION] = NLA_POLICY_MAX(NLA_U8, 2), +}; + /* DEVLINK_CMD_TRAP_GROUP_GET - do */ static const struct nla_policy devlink_trap_group_get_do_nl_policy[DEVLINK_ATTR_TRAP_GROUP_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -161,6 +442,15 @@ static const struct nla_policy devlink_trap_group_get_dump_nl_policy[DEVLINK_ATT [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_TRAP_GROUP_SET - do */ +static const struct nla_policy devlink_trap_group_set_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_ACTION] = NLA_POLICY_MAX(NLA_U8, 2), + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_TRAP_POLICER_GET - do */ static const struct nla_policy devlink_trap_policer_get_do_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -174,6 +464,23 @@ static const struct nla_policy devlink_trap_policer_get_dump_nl_policy[DEVLINK_A [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_TRAP_POLICER_SET - do */ +static const struct nla_policy devlink_trap_policer_set_nl_policy[DEVLINK_ATTR_TRAP_POLICER_BURST + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, }, + [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64, }, + [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */ +static const struct nla_policy devlink_health_reporter_test_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + /* DEVLINK_CMD_RATE_GET - do */ static const struct nla_policy devlink_rate_get_do_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -188,6 +495,37 @@ static const struct nla_policy devlink_rate_get_dump_nl_policy[DEVLINK_ATTR_DEV_ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_RATE_SET - do */ +static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_RATE_NEW - do */ +static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_RATE_DEL - do */ +static const struct nla_policy devlink_rate_del_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, +}; + /* DEVLINK_CMD_LINECARD_GET - do */ static const struct nla_policy devlink_linecard_get_do_nl_policy[DEVLINK_ATTR_LINECARD_INDEX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -201,14 +539,29 @@ static const struct nla_policy devlink_linecard_get_dump_nl_policy[DEVLINK_ATTR_ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_LINECARD_SET - do */ +static const struct nla_policy devlink_linecard_set_nl_policy[DEVLINK_ATTR_LINECARD_TYPE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING, }, +}; + /* DEVLINK_CMD_SELFTESTS_GET - do */ static const struct nla_policy devlink_selftests_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_SELFTESTS_RUN - do */ +static const struct nla_policy devlink_selftests_run_nl_policy[DEVLINK_ATTR_SELFTESTS + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SELFTESTS] = NLA_POLICY_NESTED(devlink_dl_selftest_id_nl_policy), +}; + /* Ops table for devlink */ -const struct genl_split_ops devlink_nl_ops[32] = { +const struct genl_split_ops devlink_nl_ops[73] = { { .cmd = DEVLINK_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT, @@ -243,6 +596,56 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_PORT_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_set_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_FUNCTION, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_NEW, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_port_new_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_new_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_PCI_SF_NUMBER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_DEL, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_del_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_del_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_SPLIT, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_split_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_split_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_SPLIT_COUNT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_UNSPLIT, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_unsplit_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_unsplit_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_SB_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -277,6 +680,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_SB_POOL_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_sb_pool_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_pool_set_nl_policy, + .maxattr = DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit_port, @@ -294,6 +707,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_sb_port_pool_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_port_pool_set_nl_policy, + .maxattr = DEVLINK_ATTR_SB_THRESHOLD, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit_port, @@ -311,6 +734,126 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_sb_tc_pool_bind_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_tc_pool_bind_set_nl_policy, + .maxattr = DEVLINK_ATTR_SB_TC_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_sb_occ_snapshot_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_occ_snapshot_nl_policy, + .maxattr = DEVLINK_ATTR_SB_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_sb_occ_max_clear_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_occ_max_clear_nl_policy, + .maxattr = DEVLINK_ATTR_SB_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_ESWITCH_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_eswitch_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_eswitch_get_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_ESWITCH_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_eswitch_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_eswitch_set_nl_policy, + .maxattr = DEVLINK_ATTR_ESWITCH_ENCAP_MODE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_dpipe_table_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_dpipe_table_get_nl_policy, + .maxattr = DEVLINK_ATTR_DPIPE_TABLE_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_dpipe_entries_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_dpipe_entries_get_nl_policy, + .maxattr = DEVLINK_ATTR_DPIPE_TABLE_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_dpipe_headers_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_dpipe_headers_get_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_dpipe_table_counters_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_dpipe_table_counters_set_nl_policy, + .maxattr = DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RESOURCE_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_resource_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_resource_set_nl_policy, + .maxattr = DEVLINK_ATTR_RESOURCE_SIZE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RESOURCE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_resource_dump_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_resource_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RELOAD, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_reload_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_reload_nl_policy, + .maxattr = DEVLINK_ATTR_RELOAD_LIMITS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_PARAM_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -328,6 +871,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_PARAM_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_param_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_param_set_nl_policy, + .maxattr = DEVLINK_ATTR_PARAM_VALUE_CMODE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_REGION_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit_port_optional, @@ -345,6 +898,60 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_REGION_NEW, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_region_new_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_region_new_nl_policy, + .maxattr = DEVLINK_ATTR_REGION_SNAPSHOT_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_REGION_DEL, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_region_del_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_region_del_nl_policy, + .maxattr = DEVLINK_ATTR_REGION_SNAPSHOT_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_REGION_READ, + .validate = GENL_DONT_VALIDATE_DUMP_STRICT, + .dumpit = devlink_nl_region_read_dumpit, + .policy = devlink_region_read_nl_policy, + .maxattr = DEVLINK_ATTR_REGION_DIRECT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_param_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_param_get_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_GET, + .validate = GENL_DONT_VALIDATE_DUMP_STRICT, + .dumpit = devlink_nl_port_param_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_param_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_param_set_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_INFO_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -378,6 +985,64 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_set_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_recover_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_recover_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_diagnose_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_diagnose_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + .validate = GENL_DONT_VALIDATE_DUMP_STRICT, + .dumpit = devlink_nl_health_reporter_dump_get_dumpit, + .policy = devlink_health_reporter_dump_get_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_dump_clear_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_dump_clear_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_FLASH_UPDATE, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_flash_update_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_flash_update_nl_policy, + .maxattr = DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_TRAP_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -395,6 +1060,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_TRAP_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_set_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_ACTION, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_TRAP_GROUP_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -412,6 +1087,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_TRAP_GROUP_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_group_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_group_set_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_POLICER_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_TRAP_POLICER_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -429,6 +1114,26 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_TRAP_POLICER_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_policer_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_policer_set_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_POLICER_BURST, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_test_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_test_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_RATE_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -446,6 +1151,36 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_RATE_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_rate_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_rate_set_nl_policy, + .maxattr = DEVLINK_ATTR_RATE_TX_WEIGHT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RATE_NEW, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_rate_new_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_rate_new_nl_policy, + .maxattr = DEVLINK_ATTR_RATE_TX_WEIGHT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RATE_DEL, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_rate_del_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_rate_del_nl_policy, + .maxattr = DEVLINK_ATTR_RATE_NODE_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_LINECARD_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -463,6 +1198,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_LINECARD_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_linecard_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_linecard_set_nl_policy, + .maxattr = DEVLINK_ATTR_LINECARD_TYPE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_SELFTESTS_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -478,4 +1223,14 @@ const struct genl_split_ops devlink_nl_ops[32] = { .dumpit = devlink_nl_selftests_get_dumpit, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = DEVLINK_CMD_SELFTESTS_RUN, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_selftests_run_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_selftests_run_nl_policy, + .maxattr = DEVLINK_ATTR_SELFTESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index f8bbc93e39be..0e9e89c31c31 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -11,8 +11,12 @@ #include <uapi/linux/devlink.h> +/* Common nested types */ +extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1]; +extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1]; + /* Ops table for devlink */ -extern const struct genl_split_ops devlink_nl_ops[32]; +extern const struct genl_split_ops devlink_nl_ops[73]; int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); @@ -30,25 +34,61 @@ int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb, + struct genl_info *info); int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_dpipe_table_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_dpipe_entries_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_dpipe_headers_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_dpipe_table_counters_set_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_resource_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_resource_dump_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_param_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_param_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_param_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_region_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_region_read_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_port_param_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_param_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_port_param_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_info_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); @@ -56,24 +96,46 @@ int devlink_nl_health_reporter_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_dump_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_flash_update_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_trap_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_trap_group_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_policer_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_trap_policer_set_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_test_doit(struct sk_buff *skb, + struct genl_info *info); int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_rate_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_linecard_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_selftests_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info); #endif /* _LINUX_DEVLINK_GEN_H */ diff --git a/net/devlink/param.c b/net/devlink/param.c index 31275f9d4cb7..d74df09311a9 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -581,7 +581,7 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, return 0; } -int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_param_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; @@ -589,22 +589,22 @@ int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, struct genl_info *info) info, DEVLINK_CMD_PARAM_NEW); } -int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +int devlink_nl_port_param_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) { NL_SET_ERR_MSG(cb->extack, "Port params are not supported"); return msg->len; } -int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_port_param_get_doit(struct sk_buff *skb, + struct genl_info *info) { NL_SET_ERR_MSG(info->extack, "Port params are not supported"); return -EINVAL; } -int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_port_param_set_doit(struct sk_buff *skb, + struct genl_info *info) { NL_SET_ERR_MSG(info->extack, "Port params are not supported"); return -EINVAL; diff --git a/net/devlink/port.c b/net/devlink/port.c index 4e9003242448..7634f187fa50 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -772,7 +772,7 @@ static int devlink_port_function_set(struct devlink_port *port, return err; } -int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; int err; @@ -798,7 +798,7 @@ int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info) return 0; } -int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; @@ -829,8 +829,7 @@ int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info) info->extack); } -int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; @@ -840,7 +839,7 @@ int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack); } -int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink_port_new_attrs new_attrs = {}; @@ -904,7 +903,7 @@ err_out_port_del: return err; } -int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct netlink_ext_ack *extack = info->extack; diff --git a/net/devlink/rate.c b/net/devlink/rate.c index dff1593b8406..94b289b93ff2 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -458,7 +458,7 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, return true; } -int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_rate *devlink_rate; @@ -480,7 +480,7 @@ int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info) return err; } -int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_rate *rate_node; @@ -536,7 +536,7 @@ err_strdup: return err; } -int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_rate *rate_node; diff --git a/net/devlink/region.c b/net/devlink/region.c index d197cdb662db..0aab7b82d678 100644 --- a/net/devlink/region.c +++ b/net/devlink/region.c @@ -588,7 +588,7 @@ int devlink_nl_region_get_dumpit(struct sk_buff *skb, return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one); } -int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; @@ -633,7 +633,7 @@ int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info) return 0; } -int devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; @@ -863,8 +863,8 @@ devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, curr_offset, chunk_size, chunk); } -int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, - struct netlink_callback *cb) +int devlink_nl_region_read_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_nl_dump_state *state = devlink_dump_state(cb); diff --git a/net/devlink/resource.c b/net/devlink/resource.c index c8b615e4c385..594c8aeb3bfa 100644 --- a/net/devlink/resource.c +++ b/net/devlink/resource.c @@ -105,7 +105,7 @@ devlink_resource_validate_size(struct devlink_resource *resource, u64 size, return err; } -int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_resource_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_resource *resource; @@ -285,7 +285,7 @@ err_resource_put: return err; } -int devlink_nl_cmd_resource_dump(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_resource_dump_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; diff --git a/net/devlink/sb.c b/net/devlink/sb.c index bd677fff5ec8..0a76bb32502b 100644 --- a/net/devlink/sb.c +++ b/net/devlink/sb.c @@ -413,7 +413,7 @@ static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, return -EOPNOTSUPP; } -int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; enum devlink_sb_threshold_type threshold_type; @@ -621,8 +621,8 @@ static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, return -EOPNOTSUPP; } -int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; @@ -861,8 +861,8 @@ static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, return -EOPNOTSUPP; } -int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; @@ -900,8 +900,7 @@ int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, pool_index, threshold, info->extack); } -int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; @@ -916,8 +915,8 @@ int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, return -EOPNOTSUPP; } -int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; diff --git a/net/devlink/trap.c b/net/devlink/trap.c index c26bf9b29bca..c26313e7ca08 100644 --- a/net/devlink/trap.c +++ b/net/devlink/trap.c @@ -414,7 +414,7 @@ static int devlink_trap_action_set(struct devlink *devlink, info->extack); } -int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_trap_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; @@ -684,8 +684,7 @@ static int devlink_trap_group_set(struct devlink *devlink, return 0; } -int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_trap_group_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; @@ -926,8 +925,8 @@ devlink_trap_policer_set(struct devlink *devlink, return 0; } -int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_trap_policer_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_trap_policer_item *policer_item; struct netlink_ext_ack *extack = info->extack; diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 12e305824a96..8a1894a42552 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -8,16 +8,16 @@ endif # the core obj-$(CONFIG_NET_DSA) += dsa_core.o dsa_core-y += \ + conduit.o \ devlink.o \ dsa.o \ - master.o \ netlink.o \ port.o \ - slave.o \ switch.o \ tag.o \ tag_8021q.o \ - trace.o + trace.o \ + user.o # tagging formats obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o diff --git a/net/dsa/master.c b/net/dsa/conduit.c index 6be89ab0cc01..3dfdb3cb47dc 100644 --- a/net/dsa/master.c +++ b/net/dsa/conduit.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Handling of a master device, switching frames via its switch fabric CPU port + * Handling of a conduit device, switching frames via its switch fabric CPU port * * Copyright (c) 2017 Savoir-faire Linux Inc. * Vivien Didelot <vivien.didelot@savoirfairelinux.com> @@ -11,12 +11,12 @@ #include <linux/netlink.h> #include <net/dsa.h> +#include "conduit.h" #include "dsa.h" -#include "master.h" #include "port.h" #include "tag.h" -static int dsa_master_get_regs_len(struct net_device *dev) +static int dsa_conduit_get_regs_len(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -45,8 +45,8 @@ static int dsa_master_get_regs_len(struct net_device *dev) return ret; } -static void dsa_master_get_regs(struct net_device *dev, - struct ethtool_regs *regs, void *data) +static void dsa_conduit_get_regs(struct net_device *dev, + struct ethtool_regs *regs, void *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -80,9 +80,9 @@ static void dsa_master_get_regs(struct net_device *dev, } } -static void dsa_master_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) +static void dsa_conduit_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -99,9 +99,9 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, ds->ops->get_ethtool_stats(ds, port, data + count); } -static void dsa_master_get_ethtool_phy_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) +static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -125,7 +125,7 @@ static void dsa_master_get_ethtool_phy_stats(struct net_device *dev, ds->ops->get_ethtool_phy_stats(ds, port, data + count); } -static int dsa_master_get_sset_count(struct net_device *dev, int sset) +static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -147,8 +147,8 @@ static int dsa_master_get_sset_count(struct net_device *dev, int sset) return count; } -static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, - uint8_t *data) +static void dsa_conduit_get_strings(struct net_device *dev, uint32_t stringset, + uint8_t *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -195,12 +195,12 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, } } -/* Deny PTP operations on master if there is at least one switch in the tree +/* Deny PTP operations on conduit if there is at least one switch in the tree * that is PTP capable. */ -int __dsa_master_hwtstamp_validate(struct net_device *dev, - const struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack) +int __dsa_conduit_hwtstamp_validate(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch *ds = cpu_dp->ds; @@ -212,7 +212,7 @@ int __dsa_master_hwtstamp_validate(struct net_device *dev, list_for_each_entry(dp, &dst->ports, list) { if (dsa_port_supports_hwtstamp(dp)) { NL_SET_ERR_MSG(extack, - "HW timestamping not allowed on DSA master when switch supports the operation"); + "HW timestamping not allowed on DSA conduit when switch supports the operation"); return -EBUSY; } } @@ -220,7 +220,7 @@ int __dsa_master_hwtstamp_validate(struct net_device *dev, return 0; } -static int dsa_master_ethtool_setup(struct net_device *dev) +static int dsa_conduit_ethtool_setup(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch *ds = cpu_dp->ds; @@ -237,19 +237,19 @@ static int dsa_master_ethtool_setup(struct net_device *dev) if (cpu_dp->orig_ethtool_ops) memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); - ops->get_regs_len = dsa_master_get_regs_len; - ops->get_regs = dsa_master_get_regs; - ops->get_sset_count = dsa_master_get_sset_count; - ops->get_ethtool_stats = dsa_master_get_ethtool_stats; - ops->get_strings = dsa_master_get_strings; - ops->get_ethtool_phy_stats = dsa_master_get_ethtool_phy_stats; + ops->get_regs_len = dsa_conduit_get_regs_len; + ops->get_regs = dsa_conduit_get_regs; + ops->get_sset_count = dsa_conduit_get_sset_count; + ops->get_ethtool_stats = dsa_conduit_get_ethtool_stats; + ops->get_strings = dsa_conduit_get_strings; + ops->get_ethtool_phy_stats = dsa_conduit_get_ethtool_phy_stats; dev->ethtool_ops = ops; return 0; } -static void dsa_master_ethtool_teardown(struct net_device *dev) +static void dsa_conduit_ethtool_teardown(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -260,16 +260,16 @@ static void dsa_master_ethtool_teardown(struct net_device *dev) cpu_dp->orig_ethtool_ops = NULL; } -/* Keep the master always promiscuous if the tagging protocol requires that +/* Keep the conduit always promiscuous if the tagging protocol requires that * (garbles MAC DA) or if it doesn't support unicast filtering, case in which * it would revert to promiscuous mode as soon as we call dev_uc_add() on it * anyway. */ -static void dsa_master_set_promiscuity(struct net_device *dev, int inc) +static void dsa_conduit_set_promiscuity(struct net_device *dev, int inc) { const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops; - if ((dev->priv_flags & IFF_UNICAST_FLT) && !ops->promisc_on_master) + if ((dev->priv_flags & IFF_UNICAST_FLT) && !ops->promisc_on_conduit) return; ASSERT_RTNL(); @@ -336,17 +336,17 @@ out: } static DEVICE_ATTR_RW(tagging); -static struct attribute *dsa_slave_attrs[] = { +static struct attribute *dsa_user_attrs[] = { &dev_attr_tagging.attr, NULL }; static const struct attribute_group dsa_group = { .name = "dsa", - .attrs = dsa_slave_attrs, + .attrs = dsa_user_attrs, }; -static void dsa_master_reset_mtu(struct net_device *dev) +static void dsa_conduit_reset_mtu(struct net_device *dev) { int err; @@ -356,7 +356,7 @@ static void dsa_master_reset_mtu(struct net_device *dev) "Unable to reset MTU to exclude DSA overheads\n"); } -int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) +int dsa_conduit_setup(struct net_device *dev, struct dsa_port *cpu_dp) { const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; @@ -365,7 +365,7 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); - /* The DSA master must use SET_NETDEV_DEV for this to work. */ + /* The DSA conduit must use SET_NETDEV_DEV for this to work. */ if (!netif_is_lag_master(dev)) { consumer_link = device_link_add(ds->dev, dev->dev.parent, DL_FLAG_AUTOREMOVE_CONSUMER); @@ -376,7 +376,7 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) } /* The switch driver may not implement ->port_change_mtu(), case in - * which dsa_slave_change_mtu() will not update the master MTU either, + * which dsa_user_change_mtu() will not update the conduit MTU either, * so we need to do that here. */ ret = dev_set_mtu(dev, mtu); @@ -392,9 +392,9 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) dev->dsa_ptr = cpu_dp; - dsa_master_set_promiscuity(dev, 1); + dsa_conduit_set_promiscuity(dev, 1); - ret = dsa_master_ethtool_setup(dev); + ret = dsa_conduit_ethtool_setup(dev); if (ret) goto out_err_reset_promisc; @@ -405,18 +405,18 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) return ret; out_err_ethtool_teardown: - dsa_master_ethtool_teardown(dev); + dsa_conduit_ethtool_teardown(dev); out_err_reset_promisc: - dsa_master_set_promiscuity(dev, -1); + dsa_conduit_set_promiscuity(dev, -1); return ret; } -void dsa_master_teardown(struct net_device *dev) +void dsa_conduit_teardown(struct net_device *dev) { sysfs_remove_group(&dev->dev.kobj, &dsa_group); - dsa_master_ethtool_teardown(dev); - dsa_master_reset_mtu(dev); - dsa_master_set_promiscuity(dev, -1); + dsa_conduit_ethtool_teardown(dev); + dsa_conduit_reset_mtu(dev); + dsa_conduit_set_promiscuity(dev, -1); dev->dsa_ptr = NULL; @@ -427,40 +427,40 @@ void dsa_master_teardown(struct net_device *dev) wmb(); } -int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, - struct netdev_lag_upper_info *uinfo, - struct netlink_ext_ack *extack) +int dsa_conduit_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack) { - bool master_setup = false; + bool conduit_setup = false; int err; if (!netdev_uses_dsa(lag_dev)) { - err = dsa_master_setup(lag_dev, cpu_dp); + err = dsa_conduit_setup(lag_dev, cpu_dp); if (err) return err; - master_setup = true; + conduit_setup = true; } err = dsa_port_lag_join(cpu_dp, lag_dev, uinfo, extack); if (err) { NL_SET_ERR_MSG_WEAK_MOD(extack, "CPU port failed to join LAG"); - goto out_master_teardown; + goto out_conduit_teardown; } return 0; -out_master_teardown: - if (master_setup) - dsa_master_teardown(lag_dev); +out_conduit_teardown: + if (conduit_setup) + dsa_conduit_teardown(lag_dev); return err; } -/* Tear down a master if there isn't any other user port on it, +/* Tear down a conduit if there isn't any other user port on it, * optionally also destroying LAG information. */ -void dsa_master_lag_teardown(struct net_device *lag_dev, - struct dsa_port *cpu_dp) +void dsa_conduit_lag_teardown(struct net_device *lag_dev, + struct dsa_port *cpu_dp) { struct net_device *upper; struct list_head *iter; @@ -468,8 +468,8 @@ void dsa_master_lag_teardown(struct net_device *lag_dev, dsa_port_lag_leave(cpu_dp, lag_dev); netdev_for_each_upper_dev_rcu(lag_dev, upper, iter) - if (dsa_slave_dev_check(upper)) + if (dsa_user_dev_check(upper)) return; - dsa_master_teardown(lag_dev); + dsa_conduit_teardown(lag_dev); } diff --git a/net/dsa/conduit.h b/net/dsa/conduit.h new file mode 100644 index 000000000000..31f8834f54bb --- /dev/null +++ b/net/dsa/conduit.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_CONDUIT_H +#define __DSA_CONDUIT_H + +struct dsa_port; +struct net_device; +struct netdev_lag_upper_info; +struct netlink_ext_ack; + +int dsa_conduit_setup(struct net_device *dev, struct dsa_port *cpu_dp); +void dsa_conduit_teardown(struct net_device *dev); +int dsa_conduit_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack); +void dsa_conduit_lag_teardown(struct net_device *lag_dev, + struct dsa_port *cpu_dp); +int __dsa_conduit_hwtstamp_validate(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); + +#endif diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index ccbdb98109f8..ac7be864e80d 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -20,14 +20,14 @@ #include <net/dsa_stubs.h> #include <net/sch_generic.h> +#include "conduit.h" #include "devlink.h" #include "dsa.h" -#include "master.h" #include "netlink.h" #include "port.h" -#include "slave.h" #include "switch.h" #include "tag.h" +#include "user.h" #define DSA_MAX_NUM_OFFLOADING_BRIDGES BITS_PER_LONG @@ -365,18 +365,18 @@ static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) return NULL; } -struct net_device *dsa_tree_find_first_master(struct dsa_switch_tree *dst) +struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst) { struct device_node *ethernet; - struct net_device *master; + struct net_device *conduit; struct dsa_port *cpu_dp; cpu_dp = dsa_tree_find_first_cpu(dst); ethernet = of_parse_phandle(cpu_dp->dn, "ethernet", 0); - master = of_find_net_device_by_node(ethernet); + conduit = of_find_net_device_by_node(ethernet); of_node_put(ethernet); - return master; + return conduit; } /* Assign the default CPU port (the first one in the tree) to all ports of the @@ -517,7 +517,7 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_USER: of_get_mac_address(dp->dn, dp->mac); - err = dsa_slave_create(dp); + err = dsa_user_create(dp); break; } @@ -554,9 +554,9 @@ static void dsa_port_teardown(struct dsa_port *dp) dsa_shared_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_USER: - if (dp->slave) { - dsa_slave_destroy(dp->slave); - dp->slave = NULL; + if (dp->user) { + dsa_user_destroy(dp->user); + dp->user = NULL; } break; } @@ -632,9 +632,9 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (ds->setup) return 0; - /* Initialize ds->phys_mii_mask before registering the slave MDIO bus + /* Initialize ds->phys_mii_mask before registering the user MDIO bus * driver and before ops->setup() has run, since the switch drivers and - * the slave MDIO bus driver rely on these values for probing PHY + * the user MDIO bus driver rely on these values for probing PHY * devices or not */ ds->phys_mii_mask |= dsa_user_ports(ds); @@ -657,21 +657,21 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (err) goto teardown; - if (!ds->slave_mii_bus && ds->ops->phy_read) { - ds->slave_mii_bus = mdiobus_alloc(); - if (!ds->slave_mii_bus) { + if (!ds->user_mii_bus && ds->ops->phy_read) { + ds->user_mii_bus = mdiobus_alloc(); + if (!ds->user_mii_bus) { err = -ENOMEM; goto teardown; } - dsa_slave_mii_bus_init(ds); + dsa_user_mii_bus_init(ds); dn = of_get_child_by_name(ds->dev->of_node, "mdio"); - err = of_mdiobus_register(ds->slave_mii_bus, dn); + err = of_mdiobus_register(ds->user_mii_bus, dn); of_node_put(dn); if (err < 0) - goto free_slave_mii_bus; + goto free_user_mii_bus; } dsa_switch_devlink_register(ds); @@ -679,9 +679,9 @@ static int dsa_switch_setup(struct dsa_switch *ds) ds->setup = true; return 0; -free_slave_mii_bus: - if (ds->slave_mii_bus && ds->ops->phy_read) - mdiobus_free(ds->slave_mii_bus); +free_user_mii_bus: + if (ds->user_mii_bus && ds->ops->phy_read) + mdiobus_free(ds->user_mii_bus); teardown: if (ds->ops->teardown) ds->ops->teardown(ds); @@ -699,10 +699,10 @@ static void dsa_switch_teardown(struct dsa_switch *ds) dsa_switch_devlink_unregister(ds); - if (ds->slave_mii_bus && ds->ops->phy_read) { - mdiobus_unregister(ds->slave_mii_bus); - mdiobus_free(ds->slave_mii_bus); - ds->slave_mii_bus = NULL; + if (ds->user_mii_bus && ds->ops->phy_read) { + mdiobus_unregister(ds->user_mii_bus); + mdiobus_free(ds->user_mii_bus); + ds->user_mii_bus = NULL; } dsa_switch_teardown_tag_protocol(ds); @@ -793,7 +793,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) return err; } -static int dsa_tree_setup_master(struct dsa_switch_tree *dst) +static int dsa_tree_setup_conduit(struct dsa_switch_tree *dst) { struct dsa_port *cpu_dp; int err = 0; @@ -801,18 +801,18 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) rtnl_lock(); dsa_tree_for_each_cpu_port(cpu_dp, dst) { - struct net_device *master = cpu_dp->master; - bool admin_up = (master->flags & IFF_UP) && - !qdisc_tx_is_noop(master); + struct net_device *conduit = cpu_dp->conduit; + bool admin_up = (conduit->flags & IFF_UP) && + !qdisc_tx_is_noop(conduit); - err = dsa_master_setup(master, cpu_dp); + err = dsa_conduit_setup(conduit, cpu_dp); if (err) break; - /* Replay master state event */ - dsa_tree_master_admin_state_change(dst, master, admin_up); - dsa_tree_master_oper_state_change(dst, master, - netif_oper_up(master)); + /* Replay conduit state event */ + dsa_tree_conduit_admin_state_change(dst, conduit, admin_up); + dsa_tree_conduit_oper_state_change(dst, conduit, + netif_oper_up(conduit)); } rtnl_unlock(); @@ -820,22 +820,22 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) return err; } -static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) +static void dsa_tree_teardown_conduit(struct dsa_switch_tree *dst) { struct dsa_port *cpu_dp; rtnl_lock(); dsa_tree_for_each_cpu_port(cpu_dp, dst) { - struct net_device *master = cpu_dp->master; + struct net_device *conduit = cpu_dp->conduit; /* Synthesizing an "admin down" state is sufficient for - * the switches to get a notification if the master is + * the switches to get a notification if the conduit is * currently up and running. */ - dsa_tree_master_admin_state_change(dst, master, false); + dsa_tree_conduit_admin_state_change(dst, conduit, false); - dsa_master_teardown(master); + dsa_conduit_teardown(conduit); } rtnl_unlock(); @@ -894,13 +894,13 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) if (err) goto teardown_switches; - err = dsa_tree_setup_master(dst); + err = dsa_tree_setup_conduit(dst); if (err) goto teardown_ports; err = dsa_tree_setup_lags(dst); if (err) - goto teardown_master; + goto teardown_conduit; dst->setup = true; @@ -908,8 +908,8 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) return 0; -teardown_master: - dsa_tree_teardown_master(dst); +teardown_conduit: + dsa_tree_teardown_conduit(dst); teardown_ports: dsa_tree_teardown_ports(dst); teardown_switches: @@ -929,7 +929,7 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_lags(dst); - dsa_tree_teardown_master(dst); + dsa_tree_teardown_conduit(dst); dsa_tree_teardown_ports(dst); @@ -978,7 +978,7 @@ out_disconnect: return err; } -/* Since the dsa/tagging sysfs device attribute is per master, the assumption +/* Since the dsa/tagging sysfs device attribute is per conduit, the assumption * is that all DSA switches within a tree share the same tagger, otherwise * they would have formed disjoint trees (different "dsa,member" values). */ @@ -999,10 +999,10 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, * restriction, there needs to be another mutex which serializes this. */ dsa_tree_for_each_user_port(dp, dst) { - if (dsa_port_to_master(dp)->flags & IFF_UP) + if (dsa_port_to_conduit(dp)->flags & IFF_UP) goto out_unlock; - if (dp->slave->flags & IFF_UP) + if (dp->user->flags & IFF_UP) goto out_unlock; } @@ -1028,62 +1028,62 @@ out_unlock: return err; } -static void dsa_tree_master_state_change(struct dsa_switch_tree *dst, - struct net_device *master) +static void dsa_tree_conduit_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit) { - struct dsa_notifier_master_state_info info; - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_notifier_conduit_state_info info; + struct dsa_port *cpu_dp = conduit->dsa_ptr; - info.master = master; - info.operational = dsa_port_master_is_operational(cpu_dp); + info.conduit = conduit; + info.operational = dsa_port_conduit_is_operational(cpu_dp); - dsa_tree_notify(dst, DSA_NOTIFIER_MASTER_STATE_CHANGE, &info); + dsa_tree_notify(dst, DSA_NOTIFIER_CONDUIT_STATE_CHANGE, &info); } -void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up) +void dsa_tree_conduit_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; bool notify = false; - /* Don't keep track of admin state on LAG DSA masters, - * but rather just of physical DSA masters + /* Don't keep track of admin state on LAG DSA conduits, + * but rather just of physical DSA conduits */ - if (netif_is_lag_master(master)) + if (netif_is_lag_master(conduit)) return; - if ((dsa_port_master_is_operational(cpu_dp)) != - (up && cpu_dp->master_oper_up)) + if ((dsa_port_conduit_is_operational(cpu_dp)) != + (up && cpu_dp->conduit_oper_up)) notify = true; - cpu_dp->master_admin_up = up; + cpu_dp->conduit_admin_up = up; if (notify) - dsa_tree_master_state_change(dst, master); + dsa_tree_conduit_state_change(dst, conduit); } -void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up) +void dsa_tree_conduit_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; bool notify = false; - /* Don't keep track of oper state on LAG DSA masters, - * but rather just of physical DSA masters + /* Don't keep track of oper state on LAG DSA conduits, + * but rather just of physical DSA conduits */ - if (netif_is_lag_master(master)) + if (netif_is_lag_master(conduit)) return; - if ((dsa_port_master_is_operational(cpu_dp)) != - (cpu_dp->master_admin_up && up)) + if ((dsa_port_conduit_is_operational(cpu_dp)) != + (cpu_dp->conduit_admin_up && up)) notify = true; - cpu_dp->master_oper_up = up; + cpu_dp->conduit_oper_up = up; if (notify) - dsa_tree_master_state_change(dst, master); + dsa_tree_conduit_state_change(dst, conduit); } static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) @@ -1129,7 +1129,7 @@ static int dsa_port_parse_dsa(struct dsa_port *dp) } static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, - struct net_device *master) + struct net_device *conduit) { enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE; struct dsa_switch *mds, *ds = dp->ds; @@ -1140,21 +1140,21 @@ static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, * happens the switch driver may want to know if its tagging protocol * is going to work in such a configuration. */ - if (dsa_slave_dev_check(master)) { - mdp = dsa_slave_to_port(master); + if (dsa_user_dev_check(conduit)) { + mdp = dsa_user_to_port(conduit); mds = mdp->ds; mdp_upstream = dsa_upstream_port(mds, mdp->index); tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream, DSA_TAG_PROTO_NONE); } - /* If the master device is not itself a DSA slave in a disjoint DSA + /* If the conduit device is not itself a DSA user in a disjoint DSA * tree, then return immediately. */ return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol); } -static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, +static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *conduit, const char *user_protocol) { const struct dsa_device_ops *tag_ops = NULL; @@ -1163,7 +1163,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, enum dsa_tag_protocol default_proto; /* Find out which protocol the switch would prefer. */ - default_proto = dsa_get_tag_protocol(dp, master); + default_proto = dsa_get_tag_protocol(dp, conduit); if (dst->default_proto) { if (dst->default_proto != default_proto) { dev_err(ds->dev, @@ -1218,7 +1218,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, dst->tag_ops = tag_ops; } - dp->master = master; + dp->conduit = conduit; dp->type = DSA_PORT_TYPE_CPU; dsa_port_set_tag_protocol(dp, dst->tag_ops); dp->dst = dst; @@ -1248,16 +1248,16 @@ static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) dp->dn = dn; if (ethernet) { - struct net_device *master; + struct net_device *conduit; const char *user_protocol; - master = of_find_net_device_by_node(ethernet); + conduit = of_find_net_device_by_node(ethernet); of_node_put(ethernet); - if (!master) + if (!conduit) return -EPROBE_DEFER; user_protocol = of_get_property(dn, "dsa-tag-protocol", NULL); - return dsa_port_parse_cpu(dp, master, user_protocol); + return dsa_port_parse_cpu(dp, conduit, user_protocol); } if (link) @@ -1412,15 +1412,15 @@ static int dsa_port_parse(struct dsa_port *dp, const char *name, struct device *dev) { if (!strcmp(name, "cpu")) { - struct net_device *master; + struct net_device *conduit; - master = dsa_dev_to_net_device(dev); - if (!master) + conduit = dsa_dev_to_net_device(dev); + if (!conduit) return -EPROBE_DEFER; - dev_put(master); + dev_put(conduit); - return dsa_port_parse_cpu(dp, master, NULL); + return dsa_port_parse_cpu(dp, conduit, NULL); } if (!strcmp(name, "dsa")) @@ -1566,14 +1566,14 @@ void dsa_unregister_switch(struct dsa_switch *ds) } EXPORT_SYMBOL_GPL(dsa_unregister_switch); -/* If the DSA master chooses to unregister its net_device on .shutdown, DSA is +/* If the DSA conduit chooses to unregister its net_device on .shutdown, DSA is * blocking that operation from completion, due to the dev_hold taken inside - * netdev_upper_dev_link. Unlink the DSA slave interfaces from being uppers of - * the DSA master, so that the system can reboot successfully. + * netdev_upper_dev_link. Unlink the DSA user interfaces from being uppers of + * the DSA conduit, so that the system can reboot successfully. */ void dsa_switch_shutdown(struct dsa_switch *ds) { - struct net_device *master, *slave_dev; + struct net_device *conduit, *user_dev; struct dsa_port *dp; mutex_lock(&dsa2_mutex); @@ -1584,17 +1584,17 @@ void dsa_switch_shutdown(struct dsa_switch *ds) rtnl_lock(); dsa_switch_for_each_user_port(dp, ds) { - master = dsa_port_to_master(dp); - slave_dev = dp->slave; + conduit = dsa_port_to_conduit(dp); + user_dev = dp->user; - netdev_upper_dev_unlink(master, slave_dev); + netdev_upper_dev_unlink(conduit, user_dev); } - /* Disconnect from further netdevice notifiers on the master, + /* Disconnect from further netdevice notifiers on the conduit, * since netdev_uses_dsa() will now return false. */ dsa_switch_for_each_cpu_port(dp, ds) - dp->master->dsa_ptr = NULL; + dp->conduit->dsa_ptr = NULL; rtnl_unlock(); out: @@ -1605,7 +1605,7 @@ EXPORT_SYMBOL_GPL(dsa_switch_shutdown); #ifdef CONFIG_PM_SLEEP static bool dsa_port_is_initialized(const struct dsa_port *dp) { - return dp->type == DSA_PORT_TYPE_USER && dp->slave; + return dp->type == DSA_PORT_TYPE_USER && dp->user; } int dsa_switch_suspend(struct dsa_switch *ds) @@ -1613,12 +1613,12 @@ int dsa_switch_suspend(struct dsa_switch *ds) struct dsa_port *dp; int ret = 0; - /* Suspend slave network devices */ + /* Suspend user network devices */ dsa_switch_for_each_port(dp, ds) { if (!dsa_port_is_initialized(dp)) continue; - ret = dsa_slave_suspend(dp->slave); + ret = dsa_user_suspend(dp->user); if (ret) return ret; } @@ -1641,12 +1641,12 @@ int dsa_switch_resume(struct dsa_switch *ds) if (ret) return ret; - /* Resume slave network devices */ + /* Resume user network devices */ dsa_switch_for_each_port(dp, ds) { if (!dsa_port_is_initialized(dp)) continue; - ret = dsa_slave_resume(dp->slave); + ret = dsa_user_resume(dp->user); if (ret) return ret; } @@ -1658,10 +1658,10 @@ EXPORT_SYMBOL_GPL(dsa_switch_resume); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev) { - if (!netdev || !dsa_slave_dev_check(netdev)) + if (!netdev || !dsa_user_dev_check(netdev)) return ERR_PTR(-ENODEV); - return dsa_slave_to_port(netdev); + return dsa_user_to_port(netdev); } EXPORT_SYMBOL_GPL(dsa_port_from_netdev); @@ -1726,7 +1726,7 @@ bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, EXPORT_SYMBOL_GPL(dsa_mdb_present_in_other_db); static const struct dsa_stubs __dsa_stubs = { - .master_hwtstamp_validate = __dsa_master_hwtstamp_validate, + .conduit_hwtstamp_validate = __dsa_conduit_hwtstamp_validate, }; static void dsa_register_stubs(void) @@ -1748,7 +1748,7 @@ static int __init dsa_init_module(void) if (!dsa_owq) return -ENOMEM; - rc = dsa_slave_register_notifier(); + rc = dsa_user_register_notifier(); if (rc) goto register_notifier_fail; @@ -1763,7 +1763,7 @@ static int __init dsa_init_module(void) return 0; netlink_register_fail: - dsa_slave_unregister_notifier(); + dsa_user_unregister_notifier(); dev_remove_pack(&dsa_pack_type); register_notifier_fail: destroy_workqueue(dsa_owq); @@ -1778,7 +1778,7 @@ static void __exit dsa_cleanup_module(void) rtnl_link_unregister(&dsa_link_ops); - dsa_slave_unregister_notifier(); + dsa_user_unregister_notifier(); dev_remove_pack(&dsa_pack_type); destroy_workqueue(dsa_owq); } diff --git a/net/dsa/dsa.h b/net/dsa/dsa.h index b7e17ae1094d..3cc7823e9ef3 100644 --- a/net/dsa/dsa.h +++ b/net/dsa/dsa.h @@ -21,16 +21,16 @@ void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag); void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag); struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, const struct net_device *lag_dev); -struct net_device *dsa_tree_find_first_master(struct dsa_switch_tree *dst); +struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst); int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, const struct dsa_device_ops *tag_ops, const struct dsa_device_ops *old_tag_ops); -void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, - struct net_device *master, +void dsa_tree_conduit_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up); +void dsa_tree_conduit_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, bool up); -void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up); unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); void dsa_bridge_num_put(const struct net_device *bridge_dev, unsigned int bridge_num); diff --git a/net/dsa/master.h b/net/dsa/master.h deleted file mode 100644 index 76e39d3ec909..000000000000 --- a/net/dsa/master.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -#ifndef __DSA_MASTER_H -#define __DSA_MASTER_H - -struct dsa_port; -struct net_device; -struct netdev_lag_upper_info; -struct netlink_ext_ack; - -int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); -void dsa_master_teardown(struct net_device *dev); -int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, - struct netdev_lag_upper_info *uinfo, - struct netlink_ext_ack *extack); -void dsa_master_lag_teardown(struct net_device *lag_dev, - struct dsa_port *cpu_dp); -int __dsa_master_hwtstamp_validate(struct net_device *dev, - const struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack); - -#endif diff --git a/net/dsa/netlink.c b/net/dsa/netlink.c index bd4bbaf851de..1332e56349e5 100644 --- a/net/dsa/netlink.c +++ b/net/dsa/netlink.c @@ -5,10 +5,10 @@ #include <net/rtnetlink.h> #include "netlink.h" -#include "slave.h" +#include "user.h" static const struct nla_policy dsa_policy[IFLA_DSA_MAX + 1] = { - [IFLA_DSA_MASTER] = { .type = NLA_U32 }, + [IFLA_DSA_CONDUIT] = { .type = NLA_U32 }, }; static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], @@ -20,15 +20,15 @@ static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], if (!data) return 0; - if (data[IFLA_DSA_MASTER]) { - u32 ifindex = nla_get_u32(data[IFLA_DSA_MASTER]); - struct net_device *master; + if (data[IFLA_DSA_CONDUIT]) { + u32 ifindex = nla_get_u32(data[IFLA_DSA_CONDUIT]); + struct net_device *conduit; - master = __dev_get_by_index(dev_net(dev), ifindex); - if (!master) + conduit = __dev_get_by_index(dev_net(dev), ifindex); + if (!conduit) return -EINVAL; - err = dsa_slave_change_master(dev, master, extack); + err = dsa_user_change_conduit(dev, conduit, extack); if (err) return err; } @@ -38,15 +38,15 @@ static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], static size_t dsa_get_size(const struct net_device *dev) { - return nla_total_size(sizeof(u32)) + /* IFLA_DSA_MASTER */ + return nla_total_size(sizeof(u32)) + /* IFLA_DSA_CONDUIT */ 0; } static int dsa_fill_info(struct sk_buff *skb, const struct net_device *dev) { - struct net_device *master = dsa_slave_to_master(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); - if (nla_put_u32(skb, IFLA_DSA_MASTER, master->ifindex)) + if (nla_put_u32(skb, IFLA_DSA_CONDUIT, conduit->ifindex)) return -EMSGSIZE; return 0; diff --git a/net/dsa/port.c b/net/dsa/port.c index 6e0d000a97c4..c42dac87671b 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -14,9 +14,9 @@ #include "dsa.h" #include "port.h" -#include "slave.h" #include "switch.h" #include "tag_8021q.h" +#include "user.h" /** * dsa_port_notify - Notify the switching fabric of changes to a port @@ -289,7 +289,7 @@ static void dsa_port_reset_vlan_filtering(struct dsa_port *dp, } /* If the bridge was vlan_filtering, the bridge core doesn't trigger an - * event for changing vlan_filtering setting upon slave ports leaving + * event for changing vlan_filtering setting upon user ports leaving * it. That is a good thing, because that lets us handle it and also * handle the case where the switch's vlan_filtering setting is global * (not per port). When that happens, the correct moment to trigger the @@ -489,7 +489,7 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, .dp = dp, .extack = extack, }; - struct net_device *dev = dp->slave; + struct net_device *dev = dp->user; struct net_device *brport_dev; int err; @@ -514,8 +514,8 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, dp->bridge->tx_fwd_offload = info.tx_fwd_offload; err = switchdev_bridge_port_offload(brport_dev, dev, dp, - &dsa_slave_switchdev_notifier, - &dsa_slave_switchdev_blocking_notifier, + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier, dp->bridge->tx_fwd_offload, extack); if (err) goto out_rollback_unbridge; @@ -528,8 +528,8 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, out_rollback_unoffload: switchdev_bridge_port_unoffload(brport_dev, dp, - &dsa_slave_switchdev_notifier, - &dsa_slave_switchdev_blocking_notifier); + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier); dsa_flush_workqueue(); out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); @@ -547,8 +547,8 @@ void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br) return; switchdev_bridge_port_unoffload(brport_dev, dp, - &dsa_slave_switchdev_notifier, - &dsa_slave_switchdev_blocking_notifier); + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier); dsa_flush_workqueue(); } @@ -741,10 +741,10 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, */ if (vlan_filtering && dsa_port_is_user(dp)) { struct net_device *br = dsa_port_bridge_dev_get(dp); - struct net_device *upper_dev, *slave = dp->slave; + struct net_device *upper_dev, *user = dp->user; struct list_head *iter; - netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { + netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { struct bridge_vlan_info br_info; u16 vid; @@ -803,9 +803,9 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, if (!ds->ops->port_vlan_filtering) return -EOPNOTSUPP; - /* We are called from dsa_slave_switchdev_blocking_event(), + /* We are called from dsa_user_switchdev_blocking_event(), * which is not under rcu_read_lock(), unlike - * dsa_slave_switchdev_event(). + * dsa_user_switchdev_event(). */ rcu_read_lock(); apply = dsa_port_can_apply_vlan_filtering(dp, vlan_filtering, extack); @@ -827,24 +827,24 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, ds->vlan_filtering = vlan_filtering; dsa_switch_for_each_user_port(other_dp, ds) { - struct net_device *slave = other_dp->slave; + struct net_device *user = other_dp->user; /* We might be called in the unbind path, so not - * all slave devices might still be registered. + * all user devices might still be registered. */ - if (!slave) + if (!user) continue; - err = dsa_slave_manage_vlan_filtering(slave, - vlan_filtering); + err = dsa_user_manage_vlan_filtering(user, + vlan_filtering); if (err) goto restore; } } else { dp->vlan_filtering = vlan_filtering; - err = dsa_slave_manage_vlan_filtering(dp->slave, - vlan_filtering); + err = dsa_user_manage_vlan_filtering(dp->user, + vlan_filtering); if (err) goto restore; } @@ -863,7 +863,7 @@ restore: } /* This enforces legacy behavior for switch drivers which assume they can't - * receive VLAN configuration when enslaved to a bridge with vlan_filtering=0 + * receive VLAN configuration when joining a bridge with vlan_filtering=0 */ bool dsa_port_skip_vlan_configuration(struct dsa_port *dp) { @@ -1047,7 +1047,7 @@ int dsa_port_standalone_host_fdb_add(struct dsa_port *dp, int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, u16 vid) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_db db = { .type = DSA_DB_BRIDGE, .bridge = *dp->bridge, @@ -1057,12 +1057,12 @@ int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, if (!dp->ds->fdb_isolation) db.bridge.num = 0; - /* Avoid a call to __dev_set_promiscuity() on the master, which + /* Avoid a call to __dev_set_promiscuity() on the conduit, which * requires rtnl_lock(), since we can't guarantee that is held here, * and we can't take it either. */ - if (master->priv_flags & IFF_UNICAST_FLT) { - err = dev_uc_add(master, addr); + if (conduit->priv_flags & IFF_UNICAST_FLT) { + err = dev_uc_add(conduit, addr); if (err) return err; } @@ -1098,7 +1098,7 @@ int dsa_port_standalone_host_fdb_del(struct dsa_port *dp, int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_db db = { .type = DSA_DB_BRIDGE, .bridge = *dp->bridge, @@ -1108,8 +1108,8 @@ int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, if (!dp->ds->fdb_isolation) db.bridge.num = 0; - if (master->priv_flags & IFF_UNICAST_FLT) { - err = dev_uc_del(master, addr); + if (conduit->priv_flags & IFF_UNICAST_FLT) { + err = dev_uc_del(conduit, addr); if (err) return err; } @@ -1229,7 +1229,7 @@ int dsa_port_standalone_host_mdb_add(const struct dsa_port *dp, int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_db db = { .type = DSA_DB_BRIDGE, .bridge = *dp->bridge, @@ -1239,7 +1239,7 @@ int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp, if (!dp->ds->fdb_isolation) db.bridge.num = 0; - err = dev_mc_add(master, mdb->addr); + err = dev_mc_add(conduit, mdb->addr); if (err) return err; @@ -1273,7 +1273,7 @@ int dsa_port_standalone_host_mdb_del(const struct dsa_port *dp, int dsa_port_bridge_host_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_db db = { .type = DSA_DB_BRIDGE, .bridge = *dp->bridge, @@ -1283,7 +1283,7 @@ int dsa_port_bridge_host_mdb_del(const struct dsa_port *dp, if (!dp->ds->fdb_isolation) db.bridge.num = 0; - err = dev_mc_del(master, mdb->addr); + err = dev_mc_del(conduit, mdb->addr); if (err) return err; @@ -1318,7 +1318,7 @@ int dsa_port_host_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_notifier_vlan_info info = { .dp = dp, .vlan = vlan, @@ -1330,7 +1330,7 @@ int dsa_port_host_vlan_add(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - vlan_vid_add(master, htons(ETH_P_8021Q), vlan->vid); + vlan_vid_add(conduit, htons(ETH_P_8021Q), vlan->vid); return err; } @@ -1338,7 +1338,7 @@ int dsa_port_host_vlan_add(struct dsa_port *dp, int dsa_port_host_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_notifier_vlan_info info = { .dp = dp, .vlan = vlan, @@ -1349,7 +1349,7 @@ int dsa_port_host_vlan_del(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - vlan_vid_del(master, htons(ETH_P_8021Q), vlan->vid); + vlan_vid_del(conduit, htons(ETH_P_8021Q), vlan->vid); return err; } @@ -1398,24 +1398,24 @@ int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, return ds->ops->port_mrp_del_ring_role(ds, dp->index, mrp); } -static int dsa_port_assign_master(struct dsa_port *dp, - struct net_device *master, - struct netlink_ext_ack *extack, - bool fail_on_err) +static int dsa_port_assign_conduit(struct dsa_port *dp, + struct net_device *conduit, + struct netlink_ext_ack *extack, + bool fail_on_err) { struct dsa_switch *ds = dp->ds; int port = dp->index, err; - err = ds->ops->port_change_master(ds, port, master, extack); + err = ds->ops->port_change_conduit(ds, port, conduit, extack); if (err && !fail_on_err) - dev_err(ds->dev, "port %d failed to assign master %s: %pe\n", - port, master->name, ERR_PTR(err)); + dev_err(ds->dev, "port %d failed to assign conduit %s: %pe\n", + port, conduit->name, ERR_PTR(err)); if (err && fail_on_err) return err; - dp->cpu_dp = master->dsa_ptr; - dp->cpu_port_in_lag = netif_is_lag_master(master); + dp->cpu_dp = conduit->dsa_ptr; + dp->cpu_port_in_lag = netif_is_lag_master(conduit); return 0; } @@ -1428,12 +1428,12 @@ static int dsa_port_assign_master(struct dsa_port *dp, * the old CPU port before changing it, and restore it on errors during the * bringup of the new one. */ -int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, - struct netlink_ext_ack *extack) +int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit, + struct netlink_ext_ack *extack) { struct net_device *bridge_dev = dsa_port_bridge_dev_get(dp); - struct net_device *old_master = dsa_port_to_master(dp); - struct net_device *dev = dp->slave; + struct net_device *old_conduit = dsa_port_to_conduit(dp); + struct net_device *dev = dp->user; struct dsa_switch *ds = dp->ds; bool vlan_filtering; int err, tmp; @@ -1454,7 +1454,7 @@ int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, */ vlan_filtering = dsa_port_is_vlan_filtering(dp); if (vlan_filtering) { - err = dsa_slave_manage_vlan_filtering(dev, false); + err = dsa_user_manage_vlan_filtering(dev, false); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to remove standalone VLANs"); @@ -1465,16 +1465,16 @@ int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, /* Standalone addresses, and addresses of upper interfaces like * VLAN, LAG, HSR need to be migrated. */ - dsa_slave_unsync_ha(dev); + dsa_user_unsync_ha(dev); - err = dsa_port_assign_master(dp, master, extack, true); + err = dsa_port_assign_conduit(dp, conduit, extack, true); if (err) goto rewind_old_addrs; - dsa_slave_sync_ha(dev); + dsa_user_sync_ha(dev); if (vlan_filtering) { - err = dsa_slave_manage_vlan_filtering(dev, true); + err = dsa_user_manage_vlan_filtering(dev, true); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to restore standalone VLANs"); @@ -1495,19 +1495,19 @@ int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, rewind_new_vlan: if (vlan_filtering) - dsa_slave_manage_vlan_filtering(dev, false); + dsa_user_manage_vlan_filtering(dev, false); rewind_new_addrs: - dsa_slave_unsync_ha(dev); + dsa_user_unsync_ha(dev); - dsa_port_assign_master(dp, old_master, NULL, false); + dsa_port_assign_conduit(dp, old_conduit, NULL, false); /* Restore the objects on the old CPU port */ rewind_old_addrs: - dsa_slave_sync_ha(dev); + dsa_user_sync_ha(dev); if (vlan_filtering) { - tmp = dsa_slave_manage_vlan_filtering(dev, true); + tmp = dsa_user_manage_vlan_filtering(dev, true); if (tmp) { dev_err(ds->dev, "port %d failed to restore standalone VLANs: %pe\n", @@ -1620,7 +1620,7 @@ static void dsa_port_phylink_mac_link_down(struct phylink_config *config, struct dsa_switch *ds = dp->ds; if (dsa_port_is_user(dp)) - phydev = dp->slave->phydev; + phydev = dp->user->phydev; if (!ds->ops->phylink_mac_link_down) { if (ds->ops->adjust_link && phydev) @@ -1808,7 +1808,7 @@ err_phy_connect: * their type. * * User ports with no phy-handle or fixed-link are expected to connect to an - * internal PHY located on the ds->slave_mii_bus at an MDIO address equal to + * internal PHY located on the ds->user_mii_bus at an MDIO address equal to * the port number. This description is still actively supported. * * Shared (CPU and DSA) ports with no phy-handle or fixed-link are expected to @@ -1829,7 +1829,7 @@ err_phy_connect: * a fixed-link, a phy-handle, or a managed = "in-band-status" property. * It becomes the responsibility of the driver to ensure that these ports * operate at the maximum speed (whatever this means) and will interoperate - * with the DSA master or other cascade port, since phylink methods will not be + * with the DSA conduit or other cascade port, since phylink methods will not be * invoked for them. * * If you are considering expanding this table for newly introduced switches, diff --git a/net/dsa/port.h b/net/dsa/port.h index 334879964e2c..6bc3291573c0 100644 --- a/net/dsa/port.h +++ b/net/dsa/port.h @@ -109,7 +109,7 @@ void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast); void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast); void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc); -int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, - struct netlink_ext_ack *extack); +int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit, + struct netlink_ext_ack *extack); #endif diff --git a/net/dsa/slave.h b/net/dsa/slave.h deleted file mode 100644 index d0abe609e00d..000000000000 --- a/net/dsa/slave.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -#ifndef __DSA_SLAVE_H -#define __DSA_SLAVE_H - -#include <linux/if_bridge.h> -#include <linux/if_vlan.h> -#include <linux/list.h> -#include <linux/netpoll.h> -#include <linux/types.h> -#include <net/dsa.h> -#include <net/gro_cells.h> - -struct net_device; -struct netlink_ext_ack; - -extern struct notifier_block dsa_slave_switchdev_notifier; -extern struct notifier_block dsa_slave_switchdev_blocking_notifier; - -struct dsa_slave_priv { - /* Copy of CPU port xmit for faster access in slave transmit hot path */ - struct sk_buff * (*xmit)(struct sk_buff *skb, - struct net_device *dev); - - struct gro_cells gcells; - - /* DSA port data, such as switch, port index, etc. */ - struct dsa_port *dp; - -#ifdef CONFIG_NET_POLL_CONTROLLER - struct netpoll *netpoll; -#endif - - /* TC context */ - struct list_head mall_tc_list; -}; - -void dsa_slave_mii_bus_init(struct dsa_switch *ds); -int dsa_slave_create(struct dsa_port *dp); -void dsa_slave_destroy(struct net_device *slave_dev); -int dsa_slave_suspend(struct net_device *slave_dev); -int dsa_slave_resume(struct net_device *slave_dev); -int dsa_slave_register_notifier(void); -void dsa_slave_unregister_notifier(void); -void dsa_slave_sync_ha(struct net_device *dev); -void dsa_slave_unsync_ha(struct net_device *dev); -void dsa_slave_setup_tagger(struct net_device *slave); -int dsa_slave_change_mtu(struct net_device *dev, int new_mtu); -int dsa_slave_change_master(struct net_device *dev, struct net_device *master, - struct netlink_ext_ack *extack); -int dsa_slave_manage_vlan_filtering(struct net_device *dev, - bool vlan_filtering); - -static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - - return p->dp; -} - -static inline struct net_device * -dsa_slave_to_master(const struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dsa_port_to_master(dp); -} - -#endif diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 1a42f9317334..3d2feeea897b 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -15,10 +15,10 @@ #include "dsa.h" #include "netlink.h" #include "port.h" -#include "slave.h" #include "switch.h" #include "tag_8021q.h" #include "trace.h" +#include "user.h" static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds, unsigned int ageing_time) @@ -894,12 +894,12 @@ static int dsa_switch_change_tag_proto(struct dsa_switch *ds, * bits that depend on the tagger, such as the MTU. */ dsa_switch_for_each_user_port(dp, ds) { - struct net_device *slave = dp->slave; + struct net_device *user = dp->user; - dsa_slave_setup_tagger(slave); + dsa_user_setup_tagger(user); /* rtnl_mutex is held in dsa_tree_change_tag_proto */ - dsa_slave_change_mtu(slave, slave->mtu); + dsa_user_change_mtu(user, user->mtu); } return 0; @@ -960,13 +960,13 @@ dsa_switch_disconnect_tag_proto(struct dsa_switch *ds, } static int -dsa_switch_master_state_change(struct dsa_switch *ds, - struct dsa_notifier_master_state_info *info) +dsa_switch_conduit_state_change(struct dsa_switch *ds, + struct dsa_notifier_conduit_state_info *info) { - if (!ds->ops->master_state_change) + if (!ds->ops->conduit_state_change) return 0; - ds->ops->master_state_change(ds, info->master, info->operational); + ds->ops->conduit_state_change(ds, info->conduit, info->operational); return 0; } @@ -1056,8 +1056,8 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL: err = dsa_switch_tag_8021q_vlan_del(ds, info); break; - case DSA_NOTIFIER_MASTER_STATE_CHANGE: - err = dsa_switch_master_state_change(ds, info); + case DSA_NOTIFIER_CONDUIT_STATE_CHANGE: + err = dsa_switch_conduit_state_change(ds, info); break; default: err = -EOPNOTSUPP; diff --git a/net/dsa/switch.h b/net/dsa/switch.h index ea034677da15..be0a2749cd97 100644 --- a/net/dsa/switch.h +++ b/net/dsa/switch.h @@ -34,7 +34,7 @@ enum { DSA_NOTIFIER_TAG_PROTO_DISCONNECT, DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, - DSA_NOTIFIER_MASTER_STATE_CHANGE, + DSA_NOTIFIER_CONDUIT_STATE_CHANGE, }; /* DSA_NOTIFIER_AGEING_TIME */ @@ -105,9 +105,9 @@ struct dsa_notifier_tag_8021q_vlan_info { u16 vid; }; -/* DSA_NOTIFIER_MASTER_STATE_CHANGE */ -struct dsa_notifier_master_state_info { - const struct net_device *master; +/* DSA_NOTIFIER_CONDUIT_STATE_CHANGE */ +struct dsa_notifier_conduit_state_info { + const struct net_device *conduit; bool operational; }; diff --git a/net/dsa/tag.c b/net/dsa/tag.c index 5105a5ff58fa..6e402d49afd3 100644 --- a/net/dsa/tag.c +++ b/net/dsa/tag.c @@ -13,8 +13,8 @@ #include <net/dsa.h> #include <net/dst_metadata.h> -#include "slave.h" #include "tag.h" +#include "user.h" static LIST_HEAD(dsa_tag_drivers_list); static DEFINE_MUTEX(dsa_tag_drivers_lock); @@ -27,7 +27,7 @@ static DEFINE_MUTEX(dsa_tag_drivers_lock); * switch, the DSA driver owning the interface to which the packet is * delivered is never notified unless we do so here. */ -static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p, +static bool dsa_skb_defer_rx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; @@ -57,7 +57,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dsa_port *cpu_dp = dev->dsa_ptr; struct sk_buff *nskb = NULL; - struct dsa_slave_priv *p; + struct dsa_user_priv *p; if (unlikely(!cpu_dp)) { kfree_skb(skb); @@ -75,7 +75,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb_has_extensions(skb)) skb->slow_gro = 0; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (likely(skb->dev)) { dsa_default_offload_fwd_mark(skb); nskb = skb; @@ -94,7 +94,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); - if (unlikely(!dsa_slave_dev_check(skb->dev))) { + if (unlikely(!dsa_user_dev_check(skb->dev))) { /* Packet is to be injected directly on an upper * device, e.g. a team/bond, so skip all DSA-port * specific actions. diff --git a/net/dsa/tag.h b/net/dsa/tag.h index 32d12f4a9d73..f6b9c73718df 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -9,7 +9,7 @@ #include <net/dsa.h> #include "port.h" -#include "slave.h" +#include "user.h" struct dsa_tag_driver { const struct dsa_device_ops *ops; @@ -29,7 +29,7 @@ static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) return ops->needed_headroom + ops->needed_tailroom; } -static inline struct net_device *dsa_master_find_slave(struct net_device *dev, +static inline struct net_device *dsa_conduit_find_user(struct net_device *dev, int device, int port) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -39,7 +39,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, list_for_each_entry(dp, &dst->ports, list) if (dp->ds->index == device && dp->index == port && dp->type == DSA_PORT_TYPE_USER) - return dp->slave; + return dp->user; return NULL; } @@ -49,7 +49,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, */ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct dsa_port *dp = dsa_user_to_port(skb->dev); struct net_device *br = dsa_port_bridge_dev_get(dp); struct net_device *dev = skb->dev; struct net_device *upper_dev; @@ -107,12 +107,12 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) * to support termination through the bridge. */ static inline struct net_device * -dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) +dsa_find_designated_bridge_port_by_vid(struct net_device *conduit, u16 vid) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct bridge_vlan_info vinfo; - struct net_device *slave; + struct net_device *user; struct dsa_port *dp; int err; @@ -134,13 +134,13 @@ dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) if (dp->cpu_dp != cpu_dp) continue; - slave = dp->slave; + user = dp->user; - err = br_vlan_get_info_rcu(slave, vid, &vinfo); + err = br_vlan_get_info_rcu(user, vid, &vinfo); if (err) continue; - return slave; + return user; } return NULL; @@ -155,7 +155,7 @@ dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) */ static inline void dsa_default_offload_fwd_mark(struct sk_buff *skb) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct dsa_port *dp = dsa_user_to_port(skb->dev); skb->offload_fwd_mark = !!(dp->bridge); } @@ -215,9 +215,9 @@ static inline void dsa_alloc_etype_header(struct sk_buff *skb, int len) memmove(skb->data, skb->data + len, 2 * ETH_ALEN); } -/* On RX, eth_type_trans() on the DSA master pulls ETH_HLEN bytes starting from +/* On RX, eth_type_trans() on the DSA conduit pulls ETH_HLEN bytes starting from * skb_mac_header(skb), which leaves skb->data pointing at the first byte after - * what the DSA master perceives as the EtherType (the beginning of the L3 + * what the DSA conduit perceives as the EtherType (the beginning of the L3 * protocol). Since DSA EtherType header taggers treat the EtherType as part of * the DSA tag itself, and the EtherType is 2 bytes in length, the DSA header * is located 2 bytes behind skb->data. Note that EtherType in this context diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index cbdfc392f7e0..71b26ae6db39 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -73,7 +73,7 @@ struct dsa_tag_8021q_vlan { struct dsa_8021q_context { struct dsa_switch *ds; struct list_head vlans; - /* EtherType of RX VID, used for filtering on master interface */ + /* EtherType of RX VID, used for filtering on conduit interface */ __be16 proto; }; @@ -338,7 +338,7 @@ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); u16 vid = dsa_tag_8021q_standalone_vid(dp); - struct net_device *master; + struct net_device *conduit; int err; /* The CPU port is implicitly configured by @@ -347,7 +347,7 @@ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) if (!dsa_port_is_user(dp)) return 0; - master = dsa_port_to_master(dp); + conduit = dsa_port_to_conduit(dp); err = dsa_port_tag_8021q_vlan_add(dp, vid, false); if (err) { @@ -357,8 +357,8 @@ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) return err; } - /* Add the VLAN to the master's RX filter. */ - vlan_vid_add(master, ctx->proto, vid); + /* Add the VLAN to the conduit's RX filter. */ + vlan_vid_add(conduit, ctx->proto, vid); return err; } @@ -368,7 +368,7 @@ static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); u16 vid = dsa_tag_8021q_standalone_vid(dp); - struct net_device *master; + struct net_device *conduit; /* The CPU port is implicitly configured by * configuring the front-panel ports @@ -376,11 +376,11 @@ static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) if (!dsa_port_is_user(dp)) return; - master = dsa_port_to_master(dp); + conduit = dsa_port_to_conduit(dp); dsa_port_tag_8021q_vlan_del(dp, vid, false); - vlan_vid_del(master, ctx->proto, vid); + vlan_vid_del(conduit, ctx->proto, vid); } static int dsa_tag_8021q_setup(struct dsa_switch *ds) @@ -468,10 +468,10 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); -struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, int vbid) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *dp; @@ -490,7 +490,7 @@ struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, continue; if (dsa_port_bridge_num_get(dp) == vbid) - return dp->slave; + return dp->user; } return NULL; diff --git a/net/dsa/tag_8021q.h b/net/dsa/tag_8021q.h index b75cbaa028ef..41f7167ac520 100644 --- a/net/dsa/tag_8021q.h +++ b/net/dsa/tag_8021q.h @@ -16,7 +16,7 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, int *vbid); -struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, int vbid); int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 7f3b7d730b85..92ce67b93a58 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -29,7 +29,7 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __le16 *phdr; u16 hdr; @@ -74,7 +74,7 @@ static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, /* Get source port information */ port = FIELD_GET(AR9331_HDR_PORT_NUM_MASK, hdr); - skb->dev = dsa_master_find_slave(ndev, 0, port); + skb->dev = dsa_conduit_find_user(ndev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index cacdafb41200..83d283a5d27e 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -85,7 +85,7 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, struct net_device *dev, unsigned int offset) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u16 queue = skb_get_queue_mapping(skb); u8 *brcm_tag; @@ -96,7 +96,7 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, * (including FCS and tag) because the length verification is done after * the Broadcom tag is stripped off the ingress packet. * - * Let dsa_slave_xmit() free the SKB + * Let dsa_user_xmit() free the SKB */ if (__skb_put_padto(skb, ETH_ZLEN + BRCM_TAG_LEN, false)) return NULL; @@ -119,7 +119,7 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; brcm_tag[3] = (1 << dp->index) & BRCM_IG_DSTMAP1_MASK; - /* Now tell the master network device about the desired output queue + /* Now tell the conduit network device about the desired output queue * as well */ skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(dp->index, queue)); @@ -164,7 +164,7 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, /* Locate which port this is coming from */ source_port = brcm_tag[3] & BRCM_EG_PID_MASK; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; @@ -216,7 +216,7 @@ MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM, BRCM_NAME); static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 *brcm_tag; /* The Ethernet switch we are interfaced with needs packets to be at @@ -226,7 +226,7 @@ static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, * (including FCS and tag) because the length verification is done after * the Broadcom tag is stripped off the ingress packet. * - * Let dsa_slave_xmit() free the SKB + * Let dsa_user_xmit() free the SKB */ if (__skb_put_padto(skb, ETH_ZLEN + BRCM_LEG_TAG_LEN, false)) return NULL; @@ -264,7 +264,7 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 1fd7fa26db64..8ed52dd663ab 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -129,7 +129,7 @@ enum dsa_code { static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, u8 extra) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct net_device *br_dev; u8 tag_dev, tag_port; enum dsa_cmd cmd; @@ -267,14 +267,14 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, lag = dsa_lag_by_id(cpu_dp->dst, source_port + 1); skb->dev = lag ? lag->dev : NULL; } else { - skb->dev = dsa_master_find_slave(dev, source_device, + skb->dev = dsa_conduit_find_user(dev, source_device, source_port); } if (!skb->dev) return NULL; - /* When using LAG offload, skb->dev is not a DSA slave interface, + /* When using LAG offload, skb->dev is not a DSA user interface, * so we cannot call dsa_default_offload_fwd_mark and we need to * special-case it. */ diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index e279cd9057b0..3539141b5350 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -61,7 +61,7 @@ static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 *gswip_tag; skb_push(skb, GSWIP_TX_HEADER_LEN); @@ -89,7 +89,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, /* Get source port information */ port = (gswip_tag[7] & GSWIP_RX_SPPID_MASK) >> GSWIP_RX_SPPID_SHIFT; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index 03a1fb9c87a9..6e233cd0aa38 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -20,7 +20,7 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 *tag; /* Calculate checksums (if required) before adding the trailer tag to @@ -45,7 +45,7 @@ static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN; unsigned int port = tag[0] & 0x03; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) { netdev_warn_once(dev, "Failed to get source port: %d\n", port); return NULL; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 3632e47dea9e..9be341fa88f0 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -87,7 +87,7 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, struct net_device *dev, unsigned int port, unsigned int len) { - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; @@ -119,7 +119,7 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct ethhdr *hdr; u8 *tag; @@ -256,7 +256,7 @@ static struct sk_buff *ksz_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) return NULL; kthread_init_work(&xmit_work->work, xmit_work_fn); - /* Increase refcount so the kfree_skb in dsa_slave_xmit + /* Increase refcount so the kfree_skb in dsa_user_xmit * won't really free the packet. */ xmit_work->dp = dp; @@ -272,7 +272,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, { u16 queue_mapping = skb_get_queue_mapping(skb); u8 prio = netdev_txq_to_tc(dev, queue_mapping); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct ethhdr *hdr; __be16 *tag; u16 val; @@ -344,7 +344,7 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, { u16 queue_mapping = skb_get_queue_mapping(skb); u8 prio = netdev_txq_to_tc(dev, queue_mapping); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct ethhdr *hdr; u8 *tag; @@ -410,7 +410,7 @@ static struct sk_buff *lan937x_xmit(struct sk_buff *skb, { u16 queue_mapping = skb_get_queue_mapping(skb); u8 prio = netdev_txq_to_tc(dev, queue_mapping); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); const struct ethhdr *hdr = eth_hdr(skb); __be16 *tag; u16 val; diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index c25f5536706b..1ed8ee24855d 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -56,7 +56,7 @@ static int lan9303_xmit_use_arl(struct dsa_port *dp, u8 *dest_addr) static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __be16 *lan9303_tag; u16 tag; @@ -99,7 +99,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev) source_port = lan9303_tag1 & 0x3; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); return NULL; diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 40af80452747..2483785f6ab1 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -23,7 +23,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 xmit_tpid; u8 *mtk_tag; @@ -85,7 +85,7 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev) /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_none.c b/net/dsa/tag_none.c index d2fd179c4227..9a473624db50 100644 --- a/net/dsa/tag_none.c +++ b/net/dsa/tag_none.c @@ -12,8 +12,8 @@ #define NONE_NAME "none" -static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, - struct net_device *dev) +static struct sk_buff *dsa_user_notag_xmit(struct sk_buff *skb, + struct net_device *dev) { /* Just return the original SKB */ return skb; @@ -22,7 +22,7 @@ static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, static const struct dsa_device_ops none_ops = { .name = NONE_NAME, .proto = DSA_TAG_PROTO_NONE, - .xmit = dsa_slave_notag_xmit, + .xmit = dsa_user_notag_xmit, }; module_dsa_tag_driver(none_ops); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 20bf7074d5a6..ef2f8fffb2c7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -45,7 +45,7 @@ static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); struct dsa_switch *ds = dp->ds; u64 vlan_tci, tag_type; void *injection; @@ -79,7 +79,7 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); void *injection; ocelot_xmit_common(skb, netdev, cpu_to_be32(0x8880000a), &injection); @@ -91,7 +91,7 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, static struct sk_buff *seville_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); void *injection; ocelot_xmit_common(skb, netdev, cpu_to_be32(0x88800005), &injection); @@ -111,12 +111,12 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, u16 vlan_tpid; u64 rew_val; - /* Revert skb->data by the amount consumed by the DSA master, + /* Revert skb->data by the amount consumed by the DSA conduit, * so it points to the beginning of the frame. */ skb_push(skb, ETH_HLEN); /* We don't care about the short prefix, it is just for easy entrance - * into the DSA master's RX filter. Discard it now by moving it into + * into the DSA conduit's RX filter. Discard it now by moving it into * the headroom. */ skb_pull(skb, OCELOT_SHORT_PREFIX_LEN); @@ -141,12 +141,12 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, ocelot_xfh_get_vlan_tci(extraction, &vlan_tci); ocelot_xfh_get_rew_val(extraction, &rew_val); - skb->dev = dsa_master_find_slave(netdev, 0, src_port); + skb->dev = dsa_conduit_find_user(netdev, 0, src_port); if (!skb->dev) /* The switch will reflect back some frames sent through - * sockets opened on the bare DSA master. These will come back + * sockets opened on the bare DSA conduit. These will come back * with src_port equal to the index of the CPU port, for which - * there is no slave registered. So don't print any error + * there is no user registered. So don't print any error * message here (ignore and drop those frames). */ return NULL; @@ -170,7 +170,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, * equal to the pvid of the ingress port and should not be used for * processing. */ - dp = dsa_slave_to_port(skb->dev); + dp = dsa_user_to_port(skb->dev); vlan_tpid = tag_type ? ETH_P_8021AD : ETH_P_8021Q; if (dsa_port_is_vlan_filtering(dp) && @@ -192,7 +192,7 @@ static const struct dsa_device_ops ocelot_netdev_ops = { .xmit = ocelot_xmit, .rcv = ocelot_rcv, .needed_headroom = OCELOT_TOTAL_TAG_LEN, - .promisc_on_master = true, + .promisc_on_conduit = true, }; DSA_TAG_DRIVER(ocelot_netdev_ops); @@ -204,7 +204,7 @@ static const struct dsa_device_ops seville_netdev_ops = { .xmit = seville_xmit, .rcv = ocelot_rcv, .needed_headroom = OCELOT_TOTAL_TAG_LEN, - .promisc_on_master = true, + .promisc_on_conduit = true, }; DSA_TAG_DRIVER(seville_netdev_ops); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 1f0b8c20eba5..210039320888 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -37,8 +37,8 @@ static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, return NULL; /* PTP over IP packets need UDP checksumming. We may have inherited - * NETIF_F_HW_CSUM from the DSA master, but these packets are not sent - * through the DSA master, so calculate the checksum here. + * NETIF_F_HW_CSUM from the DSA conduit, but these packets are not sent + * through the DSA conduit, so calculate the checksum here. */ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) return NULL; @@ -49,7 +49,7 @@ static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, /* Calls felix_port_deferred_xmit in felix.c */ kthread_init_work(&xmit_work->work, xmit_work_fn); - /* Increase refcount so the kfree_skb in dsa_slave_xmit + /* Increase refcount so the kfree_skb in dsa_user_xmit * won't really free the packet. */ xmit_work->dp = dp; @@ -63,7 +63,7 @@ static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); @@ -83,7 +83,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, dsa_8021q_rcv(skb, &src_port, &switch_id, NULL); - skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); + skb->dev = dsa_conduit_find_user(netdev, switch_id, src_port); if (!skb->dev) return NULL; @@ -130,7 +130,7 @@ static const struct dsa_device_ops ocelot_8021q_netdev_ops = { .connect = ocelot_connect, .disconnect = ocelot_disconnect, .needed_headroom = VLAN_HLEN, - .promisc_on_master = true, + .promisc_on_conduit = true, }; MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index e5ff7c34e577..6514aa7993ce 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -14,7 +14,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __be16 *phdr; u16 hdr; @@ -78,7 +78,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) /* Get source port information */ port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, hdr); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; @@ -116,7 +116,7 @@ static const struct dsa_device_ops qca_netdev_ops = { .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, .needed_headroom = QCA_HDR_LEN, - .promisc_on_master = true, + .promisc_on_conduit = true, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index c327314b95e3..4da5bad1a7aa 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -36,7 +36,7 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __be16 *p; u8 *tag; u16 out; @@ -97,9 +97,9 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, } port = protport & 0xff; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) { - netdev_dbg(dev, "could not find slave for port %d\n", port); + netdev_dbg(dev, "could not find user for port %d\n", port); return NULL; } diff --git a/net/dsa/tag_rtl8_4.c b/net/dsa/tag_rtl8_4.c index 4f67834fd121..07e857debabf 100644 --- a/net/dsa/tag_rtl8_4.c +++ b/net/dsa/tag_rtl8_4.c @@ -103,7 +103,7 @@ static void rtl8_4_write_tag(struct sk_buff *skb, struct net_device *dev, void *tag) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __be16 tag16[RTL8_4_TAG_LEN / 2]; /* Set Realtek EtherType */ @@ -180,10 +180,10 @@ static int rtl8_4_read_tag(struct sk_buff *skb, struct net_device *dev, /* Parse TX (switch->CPU) */ port = FIELD_GET(RTL8_4_TX, ntohs(tag16[3])); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) { dev_warn_ratelimited(&dev->dev, - "could not find slave for port %d\n", + "could not find user for port %d\n", port); return -ENOENT; } diff --git a/net/dsa/tag_rzn1_a5psw.c b/net/dsa/tag_rzn1_a5psw.c index 437a6820ac42..2ce866b45615 100644 --- a/net/dsa/tag_rzn1_a5psw.c +++ b/net/dsa/tag_rzn1_a5psw.c @@ -39,7 +39,7 @@ struct a5psw_tag { static struct sk_buff *a5psw_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct a5psw_tag *ptag; u32 data2_val; @@ -90,7 +90,7 @@ static struct sk_buff *a5psw_tag_rcv(struct sk_buff *skb, port = FIELD_GET(A5PSW_CTRL_DATA_PORT, ntohs(tag->ctrl_data)); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index ade3eeb2f3e6..1fffe8c2b589 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -157,7 +157,7 @@ static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, return NULL; kthread_init_work(&xmit_work->work, xmit_work_fn); - /* Increase refcount so the kfree_skb in dsa_slave_xmit + /* Increase refcount so the kfree_skb in dsa_user_xmit * won't really free the packet. */ xmit_work->dp = dp; @@ -210,7 +210,7 @@ static u16 sja1105_xmit_tpid(struct dsa_port *dp) static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); unsigned int bridge_num = dsa_port_bridge_num_get(dp); struct net_device *br = dsa_port_bridge_dev_get(dp); u16 tx_vid; @@ -235,7 +235,7 @@ static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, /* Transform untagged control packets into pvid-tagged control packets so that * all packets sent by this tagger are VLAN-tagged and we can configure the - * switch to drop untagged packets coming from the DSA master. + * switch to drop untagged packets coming from the DSA conduit. */ static struct sk_buff *sja1105_pvid_tag_control_pkt(struct dsa_port *dp, struct sk_buff *skb, u8 pcp) @@ -266,7 +266,7 @@ static struct sk_buff *sja1105_pvid_tag_control_pkt(struct dsa_port *dp, static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); @@ -294,7 +294,7 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, struct net_device *netdev) { struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); @@ -383,7 +383,7 @@ static struct sk_buff * Buffer it until we get its meta frame. */ if (is_link_local) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct dsa_port *dp = dsa_user_to_port(skb->dev); struct sja1105_tagger_private *priv; struct dsa_switch *ds = dp->ds; @@ -396,7 +396,7 @@ static struct sk_buff if (priv->stampable_skb) { dev_err_ratelimited(ds->dev, "Expected meta frame, is %12llx " - "in the DSA master multicast filter?\n", + "in the DSA conduit multicast filter?\n", SJA1105_META_DMAC); kfree_skb(priv->stampable_skb); } @@ -417,7 +417,7 @@ static struct sk_buff * frame, which serves no further purpose). */ } else if (is_meta) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct dsa_port *dp = dsa_user_to_port(skb->dev); struct sja1105_tagger_private *priv; struct dsa_switch *ds = dp->ds; struct sk_buff *stampable_skb; @@ -550,7 +550,7 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, } if (source_port != -1 && switch_id != -1) - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + skb->dev = dsa_conduit_find_user(netdev, switch_id, source_port); else if (vbid >= 1) skb->dev = dsa_tag_8021q_find_port_by_vbid(netdev, vbid); else @@ -573,16 +573,16 @@ static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); struct sja1105_tagger_data *tagger_data; - struct net_device *master = skb->dev; + struct net_device *conduit = skb->dev; struct dsa_port *cpu_dp; struct dsa_switch *ds; int i; - cpu_dp = master->dsa_ptr; + cpu_dp = conduit->dsa_ptr; ds = dsa_switch_find(cpu_dp->dst->index, switch_id); if (!ds) { net_err_ratelimited("%s: cannot find switch id %d\n", - master->name, switch_id); + conduit->name, switch_id); return NULL; } @@ -649,7 +649,7 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, /* skb->len counts from skb->data, while start_of_padding * counts from the destination MAC address. Right now skb->data - * is still as set by the DSA master, so to trim away the + * is still as set by the DSA conduit, so to trim away the * padding and trailer we need to account for the fact that * skb->data points to skb_mac_header(skb) + ETH_HLEN. */ @@ -698,7 +698,7 @@ static struct sk_buff *sja1110_rcv(struct sk_buff *skb, else if (source_port == -1 || switch_id == -1) skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); else - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + skb->dev = dsa_conduit_find_user(netdev, switch_id, source_port); if (!skb->dev) { netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; @@ -778,7 +778,7 @@ static const struct dsa_device_ops sja1105_netdev_ops = { .disconnect = sja1105_disconnect, .needed_headroom = VLAN_HLEN, .flow_dissect = sja1105_flow_dissect, - .promisc_on_master = true, + .promisc_on_conduit = true, }; DSA_TAG_DRIVER(sja1105_netdev_ops); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 7361b9106382..1ebb25a8b140 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -14,7 +14,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 *trailer; trailer = skb_put(skb, 4); @@ -41,7 +41,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev) source_port = trailer[1] & 7; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c index af19969f9bc4..c9c163598ef2 100644 --- a/net/dsa/tag_xrs700x.c +++ b/net/dsa/tag_xrs700x.c @@ -13,7 +13,7 @@ static struct sk_buff *xrs700x_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *partner, *dp = dsa_slave_to_port(dev); + struct dsa_port *partner, *dp = dsa_user_to_port(dev); u8 *trailer; trailer = skb_put(skb, 1); @@ -39,7 +39,7 @@ static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev) if (source_port < 0) return NULL; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/slave.c b/net/dsa/user.c index 4c3e502d7e16..d438884a4eb0 100644 --- a/net/dsa/slave.c +++ b/net/dsa/user.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * net/dsa/slave.c - Slave device handling + * net/dsa/user.c - user device handling * Copyright (c) 2008-2009 Marvell Semiconductor */ @@ -23,13 +23,13 @@ #include <linux/netpoll.h> #include <linux/string.h> +#include "conduit.h" #include "dsa.h" -#include "port.h" -#include "master.h" #include "netlink.h" -#include "slave.h" +#include "port.h" #include "switch.h" #include "tag.h" +#include "user.h" struct dsa_switchdev_event_work { struct net_device *dev; @@ -79,13 +79,13 @@ static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) !ds->needs_standalone_vlan_filtering; } -static void dsa_slave_standalone_event_work(struct work_struct *work) +static void dsa_user_standalone_event_work(struct work_struct *work) { struct dsa_standalone_event_work *standalone_work = container_of(work, struct dsa_standalone_event_work, work); const unsigned char *addr = standalone_work->addr; struct net_device *dev = standalone_work->dev; - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_mdb mdb; struct dsa_switch *ds = dp->ds; u16 vid = standalone_work->vid; @@ -140,10 +140,10 @@ static void dsa_slave_standalone_event_work(struct work_struct *work) kfree(standalone_work); } -static int dsa_slave_schedule_standalone_work(struct net_device *dev, - enum dsa_standalone_event event, - const unsigned char *addr, - u16 vid) +static int dsa_user_schedule_standalone_work(struct net_device *dev, + enum dsa_standalone_event event, + const unsigned char *addr, + u16 vid) { struct dsa_standalone_event_work *standalone_work; @@ -151,7 +151,7 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev, if (!standalone_work) return -ENOMEM; - INIT_WORK(&standalone_work->work, dsa_slave_standalone_event_work); + INIT_WORK(&standalone_work->work, dsa_user_standalone_event_work); standalone_work->event = event; standalone_work->dev = dev; @@ -163,18 +163,18 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev, return 0; } -static int dsa_slave_host_vlan_rx_filtering(void *arg, int vid) +static int dsa_user_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; - return dsa_slave_schedule_standalone_work(ctx->dev, ctx->event, + return dsa_user_schedule_standalone_work(ctx->dev, ctx->event, ctx->addr, vid); } -static int dsa_slave_vlan_for_each(struct net_device *dev, - int (*cb)(void *arg, int vid), void *arg) +static int dsa_user_vlan_for_each(struct net_device *dev, + int (*cb)(void *arg, int vid), void *arg) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_vlan *v; int err; @@ -193,99 +193,99 @@ static int dsa_slave_vlan_for_each(struct net_device *dev, return 0; } -static int dsa_slave_sync_uc(struct net_device *dev, - const unsigned char *addr) +static int dsa_user_sync_uc(struct net_device *dev, + const unsigned char *addr) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_ADD, }; - dev_uc_add(master, addr); + dev_uc_add(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } -static int dsa_slave_unsync_uc(struct net_device *dev, - const unsigned char *addr) +static int dsa_user_unsync_uc(struct net_device *dev, + const unsigned char *addr) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_DEL, }; - dev_uc_del(master, addr); + dev_uc_del(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } -static int dsa_slave_sync_mc(struct net_device *dev, - const unsigned char *addr) +static int dsa_user_sync_mc(struct net_device *dev, + const unsigned char *addr) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_ADD, }; - dev_mc_add(master, addr); + dev_mc_add(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } -static int dsa_slave_unsync_mc(struct net_device *dev, - const unsigned char *addr) +static int dsa_user_unsync_mc(struct net_device *dev, + const unsigned char *addr) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_DEL, }; - dev_mc_del(master, addr); + dev_mc_del(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } -void dsa_slave_sync_ha(struct net_device *dev) +void dsa_user_sync_ha(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_mc_addr(ha, dev) - dsa_slave_sync_mc(dev, ha->addr); + dsa_user_sync_mc(dev, ha->addr); netdev_for_each_synced_uc_addr(ha, dev) - dsa_slave_sync_uc(dev, ha->addr); + dsa_user_sync_uc(dev, ha->addr); netif_addr_unlock_bh(dev); @@ -294,19 +294,19 @@ void dsa_slave_sync_ha(struct net_device *dev) dsa_flush_workqueue(); } -void dsa_slave_unsync_ha(struct net_device *dev) +void dsa_user_unsync_ha(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_uc_addr(ha, dev) - dsa_slave_unsync_uc(dev, ha->addr); + dsa_user_unsync_uc(dev, ha->addr); netdev_for_each_synced_mc_addr(ha, dev) - dsa_slave_unsync_mc(dev, ha->addr); + dsa_user_unsync_mc(dev, ha->addr); netif_addr_unlock_bh(dev); @@ -315,8 +315,8 @@ void dsa_slave_unsync_ha(struct net_device *dev) dsa_flush_workqueue(); } -/* slave mii_bus handling ***************************************************/ -static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) +/* user mii_bus handling ***************************************************/ +static int dsa_user_phy_read(struct mii_bus *bus, int addr, int reg) { struct dsa_switch *ds = bus->priv; @@ -326,7 +326,7 @@ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) return 0xffff; } -static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) +static int dsa_user_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) { struct dsa_switch *ds = bus->priv; @@ -336,35 +336,35 @@ static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) return 0; } -void dsa_slave_mii_bus_init(struct dsa_switch *ds) +void dsa_user_mii_bus_init(struct dsa_switch *ds) { - ds->slave_mii_bus->priv = (void *)ds; - ds->slave_mii_bus->name = "dsa slave smi"; - ds->slave_mii_bus->read = dsa_slave_phy_read; - ds->slave_mii_bus->write = dsa_slave_phy_write; - snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", + ds->user_mii_bus->priv = (void *)ds; + ds->user_mii_bus->name = "dsa user smi"; + ds->user_mii_bus->read = dsa_user_phy_read; + ds->user_mii_bus->write = dsa_user_phy_write; + snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", ds->dst->index, ds->index); - ds->slave_mii_bus->parent = ds->dev; - ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; + ds->user_mii_bus->parent = ds->dev; + ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; } -/* slave device handling ****************************************************/ -static int dsa_slave_get_iflink(const struct net_device *dev) +/* user device handling ****************************************************/ +static int dsa_user_get_iflink(const struct net_device *dev) { - return dsa_slave_to_master(dev)->ifindex; + return dsa_user_to_conduit(dev)->ifindex; } -static int dsa_slave_open(struct net_device *dev) +static int dsa_user_open(struct net_device *dev) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err; - err = dev_open(master, NULL); + err = dev_open(conduit, NULL); if (err < 0) { - netdev_err(dev, "failed to open master %s\n", master->name); + netdev_err(dev, "failed to open conduit %s\n", conduit->name); goto out; } @@ -374,8 +374,8 @@ static int dsa_slave_open(struct net_device *dev) goto out; } - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) { - err = dev_uc_add(master, dev->dev_addr); + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) { + err = dev_uc_add(conduit, dev->dev_addr); if (err < 0) goto del_host_addr; } @@ -387,8 +387,8 @@ static int dsa_slave_open(struct net_device *dev) return 0; del_unicast: - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) + dev_uc_del(conduit, dev->dev_addr); del_host_addr: if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); @@ -396,16 +396,16 @@ out: return err; } -static int dsa_slave_close(struct net_device *dev) +static int dsa_user_close(struct net_device *dev) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; dsa_port_disable_rt(dp); - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) + dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); @@ -413,43 +413,43 @@ static int dsa_slave_close(struct net_device *dev) return 0; } -static void dsa_slave_manage_host_flood(struct net_device *dev) +static void dsa_user_manage_host_flood(struct net_device *dev) { bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); bool uc = dev->flags & IFF_PROMISC; dsa_port_set_host_flood(dp, uc, mc); } -static void dsa_slave_change_rx_flags(struct net_device *dev, int change) +static void dsa_user_change_rx_flags(struct net_device *dev, int change) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (change & IFF_ALLMULTI) - dev_set_allmulti(master, + dev_set_allmulti(conduit, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) - dev_set_promiscuity(master, + dev_set_promiscuity(conduit, dev->flags & IFF_PROMISC ? 1 : -1); if (dsa_switch_supports_uc_filtering(ds) && dsa_switch_supports_mc_filtering(ds)) - dsa_slave_manage_host_flood(dev); + dsa_user_manage_host_flood(dev); } -static void dsa_slave_set_rx_mode(struct net_device *dev) +static void dsa_user_set_rx_mode(struct net_device *dev) { - __dev_mc_sync(dev, dsa_slave_sync_mc, dsa_slave_unsync_mc); - __dev_uc_sync(dev, dsa_slave_sync_uc, dsa_slave_unsync_uc); + __dev_mc_sync(dev, dsa_user_sync_mc, dsa_user_unsync_mc); + __dev_uc_sync(dev, dsa_user_sync_uc, dsa_user_unsync_uc); } -static int dsa_slave_set_mac_address(struct net_device *dev, void *a) +static int dsa_user_set_mac_address(struct net_device *dev, void *a) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct sockaddr *addr = a; int err; @@ -465,7 +465,7 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a) } /* If the port is down, the address isn't synced yet to hardware or - * to the DSA master, so there is nothing to change. + * to the DSA conduit, so there is nothing to change. */ if (!(dev->flags & IFF_UP)) goto out_change_dev_addr; @@ -476,14 +476,14 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a) return err; } - if (!ether_addr_equal(addr->sa_data, master->dev_addr)) { - err = dev_uc_add(master, addr->sa_data); + if (!ether_addr_equal(addr->sa_data, conduit->dev_addr)) { + err = dev_uc_add(conduit, addr->sa_data); if (err < 0) goto del_unicast; } - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) + dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); @@ -500,7 +500,7 @@ del_unicast: return err; } -struct dsa_slave_dump_ctx { +struct dsa_user_dump_ctx { struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; @@ -508,10 +508,10 @@ struct dsa_slave_dump_ctx { }; static int -dsa_slave_port_fdb_do_dump(const unsigned char *addr, u16 vid, - bool is_static, void *data) +dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, + bool is_static, void *data) { - struct dsa_slave_dump_ctx *dump = data; + struct dsa_user_dump_ctx *dump = data; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; @@ -552,12 +552,12 @@ nla_put_failure: } static int -dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, struct net_device *filter_dev, - int *idx) +dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, struct net_device *filter_dev, + int *idx) { - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_dump_ctx dump = { + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, @@ -565,15 +565,15 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, }; int err; - err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump); + err = dsa_port_fdb_dump(dp, dsa_user_port_fdb_do_dump, &dump); *idx = dump.idx; return err; } -static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; int port = p->dp->index; @@ -592,11 +592,11 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } -static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, - const struct switchdev_attr *attr, - struct netlink_ext_ack *extack) +static int dsa_user_port_attr_set(struct net_device *dev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); int ret; if (ctx && ctx != dp) @@ -663,13 +663,13 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, /* Must be called under rcu_read_lock() */ static int -dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave, - const struct switchdev_obj_port_vlan *vlan) +dsa_user_vlan_check_for_8021q_uppers(struct net_device *user, + const struct switchdev_obj_port_vlan *vlan) { struct net_device *upper_dev; struct list_head *iter; - netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { + netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { u16 vid; if (!is_vlan_dev(upper_dev)) @@ -683,11 +683,11 @@ dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave, return 0; } -static int dsa_slave_vlan_add(struct net_device *dev, - const struct switchdev_obj *obj, - struct netlink_ext_ack *extack) +static int dsa_user_vlan_add(struct net_device *dev, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; int err; @@ -703,7 +703,7 @@ static int dsa_slave_vlan_add(struct net_device *dev, */ if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); - err = dsa_slave_vlan_check_for_8021q_uppers(dev, vlan); + err = dsa_user_vlan_check_for_8021q_uppers(dev, vlan); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG_MOD(extack, @@ -718,11 +718,11 @@ static int dsa_slave_vlan_add(struct net_device *dev, /* Offload a VLAN installed on the bridge or on a foreign interface by * installing it as a VLAN towards the CPU port. */ -static int dsa_slave_host_vlan_add(struct net_device *dev, - const struct switchdev_obj *obj, - struct netlink_ext_ack *extack) +static int dsa_user_host_vlan_add(struct net_device *dev, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan; /* Do nothing if this is a software bridge */ @@ -744,11 +744,11 @@ static int dsa_slave_host_vlan_add(struct net_device *dev, return dsa_port_host_vlan_add(dp, &vlan, extack); } -static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, - const struct switchdev_obj *obj, - struct netlink_ext_ack *extack) +static int dsa_user_port_obj_add(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) @@ -769,9 +769,9 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) - err = dsa_slave_vlan_add(dev, obj, extack); + err = dsa_user_vlan_add(dev, obj, extack); else - err = dsa_slave_host_vlan_add(dev, obj, extack); + err = dsa_user_host_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) @@ -794,10 +794,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, return err; } -static int dsa_slave_vlan_del(struct net_device *dev, - const struct switchdev_obj *obj) +static int dsa_user_vlan_del(struct net_device *dev, + const struct switchdev_obj *obj) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; if (dsa_port_skip_vlan_configuration(dp)) @@ -808,10 +808,10 @@ static int dsa_slave_vlan_del(struct net_device *dev, return dsa_port_vlan_del(dp, vlan); } -static int dsa_slave_host_vlan_del(struct net_device *dev, - const struct switchdev_obj *obj) +static int dsa_user_host_vlan_del(struct net_device *dev, + const struct switchdev_obj *obj) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; /* Do nothing if this is a software bridge */ @@ -826,10 +826,10 @@ static int dsa_slave_host_vlan_del(struct net_device *dev, return dsa_port_host_vlan_del(dp, vlan); } -static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, - const struct switchdev_obj *obj) +static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) @@ -850,9 +850,9 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) - err = dsa_slave_vlan_del(dev, obj); + err = dsa_user_vlan_del(dev, obj); else - err = dsa_slave_host_vlan_del(dev, obj); + err = dsa_user_host_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) @@ -875,11 +875,11 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, return err; } -static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, - struct sk_buff *skb) +static inline netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, + struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); return netpoll_send_skb(p->netpoll, skb); #else @@ -888,7 +888,7 @@ static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, #endif } -static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p, +static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; @@ -908,12 +908,12 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) - return dsa_slave_netpoll_send_skb(dev, skb); + return dsa_user_netpoll_send_skb(dev, skb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ - skb->dev = dsa_slave_to_master(dev); + skb->dev = dsa_user_to_conduit(dev); dev_queue_xmit(skb); return NETDEV_TX_OK; @@ -927,7 +927,7 @@ static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev) /* For tail taggers, we need to pad short frames ourselves, to ensure * that the tail tag does not fail at its role of being at the end of - * the packet, once the master interface pads the frame. Account for + * the packet, once the conduit interface pads the frame. Account for * that pad length here, and pad later. */ if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) @@ -944,9 +944,9 @@ static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev) GFP_ATOMIC); } -static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct sk_buff *nskb; dev_sw_netstats_tx_add(dev, 1, skb->len); @@ -981,17 +981,17 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) /* ethtool operations *******************************************************/ -static void dsa_slave_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *drvinfo) +static void dsa_user_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); strscpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strscpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } -static int dsa_slave_get_regs_len(struct net_device *dev) +static int dsa_user_get_regs_len(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) @@ -1001,25 +1001,25 @@ static int dsa_slave_get_regs_len(struct net_device *dev) } static void -dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) +dsa_user_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) ds->ops->get_regs(ds, dp->index, regs, _p); } -static int dsa_slave_nway_reset(struct net_device *dev) +static int dsa_user_nway_reset(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_nway_reset(dp->pl); } -static int dsa_slave_get_eeprom_len(struct net_device *dev) +static int dsa_user_get_eeprom_len(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) @@ -1031,10 +1031,10 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev) return 0; } -static int dsa_slave_get_eeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) +static int dsa_user_get_eeprom(struct net_device *dev, + struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) @@ -1043,10 +1043,10 @@ static int dsa_slave_get_eeprom(struct net_device *dev, return -EOPNOTSUPP; } -static int dsa_slave_set_eeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) +static int dsa_user_set_eeprom(struct net_device *dev, + struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) @@ -1055,10 +1055,10 @@ static int dsa_slave_set_eeprom(struct net_device *dev, return -EOPNOTSUPP; } -static void dsa_slave_get_strings(struct net_device *dev, - uint32_t stringset, uint8_t *data) +static void dsa_user_get_strings(struct net_device *dev, + uint32_t stringset, uint8_t *data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { @@ -1077,11 +1077,11 @@ static void dsa_slave_get_strings(struct net_device *dev, } -static void dsa_slave_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) +static void dsa_user_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; @@ -1107,9 +1107,9 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } -static int dsa_slave_get_sset_count(struct net_device *dev, int sset) +static int dsa_user_get_sset_count(struct net_device *dev, int sset) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { @@ -1129,20 +1129,20 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) return -EOPNOTSUPP; } -static void dsa_slave_get_eth_phy_stats(struct net_device *dev, - struct ethtool_eth_phy_stats *phy_stats) +static void dsa_user_get_eth_phy_stats(struct net_device *dev, + struct ethtool_eth_phy_stats *phy_stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_phy_stats) ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); } -static void dsa_slave_get_eth_mac_stats(struct net_device *dev, - struct ethtool_eth_mac_stats *mac_stats) +static void dsa_user_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_mac_stats) @@ -1150,10 +1150,10 @@ static void dsa_slave_get_eth_mac_stats(struct net_device *dev, } static void -dsa_slave_get_eth_ctrl_stats(struct net_device *dev, - struct ethtool_eth_ctrl_stats *ctrl_stats) +dsa_user_get_eth_ctrl_stats(struct net_device *dev, + struct ethtool_eth_ctrl_stats *ctrl_stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_ctrl_stats) @@ -1161,21 +1161,21 @@ dsa_slave_get_eth_ctrl_stats(struct net_device *dev, } static void -dsa_slave_get_rmon_stats(struct net_device *dev, - struct ethtool_rmon_stats *rmon_stats, - const struct ethtool_rmon_hist_range **ranges) +dsa_user_get_rmon_stats(struct net_device *dev, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_rmon_stats) ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } -static void dsa_slave_net_selftest(struct net_device *ndev, - struct ethtool_test *etest, u64 *buf) +static void dsa_user_net_selftest(struct net_device *ndev, + struct ethtool_test *etest, u64 *buf) { - struct dsa_port *dp = dsa_slave_to_port(ndev); + struct dsa_port *dp = dsa_user_to_port(ndev); struct dsa_switch *ds = dp->ds; if (ds->ops->self_test) { @@ -1186,10 +1186,10 @@ static void dsa_slave_net_selftest(struct net_device *ndev, net_selftest(ndev, etest, buf); } -static int dsa_slave_get_mm(struct net_device *dev, - struct ethtool_mm_state *state) +static int dsa_user_get_mm(struct net_device *dev, + struct ethtool_mm_state *state) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_mm) @@ -1198,10 +1198,10 @@ static int dsa_slave_get_mm(struct net_device *dev, return ds->ops->get_mm(ds, dp->index, state); } -static int dsa_slave_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, - struct netlink_ext_ack *extack) +static int dsa_user_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_mm) @@ -1210,19 +1210,19 @@ static int dsa_slave_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, return ds->ops->set_mm(ds, dp->index, cfg, extack); } -static void dsa_slave_get_mm_stats(struct net_device *dev, - struct ethtool_mm_stats *stats) +static void dsa_user_get_mm_stats(struct net_device *dev, + struct ethtool_mm_stats *stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_mm_stats) ds->ops->get_mm_stats(ds, dp->index, stats); } -static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) +static void dsa_user_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; phylink_ethtool_get_wol(dp->pl, w); @@ -1231,9 +1231,9 @@ static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) ds->ops->get_wol(ds, dp->index, w); } -static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) +static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; @@ -1245,9 +1245,9 @@ static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) return ret; } -static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) +static int dsa_user_set_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; @@ -1265,9 +1265,9 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) return phylink_ethtool_set_eee(dp->pl, e); } -static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) +static int dsa_user_get_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; @@ -1285,54 +1285,54 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) return phylink_ethtool_get_eee(dp->pl, e); } -static int dsa_slave_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) +static int dsa_user_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_get(dp->pl, cmd); } -static int dsa_slave_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) +static int dsa_user_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_set(dp->pl, cmd); } -static void dsa_slave_get_pause_stats(struct net_device *dev, - struct ethtool_pause_stats *pause_stats) +static void dsa_user_get_pause_stats(struct net_device *dev, + struct ethtool_pause_stats *pause_stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_pause_stats) ds->ops->get_pause_stats(ds, dp->index, pause_stats); } -static void dsa_slave_get_pauseparam(struct net_device *dev, - struct ethtool_pauseparam *pause) +static void dsa_user_get_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); phylink_ethtool_get_pauseparam(dp->pl, pause); } -static int dsa_slave_set_pauseparam(struct net_device *dev, - struct ethtool_pauseparam *pause) +static int dsa_user_set_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_set_pauseparam(dp->pl, pause); } #ifdef CONFIG_NET_POLL_CONTROLLER -static int dsa_slave_netpoll_setup(struct net_device *dev, - struct netpoll_info *ni) +static int dsa_user_netpoll_setup(struct net_device *dev, + struct netpoll_info *ni) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_slave_priv *p = netdev_priv(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll; int err = 0; @@ -1340,7 +1340,7 @@ static int dsa_slave_netpoll_setup(struct net_device *dev, if (!netpoll) return -ENOMEM; - err = __netpoll_setup(netpoll, master); + err = __netpoll_setup(netpoll, conduit); if (err) { kfree(netpoll); goto out; @@ -1351,9 +1351,9 @@ out: return err; } -static void dsa_slave_netpoll_cleanup(struct net_device *dev) +static void dsa_user_netpoll_cleanup(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll = p->netpoll; if (!netpoll) @@ -1364,15 +1364,15 @@ static void dsa_slave_netpoll_cleanup(struct net_device *dev) __netpoll_free(netpoll); } -static void dsa_slave_poll_controller(struct net_device *dev) +static void dsa_user_poll_controller(struct net_device *dev) { } #endif static struct dsa_mall_tc_entry * -dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) +dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) @@ -1383,13 +1383,13 @@ dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) } static int -dsa_slave_add_cls_matchall_mirred(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) +dsa_user_add_cls_matchall_mirred(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_mirror_tc_entry *mirror; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; @@ -1409,7 +1409,7 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, if (!act->dev) return -EINVAL; - if (!dsa_slave_dev_check(act->dev)) + if (!dsa_user_dev_check(act->dev)) return -EOPNOTSUPP; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); @@ -1420,7 +1420,7 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; - to_dp = dsa_slave_to_port(act->dev); + to_dp = dsa_user_to_port(act->dev); mirror->to_local_port = to_dp->index; mirror->ingress = ingress; @@ -1437,13 +1437,13 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, } static int -dsa_slave_add_cls_matchall_police(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) +dsa_user_add_cls_matchall_police(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_policer_tc_entry *policer; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; @@ -1497,31 +1497,31 @@ dsa_slave_add_cls_matchall_police(struct net_device *dev, return err; } -static int dsa_slave_add_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) +static int dsa_user_add_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) { int err = -EOPNOTSUPP; if (cls->common.protocol == htons(ETH_P_ALL) && flow_offload_has_one_action(&cls->rule->action) && cls->rule->action.entries[0].id == FLOW_ACTION_MIRRED) - err = dsa_slave_add_cls_matchall_mirred(dev, cls, ingress); + err = dsa_user_add_cls_matchall_mirred(dev, cls, ingress); else if (flow_offload_has_one_action(&cls->rule->action) && cls->rule->action.entries[0].id == FLOW_ACTION_POLICE) - err = dsa_slave_add_cls_matchall_police(dev, cls, ingress); + err = dsa_user_add_cls_matchall_police(dev, cls, ingress); return err; } -static void dsa_slave_del_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls) +static void dsa_user_del_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; - mall_tc_entry = dsa_slave_mall_tc_entry_find(dev, cls->cookie); + mall_tc_entry = dsa_user_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; @@ -1544,29 +1544,29 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, kfree(mall_tc_entry); } -static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) +static int dsa_user_setup_tc_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) { if (cls->common.chain_index) return -EOPNOTSUPP; switch (cls->command) { case TC_CLSMATCHALL_REPLACE: - return dsa_slave_add_cls_matchall(dev, cls, ingress); + return dsa_user_add_cls_matchall(dev, cls, ingress); case TC_CLSMATCHALL_DESTROY: - dsa_slave_del_cls_matchall(dev, cls); + dsa_user_del_cls_matchall(dev, cls); return 0; default: return -EOPNOTSUPP; } } -static int dsa_slave_add_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) +static int dsa_user_add_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -1576,11 +1576,11 @@ static int dsa_slave_add_cls_flower(struct net_device *dev, return ds->ops->cls_flower_add(ds, port, cls, ingress); } -static int dsa_slave_del_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) +static int dsa_user_del_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -1590,11 +1590,11 @@ static int dsa_slave_del_cls_flower(struct net_device *dev, return ds->ops->cls_flower_del(ds, port, cls, ingress); } -static int dsa_slave_stats_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) +static int dsa_user_stats_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -1604,24 +1604,24 @@ static int dsa_slave_stats_cls_flower(struct net_device *dev, return ds->ops->cls_flower_stats(ds, port, cls, ingress); } -static int dsa_slave_setup_tc_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) +static int dsa_user_setup_tc_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) { switch (cls->command) { case FLOW_CLS_REPLACE: - return dsa_slave_add_cls_flower(dev, cls, ingress); + return dsa_user_add_cls_flower(dev, cls, ingress); case FLOW_CLS_DESTROY: - return dsa_slave_del_cls_flower(dev, cls, ingress); + return dsa_user_del_cls_flower(dev, cls, ingress); case FLOW_CLS_STATS: - return dsa_slave_stats_cls_flower(dev, cls, ingress); + return dsa_user_stats_cls_flower(dev, cls, ingress); default: return -EOPNOTSUPP; } } -static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv, bool ingress) +static int dsa_user_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv, bool ingress) { struct net_device *dev = cb_priv; @@ -1630,46 +1630,46 @@ static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSMATCHALL: - return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress); + return dsa_user_setup_tc_cls_matchall(dev, type_data, ingress); case TC_SETUP_CLSFLOWER: - return dsa_slave_setup_tc_cls_flower(dev, type_data, ingress); + return dsa_user_setup_tc_cls_flower(dev, type_data, ingress); default: return -EOPNOTSUPP; } } -static int dsa_slave_setup_tc_block_cb_ig(enum tc_setup_type type, - void *type_data, void *cb_priv) +static int dsa_user_setup_tc_block_cb_ig(enum tc_setup_type type, + void *type_data, void *cb_priv) { - return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, true); + return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, true); } -static int dsa_slave_setup_tc_block_cb_eg(enum tc_setup_type type, - void *type_data, void *cb_priv) +static int dsa_user_setup_tc_block_cb_eg(enum tc_setup_type type, + void *type_data, void *cb_priv) { - return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, false); + return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, false); } -static LIST_HEAD(dsa_slave_block_cb_list); +static LIST_HEAD(dsa_user_block_cb_list); -static int dsa_slave_setup_tc_block(struct net_device *dev, - struct flow_block_offload *f) +static int dsa_user_setup_tc_block(struct net_device *dev, + struct flow_block_offload *f) { struct flow_block_cb *block_cb; flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) - cb = dsa_slave_setup_tc_block_cb_ig; + cb = dsa_user_setup_tc_block_cb_ig; else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) - cb = dsa_slave_setup_tc_block_cb_eg; + cb = dsa_user_setup_tc_block_cb_eg; else return -EOPNOTSUPP; - f->driver_block_list = &dsa_slave_block_cb_list; + f->driver_block_list = &dsa_user_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: - if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list)) + if (flow_block_cb_is_busy(cb, dev, &dsa_user_block_cb_list)) return -EBUSY; block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); @@ -1677,7 +1677,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, return PTR_ERR(block_cb); flow_block_cb_add(block_cb, f); - list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list); + list_add_tail(&block_cb->driver_list, &dsa_user_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: block_cb = flow_block_cb_lookup(f->block, cb, dev); @@ -1692,28 +1692,28 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, } } -static int dsa_slave_setup_ft_block(struct dsa_switch *ds, int port, - void *type_data) +static int dsa_user_setup_ft_block(struct dsa_switch *ds, int port, + void *type_data) { - struct net_device *master = dsa_port_to_master(dsa_to_port(ds, port)); + struct net_device *conduit = dsa_port_to_conduit(dsa_to_port(ds, port)); - if (!master->netdev_ops->ndo_setup_tc) + if (!conduit->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; - return master->netdev_ops->ndo_setup_tc(master, TC_SETUP_FT, type_data); + return conduit->netdev_ops->ndo_setup_tc(conduit, TC_SETUP_FT, type_data); } -static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, - void *type_data) +static int dsa_user_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; switch (type) { case TC_SETUP_BLOCK: - return dsa_slave_setup_tc_block(dev, type_data); + return dsa_user_setup_tc_block(dev, type_data); case TC_SETUP_FT: - return dsa_slave_setup_ft_block(ds, dp->index, type_data); + return dsa_user_setup_ft_block(ds, dp->index, type_data); default: break; } @@ -1724,10 +1724,10 @@ static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, return ds->ops->port_setup_tc(ds, dp->index, type, type_data); } -static int dsa_slave_get_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *nfc, u32 *rule_locs) +static int dsa_user_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *nfc, u32 *rule_locs) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) @@ -1736,10 +1736,10 @@ static int dsa_slave_get_rxnfc(struct net_device *dev, return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } -static int dsa_slave_set_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *nfc) +static int dsa_user_set_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *nfc) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) @@ -1748,10 +1748,10 @@ static int dsa_slave_set_rxnfc(struct net_device *dev, return ds->ops->set_rxnfc(ds, dp->index, nfc); } -static int dsa_slave_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *ts) +static int dsa_user_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *ts) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; if (!ds->ops->get_ts_info) @@ -1760,10 +1760,10 @@ static int dsa_slave_get_ts_info(struct net_device *dev, return ds->ops->get_ts_info(ds, p->dp->index, ts); } -static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, - u16 vid) +static int dsa_user_vlan_rx_add_vid(struct net_device *dev, __be16 proto, + u16 vid) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, @@ -1810,15 +1810,15 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { - dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, - ha->addr, vid); + dsa_user_schedule_standalone_work(dev, DSA_MC_ADD, + ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { - dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, - ha->addr, vid); + dsa_user_schedule_standalone_work(dev, DSA_UC_ADD, + ha->addr, vid); } } @@ -1835,10 +1835,10 @@ rollback: return ret; } -static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, - u16 vid) +static int dsa_user_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, + u16 vid) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ @@ -1874,15 +1874,15 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { - dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, - ha->addr, vid); + dsa_user_schedule_standalone_work(dev, DSA_MC_DEL, + ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { - dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, - ha->addr, vid); + dsa_user_schedule_standalone_work(dev, DSA_UC_DEL, + ha->addr, vid); } } @@ -1893,18 +1893,18 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, return 0; } -static int dsa_slave_restore_vlan(struct net_device *vdev, int vid, void *arg) +static int dsa_user_restore_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); - return dsa_slave_vlan_rx_add_vid(arg, proto, vid); + return dsa_user_vlan_rx_add_vid(arg, proto, vid); } -static int dsa_slave_clear_vlan(struct net_device *vdev, int vid, void *arg) +static int dsa_user_clear_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); - return dsa_slave_vlan_rx_kill_vid(arg, proto, vid); + return dsa_user_vlan_rx_kill_vid(arg, proto, vid); } /* Keep the VLAN RX filtering list in sync with the hardware only if VLAN @@ -1938,26 +1938,26 @@ static int dsa_slave_clear_vlan(struct net_device *vdev, int vid, void *arg) * - the bridge VLANs * - the 8021q upper VLANs */ -int dsa_slave_manage_vlan_filtering(struct net_device *slave, - bool vlan_filtering) +int dsa_user_manage_vlan_filtering(struct net_device *user, + bool vlan_filtering) { int err; if (vlan_filtering) { - slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - err = vlan_for_each(slave, dsa_slave_restore_vlan, slave); + err = vlan_for_each(user, dsa_user_restore_vlan, user); if (err) { - vlan_for_each(slave, dsa_slave_clear_vlan, slave); - slave->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + vlan_for_each(user, dsa_user_clear_vlan, user); + user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; return err; } } else { - err = vlan_for_each(slave, dsa_slave_clear_vlan, slave); + err = vlan_for_each(user, dsa_user_clear_vlan, user); if (err) return err; - slave->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; } return 0; @@ -2028,7 +2028,7 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) list_for_each_entry(dst, &dsa_tree_list, list) { list_for_each_entry(other_dp, &dst->ports, list) { struct dsa_hw_port *hw_port; - struct net_device *slave; + struct net_device *user; if (other_dp->type != DSA_PORT_TYPE_USER) continue; @@ -2039,17 +2039,17 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) if (!other_dp->ds->mtu_enforcement_ingress) continue; - slave = other_dp->slave; + user = other_dp->user; - if (min_mtu > slave->mtu) - min_mtu = slave->mtu; + if (min_mtu > user->mtu) + min_mtu = user->mtu; hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); if (!hw_port) goto out; - hw_port->dev = slave; - hw_port->old_mtu = slave->mtu; + hw_port->dev = user; + hw_port->old_mtu = user->mtu; list_add(&hw_port->list, &hw_port_list); } @@ -2059,7 +2059,7 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) * interface's MTU first, regardless of whether the intention of the * user was to raise or lower it. */ - err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->slave->mtu); + err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->user->mtu); if (!err) goto out; @@ -2073,16 +2073,16 @@ out: dsa_hw_port_list_free(&hw_port_list); } -int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) +int dsa_user_change_mtu(struct net_device *dev, int new_mtu) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_port *cpu_dp = dp->cpu_dp; struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int largest_mtu = 0; - int new_master_mtu; - int old_master_mtu; + int new_conduit_mtu; + int old_conduit_mtu; int mtu_limit; int overhead; int cpu_mtu; @@ -2092,44 +2092,44 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) return -EOPNOTSUPP; dsa_tree_for_each_user_port(other_dp, ds->dst) { - int slave_mtu; + int user_mtu; - /* During probe, this function will be called for each slave + /* During probe, this function will be called for each user * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ - if (!other_dp->slave) + if (!other_dp->user) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ if (dp == other_dp) - slave_mtu = new_mtu; + user_mtu = new_mtu; else - slave_mtu = other_dp->slave->mtu; + user_mtu = other_dp->user->mtu; - if (largest_mtu < slave_mtu) - largest_mtu = slave_mtu; + if (largest_mtu < user_mtu) + largest_mtu = user_mtu; } overhead = dsa_tag_protocol_overhead(cpu_dp->tag_ops); - mtu_limit = min_t(int, master->max_mtu, dev->max_mtu + overhead); - old_master_mtu = master->mtu; - new_master_mtu = largest_mtu + overhead; - if (new_master_mtu > mtu_limit) + mtu_limit = min_t(int, conduit->max_mtu, dev->max_mtu + overhead); + old_conduit_mtu = conduit->mtu; + new_conduit_mtu = largest_mtu + overhead; + if (new_conduit_mtu > mtu_limit) return -ERANGE; - /* If the master MTU isn't over limit, there's no need to check the CPU + /* If the conduit MTU isn't over limit, there's no need to check the CPU * MTU, since that surely isn't either. */ cpu_mtu = largest_mtu; /* Start applying stuff */ - if (new_master_mtu != old_master_mtu) { - err = dev_set_mtu(master, new_master_mtu); + if (new_conduit_mtu != old_conduit_mtu) { + err = dev_set_mtu(conduit, new_conduit_mtu); if (err < 0) - goto out_master_failed; + goto out_conduit_failed; /* We only need to propagate the MTU of the CPU port to * upstream switches, so emit a notifier which updates them. @@ -2150,19 +2150,19 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) return 0; out_port_failed: - if (new_master_mtu != old_master_mtu) - dsa_port_mtu_change(cpu_dp, old_master_mtu - overhead); + if (new_conduit_mtu != old_conduit_mtu) + dsa_port_mtu_change(cpu_dp, old_conduit_mtu - overhead); out_cpu_failed: - if (new_master_mtu != old_master_mtu) - dev_set_mtu(master, old_master_mtu); -out_master_failed: + if (new_conduit_mtu != old_conduit_mtu) + dev_set_mtu(conduit, old_conduit_mtu); +out_conduit_failed: return err; } static int __maybe_unused -dsa_slave_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) +dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; @@ -2187,9 +2187,9 @@ dsa_slave_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) } static int __maybe_unused -dsa_slave_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) +dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; @@ -2220,29 +2220,29 @@ dsa_slave_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) return 0; } -static int __maybe_unused dsa_slave_dcbnl_ieee_setapp(struct net_device *dev, - struct dcb_app *app) +static int __maybe_unused dsa_user_dcbnl_ieee_setapp(struct net_device *dev, + struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: - return dsa_slave_dcbnl_set_default_prio(dev, app); + return dsa_user_dcbnl_set_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: - return dsa_slave_dcbnl_add_dscp_prio(dev, app); + return dsa_user_dcbnl_add_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } static int __maybe_unused -dsa_slave_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) +dsa_user_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; @@ -2267,9 +2267,9 @@ dsa_slave_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) } static int __maybe_unused -dsa_slave_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) +dsa_user_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err, port = dp->index; u8 dscp = app->protocol; @@ -2290,20 +2290,20 @@ dsa_slave_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) return 0; } -static int __maybe_unused dsa_slave_dcbnl_ieee_delapp(struct net_device *dev, - struct dcb_app *app) +static int __maybe_unused dsa_user_dcbnl_ieee_delapp(struct net_device *dev, + struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: - return dsa_slave_dcbnl_del_default_prio(dev, app); + return dsa_user_dcbnl_del_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: - return dsa_slave_dcbnl_del_dscp_prio(dev, app); + return dsa_user_dcbnl_del_dscp_prio(dev, app); default: return -EOPNOTSUPP; } @@ -2312,9 +2312,9 @@ static int __maybe_unused dsa_slave_dcbnl_ieee_delapp(struct net_device *dev, /* Pre-populate the DCB application priority table with the priorities * configured during switch setup, which we read from hardware here. */ -static int dsa_slave_dcbnl_init(struct net_device *dev) +static int dsa_user_dcbnl_init(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; int err; @@ -2362,49 +2362,49 @@ static int dsa_slave_dcbnl_init(struct net_device *dev) return 0; } -static const struct ethtool_ops dsa_slave_ethtool_ops = { - .get_drvinfo = dsa_slave_get_drvinfo, - .get_regs_len = dsa_slave_get_regs_len, - .get_regs = dsa_slave_get_regs, - .nway_reset = dsa_slave_nway_reset, +static const struct ethtool_ops dsa_user_ethtool_ops = { + .get_drvinfo = dsa_user_get_drvinfo, + .get_regs_len = dsa_user_get_regs_len, + .get_regs = dsa_user_get_regs, + .nway_reset = dsa_user_nway_reset, .get_link = ethtool_op_get_link, - .get_eeprom_len = dsa_slave_get_eeprom_len, - .get_eeprom = dsa_slave_get_eeprom, - .set_eeprom = dsa_slave_set_eeprom, - .get_strings = dsa_slave_get_strings, - .get_ethtool_stats = dsa_slave_get_ethtool_stats, - .get_sset_count = dsa_slave_get_sset_count, - .get_eth_phy_stats = dsa_slave_get_eth_phy_stats, - .get_eth_mac_stats = dsa_slave_get_eth_mac_stats, - .get_eth_ctrl_stats = dsa_slave_get_eth_ctrl_stats, - .get_rmon_stats = dsa_slave_get_rmon_stats, - .set_wol = dsa_slave_set_wol, - .get_wol = dsa_slave_get_wol, - .set_eee = dsa_slave_set_eee, - .get_eee = dsa_slave_get_eee, - .get_link_ksettings = dsa_slave_get_link_ksettings, - .set_link_ksettings = dsa_slave_set_link_ksettings, - .get_pause_stats = dsa_slave_get_pause_stats, - .get_pauseparam = dsa_slave_get_pauseparam, - .set_pauseparam = dsa_slave_set_pauseparam, - .get_rxnfc = dsa_slave_get_rxnfc, - .set_rxnfc = dsa_slave_set_rxnfc, - .get_ts_info = dsa_slave_get_ts_info, - .self_test = dsa_slave_net_selftest, - .get_mm = dsa_slave_get_mm, - .set_mm = dsa_slave_set_mm, - .get_mm_stats = dsa_slave_get_mm_stats, + .get_eeprom_len = dsa_user_get_eeprom_len, + .get_eeprom = dsa_user_get_eeprom, + .set_eeprom = dsa_user_set_eeprom, + .get_strings = dsa_user_get_strings, + .get_ethtool_stats = dsa_user_get_ethtool_stats, + .get_sset_count = dsa_user_get_sset_count, + .get_eth_phy_stats = dsa_user_get_eth_phy_stats, + .get_eth_mac_stats = dsa_user_get_eth_mac_stats, + .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, + .get_rmon_stats = dsa_user_get_rmon_stats, + .set_wol = dsa_user_set_wol, + .get_wol = dsa_user_get_wol, + .set_eee = dsa_user_set_eee, + .get_eee = dsa_user_get_eee, + .get_link_ksettings = dsa_user_get_link_ksettings, + .set_link_ksettings = dsa_user_set_link_ksettings, + .get_pause_stats = dsa_user_get_pause_stats, + .get_pauseparam = dsa_user_get_pauseparam, + .set_pauseparam = dsa_user_set_pauseparam, + .get_rxnfc = dsa_user_get_rxnfc, + .set_rxnfc = dsa_user_set_rxnfc, + .get_ts_info = dsa_user_get_ts_info, + .self_test = dsa_user_net_selftest, + .get_mm = dsa_user_get_mm, + .set_mm = dsa_user_set_mm, + .get_mm_stats = dsa_user_get_mm_stats, }; -static const struct dcbnl_rtnl_ops __maybe_unused dsa_slave_dcbnl_ops = { - .ieee_setapp = dsa_slave_dcbnl_ieee_setapp, - .ieee_delapp = dsa_slave_dcbnl_ieee_delapp, +static const struct dcbnl_rtnl_ops __maybe_unused dsa_user_dcbnl_ops = { + .ieee_setapp = dsa_user_dcbnl_ieee_setapp, + .ieee_delapp = dsa_user_dcbnl_ieee_delapp, }; -static void dsa_slave_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *s) +static void dsa_user_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *s) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_stats64) @@ -2413,43 +2413,43 @@ static void dsa_slave_get_stats64(struct net_device *dev, dev_get_tstats64(dev, s); } -static int dsa_slave_fill_forward_path(struct net_device_path_ctx *ctx, - struct net_device_path *path) +static int dsa_user_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) { - struct dsa_port *dp = dsa_slave_to_port(ctx->dev); - struct net_device *master = dsa_port_to_master(dp); + struct dsa_port *dp = dsa_user_to_port(ctx->dev); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_port *cpu_dp = dp->cpu_dp; path->dev = ctx->dev; path->type = DEV_PATH_DSA; path->dsa.proto = cpu_dp->tag_ops->proto; path->dsa.port = dp->index; - ctx->dev = master; + ctx->dev = conduit; return 0; } -static const struct net_device_ops dsa_slave_netdev_ops = { - .ndo_open = dsa_slave_open, - .ndo_stop = dsa_slave_close, - .ndo_start_xmit = dsa_slave_xmit, - .ndo_change_rx_flags = dsa_slave_change_rx_flags, - .ndo_set_rx_mode = dsa_slave_set_rx_mode, - .ndo_set_mac_address = dsa_slave_set_mac_address, - .ndo_fdb_dump = dsa_slave_fdb_dump, - .ndo_eth_ioctl = dsa_slave_ioctl, - .ndo_get_iflink = dsa_slave_get_iflink, +static const struct net_device_ops dsa_user_netdev_ops = { + .ndo_open = dsa_user_open, + .ndo_stop = dsa_user_close, + .ndo_start_xmit = dsa_user_xmit, + .ndo_change_rx_flags = dsa_user_change_rx_flags, + .ndo_set_rx_mode = dsa_user_set_rx_mode, + .ndo_set_mac_address = dsa_user_set_mac_address, + .ndo_fdb_dump = dsa_user_fdb_dump, + .ndo_eth_ioctl = dsa_user_ioctl, + .ndo_get_iflink = dsa_user_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_netpoll_setup = dsa_slave_netpoll_setup, - .ndo_netpoll_cleanup = dsa_slave_netpoll_cleanup, - .ndo_poll_controller = dsa_slave_poll_controller, + .ndo_netpoll_setup = dsa_user_netpoll_setup, + .ndo_netpoll_cleanup = dsa_user_netpoll_cleanup, + .ndo_poll_controller = dsa_user_poll_controller, #endif - .ndo_setup_tc = dsa_slave_setup_tc, - .ndo_get_stats64 = dsa_slave_get_stats64, - .ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, - .ndo_change_mtu = dsa_slave_change_mtu, - .ndo_fill_forward_path = dsa_slave_fill_forward_path, + .ndo_setup_tc = dsa_user_setup_tc, + .ndo_get_stats64 = dsa_user_get_stats64, + .ndo_vlan_rx_add_vid = dsa_user_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = dsa_user_vlan_rx_kill_vid, + .ndo_change_mtu = dsa_user_change_mtu, + .ndo_fill_forward_path = dsa_user_fill_forward_path, }; static struct device_type dsa_type = { @@ -2465,8 +2465,8 @@ void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) } EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); -static void dsa_slave_phylink_fixed_state(struct phylink_config *config, - struct phylink_link_state *state) +static void dsa_user_phylink_fixed_state(struct phylink_config *config, + struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -2477,33 +2477,33 @@ static void dsa_slave_phylink_fixed_state(struct phylink_config *config, ds->ops->phylink_fixed_state(ds, dp->index, state); } -/* slave device setup *******************************************************/ -static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr, - u32 flags) +/* user device setup *******************************************************/ +static int dsa_user_phy_connect(struct net_device *user_dev, int addr, + u32 flags) { - struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_switch *ds = dp->ds; - slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); - if (!slave_dev->phydev) { - netdev_err(slave_dev, "no phy at %d\n", addr); + user_dev->phydev = mdiobus_get_phy(ds->user_mii_bus, addr); + if (!user_dev->phydev) { + netdev_err(user_dev, "no phy at %d\n", addr); return -ENODEV; } - slave_dev->phydev->dev_flags |= flags; + user_dev->phydev->dev_flags |= flags; - return phylink_connect_phy(dp->pl, slave_dev->phydev); + return phylink_connect_phy(dp->pl, user_dev->phydev); } -static int dsa_slave_phy_setup(struct net_device *slave_dev) +static int dsa_user_phy_setup(struct net_device *user_dev) { - struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; u32 phy_flags = 0; int ret; - dp->pl_config.dev = &slave_dev->dev; + dp->pl_config.dev = &user_dev->dev; dp->pl_config.type = PHYLINK_NETDEV; /* The get_fixed_state callback takes precedence over polling the @@ -2511,7 +2511,7 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) * this if the switch provides such a callback. */ if (ds->ops->phylink_fixed_state) { - dp->pl_config.get_fixed_state = dsa_slave_phylink_fixed_state; + dp->pl_config.get_fixed_state = dsa_user_phylink_fixed_state; dp->pl_config.poll_fixed_state = true; } @@ -2523,14 +2523,14 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) phy_flags = ds->ops->get_phy_flags(ds, dp->index); ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); - if (ret == -ENODEV && ds->slave_mii_bus) { + if (ret == -ENODEV && ds->user_mii_bus) { /* We could not connect to a designated PHY or SFP, so try to * use the switch internal MDIO bus instead */ - ret = dsa_slave_phy_connect(slave_dev, dp->index, phy_flags); + ret = dsa_user_phy_connect(user_dev, dp->index, phy_flags); } if (ret) { - netdev_err(slave_dev, "failed to connect to PHY: %pe\n", + netdev_err(user_dev, "failed to connect to PHY: %pe\n", ERR_PTR(ret)); dsa_port_phylink_destroy(dp); } @@ -2538,42 +2538,42 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } -void dsa_slave_setup_tagger(struct net_device *slave) +void dsa_user_setup_tagger(struct net_device *user) { - struct dsa_port *dp = dsa_slave_to_port(slave); - struct net_device *master = dsa_port_to_master(dp); - struct dsa_slave_priv *p = netdev_priv(slave); + struct dsa_port *dp = dsa_user_to_port(user); + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_user_priv *p = netdev_priv(user); const struct dsa_port *cpu_dp = dp->cpu_dp; const struct dsa_switch *ds = dp->ds; - slave->needed_headroom = cpu_dp->tag_ops->needed_headroom; - slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; - /* Try to save one extra realloc later in the TX path (in the master) - * by also inheriting the master's needed headroom and tailroom. + user->needed_headroom = cpu_dp->tag_ops->needed_headroom; + user->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; + /* Try to save one extra realloc later in the TX path (in the conduit) + * by also inheriting the conduit's needed headroom and tailroom. * The 8021q driver also does this. */ - slave->needed_headroom += master->needed_headroom; - slave->needed_tailroom += master->needed_tailroom; + user->needed_headroom += conduit->needed_headroom; + user->needed_tailroom += conduit->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; - slave->features = master->vlan_features | NETIF_F_HW_TC; - slave->hw_features |= NETIF_F_HW_TC; - slave->features |= NETIF_F_LLTX; - if (slave->needed_tailroom) - slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); + user->features = conduit->vlan_features | NETIF_F_HW_TC; + user->hw_features |= NETIF_F_HW_TC; + user->features |= NETIF_F_LLTX; + if (user->needed_tailroom) + user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); if (ds->needs_standalone_vlan_filtering) - slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } -int dsa_slave_suspend(struct net_device *slave_dev) +int dsa_user_suspend(struct net_device *user_dev) { - struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); - if (!netif_running(slave_dev)) + if (!netif_running(user_dev)) return 0; - netif_device_detach(slave_dev); + netif_device_detach(user_dev); rtnl_lock(); phylink_stop(dp->pl); @@ -2582,14 +2582,14 @@ int dsa_slave_suspend(struct net_device *slave_dev) return 0; } -int dsa_slave_resume(struct net_device *slave_dev) +int dsa_user_resume(struct net_device *user_dev) { - struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); - if (!netif_running(slave_dev)) + if (!netif_running(user_dev)) return 0; - netif_device_attach(slave_dev); + netif_device_attach(user_dev); rtnl_lock(); phylink_start(dp->pl); @@ -2598,12 +2598,12 @@ int dsa_slave_resume(struct net_device *slave_dev) return 0; } -int dsa_slave_create(struct dsa_port *port) +int dsa_user_create(struct dsa_port *port) { - struct net_device *master = dsa_port_to_master(port); + struct net_device *conduit = dsa_port_to_conduit(port); struct dsa_switch *ds = port->ds; - struct net_device *slave_dev; - struct dsa_slave_priv *p; + struct net_device *user_dev; + struct dsa_user_priv *p; const char *name; int assign_type; int ret; @@ -2619,55 +2619,55 @@ int dsa_slave_create(struct dsa_port *port) assign_type = NET_NAME_ENUM; } - slave_dev = alloc_netdev_mqs(sizeof(struct dsa_slave_priv), name, - assign_type, ether_setup, - ds->num_tx_queues, 1); - if (slave_dev == NULL) + user_dev = alloc_netdev_mqs(sizeof(struct dsa_user_priv), name, + assign_type, ether_setup, + ds->num_tx_queues, 1); + if (user_dev == NULL) return -ENOMEM; - slave_dev->rtnl_link_ops = &dsa_link_ops; - slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; + user_dev->rtnl_link_ops = &dsa_link_ops; + user_dev->ethtool_ops = &dsa_user_ethtool_ops; #if IS_ENABLED(CONFIG_DCB) - slave_dev->dcbnl_ops = &dsa_slave_dcbnl_ops; + user_dev->dcbnl_ops = &dsa_user_dcbnl_ops; #endif if (!is_zero_ether_addr(port->mac)) - eth_hw_addr_set(slave_dev, port->mac); + eth_hw_addr_set(user_dev, port->mac); else - eth_hw_addr_inherit(slave_dev, master); - slave_dev->priv_flags |= IFF_NO_QUEUE; + eth_hw_addr_inherit(user_dev, conduit); + user_dev->priv_flags |= IFF_NO_QUEUE; if (dsa_switch_supports_uc_filtering(ds)) - slave_dev->priv_flags |= IFF_UNICAST_FLT; - slave_dev->netdev_ops = &dsa_slave_netdev_ops; + user_dev->priv_flags |= IFF_UNICAST_FLT; + user_dev->netdev_ops = &dsa_user_netdev_ops; if (ds->ops->port_max_mtu) - slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); - SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); - - SET_NETDEV_DEV(slave_dev, port->ds->dev); - SET_NETDEV_DEVLINK_PORT(slave_dev, &port->devlink_port); - slave_dev->dev.of_node = port->dn; - slave_dev->vlan_features = master->vlan_features; - - p = netdev_priv(slave_dev); - slave_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!slave_dev->tstats) { - free_netdev(slave_dev); + user_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); + SET_NETDEV_DEVTYPE(user_dev, &dsa_type); + + SET_NETDEV_DEV(user_dev, port->ds->dev); + SET_NETDEV_DEVLINK_PORT(user_dev, &port->devlink_port); + user_dev->dev.of_node = port->dn; + user_dev->vlan_features = conduit->vlan_features; + + p = netdev_priv(user_dev); + user_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!user_dev->tstats) { + free_netdev(user_dev); return -ENOMEM; } - ret = gro_cells_init(&p->gcells, slave_dev); + ret = gro_cells_init(&p->gcells, user_dev); if (ret) goto out_free; p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); - port->slave = slave_dev; - dsa_slave_setup_tagger(slave_dev); + port->user = user_dev; + dsa_user_setup_tagger(user_dev); - netif_carrier_off(slave_dev); + netif_carrier_off(user_dev); - ret = dsa_slave_phy_setup(slave_dev); + ret = dsa_user_phy_setup(user_dev); if (ret) { - netdev_err(slave_dev, + netdev_err(user_dev, "error %d setting up PHY for tree %d, switch %d, port %d\n", ret, ds->dst->index, ds->index, port->index); goto out_gcells; @@ -2675,23 +2675,23 @@ int dsa_slave_create(struct dsa_port *port) rtnl_lock(); - ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN); + ret = dsa_user_change_mtu(user_dev, ETH_DATA_LEN); if (ret && ret != -EOPNOTSUPP) dev_warn(ds->dev, "nonfatal error %d setting MTU to %d on port %d\n", ret, ETH_DATA_LEN, port->index); - ret = register_netdevice(slave_dev); + ret = register_netdevice(user_dev); if (ret) { - netdev_err(master, "error %d registering interface %s\n", - ret, slave_dev->name); + netdev_err(conduit, "error %d registering interface %s\n", + ret, user_dev->name); rtnl_unlock(); goto out_phy; } if (IS_ENABLED(CONFIG_DCB)) { - ret = dsa_slave_dcbnl_init(slave_dev); + ret = dsa_user_dcbnl_init(user_dev); if (ret) { - netdev_err(slave_dev, + netdev_err(user_dev, "failed to initialize DCB: %pe\n", ERR_PTR(ret)); rtnl_unlock(); @@ -2699,7 +2699,7 @@ int dsa_slave_create(struct dsa_port *port) } } - ret = netdev_upper_dev_link(master, slave_dev, NULL); + ret = netdev_upper_dev_link(conduit, user_dev, NULL); rtnl_unlock(); @@ -2709,7 +2709,7 @@ int dsa_slave_create(struct dsa_port *port) return 0; out_unregister: - unregister_netdev(slave_dev); + unregister_netdev(user_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); @@ -2718,122 +2718,122 @@ out_phy: out_gcells: gro_cells_destroy(&p->gcells); out_free: - free_percpu(slave_dev->tstats); - free_netdev(slave_dev); - port->slave = NULL; + free_percpu(user_dev->tstats); + free_netdev(user_dev); + port->user = NULL; return ret; } -void dsa_slave_destroy(struct net_device *slave_dev) +void dsa_user_destroy(struct net_device *user_dev) { - struct net_device *master = dsa_slave_to_master(slave_dev); - struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct net_device *conduit = dsa_user_to_conduit(user_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); + struct dsa_user_priv *p = netdev_priv(user_dev); - netif_carrier_off(slave_dev); + netif_carrier_off(user_dev); rtnl_lock(); - netdev_upper_dev_unlink(master, slave_dev); - unregister_netdevice(slave_dev); + netdev_upper_dev_unlink(conduit, user_dev); + unregister_netdevice(user_dev); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); - free_percpu(slave_dev->tstats); - free_netdev(slave_dev); + free_percpu(user_dev->tstats); + free_netdev(user_dev); } -int dsa_slave_change_master(struct net_device *dev, struct net_device *master, +int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack) { - struct net_device *old_master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *old_conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct net_device *upper; struct list_head *iter; int err; - if (master == old_master) + if (conduit == old_conduit) return 0; - if (!ds->ops->port_change_master) { + if (!ds->ops->port_change_conduit) { NL_SET_ERR_MSG_MOD(extack, - "Driver does not support changing DSA master"); + "Driver does not support changing DSA conduit"); return -EOPNOTSUPP; } - if (!netdev_uses_dsa(master)) { + if (!netdev_uses_dsa(conduit)) { NL_SET_ERR_MSG_MOD(extack, - "Interface not eligible as DSA master"); + "Interface not eligible as DSA conduit"); return -EOPNOTSUPP; } - netdev_for_each_upper_dev_rcu(master, upper, iter) { - if (dsa_slave_dev_check(upper)) + netdev_for_each_upper_dev_rcu(conduit, upper, iter) { + if (dsa_user_dev_check(upper)) continue; if (netif_is_bridge_master(upper)) continue; - NL_SET_ERR_MSG_MOD(extack, "Cannot join master with unknown uppers"); + NL_SET_ERR_MSG_MOD(extack, "Cannot join conduit with unknown uppers"); return -EOPNOTSUPP; } - /* Since we allow live-changing the DSA master, plus we auto-open the - * DSA master when the user port opens => we need to ensure that the - * new DSA master is open too. + /* Since we allow live-changing the DSA conduit, plus we auto-open the + * DSA conduit when the user port opens => we need to ensure that the + * new DSA conduit is open too. */ if (dev->flags & IFF_UP) { - err = dev_open(master, extack); + err = dev_open(conduit, extack); if (err) return err; } - netdev_upper_dev_unlink(old_master, dev); + netdev_upper_dev_unlink(old_conduit, dev); - err = netdev_upper_dev_link(master, dev, extack); + err = netdev_upper_dev_link(conduit, dev, extack); if (err) - goto out_revert_old_master_unlink; + goto out_revert_old_conduit_unlink; - err = dsa_port_change_master(dp, master, extack); + err = dsa_port_change_conduit(dp, conduit, extack); if (err) - goto out_revert_master_link; + goto out_revert_conduit_link; /* Update the MTU of the new CPU port through cross-chip notifiers */ - err = dsa_slave_change_mtu(dev, dev->mtu); + err = dsa_user_change_mtu(dev, dev->mtu); if (err && err != -EOPNOTSUPP) { netdev_warn(dev, - "nonfatal error updating MTU with new master: %pe\n", + "nonfatal error updating MTU with new conduit: %pe\n", ERR_PTR(err)); } /* If the port doesn't have its own MAC address and relies on the DSA - * master's one, inherit it again from the new DSA master. + * conduit's one, inherit it again from the new DSA conduit. */ if (is_zero_ether_addr(dp->mac)) - eth_hw_addr_inherit(dev, master); + eth_hw_addr_inherit(dev, conduit); return 0; -out_revert_master_link: - netdev_upper_dev_unlink(master, dev); -out_revert_old_master_unlink: - netdev_upper_dev_link(old_master, dev, NULL); +out_revert_conduit_link: + netdev_upper_dev_unlink(conduit, dev); +out_revert_old_conduit_unlink: + netdev_upper_dev_link(old_conduit, dev, NULL); return err; } -bool dsa_slave_dev_check(const struct net_device *dev) +bool dsa_user_dev_check(const struct net_device *dev) { - return dev->netdev_ops == &dsa_slave_netdev_ops; + return dev->netdev_ops == &dsa_user_netdev_ops; } -EXPORT_SYMBOL_GPL(dsa_slave_dev_check); +EXPORT_SYMBOL_GPL(dsa_user_dev_check); -static int dsa_slave_changeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +static int dsa_user_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct netlink_ext_ack *extack; int err = NOTIFY_DONE; - if (!dsa_slave_dev_check(dev)) + if (!dsa_user_dev_check(dev)) return err; extack = netdev_notifier_info_to_extack(&info->info); @@ -2885,28 +2885,28 @@ static int dsa_slave_changeupper(struct net_device *dev, return err; } -static int dsa_slave_prechangeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +static int dsa_user_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); - if (!dsa_slave_dev_check(dev)) + if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; if (netif_is_bridge_master(info->upper_dev) && !info->linking) dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) dsa_port_pre_lag_leave(dp, info->upper_dev); - /* dsa_port_pre_hsr_leave is not yet necessary since hsr cannot be - * meaningfully enslaved to a bridge yet + /* dsa_port_pre_hsr_leave is not yet necessary since hsr devices cannot + * meaningfully placed under a bridge yet */ return NOTIFY_DONE; } static int -dsa_slave_lag_changeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_user_lag_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; @@ -2917,15 +2917,15 @@ dsa_slave_lag_changeupper(struct net_device *dev, return err; netdev_for_each_lower_dev(dev, lower, iter) { - if (!dsa_slave_dev_check(lower)) + if (!dsa_user_dev_check(lower)) continue; - dp = dsa_slave_to_port(lower); + dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; - err = dsa_slave_changeupper(lower, info); + err = dsa_user_changeupper(lower, info); if (notifier_to_errno(err)) break; } @@ -2933,12 +2933,12 @@ dsa_slave_lag_changeupper(struct net_device *dev, return err; } -/* Same as dsa_slave_lag_changeupper() except that it calls - * dsa_slave_prechangeupper() +/* Same as dsa_user_lag_changeupper() except that it calls + * dsa_user_prechangeupper() */ static int -dsa_slave_lag_prechangeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_user_lag_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; @@ -2949,15 +2949,15 @@ dsa_slave_lag_prechangeupper(struct net_device *dev, return err; netdev_for_each_lower_dev(dev, lower, iter) { - if (!dsa_slave_dev_check(lower)) + if (!dsa_user_dev_check(lower)) continue; - dp = dsa_slave_to_port(lower); + dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; - err = dsa_slave_prechangeupper(lower, info); + err = dsa_user_prechangeupper(lower, info); if (notifier_to_errno(err)) break; } @@ -2970,7 +2970,7 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; - struct net_device *slave, *br; + struct net_device *user, *br; struct dsa_port *dp; ext_ack = netdev_notifier_info_to_extack(&info->info); @@ -2978,11 +2978,11 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, if (!is_vlan_dev(dev)) return NOTIFY_DONE; - slave = vlan_dev_real_dev(dev); - if (!dsa_slave_dev_check(slave)) + user = vlan_dev_real_dev(dev); + if (!dsa_user_dev_check(user)) return NOTIFY_DONE; - dp = dsa_slave_to_port(slave); + dp = dsa_user_to_port(user); br = dsa_port_bridge_dev_get(dp); if (!br) return NOTIFY_DONE; @@ -2991,7 +2991,7 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, if (br_vlan_enabled(br) && netif_is_bridge_master(info->upper_dev) && info->linking) { NL_SET_ERR_MSG_MOD(ext_ack, - "Cannot enslave VLAN device into VLAN aware bridge"); + "Cannot make VLAN device join VLAN-aware bridge"); return notifier_from_errno(-EINVAL); } @@ -2999,10 +2999,10 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, } static int -dsa_slave_check_8021q_upper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_user_check_8021q_upper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct net_device *br = dsa_port_bridge_dev_get(dp); struct bridge_vlan_info br_info; struct netlink_ext_ack *extack; @@ -3030,17 +3030,17 @@ dsa_slave_check_8021q_upper(struct net_device *dev, } static int -dsa_slave_prechangeupper_sanity_check(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_user_prechangeupper_sanity_check(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct dsa_switch *ds; struct dsa_port *dp; int err; - if (!dsa_slave_dev_check(dev)) + if (!dsa_user_dev_check(dev)) return dsa_prevent_bridging_8021q_upper(dev, info); - dp = dsa_slave_to_port(dev); + dp = dsa_user_to_port(dev); ds = dp->ds; if (ds->ops->port_prechangeupper) { @@ -3050,17 +3050,17 @@ dsa_slave_prechangeupper_sanity_check(struct net_device *dev, } if (is_vlan_dev(info->upper_dev)) - return dsa_slave_check_8021q_upper(dev, info); + return dsa_user_check_8021q_upper(dev, info); return NOTIFY_DONE; } -/* To be eligible as a DSA master, a LAG must have all lower interfaces be - * eligible DSA masters. Additionally, all LAG slaves must be DSA masters of +/* To be eligible as a DSA conduit, a LAG must have all lower interfaces be + * eligible DSA conduits. Additionally, all LAG slaves must be DSA conduits of * switches in the same switch tree. */ -static int dsa_lag_master_validate(struct net_device *lag_dev, - struct netlink_ext_ack *extack) +static int dsa_lag_conduit_validate(struct net_device *lag_dev, + struct netlink_ext_ack *extack) { struct net_device *lower1, *lower2; struct list_head *iter1, *iter2; @@ -3070,7 +3070,7 @@ static int dsa_lag_master_validate(struct net_device *lag_dev, if (!netdev_uses_dsa(lower1) || !netdev_uses_dsa(lower2)) { NL_SET_ERR_MSG_MOD(extack, - "All LAG ports must be eligible as DSA masters"); + "All LAG ports must be eligible as DSA conduits"); return notifier_from_errno(-EINVAL); } @@ -3080,7 +3080,7 @@ static int dsa_lag_master_validate(struct net_device *lag_dev, if (!dsa_port_tree_same(lower1->dsa_ptr, lower2->dsa_ptr)) { NL_SET_ERR_MSG_MOD(extack, - "LAG contains DSA masters of disjoint switch trees"); + "LAG contains DSA conduits of disjoint switch trees"); return notifier_from_errno(-EINVAL); } } @@ -3090,41 +3090,41 @@ static int dsa_lag_master_validate(struct net_device *lag_dev, } static int -dsa_master_prechangeupper_sanity_check(struct net_device *master, - struct netdev_notifier_changeupper_info *info) +dsa_conduit_prechangeupper_sanity_check(struct net_device *conduit, + struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); - if (!netdev_uses_dsa(master)) + if (!netdev_uses_dsa(conduit)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; /* Allow DSA switch uppers */ - if (dsa_slave_dev_check(info->upper_dev)) + if (dsa_user_dev_check(info->upper_dev)) return NOTIFY_DONE; - /* Allow bridge uppers of DSA masters, subject to further + /* Allow bridge uppers of DSA conduits, subject to further * restrictions in dsa_bridge_prechangelower_sanity_check() */ if (netif_is_bridge_master(info->upper_dev)) return NOTIFY_DONE; /* Allow LAG uppers, subject to further restrictions in - * dsa_lag_master_prechangelower_sanity_check() + * dsa_lag_conduit_prechangelower_sanity_check() */ if (netif_is_lag_master(info->upper_dev)) - return dsa_lag_master_validate(info->upper_dev, extack); + return dsa_lag_conduit_validate(info->upper_dev, extack); NL_SET_ERR_MSG_MOD(extack, - "DSA master cannot join unknown upper interfaces"); + "DSA conduit cannot join unknown upper interfaces"); return notifier_from_errno(-EBUSY); } static int -dsa_lag_master_prechangelower_sanity_check(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_lag_conduit_prechangelower_sanity_check(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); struct net_device *lag_dev = info->upper_dev; @@ -3139,14 +3139,14 @@ dsa_lag_master_prechangelower_sanity_check(struct net_device *dev, if (!netdev_uses_dsa(dev)) { NL_SET_ERR_MSG(extack, - "Only DSA masters can join a LAG DSA master"); + "Only DSA conduits can join a LAG DSA conduit"); return notifier_from_errno(-EINVAL); } netdev_for_each_lower_dev(lag_dev, lower, iter) { if (!dsa_port_tree_same(dev->dsa_ptr, lower->dsa_ptr)) { NL_SET_ERR_MSG(extack, - "Interface is DSA master for a different switch tree than this LAG"); + "Interface is DSA conduit for a different switch tree than this LAG"); return notifier_from_errno(-EINVAL); } @@ -3156,13 +3156,13 @@ dsa_lag_master_prechangelower_sanity_check(struct net_device *dev, return NOTIFY_DONE; } -/* Don't allow bridging of DSA masters, since the bridge layer rx_handler +/* Don't allow bridging of DSA conduits, since the bridge layer rx_handler * prevents the DSA fake ethertype handler to be invoked, so we don't get the * chance to strip off and parse the DSA switch tag protocol header (the bridge * layer just returns RX_HANDLER_CONSUMED, stopping RX processing for these * frames). * The only case where that would not be an issue is when bridging can already - * be offloaded, such as when the DSA master is itself a DSA or plain switchdev + * be offloaded, such as when the DSA conduit is itself a DSA or plain switchdev * port, and is bridged only with other ports from the same hardware device. */ static int @@ -3188,7 +3188,7 @@ dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, if (!netdev_port_same_parent_id(lower, new_lower)) { NL_SET_ERR_MSG(extack, - "Cannot do software bridging with a DSA master"); + "Cannot do software bridging with a DSA conduit"); return notifier_from_errno(-EINVAL); } } @@ -3196,45 +3196,45 @@ dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, return NOTIFY_DONE; } -static void dsa_tree_migrate_ports_from_lag_master(struct dsa_switch_tree *dst, - struct net_device *lag_dev) +static void dsa_tree_migrate_ports_from_lag_conduit(struct dsa_switch_tree *dst, + struct net_device *lag_dev) { - struct net_device *new_master = dsa_tree_find_first_master(dst); + struct net_device *new_conduit = dsa_tree_find_first_conduit(dst); struct dsa_port *dp; int err; dsa_tree_for_each_user_port(dp, dst) { - if (dsa_port_to_master(dp) != lag_dev) + if (dsa_port_to_conduit(dp) != lag_dev) continue; - err = dsa_slave_change_master(dp->slave, new_master, NULL); + err = dsa_user_change_conduit(dp->user, new_conduit, NULL); if (err) { - netdev_err(dp->slave, - "failed to restore master to %s: %pe\n", - new_master->name, ERR_PTR(err)); + netdev_err(dp->user, + "failed to restore conduit to %s: %pe\n", + new_conduit->name, ERR_PTR(err)); } } } -static int dsa_master_lag_join(struct net_device *master, - struct net_device *lag_dev, - struct netdev_lag_upper_info *uinfo, - struct netlink_ext_ack *extack) +static int dsa_conduit_lag_join(struct net_device *conduit, + struct net_device *lag_dev, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *dp; int err; - err = dsa_master_lag_setup(lag_dev, cpu_dp, uinfo, extack); + err = dsa_conduit_lag_setup(lag_dev, cpu_dp, uinfo, extack); if (err) return err; dsa_tree_for_each_user_port(dp, dst) { - if (dsa_port_to_master(dp) != master) + if (dsa_port_to_conduit(dp) != conduit) continue; - err = dsa_slave_change_master(dp->slave, lag_dev, extack); + err = dsa_user_change_conduit(dp->user, lag_dev, extack); if (err) goto restore; } @@ -3243,24 +3243,24 @@ static int dsa_master_lag_join(struct net_device *master, restore: dsa_tree_for_each_user_port_continue_reverse(dp, dst) { - if (dsa_port_to_master(dp) != lag_dev) + if (dsa_port_to_conduit(dp) != lag_dev) continue; - err = dsa_slave_change_master(dp->slave, master, NULL); + err = dsa_user_change_conduit(dp->user, conduit, NULL); if (err) { - netdev_err(dp->slave, - "failed to restore master to %s: %pe\n", - master->name, ERR_PTR(err)); + netdev_err(dp->user, + "failed to restore conduit to %s: %pe\n", + conduit->name, ERR_PTR(err)); } } - dsa_master_lag_teardown(lag_dev, master->dsa_ptr); + dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); return err; } -static void dsa_master_lag_leave(struct net_device *master, - struct net_device *lag_dev) +static void dsa_conduit_lag_leave(struct net_device *conduit, + struct net_device *lag_dev) { struct dsa_port *dp, *cpu_dp = lag_dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; @@ -3277,10 +3277,10 @@ static void dsa_master_lag_leave(struct net_device *master, if (new_cpu_dp) { /* Update the CPU port of the user ports still under the LAG - * so that dsa_port_to_master() continues to work properly + * so that dsa_port_to_conduit() continues to work properly */ dsa_tree_for_each_user_port(dp, dst) - if (dsa_port_to_master(dp) == lag_dev) + if (dsa_port_to_conduit(dp) == lag_dev) dp->cpu_dp = new_cpu_dp; /* Update the index of the virtual CPU port to match the lowest @@ -3289,20 +3289,20 @@ static void dsa_master_lag_leave(struct net_device *master, lag_dev->dsa_ptr = new_cpu_dp; wmb(); } else { - /* If the LAG DSA master has no ports left, migrate back all + /* If the LAG DSA conduit has no ports left, migrate back all * user ports to the first physical CPU port */ - dsa_tree_migrate_ports_from_lag_master(dst, lag_dev); + dsa_tree_migrate_ports_from_lag_conduit(dst, lag_dev); } - /* This DSA master has left its LAG in any case, so let + /* This DSA conduit has left its LAG in any case, so let * the CPU port leave the hardware LAG as well */ - dsa_master_lag_teardown(lag_dev, master->dsa_ptr); + dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); } -static int dsa_master_changeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +static int dsa_conduit_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; @@ -3314,11 +3314,11 @@ static int dsa_master_changeupper(struct net_device *dev, if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { - err = dsa_master_lag_join(dev, info->upper_dev, - info->upper_info, extack); + err = dsa_conduit_lag_join(dev, info->upper_dev, + info->upper_info, extack); err = notifier_from_errno(err); } else { - dsa_master_lag_leave(dev, info->upper_dev); + dsa_conduit_lag_leave(dev, info->upper_dev); err = NOTIFY_OK; } } @@ -3326,8 +3326,8 @@ static int dsa_master_changeupper(struct net_device *dev, return err; } -static int dsa_slave_netdevice_event(struct notifier_block *nb, - unsigned long event, void *ptr) +static int dsa_user_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); @@ -3336,15 +3336,15 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, struct netdev_notifier_changeupper_info *info = ptr; int err; - err = dsa_slave_prechangeupper_sanity_check(dev, info); + err = dsa_user_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; - err = dsa_master_prechangeupper_sanity_check(dev, info); + err = dsa_conduit_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; - err = dsa_lag_master_prechangelower_sanity_check(dev, info); + err = dsa_lag_conduit_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; @@ -3352,11 +3352,11 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, if (notifier_to_errno(err)) return err; - err = dsa_slave_prechangeupper(dev, ptr); + err = dsa_user_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; - err = dsa_slave_lag_prechangeupper(dev, ptr); + err = dsa_user_lag_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; @@ -3365,15 +3365,15 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, case NETDEV_CHANGEUPPER: { int err; - err = dsa_slave_changeupper(dev, ptr); + err = dsa_user_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; - err = dsa_slave_lag_changeupper(dev, ptr); + err = dsa_user_lag_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; - err = dsa_master_changeupper(dev, ptr); + err = dsa_conduit_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; @@ -3384,13 +3384,13 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, struct dsa_port *dp; int err = 0; - if (dsa_slave_dev_check(dev)) { - dp = dsa_slave_to_port(dev); + if (dsa_user_dev_check(dev)) { + dp = dsa_user_to_port(dev); err = dsa_port_lag_change(dp, info->lower_state_info); } - /* Mirror LAG port events on DSA masters that are in + /* Mirror LAG port events on DSA conduits that are in * a LAG towards their respective switch CPU ports */ if (netdev_uses_dsa(dev)) { @@ -3403,28 +3403,28 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, } case NETDEV_CHANGE: case NETDEV_UP: { - /* Track state of master port. - * DSA driver may require the master port (and indirectly + /* Track state of conduit port. + * DSA driver may require the conduit port (and indirectly * the tagger) to be available for some special operation. */ if (netdev_uses_dsa(dev)) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->ds->dst; - /* Track when the master port is UP */ - dsa_tree_master_oper_state_change(dst, dev, - netif_oper_up(dev)); + /* Track when the conduit port is UP */ + dsa_tree_conduit_oper_state_change(dst, dev, + netif_oper_up(dev)); - /* Track when the master port is ready and can accept + /* Track when the conduit port is ready and can accept * packet. * NETDEV_UP event is not enough to flag a port as ready. * We also have to wait for linkwatch_do_dev to dev_activate * and emit a NETDEV_CHANGE event. - * We check if a master port is ready by checking if the dev + * We check if a conduit port is ready by checking if the dev * have a qdisc assigned and is not noop. */ - dsa_tree_master_admin_state_change(dst, dev, - !qdisc_tx_is_noop(dev)); + dsa_tree_conduit_admin_state_change(dst, dev, + !qdisc_tx_is_noop(dev)); return NOTIFY_OK; } @@ -3442,7 +3442,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, cpu_dp = dev->dsa_ptr; dst = cpu_dp->ds->dst; - dsa_tree_master_admin_state_change(dst, dev, false); + dsa_tree_conduit_admin_state_change(dst, dev, false); list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_user(dp)) @@ -3451,7 +3451,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, if (dp->cpu_dp != cpu_dp) continue; - list_add(&dp->slave->close_list, &close_list); + list_add(&dp->user->close_list, &close_list); } dev_close_many(&close_list, true); @@ -3477,7 +3477,7 @@ dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) switchdev_work->orig_dev, &info.info, NULL); } -static void dsa_slave_switchdev_event_work(struct work_struct *work) +static void dsa_user_switchdev_event_work(struct work_struct *work) { struct dsa_switchdev_event_work *switchdev_work = container_of(work, struct dsa_switchdev_event_work, work); @@ -3488,7 +3488,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) struct dsa_port *dp; int err; - dp = dsa_slave_to_port(dev); + dp = dsa_user_to_port(dev); ds = dp->ds; switch (switchdev_work->event) { @@ -3530,7 +3530,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) static bool dsa_foreign_dev_check(const struct net_device *dev, const struct net_device *foreign_dev) { - const struct dsa_port *dp = dsa_slave_to_port(dev); + const struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch_tree *dst = dp->ds->dst; if (netif_is_bridge_master(foreign_dev)) @@ -3543,13 +3543,13 @@ static bool dsa_foreign_dev_check(const struct net_device *dev, return true; } -static int dsa_slave_fdb_event(struct net_device *dev, - struct net_device *orig_dev, - unsigned long event, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info) +static int dsa_user_fdb_event(struct net_device *dev, + struct net_device *orig_dev, + unsigned long event, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info) { struct dsa_switchdev_event_work *switchdev_work; - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); bool host_addr = fdb_info->is_local; struct dsa_switch *ds = dp->ds; @@ -3598,7 +3598,7 @@ static int dsa_slave_fdb_event(struct net_device *dev, orig_dev->name, fdb_info->addr, fdb_info->vid, host_addr ? " as host address" : ""); - INIT_WORK(&switchdev_work->work, dsa_slave_switchdev_event_work); + INIT_WORK(&switchdev_work->work, dsa_user_switchdev_event_work); switchdev_work->event = event; switchdev_work->dev = dev; switchdev_work->orig_dev = orig_dev; @@ -3613,8 +3613,8 @@ static int dsa_slave_fdb_event(struct net_device *dev, } /* Called under rcu_read_lock() */ -static int dsa_slave_switchdev_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int dsa_user_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; @@ -3622,15 +3622,15 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, - dsa_slave_dev_check, - dsa_slave_port_attr_set); + dsa_user_dev_check, + dsa_user_port_attr_set); return notifier_from_errno(err); case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: err = switchdev_handle_fdb_event_to_device(dev, event, ptr, - dsa_slave_dev_check, + dsa_user_dev_check, dsa_foreign_dev_check, - dsa_slave_fdb_event); + dsa_user_fdb_event); return notifier_from_errno(err); default: return NOTIFY_DONE; @@ -3639,8 +3639,8 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, return NOTIFY_OK; } -static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int dsa_user_switchdev_blocking_event(struct notifier_block *unused, + unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; @@ -3648,52 +3648,52 @@ static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_PORT_OBJ_ADD: err = switchdev_handle_port_obj_add_foreign(dev, ptr, - dsa_slave_dev_check, + dsa_user_dev_check, dsa_foreign_dev_check, - dsa_slave_port_obj_add); + dsa_user_port_obj_add); return notifier_from_errno(err); case SWITCHDEV_PORT_OBJ_DEL: err = switchdev_handle_port_obj_del_foreign(dev, ptr, - dsa_slave_dev_check, + dsa_user_dev_check, dsa_foreign_dev_check, - dsa_slave_port_obj_del); + dsa_user_port_obj_del); return notifier_from_errno(err); case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, - dsa_slave_dev_check, - dsa_slave_port_attr_set); + dsa_user_dev_check, + dsa_user_port_attr_set); return notifier_from_errno(err); } return NOTIFY_DONE; } -static struct notifier_block dsa_slave_nb __read_mostly = { - .notifier_call = dsa_slave_netdevice_event, +static struct notifier_block dsa_user_nb __read_mostly = { + .notifier_call = dsa_user_netdevice_event, }; -struct notifier_block dsa_slave_switchdev_notifier = { - .notifier_call = dsa_slave_switchdev_event, +struct notifier_block dsa_user_switchdev_notifier = { + .notifier_call = dsa_user_switchdev_event, }; -struct notifier_block dsa_slave_switchdev_blocking_notifier = { - .notifier_call = dsa_slave_switchdev_blocking_event, +struct notifier_block dsa_user_switchdev_blocking_notifier = { + .notifier_call = dsa_user_switchdev_blocking_event, }; -int dsa_slave_register_notifier(void) +int dsa_user_register_notifier(void) { struct notifier_block *nb; int err; - err = register_netdevice_notifier(&dsa_slave_nb); + err = register_netdevice_notifier(&dsa_user_nb); if (err) return err; - err = register_switchdev_notifier(&dsa_slave_switchdev_notifier); + err = register_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) goto err_switchdev_nb; - nb = &dsa_slave_switchdev_blocking_notifier; + nb = &dsa_user_switchdev_blocking_notifier; err = register_switchdev_blocking_notifier(nb); if (err) goto err_switchdev_blocking_nb; @@ -3701,27 +3701,27 @@ int dsa_slave_register_notifier(void) return 0; err_switchdev_blocking_nb: - unregister_switchdev_notifier(&dsa_slave_switchdev_notifier); + unregister_switchdev_notifier(&dsa_user_switchdev_notifier); err_switchdev_nb: - unregister_netdevice_notifier(&dsa_slave_nb); + unregister_netdevice_notifier(&dsa_user_nb); return err; } -void dsa_slave_unregister_notifier(void) +void dsa_user_unregister_notifier(void) { struct notifier_block *nb; int err; - nb = &dsa_slave_switchdev_blocking_notifier; + nb = &dsa_user_switchdev_blocking_notifier; err = unregister_switchdev_blocking_notifier(nb); if (err) pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err); - err = unregister_switchdev_notifier(&dsa_slave_switchdev_notifier); + err = unregister_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); - err = unregister_netdevice_notifier(&dsa_slave_nb); + err = unregister_netdevice_notifier(&dsa_user_nb); if (err) - pr_err("DSA: failed to unregister slave notifier (%d)\n", err); + pr_err("DSA: failed to unregister user notifier (%d)\n", err); } diff --git a/net/dsa/user.h b/net/dsa/user.h new file mode 100644 index 000000000000..996069130bea --- /dev/null +++ b/net/dsa/user.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_USER_H +#define __DSA_USER_H + +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> +#include <linux/list.h> +#include <linux/netpoll.h> +#include <linux/types.h> +#include <net/dsa.h> +#include <net/gro_cells.h> + +struct net_device; +struct netlink_ext_ack; + +extern struct notifier_block dsa_user_switchdev_notifier; +extern struct notifier_block dsa_user_switchdev_blocking_notifier; + +struct dsa_user_priv { + /* Copy of CPU port xmit for faster access in user transmit hot path */ + struct sk_buff * (*xmit)(struct sk_buff *skb, + struct net_device *dev); + + struct gro_cells gcells; + + /* DSA port data, such as switch, port index, etc. */ + struct dsa_port *dp; + +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *netpoll; +#endif + + /* TC context */ + struct list_head mall_tc_list; +}; + +void dsa_user_mii_bus_init(struct dsa_switch *ds); +int dsa_user_create(struct dsa_port *dp); +void dsa_user_destroy(struct net_device *user_dev); +int dsa_user_suspend(struct net_device *user_dev); +int dsa_user_resume(struct net_device *user_dev); +int dsa_user_register_notifier(void); +void dsa_user_unregister_notifier(void); +void dsa_user_sync_ha(struct net_device *dev); +void dsa_user_unsync_ha(struct net_device *dev); +void dsa_user_setup_tagger(struct net_device *user); +int dsa_user_change_mtu(struct net_device *dev, int new_mtu); +int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, + struct netlink_ext_ack *extack); +int dsa_user_manage_vlan_filtering(struct net_device *dev, + bool vlan_filtering); + +static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev) +{ + struct dsa_user_priv *p = netdev_priv(dev); + + return p->dp; +} + +static inline struct net_device * +dsa_user_to_conduit(const struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + return dsa_port_to_conduit(dp); +} + +#endif diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 883ed9be81f9..0515d6604b3b 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -431,10 +431,8 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { - u32 *orig_bitmap, *saved_bitmap = NULL; struct nlattr *bit_attr; bool no_mask; - bool dummy; int rem; int ret; @@ -450,22 +448,8 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, } no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; - if (no_mask) { - unsigned int nwords = DIV_ROUND_UP(nbits, 32); - unsigned int nbytes = nwords * sizeof(u32); - - /* The bitmap size is only the size of the map part without - * its mask part. - */ - saved_bitmap = kcalloc(nwords, sizeof(u32), GFP_KERNEL); - if (!saved_bitmap) - return -ENOMEM; - memcpy(saved_bitmap, bitmap, nbytes); - ethnl_bitmap32_clear(bitmap, 0, nbits, &dummy); - orig_bitmap = saved_bitmap; - } else { - orig_bitmap = bitmap; - } + if (no_mask) + ethnl_bitmap32_clear(bitmap, 0, nbits, mod); nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { bool old_val, new_val; @@ -474,14 +458,13 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, if (nla_type(bit_attr) != ETHTOOL_A_BITSET_BITS_BIT) { NL_SET_ERR_MSG_ATTR(extack, bit_attr, "only ETHTOOL_A_BITSET_BITS_BIT allowed in ETHTOOL_A_BITSET_BITS"); - ret = -EINVAL; - goto out; + return -EINVAL; } ret = ethnl_parse_bit(&idx, &new_val, nbits, bit_attr, no_mask, names, extack); if (ret < 0) - goto out; - old_val = orig_bitmap[idx / 32] & ((u32)1 << (idx % 32)); + return ret; + old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32)); if (new_val != old_val) { if (new_val) bitmap[idx / 32] |= ((u32)1 << (idx % 32)); @@ -491,10 +474,7 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, } } - ret = 0; -out: - kfree(saved_bitmap); - return ret; + return 0; } static int ethnl_compact_sanity_checks(unsigned int nbits, diff --git a/net/ethtool/common.c b/net/ethtool/common.c index f5598c5f50de..b4419fb6df6a 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -685,3 +685,24 @@ ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, link_ksettings->base.duplex = link_info->duplex; } EXPORT_SYMBOL_GPL(ethtool_params_from_link_mode); + +/** + * ethtool_forced_speed_maps_init + * @maps: Pointer to an array of Ethtool forced speed map + * @size: Array size + * + * Initialize an array of Ethtool forced speed map to Ethtool link modes. This + * should be called during driver module init. + */ +void +ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size) +{ + for (u32 i = 0; i < size; i++) { + struct ethtool_forced_speed_map *map = &maps[i]; + + linkmode_set_bit_array(map->cap_arr, map->arr_size, map->caps); + map->cap_arr = NULL; + map->arr_size = 0; + } +} +EXPORT_SYMBOL_GPL(ethtool_forced_speed_maps_init); diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index 64a0046dd611..89637e732866 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -87,29 +87,6 @@ struct nlmsghdr *handshake_genl_put(struct sk_buff *msg, } EXPORT_SYMBOL(handshake_genl_put); -/* - * dup() a kernel socket for use as a user space file descriptor - * in the current process. The kernel socket must have an - * instatiated struct file. - * - * Implicit argument: "current()" - */ -static int handshake_dup(struct socket *sock) -{ - struct file *file; - int newfd; - - file = get_file(sock->file); - newfd = get_unused_fd_flags(O_CLOEXEC); - if (newfd < 0) { - fput(file); - return newfd; - } - - fd_install(newfd, file); - return newfd; -} - int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); @@ -133,17 +110,20 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) goto out_status; sock = req->hr_sk->sk_socket; - fd = handshake_dup(sock); + fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { err = fd; goto out_complete; } + err = req->hr_proto->hp_accept(req, info, fd); if (err) { - fput(sock->file); + put_unused_fd(fd); goto out_complete; } + fd_install(fd, get_file(sock->file)); + trace_handshake_cmd_accept(net, req, req->hr_sk, fd); return 0; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5ce275b2d7ef..fb81de10d332 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -597,7 +597,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; - sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -613,7 +612,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; - sk->sk_wait_pending--; return timeo; } @@ -642,6 +640,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) { + sk->sk_disconnects++; err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; goto out; @@ -696,6 +695,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int writebias = (sk->sk_protocol == IPPROTO_TCP) && tcp_sk(sk)->fastopen_req && tcp_sk(sk)->fastopen_req->data ? 1 : 0; + int dis = sk->sk_disconnects; /* Error code is set above */ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) @@ -704,6 +704,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = sock_intr_errno(timeo); if (signal_pending(current)) goto out; + + if (dis != sk->sk_disconnects) { + err = -EPIPE; + goto out; + } } /* Connection was closed by RST, timeout, ICMP error @@ -725,6 +730,7 @@ out: sock_error: err = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; + sk->sk_disconnects++; if (sk->sk_prot->disconnect(sk, flags)) sock->state = SS_DISCONNECTING; goto out; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 2be2d4922557..4ccfc104f13a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -732,7 +732,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; @@ -784,7 +786,7 @@ int esp_input_done2(struct sk_buff *skb, int err) /* * 1) if the NAT-T peer's IP or port changed then - * advertize the change to the keying daemon. + * advertise the change to the keying daemon. * This is an inbound SA, so just compare * SRC ports. */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 1ea82bc33ef1..5eb1b8d302bb 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1325,15 +1325,18 @@ __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope) { struct fib_nh *nh; + __be32 saddr; if (nhc->nhc_family != AF_INET) return inet_select_addr(nhc->nhc_dev, 0, scope); nh = container_of(nhc, struct fib_nh, nh_common); - nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); - nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid); + saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); - return nh->nh_saddr; + WRITE_ONCE(nh->nh_saddr, saddr); + WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid)); + + return saddr; } __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) @@ -1347,8 +1350,9 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); - if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid)) - return nh->nh_saddr; + if (READ_ONCE(nh->nh_saddr_genid) == + atomic_read(&net->ipv4.dev_addr_genid)) + return READ_ONCE(nh->nh_saddr); } return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index aeebe8816689..394a498c2823 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1145,7 +1145,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); - newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c32f5e28758b..598c1b114d2c 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -149,8 +149,14 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb2->family) - return false; + if (sk->sk_family != tb2->family) { + if (sk->sk_family == AF_INET) + return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) && + tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; + + return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) && + sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr; + } if (sk->sk_family == AF_INET6) return ipv6_addr_equal(&tb2->v6_rcv_saddr, @@ -819,19 +825,7 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, tb->l3mdev != l3mdev) return false; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb->family) { - if (sk->sk_family == AF_INET) - return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) && - tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; - - return false; - } - - if (sk->sk_family == AF_INET6) - return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); -#endif - return tb->rcv_saddr == sk->sk_rcv_saddr; + return inet_bind2_bucket_addr_match(tb, sk); } bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 89e62ed08dad..b06f678b03a1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -101,6 +101,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); + IP_INC_STATS(net, IPSTATS_MIB_OUTREQUESTS); + iph_set_totlen(iph, skb->len); ip_send_check(iph); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 0b74ac49d6a6..9c68b6b74d9f 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -585,9 +585,9 @@ out: return err; } -void ip_sock_set_tos(struct sock *sk, int val) +void __ip_sock_set_tos(struct sock *sk, int val) { - u8 old_tos = READ_ONCE(inet_sk(sk)->tos); + u8 old_tos = inet_sk(sk)->tos; if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; @@ -599,6 +599,13 @@ void ip_sock_set_tos(struct sock *sk, int val) sk_dst_reset(sk); } } + +void ip_sock_set_tos(struct sock *sk, int val) +{ + lock_sock(sk); + __ip_sock_set_tos(sk, val); + release_sock(sk); +} EXPORT_SYMBOL(ip_sock_set_tos); void ip_sock_set_freebind(struct sock *sk) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 3abb430af9e6..385d945d8ebe 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -36,12 +36,12 @@ static const struct xt_table packet_mangler = { static unsigned int ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - unsigned int ret; + unsigned int ret, verdict; const struct iphdr *iph; - u_int8_t tos; __be32 saddr, daddr; - u_int32_t mark; + u32 mark; int err; + u8 tos; /* Save things which could affect route */ mark = skb->mark; @@ -51,8 +51,9 @@ ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat tos = iph->tos; ret = ipt_do_table(priv, skb, state); + verdict = ret & NF_VERDICT_MASK; /* Reroute for ANY change. */ - if (ret != NF_DROP && ret != NF_STOLEN) { + if (verdict != NF_DROP && verdict != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index eaf1d3113b62..a85b0aba3646 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -83,7 +83,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("InUnknownProtos", IPSTATS_MIB_INUNKNOWNPROTOS), SNMP_MIB_ITEM("InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("InDelivers", IPSTATS_MIB_INDELIVERS), - SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTPKTS), + SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTREQUESTS), SNMP_MIB_ITEM("OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -93,6 +93,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("FragOKs", IPSTATS_MIB_FRAGOKS), SNMP_MIB_ITEM("FragFails", IPSTATS_MIB_FRAGFAILS), SNMP_MIB_ITEM("FragCreates", IPSTATS_MIB_FRAGCREATES), + SNMP_MIB_ITEM("OutTransmits", IPSTATS_MIB_OUTPKTS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index dc478a0574cb..c64334363230 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -41,7 +41,6 @@ static siphash_aligned_key_t syncookie_secret[2]; * requested/supported by the syn/synack exchange. */ #define TSBITS 6 -#define TSMASK (((__u32)1 << TSBITS) - 1) static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, u32 count, int c) @@ -52,6 +51,14 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, count, &syncookie_secret[c]); } +/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ +static u64 tcp_ns_to_ts(bool usec_ts, u64 val) +{ + if (usec_ts) + return div_u64(val, NSEC_PER_USEC); + + return div_u64(val, NSEC_PER_MSEC); +} /* * when syncookies are in effect and tcp timestamps are enabled we encode @@ -62,27 +69,24 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, */ u64 cookie_init_timestamp(struct request_sock *req, u64 now) { - struct inet_request_sock *ireq; - u32 ts, ts_now = tcp_ns_to_ts(now); + const struct inet_request_sock *ireq = inet_rsk(req); + u64 ts, ts_now = tcp_ns_to_ts(false, now); u32 options = 0; - ireq = inet_rsk(req); - options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK; if (ireq->sack_ok) options |= TS_OPT_SACK; if (ireq->ecn_ok) options |= TS_OPT_ECN; - ts = ts_now & ~TSMASK; + ts = (ts_now >> TSBITS) << TSBITS; ts |= options; - if (ts > ts_now) { - ts >>= TSBITS; - ts--; - ts <<= TSBITS; - ts |= options; - } - return (u64)ts * (NSEC_PER_SEC / TCP_TS_HZ); + if (ts > ts_now) + ts -= (1UL << TSBITS); + + if (tcp_rsk(req)->req_usec_ts) + return ts * NSEC_PER_USEC; + return ts * NSEC_PER_MSEC; } @@ -302,6 +306,8 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, treq->af_specific = af_ops; treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; + treq->req_usec_ts = -1; + #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); if (treq->is_mptcp) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index faabb5a4a378..156264531124 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -831,7 +831,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; - sk_wait_data(sk, &timeo, NULL); + ret = sk_wait_data(sk, &timeo, NULL); + if (ret < 0) + break; if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -925,10 +927,11 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -/* In some cases, both sendmsg() could have added an skb to the write queue, - * but failed adding payload on it. We need to remove it to consume less +/* In some cases, sendmsg() could have added an skb to the write queue, + * but failed adding payload on it. We need to remove it to consume less * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger - * epoll() users. + * epoll() users. Another reason is that tcp_write_xmit() does not like + * finding an empty skb in the write queue. */ void tcp_remove_empty_skb(struct sock *sk) { @@ -1287,6 +1290,7 @@ new_segment: wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + tcp_remove_empty_skb(sk); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); @@ -2442,7 +2446,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); - sk_wait_data(sk, &timeo, last); + err = sk_wait_data(sk, &timeo, last); + if (err < 0) { + err = copied ? : err; + goto out; + } } if ((flags & MSG_PEEK) && @@ -2966,12 +2974,6 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; - /* Deny disconnect if other threads are blocked in sk_wait_event() - * or inet_wait_for_connect(). - */ - if (sk->sk_wait_pending) - return -EBUSY; - if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -3629,10 +3631,16 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, tp->fastopen_no_cookie = val; break; case TCP_TIMESTAMP: - if (!tp->repair) + if (!tp->repair) { err = -EPERM; - else - WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); + break; + } + /* val is an opaque field, + * and low order bit contains usec_ts enable bit. + * Its a best effort, and we do not care if user makes an error. + */ + tp->tcp_usec_ts = val & 1; + WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts)); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -3754,6 +3762,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; + if (tp->tcp_usec_ts) + info->tcpi_options |= TCPI_OPT_USEC_TS; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, @@ -3817,10 +3827,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_rto = tp->total_rto; info->tcpi_total_rto_recoveries = tp->total_rto_recoveries; info->tcpi_total_rto_time = tp->total_rto_time; - if (tp->rto_stamp) { - info->tcpi_total_rto_time += tcp_time_stamp_raw() - - tp->rto_stamp; - } + if (tp->rto_stamp) + info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; unlock_sock_fast(sk, slow); } @@ -4145,7 +4153,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); + val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset); + if (tp->tcp_usec_ts) + val |= 1; + else + val &= ~1; break; case TCP_NOTSENT_LOWAT: val = READ_ONCE(tp->notsent_lowat); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 327268203001..53b0d62fd2c2 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -307,6 +307,10 @@ msg_bytes_ready: } data = tcp_msg_wait_data(sk, psock, timeo); + if (data < 0) { + copied = data; + goto unlock; + } if (data && !sk_psock_queue_empty(psock)) goto msg_bytes_ready; copied = -EAGAIN; @@ -317,6 +321,8 @@ out: tcp_rcv_space_adjust(sk); if (copied > 0) __tcp_cleanup_rbuf(sk, copied); + +unlock: release_sock(sk); sk_psock_put(sk, psock); return copied; @@ -351,6 +357,10 @@ msg_bytes_ready: timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); data = tcp_msg_wait_data(sk, psock, timeo); + if (data < 0) { + ret = data; + goto unlock; + } if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; @@ -361,6 +371,8 @@ msg_bytes_ready: copied = -EAGAIN; } ret = copied; + +unlock: release_sock(sk); sk_psock_put(sk, psock); return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ab87f0285b72..00d04ab68958 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -693,6 +693,23 @@ new_measure: tp->rcv_rtt_est.time = tp->tcp_mstamp; } +static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp) +{ + u32 delta, delta_us; + + delta = tcp_time_stamp_ts(tp) - tp->rx_opt.rcv_tsecr; + if (tp->tcp_usec_ts) + return delta; + + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; + delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + return delta_us; + } + return -1; +} + static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb) { @@ -704,15 +721,10 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, if (TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) { - u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - u32 delta_us; - - if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { - if (!delta) - delta = 1; - delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - tcp_rcv_rtt_update(tp, delta_us, 0); - } + s32 delta = tcp_rtt_tsopt_us(tp); + + if (delta >= 0) + tcp_rcv_rtt_update(tp, delta, 0); } } @@ -2222,16 +2234,17 @@ void tcp_enter_loss(struct sock *sk) * restore sanity to the SACK scoreboard. If the apparent reneging * persists until this RTO then we'll clear the SACK scoreboard. */ -static bool tcp_check_sack_reneging(struct sock *sk, int flag) +static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag) { - if (flag & FLAG_SACK_RENEGING && - flag & FLAG_SND_UNA_ADVANCED) { + if (*ack_flag & FLAG_SACK_RENEGING && + *ack_flag & FLAG_SND_UNA_ADVANCED) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX); + *ack_flag &= ~FLAG_SET_XMIT_TIMER; return true; } return false; @@ -2442,7 +2455,7 @@ static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp, const struct sk_buff *skb) { return (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) && - tcp_tsopt_ecr_before(tp, tcp_skb_timestamp(skb)); + tcp_tsopt_ecr_before(tp, tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb)); } /* Nothing was retransmitted or returned timestamp is less @@ -2856,7 +2869,7 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack) static void tcp_update_rto_time(struct tcp_sock *tp) { if (tp->rto_stamp) { - tp->total_rto_time += tcp_time_stamp(tp) - tp->rto_stamp; + tp->total_rto_time += tcp_time_stamp_ms(tp) - tp->rto_stamp; tp->rto_stamp = 0; } } @@ -3009,7 +3022,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, tp->prior_ssthresh = 0; /* B. In all the states check for reneging SACKs. */ - if (tcp_check_sack_reneging(sk, flag)) + if (tcp_check_sack_reneging(sk, ack_flag)) return; /* C. Check consistency of the current state. */ @@ -3146,17 +3159,10 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && - flag & FLAG_ACKED) { - u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - - if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { - if (!delta) - delta = 1; - seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - ca_rtt_us = seq_rtt_us; - } - } + if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && + tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) + seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp); + rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) return false; @@ -6293,7 +6299,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, - tcp_time_stamp(tp))) { + tcp_time_stamp_ts(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; @@ -7042,6 +7048,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, req->syncookie = want_cookie; tcp_rsk(req)->af_specific = af_ops; tcp_rsk(req)->ts_off = 0; + tcp_rsk(req)->req_usec_ts = -1; #if IS_ENABLED(CONFIG_MPTCP) tcp_rsk(req)->is_mptcp = 0; #endif diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2519f530b114..7583d4e34c8c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -296,6 +296,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = NULL; goto failure; } + tp->tcp_usec_ts = dst_tcp_usec_ts(&rt->dst); /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); @@ -954,7 +955,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp_raw() + tcptw->tw_ts_offset, + tcp_tw_tsval(tcptw), tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -988,7 +989,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, + tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), @@ -1870,6 +1871,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TLS_DEVICE tail->decrypted != skb->decrypted || #endif + !mptcp_skb_can_collapse(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index ae36780977d2..52fe17167460 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -272,7 +272,7 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct tcp_sock *tp = tcp_sk(sk); struct lp *lp = inet_csk_ca(sk); - u32 now = tcp_time_stamp(tp); + u32 now = tcp_time_stamp_ts(tp); u32 delta; if (sample->rtt_us > 0) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 3f87611077ef..ace806c5bd0c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -300,6 +300,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_ts_recent = tp->rx_opt.ts_recent; tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp; tcptw->tw_ts_offset = tp->tsoffset; + tw->tw_usec_ts = tp->tcp_usec_ts; tcptw->tw_last_oow_ack_time = 0; tcptw->tw_tx_delay = tp->tcp_tx_delay; tw->tw_txhash = sk->sk_txhash; @@ -554,21 +555,29 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { + newtp->tcp_usec_ts = treq->req_usec_ts; newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { + newtp->tcp_usec_ts = 0; newtp->rx_opt.ts_recent_stamp = 0; newtp->tcp_header_len = sizeof(struct tcphdr); } if (req->num_timeout) { - newtp->undo_marker = treq->snt_isn; - newtp->retrans_stamp = div_u64(treq->snt_synack, - USEC_PER_SEC / TCP_TS_HZ); newtp->total_rto = req->num_timeout; - newtp->total_rto_recoveries = 1; - newtp->total_rto_time = tcp_time_stamp_raw() - + newtp->undo_marker = treq->snt_isn; + if (newtp->tcp_usec_ts) { + newtp->retrans_stamp = treq->snt_synack; + newtp->total_rto_time = (u32)(tcp_clock_us() - + newtp->retrans_stamp) / USEC_PER_MSEC; + } else { + newtp->retrans_stamp = div_u64(treq->snt_synack, + USEC_PER_SEC / TCP_TS_HZ); + newtp->total_rto_time = tcp_clock_ms() - newtp->retrans_stamp; + } + newtp->total_rto_recoveries = 1; } newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8e6ebf35ed58..ca4d7594efd4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -799,7 +799,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) { opts->options |= OPTION_TS; - opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; + opts->tsval = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -884,7 +884,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, } if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; + opts->tsval = tcp_skb_timestamp_ts(tcp_rsk(req)->req_usec_ts, skb) + + tcp_rsk(req)->ts_off; opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -943,7 +944,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0; + opts->tsval = skb ? tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } @@ -1696,14 +1698,6 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mss_now -= icsk->icsk_af_ops->net_frag_header_len; - } - /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; @@ -1731,21 +1725,11 @@ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - int mtu; - mtu = mss + + return mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; - - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mtu += icsk->icsk_af_ops->net_frag_header_len; - } - return mtu; } EXPORT_SYMBOL(tcp_mss_to_mtu); @@ -2535,6 +2519,18 @@ static bool tcp_pacing_check(struct sock *sk) return true; } +static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk) +{ + const struct rb_node *node = sk->tcp_rtx_queue.rb_node; + + /* No skb in the rtx queue. */ + if (!node) + return true; + + /* Only one skb in rtx queue. */ + return !node->rb_left && !node->rb_right; +} + /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) @@ -2573,12 +2569,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit += extra_bytes; } if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send skb if rtx queue is empty. + /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (tcp_rtx_queue_empty(sk)) + if (tcp_rtx_queue_empty_or_single_skb(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2782,7 +2778,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, rto_delta_us; + u32 timeout, timeout_us, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS @@ -2806,11 +2802,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { - timeout = usecs_to_jiffies(tp->srtt_us >> 2); + timeout_us = tp->srtt_us >> 2; if (tp->packets_out == 1) - timeout += TCP_RTO_MIN; + timeout_us += tcp_rto_min_us(sk); else - timeout += TCP_TIMEOUT_MIN; + timeout_us += TCP_TIMEOUT_MIN_US; + timeout = usecs_to_jiffies(timeout_us); } else { timeout = TCP_TIMEOUT_INIT; } @@ -3366,7 +3363,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) /* Save stamp of the first (attempted) retransmit. */ if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_skb_timestamp(skb); + tp->retrans_stamp = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb); if (tp->undo_retrans < 0) tp->undo_retrans = 0; @@ -3652,6 +3649,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); memset(&opts, 0, sizeof(opts)); + if (tcp_rsk(req)->req_usec_ts < 0) + tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) @@ -3948,7 +3947,7 @@ int tcp_connect(struct sock *sk) tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tcp_mstamp_refresh(tp); - tp->retrans_stamp = tcp_time_stamp(tp); + tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index acf4869c5d3b..bba10110fbbc 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -104,7 +104,7 @@ bool tcp_rack_mark_lost(struct sock *sk) tp->rack.advanced = 0; tcp_rack_detect_loss(sk, &timeout); if (timeout) { - timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN; + timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US); inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0862b73dd3b5..1f9f6c1c196b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -26,14 +26,18 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - u32 elapsed, start_ts, user_timeout; + const struct tcp_sock *tp = tcp_sk(sk); + u32 elapsed, user_timeout; s32 remaining; - start_ts = tcp_sk(sk)->retrans_stamp; user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (!user_timeout) return icsk->icsk_rto; - elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; + + elapsed = tcp_time_stamp_ts(tp) - tp->retrans_stamp; + if (tp->tcp_usec_ts) + elapsed /= USEC_PER_MSEC; + remaining = user_timeout - elapsed; if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ @@ -212,12 +216,13 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { - unsigned int start_ts; + struct tcp_sock *tp = tcp_sk(sk); + unsigned int start_ts, delta; if (!inet_csk(sk)->icsk_retransmits) return false; - start_ts = tcp_sk(sk)->retrans_stamp; + start_ts = tp->retrans_stamp; if (likely(timeout == 0)) { unsigned int rto_base = TCP_RTO_MIN; @@ -226,7 +231,12 @@ static bool retransmits_timed_out(struct sock *sk, timeout = tcp_model_timeout(sk, boundary, rto_base); } - return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; + if (tp->tcp_usec_ts) { + /* delta maybe off up to a jiffy due to timer granularity. */ + delta = tp->tcp_mstamp - start_ts + jiffies_to_usecs(1); + return (s32)(delta - timeout * USEC_PER_MSEC) >= 0; + } + return (s32)(tcp_time_stamp_ts(tp) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ @@ -422,7 +432,7 @@ static void tcp_update_rto_stats(struct sock *sk) if (!icsk->icsk_retransmits) { tp->total_rto_recoveries++; - tp->rto_stamp = tcp_time_stamp(tp); + tp->rto_stamp = tcp_time_stamp_ms(tp); } icsk->icsk_retransmits++; tp->total_rto++; @@ -462,26 +472,24 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_time_stamp(tp); + tp->retrans_stamp = tcp_time_stamp_ts(tp); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, req->timeout << req->num_timeout, TCP_RTO_MAX); } static bool tcp_rtx_probe0_timed_out(const struct sock *sk, - const struct sk_buff *skb) + const struct sk_buff *skb, + u32 rtx_delta) { const struct tcp_sock *tp = tcp_sk(sk); const int timeout = TCP_RTO_MAX * 2; - u32 rcv_delta, rtx_delta; + u32 rcv_delta; rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; - rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - - (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); - - return rtx_delta > timeout; + return msecs_to_jiffies(rtx_delta) > timeout; } /** @@ -534,7 +542,11 @@ void tcp_retransmit_timer(struct sock *sk) struct inet_sock *inet = inet_sk(sk); u32 rtx_delta; - rtx_delta = tcp_time_stamp(tp) - (tp->retrans_stamp ?: tcp_skb_timestamp(skb)); + rtx_delta = tcp_time_stamp_ts(tp) - (tp->retrans_stamp ?: + tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb)); + if (tp->tcp_usec_ts) + rtx_delta /= USEC_PER_MSEC; + if (sk->sk_family == AF_INET) { net_dbg_ratelimited("Probing zero-window on %pI4:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n", &inet->inet_daddr, ntohs(inet->inet_dport), @@ -551,7 +563,7 @@ void tcp_retransmit_timer(struct sock *sk) rtx_delta); } #endif - if (tcp_rtx_probe0_timed_out(sk, skb)) { + if (tcp_rtx_probe0_timed_out(sk, skb, rtx_delta)) { tcp_write_err(sk); goto out; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c2d471ad7922..3aaea56b5166 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1399,6 +1399,7 @@ retry: idev->cnf.temp_valid_lft + age); cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor; cfg.preferred_lft = min_t(__u32, ifp->prefered_lft, cfg.preferred_lft); + cfg.preferred_lft = min_t(__u32, cfg.valid_lft, cfg.preferred_lft); cfg.plen = ifp->prefix_len; tmp_tstamp = ifp->tstamp; @@ -1406,15 +1407,23 @@ retry: write_unlock_bh(&idev->lock); - /* A temporary address is created only if this calculated Preferred - * Lifetime is greater than REGEN_ADVANCE time units. In particular, - * an implementation must not create a temporary address with a zero - * Preferred Lifetime. + /* From RFC 4941: + * + * A temporary address is created only if this calculated Preferred + * Lifetime is greater than REGEN_ADVANCE time units. In + * particular, an implementation must not create a temporary address + * with a zero Preferred Lifetime. + * + * Clamp the preferred lifetime to a minimum of regen_advance, unless + * that would exceed valid_lft. + * * Use age calculation as in addrconf_verify to avoid unnecessary * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (cfg.preferred_lft <= regen_advance + age) { + if (cfg.preferred_lft <= regen_advance + age) + cfg.preferred_lft = regen_advance + age + 1; + if (cfg.preferred_lft > cfg.valid_lft) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index fddd0cbdede1..2cc1a45742d8 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -770,7 +770,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; @@ -831,7 +833,7 @@ int esp6_input_done2(struct sk_buff *skb, int err) /* * 1) if the NAT-T peer's IP or port changed then - * advertize the change to the keying daemon. + * advertise the change to the keying daemon. * This is an inbound SA, so just compare * SRC ports. */ diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index f6f5b83dd954..7563f8c6aa87 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -46,7 +46,7 @@ struct ioam6_lwt { struct ioam6_lwt_encap tuninfo; }; -static struct netlink_range_validation freq_range = { +static const struct netlink_range_validation freq_range = { .min = IOAM6_IPTUNNEL_FREQ_MIN, .max = IOAM6_IPTUNNEL_FREQ_MAX, }; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a471c7e91761..a722a43dd668 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -117,6 +117,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * return res; } + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); @@ -162,7 +164,13 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, int err; skb_mark_not_on_list(segs); - err = ip6_fragment(net, sk, segs, ip6_finish_output2); + /* Last GSO segment can be smaller than gso_size (and MTU). + * Adding a fragment header would produce an "atomic fragment", + * which is considered harmful (RFC-8021). Avoid that. + */ + err = segs->len > mtu ? + ip6_fragment(net, sk, segs, ip6_finish_output2) : + ip6_finish_output2(net, sk, segs); if (err && ret == 0) ret = err; } @@ -170,6 +178,16 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, return ret; } +static int ip6_finish_output_gso(struct net *net, struct sock *sk, + struct sk_buff *skb, unsigned int mtu) +{ + if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && + !skb_gso_validate_network_len(skb, mtu)) + return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); + + return ip6_finish_output2(net, sk, skb); +} + static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; @@ -183,17 +201,14 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff #endif mtu = ip6_skb_dst_mtu(skb); - if (skb_is_gso(skb) && - !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && - !skb_gso_validate_network_len(skb, mtu)) - return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); + if (skb_is_gso(skb)) + return ip6_finish_output_gso(net, sk, skb, mtu); - if ((skb->len > mtu && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb)) || + if (skb->len > mtu || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(net, sk, skb, ip6_finish_output2); - else - return ip6_finish_output2(net, sk, skb); + + return ip6_finish_output2(net, sk, skb); } static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -328,7 +343,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -1015,9 +1030,6 @@ slow_path: return err; fail_toobig: - if (skb->sk && dst_allfrag(skb_dst(skb))) - sk_gso_disable(skb->sk); - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; @@ -1281,74 +1293,6 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); -/** - * ip6_dst_lookup_tunnel - perform route lookup on tunnel - * @skb: Packet for which lookup is done - * @dev: Tunnel device - * @net: Network namespace of tunnel device - * @sock: Socket which provides route info - * @saddr: Memory to store the src ip address - * @info: Tunnel information - * @protocol: IP protocol - * @use_cache: Flag to enable cache usage - * This function performs a route lookup on a tunnel - * - * It returns a valid dst pointer and stores src address to be used in - * tunnel in param saddr on success, else a pointer encoded error code. - */ - -struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, - struct net_device *dev, - struct net *net, - struct socket *sock, - struct in6_addr *saddr, - const struct ip_tunnel_info *info, - u8 protocol, - bool use_cache) -{ - struct dst_entry *dst = NULL; -#ifdef CONFIG_DST_CACHE - struct dst_cache *dst_cache; -#endif - struct flowi6 fl6; - __u8 prio; - -#ifdef CONFIG_DST_CACHE - dst_cache = (struct dst_cache *)&info->dst_cache; - if (use_cache) { - dst = dst_cache_get_ip6(dst_cache, saddr); - if (dst) - return dst; - } -#endif - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = skb->mark; - fl6.flowi6_proto = protocol; - fl6.daddr = info->key.u.ipv6.dst; - fl6.saddr = info->key.u.ipv6.src; - prio = info->key.tos; - fl6.flowlabel = ip6_make_flowinfo(prio, info->key.label); - - dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, - NULL); - if (IS_ERR(dst)) { - netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); - return ERR_PTR(-ENETUNREACH); - } - if (dst->dev == dev) { /* is this necessary? */ - netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); - dst_release(dst); - return ERR_PTR(-ELOOP); - } -#ifdef CONFIG_DST_CACHE - if (use_cache) - dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); -#endif - *saddr = fl6.saddr; - return dst; -} -EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel); - static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { @@ -1450,10 +1394,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, cork->base.mark = ipc6->sockc.mark; sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags); - if (dst_allfrag(xfrm_dst_path(&rt->dst))) - cork->base.flags |= IPCORK_ALLFRAG; cork->base.length = 0; - cork->base.transmit_time = ipc6->sockc.transmit_time; return 0; @@ -1510,8 +1451,6 @@ static int __ip6_append_data(struct sock *sk, headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + - (dst_allfrag(&rt->dst) ? - sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; if (mtu <= fragheaderlen || @@ -1621,7 +1560,7 @@ emsgsize: while (length > 0) { /* Check if the remaining data fits into current packet. */ - copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; + copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; @@ -1652,7 +1591,7 @@ alloc_new_skb: */ datalen = length + fraggap; - if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) + if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; pagedlen = 0; @@ -1901,7 +1840,6 @@ static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) struct dst_entry *dst = cork->base.dst; cork->base.dst = NULL; - cork->base.flags &= ~IPCORK_ALLFRAG; skb_dst_set(skb, dst); } @@ -1922,7 +1860,6 @@ static void ip6_cork_release(struct inet_cork_full *cork, if (cork->base.dst) { dst_release(cork->base.dst); cork->base.dst = NULL; - cork->base.flags &= ~IPCORK_ALLFRAG; } } @@ -1987,7 +1924,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->tstamp = cork->base.transmit_time; ip6_cork_steal_dst(skb, cork); - IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index 70d38705c92f..a7bf0327b380 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -1,3 +1,4 @@ + // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> @@ -112,4 +113,73 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); +/** + * udp_tunnel6_dst_lookup - perform route lookup on UDP tunnel + * @skb: Packet for which lookup is done + * @dev: Tunnel device + * @net: Network namespace of tunnel device + * @sock: Socket which provides route info + * @oif: Index of the output interface + * @saddr: Memory to store the src ip address + * @key: Tunnel information + * @sport: UDP source port + * @dport: UDP destination port + * @dsfield: The traffic class field + * @dst_cache: The dst cache to use for lookup + * This function performs a route lookup on a UDP tunnel + * + * It returns a valid dst pointer and stores src address to be used in + * tunnel in param saddr on success, else a pointer encoded error code. + */ + +struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, + struct net_device *dev, + struct net *net, + struct socket *sock, + int oif, + struct in6_addr *saddr, + const struct ip_tunnel_key *key, + __be16 sport, __be16 dport, u8 dsfield, + struct dst_cache *dst_cache) +{ + struct dst_entry *dst = NULL; + struct flowi6 fl6; + +#ifdef CONFIG_DST_CACHE + if (dst_cache) { + dst = dst_cache_get_ip6(dst_cache, saddr); + if (dst) + return dst; + } +#endif + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = IPPROTO_UDP; + fl6.flowi6_oif = oif; + fl6.daddr = key->u.ipv6.dst; + fl6.saddr = key->u.ipv6.src; + fl6.fl6_sport = sport; + fl6.fl6_dport = dport; + fl6.flowlabel = ip6_make_flowinfo(dsfield, key->label); + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, + NULL); + if (IS_ERR(dst)) { + netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (dst->dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); + dst_release(dst); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (dst_cache) + dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); +#endif + *saddr = fl6.saddr; + return dst; +} +EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup); + MODULE_LICENSE("GPL"); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 99e28b444a4c..b75d3c9d41bb 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1789,7 +1789,7 @@ static void mld_sendpack(struct sk_buff *skb) rcu_read_lock(); idev = __in6_dev_get(skb->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - sizeof(*pip6); @@ -2147,8 +2147,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) full_len = sizeof(struct ipv6hdr) + payload_len; rcu_read_lock(); - IP6_UPD_PO_STATS(net, __in6_dev_get(dev), - IPSTATS_MIB_OUT, full_len); + IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS); rcu_read_unlock(); skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 679443d7ecb5..a19999b30bc0 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -504,7 +504,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, rcu_read_lock(); idev = __in6_dev_get(dst->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index a88b2ce4a3cb..8dd4cd0c47bd 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -31,10 +31,10 @@ static const struct xt_table packet_mangler = { static unsigned int ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - unsigned int ret; struct in6_addr saddr, daddr; - u_int8_t hop_limit; - u_int32_t flowlabel, mark; + unsigned int ret, verdict; + u32 flowlabel, mark; + u8 hop_limit; int err; /* save source/dest address, mark, hoplimit, flowlabel, priority, */ @@ -47,8 +47,9 @@ ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *sta flowlabel = *((u_int32_t *)ipv6_hdr(skb)); ret = ip6t_do_table(priv, skb, state); + verdict = ret & NF_VERDICT_MASK; - if (ret != NF_DROP && ret != NF_STOLEN && + if (verdict != NF_DROP && verdict != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || !ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) || skb->mark != mark || diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index e20b3705c2d2..6d1d9221649d 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -61,7 +61,7 @@ static const struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("Ip6InDelivers", IPSTATS_MIB_INDELIVERS), SNMP_MIB_ITEM("Ip6OutForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS), - SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTPKTS), + SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTREQUESTS), SNMP_MIB_ITEM("Ip6OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("Ip6OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("Ip6ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -84,6 +84,7 @@ static const struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InECT1Pkts", IPSTATS_MIB_ECT1PKTS), SNMP_MIB_ITEM("Ip6InECT0Pkts", IPSTATS_MIB_ECT0PKTS), SNMP_MIB_ITEM("Ip6InCEPkts", IPSTATS_MIB_CEPKTS), + SNMP_MIB_ITEM("Ip6OutTransmits", IPSTATS_MIB_OUTPKTS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a2aa54a2baae..dd0a4e73e602 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -651,7 +651,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, * have been queued for deletion. */ rcu_read_lock(); - IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d410703bb5a1..dc27988512a6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -286,6 +286,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, goto failure; } + tp->tcp_usec_ts = dst_tcp_usec_ts(dst); tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { @@ -1096,7 +1097,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp_raw() + tcptw->tw_ts_offset, + tcp_tw_tsval(tcptw), tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority, tw->tw_txhash); @@ -1123,7 +1124,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, + tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, @@ -1894,7 +1895,6 @@ const struct inet_connection_sock_af_ops ipv6_specific = { .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), - .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index ad07904642ca..5f7b1fdbffe6 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -95,7 +95,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) return -EMSGSIZE; } - if (toobig || dst_allfrag(skb_dst(skb))) + if (toobig) return ip6_fragment(net, sk, skb, __xfrm6_output_finish); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 41a680c76d2e..42fb6996b077 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -117,10 +117,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (likely(xdst->u.rt6.rt6i_idev)) - in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); rt6_uncached_list_del(&xdst->u.rt6); + if (likely(xdst->u.rt6.rt6i_idev)) + in6_dev_put(xdst->u.rt6.rt6i_idev); xfrm_dst_destroy(xdst); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6f679d2c0409..64352e4e6d00 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2469,8 +2469,7 @@ ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) /* drop unicast public action frames when using MPF */ if (is_unicast_ether_addr(mgmt->da) && - ieee80211_is_public_action((void *)rx->skb->data, - rx->skb->len)) + ieee80211_is_protected_dual_of_public_action(rx->skb)) return RX_DROP_U_UNPROT_UNICAST_PUB_ACTION; } diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index 84e531f86b82..bcf1dbf3a432 100644 --- a/net/mptcp/Makefile +++ b/net/mptcp/Makefile @@ -2,7 +2,8 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ - mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o + mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o \ + mptcp_pm_gen.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index e72b518c5d02..13fe0748dde8 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -27,6 +27,7 @@ struct mptcp_pernet { #endif unsigned int add_addr_timeout; + unsigned int close_timeout; unsigned int stale_loss_cnt; u8 mptcp_enabled; u8 checksum_enabled; @@ -65,6 +66,13 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net) return mptcp_get_pernet(net)->stale_loss_cnt; } +unsigned int mptcp_close_timeout(const struct sock *sk) +{ + if (sock_flag(sk, SOCK_DEAD)) + return TCP_TIMEWAIT_LEN; + return mptcp_get_pernet(sock_net(sk))->close_timeout; +} + int mptcp_get_pm_type(const struct net *net) { return mptcp_get_pernet(net)->pm_type; @@ -79,6 +87,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; + pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; pernet->allow_join_initial_addr_port = 1; pernet->stale_loss_cnt = 4; @@ -141,6 +150,12 @@ static struct ctl_table mptcp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dostring, }, + { + .procname = "close_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, {} }; @@ -163,6 +178,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[4].data = &pernet->stale_loss_cnt; table[5].data = &pernet->pm_type; table[6].data = &pernet->scheduler; + table[7].data = &pernet->close_timeout; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index bceaab8dd8e4..74698582a285 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -52,6 +52,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); + mptcp_sk(sk)->bytes_received += skb->len; sk->sk_data_ready(sk); diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c new file mode 100644 index 000000000000..a2325e70ddab --- /dev/null +++ b/net/mptcp/mptcp_pm_gen.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/mptcp.yaml */ +/* YNL-GEN kernel source */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "mptcp_pm_gen.h" + +#include <uapi/linux/mptcp_pm.h> + +/* Common nested types */ +const struct nla_policy mptcp_pm_address_nl_policy[MPTCP_PM_ADDR_ATTR_IF_IDX + 1] = { + [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, + [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, + [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, + [MPTCP_PM_ADDR_ATTR_ADDR6] = NLA_POLICY_EXACT_LEN(16), + [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16, }, + [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32, }, + [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32, }, +}; + +/* MPTCP_PM_CMD_ADD_ADDR - do */ +const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_DEL_ADDR - do */ +const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_GET_ADDR - do */ +const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_FLUSH_ADDRS - do */ +const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_SET_LIMITS - do */ +const struct nla_policy mptcp_pm_set_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1] = { + [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_GET_LIMITS - do */ +const struct nla_policy mptcp_pm_get_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1] = { + [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_SET_FLAGS - do */ +const struct nla_policy mptcp_pm_set_flags_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_ANNOUNCE - do */ +const struct nla_policy mptcp_pm_announce_nl_policy[MPTCP_PM_ATTR_TOKEN + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_REMOVE - do */ +const struct nla_policy mptcp_pm_remove_nl_policy[MPTCP_PM_ATTR_LOC_ID + 1] = { + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_LOC_ID] = { .type = NLA_U8, }, +}; + +/* MPTCP_PM_CMD_SUBFLOW_CREATE - do */ +const struct nla_policy mptcp_pm_subflow_create_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_SUBFLOW_DESTROY - do */ +const struct nla_policy mptcp_pm_subflow_destroy_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* Ops table for mptcp_pm */ +const struct genl_ops mptcp_pm_nl_ops[11] = { + { + .cmd = MPTCP_PM_CMD_ADD_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_add_addr_doit, + .policy = mptcp_pm_add_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_DEL_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_del_addr_doit, + .policy = mptcp_pm_del_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_GET_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_get_addr_doit, + .dumpit = mptcp_pm_nl_get_addr_dumpit, + .policy = mptcp_pm_get_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_flush_addrs_doit, + .policy = mptcp_pm_flush_addrs_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SET_LIMITS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_set_limits_doit, + .policy = mptcp_pm_set_limits_nl_policy, + .maxattr = MPTCP_PM_ATTR_SUBFLOWS, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_GET_LIMITS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_get_limits_doit, + .policy = mptcp_pm_get_limits_nl_policy, + .maxattr = MPTCP_PM_ATTR_SUBFLOWS, + }, + { + .cmd = MPTCP_PM_CMD_SET_FLAGS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_set_flags_doit, + .policy = mptcp_pm_set_flags_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_ANNOUNCE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_announce_doit, + .policy = mptcp_pm_announce_nl_policy, + .maxattr = MPTCP_PM_ATTR_TOKEN, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_REMOVE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_remove_doit, + .policy = mptcp_pm_remove_nl_policy, + .maxattr = MPTCP_PM_ATTR_LOC_ID, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SUBFLOW_CREATE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_subflow_create_doit, + .policy = mptcp_pm_subflow_create_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SUBFLOW_DESTROY, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_subflow_destroy_doit, + .policy = mptcp_pm_subflow_destroy_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, +}; diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h new file mode 100644 index 000000000000..10579d184587 --- /dev/null +++ b/net/mptcp/mptcp_pm_gen.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/mptcp.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_MPTCP_PM_GEN_H +#define _LINUX_MPTCP_PM_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <uapi/linux/mptcp_pm.h> + +/* Common nested types */ +extern const struct nla_policy mptcp_pm_address_nl_policy[MPTCP_PM_ADDR_ATTR_IF_IDX + 1]; + +extern const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_set_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1]; + +extern const struct nla_policy mptcp_pm_get_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1]; + +extern const struct nla_policy mptcp_pm_set_flags_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +extern const struct nla_policy mptcp_pm_announce_nl_policy[MPTCP_PM_ATTR_TOKEN + 1]; + +extern const struct nla_policy mptcp_pm_remove_nl_policy[MPTCP_PM_ATTR_LOC_ID + 1]; + +extern const struct nla_policy mptcp_pm_subflow_create_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +extern const struct nla_policy mptcp_pm_subflow_destroy_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +/* Ops table for mptcp_pm */ +extern const struct genl_ops mptcp_pm_nl_ops[11]; + +int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, + struct genl_info *info); +int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, + struct genl_info *info); + +#endif /* _LINUX_MPTCP_PM_GEN_H */ diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 9661f3812682..1529ec358815 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1104,29 +1104,6 @@ static const struct genl_multicast_group mptcp_pm_mcgrps[] = { }, }; -static const struct nla_policy -mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = { - [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, - [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, - [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, - [MPTCP_PM_ADDR_ATTR_ADDR6] = - NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), - [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16 }, - [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32 }, - [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32 }, -}; - -static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = { - [MPTCP_PM_ATTR_ADDR] = - NLA_POLICY_NESTED(mptcp_pm_addr_policy), - [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_LOC_ID] = { .type = NLA_U8, }, - [MPTCP_PM_ATTR_ADDR_REMOTE] = - NLA_POLICY_NESTED(mptcp_pm_addr_policy), -}; - void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk); @@ -1188,7 +1165,7 @@ static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[], /* no validation needed - was already done via nested policy */ err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, - mptcp_pm_addr_policy, info->extack); + mptcp_pm_address_nl_policy, info->extack); if (err) return err; @@ -1303,9 +1280,9 @@ next: return 0; } -static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; int ret; @@ -1484,9 +1461,9 @@ next: return 0; } -static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; unsigned int addr_max; @@ -1619,7 +1596,7 @@ static void __reset_counters(struct pm_nl_pernet *pernet) pernet->addrs = 0; } -static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); LIST_HEAD(free_list); @@ -1675,9 +1652,9 @@ nla_put_failure: return -EMSGSIZE; } -static int mptcp_nl_cmd_get_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; struct sk_buff *msg; @@ -1725,8 +1702,8 @@ fail: return ret; } -static int mptcp_nl_cmd_dump_addrs(struct sk_buff *msg, - struct netlink_callback *cb) +int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) { struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; @@ -1783,8 +1760,7 @@ static int parse_limit(struct genl_info *info, int id, unsigned int *limit) return 0; } -static int -mptcp_nl_cmd_set_limits(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); unsigned int rcv_addrs, subflows; @@ -1809,8 +1785,7 @@ unlock: return ret; } -static int -mptcp_nl_cmd_get_limits(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct sk_buff *msg; @@ -1919,7 +1894,7 @@ int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 return 0; } -static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, }; struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; @@ -2283,72 +2258,13 @@ nla_put_failure: nlmsg_free(skb); } -static const struct genl_small_ops mptcp_pm_ops[] = { - { - .cmd = MPTCP_PM_CMD_ADD_ADDR, - .doit = mptcp_nl_cmd_add_addr, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_DEL_ADDR, - .doit = mptcp_nl_cmd_del_addr, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, - .doit = mptcp_nl_cmd_flush_addrs, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_GET_ADDR, - .doit = mptcp_nl_cmd_get_addr, - .dumpit = mptcp_nl_cmd_dump_addrs, - }, - { - .cmd = MPTCP_PM_CMD_SET_LIMITS, - .doit = mptcp_nl_cmd_set_limits, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_GET_LIMITS, - .doit = mptcp_nl_cmd_get_limits, - }, - { - .cmd = MPTCP_PM_CMD_SET_FLAGS, - .doit = mptcp_nl_cmd_set_flags, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_ANNOUNCE, - .doit = mptcp_nl_cmd_announce, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_REMOVE, - .doit = mptcp_nl_cmd_remove, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_SUBFLOW_CREATE, - .doit = mptcp_nl_cmd_sf_create, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_SUBFLOW_DESTROY, - .doit = mptcp_nl_cmd_sf_destroy, - .flags = GENL_UNS_ADMIN_PERM, - }, -}; - static struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, - .maxattr = MPTCP_PM_ATTR_MAX, - .policy = mptcp_pm_policy, .netnsok = true, .module = THIS_MODULE, - .small_ops = mptcp_pm_ops, - .n_small_ops = ARRAY_SIZE(mptcp_pm_ops), + .ops = mptcp_pm_nl_ops, + .n_ops = ARRAY_SIZE(mptcp_pm_nl_ops), .resv_start_op = MPTCP_PM_CMD_SUBFLOW_DESTROY + 1, .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index d042d32beb4d..0f92e5b13a8a 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -145,7 +145,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); } -int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *addr = info->attrs[MPTCP_PM_ATTR_ADDR]; @@ -208,7 +208,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) return err; } -int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID]; @@ -270,7 +270,7 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) return err; } -int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; @@ -394,7 +394,7 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk, return NULL; } -int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c3b83cb390d9..1dacc072dcca 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -121,8 +121,6 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) ret = __mptcp_socket_create(msk); if (ret) return ERR_PTR(ret); - - mptcp_sockopt_sync(msk, msk->first); } return msk->first; @@ -863,9 +861,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); - if (move_skbs_to_msk(msk, ssk)) + if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); - mptcp_data_unlock(sk); } @@ -893,6 +890,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); mptcp_stop_tout_timer(sk); + __mptcp_propagate_sndbuf(sk, ssk); return true; } @@ -1079,15 +1077,16 @@ static void mptcp_enter_memory_pressure(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); bool first = true; - sk_stream_moderate_sndbuf(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (first) tcp_enter_memory_pressure(ssk); sk_stream_moderate_sndbuf(ssk); + first = false; } + __mptcp_sync_sndbuf(sk); } /* ensure we get enough memory for the frag hdr, beyond some minimal amount of @@ -1298,7 +1297,7 @@ alloc_skb: if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); - if (snd_una != msk->snd_nxt) { + if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { tcp_remove_empty_skb(ssk); return 0; } @@ -1306,11 +1305,6 @@ alloc_skb: zero_window_probe = true; data_seq = snd_una - 1; copy = 1; - - /* all mptcp-level data is acked, no skbs should be present into the - * ssk write queue - */ - WARN_ON_ONCE(reuse_skb); } copy = min_t(size_t, copy, info->limit - info->sent); @@ -1339,7 +1333,6 @@ alloc_skb: if (reuse_skb) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; mpext->data_len += copy; - WARN_ON_ONCE(zero_window_probe); goto out; } @@ -1767,6 +1760,18 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, return ret; } +static int do_copy_data_nocache(struct sock *sk, int copy, + struct iov_iter *from, char *to) +{ + if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { + if (!copy_from_iter_full_nocache(to, copy, from)) + return -EFAULT; + } else if (!copy_from_iter_full(to, copy, from)) { + return -EFAULT; + } + return 0; +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1840,11 +1845,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!sk_wmem_schedule(sk, total_ts)) goto wait_for_memory; - if (copy_page_from_iter(dfrag->page, offset, psize, - &msg->msg_iter) != psize) { - ret = -EFAULT; + ret = do_copy_data_nocache(sk, psize, &msg->msg_iter, + page_address(dfrag->page) + offset); + if (ret) goto do_error; - } /* data successfully copied into the write queue */ sk_forward_alloc_add(sk, -total_ts); @@ -1928,6 +1932,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, if (!(flags & MSG_PEEK)) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; + msk->bytes_consumed += count; } break; } @@ -1938,6 +1943,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); + msk->bytes_consumed += count; } if (copied >= len) @@ -2354,6 +2360,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) #define MPTCP_CF_PUSH BIT(1) #define MPTCP_CF_FASTCLOSE BIT(2) +/* be sure to send a reset only if the caller asked for it, also + * clean completely the subflow status when the subflow reaches + * TCP_CLOSE state + */ +static void __mptcp_subflow_disconnect(struct sock *ssk, + struct mptcp_subflow_context *subflow, + unsigned int flags) +{ + if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + (flags & MPTCP_CF_FASTCLOSE)) { + /* The MPTCP code never wait on the subflow sockets, TCP-level + * disconnect should never fail + */ + WARN_ON_ONCE(tcp_disconnect(ssk, 0)); + mptcp_subflow_ctx_reset(subflow); + } else { + tcp_shutdown(ssk, SEND_SHUTDOWN); + } +} + /* subflow sockets can be either outgoing (connect) or incoming * (accept). * @@ -2377,8 +2403,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (msk->in_accept_queue && msk->first == ssk && (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ - mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1)); sock_set_flag(sk, SOCK_DEAD); + mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1)); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); goto out_release; @@ -2391,7 +2417,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { - /* be sure to force the tcp_disconnect() path, + /* be sure to force the tcp_close path * to generate the egress reset */ ssk->sk_lingertime = 0; @@ -2401,11 +2427,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { - /* The MPTCP code never wait on the subflow sockets, TCP-level - * disconnect should never fail - */ - WARN_ON_ONCE(tcp_disconnect(ssk, 0)); - mptcp_subflow_ctx_reset(subflow); + __mptcp_subflow_disconnect(ssk, subflow, flags); release_sock(ssk); goto out; @@ -2438,6 +2460,7 @@ out_release: WRITE_ONCE(msk->first, NULL); out: + __mptcp_sync_sndbuf(sk); if (need_push) __mptcp_push_pending(sk, 0); @@ -2506,7 +2529,7 @@ static bool mptcp_close_tout_expired(const struct sock *sk) return false; return time_after32(tcp_jiffies32, - inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN); + inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk)); } static void mptcp_check_fastclose(struct mptcp_sock *msk) @@ -2649,7 +2672,7 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) return; close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + - TCP_TIMEWAIT_LEN; + mptcp_close_timeout(sk); /* the close timeout takes precedence on the fail one, and here at least one of * them is active @@ -2745,6 +2768,7 @@ static void __mptcp_init_sock(struct sock *sk) msk->rmem_fwd_alloc = 0; WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; + msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; @@ -2954,16 +2978,9 @@ void __mptcp_unaccepted_force_close(struct sock *sk) __mptcp_destroy_sock(sk); } -static __poll_t mptcp_check_readable(struct mptcp_sock *msk) +static __poll_t mptcp_check_readable(struct sock *sk) { - /* Concurrent splices from sk_receive_queue into receive_queue will - * always show at least one non-empty queue when checked in this order. - */ - if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) && - skb_queue_empty_lockless(&msk->receive_queue)) - return 0; - - return EPOLLIN | EPOLLRDNORM; + return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0; } static void mptcp_check_listen_stop(struct sock *sk) @@ -3001,7 +3018,7 @@ bool __mptcp_close(struct sock *sk, long timeout) goto cleanup; } - if (mptcp_check_readable(msk) || timeout < 0) { + if (mptcp_data_avail(msk) || timeout < 0) { /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ @@ -3098,12 +3115,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) { struct mptcp_sock *msk = mptcp_sk(sk); - /* Deny disconnect if other threads are blocked in sk_wait_event() - * or inet_wait_for_connect(). - */ - if (sk->sk_wait_pending) - return -EBUSY; - /* We are on the fastopen error path. We can't call straight into the * subflows cleanup code due to lock nesting (we are already under * msk->firstsocket lock). @@ -3134,6 +3145,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->snd_data_fin_enable = false; msk->rcv_fastclose = false; msk->use_64bit_ack = false; + msk->bytes_consumed = 0; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); @@ -3173,7 +3185,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); #endif - nsk->sk_wait_pending = 0; __mptcp_init_sock(nsk); msk = mptcp_sk(nsk); @@ -3216,7 +3227,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, * uses the correct data */ mptcp_copy_inaddrs(nsk, ssk); - mptcp_propagate_sndbuf(nsk, ssk); + __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); @@ -3394,6 +3405,8 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_set_connected(sk); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); + if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) + __mptcp_sync_sndbuf(sk); } __mptcp_update_rmem(sk); @@ -3438,6 +3451,14 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status) __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } + if (status & BIT(MPTCP_DELEGATE_SNDBUF)) { + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_sync_sndbuf(sk); + else + __set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags); + mptcp_data_unlock(sk); + } if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); } @@ -3522,6 +3543,7 @@ bool mptcp_finish_join(struct sock *ssk) /* active subflow, already present inside the conn_list */ if (!list_empty(&subflow->node)) { mptcp_subflow_joined(msk, ssk); + mptcp_propagate_sndbuf(parent, ssk); return true; } @@ -3906,7 +3928,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { - mask |= mptcp_check_readable(msk); + mask |= mptcp_check_readable(sk); if (shutdown & SEND_SHUTDOWN) mask |= EPOLLOUT | EPOLLWRNORM; else @@ -3944,6 +3966,7 @@ static const struct proto_ops mptcp_stream_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .set_rcvlowat = mptcp_set_rcvlowat, }; static struct inet_protosw mptcp_protosw = { @@ -4045,6 +4068,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif + .set_rcvlowat = mptcp_set_rcvlowat, }; static struct proto mptcp_v6_prot; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3612545fa62e..9092fcf18798 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -13,6 +13,8 @@ #include <uapi/linux/mptcp.h> #include <net/genetlink.h> +#include "mptcp_pm_gen.h" + #define MPTCP_SUPPORTED_VERSION 1 /* MPTCP option bits */ @@ -123,6 +125,7 @@ #define MPTCP_RETRANSMIT 4 #define MPTCP_FLUSH_JOIN_LIST 5 #define MPTCP_CONNECTED 6 +#define MPTCP_SYNC_SNDBUF 7 struct mptcp_skb_cb { u64 map_seq; @@ -267,6 +270,7 @@ struct mptcp_sock { atomic64_t rcv_wnd_sent; u64 rcv_data_fin_seq; u64 bytes_retrans; + u64 bytes_consumed; int rmem_fwd_alloc; int snd_burst; int old_wspace; @@ -432,11 +436,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) return (struct mptcp_subflow_request_sock *)rsk; } -enum mptcp_data_avail { - MPTCP_SUBFLOW_NODATA, - MPTCP_SUBFLOW_DATA_AVAIL, -}; - struct mptcp_delegated_action { struct napi_struct napi; struct list_head head; @@ -447,6 +446,7 @@ DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); #define MPTCP_DELEGATE_SCHEDULED 0 #define MPTCP_DELEGATE_SEND 1 #define MPTCP_DELEGATE_ACK 2 +#define MPTCP_DELEGATE_SNDBUF 3 #define MPTCP_DELEGATE_ACTIONS_MASK (~BIT(MPTCP_DELEGATE_SCHEDULED)) /* MPTCP subflow context */ @@ -492,7 +492,7 @@ struct mptcp_subflow_context { valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ __unused : 9; - enum mptcp_data_avail data_avail; + bool data_avail; bool scheduled; u32 remote_nonce; u64 thmac; @@ -520,6 +520,9 @@ struct mptcp_subflow_context { u32 setsockopt_seq; u32 stale_rcv_tstamp; + int cached_sndbuf; /* sndbuf size when last synced with the msk sndbuf, + * protected by the msk socket lock + */ struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ @@ -613,6 +616,7 @@ unsigned int mptcp_get_add_addr_timeout(const struct net *net); int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); +unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, @@ -661,6 +665,24 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk); int mptcp_sched_get_send(struct mptcp_sock *msk); int mptcp_sched_get_retrans(struct mptcp_sock *msk); +static inline u64 mptcp_data_avail(const struct mptcp_sock *msk) +{ + return READ_ONCE(msk->bytes_received) - READ_ONCE(msk->bytes_consumed); +} + +static inline bool mptcp_epollin_ready(const struct sock *sk) +{ + /* mptcp doesn't have to deal with small skbs in the receive queue, + * at it can always coalesce them + */ + return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) || + (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) || + READ_ONCE(tcp_memory_pressure); +} + +int mptcp_set_rcvlowat(struct sock *sk, int val); + static inline bool __tcp_can_send(const struct sock *ssk) { /* only send if our side has not closed yet */ @@ -735,6 +757,7 @@ static inline bool mptcp_is_fully_established(struct sock *sk) return inet_sk_state_load(sk) == TCP_ESTABLISHED && READ_ONCE(mptcp_sk(sk)->fully_established); } + void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); @@ -762,13 +785,52 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } -static inline bool mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +static inline void __mptcp_sync_sndbuf(struct sock *sk) { - if ((sk->sk_userlocks & SOCK_SNDBUF_LOCK) || ssk->sk_sndbuf <= READ_ONCE(sk->sk_sndbuf)) - return false; + struct mptcp_subflow_context *subflow; + int ssk_sndbuf, new_sndbuf; + + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return; + + new_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[0]; + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + ssk_sndbuf = READ_ONCE(mptcp_subflow_tcp_sock(subflow)->sk_sndbuf); + + subflow->cached_sndbuf = ssk_sndbuf; + new_sndbuf += ssk_sndbuf; + } + + /* the msk max wmem limit is <nr_subflows> * tcp wmem[2] */ + WRITE_ONCE(sk->sk_sndbuf, new_sndbuf); +} + +/* The called held both the msk socket and the subflow socket locks, + * possibly under BH + */ +static inline void __mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (READ_ONCE(ssk->sk_sndbuf) != subflow->cached_sndbuf) + __mptcp_sync_sndbuf(sk); +} + +/* the caller held only the subflow socket lock, either in process or + * BH context. Additionally this can be called under the msk data lock, + * so we can't acquire such lock here: let the delegate action acquires + * the needed locks in suitable order. + */ +static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (likely(READ_ONCE(ssk->sk_sndbuf) == subflow->cached_sndbuf)) + return; - WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf); - return true; + local_bh_disable(); + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_SNDBUF); + local_bh_enable(); } static inline void mptcp_write_space(struct sock *sk) @@ -877,10 +939,6 @@ void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); -int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info); void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 18ce624bfde2..574e221bb765 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -95,6 +95,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in case SO_SNDBUFFORCE: ssk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); + mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; break; case SO_RCVBUF: case SO_RCVBUFFORCE: @@ -738,7 +739,7 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname, mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - ip_sock_set_tos(ssk, val); + __ip_sock_set_tos(ssk, val); } release_sock(sk); @@ -1411,12 +1412,14 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) ssk->sk_bound_dev_if = sk->sk_bound_dev_if; ssk->sk_incoming_cpu = sk->sk_incoming_cpu; ssk->sk_ipv6only = sk->sk_ipv6only; - ip_sock_set_tos(ssk, inet_sk(sk)->tos); + __ip_sock_set_tos(ssk, inet_sk(sk)->tos); if (sk->sk_userlocks & tx_rx_locks) { ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks; - if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) { WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); + mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; + } if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf); } @@ -1444,37 +1447,63 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); } -static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) -{ - bool slow = lock_sock_fast(ssk); - - sync_socket_options(msk, ssk); - - unlock_sock_fast(ssk, slow); -} - -void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) +void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); msk_owned_by_me(msk); + ssk->sk_rcvlowat = 0; + + /* subflows must ignore any latency-related settings: will not affect + * the user-space - only the msk is relevant - but will foul the + * mptcp scheduler + */ + tcp_sk(ssk)->notsent_lowat = UINT_MAX; + if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { - __mptcp_sockopt_sync(msk, ssk); + sync_socket_options(msk, ssk); subflow->setsockopt_seq = msk->setsockopt_seq; } } -void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) +/* unfortunately this is different enough from the tcp version so + * that we can't factor it out + */ +int mptcp_set_rcvlowat(struct sock *sk, int val) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct mptcp_subflow_context *subflow; + int space, cap; - msk_owned_by_me(msk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + cap = sk->sk_rcvbuf >> 1; + else + cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; + val = min(val, cap); + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); - if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { - sync_socket_options(msk, ssk); + /* Check if we need to signal EPOLLIN right now */ + if (mptcp_epollin_ready(sk)) + sk->sk_data_ready(sk); - subflow->setsockopt_seq = msk->setsockopt_seq; + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + return 0; + + space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val); + if (space <= sk->sk_rcvbuf) + return 0; + + /* propagate the rcvbuf changes to all the subflows */ + WRITE_ONCE(sk->sk_rcvbuf, space); + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + + slow = lock_sock_fast(ssk); + WRITE_ONCE(ssk->sk_rcvbuf, space); + tcp_sk(ssk)->window_clamp = val; + unlock_sock_fast(ssk, slow); } + return 0; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9c1f8d1d63d2..e120e9616454 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -421,6 +421,7 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc void __mptcp_set_connected(struct sock *sk) { + __mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first); if (sk->sk_state == TCP_SYN_SENT) { inet_sk_state_store(sk, TCP_ESTABLISHED); sk->sk_state_change(sk); @@ -472,7 +473,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) return; msk = mptcp_sk(parent); - mptcp_propagate_sndbuf(parent, sk); subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; @@ -1237,7 +1237,7 @@ static bool subflow_check_data_avail(struct sock *ssk) struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); if (subflow->data_avail) return true; @@ -1271,7 +1271,7 @@ static bool subflow_check_data_avail(struct sock *ssk) continue; } - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); break; } return true; @@ -1293,7 +1293,7 @@ fallback: goto reset; } mptcp_subflow_fail(msk, ssk); - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); return true; } @@ -1310,7 +1310,7 @@ reset: while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); tcp_send_active_reset(ssk, GFP_ATOMIC); - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); return false; } @@ -1322,7 +1322,7 @@ reset: subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); return true; } @@ -1334,7 +1334,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, @@ -1405,10 +1405,18 @@ static void subflow_data_ready(struct sock *sk) WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && !subflow->mp_join && !(state & TCPF_CLOSE)); - if (mptcp_subflow_data_available(sk)) + if (mptcp_subflow_data_available(sk)) { mptcp_data_ready(parent, sk); - else if (unlikely(sk->sk_err)) + + /* subflow-level lowat test are not relevant. + * respect the msk-level threshold eventually mandating an immediate ack + */ + if (mptcp_data_avail(msk) < parent->sk_rcvlowat && + (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } else if (unlikely(sk->sk_err)) { subflow_error_report(sk); + } } static void subflow_write_space(struct sock *ssk) @@ -1525,8 +1533,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, if (addr.ss_family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif - mptcp_sockopt_sync(msk, ssk); - ssk->sk_bound_dev_if = ifindex; err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen); if (err) @@ -1637,7 +1643,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, err = security_mptcp_add_subflow(sk, sf->sk); if (err) - goto release_ssk; + goto err_free; /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); @@ -1651,15 +1657,12 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); err = tcp_set_ulp(sf->sk, "mptcp"); + if (err) + goto err_free; -release_ssk: + mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk); release_sock(sf->sk); - if (err) { - sock_release(sf); - return err; - } - /* the newly created socket really belongs to the owning MPTCP master * socket, even if for additional subflows the allocation is performed * by a kernel workqueue. Adjust inode references, so that the @@ -1679,6 +1682,11 @@ release_ssk: mptcp_subflow_ops_override(sf->sk); return 0; + +err_free: + release_sock(sf->sk); + sock_release(sf); + return err; } static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, @@ -1728,7 +1736,6 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { - mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); mptcp_rcv_space_init(msk, sk); pr_fallback(msk); @@ -2044,7 +2051,6 @@ void __init mptcp_subflow_init(void) subflow_v6m_specific.send_check = ipv4_specific.send_check; subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len; subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced; - subflow_v6m_specific.net_frag_header_len = 0; subflow_v6m_specific.rebuild_header = subflow_rebuild_header; tcpv6_prot_override = tcpv6_prot; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index ef4e76e5aef9..3126911f5042 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -639,10 +639,10 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, if (ret == 1) continue; return ret; + case NF_STOLEN: + return NF_DROP_GETERR(verdict); default: - /* Implicit handling for NF_STOLEN, as well as any other - * non conventional verdicts. - */ + WARN_ON_ONCE(1); return 0; } } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 124136b5a79a..2e5f3864d353 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2169,11 +2169,11 @@ static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num); if (dataoff <= 0) - return -1; + return NF_DROP; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, l4num, net, &tuple)) - return -1; + return NF_DROP; if (ct->status & IPS_SRC_NAT) { memcpy(tuple.src.u3.all, @@ -2193,7 +2193,7 @@ static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, h = nf_conntrack_find_get(net, nf_ct_zone(ct), &tuple); if (!h) - return 0; + return NF_ACCEPT; /* Store status bits of the conntrack that is clashing to re-do NAT * mangling according to what it has been done already to this packet. @@ -2206,19 +2206,25 @@ static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, nat_hook = rcu_dereference(nf_nat_hook); if (!nat_hook) - return 0; + return NF_ACCEPT; - if (status & IPS_SRC_NAT && - nat_hook->manip_pkt(skb, ct, NF_NAT_MANIP_SRC, - IP_CT_DIR_ORIGINAL) == NF_DROP) - return -1; + if (status & IPS_SRC_NAT) { + unsigned int verdict = nat_hook->manip_pkt(skb, ct, + NF_NAT_MANIP_SRC, + IP_CT_DIR_ORIGINAL); + if (verdict != NF_ACCEPT) + return verdict; + } - if (status & IPS_DST_NAT && - nat_hook->manip_pkt(skb, ct, NF_NAT_MANIP_DST, - IP_CT_DIR_ORIGINAL) == NF_DROP) - return -1; + if (status & IPS_DST_NAT) { + unsigned int verdict = nat_hook->manip_pkt(skb, ct, + NF_NAT_MANIP_DST, + IP_CT_DIR_ORIGINAL); + if (verdict != NF_ACCEPT) + return verdict; + } - return 0; + return NF_ACCEPT; } /* This packet is coming from userspace via nf_queue, complete the packet @@ -2233,14 +2239,14 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct, help = nfct_help(ct); if (!help) - return 0; + return NF_ACCEPT; helper = rcu_dereference(help->helper); if (!helper) - return 0; + return NF_ACCEPT; if (!(helper->flags & NF_CT_HELPER_F_USERSPACE)) - return 0; + return NF_ACCEPT; switch (nf_ct_l3num(ct)) { case NFPROTO_IPV4: @@ -2255,42 +2261,44 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct, protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); if (protoff < 0 || (frag_off & htons(~0x7)) != 0) - return 0; + return NF_ACCEPT; break; } #endif default: - return 0; + return NF_ACCEPT; } if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && !nf_is_loopback_packet(skb)) { if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); - return -1; + return NF_DROP; } } /* We've seen it coming out the other side: confirm it */ - return nf_conntrack_confirm(skb) == NF_DROP ? - 1 : 0; + return nf_conntrack_confirm(skb); } static int nf_conntrack_update(struct net *net, struct sk_buff *skb) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; - int err; ct = nf_ct_get(skb, &ctinfo); if (!ct) - return 0; + return NF_ACCEPT; if (!nf_ct_is_confirmed(ct)) { - err = __nf_conntrack_update(net, skb, ct, ctinfo); - if (err < 0) - return err; + int ret = __nf_conntrack_update(net, skb, ct, ctinfo); + + if (ret != NF_ACCEPT) + return ret; ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return NF_ACCEPT; } return nf_confirm_cthelper(skb, ct, ctinfo); diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 6e70e137a0a6..6c46aad23313 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -11,8 +11,6 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h> -static DEFINE_SPINLOCK(nf_connlabels_lock); - static int replace_u32(u32 *address, u32 mask, u32 new) { u32 old, tmp; @@ -60,23 +58,24 @@ EXPORT_SYMBOL_GPL(nf_connlabels_replace); int nf_connlabels_get(struct net *net, unsigned int bits) { + int v; + if (BIT_WORD(bits) >= NF_CT_LABELS_MAX_SIZE / sizeof(long)) return -ERANGE; - spin_lock(&nf_connlabels_lock); - net->ct.labels_used++; - spin_unlock(&nf_connlabels_lock); - BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX); + v = atomic_inc_return_relaxed(&net->ct.labels_used); + WARN_ON_ONCE(v <= 0); + return 0; } EXPORT_SYMBOL_GPL(nf_connlabels_get); void nf_connlabels_put(struct net *net) { - spin_lock(&nf_connlabels_lock); - net->ct.labels_used--; - spin_unlock(&nf_connlabels_lock); + int v = atomic_dec_return_relaxed(&net->ct.labels_used); + + WARN_ON_ONCE(v < 0); } EXPORT_SYMBOL_GPL(nf_connlabels_put); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1d34d700bd09..920a5a29ae1d 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -316,12 +316,6 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, } EXPORT_SYMBOL_GPL(flow_offload_refresh); -static bool nf_flow_is_outdated(const struct flow_offload *flow) -{ - return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && - !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); -} - static inline bool nf_flow_has_expired(const struct flow_offload *flow) { return nf_flow_timeout_delta(flow->timeout) <= 0; @@ -407,12 +401,18 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } +static bool nf_flow_custom_gc(struct nf_flowtable *flow_table, + const struct flow_offload *flow) +{ + return flow_table->type->gc && flow_table->type->gc(flow); +} + static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - nf_flow_is_outdated(flow)) + nf_flow_custom_gc(flow_table, flow)) flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 5a049740758f..6d969468c779 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -999,11 +999,12 @@ static unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - unsigned int ret; + unsigned int ret, verdict; struct in6_addr daddr = ipv6_hdr(skb)->daddr; ret = nf_nat_ipv6_fn(priv, skb, state); - if (ret != NF_DROP && ret != NF_STOLEN && + verdict = ret & NF_VERDICT_MASK; + if (verdict != NF_DROP && verdict != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 16915f8eef2b..467671f2d42f 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -153,7 +153,7 @@ void synproxy_init_timestamp_cookie(const struct nf_synproxy_info *info, struct synproxy_options *opts) { opts->tsecr = opts->tsval; - opts->tsval = tcp_time_stamp_raw() & ~0x3f; + opts->tsval = tcp_clock_ms() & ~0x3f; if (opts->options & NF_SYNPROXY_OPT_WSCALE) { opts->tsval |= opts->wscale; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 68321345bb6d..3c1fd8283bf4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -591,9 +591,9 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - nft_setelem_data_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem_priv); return 0; } @@ -601,7 +601,7 @@ static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set_elem_catchall { struct list_head list; struct rcu_head rcu; - void *elem; + struct nft_elem_priv *elem; }; static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, @@ -609,7 +609,6 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { @@ -617,8 +616,7 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - nft_setelem_data_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, catchall->elem); break; } } @@ -3166,7 +3164,7 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, if (err < 0) return err; - if (!tb[NFTA_EXPR_DATA]) + if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME]) return -EINVAL; type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); @@ -3551,6 +3549,23 @@ done: return skb->len; } +static int nf_tables_dumpreset_rules(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); + int ret; + + /* Mutex is held is to prevent that two concurrent dump-and-reset calls + * do not underrun counters and quotas. The commit_mutex is used for + * the lack a better lock, this is not transaction path. + */ + mutex_lock(&nft_net->commit_mutex); + ret = nf_tables_dump_rules(skb, cb); + mutex_unlock(&nft_net->commit_mutex); + + return ret; +} + static int nf_tables_dump_rules_start(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; @@ -3570,12 +3585,18 @@ static int nf_tables_dump_rules_start(struct netlink_callback *cb) return -ENOMEM; } } - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) - ctx->reset = true; - return 0; } +static int nf_tables_dumpreset_rules_start(struct netlink_callback *cb) +{ + struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + + return nf_tables_dump_rules_start(cb); +} + static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; @@ -3586,8 +3607,9 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getrule_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); @@ -3597,60 +3619,110 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; - bool reset = false; int err; - if (info->nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .start= nf_tables_dump_rules_start, - .dump = nf_tables_dump_rules, - .done = nf_tables_dump_rules_done, - .module = THIS_MODULE, - .data = (void *)nla, - }; - - return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); - } - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); - return PTR_ERR(table); + return ERR_CAST(table); } chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); - return PTR_ERR(chain); + return ERR_CAST(chain); } rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); - return PTR_ERR(rule); + return ERR_CAST(rule); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) - return -ENOMEM; - - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) - reset = true; + return ERR_PTR(-ENOMEM); - err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, + err = nf_tables_fill_rule_info(skb2, net, portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, family, table, chain, rule, 0, reset); - if (err < 0) - goto err_fill_rule_info; + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + } - if (reset) - audit_log_rule_reset(table, nft_pernet(net)->base_seq, 1); + return skb2; +} - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); +static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; -err_fill_rule_info: - kfree_skb(skb2); - return err; + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start= nf_tables_dump_rules_start, + .dump = nf_tables_dump_rules, + .done = nf_tables_dump_rules_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + skb2 = nf_tables_getrule_single(portid, info, nla, false); + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + return nfnetlink_unicast(skb2, net, portid); +} + +static int nf_tables_getrule_reset(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start= nf_tables_dumpreset_rules_start, + .dump = nf_tables_dumpreset_rules, + .done = nf_tables_dump_rules_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + rcu_read_unlock(); + mutex_lock(&nft_net->commit_mutex); + skb2 = nf_tables_getrule_single(portid, info, nla, true); + mutex_unlock(&nft_net->commit_mutex); + rcu_read_lock(); + module_put(THIS_MODULE); + + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + buf = kasprintf(GFP_ATOMIC, "%.*s:%u", + nla_len(nla[NFTA_RULE_TABLE]), + (char *)nla_data(nla[NFTA_RULE_TABLE]), + nft_net->base_seq); + audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, + AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); + kfree(buf); + + return nfnetlink_unicast(skb2, net, portid); } void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) @@ -3733,9 +3805,9 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; @@ -3765,7 +3837,6 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; int ret = 0; @@ -3774,8 +3845,7 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - ret = nft_setelem_validate(ctx, set, NULL, &elem); + ret = nft_setelem_validate(ctx, set, NULL, catchall->elem); if (ret < 0) return ret; } @@ -5227,9 +5297,9 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, static int nft_setelem_data_validate(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); enum nft_registers dreg; dreg = nft_type_to_reg(set->dtype); @@ -5242,9 +5312,9 @@ static int nft_setelem_data_validate(const struct nft_ctx *ctx, static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - return nft_setelem_data_validate(ctx, set, elem); + return nft_setelem_data_validate(ctx, set, elem_priv); } static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, @@ -5252,7 +5322,6 @@ static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; int ret = 0; @@ -5261,8 +5330,7 @@ static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - ret = nft_setelem_data_validate(ctx, set, &elem); + ret = nft_setelem_data_validate(ctx, set, catchall->elem); if (ret < 0) break; } @@ -5329,14 +5397,14 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, - struct nft_set_elem *elem); + struct nft_elem_priv *elem_priv); static int nft_mapelem_activate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - nft_setelem_data_activate(ctx->net, set, elem); + nft_setelem_data_activate(ctx->net, set, elem_priv); return 0; } @@ -5346,7 +5414,6 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { @@ -5354,8 +5421,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - nft_setelem_data_activate(ctx->net, set, &elem); + nft_setelem_data_activate(ctx->net, set, catchall->elem); break; } } @@ -5534,13 +5600,12 @@ nla_put_failure: static int nf_tables_fill_setelem(struct sk_buff *skb, const struct nft_set *set, - const struct nft_set_elem *elem, + const struct nft_elem_priv *elem_priv, bool reset) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - u64 timeout = 0; nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (nest == NULL) @@ -5576,15 +5641,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, htonl(*nft_set_ext_flags(ext)))) goto nla_put_failure; - if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) { - timeout = *nft_set_ext_timeout(ext); - if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - nf_jiffies64_to_msecs(timeout), - NFTA_SET_ELEM_PAD)) - goto nla_put_failure; - } else if (set->flags & NFT_SET_TIMEOUT) { - timeout = READ_ONCE(set->timeout); - } + if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && + nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, + nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)), + NFTA_SET_ELEM_PAD)) + goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { u64 expires, now = get_jiffies_64(); @@ -5599,9 +5660,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, nf_jiffies64_to_msecs(expires), NFTA_SET_ELEM_PAD)) goto nla_put_failure; - - if (reset) - *nft_set_ext_expiration(ext) = now + timeout; } if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) { @@ -5631,16 +5689,16 @@ struct nft_set_dump_args { static int nf_tables_dump_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; if (nft_set_elem_expired(ext)) return 0; args = container_of(iter, struct nft_set_dump_args, iter); - return nf_tables_fill_setelem(args->skb, set, elem, args->reset); + return nf_tables_fill_setelem(args->skb, set, elem_priv, args->reset); } static void audit_log_nft_set_reset(const struct nft_table *table, @@ -5657,6 +5715,7 @@ static void audit_log_nft_set_reset(const struct nft_table *table, struct nft_set_dump_ctx { const struct nft_set *set; struct nft_ctx ctx; + bool reset; }; static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, @@ -5665,7 +5724,6 @@ static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); - struct nft_set_elem elem; struct nft_set_ext *ext; int ret = 0; @@ -5675,8 +5733,7 @@ static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, nft_set_elem_expired(ext)) continue; - elem.priv = catchall->elem; - ret = nf_tables_fill_setelem(skb, set, &elem, reset); + ret = nf_tables_fill_setelem(skb, set, catchall->elem, reset); if (reset && !ret) audit_log_nft_set_reset(set->table, base_seq, 1); break; @@ -5696,7 +5753,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) bool set_found = false; struct nlmsghdr *nlh; struct nlattr *nest; - bool reset = false; u32 portid, seq; int event; @@ -5744,12 +5800,9 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto nla_put_failure; - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET) - reset = true; - args.cb = cb; args.skb = skb; - args.reset = reset; + args.reset = dump_ctx->reset; args.iter.genmask = nft_genmask_cur(net); args.iter.skip = cb->args[0]; args.iter.count = 0; @@ -5759,11 +5812,11 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (!args.iter.err && args.iter.count == cb->args[0]) args.iter.err = nft_set_catchall_dump(net, skb, set, - reset, cb->seq); + dump_ctx->reset, cb->seq); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); - if (reset && args.iter.count > args.iter.skip) + if (dump_ctx->reset && args.iter.count > args.iter.skip) audit_log_nft_set_reset(table, cb->seq, args.iter.count - args.iter.skip); @@ -5801,7 +5854,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_ctx *ctx, u32 seq, u32 portid, int event, u16 flags, const struct nft_set *set, - const struct nft_set_elem *elem, + const struct nft_elem_priv *elem_priv, bool reset) { struct nlmsghdr *nlh; @@ -5823,7 +5876,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, if (nest == NULL) goto nla_put_failure; - err = nf_tables_fill_setelem(skb, set, elem, reset); + err = nf_tables_fill_setelem(skb, set, elem_priv, reset); if (err < 0) goto nla_put_failure; @@ -5973,7 +6026,7 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, - NFT_MSG_NEWSETELEM, 0, set, &elem, + NFT_MSG_NEWSETELEM, 0, set, elem.priv, reset); if (err < 0) goto err_fill_setelem; @@ -6016,6 +6069,9 @@ static int nf_tables_getsetelem(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET) + reset = true; + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, @@ -6026,6 +6082,7 @@ static int nf_tables_getsetelem(struct sk_buff *skb, struct nft_set_dump_ctx dump_ctx = { .set = set, .ctx = ctx, + .reset = reset, }; c.data = &dump_ctx; @@ -6035,9 +6092,6 @@ static int nf_tables_getsetelem(struct sk_buff *skb, if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return -EINVAL; - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET) - reset = true; - nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&ctx, set, attr, reset); if (err < 0) { @@ -6056,7 +6110,7 @@ static int nf_tables_getsetelem(struct sk_buff *skb, static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, - const struct nft_set_elem *elem, + const struct nft_elem_priv *elem_priv, int event) { struct nftables_pernet *nft_net; @@ -6077,7 +6131,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, - set, elem, false); + set, elem_priv, false); if (err < 0) { kfree_skb(skb); goto err; @@ -6152,10 +6206,11 @@ static int nft_set_ext_memcpy(const struct nft_set_ext_tmpl *tmpl, u8 id, return 0; } -void *nft_set_elem_init(const struct nft_set *set, - const struct nft_set_ext_tmpl *tmpl, - const u32 *key, const u32 *key_end, - const u32 *data, u64 timeout, u64 expiration, gfp_t gfp) +struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, + const struct nft_set_ext_tmpl *tmpl, + const u32 *key, const u32 *key_end, + const u32 *data, + u64 timeout, u64 expiration, gfp_t gfp) { struct nft_set_ext *ext; void *elem; @@ -6220,10 +6275,11 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, } /* Drop references and destroy. Called from gc, dynset and abort path. */ -void nft_set_elem_destroy(const struct nft_set *set, void *elem, +void nft_set_elem_destroy(const struct nft_set *set, + const struct nft_elem_priv *elem_priv, bool destroy_expr) { - struct nft_set_ext *ext = nft_set_elem_ext(set, elem); + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_ctx ctx = { .net = read_pnet(&set->net), .family = set->table->family, @@ -6234,10 +6290,10 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_data_release(nft_set_ext_data(ext), set->dtype); if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); - if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_dec(&(*nft_set_ext_obj(ext))->use); - kfree(elem); + + kfree(elem_priv); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -6245,14 +6301,15 @@ EXPORT_SYMBOL_GPL(nft_set_elem_destroy); * path via nft_setelem_data_deactivate(). */ void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, - const struct nft_set *set, void *elem) + const struct nft_set *set, + const struct nft_elem_priv *elem_priv) { - struct nft_set_ext *ext = nft_set_elem_ext(set, elem); + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) nft_set_elem_expr_destroy(ctx, nft_set_ext_expr(ext)); - kfree(elem); + kfree(elem_priv); } int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, @@ -6347,7 +6404,7 @@ EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **pext) + struct nft_elem_priv **priv) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_next(net); @@ -6356,7 +6413,7 @@ static int nft_setelem_catchall_insert(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask)) { - *pext = ext; + *priv = catchall->elem; return -EEXIST; } } @@ -6374,22 +6431,23 @@ static int nft_setelem_catchall_insert(const struct net *net, static int nft_setelem_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext, unsigned int flags) + struct nft_elem_priv **elem_priv, + unsigned int flags) { int ret; if (flags & NFT_SET_ELEM_CATCHALL) - ret = nft_setelem_catchall_insert(net, set, elem, ext); + ret = nft_setelem_catchall_insert(net, set, elem, elem_priv); else - ret = set->ops->insert(net, set, elem, ext); + ret = set->ops->insert(net, set, elem, elem_priv); return ret; } static bool nft_setelem_is_catchall(const struct nft_set *set, - const struct nft_set_elem *elem) + const struct nft_elem_priv *elem_priv) { - struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_CATCHALL) @@ -6399,14 +6457,14 @@ static bool nft_setelem_is_catchall(const struct nft_set *set, } static void nft_setelem_activate(struct net *net, struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); - if (nft_setelem_is_catchall(set, elem)) { + if (nft_setelem_is_catchall(set, elem_priv)) { nft_set_elem_change_active(net, set, ext); } else { - set->ops->activate(net, set, elem); + set->ops->activate(net, set, elem_priv); } } @@ -6464,12 +6522,12 @@ static int nft_setelem_deactivate(const struct net *net, static void nft_setelem_catchall_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { struct nft_set_elem_catchall *catchall, *next; list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { - if (catchall->elem == elem->priv) { + if (catchall->elem == elem_priv) { list_del_rcu(&catchall->list); kfree_rcu(catchall, rcu); break; @@ -6479,12 +6537,12 @@ static void nft_setelem_catchall_remove(const struct net *net, static void nft_setelem_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - if (nft_setelem_is_catchall(set, elem)) - nft_setelem_catchall_remove(net, set, elem); + if (nft_setelem_is_catchall(set, elem_priv)) + nft_setelem_catchall_remove(net, set, elem_priv); else - set->ops->remove(net, set, elem); + set->ops->remove(net, set, elem_priv); } static bool nft_setelem_valid_key_end(const struct nft_set *set, @@ -6517,13 +6575,14 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; struct nft_set_binding *binding; + struct nft_elem_priv *elem_priv; struct nft_object *obj = NULL; struct nft_userdata *udata; struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; - u64 timeout; u64 expiration; + u64 timeout; int err, i; u8 ulen; @@ -6816,9 +6875,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ext->genmask = nft_genmask_cur(ctx->net); - err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); + err = nft_setelem_insert(ctx->net, set, &elem, &elem_priv, flags); if (err) { if (err == -EEXIST) { + ext2 = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) || nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ @@ -6852,12 +6912,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } } - nft_trans_elem(trans) = elem; + nft_trans_elem_priv(trans) = elem.priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_set_full: - nft_setelem_remove(ctx->net, set, &elem); + nft_setelem_remove(ctx->net, set, elem.priv); err_element_clash: kfree(trans); err_elem_free: @@ -6958,9 +7018,9 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); @@ -6970,9 +7030,9 @@ static void nft_setelem_data_activate(const struct net *net, void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); @@ -7057,9 +7117,9 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto fail_ops; - nft_setelem_data_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, elem.priv); - nft_trans_elem(trans) = elem; + nft_trans_elem_priv(trans) = elem.priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -7077,36 +7137,29 @@ fail_elem: static int nft_setelem_flush(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { struct nft_trans *trans; - int err; trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, sizeof(struct nft_trans_elem), GFP_ATOMIC); if (!trans) return -ENOMEM; - if (!set->ops->flush(ctx->net, set, elem->priv)) { - err = -ENOENT; - goto err1; - } + set->ops->flush(ctx->net, set, elem_priv); set->ndeact++; - nft_setelem_data_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_elem_set(trans) = set; - nft_trans_elem(trans) = *elem; + nft_trans_elem_priv(trans) = elem_priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; -err1: - kfree(trans); - return err; } static int __nft_set_catchall_flush(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { struct nft_trans *trans; @@ -7115,9 +7168,9 @@ static int __nft_set_catchall_flush(const struct nft_ctx *ctx, if (!trans) return -ENOMEM; - nft_setelem_data_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_elem_set(trans) = set; - nft_trans_elem(trans) = *elem; + nft_trans_elem_priv(trans) = elem_priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -7128,7 +7181,6 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; int ret = 0; @@ -7137,8 +7189,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - ret = __nft_set_catchall_flush(ctx, set, &elem); + ret = __nft_set_catchall_flush(ctx, set, catchall->elem); if (ret < 0) break; nft_set_elem_change_active(ctx->net, set, ext); @@ -7605,25 +7656,35 @@ nla_put_failure: return -1; } -struct nft_obj_filter { +static void audit_log_obj_reset(const struct nft_table *table, + unsigned int base_seq, unsigned int nentries) +{ + char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); + + audit_log_nfcfg(buf, table->family, nentries, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); +} + +struct nft_obj_dump_ctx { + unsigned int s_idx; char *table; u32 type; + bool reset; }; static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); - const struct nft_table *table; - unsigned int idx = 0, s_idx = cb->args[0]; - struct nft_obj_filter *filter = cb->data; + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; + const struct nft_table *table; + unsigned int entries = 0; struct nft_object *obj; - bool reset = false; - - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - reset = true; + unsigned int idx = 0; + int rc = 0; rcu_read_lock(); nft_net = nft_pernet(net); @@ -7633,89 +7694,71 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) if (family != NFPROTO_UNSPEC && family != table->family) continue; + entries = 0; list_for_each_entry_rcu(obj, &table->objects, list) { if (!nft_is_active(net, obj)) goto cont; - if (idx < s_idx) + if (idx < ctx->s_idx) goto cont; - if (idx > s_idx) - memset(&cb->args[1], 0, - sizeof(cb->args) - sizeof(cb->args[0])); - if (filter && filter->table && - strcmp(filter->table, table->name)) + if (ctx->table && strcmp(ctx->table, table->name)) goto cont; - if (filter && - filter->type != NFT_OBJECT_UNSPEC && - obj->ops->type->type != filter->type) + if (ctx->type != NFT_OBJECT_UNSPEC && + obj->ops->type->type != ctx->type) goto cont; - if (reset) { - char *buf = kasprintf(GFP_ATOMIC, - "%s:%u", - table->name, - nft_net->base_seq); - - audit_log_nfcfg(buf, - family, - obj->handle, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); - } - if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NFT_MSG_NEWOBJ, - NLM_F_MULTI | NLM_F_APPEND, - table->family, table, - obj, reset) < 0) - goto done; + rc = nf_tables_fill_obj_info(skb, net, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NFT_MSG_NEWOBJ, + NLM_F_MULTI | NLM_F_APPEND, + table->family, table, + obj, ctx->reset); + if (rc < 0) + break; + entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } + if (ctx->reset && entries) + audit_log_obj_reset(table, nft_net->base_seq, entries); + if (rc < 0) + break; } -done: rcu_read_unlock(); - cb->args[0] = idx; + ctx->s_idx = idx; return skb->len; } static int nf_tables_dump_obj_start(struct netlink_callback *cb) { + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; const struct nlattr * const *nla = cb->data; - struct nft_obj_filter *filter = NULL; - if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) { - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); - if (!filter) + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + if (nla[NFTA_OBJ_TABLE]) { + ctx->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); + if (!ctx->table) return -ENOMEM; + } - if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return -ENOMEM; - } - } + if (nla[NFTA_OBJ_TYPE]) + ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (nla[NFTA_OBJ_TYPE]) - filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - } + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) + ctx->reset = true; - cb->data = filter; return 0; } static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_filter *filter = cb->data; + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; - if (filter) { - kfree(filter->table); - kfree(filter); - } + kfree(ctx->table); return 0; } @@ -7780,7 +7823,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, audit_log_nfcfg(buf, family, - obj->handle, + 1, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); @@ -8974,7 +9017,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_rule_policy, }, [NFT_MSG_GETRULE_RESET] = { - .call = nf_tables_getrule, + .call = nf_tables_getrule_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, @@ -9224,7 +9267,7 @@ static void nft_commit_release(struct nft_trans *trans) case NFT_MSG_DESTROYSETELEM: nf_tables_set_elem_destroy(&trans->ctx, nft_trans_elem_set(trans), - nft_trans_elem(trans).priv); + nft_trans_elem_priv(trans)); break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: @@ -9453,16 +9496,12 @@ void nft_chain_del(struct nft_chain *chain) static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, struct nft_trans_gc *trans) { - void **priv = trans->priv; + struct nft_elem_priv **priv = trans->priv; unsigned int i; for (i = 0; i < trans->count; i++) { - struct nft_set_elem elem = { - .priv = priv[i], - }; - - nft_setelem_data_deactivate(ctx->net, trans->set, &elem); - nft_setelem_remove(ctx->net, trans->set, &elem); + nft_setelem_data_deactivate(ctx->net, trans->set, priv[i]); + nft_setelem_remove(ctx->net, trans->set, priv[i]); } } @@ -9475,7 +9514,7 @@ void nft_trans_gc_destroy(struct nft_trans_gc *trans) static void nft_trans_gc_trans_free(struct rcu_head *rcu) { - struct nft_set_elem elem = {}; + struct nft_elem_priv *elem_priv; struct nft_trans_gc *trans; struct nft_ctx ctx = {}; unsigned int i; @@ -9484,11 +9523,11 @@ static void nft_trans_gc_trans_free(struct rcu_head *rcu) ctx.net = read_pnet(&trans->set->net); for (i = 0; i < trans->count; i++) { - elem.priv = trans->priv[i]; - if (!nft_setelem_is_catchall(trans->set, &elem)) + elem_priv = trans->priv[i]; + if (!nft_setelem_is_catchall(trans->set, elem_priv)) atomic_dec(&trans->set->nelems); - nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv); + nf_tables_set_elem_destroy(&ctx, trans->set, elem_priv); } nft_trans_gc_destroy(trans); @@ -10056,9 +10095,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_setelem_activate(net, te->set, &te->elem); + nft_setelem_activate(net, te->set, te->elem_priv); nf_tables_setelem_notify(&trans->ctx, te->set, - &te->elem, + te->elem_priv, NFT_MSG_NEWSETELEM); if (te->set->ops->commit && list_empty(&te->set->pending_update)) { @@ -10072,10 +10111,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) te = (struct nft_trans_elem *)trans->data; nf_tables_setelem_notify(&trans->ctx, te->set, - &te->elem, + te->elem_priv, trans->msg_type); - nft_setelem_remove(net, te->set, &te->elem); - if (!nft_setelem_is_catchall(te->set, &te->elem)) { + nft_setelem_remove(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) { atomic_dec(&te->set->nelems); te->set->ndeact--; } @@ -10195,7 +10234,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv, true); + nft_trans_elem_priv(trans), true); break; case NFT_MSG_NEWOBJ: nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); @@ -10342,8 +10381,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; } te = (struct nft_trans_elem *)trans->data; - nft_setelem_remove(net, te->set, &te->elem); - if (!nft_setelem_is_catchall(te->set, &te->elem)) + nft_setelem_remove(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) atomic_dec(&te->set->nelems); if (te->set->ops->abort && @@ -10356,9 +10395,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_setelem_data_activate(net, te->set, &te->elem); - nft_setelem_activate(net, te->set, &te->elem); - if (!nft_setelem_is_catchall(te->set, &te->elem)) + nft_setelem_data_activate(net, te->set, te->elem_priv); + nft_setelem_activate(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) te->set->ndeact--; if (te->set->ops->abort && @@ -10534,9 +10573,9 @@ static int nft_check_loops(const struct nft_ctx *ctx, static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 4d0ce12221f6..8b536d7ef6c2 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -115,7 +115,7 @@ static noinline void __nft_trace_verdict(const struct nft_pktinfo *pkt, { enum nft_trace_types type; - switch (regs->verdict.code) { + switch (regs->verdict.code & NF_VERDICT_MASK) { case NFT_CONTINUE: case NFT_RETURN: type = NFT_TRACETYPE_RETURN; @@ -308,10 +308,11 @@ next_rule: switch (regs.verdict.code & NF_VERDICT_MASK) { case NF_ACCEPT: - case NF_DROP: case NF_QUEUE: case NF_STOLEN: return regs.verdict.code; + case NF_DROP: + return NF_DROP_REASON(pkt->skb, SKB_DROP_REASON_NETFILTER_DROP, EPERM); } switch (regs.verdict.code) { @@ -342,6 +343,9 @@ next_rule: if (static_branch_unlikely(&nft_counters_enabled)) nft_update_chain_stats(basechain, pkt); + if (nft_base_chain(basechain)->policy == NF_DROP) + return NF_DROP_REASON(pkt->skb, SKB_DROP_REASON_NETFILTER_DROP, EPERM); + return nft_base_chain(basechain)->policy; } EXPORT_SYMBOL_GPL(nft_do_chain); diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 6d41c0bd3d78..a83637e3f455 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -258,17 +258,21 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, case __NFT_TRACETYPE_MAX: break; case NFT_TRACETYPE_RETURN: - case NFT_TRACETYPE_RULE: + case NFT_TRACETYPE_RULE: { + unsigned int v; + if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, verdict)) goto nla_put_failure; /* pkt->skb undefined iff NF_STOLEN, disable dump */ - if (verdict->code == NF_STOLEN) + v = verdict->code & NF_VERDICT_MASK; + if (v == NF_STOLEN) info->packet_dumped = true; else mark = pkt->skb->mark; break; + } case NFT_TRACETYPE_POLICY: mark = pkt->skb->mark; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 53c9e76473ba..f03f4d4d7d88 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -698,8 +698,8 @@ nfulnl_log_packet(struct net *net, unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; + enum ip_conntrack_info ctinfo = 0; struct nf_conn *ct = NULL; - enum ip_conntrack_info ctinfo; if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 556bc902af00..171d1f52d3dd 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -228,19 +228,22 @@ find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; - int err; if (verdict == NF_ACCEPT || verdict == NF_REPEAT || verdict == NF_STOP) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); - if (ct_hook) { - err = ct_hook->update(entry->state.net, entry->skb); - if (err < 0) - verdict = NF_DROP; - } + if (ct_hook) + verdict = ct_hook->update(entry->state.net, entry->skb); rcu_read_unlock(); + + switch (verdict & NF_VERDICT_MASK) { + case NF_STOLEN: + nf_queue_entry_free(entry); + return; + } + } nf_reinject(entry, verdict); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 5c5cc01c73c5..b18a79039125 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -44,33 +44,34 @@ static int nft_dynset_expr_setup(const struct nft_dynset *priv, return 0; } -static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, - struct nft_regs *regs) +static struct nft_elem_priv *nft_dynset_new(struct nft_set *set, + const struct nft_expr *expr, + struct nft_regs *regs) { const struct nft_dynset *priv = nft_expr_priv(expr); struct nft_set_ext *ext; + void *elem_priv; u64 timeout; - void *elem; if (!atomic_add_unless(&set->nelems, 1, set->size)) return NULL; timeout = priv->timeout ? : set->timeout; - elem = nft_set_elem_init(set, &priv->tmpl, - ®s->data[priv->sreg_key], NULL, - ®s->data[priv->sreg_data], - timeout, 0, GFP_ATOMIC); - if (IS_ERR(elem)) + elem_priv = nft_set_elem_init(set, &priv->tmpl, + ®s->data[priv->sreg_key], NULL, + ®s->data[priv->sreg_data], + timeout, 0, GFP_ATOMIC); + if (IS_ERR(elem_priv)) goto err1; - ext = nft_set_elem_ext(set, elem); + ext = nft_set_elem_ext(set, elem_priv); if (priv->num_exprs && nft_dynset_expr_setup(priv, ext) < 0) goto err2; - return elem; + return elem_priv; err2: - nft_set_elem_destroy(set, elem, false); + nft_set_elem_destroy(set, elem_priv, false); err1: if (set->size) atomic_dec(&set->nelems); diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 28e2873ba24e..928312d01eb1 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -298,6 +298,7 @@ static int nft_inner_init(const struct nft_ctx *ctx, int err; if (!tb[NFTA_INNER_FLAGS] || + !tb[NFTA_INNER_NUM] || !tb[NFTA_INNER_HDRSIZE] || !tb[NFTA_INNER_TYPE] || !tb[NFTA_INNER_EXPR]) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 120f6d395b98..0a689c8e0295 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -179,7 +179,7 @@ void nft_payload_eval(const struct nft_expr *expr, switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: - if (!skb_mac_header_was_set(skb)) + if (!skb_mac_header_was_set(skb) || skb_mac_header_len(skb) == 0) goto err; if (skb_vlan_tag_present(skb) && diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 1e5e7a181e0b..32df7a16835d 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -13,6 +13,7 @@ #include <net/netfilter/nf_tables_core.h> struct nft_bitmap_elem { + struct nft_elem_priv priv; struct list_head head; struct nft_set_ext ext; }; @@ -104,8 +105,9 @@ nft_bitmap_elem_find(const struct nft_set *set, struct nft_bitmap_elem *this, return NULL; } -static void *nft_bitmap_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_bitmap_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { const struct nft_bitmap *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); @@ -116,23 +118,23 @@ static void *nft_bitmap_get(const struct net *net, const struct nft_set *set, !nft_set_elem_active(&be->ext, genmask)) continue; - return be; + return &be->priv; } return ERR_PTR(-ENOENT); } static int nft_bitmap_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { + struct nft_bitmap_elem *new = nft_elem_priv_cast(elem->priv), *be; struct nft_bitmap *priv = nft_set_priv(set); - struct nft_bitmap_elem *new = elem->priv, *be; u8 genmask = nft_genmask_next(net); u32 idx, off; be = nft_bitmap_elem_find(set, new, genmask); if (be) { - *ext = &be->ext; + *elem_priv = &be->priv; return -EEXIST; } @@ -144,12 +146,11 @@ static int nft_bitmap_insert(const struct net *net, const struct nft_set *set, return 0; } -static void nft_bitmap_remove(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_bitmap_remove(const struct net *net, const struct nft_set *set, + struct nft_elem_priv *elem_priv) { + struct nft_bitmap_elem *be = nft_elem_priv_cast(elem_priv); struct nft_bitmap *priv = nft_set_priv(set); - struct nft_bitmap_elem *be = elem->priv; u8 genmask = nft_genmask_next(net); u32 idx, off; @@ -161,10 +162,10 @@ static void nft_bitmap_remove(const struct net *net, static void nft_bitmap_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { + struct nft_bitmap_elem *be = nft_elem_priv_cast(elem_priv); struct nft_bitmap *priv = nft_set_priv(set); - struct nft_bitmap_elem *be = elem->priv; u8 genmask = nft_genmask_next(net); u32 idx, off; @@ -174,28 +175,27 @@ static void nft_bitmap_activate(const struct net *net, nft_set_elem_change_active(net, set, &be->ext); } -static bool nft_bitmap_flush(const struct net *net, - const struct nft_set *set, void *_be) +static void nft_bitmap_flush(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) { + struct nft_bitmap_elem *be = nft_elem_priv_cast(elem_priv); struct nft_bitmap *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); - struct nft_bitmap_elem *be = _be; u32 idx, off; nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 10 state, similar to deactivation. */ priv->bitmap[idx] &= ~(genmask << off); nft_set_elem_change_active(net, set, &be->ext); - - return true; } -static void *nft_bitmap_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_bitmap_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { + struct nft_bitmap_elem *this = nft_elem_priv_cast(elem->priv), *be; struct nft_bitmap *priv = nft_set_priv(set); - struct nft_bitmap_elem *this = elem->priv, *be; u8 genmask = nft_genmask_next(net); u32 idx, off; @@ -209,7 +209,7 @@ static void *nft_bitmap_deactivate(const struct net *net, priv->bitmap[idx] &= ~(genmask << off); nft_set_elem_change_active(net, set, &be->ext); - return be; + return &be->priv; } static void nft_bitmap_walk(const struct nft_ctx *ctx, @@ -218,7 +218,6 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, { const struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be; - struct nft_set_elem elem; list_for_each_entry_rcu(be, &priv->list, head) { if (iter->count < iter->skip) @@ -226,9 +225,7 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, if (!nft_set_elem_active(&be->ext, iter->genmask)) goto cont; - elem.priv = be; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &be->priv); if (iter->err < 0) return; @@ -265,6 +262,8 @@ static int nft_bitmap_init(const struct nft_set *set, { struct nft_bitmap *priv = nft_set_priv(set); + BUILD_BUG_ON(offsetof(struct nft_bitmap_elem, priv) != 0); + INIT_LIST_HEAD(&priv->list); priv->bitmap_size = nft_bitmap_size(set->klen); @@ -278,7 +277,7 @@ static void nft_bitmap_destroy(const struct nft_ctx *ctx, struct nft_bitmap_elem *be, *n; list_for_each_entry_safe(be, n, &priv->list, head) - nf_tables_set_elem_destroy(ctx, set, be); + nf_tables_set_elem_destroy(ctx, set, &be->priv); } static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 2013de934cef..6c2061bfdae6 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -27,6 +27,7 @@ struct nft_rhash { }; struct nft_rhash_elem { + struct nft_elem_priv priv; struct rhash_head node; struct nft_set_ext ext; }; @@ -95,8 +96,9 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, return !!he; } -static void *nft_rhash_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_rhash_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he; @@ -108,13 +110,14 @@ static void *nft_rhash_get(const struct net *net, const struct nft_set *set, he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); if (he != NULL) - return he; + return &he->priv; return ERR_PTR(-ENOENT); } static bool nft_rhash_update(struct nft_set *set, const u32 *key, - void *(*new)(struct nft_set *, + struct nft_elem_priv * + (*new)(struct nft_set *, const struct nft_expr *, struct nft_regs *regs), const struct nft_expr *expr, @@ -123,6 +126,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, { struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he, *prev; + struct nft_elem_priv *elem_priv; struct nft_rhash_cmp_arg arg = { .genmask = NFT_GENMASK_ANY, .set = set, @@ -133,10 +137,11 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, if (he != NULL) goto out; - he = new(set, expr, regs); - if (he == NULL) + elem_priv = new(set, expr, regs); + if (!elem_priv) goto err1; + he = nft_elem_priv_cast(elem_priv); prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, nft_rhash_params); if (IS_ERR(prev)) @@ -144,7 +149,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, /* Another cpu may race to insert the element with the same key */ if (prev) { - nft_set_elem_destroy(set, he, true); + nft_set_elem_destroy(set, &he->priv, true); atomic_dec(&set->nelems); he = prev; } @@ -154,7 +159,7 @@ out: return true; err2: - nft_set_elem_destroy(set, he, true); + nft_set_elem_destroy(set, &he->priv, true); atomic_dec(&set->nelems); err1: return false; @@ -162,10 +167,10 @@ err1: static int nft_rhash_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { + struct nft_rhash_elem *he = nft_elem_priv_cast(elem->priv); struct nft_rhash *priv = nft_set_priv(set); - struct nft_rhash_elem *he = elem->priv; struct nft_rhash_cmp_arg arg = { .genmask = nft_genmask_next(net), .set = set, @@ -178,33 +183,32 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set, if (IS_ERR(prev)) return PTR_ERR(prev); if (prev) { - *ext = &prev->ext; + *elem_priv = &prev->priv; return -EEXIST; } return 0; } static void nft_rhash_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_rhash_elem *he = elem->priv; + struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &he->ext); } -static bool nft_rhash_flush(const struct net *net, - const struct nft_set *set, void *priv) +static void nft_rhash_flush(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) { - struct nft_rhash_elem *he = priv; + struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &he->ext); - - return true; } -static void *nft_rhash_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_rhash_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he; @@ -221,15 +225,15 @@ static void *nft_rhash_deactivate(const struct net *net, rcu_read_unlock(); - return he; + return &he->priv; } static void nft_rhash_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { + struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); struct nft_rhash *priv = nft_set_priv(set); - struct nft_rhash_elem *he = elem->priv; rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); } @@ -260,7 +264,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he; struct rhashtable_iter hti; - struct nft_set_elem elem; rhashtable_walk_enter(&priv->ht, &hti); rhashtable_walk_start(&hti); @@ -280,9 +283,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; - elem.priv = he; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) break; @@ -406,6 +407,8 @@ static int nft_rhash_init(const struct nft_set *set, struct rhashtable_params params = nft_rhash_params; int err; + BUILD_BUG_ON(offsetof(struct nft_rhash_elem, priv) != 0); + params.nelem_hint = desc->size ?: NFT_RHASH_ELEMENT_HINT; params.key_len = set->klen; @@ -428,8 +431,9 @@ struct nft_rhash_ctx { static void nft_rhash_elem_destroy(void *ptr, void *arg) { struct nft_rhash_ctx *rhash_ctx = arg; + struct nft_rhash_elem *he = ptr; - nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr); + nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, &he->priv); } static void nft_rhash_destroy(const struct nft_ctx *ctx, @@ -476,6 +480,7 @@ struct nft_hash { }; struct nft_hash_elem { + struct nft_elem_priv priv; struct hlist_node node; struct nft_set_ext ext; }; @@ -501,8 +506,9 @@ bool nft_hash_lookup(const struct net *net, const struct nft_set *set, return false; } -static void *nft_hash_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_hash_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); @@ -514,7 +520,7 @@ static void *nft_hash_get(const struct net *net, const struct nft_set *set, hlist_for_each_entry_rcu(he, &priv->table[hash], node) { if (!memcmp(nft_set_ext_key(&he->ext), elem->key.val.data, set->klen) && nft_set_elem_active(&he->ext, genmask)) - return he; + return &he->priv; } return ERR_PTR(-ENOENT); } @@ -562,9 +568,9 @@ static u32 nft_jhash(const struct nft_set *set, const struct nft_hash *priv, static int nft_hash_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { - struct nft_hash_elem *this = elem->priv, *he; + struct nft_hash_elem *this = nft_elem_priv_cast(elem->priv), *he; struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); u32 hash; @@ -574,7 +580,7 @@ static int nft_hash_insert(const struct net *net, const struct nft_set *set, if (!memcmp(nft_set_ext_key(&this->ext), nft_set_ext_key(&he->ext), set->klen) && nft_set_elem_active(&he->ext, genmask)) { - *ext = &he->ext; + *elem_priv = &he->priv; return -EEXIST; } } @@ -583,28 +589,28 @@ static int nft_hash_insert(const struct net *net, const struct nft_set *set, } static void nft_hash_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_hash_elem *he = elem->priv; + struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &he->ext); } -static bool nft_hash_flush(const struct net *net, - const struct nft_set *set, void *priv) +static void nft_hash_flush(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) { - struct nft_hash_elem *he = priv; + struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &he->ext); - return true; } -static void *nft_hash_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_hash_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { + struct nft_hash_elem *this = nft_elem_priv_cast(elem->priv), *he; struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *this = elem->priv, *he; u8 genmask = nft_genmask_next(net); u32 hash; @@ -614,7 +620,7 @@ static void *nft_hash_deactivate(const struct net *net, set->klen) && nft_set_elem_active(&he->ext, genmask)) { nft_set_elem_change_active(net, set, &he->ext); - return he; + return &he->priv; } } return NULL; @@ -622,9 +628,9 @@ static void *nft_hash_deactivate(const struct net *net, static void nft_hash_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_hash_elem *he = elem->priv; + struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); hlist_del_rcu(&he->node); } @@ -634,7 +640,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he; - struct nft_set_elem elem; int i; for (i = 0; i < priv->buckets; i++) { @@ -644,9 +649,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; - elem.priv = he; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) return; cont: @@ -685,7 +688,7 @@ static void nft_hash_destroy(const struct nft_ctx *ctx, for (i = 0; i < priv->buckets; i++) { hlist_for_each_entry_safe(he, next, &priv->table[i], node) { hlist_del_rcu(&he->node); - nf_tables_set_elem_destroy(ctx, set, he); + nf_tables_set_elem_destroy(ctx, set, &he->priv); } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index c0dcc40de358..701977af3ee8 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -599,11 +599,18 @@ out: * @elem: nftables API element representation containing key data * @flags: Unused */ -static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_pipapo_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { - return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + static struct nft_pipapo_elem *e; + + e = pipapo_get(net, set, (const u8 *)elem->key.val.data, + nft_genmask_cur(net)); + if (IS_ERR(e)) + return ERR_CAST(e); + + return &e->priv; } /** @@ -1151,21 +1158,21 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, * @net: Network namespace * @set: nftables API set representation * @elem: nftables API element representation containing key data - * @ext2: Filled with pointer to &struct nft_set_ext in inserted element + * @elem_priv: Filled with pointer to &struct nft_set_ext in inserted element * * Return: 0 on success, error pointer on failure. */ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext2) + struct nft_elem_priv **elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const u8 *start = (const u8 *)elem->key.val.data, *end; - struct nft_pipapo_elem *e = elem->priv, *dup; struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); + struct nft_pipapo_elem *e, *dup; struct nft_pipapo_field *f; const u8 *start_p, *end_p; int i, bsize_max, err = 0; @@ -1188,7 +1195,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (!memcmp(start, dup_key->data, sizeof(*dup_key->data)) && !memcmp(end, dup_end->data, sizeof(*dup_end->data))) { - *ext2 = &dup->ext; + *elem_priv = &dup->priv; return -EEXIST; } @@ -1203,7 +1210,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) != -ENOENT) { if (IS_ERR(dup)) return PTR_ERR(dup); - *ext2 = &dup->ext; + *elem_priv = &dup->priv; return -ENOTEMPTY; } @@ -1263,7 +1270,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, put_cpu_ptr(m->scratch); } - *ext2 = &e->ext; + e = nft_elem_priv_cast(elem->priv); + *elem_priv = &e->priv; pipapo_map(m, rulemap, e); @@ -1540,21 +1548,16 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, struct nft_pipapo_elem *e) { - struct nft_set_elem elem = { - .priv = e, - }; - - nft_setelem_data_deactivate(net, set, &elem); + nft_setelem_data_deactivate(net, set, &e->priv); } /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements - * @_set: nftables API set representation + * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) +static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) { - struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); int rules_f0, first_rule = 0; @@ -1672,7 +1675,7 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) * We also need to create a new working copy for subsequent insertions and * deletions. */ -static void nft_pipapo_commit(const struct nft_set *set) +static void nft_pipapo_commit(struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *new_clone, *old; @@ -1732,7 +1735,7 @@ static void nft_pipapo_abort(const struct nft_set *set) * nft_pipapo_activate() - Mark element reference as active given key, commit * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @elem_priv: nftables API element representation containing key data * * On insertion, elements are added to a copy of the matching data currently * in use for lookups, and not directly inserted into current lookup data. Both @@ -1741,9 +1744,9 @@ static void nft_pipapo_abort(const struct nft_set *set) */ static void nft_pipapo_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_pipapo_elem *e = elem->priv; + struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &e->ext); } @@ -1783,9 +1786,9 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, * * Return: deactivated element if found, NULL otherwise. */ -static void *nft_pipapo_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_pipapo_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -1796,7 +1799,7 @@ static void *nft_pipapo_deactivate(const struct net *net, * nft_pipapo_flush() - Call pipapo_deactivate() to make element inactive * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @elem_priv: nftables API element representation containing key data * * This is functionally the same as nft_pipapo_deactivate(), with a slightly * different interface, and it's also called once for each element in a set @@ -1810,13 +1813,12 @@ static void *nft_pipapo_deactivate(const struct net *net, * * Return: true if element was found and deactivated. */ -static bool nft_pipapo_flush(const struct net *net, const struct nft_set *set, - void *elem) +static void nft_pipapo_flush(const struct net *net, const struct nft_set *set, + struct nft_elem_priv *elem_priv) { - struct nft_pipapo_elem *e = elem; + struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); - return pipapo_deactivate(net, set, (const u8 *)nft_set_ext_key(&e->ext), - &e->ext); + nft_set_elem_change_active(net, set, &e->ext); } /** @@ -1939,7 +1941,7 @@ static bool pipapo_match_field(struct nft_pipapo_field *f, * nft_pipapo_remove() - Remove element given key, commit * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @elem_priv: nftables API element representation containing key data * * Similarly to nft_pipapo_activate(), this is used as commit operation by the * API, but it's called once per element in the pending transaction, so we can't @@ -1947,14 +1949,15 @@ static bool pipapo_match_field(struct nft_pipapo_field *f, * the matched element here, if any, and commit the updated matching data. */ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; - struct nft_pipapo_elem *e = elem->priv; int rules_f0, first_rule = 0; + struct nft_pipapo_elem *e; const u8 *data; + e = nft_elem_priv_cast(elem_priv); data = (const u8 *)nft_set_ext_key(&e->ext); while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { @@ -2031,7 +2034,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, for (r = 0; r < f->rules; r++) { struct nft_pipapo_elem *e; - struct nft_set_elem elem; if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e) continue; @@ -2041,9 +2043,7 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; - elem.priv = e; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) goto out; @@ -2115,6 +2115,8 @@ static int nft_pipapo_init(const struct nft_set *set, struct nft_pipapo_field *f; int err, i, field_count; + BUILD_BUG_ON(offsetof(struct nft_pipapo_elem, priv) != 0); + field_count = desc->field_count ? : 1; if (field_count > NFT_PIPAPO_MAX_FIELDS) @@ -2209,7 +2211,7 @@ static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, e = f->mt[r].e; - nf_tables_set_elem_destroy(ctx, set, e); + nf_tables_set_elem_destroy(ctx, set, &e->priv); } } diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 25a75591583e..1040223da5fa 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -147,7 +147,7 @@ struct nft_pipapo_match { unsigned long * __percpu *scratch; size_t bsize_max; struct rcu_head rcu; - struct nft_pipapo_field f[]; + struct nft_pipapo_field f[] __counted_by(field_count); }; /** @@ -170,10 +170,12 @@ struct nft_pipapo_elem; /** * struct nft_pipapo_elem - API-facing representation of single set element + * @priv: element placeholder * @ext: nftables API extensions */ struct nft_pipapo_elem { - struct nft_set_ext ext; + struct nft_elem_priv priv; + struct nft_set_ext ext; }; int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 2660ceab3759..6f1186abd47b 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -19,10 +19,11 @@ struct nft_rbtree { struct rb_root root; rwlock_t lock; seqcount_rwlock_t count; - struct delayed_work gc_work; + unsigned long last_gc; }; struct nft_rbtree_elem { + struct nft_elem_priv priv; struct rb_node node; struct nft_set_ext ext; }; @@ -48,8 +49,7 @@ static int nft_rbtree_cmp(const struct nft_set *set, static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) { - return nft_set_elem_expired(&rbe->ext) || - nft_set_elem_is_dead(&rbe->ext); + return nft_set_elem_expired(&rbe->ext); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, @@ -197,8 +197,9 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, return false; } -static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_rbtree_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); @@ -209,27 +210,25 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); if (ret || !read_seqcount_retry(&priv->count, seq)) - return rbe; + return &rbe->priv; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); - if (!ret) - rbe = ERR_PTR(-ENOENT); read_unlock_bh(&priv->lock); - return rbe; + if (!ret) + return ERR_PTR(-ENOENT); + + return &rbe->priv; } -static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, - struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe) +static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) { - struct nft_set_elem elem = { - .priv = rbe, - }; - - nft_setelem_data_deactivate(net, set, &elem); + lockdep_assert_held_write(&priv->lock); + nft_setelem_data_deactivate(net, set, &rbe->priv); rb_erase(&rbe->node, &priv->root); } @@ -263,7 +262,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); - nft_rbtree_gc_remove(net, set, priv, rbe_prev); + nft_rbtree_gc_elem_remove(net, set, priv, rbe_prev); /* There is always room in this trans gc for this element, * memory allocation never actually happens, hence, the warning @@ -277,7 +276,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, nft_trans_gc_elem_add(gc, rbe_prev); } - nft_rbtree_gc_remove(net, set, priv, rbe); + nft_rbtree_gc_elem_remove(net, set, priv, rbe); gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) return ERR_PTR(-ENOMEM); @@ -307,7 +306,7 @@ static bool nft_rbtree_update_first(const struct nft_set *set, static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; struct rb_node *node, *next, *parent, **p, *first = NULL; @@ -424,7 +423,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, */ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { - *ext = &rbe_ge->ext; + *elem_priv = &rbe_ge->priv; return -EEXIST; } @@ -433,7 +432,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, */ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { - *ext = &rbe_le->ext; + *elem_priv = &rbe_le->priv; return -EEXIST; } @@ -485,10 +484,10 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { + struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem->priv); struct nft_rbtree *priv = nft_set_priv(set); - struct nft_rbtree_elem *rbe = elem->priv; int err; do { @@ -499,7 +498,7 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); - err = __nft_rbtree_insert(net, set, rbe, ext); + err = __nft_rbtree_insert(net, set, rbe, elem_priv); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } while (err == -EAGAIN); @@ -507,13 +506,8 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, return err; } -static void nft_rbtree_remove(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_rbtree_erase(struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { - struct nft_rbtree *priv = nft_set_priv(set); - struct nft_rbtree_elem *rbe = elem->priv; - write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); rb_erase(&rbe->node, &priv->root); @@ -521,32 +515,41 @@ static void nft_rbtree_remove(const struct net *net, write_unlock_bh(&priv->lock); } +static void nft_rbtree_remove(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) +{ + struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); + struct nft_rbtree *priv = nft_set_priv(set); + + nft_rbtree_erase(priv, rbe); +} + static void nft_rbtree_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_rbtree_elem *rbe = elem->priv; + struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &rbe->ext); } -static bool nft_rbtree_flush(const struct net *net, - const struct nft_set *set, void *priv) +static void nft_rbtree_flush(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) { - struct nft_rbtree_elem *rbe = priv; + struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &rbe->ext); - - return true; } -static void *nft_rbtree_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { + struct nft_rbtree_elem *rbe, *this = nft_elem_priv_cast(elem->priv); const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; - struct nft_rbtree_elem *rbe, *this = elem->priv; u8 genmask = nft_genmask_next(net); int d; @@ -568,12 +571,14 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; + } else if (nft_set_elem_expired(&rbe->ext)) { + break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; } - nft_rbtree_flush(net, set, rbe); - return rbe; + nft_rbtree_flush(net, set, &rbe->priv); + return &rbe->priv; } } return NULL; @@ -585,7 +590,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; - struct nft_set_elem elem; struct rb_node *node; read_lock_bh(&priv->lock); @@ -597,9 +601,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; - elem.priv = rbe; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { read_unlock_bh(&priv->lock); return; @@ -610,45 +612,36 @@ cont: read_unlock_bh(&priv->lock); } -static void nft_rbtree_gc(struct work_struct *work) +static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) { + nft_setelem_data_deactivate(net, set, &rbe->priv); + nft_rbtree_erase(priv, rbe); +} + +static void nft_rbtree_gc(struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe, *rbe_end = NULL; struct nftables_pernet *nft_net; - struct nft_rbtree *priv; + struct rb_node *node, *next; struct nft_trans_gc *gc; - struct rb_node *node; - struct nft_set *set; - unsigned int gc_seq; struct net *net; - priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); net = read_pnet(&set->net); nft_net = nft_pernet(net); - gc_seq = READ_ONCE(nft_net->gc_seq); - if (nft_set_gc_is_pending(set)) - goto done; - - gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (!gc) - goto done; - - read_lock_bh(&priv->lock); - for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + return; - /* Ruleset has been updated, try later. */ - if (READ_ONCE(nft_net->gc_seq) != gc_seq) { - nft_trans_gc_destroy(gc); - gc = NULL; - goto try_later; - } + for (node = rb_first(&priv->root); node ; node = next) { + next = rb_next(node); rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (nft_set_elem_is_dead(&rbe->ext)) - goto dead_elem; - /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is * always visited before the start element. @@ -660,37 +653,34 @@ static void nft_rbtree_gc(struct work_struct *work) if (!nft_set_elem_expired(&rbe->ext)) continue; - nft_set_elem_dead(&rbe->ext); - - if (!rbe_end) - continue; - - nft_set_elem_dead(&rbe_end->ext); - - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; - nft_trans_gc_elem_add(gc, rbe_end); - rbe_end = NULL; -dead_elem: - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + /* end element needs to be removed first, it has + * no timeout extension. + */ + if (rbe_end) { + nft_rbtree_gc_remove(net, set, priv, rbe_end); + nft_trans_gc_elem_add(gc, rbe_end); + rbe_end = NULL; + } + + gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; + nft_rbtree_gc_remove(net, set, priv, rbe); nft_trans_gc_elem_add(gc, rbe); } - gc = nft_trans_gc_catchall_async(gc, gc_seq); - try_later: - read_unlock_bh(&priv->lock); - if (gc) - nft_trans_gc_queue_async_done(gc); -done: - queue_delayed_work(system_power_efficient_wq, &priv->gc_work, - nft_set_gc_interval(set)); + if (gc) { + gc = nft_trans_gc_catchall_sync(gc); + nft_trans_gc_queue_sync_done(gc); + priv->last_gc = jiffies; + } } static u64 nft_rbtree_privsize(const struct nlattr * const nla[], @@ -705,15 +695,12 @@ static int nft_rbtree_init(const struct nft_set *set, { struct nft_rbtree *priv = nft_set_priv(set); + BUILD_BUG_ON(offsetof(struct nft_rbtree_elem, priv) != 0); + rwlock_init(&priv->lock); seqcount_rwlock_init(&priv->count, &priv->lock); priv->root = RB_ROOT; - INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rbtree_gc); - if (set->flags & NFT_SET_TIMEOUT) - queue_delayed_work(system_power_efficient_wq, &priv->gc_work, - nft_set_gc_interval(set)); - return 0; } @@ -724,12 +711,10 @@ static void nft_rbtree_destroy(const struct nft_ctx *ctx, struct nft_rbtree_elem *rbe; struct rb_node *node; - cancel_delayed_work_sync(&priv->gc_work); - rcu_barrier(); while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nf_tables_set_elem_destroy(ctx, set, rbe); + nf_tables_set_elem_destroy(ctx, set, &rbe->priv); } } @@ -751,6 +736,21 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static void nft_rbtree_commit(struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); + + if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) + nft_rbtree_gc(set); +} + +static void nft_rbtree_gc_init(const struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); + + priv->last_gc = jiffies; +} + const struct nft_set_type nft_set_rbtree_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { @@ -764,6 +764,8 @@ const struct nft_set_type nft_set_rbtree_type = { .deactivate = nft_rbtree_deactivate, .flush = nft_rbtree_flush, .activate = nft_rbtree_activate, + .commit = nft_rbtree_commit, + .gc_init = nft_rbtree_gc_init, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .get = nft_rbtree_get, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 8315d31b53db..92ef5ed2e7b0 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -225,7 +225,8 @@ static void genl_op_from_split(struct genl_op_iter *iter) } if (i + cnt < family->n_split_ops && - family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP) { + family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP && + (!cnt || family->split_ops[i + cnt].cmd == iter->doit.cmd)) { iter->dumpit = family->split_ops[i + cnt]; genl_op_fill_in_reject_policy_split(family, &iter->dumpit); cnt++; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index e2f111edf66c..1f8909c16f14 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -230,6 +230,8 @@ int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt) case NLA_S16: case NLA_S32: case NLA_S64: + case NLA_SINT: + case NLA_UINT: /* maximum is common, u64 min/max with padding */ return common + 2 * (nla_attr_size(0) + nla_attr_size(sizeof(u64))); @@ -288,6 +290,7 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, case NLA_U16: case NLA_U32: case NLA_U64: + case NLA_UINT: case NLA_MSECS: { struct netlink_range_validation range; @@ -297,8 +300,10 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, type = NL_ATTR_TYPE_U16; else if (pt->type == NLA_U32) type = NL_ATTR_TYPE_U32; - else + else if (pt->type == NLA_U64) type = NL_ATTR_TYPE_U64; + else + type = NL_ATTR_TYPE_UINT; if (pt->validation_type == NLA_VALIDATE_MASK) { if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MASK, @@ -320,7 +325,8 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, case NLA_S8: case NLA_S16: case NLA_S32: - case NLA_S64: { + case NLA_S64: + case NLA_SINT: { struct netlink_range_validation_signed range; if (pt->type == NLA_S8) @@ -329,8 +335,10 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, type = NL_ATTR_TYPE_S16; else if (pt->type == NLA_S32) type = NL_ATTR_TYPE_S32; - else + else if (pt->type == NLA_S64) type = NL_ATTR_TYPE_S64; + else + type = NL_ATTR_TYPE_SINT; nla_get_range_signed(pt, &range); diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index 0935527d1d12..b68150c971d0 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -151,6 +151,8 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge) int ret; skb = nci_skb_alloc(nspi->ndev, 0, GFP_KERNEL); + if (!skb) + return -ENOMEM; /* add the NCI SPI header to the start of the buffer */ hdr = skb_push(skb, NCI_SPI_HDR_LEN); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 08630896b6c8..14cc8fe8584b 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1180,7 +1180,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) init_waitqueue_head(&data->read_wait); mutex_lock(&rfkill_global_mutex); - mutex_lock(&data->mtx); /* * start getting events from elsewhere but hold mtx to get * startup events added first @@ -1192,10 +1191,11 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) goto free; rfkill_sync(rfkill); rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD); + mutex_lock(&data->mtx); list_add_tail(&ev->list, &data->events); + mutex_unlock(&data->mtx); } list_add(&data->list, &rfkill_fds); - mutex_unlock(&data->mtx); mutex_unlock(&rfkill_global_mutex); file->private_data = data; @@ -1203,7 +1203,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) return stream_open(inode, file); free: - mutex_unlock(&data->mtx); mutex_unlock(&rfkill_global_mutex); mutex_destroy(&data->mtx); list_for_each_entry_safe(ev, tmp, &data->events, list) diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index e9d1b2f2ff0a..5a81505fba9a 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -108,13 +108,13 @@ static int rfkill_gpio_probe(struct platform_device *pdev) rfkill->clk = devm_clk_get(&pdev->dev, NULL); - gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW); + gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_ASIS); if (IS_ERR(gpio)) return PTR_ERR(gpio); rfkill->reset_gpio = gpio; - gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW); + gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_ASIS); if (IS_ERR(gpio)) return PTR_ERR(gpio); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 7c652d14528b..9583645e86c2 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -278,7 +278,16 @@ err_nat: return err; } +static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) +{ + return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && + test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) && + !test_bit(NF_FLOW_HW_PENDING, &flow->flags) && + !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); +} + static struct nf_flowtable_type flowtable_ct = { + .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, .owner = THIS_MODULE, }; @@ -690,7 +699,6 @@ static struct tc_action_ops act_ct_ops; struct tc_ct_action_net { struct tc_action_net tn; /* Must be first */ - bool labels; }; /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ @@ -829,8 +837,13 @@ static void tcf_ct_params_free(struct tcf_ct_params *params) } if (params->ct_ft) tcf_ct_flow_table_put(params->ct_ft); - if (params->tmpl) + if (params->tmpl) { + if (params->put_labels) + nf_connlabels_put(nf_ct_net(params->tmpl)); + nf_ct_put(params->tmpl); + } + kfree(params); } @@ -1154,9 +1167,9 @@ static int tcf_ct_fill_params(struct net *net, struct nlattr **tb, struct netlink_ext_ack *extack) { - struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); struct nf_conntrack_zone zone; int err, family, proto, len; + bool put_labels = false; struct nf_conn *tmpl; char *name; @@ -1186,15 +1199,20 @@ static int tcf_ct_fill_params(struct net *net, } if (tb[TCA_CT_LABELS]) { + unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) { NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled."); return -EOPNOTSUPP; } - if (!tn->labels) { + if (nf_connlabels_get(net, n_bits - 1)) { NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length"); return -EOPNOTSUPP; + } else { + put_labels = true; } + tcf_ct_set_key_val(tb, p->labels, TCA_CT_LABELS, p->labels_mask, TCA_CT_LABELS_MASK, @@ -1238,10 +1256,15 @@ static int tcf_ct_fill_params(struct net *net, } } + p->put_labels = put_labels; + if (p->ct_action & TCA_CT_ACT_COMMIT) __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); return 0; err: + if (put_labels) + nf_connlabels_put(net); + nf_ct_put(p->tmpl); p->tmpl = NULL; return err; @@ -1542,32 +1565,13 @@ static struct tc_action_ops act_ct_ops = { static __net_init int ct_init_net(struct net *net) { - unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); - if (nf_connlabels_get(net, n_bits - 1)) { - tn->labels = false; - pr_err("act_ct: Failed to set connlabels length"); - } else { - tn->labels = true; - } - return tc_action_net_init(net, &tn->tn, &act_ct_ops); } static void __net_exit ct_exit_net(struct list_head *net_list) { - struct net *net; - - rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) { - struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); - - if (tn->labels) - nf_connlabels_put(net); - } - rtnl_unlock(); - tc_action_net_exit(net_list, act_ct_ops.net_id); } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 8eacdb54e72f..0fd18c344ab5 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -383,6 +383,10 @@ static struct fq_flow *fq_classify(struct Qdisc *sch, struct sk_buff *skb, if (fq_fastpath_check(sch, skb, now)) { q->internal.stat_fastpath_packets++; + if (skb->sk == sk && q->rate_enable && + READ_ONCE(sk->sk_pacing_status) != SK_PACING_FQ) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); return &q->internal; } @@ -651,7 +655,7 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) begin: head = fq_pband_head_select(pband); if (!head) { - while (++retry < FQ_BANDS) { + while (++retry <= FQ_BANDS) { if (++q->band_nr == FQ_BANDS) q->band_nr = 0; pband = &q->band_flows[q->band_nr]; @@ -893,7 +897,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) return 0; } -static struct netlink_range_validation iq_range = { +static const struct netlink_range_validation iq_range = { .max = INT_MAX, }; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 68e6acd0f130..5b595773e59b 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -202,7 +202,7 @@ out: return NET_XMIT_CN; } -static struct netlink_range_validation fq_pie_q_range = { +static const struct netlink_range_validation fq_pie_q_range = { .min = 1, .max = 1 << 20, }; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3554085bc2be..880c5f16b29c 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -902,6 +902,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc, cl->cl_flags |= HFSC_USC; } +static void +hfsc_upgrade_rt(struct hfsc_class *cl) +{ + cl->cl_fsc = cl->cl_rsc; + rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); + cl->cl_flags |= HFSC_FSC; +} + static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { [TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) }, @@ -1011,10 +1019,6 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (parent == NULL) return -ENOENT; } - if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { - NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC"); - return -EINVAL; - } if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0) return -EINVAL; @@ -1065,6 +1069,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->cf_tree = RB_ROOT; sch_tree_lock(sch); + /* Check if the inner class is a misconfigured 'rt' */ + if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { + NL_SET_ERR_MSG(extack, + "Forced curve change on parent 'rt' to 'sc'"); + hfsc_upgrade_rt(parent); + } qdisc_class_hash_insert(&q->clhash, &cl->cl_common); list_add_tail(&cl->siblings, &parent->children); if (parent->level == 0) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 546c10adcacd..28315166fe8e 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -213,7 +213,7 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct qfq_class, common); } -static struct netlink_range_validation lmax_range = { +static const struct netlink_range_validation lmax_range = { .min = QFQ_MIN_LMAX, .max = QFQ_MAX_LMAX, }; @@ -1003,7 +1003,7 @@ static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, *cl = list_first_entry(&agg->active, struct qfq_class, alist); skb = (*cl)->qdisc->ops->peek((*cl)->qdisc); if (skb == NULL) - WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n"); + qdisc_warn_nonwc("qfq_dequeue", (*cl)->qdisc); else *len = qdisc_pkt_len(skb); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 1cb5e41c0ec7..2e1949de4171 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1015,7 +1015,7 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { TC_FP_PREEMPTIBLE), }; -static struct netlink_range_validation_signed taprio_cycle_time_range = { +static const struct netlink_range_validation_signed taprio_cycle_time_range = { .min = 0, .max = INT_MAX, }; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 297681601414..abd2667734d4 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1201,6 +1201,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, (struct smc_clc_msg_accept_confirm_v2 *)aclc; struct smc_clc_first_contact_ext *fce = smc_get_clc_first_contact_ext(clc_v2, false); + struct net *net = sock_net(&smc->sk); int rc; if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1) @@ -1210,7 +1211,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN); ini->smcrv2.uses_gateway = false; } else { - if (smc_ib_find_route(smc->clcsock->sk->sk_rcv_saddr, + if (smc_ib_find_route(net, smc->clcsock->sk->sk_rcv_saddr, smc_ib_gid_to_ipv4(aclc->r0.lcl.gid), ini->smcrv2.nexthop_mac, &ini->smcrv2.uses_gateway)) @@ -2361,7 +2362,7 @@ static int smc_listen_find_device(struct smc_sock *new_smc, smc_find_ism_store_rc(rc, ini); return (!rc) ? 0 : ini->rc; } - return SMC_CLC_DECL_NOSMCDEV; + return prfx_rc; } /* listen worker: finish RDMA setup */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 9b66d6aeeb1a..89981dbe46c9 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -193,7 +193,7 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; } -int smc_ib_find_route(__be32 saddr, __be32 daddr, +int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, u8 nexthop_mac[], u8 *uses_gateway) { struct neighbour *neigh = NULL; @@ -205,7 +205,7 @@ int smc_ib_find_route(__be32 saddr, __be32 daddr, if (daddr == cpu_to_be32(INADDR_NONE)) goto out; - rt = ip_route_output_flow(&init_net, &fl4, NULL); + rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out; if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET) @@ -235,6 +235,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev, if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) { struct in_device *in_dev = __in_dev_get_rcu(ndev); + struct net *net = dev_net(ndev); const struct in_ifaddr *ifa; bool subnet_match = false; @@ -248,7 +249,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev, } if (!subnet_match) goto out; - if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr, + if (smcrv2->daddr && smc_ib_find_route(net, smcrv2->saddr, smcrv2->daddr, smcrv2->nexthop_mac, &smcrv2->uses_gateway)) diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 4df5f8c8a0a1..ef8ac2b7546d 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -112,7 +112,7 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk, int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index, struct smc_init_info_smcrv2 *smcrv2); -int smc_ib_find_route(__be32 saddr, __be32 daddr, +int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, u8 nexthop_mac[], u8 *uses_gateway); bool smc_ib_is_valid_local_systemid(void); int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/tls/tls.h b/net/tls/tls.h index 478b2c0060aa..762f424ff2d5 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -144,8 +144,7 @@ void tls_err_abort(struct sock *sk, int err); int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, - const struct tls_cipher_desc *cipher_desc, - int mode); + const struct tls_cipher_desc *cipher_desc); int tls_set_sw_offload(struct sock *sk, int tx); void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index f01543557a60..bf8ed36b1ad6 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1099,7 +1099,7 @@ int tls_set_device_offload(struct sock *sk) goto release_netdev; } - rc = init_prot_info(prot, crypto_info, cipher_desc, TLS_HW); + rc = init_prot_info(prot, crypto_info, cipher_desc); if (rc) goto release_netdev; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b125a08a618a..1c2c6800949d 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -140,8 +140,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx) int wait_on_pending_writer(struct sock *sk, long *timeo) { - int rc = 0; DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret, rc = 0; add_wait_queue(sk_sleep(sk), &wait); while (1) { @@ -155,9 +155,13 @@ int wait_on_pending_writer(struct sock *sk, long *timeo) break; } - if (sk_wait_event(sk, timeo, - !READ_ONCE(sk->sk_write_pending), &wait)) + ret = sk_wait_event(sk, timeo, + !READ_ONCE(sk->sk_write_pending), &wait); + if (ret) { + if (ret < 0) + rc = ret; break; + } } remove_wait_queue(sk_sleep(sk), &wait); return rc; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0f6da4ce3ed7..a78e8e722409 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1291,6 +1291,7 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; long timeo; timeo = sock_rcvtimeo(sk, nonblock); @@ -1302,6 +1303,9 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, if (sk->sk_err) return sock_error(sk); + if (ret < 0) + return ret; + if (!skb_queue_empty(&sk->sk_receive_queue)) { tls_strp_check_rcv(&ctx->strp); if (tls_strp_msg_ready(ctx)) @@ -1320,10 +1324,10 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, released = true; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - sk_wait_event(sk, &timeo, - tls_strp_msg_ready(ctx) || - !sk_psock_queue_empty(psock), - &wait); + ret = sk_wait_event(sk, &timeo, + tls_strp_msg_ready(ctx) || + !sk_psock_queue_empty(psock), + &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); @@ -1852,6 +1856,7 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx, bool nonblock) { long timeo; + int ret; timeo = sock_rcvtimeo(sk, nonblock); @@ -1861,14 +1866,16 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx, ctx->reader_contended = 1; add_wait_queue(&ctx->wq, &wait); - sk_wait_event(sk, &timeo, - !READ_ONCE(ctx->reader_present), &wait); + ret = sk_wait_event(sk, &timeo, + !READ_ONCE(ctx->reader_present), &wait); remove_wait_queue(&ctx->wq, &wait); if (timeo <= 0) return -EAGAIN; if (signal_pending(current)) return sock_intr_errno(timeo); + if (ret < 0) + return ret; } WRITE_ONCE(ctx->reader_present, 1); @@ -2622,8 +2629,7 @@ static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx) int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, - const struct tls_cipher_desc *cipher_desc, - int mode) + const struct tls_cipher_desc *cipher_desc) { u16 nonce_size = cipher_desc->nonce; @@ -2636,11 +2642,6 @@ int init_prot_info(struct tls_prot_info *prot, prot->tail_size = 0; } - if (mode == TLS_HW) { - prot->aad_size = 0; - prot->tail_size = 0; - } - /* Sanity-check the sizes for stack allocations. */ if (nonce_size > TLS_MAX_IV_SIZE || prot->aad_size > TLS_MAX_AAD_SIZE) return -EINVAL; @@ -2700,7 +2701,7 @@ int tls_set_sw_offload(struct sock *sk, int tx) goto free_priv; } - rc = init_prot_info(prot, crypto_info, cipher_desc, TLS_SW); + rc = init_prot_info(prot, crypto_info, cipher_desc); if (rc) goto free_priv; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index d324ae13e2f5..af5bab1acee1 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -636,6 +636,11 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) virtio_device_ready(vdev); + return 0; +} + +static void virtio_vsock_vqs_start(struct virtio_vsock *vsock) +{ mutex_lock(&vsock->tx_lock); vsock->tx_run = true; mutex_unlock(&vsock->tx_lock); @@ -650,7 +655,16 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) vsock->event_run = true; mutex_unlock(&vsock->event_lock); - return 0; + /* virtio_transport_send_pkt() can queue packets once + * the_virtio_vsock is set, but they won't be processed until + * vsock->tx_run is set to true. We queue vsock->send_pkt_work + * when initialization finishes to send those packets queued + * earlier. + * We don't need to queue the other workers (rx, event) because + * as long as we don't fill the queues with empty buffers, the + * host can't send us any notification. + */ + queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); } static void virtio_vsock_vqs_del(struct virtio_vsock *vsock) @@ -749,6 +763,7 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->out_sgs[i] = &vsock->out_bufs[i]; rcu_assign_pointer(the_virtio_vsock, vsock); + virtio_vsock_vqs_start(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -821,6 +836,7 @@ static int virtio_vsock_restore(struct virtio_device *vdev) goto out; rcu_assign_pointer(the_virtio_vsock, vsock); + virtio_vsock_vqs_start(vsock); out: mutex_unlock(&the_virtio_vsock_mutex); diff --git a/net/wireless/core.c b/net/wireless/core.c index 7df8ffcfa0c4..758c9a2a12c0 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1613,7 +1613,7 @@ void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work) list_add_tail(&work->entry, &rdev->wiphy_work_list); spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); - schedule_work(&rdev->wiphy_work); + queue_work(system_unbound_wq, &rdev->wiphy_work); } EXPORT_SYMBOL_GPL(wiphy_work_queue); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index f90f58c65688..bad9e4fd842f 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -43,10 +43,11 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { cr.links[link_id].status = data->links[link_id].status; + cr.links[link_id].bss = data->links[link_id].bss; + WARN_ON_ONCE(cr.links[link_id].status != WLAN_STATUS_SUCCESS && (!cr.ap_mld_addr || !cr.links[link_id].bss)); - cr.links[link_id].bss = data->links[link_id].bss; if (!cr.links[link_id].bss) continue; cr.links[link_id].bssid = data->links[link_id].bss->bssid; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 56fd7cf2563b..569234bc2be6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -463,7 +463,7 @@ nl80211_sta_wme_policy[NL80211_STA_WME_MAX + 1] = { [NL80211_STA_WME_MAX_SP] = { .type = NLA_U8 }, }; -static struct netlink_range_validation nl80211_punct_bitmap_range = { +static const struct netlink_range_validation nl80211_punct_bitmap_range = { .min = 0, .max = 0xffff, }; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 6c2acd3fa36a..9e5ccffd6868 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2147,7 +2147,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, if (!res) goto drop; - rdev_inform_bss(rdev, &res->pub, ies, data->drv_data); + rdev_inform_bss(rdev, &res->pub, ies, drv_data->drv_data); if (data->bss_source == BSS_SOURCE_MBSSID) { /* this is a nontransmitting bss, we need to add it to diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index f5e96e0d6e01..ae9f8cb611f6 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -33,6 +33,7 @@ #include "xsk.h" #define TX_BATCH_SIZE 32 +#define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE) static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); @@ -391,6 +392,16 @@ void __xsk_map_flush(void) } } +#ifdef CONFIG_DEBUG_NET +bool xsk_map_check_flush(void) +{ + if (list_empty(this_cpu_ptr(&xskmap_flush_list))) + return false; + __xsk_map_flush(); + return true; +} +#endif + void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { xskq_prod_submit_n(pool->cq, nb_entries); @@ -413,16 +424,25 @@ EXPORT_SYMBOL(xsk_tx_release); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { + bool budget_exhausted = false; struct xdp_sock *xs; rcu_read_lock(); +again: list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { + if (xs->tx_budget_spent >= MAX_PER_SOCKET_BUDGET) { + budget_exhausted = true; + continue; + } + if (!xskq_cons_peek_desc(xs->tx, desc, pool)) { if (xskq_has_descs(xs->tx)) xskq_cons_release(xs->tx); continue; } + xs->tx_budget_spent++; + /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement @@ -436,6 +456,14 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) return true; } + if (budget_exhausted) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) + xs->tx_budget_spent = 0; + + budget_exhausted = false; + goto again; + } + out: rcu_read_unlock(); return false; diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index b86474084690..e21cc71095bb 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -380,8 +380,8 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err) skb->dev = dev; if (err) { - dev->stats.rx_errors++; - dev->stats.rx_dropped++; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_dropped); return 0; } @@ -426,7 +426,6 @@ static int xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct xfrm_if *xi = netdev_priv(dev); - struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); unsigned int length = skb->len; struct net_device *tdev; @@ -473,7 +472,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) tdev = dst->dev; if (tdev == dev) { - stats->collisions++; + DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", dev->name); goto tx_err_dst_release; @@ -512,13 +511,13 @@ xmit: if (net_xmit_eval(err) == 0) { dev_sw_netstats_tx_add(dev, 1, length); } else { - stats->tx_errors++; - stats->tx_aborted_errors++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_aborted_errors); } return 0; tx_err_link_failure: - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); @@ -528,7 +527,6 @@ tx_err_dst_release: static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); - struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; @@ -545,7 +543,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); if (dst->error) { dst_release(dst); - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, dst); @@ -561,7 +559,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); if (IS_ERR(rt)) { - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, &rt->dst); @@ -580,8 +578,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; tx_err: - stats->tx_errors++; - stats->tx_dropped++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index c4c4fc29ccf5..5cdd3bca3637 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -851,7 +851,7 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, struct hlist_node *newpos = NULL; bool matches_s, matches_d; - if (!policy->bydst_reinsert) + if (policy->walk.dead || !policy->bydst_reinsert) continue; WARN_ON_ONCE(policy->family != family); @@ -1256,8 +1256,11 @@ static void xfrm_hash_rebuild(struct work_struct *work) struct xfrm_pol_inexact_bin *bin; u8 dbits, sbits; + if (policy->walk.dead) + continue; + dir = xfrm_policy_id2dir(policy->index); - if (policy->walk.dead || dir >= XFRM_POLICY_MAX) + if (dir >= XFRM_POLICY_MAX) continue; if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { @@ -1372,8 +1375,6 @@ EXPORT_SYMBOL(xfrm_policy_hash_rebuild); * of an absolute inpredictability of ordering of rules. This will not pass. */ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { - static u32 idx_generator; - for (;;) { struct hlist_head *list; struct xfrm_policy *p; @@ -1381,8 +1382,8 @@ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) int found; if (!index) { - idx = (idx_generator | dir); - idx_generator += 8; + idx = (net->xfrm.idx_generator | dir); + net->xfrm.idx_generator += 8; } else { idx = index; index = 0; @@ -1823,9 +1824,11 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { + if (pol->walk.dead) + continue; + dir = xfrm_policy_id2dir(pol->index); - if (pol->walk.dead || - dir >= XFRM_POLICY_MAX || + if (dir >= XFRM_POLICY_MAX || pol->type != type) continue; @@ -1862,9 +1865,11 @@ int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { + if (pol->walk.dead) + continue; + dir = xfrm_policy_id2dir(pol->index); - if (pol->walk.dead || - dir >= XFRM_POLICY_MAX || + if (dir >= XFRM_POLICY_MAX || pol->xdo.dev != dev) continue; @@ -3215,7 +3220,7 @@ no_transform: } for (i = 0; i < num_pols; i++) - pols[i]->curlft.use_time = ktime_get_real_seconds(); + WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds()); if (num_xfrms < 0) { /* Prohibit the flow */ |