diff options
Diffstat (limited to 'net')
117 files changed, 1296 insertions, 668 deletions
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index c64050e839ac..1fffe2bed5b0 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -280,6 +280,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock); for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 17b946f9ba31..8455ba141ee6 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -68,7 +68,7 @@ static const struct sco_param esco_param_msbc[] = { }; /* This function requires the caller holds hdev->lock */ -static void hci_connect_le_scan_cleanup(struct hci_conn *conn) +static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; @@ -88,9 +88,28 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn) params = hci_pend_le_action_lookup(&hdev->pend_le_conns, bdaddr, bdaddr_type); - if (!params || !params->explicit_connect) + if (!params) return; + if (params->conn) { + hci_conn_drop(params->conn); + hci_conn_put(params->conn); + params->conn = NULL; + } + + if (!params->explicit_connect) + return; + + /* If the status indicates successful cancellation of + * the attempt (i.e. Unknown Connection Id) there's no point of + * notifying failure since we'll go back to keep trying to + * connect. The only exception is explicit connect requests + * where a timeout + cancel does indicate an actual failure. + */ + if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + /* The connection attempt was doing scan for new RPA, and is * in scan phase. If params are not associated with any other * autoconnect action, remove them completely. If they are, just unmark @@ -178,7 +197,7 @@ static void le_scan_cleanup(struct work_struct *work) rcu_read_unlock(); if (c == conn) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); hci_conn_cleanup(conn); } @@ -1049,6 +1068,17 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, return conn; } +static bool hci_conn_unlink(struct hci_conn *conn) +{ + if (!conn->link) + return false; + + conn->link->link = NULL; + conn->link = NULL; + + return true; +} + int hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -1060,15 +1090,16 @@ int hci_conn_del(struct hci_conn *conn) cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - struct hci_conn *sco = conn->link; - if (sco) { - sco->link = NULL; + struct hci_conn *link = conn->link; + + if (link) { + hci_conn_unlink(conn); /* Due to race, SCO connection might be not established * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. */ - if (sco->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(sco); + if (link->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(link); } /* Unacked frames */ @@ -1084,7 +1115,7 @@ int hci_conn_del(struct hci_conn *conn) struct hci_conn *acl = conn->link; if (acl) { - acl->link = NULL; + hci_conn_unlink(conn); hci_conn_drop(acl); } @@ -1179,31 +1210,8 @@ EXPORT_SYMBOL(hci_get_route); static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; - struct hci_conn_params *params; - params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, - conn->dst_type); - if (params && params->conn) { - hci_conn_drop(params->conn); - hci_conn_put(params->conn); - params->conn = NULL; - } - - /* If the status indicates successful cancellation of - * the attempt (i.e. Unknown Connection Id) there's no point of - * notifying failure since we'll go back to keep trying to - * connect. The only exception is explicit connect requests - * where a timeout + cancel does indicate an actual failure. - */ - if (status != HCI_ERROR_UNKNOWN_CONN_ID || - (params && params->explicit_connect)) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, status); - - /* Since we may have temporarily stopped the background scanning in - * favor of connection establishment, we should restart it. - */ - hci_update_passive_scan(hdev); + hci_connect_le_scan_cleanup(conn, status); /* Enable advertising in case this was a failed connection * attempt as a peripheral. @@ -1237,15 +1245,15 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; + bt_dev_dbg(hdev, "err %d", err); + hci_dev_lock(hdev); if (!err) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); goto done; } - bt_dev_err(hdev, "request failed to create LE connection: err %d", err); - /* Check if connection is still pending */ if (conn != hci_lookup_le_connect(hdev)) goto done; @@ -2438,6 +2446,12 @@ void hci_conn_hash_flush(struct hci_dev *hdev) c->state = BT_CLOSED; hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + + /* Unlink before deleting otherwise it is possible that + * hci_conn_del removes the link which may cause the list to + * contain items already freed. + */ + hci_conn_unlink(c); hci_conn_del(c); } } @@ -2775,6 +2789,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) { int r = 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b65c3aabcd53..334e308451f5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2871,10 +2871,25 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb) return -ENXIO; } - if (hci_skb_pkt_type(skb) != HCI_EVENT_PKT && - hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && - hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && - hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) { + switch (hci_skb_pkt_type(skb)) { + case HCI_EVENT_PKT: + break; + case HCI_ACLDATA_PKT: + /* Detect if ISO packet has been sent as ACL */ + if (hci_conn_num(hdev, ISO_LINK)) { + __u16 handle = __le16_to_cpu(hci_acl_hdr(skb)->handle); + __u8 type; + + type = hci_conn_lookup_type(hdev, hci_handle(handle)); + if (type == ISO_LINK) + hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; + } + break; + case HCI_SCODATA_PKT: + break; + case HCI_ISODATA_PKT: + break; + default: kfree_skb(skb); return -EINVAL; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ad92a4be5851..e87c928c9e17 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2881,16 +2881,6 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, conn->resp_addr_type = peer_addr_type; bacpy(&conn->resp_addr, peer_addr); - - /* We don't want the connection attempt to stick around - * indefinitely since LE doesn't have a page timeout concept - * like BR/EDR. Set a timer for any connection that doesn't use - * the accept list for connecting. - */ - if (filter_policy == HCI_LE_USE_PEER_ADDR) - queue_delayed_work(conn->hdev->workqueue, - &conn->le_conn_timeout, - conn->conn_timeout); } static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) @@ -5902,6 +5892,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, if (status) goto unlock; + /* Drop the connection if it has been aborted */ + if (test_bit(HCI_CONN_CANCEL, &conn->flags)) { + hci_conn_drop(conn); + goto unlock; + } + if (conn->dst_type == ADDR_LE_DEV_PUBLIC) addr_type = BDADDR_LE_PUBLIC; else @@ -6995,7 +6991,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.in.sdu = le16_to_cpu(ev->max_pdu); - hci_connect_cfm(bis, ev->status); + hci_iso_setup_path(bis); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 117eedb6f709..632be1267288 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -246,8 +246,9 @@ 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)) { - bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, - PTR_ERR(skb)); + if (!event) + bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, + PTR_ERR(skb)); return PTR_ERR(skb); } @@ -643,6 +644,7 @@ void hci_cmd_sync_clear(struct hci_dev *hdev) cancel_work_sync(&hdev->cmd_sync_work); cancel_work_sync(&hdev->reenable_adv_work); + mutex_lock(&hdev->cmd_sync_work_lock); list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) { if (entry->destroy) entry->destroy(hdev, entry->data, -ECANCELED); @@ -650,6 +652,7 @@ void hci_cmd_sync_clear(struct hci_dev *hdev) list_del(&entry->list); kfree(entry); } + mutex_unlock(&hdev->cmd_sync_work_lock); } void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) @@ -2367,6 +2370,45 @@ static int hci_resume_advertising_sync(struct hci_dev *hdev) return err; } +static int hci_pause_addr_resolution(struct hci_dev *hdev) +{ + int err; + + if (!use_ll_privacy(hdev)) + return 0; + + if (!hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION)) + return 0; + + /* Cannot disable addr resolution if scanning is enabled or + * when initiating an LE connection. + */ + if (hci_dev_test_flag(hdev, HCI_LE_SCAN) || + hci_lookup_le_connect(hdev)) { + bt_dev_err(hdev, "Command not allowed when scan/LE connect"); + return -EPERM; + } + + /* Cannot disable addr resolution if advertising is enabled. */ + err = hci_pause_advertising_sync(hdev); + if (err) { + bt_dev_err(hdev, "Pause advertising failed: %d", err); + return err; + } + + err = hci_le_set_addr_resolution_enable_sync(hdev, 0x00); + if (err) + bt_dev_err(hdev, "Unable to disable Address Resolution: %d", + err); + + /* Return if address resolution is disabled and RPA is not used. */ + if (!err && scan_use_rpa(hdev)) + return err; + + hci_resume_advertising_sync(hdev); + return err; +} + struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, bool extended, struct sock *sk) { @@ -2402,7 +2444,7 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) u8 filter_policy; int err; - /* Pause advertising if resolving list can be used as controllers are + /* Pause advertising if resolving list can be used as controllers * cannot accept resolving list modifications while advertising. */ if (use_ll_privacy(hdev)) { @@ -3319,6 +3361,7 @@ static const struct hci_init_stage amp_init1[] = { HCI_INIT(hci_read_flow_control_mode_sync), /* HCI_OP_READ_LOCATION_DATA */ HCI_INIT(hci_read_location_data_sync), + {} }; static int hci_init1_sync(struct hci_dev *hdev) @@ -3353,6 +3396,7 @@ static int hci_init1_sync(struct hci_dev *hdev) static const struct hci_init_stage amp_init2[] = { /* HCI_OP_READ_LOCAL_FEATURES */ HCI_INIT(hci_read_local_features_sync), + {} }; /* Read Buffer Size (ACL mtu, max pkt, etc.) */ @@ -5083,8 +5127,11 @@ static int hci_le_connect_cancel_sync(struct hci_dev *hdev, if (test_bit(HCI_CONN_SCANNING, &conn->flags)) return 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, - 6, &conn->dst, HCI_CMD_TIMEOUT); + 0, NULL, HCI_CMD_TIMEOUT); } static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -5394,27 +5441,12 @@ static int hci_active_scan_sync(struct hci_dev *hdev, uint16_t interval) cancel_interleave_scan(hdev); - /* Pause advertising since active scanning disables address resolution - * which advertising depend on in order to generate its RPAs. + /* Pause address resolution for active scan and stop advertising if + * privacy is enabled. */ - if (use_ll_privacy(hdev) && hci_dev_test_flag(hdev, HCI_PRIVACY)) { - err = hci_pause_advertising_sync(hdev); - if (err) { - bt_dev_err(hdev, "pause advertising failed: %d", err); - goto failed; - } - } - - /* Disable address resolution while doing active scanning since the - * accept list shall not be used and all reports shall reach the host - * anyway. - */ - err = hci_le_set_addr_resolution_enable_sync(hdev, 0x00); - if (err) { - bt_dev_err(hdev, "Unable to disable Address Resolution: %d", - err); + err = hci_pause_addr_resolution(hdev); + if (err) goto failed; - } /* All active scans will be done with either a resolvable private * address (when privacy feature has been enabled) or non-resolvable @@ -6074,6 +6106,9 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) conn->conn_timeout, NULL); done: + if (err == -ETIMEDOUT) + hci_le_connect_cancel_sync(hdev, conn); + /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); return err; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index bed1a7b9205c..707f229f896a 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -433,7 +433,7 @@ static void hidp_set_timer(struct hidp_session *session) static void hidp_del_timer(struct hidp_session *session) { if (session->idle_to > 0) - del_timer(&session->timer); + del_timer_sync(&session->timer); } static void hidp_process_report(struct hidp_session *session, int type, diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 24444b502e58..8d136a730163 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1620,7 +1620,6 @@ static void iso_disconn_cfm(struct hci_conn *hcon, __u8 reason) void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) { struct iso_conn *conn = hcon->iso_data; - struct hci_iso_data_hdr *hdr; __u16 pb, ts, len; if (!conn) @@ -1642,6 +1641,8 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) } if (ts) { + struct hci_iso_ts_data_hdr *hdr; + /* TODO: add timestamp to the packet? */ hdr = skb_pull_data(skb, HCI_ISO_TS_DATA_HDR_SIZE); if (!hdr) { @@ -1649,15 +1650,19 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) goto drop; } + len = __le16_to_cpu(hdr->slen); } else { + struct hci_iso_data_hdr *hdr; + hdr = skb_pull_data(skb, HCI_ISO_DATA_HDR_SIZE); if (!hdr) { BT_ERR("Frame is too short (len %d)", skb->len); goto drop; } + + len = __le16_to_cpu(hdr->slen); } - len = __le16_to_cpu(hdr->slen); flags = hci_iso_data_flags(len); len = hci_iso_data_len(len); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index adfc3ea06d08..55a7226233f9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -708,6 +708,17 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) } EXPORT_SYMBOL_GPL(l2cap_chan_del); +static void __l2cap_chan_list_id(struct l2cap_conn *conn, u16 id, + l2cap_chan_func_t func, void *data) +{ + struct l2cap_chan *chan, *l; + + list_for_each_entry_safe(chan, l, &conn->chan_l, list) { + if (chan->ident == id) + func(chan, data); + } +} + static void __l2cap_chan_list(struct l2cap_conn *conn, l2cap_chan_func_t func, void *data) { @@ -775,23 +786,9 @@ static void l2cap_chan_le_connect_reject(struct l2cap_chan *chan) static void l2cap_chan_ecred_connect_reject(struct l2cap_chan *chan) { - struct l2cap_conn *conn = chan->conn; - struct l2cap_ecred_conn_rsp rsp; - u16 result; - - if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) - result = L2CAP_CR_LE_AUTHORIZATION; - else - result = L2CAP_CR_LE_BAD_PSM; - l2cap_state_change(chan, BT_DISCONN); - memset(&rsp, 0, sizeof(rsp)); - - rsp.result = cpu_to_le16(result); - - l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_RSP, sizeof(rsp), - &rsp); + __l2cap_ecred_conn_rsp_defer(chan); } static void l2cap_chan_connect_reject(struct l2cap_chan *chan) @@ -846,7 +843,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) break; case L2CAP_MODE_EXT_FLOWCTL: l2cap_chan_ecred_connect_reject(chan); - break; + return; } } } @@ -3938,43 +3935,86 @@ void __l2cap_le_connect_rsp_defer(struct l2cap_chan *chan) &rsp); } -void __l2cap_ecred_conn_rsp_defer(struct l2cap_chan *chan) +static void l2cap_ecred_list_defer(struct l2cap_chan *chan, void *data) { + int *result = data; + + if (*result || test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) + return; + + switch (chan->state) { + case BT_CONNECT2: + /* If channel still pending accept add to result */ + (*result)++; + return; + case BT_CONNECTED: + return; + default: + /* If not connected or pending accept it has been refused */ + *result = -ECONNREFUSED; + return; + } +} + +struct l2cap_ecred_rsp_data { struct { struct l2cap_ecred_conn_rsp rsp; - __le16 dcid[5]; + __le16 scid[L2CAP_ECRED_MAX_CID]; } __packed pdu; + int count; +}; + +static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) +{ + struct l2cap_ecred_rsp_data *rsp = data; + + if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) + return; + + /* Reset ident so only one response is sent */ + chan->ident = 0; + + /* Include all channels pending with the same ident */ + if (!rsp->pdu.rsp.result) + rsp->pdu.rsp.dcid[rsp->count++] = cpu_to_le16(chan->scid); + else + l2cap_chan_del(chan, ECONNRESET); +} + +void __l2cap_ecred_conn_rsp_defer(struct l2cap_chan *chan) +{ struct l2cap_conn *conn = chan->conn; - u16 ident = chan->ident; - int i = 0; + struct l2cap_ecred_rsp_data data; + u16 id = chan->ident; + int result = 0; - if (!ident) + if (!id) return; - BT_DBG("chan %p ident %d", chan, ident); + BT_DBG("chan %p id %d", chan, id); - pdu.rsp.mtu = cpu_to_le16(chan->imtu); - pdu.rsp.mps = cpu_to_le16(chan->mps); - pdu.rsp.credits = cpu_to_le16(chan->rx_credits); - pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_SUCCESS); + memset(&data, 0, sizeof(data)); - mutex_lock(&conn->chan_lock); + data.pdu.rsp.mtu = cpu_to_le16(chan->imtu); + data.pdu.rsp.mps = cpu_to_le16(chan->mps); + data.pdu.rsp.credits = cpu_to_le16(chan->rx_credits); + data.pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_SUCCESS); - list_for_each_entry(chan, &conn->chan_l, list) { - if (chan->ident != ident) - continue; + /* Verify that all channels are ready */ + __l2cap_chan_list_id(conn, id, l2cap_ecred_list_defer, &result); - /* Reset ident so only one response is sent */ - chan->ident = 0; + if (result > 0) + return; - /* Include all channels pending with the same ident */ - pdu.dcid[i++] = cpu_to_le16(chan->scid); - } + if (result < 0) + data.pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_AUTHORIZATION); - mutex_unlock(&conn->chan_lock); + /* Build response */ + __l2cap_chan_list_id(conn, id, l2cap_ecred_rsp_defer, &data); - l2cap_send_cmd(conn, ident, L2CAP_ECRED_CONN_RSP, - sizeof(pdu.rsp) + i * sizeof(__le16), &pdu); + l2cap_send_cmd(conn, id, L2CAP_ECRED_CONN_RSP, + sizeof(data.pdu.rsp) + (data.count * sizeof(__le16)), + &data.pdu); } void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) @@ -4612,33 +4652,27 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, dcid); + chan = l2cap_get_chan_by_scid(conn, dcid); if (!chan) { - mutex_unlock(&conn->chan_lock); cmd_reject_invalid_cid(conn, cmd->ident, dcid, scid); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - rsp.dcid = cpu_to_le16(chan->scid); rsp.scid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp); chan->ops->set_shutdown(chan); + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, ECONNRESET); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -4658,33 +4692,27 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, scid); + chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); return 0; } + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, 0); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -6078,6 +6106,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); chan->ident = cmd->ident; + chan->mode = L2CAP_MODE_EXT_FLOWCTL; if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { l2cap_state_change(chan, BT_CONNECT2); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7add66f30e4d..249dc6777fb4 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -4639,12 +4639,6 @@ static int set_mgmt_mesh_func(struct sock *sk, struct hci_dev *hdev, MGMT_OP_SET_EXP_FEATURE, MGMT_STATUS_INVALID_INDEX); - /* Changes can only be made when controller is powered down */ - if (hdev_is_powered(hdev)) - return mgmt_cmd_status(sk, hdev->id, - MGMT_OP_SET_EXP_FEATURE, - MGMT_STATUS_REJECTED); - /* Parameters are limited to a single octet */ if (data_len != MGMT_SET_EXP_FEATURE_SIZE + 1) return mgmt_cmd_status(sk, hdev->id, @@ -9363,7 +9357,8 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { { add_ext_adv_data, MGMT_ADD_EXT_ADV_DATA_SIZE, HCI_MGMT_VAR_LEN }, { add_adv_patterns_monitor_rssi, - MGMT_ADD_ADV_PATTERNS_MONITOR_RSSI_SIZE }, + MGMT_ADD_ADV_PATTERNS_MONITOR_RSSI_SIZE, + HCI_MGMT_VAR_LEN }, { set_mesh, MGMT_SET_MESH_RECEIVER_SIZE, HCI_MGMT_VAR_LEN }, { mesh_features, MGMT_MESH_READ_FEATURES_SIZE }, diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1111da4e2f2b..cd1a27ac555d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -235,27 +235,41 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk, return err; } -static int sco_connect(struct hci_dev *hdev, struct sock *sk) +static int sco_connect(struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; + struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); + hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); + if (!hdev) + return -EHOSTUNREACH; + + hci_dev_lock(hdev); + if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) - return -EOPNOTSUPP; + (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { + err = -EOPNOTSUPP; + goto unlock; + } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting, &sco_pi(sk)->codec); - if (IS_ERR(hcon)) - return PTR_ERR(hcon); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } + + hci_dev_unlock(hdev); + hci_dev_put(hdev); conn = sco_conn_add(hcon); if (!conn) { @@ -263,13 +277,15 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) return -ENOMEM; } - /* Update source addr of the socket */ - bacpy(&sco_pi(sk)->src, &hcon->src); - err = sco_chan_add(conn, sk, NULL); if (err) return err; + lock_sock(sk); + + /* Update source addr of the socket */ + bacpy(&sco_pi(sk)->src, &hcon->src); + if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; @@ -278,6 +294,13 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) sco_sock_set_timer(sk, sk->sk_sndtimeo); } + release_sock(sk); + + return err; + +unlock: + hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } @@ -565,7 +588,6 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; - struct hci_dev *hdev; int err; BT_DBG("sk %p", sk); @@ -574,37 +596,26 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen addr->sa_family != AF_BLUETOOTH) return -EINVAL; - lock_sock(sk); - if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { - err = -EBADFD; - goto done; - } + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) + return -EBADFD; - if (sk->sk_type != SOCK_SEQPACKET) { + if (sk->sk_type != SOCK_SEQPACKET) err = -EINVAL; - goto done; - } - - hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR); - if (!hdev) { - err = -EHOSTUNREACH; - goto done; - } - hci_dev_lock(hdev); + lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); + release_sock(sk); - err = sco_connect(hdev, sk); - hci_dev_unlock(hdev); - hci_dev_put(hdev); + err = sco_connect(sk); if (err) - goto done; + return err; + + lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); -done: release_sock(sk); return err; } @@ -1129,6 +1140,8 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, break; } + release_sock(sk); + /* find total buffer size required to copy codec + caps */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { @@ -1146,15 +1159,13 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, buf_len += sizeof(struct bt_codecs); if (buf_len > len) { hci_dev_put(hdev); - err = -ENOBUFS; - break; + return -ENOBUFS; } ptr = optval; if (put_user(num_codecs, ptr)) { hci_dev_put(hdev); - err = -EFAULT; - break; + return -EFAULT; } ptr += sizeof(num_codecs); @@ -1194,12 +1205,14 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, ptr += len; } - if (!err && put_user(buf_len, optlen)) - err = -EFAULT; - hci_dev_unlock(hdev); hci_dev_put(hdev); + lock_sock(sk); + + if (!err && put_user(buf_len, optlen)) + err = -EFAULT; + break; default: diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6f3d654b3339..f81b24320a36 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -97,8 +97,11 @@ reset: struct xdp_page_head { struct xdp_buff orig_ctx; struct xdp_buff ctx; - struct xdp_frame frm; - u8 data[]; + union { + /* ::data_hard_start starts here */ + DECLARE_FLEX_ARRAY(struct xdp_frame, frame); + DECLARE_FLEX_ARRAY(u8, data); + }; }; struct xdp_test_data { @@ -113,6 +116,10 @@ struct xdp_test_data { u32 frame_cnt; }; +/* tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c:%MAX_PKT_SIZE + * must be updated accordingly this gets changed, otherwise BPF selftests + * will fail. + */ #define TEST_XDP_FRAME_SIZE (PAGE_SIZE - sizeof(struct xdp_page_head)) #define TEST_XDP_MAX_BATCH 256 @@ -132,8 +139,8 @@ static void xdp_test_run_init_page(struct page *page, void *arg) headroom -= meta_len; new_ctx = &head->ctx; - frm = &head->frm; - data = &head->data; + frm = head->frame; + data = head->data; memcpy(data + headroom, orig_ctx->data_meta, frm_len); xdp_init_buff(new_ctx, TEST_XDP_FRAME_SIZE, &xdp->rxq); @@ -223,7 +230,7 @@ static void reset_ctx(struct xdp_page_head *head) head->ctx.data = head->orig_ctx.data; head->ctx.data_meta = head->orig_ctx.data_meta; head->ctx.data_end = head->orig_ctx.data_end; - xdp_update_frame_from_buff(&head->ctx, &head->frm); + xdp_update_frame_from_buff(&head->ctx, head->frame); } static int xdp_recv_frames(struct xdp_frame **frames, int nframes, @@ -285,7 +292,7 @@ static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog, head = phys_to_virt(page_to_phys(page)); reset_ctx(head); ctx = &head->ctx; - frm = &head->frm; + frm = head->frame; xdp->frame_cnt++; act = bpf_prog_run_xdp(prog, ctx); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 638a4d5359db..4bc6761517bb 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -868,12 +868,17 @@ static unsigned int ip_sabotage_in(void *priv, { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge && !nf_bridge->in_prerouting && - !netif_is_l3_master(skb->dev) && - !netif_is_l3_slave(skb->dev)) { - nf_bridge_info_free(skb); - state->okfn(state->net, state->sk, skb); - return NF_STOLEN; + if (nf_bridge) { + if (nf_bridge->sabotage_in_done) + return NF_ACCEPT; + + if (!nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev) && + !netif_is_l3_slave(skb->dev)) { + nf_bridge->sabotage_in_done = 1; + state->okfn(state->net, state->sk, skb); + return NF_STOLEN; + } } return NF_ACCEPT; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index de18e9c1d7a7..ba95c4d74a60 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -148,6 +148,17 @@ br_switchdev_fdb_notify(struct net_bridge *br, if (test_bit(BR_FDB_LOCKED, &fdb->flags)) return; + /* Entries with these flags were created using ndm_state == NUD_REACHABLE, + * ndm_flags == NTF_MASTER( | NTF_STICKY), ext_flags == 0 by something + * equivalent to 'bridge fdb add ... master dynamic (sticky)'. + * Drivers don't know how to deal with these, so don't notify them to + * avoid confusing them. + */ + if (test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags) && + !test_bit(BR_FDB_STATIC, &fdb->flags) && + !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) + return; + br_switchdev_fdb_populate(br, &item, fdb, NULL); switch (type) { diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index ebc202ffdd8d..bf61ea4b8132 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -134,6 +134,9 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, struct usb_device *usbdev; int res; + if (what == NETDEV_UNREGISTER && dev->reg_state >= NETREG_UNREGISTERED) + return 0; + /* Check whether we have a NCM device, and find its VID/PID. */ if (!(dev->dev.parent && dev->dev.parent->driver && strcmp(dev->dev.parent->driver->name, "cdc_ncm") == 0)) diff --git a/net/can/bcm.c b/net/can/bcm.c index 27706f6ace34..a962ec2b8ba5 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -941,6 +941,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); + if (err < 0) + goto free_op; if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) @@ -950,12 +952,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = -EINVAL; } - if (err < 0) { - if (op->frames != &op->sframe) - kfree(op->frames); - kfree(op); - return err; - } + if (err < 0) + goto free_op; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ @@ -1026,6 +1024,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_tx_start_timer(op); return msg_head->nframes * op->cfsiz + MHSIZ; + +free_op: + if (op->frames != &op->sframe) + kfree(op->frames); + kfree(op); + return err; } /* diff --git a/net/can/isotp.c b/net/can/isotp.c index 9bc344851704..5761d4ab839d 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -119,7 +119,8 @@ enum { ISOTP_WAIT_FIRST_FC, ISOTP_WAIT_FC, ISOTP_WAIT_DATA, - ISOTP_SENDING + ISOTP_SENDING, + ISOTP_SHUTDOWN, }; struct tpcon { @@ -880,8 +881,8 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) txtimer); struct sock *sk = &so->sk; - /* don't handle timeouts in IDLE state */ - if (so->tx.state == ISOTP_IDLE) + /* don't handle timeouts in IDLE or SHUTDOWN state */ + if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN) return HRTIMER_NORESTART; /* we did not get any flow control or echo frame in time */ @@ -918,7 +919,6 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); - u32 old_state = so->tx.state; struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; @@ -928,23 +928,24 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) int off; int err; - if (!so->bound) + if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; +wait_free_buffer: /* we do not support multiple buffers - for now */ - if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE || - wq_has_sleeper(&so->wait)) { - if (msg->msg_flags & MSG_DONTWAIT) { - err = -EAGAIN; - goto err_out; - } + if (wq_has_sleeper(&so->wait) && (msg->msg_flags & MSG_DONTWAIT)) + return -EAGAIN; - /* wait for complete transmission of current pdu */ - err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); - if (err) - goto err_out; + /* wait for complete transmission of current pdu */ + err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + if (err) + goto err_event_drop; - so->tx.state = ISOTP_SENDING; + if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { + if (so->tx.state == ISOTP_SHUTDOWN) + return -EADDRNOTAVAIL; + + goto wait_free_buffer; } if (!size || size > MAX_MSG_LENGTH) { @@ -1074,7 +1075,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (wait_tx_done) { /* wait for complete transmission of current pdu */ - wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + if (err) + goto err_event_drop; if (sk->sk_err) return -sk->sk_err; @@ -1082,13 +1085,15 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return size; +err_event_drop: + /* got signal: force tx state machine to be idle */ + so->tx.state = ISOTP_IDLE; + hrtimer_cancel(&so->txfrtimer); + hrtimer_cancel(&so->txtimer); err_out_drop: /* drop this PDU and unlock a potential wait queue */ - old_state = ISOTP_IDLE; -err_out: - so->tx.state = old_state; - if (so->tx.state == ISOTP_IDLE) - wake_up_interruptible(&so->wait); + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); return err; } @@ -1120,7 +1125,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (ret < 0) goto out_err; - sock_recv_timestamp(msg, sk, skb); + sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(ISOTP_MIN_NAMELEN); @@ -1150,10 +1155,12 @@ static int isotp_release(struct socket *sock) net = sock_net(sk); /* wait for complete transmission of current pdu */ - wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 && + cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE) + ; /* force state machines to be idle also when a signal occurred */ - so->tx.state = ISOTP_IDLE; + so->tx.state = ISOTP_SHUTDOWN; so->rx.state = ISOTP_IDLE; spin_lock(&isotp_notifier_lock); @@ -1608,6 +1615,21 @@ static int isotp_init(struct sock *sk) return 0; } +static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wait) +{ + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + + __poll_t mask = datagram_poll(file, sock, wait); + poll_wait(file, &so->wait, wait); + + /* Check for false positives due to TX state */ + if ((mask & EPOLLWRNORM) && (so->tx.state != ISOTP_IDLE)) + mask &= ~(EPOLLOUT | EPOLLWRNORM); + + return mask; +} + static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { @@ -1623,7 +1645,7 @@ static const struct proto_ops isotp_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = isotp_getname, - .poll = datagram_poll, + .poll = isotp_poll, .ioctl = isotp_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fce9b9ebf13f..fe3df23a2595 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -604,7 +604,10 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, /* reserve CAN header */ skb_reserve(skb, offsetof(struct can_frame, data)); - memcpy(skb->cb, re_skcb, sizeof(skb->cb)); + /* skb->cb must be large enough to hold a j1939_sk_buff_cb structure */ + BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*re_skcb)); + + memcpy(skb->cb, re_skcb, sizeof(*re_skcb)); skcb = j1939_skb_to_cb(skb); if (swap_src_dst) j1939_skbcb_swap(skcb); @@ -1124,8 +1127,6 @@ static void __j1939_session_cancel(struct j1939_session *session, if (session->sk) j1939_sk_send_loop_abort(session->sk, session->err); - else - j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); } static void j1939_session_cancel(struct j1939_session *session, @@ -1140,6 +1141,9 @@ static void j1939_session_cancel(struct j1939_session *session, } j1939_session_list_unlock(session->priv); + + if (!session->sk) + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); } static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) @@ -1253,6 +1257,9 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer) __j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); } j1939_session_list_unlock(session->priv); + + if (!session->sk) + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); } j1939_session_put(session); diff --git a/net/core/dev.c b/net/core/dev.c index 253584777101..1488f700bf81 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3199,6 +3199,7 @@ static u16 skb_tx_hash(const struct net_device *dev, } if (skb_rx_queue_recorded(skb)) { + DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; @@ -10846,7 +10847,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, - portid, nlmsg_seq(nlh)); + portid, nlh); /* * Flush the unicast and multicast chains diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 48812ec843f5..3abab70d66dd 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: BSD-3-Clause +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN kernel source */ diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index b16dc7e026bb..74d74fc23167 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: BSD-3-Clause */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN kernel header */ diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a089b704b986..e6a739b1afa9 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -137,6 +137,20 @@ static void queue_process(struct work_struct *work) } } +static int netif_local_xmit_active(struct net_device *dev) +{ + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + return 1; + } + + return 0; +} + static void poll_one_napi(struct napi_struct *napi) { int work; @@ -183,7 +197,10 @@ void netpoll_poll_dev(struct net_device *dev) if (!ni || down_trylock(&ni->dev_lock)) return; - if (!netif_running(dev)) { + /* Some drivers will take the same locks in poll and xmit, + * we can't poll if local CPU is already in xmit. + */ + if (!netif_running(dev) || netif_local_xmit_active(dev)) { up(&ni->dev_lock); return; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5d8eb57867a9..6e44e92ebdf5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3972,16 +3972,23 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq) + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + u32 seq = 0; skb = nlmsg_new(if_nlmsg_size(dev, 0), flags); if (skb == NULL) goto errout; + if (nlmsg_report(nlh)) + seq = nlmsg_seq(nlh); + else + portid = 0; + err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, portid, seq, change, 0, 0, event, new_nsid, new_ifindex, -1, flags); @@ -4017,7 +4024,7 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, return; skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid, - new_ifindex, portid, nlmsg_seq(nlh)); + new_ifindex, portid, nlh); if (skb) rtmsg_ifinfo_send(skb, dev, flags, portid, nlh); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index eb7d33b41e71..4c0879798eb8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -517,18 +517,16 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, #ifdef HAVE_SKB_SMALL_HEAD_CACHE if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && !(flags & KMALLOC_NOT_NORMAL_BITS)) { - - /* skb_small_head_cache has non power of two size, - * likely forcing SLUB to use order-3 pages. - * We deliberately attempt a NOMEMALLOC allocation only. - */ obj = kmem_cache_alloc_node(skb_small_head_cache, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); - if (obj) { - *size = SKB_SMALL_HEAD_CACHE_SIZE; + *size = SKB_SMALL_HEAD_CACHE_SIZE; + if (obj || !(gfp_pfmemalloc_allowed(flags))) goto out; - } + /* Try again but now we are using pfmemalloc reserves */ + ret_pfmemalloc = true; + obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node); + goto out; } #endif *size = obj_size = kmalloc_size_roundup(obj_size); @@ -2082,6 +2080,7 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) } EXPORT_SYMBOL(skb_realloc_headroom); +/* Note: We plan to rework this in linux-6.4 */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { unsigned int saved_end_offset, saved_truesize; @@ -2100,6 +2099,22 @@ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) if (likely(skb_end_offset(skb) == saved_end_offset)) return 0; +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + /* We can not change skb->end if the original or new value + * is SKB_SMALL_HEAD_HEADROOM, as it might break skb_kfree_head(). + */ + if (saved_end_offset == SKB_SMALL_HEAD_HEADROOM || + skb_end_offset(skb) == SKB_SMALL_HEAD_HEADROOM) { + /* We think this path should not be taken. + * Add a temporary trace to warn us just in case. + */ + pr_err_once("__skb_unclone_keeptruesize() skb_end_offset() %u -> %u\n", + saved_end_offset, skb_end_offset(skb)); + WARN_ON_ONCE(1); + return 0; + } +#endif + shinfo = skb_shinfo(skb); /* We are about to change back skb->end, @@ -5584,18 +5599,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* In general, avoid mixing slab allocated and page_pool allocated - * pages within the same SKB. However when @to is not pp_recycle and - * @from is cloned, we can transition frag pages from page_pool to - * reference counted. - * - * On the other hand, don't allow coalescing two pp_recycle SKBs if - * @from is cloned, in case the SKB is using page_pool fragment + /* 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 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 + * !@to->pp_recycle but its tricky (due to potential race with + * the clone disappearing) and rare, so not worth dealing with. */ - if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) + if (to->pp_recycle != from->pp_recycle || + (from->pp_recycle && skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/core/sock.c b/net/core/sock.c index 341c565dbc26..c25888795390 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2818,7 +2818,8 @@ static void sk_enter_memory_pressure(struct sock *sk) static void sk_leave_memory_pressure(struct sock *sk) { if (sk->sk_prot->leave_memory_pressure) { - sk->sk_prot->leave_memory_pressure(sk); + INDIRECT_CALL_INET_1(sk->sk_prot->leave_memory_pressure, + tcp_leave_memory_pressure, sk); } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 74842b453407..782273bb93c2 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -177,7 +177,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, if (orig_sock_table) { static_branch_dec(&rps_needed); static_branch_dec(&rfs_needed); - kvfree_rcu(orig_sock_table); + kvfree_rcu_mightsleep(orig_sock_table); } } } @@ -215,7 +215,7 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, lockdep_is_held(&flow_limit_update_mutex)); if (cur && !cpumask_test_cpu(i, mask)) { RCU_INIT_POINTER(sd->flow_limit, NULL); - kfree_rcu(cur); + kfree_rcu_mightsleep(cur); } else if (!cur && cpumask_test_cpu(i, mask)) { cur = kzalloc_node(len, GFP_KERNEL, cpu_to_node(i)); diff --git a/net/core/xdp.c b/net/core/xdp.c index 8c92fc553317..fb85aca81961 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -720,7 +720,10 @@ __diag_ignore_all("-Wmissing-prototypes", * @ctx: XDP context pointer. * @timestamp: Return value pointer. * - * Returns 0 on success or ``-errno`` on error. + * Return: + * * Returns 0 on success or ``-errno`` on error. + * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc + * * ``-ENODATA`` : means no RX-timestamp available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { @@ -731,10 +734,21 @@ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *tim * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. + * @rss_type: Return value pointer for RSS type. * - * Returns 0 on success or ``-errno`` on error. + * The RSS hash type (@rss_type) specifies what portion of packet headers NIC + * hardware used when calculating RSS hash value. The RSS type can be decoded + * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits + * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* + * ``XDP_RSS_TYPE_L*``. + * + * Return: + * * Returns 0 on success or ``-errno`` on error. + * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc + * * ``-ENODATA`` : means no RX-hash available for this frame */ -__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) +__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } @@ -774,20 +788,34 @@ static int __init xdp_metadata_init(void) } late_initcall(xdp_metadata_init); +void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) +{ + val &= NETDEV_XDP_ACT_MASK; + if (dev->xdp_features == val) + return; + + dev->xdp_features = val; + + if (dev->reg_state == NETREG_REGISTERED) + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); +} +EXPORT_SYMBOL_GPL(xdp_set_features_flag); + void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { - dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; - if (support_sg) - dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG; + xdp_features_t val = (dev->xdp_features | NETDEV_XDP_ACT_NDO_XMIT); - call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); + if (support_sg) + val |= NETDEV_XDP_ACT_NDO_XMIT_SG; + xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target); void xdp_features_clear_redirect_target(struct net_device *dev) { - dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT | - NETDEV_XDP_ACT_NDO_XMIT_SG); - call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); + xdp_features_t val = dev->xdp_features; + + val &= ~(NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG); + xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6957971c2db2..165bb2cb8431 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -57,6 +57,12 @@ struct dsa_standalone_event_work { u16 vid; }; +struct dsa_host_vlan_rx_filtering_ctx { + struct net_device *dev; + const unsigned char *addr; + enum dsa_standalone_event event; +}; + static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) { return ds->ops->port_fdb_add && ds->ops->port_fdb_del && @@ -155,18 +161,37 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev, return 0; } +static int dsa_slave_host_vlan_rx_filtering(struct net_device *vdev, int vid, + void *arg) +{ + struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; + + return dsa_slave_schedule_standalone_work(ctx->dev, ctx->event, + ctx->addr, vid); +} + static int dsa_slave_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 dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_UC_ADD, + }; + int err; dev_uc_add(master, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - return dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, addr, 0); + err = dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, addr, 0); + if (err) + return err; + + return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); } static int dsa_slave_unsync_uc(struct net_device *dev, @@ -174,13 +199,23 @@ static int dsa_slave_unsync_uc(struct net_device *dev, { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_UC_DEL, + }; + int err; dev_uc_del(master, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - return dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, addr, 0); + err = dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, addr, 0); + if (err) + return err; + + return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); } static int dsa_slave_sync_mc(struct net_device *dev, @@ -188,13 +223,23 @@ static int dsa_slave_sync_mc(struct net_device *dev, { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_MC_ADD, + }; + int err; dev_mc_add(master, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - return dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, addr, 0); + err = dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, addr, 0); + if (err) + return err; + + return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); } static int dsa_slave_unsync_mc(struct net_device *dev, @@ -202,13 +247,23 @@ static int dsa_slave_unsync_mc(struct net_device *dev, { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_MC_DEL, + }; + int err; dev_mc_del(master, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - return dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, addr, 0); + err = dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, addr, 0); + if (err) + return err; + + return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); } void dsa_slave_sync_ha(struct net_device *dev) @@ -1702,6 +1757,8 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, .flags = 0, }; struct netlink_ext_ack extack = {0}; + struct dsa_switch *ds = dp->ds; + struct netdev_hw_addr *ha; int ret; /* User port... */ @@ -1721,6 +1778,30 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, return ret; } + if (!dsa_switch_supports_uc_filtering(ds) && + !dsa_switch_supports_mc_filtering(ds)) + return 0; + + netif_addr_lock_bh(dev); + + 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); + } + } + + 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); + } + } + + netif_addr_unlock_bh(dev); + + dsa_flush_workqueue(); + return 0; } @@ -1733,13 +1814,43 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; + struct dsa_switch *ds = dp->ds; + struct netdev_hw_addr *ha; int err; err = dsa_port_vlan_del(dp, &vlan); if (err) return err; - return dsa_port_host_vlan_del(dp, &vlan); + err = dsa_port_host_vlan_del(dp, &vlan); + if (err) + return err; + + if (!dsa_switch_supports_uc_filtering(ds) && + !dsa_switch_supports_mc_filtering(ds)) + return 0; + + netif_addr_lock_bh(dev); + + 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); + } + } + + 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); + } + } + + netif_addr_unlock_bh(dev); + + dsa_flush_workqueue(); + + return 0; } static int dsa_slave_restore_vlan(struct net_device *vdev, int vid, void *arg) @@ -1933,6 +2044,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) int new_master_mtu; int old_master_mtu; int mtu_limit; + int overhead; int cpu_mtu; int err; @@ -1961,9 +2073,10 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) largest_mtu = slave_mtu; } - mtu_limit = min_t(int, master->max_mtu, dev->max_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 + dsa_tag_protocol_overhead(cpu_dp->tag_ops); + new_master_mtu = largest_mtu + overhead; if (new_master_mtu > mtu_limit) return -ERANGE; @@ -1998,8 +2111,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) out_port_failed: if (new_master_mtu != old_master_mtu) - dsa_port_mtu_change(cpu_dp, old_master_mtu - - dsa_tag_protocol_overhead(cpu_dp->tag_ops)); + dsa_port_mtu_change(cpu_dp, old_master_mtu - overhead); out_cpu_failed: if (new_master_mtu != old_master_mtu) dev_set_mtu(master, old_master_mtu); diff --git a/net/dsa/tag.c b/net/dsa/tag.c index b2fba1a003ce..5105a5ff58fa 100644 --- a/net/dsa/tag.c +++ b/net/dsa/tag.c @@ -114,7 +114,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, skb = nskb; } - dev_sw_netstats_rx_add(skb->dev, skb->len); + dev_sw_netstats_rx_add(skb->dev, skb->len + ETH_HLEN); if (dsa_skb_defer_rx_timestamp(p, skb)) return 0; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 10239daa5745..cacdafb41200 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -7,6 +7,7 @@ #include <linux/dsa/brcm.h> #include <linux/etherdevice.h> +#include <linux/if_vlan.h> #include <linux/list.h> #include <linux/slab.h> @@ -252,6 +253,7 @@ static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, struct net_device *dev) { + int len = BRCM_LEG_TAG_LEN; int source_port; u8 *brcm_tag; @@ -266,12 +268,16 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, if (!skb->dev) return NULL; + /* VLAN tag is added by BCM63xx internal switch */ + if (netdev_uses_dsa(skb->dev)) + len += VLAN_HLEN; + /* Remove Broadcom tag and update checksum */ - skb_pull_rcsum(skb, BRCM_LEG_TAG_LEN); + skb_pull_rcsum(skb, len); dsa_default_offload_fwd_mark(skb); - dsa_strip_etype_header(skb, BRCM_LEG_TAG_LEN); + dsa_strip_etype_header(skb, len); return skb; } diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index fab66c169b9f..20165e07ef90 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -270,11 +270,12 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, "lanes configuration not supported by device"); return -EOPNOTSUPP; } - } else if (!lsettings->autoneg) { - /* If autoneg is off and lanes parameter is not passed from user, - * set the lanes parameter to 0. + } else if (!lsettings->autoneg && ksettings->lanes) { + /* If autoneg is off and lanes parameter is not passed from user but + * it was defined previously then set the lanes parameter to 0. */ ksettings->lanes = 0; + *mod = true; } ret = ethnl_update_bitset(ksettings->link_modes.advertising, diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 00db74d96583..b77f1189d19d 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -415,7 +415,7 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst) { - if (net_ratelimit()) + if (port->hsr->prot_version != PRP_V1 && net_ratelimit()) netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; } diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 2215f576ee37..832e3c50816c 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -1412,7 +1412,7 @@ static int nl802154_trigger_scan(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; } - if (!nla_get_u8(info->attrs[NL802154_ATTR_SCAN_TYPE])) { + if (!info->attrs[NL802154_ATTR_SCAN_TYPE]) { NL_SET_ERR_MSG(info->extack, "Malformed request, missing scan type"); return -EINVAL; } @@ -2488,8 +2488,7 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb, if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; - if (!info->attrs[NL802154_ATTR_SEC_LEVEL] || - llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], + if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) return -EINVAL; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b5736ef16ed2..390f4be7f7be 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -576,6 +576,9 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, cfg->fc_scope = RT_SCOPE_UNIVERSE; } + if (!cfg->fc_table) + cfg->fc_table = RT_TABLE_MAIN; + if (cmd == SIOCDELRT) return 0; diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 6c3820f41dd5..6c37c4f98cca 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: BSD-3-Clause +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel source */ diff --git a/net/ipv4/fou_nl.h b/net/ipv4/fou_nl.h index b7a68121ce6f..dbd0780a5d34 100644 --- a/net/ipv4/fou_nl.h +++ b/net/ipv4/fou_nl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: BSD-3-Clause */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel header */ diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 8cebb476b3ab..b8607763d113 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -749,6 +749,11 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, room = 576; room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); + /* Guard against tiny mtu. We need to include at least one + * IP network header for this message to make any sense. + */ + if (room <= (int)sizeof(struct iphdr)) + goto ende; icmp_param.data_len = skb_in->len - icmp_param.offset; if (icmp_param.data_len > room) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e41fdc38ce19..6edae3886885 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -828,8 +828,14 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const #if IS_ENABLED(CONFIG_IPV6) struct in6_addr addr_any = {}; - if (sk->sk_family != tb->family) + if (sk->sk_family != tb->family) { + if (sk->sk_family == AF_INET) + return net_eq(ib2_net(tb), net) && tb->port == port && + tb->l3mdev == l3mdev && + ipv6_addr_equal(&tb->v6_rcv_saddr, &addr_any); + return false; + } if (sk->sk_family == AF_INET6) return net_eq(ib2_net(tb), net) && tb->port == port && diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ffff46cdcb58..e55a20264960 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -552,7 +552,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) truncate = true; } - nhoff = skb_network_header(skb) - skb_mac_header(skb); + nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; @@ -561,7 +561,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) int thoff; if (skb_transport_header_was_set(skb)) - thoff = skb_transport_header(skb) - skb_mac_header(skb); + thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index de90b09dfe78..2541083d49ad 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -614,10 +614,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > dev->needed_headroom) - dev->needed_headroom = headroom; + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); goto tx_dropped; } @@ -800,10 +800,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index b22b2c745c76..69e331799604 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -38,7 +38,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, hp->source, lport ? lport : hp->dest, skb->dev, NF_TPROXY_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule_put(inet_twsk(sk)); + nf_tproxy_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 409ec2a1f95b..5178a3f3cb53 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -1089,13 +1089,13 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) } void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) - __acquires(RCU) + __acquires(ping_table.lock) { struct ping_iter_state *state = seq->private; state->bucket = 0; state->family = family; - rcu_read_lock(); + spin_lock(&ping_table.lock); return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } @@ -1121,9 +1121,9 @@ void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(ping_seq_next); void ping_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) + __releases(ping_table.lock) { - rcu_read_unlock(); + spin_unlock(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_seq_stop); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 94df935ee0c5..8088a5011e7d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -91,12 +91,12 @@ EXPORT_SYMBOL_GPL(raw_v4_hashinfo); int raw_hash_sk(struct sock *sk) { struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; - struct hlist_nulls_head *hlist; + struct hlist_head *hlist; hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)]; spin_lock(&h->lock); - __sk_nulls_add_node_rcu(sk, hlist); + sk_add_node_rcu(sk, hlist); sock_set_flag(sk, SOCK_RCU_FREE); spin_unlock(&h->lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -110,7 +110,7 @@ void raw_unhash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; spin_lock(&h->lock); - if (__sk_nulls_del_node_init_rcu(sk)) + if (sk_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock(&h->lock); } @@ -163,16 +163,15 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) static int raw_v4_input(struct net *net, struct sk_buff *skb, const struct iphdr *iph, int hash) { - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int sdif = inet_sdif(skb); + struct hlist_head *hlist; int dif = inet_iif(skb); int delivered = 0; struct sock *sk; hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { if (!raw_v4_match(net, sk, iph->protocol, iph->saddr, iph->daddr, dif, sdif)) continue; @@ -264,10 +263,9 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); + struct hlist_head *hlist; const struct iphdr *iph; struct sock *sk; int hash; @@ -276,7 +274,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { iph = (const struct iphdr *)skb->data; if (!raw_v4_match(net, sk, iph->protocol, iph->daddr, iph->saddr, dif, sdif)) @@ -950,14 +948,13 @@ static struct sock *raw_get_first(struct seq_file *seq, int bucket) { struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; for (state->bucket = bucket; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { hlist = &h->ht[state->bucket]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each(sk, hlist) { if (sock_net(sk) == seq_file_net(seq)) return sk; } @@ -970,7 +967,7 @@ static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) struct raw_iter_state *state = raw_seq_private(seq); do { - sk = sk_nulls_next(sk); + sk = sk_next(sk); } while (sk && sock_net(sk) != seq_file_net(seq)); if (!sk) @@ -989,9 +986,12 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) } void *raw_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) + __acquires(&h->lock) { - rcu_read_lock(); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); + + spin_lock(&h->lock); + return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } EXPORT_SYMBOL_GPL(raw_seq_start); @@ -1010,9 +1010,11 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) + __releases(&h->lock) { - rcu_read_unlock(); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); + + spin_unlock(&h->lock); } EXPORT_SYMBOL_GPL(raw_seq_stop); diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index 999321834b94..da3591a66a16 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -57,8 +57,7 @@ static bool raw_lookup(struct net *net, struct sock *sk, static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r) { struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; int slot; @@ -68,7 +67,7 @@ static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 rcu_read_lock(); for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) { hlist = &hashinfo->ht[slot]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { if (raw_lookup(net, sk, r)) { /* * Grab it and keep until we fill @@ -142,9 +141,8 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); struct net *net = sock_net(skb->sk); struct inet_diag_dump_data *cb_data; - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int num, s_num, slot, s_slot; + struct hlist_head *hlist; struct sock *sk = NULL; struct nlattr *bc; @@ -161,7 +159,7 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, num = 0; hlist = &hashinfo->ht[slot]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d0cc4ef2b85..40fe70fc2015 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -25,6 +25,7 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; +static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; @@ -1198,6 +1199,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale", diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index cf26d65ca389..ebf917511937 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -186,6 +186,9 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); + if (!len) + return 0; + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, flags, addr_len); @@ -244,6 +247,9 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); + if (!len) + return 0; + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, flags, addr_len); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ea370afa70ed..b9d55277cb85 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2780,7 +2780,7 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { while (iter->cur_sk < iter->end_sk) - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, @@ -2941,7 +2941,7 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) * st->bucket. See tcp_seek_last_pos(). */ st->offset++; - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } if (iter->cur_sk < iter->end_sk) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 71d01cf3c13e..ba839e441450 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3605,7 +3605,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write(th, NULL, &opts); th->doff = (tcp_header_size >> 2); - __TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index e5dc91d0e079..0735d820e413 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -68,6 +68,9 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); + if (!len) + return 0; + psock = sk_psock_get(sk); if (unlikely(!psock)) return sk_udp_recvmsg(sk, msg, len, flags, addr_len); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 47447f0241df..bee45dfeb187 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -477,6 +477,7 @@ int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) rcu_read_lock(); + ret = -ESRCH; ila = ila_lookup_by_params(&xp, ilan); if (ila) { ret = ila_dump_info(ila, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 89f5f0f3f5d6..a4ecfc9d2593 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -959,7 +959,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } - nhoff = skb_network_header(skb) - skb_mac_header(skb); + nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; @@ -968,7 +968,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, int thoff; if (skb_transport_header_was_set(skb)) - thoff = skb_transport_header(skb) - skb_mac_header(skb); + thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c314fdde0097..95a55c6630ad 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1965,8 +1965,13 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + u8 icmp6_type; - ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + icmp6_type = fl6->fl6_icmp_type; + else + icmp6_type = icmp6_hdr(skb)->icmp6_type; + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 47b6607a1370..5e80e517f071 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1240,8 +1240,8 @@ route_lookup: */ max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c index 929502e51203..52f828bb5a83 100644 --- a/net/ipv6/netfilter/nf_tproxy_ipv6.c +++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c @@ -63,7 +63,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, lport ? lport : hp->dest, skb->dev, NF_TPROXY_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule_put(inet_twsk(sk)); + nf_tproxy_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index bac9ba747bde..a327aa481df4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -141,10 +141,9 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister); static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; const struct in6_addr *saddr; const struct in6_addr *daddr; + struct hlist_head *hlist; struct sock *sk; bool delivered = false; __u8 hash; @@ -155,7 +154,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { int filtered; if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, @@ -333,15 +332,14 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; int hash; hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c index 488aec9e1a74..d1876f192225 100644 --- a/net/ipv6/rpl.c +++ b/net/ipv6/rpl.c @@ -32,7 +32,8 @@ static void *ipv6_rpl_segdata_pos(const struct ipv6_rpl_sr_hdr *hdr, int i) size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre) { - return (n * IPV6_PFXTAIL_LEN(cmpri)) + IPV6_PFXTAIL_LEN(cmpre); + return sizeof(struct ipv6_rpl_sr_hdr) + (n * IPV6_PFXTAIL_LEN(cmpri)) + + IPV6_PFXTAIL_LEN(cmpre); } void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9fb2f33ee3a7..a675acfb901d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1395,9 +1395,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(sk, msg, len); + err = ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } } diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index eb0295d90039..fc3fddeb6f36 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -83,7 +83,7 @@ struct iucv_irq_data { u16 ippathid; u8 ipflags1; u8 iptype; - u32 res2[8]; + u32 res2[9]; }; struct iucv_irq_list { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 4db5a554bdbd..41a74fc84ca1 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -677,8 +677,8 @@ MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); -/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like - * enums +/* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, + * because __stringify doesn't like enums */ -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); -MODULE_ALIAS_NET_PF_PROTO(PF_INET, IPPROTO_L2TP); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 115, 2); +MODULE_ALIAS_NET_PF_PROTO(PF_INET, 115); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 2478aa60145f..5137ea1861ce 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -806,8 +806,8 @@ MODULE_AUTHOR("Chris Elston <celston@katalix.com>"); MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6"); MODULE_VERSION("1.0"); -/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like - * enums +/* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, + * because __stringify doesn't like enums */ -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP); -MODULE_ALIAS_NET_PF_PROTO(PF_INET6, IPPROTO_L2TP); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 115, 2); +MODULE_ALIAS_NET_PF_PROTO(PF_INET6, 115); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 8eb342300868..d3d861911ed6 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2611,6 +2611,17 @@ static int ieee80211_change_bss(struct wiphy *wiphy, if (!sband) return -EINVAL; + if (params->basic_rates) { + if (!ieee80211_parse_bitrates(link->conf->chandef.width, + wiphy->bands[sband->band], + params->basic_rates, + params->basic_rates_len, + &link->conf->basic_rates)) + return -EINVAL; + changed |= BSS_CHANGED_BASIC_RATES; + ieee80211_check_rate_mask(link); + } + if (params->use_cts_prot >= 0) { link->conf->use_cts_prot = params->use_cts_prot; changed |= BSS_CHANGED_ERP_CTS_PROT; @@ -2632,16 +2643,6 @@ static int ieee80211_change_bss(struct wiphy *wiphy, changed |= BSS_CHANGED_ERP_SLOT; } - if (params->basic_rates) { - ieee80211_parse_bitrates(link->conf->chandef.width, - wiphy->bands[sband->band], - params->basic_rates, - params->basic_rates_len, - &link->conf->basic_rates); - changed |= BSS_CHANGED_BASIC_RATES; - ieee80211_check_rate_mask(link); - } - if (params->ap_isolate >= 0) { if (params->ap_isolate) sdata->flags |= IEEE80211_SDATA_DONT_BRIDGE_PACKETS; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ecc232eb1ee8..e082582e0aa2 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1284,6 +1284,9 @@ struct ieee80211_local { struct list_head active_txqs[IEEE80211_NUM_ACS]; u16 schedule_round[IEEE80211_NUM_ACS]; + /* serializes ieee80211_handle_wake_tx_queue */ + spinlock_t handle_wake_tx_queue_lock; + u16 airtime_flags; u32 aql_txq_limit_low[IEEE80211_NUM_ACS]; u32 aql_txq_limit_high[IEEE80211_NUM_ACS]; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 846528850612..ddf2b7811c55 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -802,6 +802,8 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, local->aql_threshold = IEEE80211_AQL_THRESHOLD; atomic_set(&local->aql_total_pending_airtime, 0); + spin_lock_init(&local->handle_wake_tx_queue_lock); + INIT_LIST_HEAD(&local->chanctx_list); mutex_init(&local->chanctx_mtx); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index f7fdfe710951..af57616d2f1d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2765,29 +2765,10 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta mesh_rmc_check(sdata, eth->h_source, mesh_hdr)) return RX_DROP_MONITOR; - /* Frame has reached destination. Don't forward */ - if (ether_addr_equal(sdata->vif.addr, eth->h_dest)) - goto rx_accept; - - if (!ifmsh->mshcfg.dot11MeshForwarding) { - if (is_multicast_ether_addr(eth->h_dest)) - goto rx_accept; - - return RX_DROP_MONITOR; - } - /* forward packet */ if (sdata->crypto_tx_tailroom_needed_cnt) tailroom = IEEE80211_ENCRYPT_TAILROOM; - if (!--mesh_hdr->ttl) { - if (multicast) - goto rx_accept; - - IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); - return RX_DROP_MONITOR; - } - if (mesh_hdr->flags & MESH_FLAGS_AE) { struct mesh_path *mppath; char *proxied_addr; @@ -2814,6 +2795,25 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta rcu_read_unlock(); } + /* Frame has reached destination. Don't forward */ + if (ether_addr_equal(sdata->vif.addr, eth->h_dest)) + goto rx_accept; + + if (!--mesh_hdr->ttl) { + if (multicast) + goto rx_accept; + + IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); + return RX_DROP_MONITOR; + } + + if (!ifmsh->mshcfg.dot11MeshForwarding) { + if (is_multicast_ether_addr(eth->h_dest)) + goto rx_accept; + + return RX_DROP_MONITOR; + } + skb_set_queue_mapping(skb, ieee802_1d_to_ac[skb->priority]); ieee80211_fill_mesh_addresses(&hdr, &hdr.frame_control, @@ -2833,6 +2833,9 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta if (skb_cow_head(fwd_skb, hdrlen - sizeof(struct ethhdr))) return RX_DROP_UNUSABLE; + + if (skb_linearize(fwd_skb)) + return RX_DROP_UNUSABLE; } fwd_hdr = skb_push(fwd_skb, hdrlen - sizeof(struct ethhdr)); @@ -2847,7 +2850,7 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta hdrlen += ETH_ALEN; else fwd_skb->protocol = htons(fwd_skb->len - hdrlen); - skb_set_network_header(fwd_skb, hdrlen); + skb_set_network_header(fwd_skb, hdrlen + 2); info = IEEE80211_SKB_CB(fwd_skb); memset(info, 0, sizeof(*info)); @@ -2896,7 +2899,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; __le16 fc = hdr->frame_control; struct sk_buff_head frame_list; - static ieee80211_rx_result res; + ieee80211_rx_result res; struct ethhdr ethhdr; const u8 *check_da = ethhdr.h_dest, *check_sa = ethhdr.h_source; @@ -2930,7 +2933,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) data_offset, true)) return RX_DROP_UNUSABLE; - if (rx->sta && rx->sta->amsdu_mesh_control < 0) { + if (rx->sta->amsdu_mesh_control < 0) { bool valid_std = ieee80211_is_valid_amsdu(skb, true); bool valid_nonstd = ieee80211_is_valid_amsdu(skb, false); @@ -3006,7 +3009,7 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) } } - if (is_multicast_ether_addr(hdr->addr1)) + if (is_multicast_ether_addr(hdr->addr1) || !rx->sta) return RX_DROP_UNUSABLE; if (rx->key) { @@ -3037,7 +3040,7 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) struct net_device *dev = sdata->dev; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; __le16 fc = hdr->frame_control; - static ieee80211_rx_result res; + ieee80211_rx_result res; bool port_control; int err; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 7d68dbc872d7..941bda9141fa 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1264,7 +1264,8 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta) list_del_rcu(&sta->list); sta->removed = true; - drv_sta_pre_rcu_remove(local, sta->sdata, sta); + if (sta->uploaded) + drv_sta_pre_rcu_remove(local, sta->sdata, sta); if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && rcu_access_pointer(sdata->u.vlan.sta) == sta) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1a28fe5cb614..8c397650b96f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -314,6 +314,8 @@ void ieee80211_handle_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif); struct ieee80211_txq *queue; + spin_lock(&local->handle_wake_tx_queue_lock); + /* Use ieee80211_next_txq() for airtime fairness accounting */ ieee80211_txq_schedule_start(hw, txq->ac); while ((queue = ieee80211_next_txq(hw, txq->ac))) { @@ -321,6 +323,7 @@ void ieee80211_handle_wake_tx_queue(struct ieee80211_hw *hw, ieee80211_return_txq(hw, queue, false); } ieee80211_txq_schedule_end(hw, txq->ac); + spin_unlock(&local->handle_wake_tx_queue_lock); } EXPORT_SYMBOL(ieee80211_handle_wake_tx_queue); @@ -4903,7 +4906,7 @@ u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) &eht_cap->eht_cap_elem, is_ap); return 2 + 1 + - sizeof(he_cap->he_cap_elem) + n + + sizeof(eht_cap->eht_cap_elem) + n + ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], eht_cap->eht_cap_elem.phy_cap_info); return 0; diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index a12c63638680..1601be576414 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -147,6 +147,7 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct sk_buff *skb) { + const struct ethhdr *eth = (void *)skb->data; struct mac80211_qos_map *qos_map; bool qos; @@ -154,8 +155,9 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, skb_get_hash(skb); /* all mesh/ocb stations are required to support WME */ - if (sta && (sdata->vif.type == NL80211_IFTYPE_MESH_POINT || - sdata->vif.type == NL80211_IFTYPE_OCB)) + if ((sdata->vif.type == NL80211_IFTYPE_MESH_POINT && + !is_multicast_ether_addr(eth->h_dest)) || + (sdata->vif.type == NL80211_IFTYPE_OCB && sta)) qos = true; else if (sta) qos = sta->sta.wme; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 9b0933a185eb..5c191bedd72c 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -52,7 +52,7 @@ static int mac802154_scan_cleanup_locked(struct ieee802154_local *local, request = rcu_replace_pointer(local->scan_req, NULL, 1); if (!request) return 0; - kfree_rcu(request); + kvfree_rcu_mightsleep(request); /* Advertize first, while we know the devices cannot be removed */ if (aborted) @@ -403,7 +403,7 @@ int mac802154_stop_beacons_locked(struct ieee802154_local *local, request = rcu_replace_pointer(local->beacon_req, NULL, 1); if (!request) return 0; - kfree_rcu(request); + kvfree_rcu_mightsleep(request); nl802154_beaconing_done(wpan_dev); diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index d237d142171c..bceaab8dd8e4 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -9,11 +9,18 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req) { - struct sock *ssk = subflow->tcp_sock; - struct sock *sk = subflow->conn; + struct sock *sk, *ssk; struct sk_buff *skb; struct tcp_sock *tp; + /* on early fallback the subflow context is deleted by + * subflow_syn_recv_sock() + */ + if (!subflow) + return; + + ssk = subflow->tcp_sock; + sk = subflow->conn; tp = tcp_sk(ssk); subflow->is_mptfo = 1; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b30cea2fbf3f..355f798d575a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1192,9 +1192,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) */ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { if (mp_opt.data_fin && mp_opt.data_len == 1 && - mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) && - schedule_work(&msk->work)) - sock_hold(subflow->conn); + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64)) + mptcp_schedule_work((struct sock *)msk); return true; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 56628b52d100..5c8dea49626c 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -997,9 +997,13 @@ out: return ret; } +static struct lock_class_key mptcp_slock_keys[2]; +static struct lock_class_key mptcp_keys[2]; + static int mptcp_pm_nl_create_listen_socket(struct sock *sk, struct mptcp_pm_addr_entry *entry) { + bool is_ipv6 = sk->sk_family == AF_INET6; int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; struct socket *ssock; @@ -1016,6 +1020,18 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (!newsk) return -EINVAL; + /* The subflow socket lock is acquired in a nested to the msk one + * in several places, even by the TCP stack, and this msk is a kernel + * socket: lockdep complains. Instead of propagating the _nested + * modifiers in several places, re-init the lock class for the msk + * socket to an mptcp specific one. + */ + sock_lock_init_class_and_name(newsk, + is_ipv6 ? "mlock-AF_INET6" : "mlock-AF_INET", + &mptcp_slock_keys[is_ipv6], + is_ipv6 ? "msk_lock-AF_INET6" : "msk_lock-AF_INET", + &mptcp_keys[is_ipv6]); + lock_sock(newsk); ssock = __mptcp_nmpc_socket(mptcp_sk(newsk)); release_sock(newsk); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3ad9c46202fc..b998e9df53ce 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -825,7 +825,6 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) if (sk->sk_socket && !ssk->sk_socket) mptcp_sock_graft(ssk, sk->sk_socket); - mptcp_propagate_sndbuf((struct sock *)msk, ssk); mptcp_sockopt_sync_locked(msk, ssk); return true; } @@ -2316,7 +2315,26 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, unsigned int flags) { struct mptcp_sock *msk = mptcp_sk(sk); - bool need_push, dispose_it; + bool dispose_it, need_push = false; + + /* If the first subflow moved to a close state before accept, e.g. due + * to an incoming reset, mptcp either: + * - if either the subflow or the msk are dead, destroy the context + * (the subflow socket is deleted by inet_child_forget) and the msk + * - otherwise do nothing at the moment and take action at accept and/or + * listener shutdown - user-space must be able to accept() the closed + * socket. + */ + if (msk->in_accept_queue && msk->first == ssk) { + if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD)) + return; + + /* ensure later check in mptcp_worker() will dispose the msk */ + sock_set_flag(sk, SOCK_DEAD); + lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + mptcp_subflow_drop_ctx(ssk); + goto out_release; + } dispose_it = !msk->subflow || ssk != msk->subflow->sk; if (dispose_it) @@ -2343,7 +2361,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out; } - sock_orphan(ssk); subflow->disposable = 1; /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops @@ -2351,6 +2368,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, * reference owned by msk; */ if (!inet_csk(ssk)->icsk_ulp_ops) { + WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD)); kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ @@ -2360,11 +2378,14 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); } + __tcp_close(ssk, 0); /* close acquired an extra ref */ __sock_put(ssk); } + +out_release: release_sock(ssk); sock_put(ssk); @@ -2399,9 +2420,10 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) return 0; } -static void __mptcp_close_subflow(struct mptcp_sock *msk) +static void __mptcp_close_subflow(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; + struct mptcp_sock *msk = mptcp_sk(sk); might_sleep(); @@ -2415,16 +2437,17 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk) if (!skb_queue_empty_lockless(&ssk->sk_receive_queue)) continue; - mptcp_close_ssk((struct sock *)msk, ssk, subflow); + mptcp_close_ssk(sk, ssk, subflow); } + } -static bool mptcp_check_close_timeout(const struct sock *sk) +static bool mptcp_should_close(const struct sock *sk) { s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp; struct mptcp_subflow_context *subflow; - if (delta >= TCP_TIMEWAIT_LEN) + if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue) return true; /* if all subflows are in closed status don't bother with additional @@ -2609,7 +2632,7 @@ static void mptcp_worker(struct work_struct *work) lock_sock(sk); state = sk->sk_state; - if (unlikely(state == TCP_CLOSE)) + if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; mptcp_check_data_fin_ack(sk); @@ -2624,12 +2647,15 @@ static void mptcp_worker(struct work_struct *work) __mptcp_check_send_data_fin(sk); mptcp_check_data_fin(sk); + if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + __mptcp_close_subflow(sk); + /* There is no point in keeping around an orphaned sk timedout or * closed, but we need the msk around to reply to incoming DATA_FIN, * even if it is orphaned and in FIN_WAIT2 state */ if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_check_close_timeout(sk)) { + if (mptcp_should_close(sk)) { inet_sk_state_store(sk, TCP_CLOSE); mptcp_do_fastclose(sk); } @@ -2639,9 +2665,6 @@ static void mptcp_worker(struct work_struct *work) } } - if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) - __mptcp_close_subflow(msk); - if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) __mptcp_retrans(sk); @@ -2878,6 +2901,14 @@ static void __mptcp_destroy_sock(struct sock *sk) sock_put(sk); } +void __mptcp_unaccepted_force_close(struct sock *sk) +{ + sock_set_flag(sk, SOCK_DEAD); + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_do_fastclose(sk); + __mptcp_destroy_sock(sk); +} + static __poll_t mptcp_check_readable(struct mptcp_sock *msk) { /* Concurrent splices from sk_receive_queue into receive_queue will @@ -3079,6 +3110,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; msk->subflow = NULL; + msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(msk->csum_enabled, true); @@ -3096,8 +3128,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, security_inet_csk_clone(nsk, req); bh_unlock_sock(nsk); - /* keep a single reference */ - __sock_put(nsk); + /* note: the newly allocated socket refcount is 2 now */ return nsk; } @@ -3153,8 +3184,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, goto out; } - /* acquire the 2nd reference for the owning socket */ - sock_hold(new_mptcp_sock); newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); } else { @@ -3705,25 +3734,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct sock *newsk = newsock->sk; set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); + msk->in_accept_queue = 0; lock_sock(newsk); - /* PM/worker can now acquire the first subflow socket - * lock without racing with listener queue cleanup, - * we can notify it, if needed. - * - * Even if remote has reset the initial subflow by now - * the refcnt is still at least one. - */ - subflow = mptcp_subflow_ctx(msk->first); - list_add(&subflow->node, &msk->conn_list); - sock_hold(msk->first); - if (mptcp_is_fully_established(newsk)) - mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL); - - mptcp_rcv_space_init(msk, msk->first); - mptcp_propagate_sndbuf(newsk, msk->first); - /* set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack. */ @@ -3733,6 +3747,18 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk->sk_socket) mptcp_sock_graft(ssk, newsock); } + + /* Do late cleanup for the first subflow as necessary. Also + * deal with bad peers not doing a complete shutdown. + */ + if (msk->first && + unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { + __mptcp_close_ssk(newsk, msk->first, + mptcp_subflow_ctx(msk->first), 0); + if (unlikely(list_empty(&msk->conn_list))) + inet_sk_state_store(newsk, TCP_CLOSE); + } + release_sock(newsk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 61fd8eabfca2..d6469b6ab38e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -295,7 +295,8 @@ struct mptcp_sock { u8 recvmsg_inq:1, cork:1, nodelay:1, - fastopening:1; + fastopening:1, + in_accept_queue:1; int connect_flags; struct work_struct work; struct sk_buff *ooo_last_skb; @@ -633,6 +634,7 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); bool __mptcp_close(struct sock *sk, long timeout); void mptcp_cancel_work(struct sock *sk); +void __mptcp_unaccepted_force_close(struct sock *sk); void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk); bool mptcp_addresses_equal(const struct mptcp_addr_info *a, @@ -666,6 +668,8 @@ void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow); bool mptcp_subflow_active(struct mptcp_subflow_context *subflow); +void mptcp_subflow_drop_ctx(struct sock *ssk); + static inline void mptcp_subflow_tcp_fallback(struct sock *sk, struct mptcp_subflow_context *ctx) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 4ae1a7304cf0..281c1cc8dc8d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -397,15 +397,19 @@ void mptcp_subflow_reset(struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; + /* mptcp_mp_fail_no_response() can reach here on an already closed + * socket + */ + if (ssk->sk_state == TCP_CLOSE) + return; + /* must hold: tcp_done() could drop last reference on parent */ sock_hold(sk); - tcp_set_state(ssk, TCP_CLOSE); tcp_send_active_reset(ssk, GFP_ATOMIC); tcp_done(ssk); - if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && - schedule_work(&mptcp_sk(sk)->work)) - return; /* worker will put sk for us */ + if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) + mptcp_schedule_work(sk); sock_put(sk); } @@ -622,7 +626,7 @@ static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init; -static struct proto tcpv6_prot_override; +static struct proto tcpv6_prot_override __ro_after_init; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -693,9 +697,10 @@ static bool subflow_hmac_valid(const struct request_sock *req, static void mptcp_force_close(struct sock *sk) { - /* the msk is not yet exposed to user-space */ + /* the msk is not yet exposed to user-space, and refcount is 2 */ inet_sk_state_store(sk, TCP_CLOSE); sk_common_release(sk); + sock_put(sk); } static void subflow_ulp_fallback(struct sock *sk, @@ -711,16 +716,19 @@ static void subflow_ulp_fallback(struct sock *sk, mptcp_subflow_ops_undo_override(sk); } -static void subflow_drop_ctx(struct sock *ssk) +void mptcp_subflow_drop_ctx(struct sock *ssk) { struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk); if (!ctx) return; - subflow_ulp_fallback(ssk, ctx); - if (ctx->conn) - sock_put(ctx->conn); + list_del(&mptcp_subflow_ctx(ssk)->node); + if (inet_csk(ssk)->icsk_ulp_ops) { + subflow_ulp_fallback(ssk, ctx); + if (ctx->conn) + sock_put(ctx->conn); + } kfree_rcu(ctx, rcu); } @@ -750,6 +758,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_options_received mp_opt; bool fallback, fallback_is_fatal; struct sock *new_msk = NULL; + struct mptcp_sock *owner; struct sock *child; pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); @@ -816,7 +825,7 @@ create_child: if (new_msk) mptcp_copy_inaddrs(new_msk, child); - subflow_drop_ctx(child); + mptcp_subflow_drop_ctx(child); goto out; } @@ -824,6 +833,8 @@ create_child: ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { + owner = mptcp_sk(new_msk); + /* this can't race with mptcp_close(), as the msk is * not yet exposted to user-space */ @@ -832,14 +843,14 @@ create_child: /* record the newly created socket as the first msk * subflow, but don't link it yet into conn_list */ - WRITE_ONCE(mptcp_sk(new_msk)->first, child); + WRITE_ONCE(owner->first, child); /* new mpc subflow takes ownership of the newly * created mptcp socket */ mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq; - mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1); - mptcp_token_accept(subflow_req, mptcp_sk(new_msk)); + mptcp_pm_new_connection(owner, child, 1); + mptcp_token_accept(subflow_req, owner); ctx->conn = new_msk; new_msk = NULL; @@ -847,15 +858,21 @@ create_child: * uses the correct data */ mptcp_copy_inaddrs(ctx->conn, child); + mptcp_propagate_sndbuf(ctx->conn, child); + + mptcp_rcv_space_init(owner, child); + list_add(&ctx->node, &owner->conn_list); + sock_hold(child); /* with OoO packets we can reach here without ingress * mpc option */ - if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) + if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { mptcp_subflow_fully_established(ctx, &mp_opt); + mptcp_pm_fully_established(owner, child, GFP_ATOMIC); + ctx->pm_notified = 1; + } } else if (ctx->mp_join) { - struct mptcp_sock *owner; - owner = subflow_req->msk; if (!owner) { subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); @@ -899,7 +916,7 @@ out: return child; dispose_child: - subflow_drop_ctx(child); + mptcp_subflow_drop_ctx(child); tcp_rsk(req)->drop_req = true; inet_csk_prepare_for_destroy_sock(child); tcp_done(child); @@ -910,7 +927,7 @@ dispose_child: } static struct inet_connection_sock_af_ops subflow_specific __ro_after_init; -static struct proto tcp_prot_override; +static struct proto tcp_prot_override __ro_after_init; enum mapping_status { MAPPING_OK, @@ -1103,8 +1120,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk, skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; } else { - if (updated && schedule_work(&msk->work)) - sock_hold((struct sock *)msk); + if (updated) + mptcp_schedule_work((struct sock *)msk); return MAPPING_DATA_FIN; } @@ -1207,17 +1224,12 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, /* sched mptcp worker to remove the subflow if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { - struct sock *sk = (struct sock *)msk; - if (likely(ssk->sk_state != TCP_CLOSE)) return; if (skb_queue_empty(&ssk->sk_receive_queue) && - !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) { - sock_hold(sk); - if (!schedule_work(&msk->work)) - sock_put(sk); - } + !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + mptcp_schedule_work((struct sock *)msk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) @@ -1432,6 +1444,13 @@ static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + /* bail early if this is a no-op, so that we avoid introducing a + * problematic lockdep dependency between TCP accept queue lock + * and msk socket spinlock + */ + if (!sk->sk_socket) + return; + mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_error_report(sk); @@ -1808,13 +1827,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; struct mptcp_sock *msk, *next, *head = NULL; struct request_sock *req; + struct sock *sk; /* build a list of all unaccepted mptcp sockets */ spin_lock_bh(&queue->rskq_lock); for (req = queue->rskq_accept_head; req; req = req->dl_next) { struct mptcp_subflow_context *subflow; struct sock *ssk = req->sk; - struct mptcp_sock *msk; if (!sk_is_mptcp(ssk)) continue; @@ -1824,10 +1843,12 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s continue; /* skip if already in list */ - msk = mptcp_sk(subflow->conn); + sk = subflow->conn; + msk = mptcp_sk(sk); if (msk->dl_next || msk == head) continue; + sock_hold(sk); msk->dl_next = head; head = msk; } @@ -1841,34 +1862,30 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s release_sock(listener_ssk); for (msk = head; msk; msk = next) { - struct sock *sk = (struct sock *)msk; - bool do_cancel_work; + sk = (struct sock *)msk; - sock_hold(sk); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); next = msk->dl_next; - msk->first = NULL; msk->dl_next = NULL; - do_cancel_work = __mptcp_close(sk, 0); + __mptcp_unaccepted_force_close(sk); release_sock(sk); - if (do_cancel_work) { - /* lockdep will report a false positive ABBA deadlock - * between cancel_work_sync and the listener socket. - * The involved locks belong to different sockets WRT - * the existing AB chain. - * Using a per socket key is problematic as key - * deregistration requires process context and must be - * performed at socket disposal time, in atomic - * context. - * Just tell lockdep to consider the listener socket - * released here. - */ - mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_); - mptcp_cancel_work(sk); - mutex_acquire(&listener_sk->sk_lock.dep_map, - SINGLE_DEPTH_NESTING, 0, _RET_IP_); - } + + /* lockdep will report a false positive ABBA deadlock + * between cancel_work_sync and the listener socket. + * The involved locks belong to different sockets WRT + * the existing AB chain. + * Using a per socket key is problematic as key + * deregistration requires process context and must be + * performed at socket disposal time, in atomic + * context. + * Just tell lockdep to consider the listener socket + * released here. + */ + mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_); + mptcp_cancel_work(sk); + mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_); + sock_put(sk); } @@ -1932,6 +1949,13 @@ static void subflow_ulp_release(struct sock *ssk) * when the subflow is still unaccepted */ release = ctx->disposable || list_empty(&ctx->node); + + /* inet_child_forget() does not call sk_state_change(), + * explicitly trigger the socket close machinery + */ + if (!release && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, + &mptcp_sk(sk)->flags)) + mptcp_schedule_work(sk); sock_put(sk); } diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 80713febfac6..d9da942ad53d 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1803,8 +1803,8 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, pdev = to_platform_device(dev->dev.parent); if (pdev) { np = pdev->dev.of_node; - if (np && (of_get_property(np, "mellanox,multi-host", NULL) || - of_get_property(np, "mlx,multi-host", NULL))) + if (np && (of_property_read_bool(np, "mellanox,multi-host") || + of_property_read_bool(np, "mlx,multi-host"))) ndp->mlx_multi_host = true; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 7250082e7de5..c6a6a6099b4e 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -96,8 +96,8 @@ static DEFINE_MUTEX(nf_conntrack_mutex); #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) #define GC_SCAN_EXPIRED_MAX (64000u / HZ) -#define MIN_CHAINLEN 8u -#define MAX_CHAINLEN (32u - MIN_CHAINLEN) +#define MIN_CHAINLEN 50u +#define MAX_CHAINLEN (80u - MIN_CHAINLEN) static struct conntrack_gc_work conntrack_gc_work; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c11dff91d52d..bfc3aaa2c872 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -328,11 +328,12 @@ nla_put_failure: } #ifdef CONFIG_NF_CONNTRACK_MARK -static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) +static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct, + bool dump) { u32 mark = READ_ONCE(ct->mark); - if (!mark) + if (!mark && !dump) return 0; if (nla_put_be32(skb, CTA_MARK, htonl(mark))) @@ -343,7 +344,7 @@ nla_put_failure: return -1; } #else -#define ctnetlink_dump_mark(a, b) (0) +#define ctnetlink_dump_mark(a, b, c) (0) #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK @@ -548,7 +549,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb, static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || - ctnetlink_dump_mark(skb, ct) < 0 || + ctnetlink_dump_mark(skb, ct, true) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || @@ -831,8 +832,7 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) } #ifdef CONFIG_NF_CONNTRACK_MARK - if (events & (1 << IPCT_MARK) && - ctnetlink_dump_mark(skb, ct) < 0) + if (ctnetlink_dump_mark(skb, ct, events & (1 << IPCT_MARK))) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -2735,7 +2735,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK - if (ctnetlink_dump_mark(skb, ct) < 0) + if (ctnetlink_dump_mark(skb, ct, true) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 6004d4b24451..e48ab8dfb541 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3447,6 +3447,64 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) return 0; } +int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + 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; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) + return 0; + + data = nft_set_ext_data(ext); + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; + default: + break; + } + + return 0; +} + +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +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; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + ret = nft_setelem_validate(ctx, set, NULL, &elem); + if (ret < 0) + return ret; + } + + return ret; +} + static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla); @@ -4759,12 +4817,6 @@ err_set_name: return err; } -struct nft_set_elem_catchall { - struct list_head list; - struct rcu_head rcu; - void *elem; -}; - static void nft_set_catchall_destroy(const struct nft_ctx *ctx, struct nft_set *set) { @@ -6056,7 +6108,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + if (((flags & NFT_SET_ELEM_CATCHALL) && nla[NFTA_SET_ELEM_KEY]) || + (!(flags & NFT_SET_ELEM_CATCHALL) && !nla[NFTA_SET_ELEM_KEY])) return -EINVAL; if (flags != 0) { @@ -7052,7 +7105,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, } if (nla[NFTA_OBJ_USERDATA]) { - obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL); + obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL_ACCOUNT); if (obj->udata == NULL) goto err_userdata; diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 7f2bda6641bd..8e6d7eaf9dc8 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -105,11 +105,15 @@ static void nft_last_destroy(const struct nft_ctx *ctx, static int nft_last_clone(struct nft_expr *dst, const struct nft_expr *src) { struct nft_last_priv *priv_dst = nft_expr_priv(dst); + struct nft_last_priv *priv_src = nft_expr_priv(src); priv_dst->last = kzalloc(sizeof(*priv_dst->last), GFP_ATOMIC); if (!priv_dst->last) return -ENOMEM; + priv_dst->last->set = priv_src->last->set; + priv_dst->last->jiffies = priv_src->last->jiffies; + return 0; } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index cae5a6724163..cecf8ab90e58 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -199,37 +199,6 @@ nla_put_failure: return -1; } -static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) -{ - 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; - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - pctx->level++; - err = nft_chain_validate(ctx, data->verdict.chain); - if (err < 0) - return err; - pctx->level--; - break; - default: - break; - } - - return 0; -} - static int nft_lookup_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **d) @@ -245,9 +214,12 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, iter.skip = 0; iter.count = 0; iter.err = 0; - iter.fn = nft_lookup_validate_setelem; + iter.fn = nft_setelem_validate; priv->set->ops->walk(ctx, priv->set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_validate(ctx, priv->set); + if (iter.err < 0) return iter.err; diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index e55e455275c4..9544c2f16998 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -43,7 +43,7 @@ static int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { - u32 plen = sizeof_field(struct nf_nat_range, min_addr.all); + u32 plen = sizeof_field(struct nf_nat_range, min_proto.all); struct nft_masq *priv = nft_expr_priv(expr); int err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 047999150390..5c29915ab028 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -226,7 +226,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->flags |= NF_NAT_RANGE_MAP_IPS; } - plen = sizeof_field(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN], &priv->sreg_proto_min, plen); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 123578e28917..3ba12a7471b0 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -236,12 +236,16 @@ static void nft_quota_destroy(const struct nft_ctx *ctx, static int nft_quota_clone(struct nft_expr *dst, const struct nft_expr *src) { struct nft_quota *priv_dst = nft_expr_priv(dst); + struct nft_quota *priv_src = nft_expr_priv(src); + + priv_dst->quota = priv_src->quota; + priv_dst->flags = priv_src->flags; priv_dst->consumed = kmalloc(sizeof(*priv_dst->consumed), GFP_ATOMIC); if (!priv_dst->consumed) return -ENOMEM; - atomic64_set(priv_dst->consumed, 0); + *priv_dst->consumed = *priv_src->consumed; return 0; } diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 5f7739987559..67cec56bc84a 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -48,7 +48,7 @@ static int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err; - plen = sizeof_field(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN], &priv->sreg_proto_min, plen); @@ -236,7 +236,7 @@ static struct nft_expr_type nft_redir_inet_type __read_mostly = { .name = "redir", .ops = &nft_redir_inet_ops, .policy = nft_redir_policy, - .maxattr = NFTA_MASQ_MAX, + .maxattr = NFTA_REDIR_MAX, .owner = THIS_MODULE, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c64277659753..f365dfdd672d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1952,7 +1952,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); - size_t copied; + size_t copied, max_recvmsg_len; struct sk_buff *skb, *data_skb; int err, ret; @@ -1985,9 +1985,10 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, #endif /* Record the max length of recvmsg() calls for future allocations */ - nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len); - nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len, - SKB_WITH_OVERHEAD(32768)); + max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); + max_recvmsg_len = min_t(size_t, max_recvmsg_len, + SKB_WITH_OVERHEAD(32768)); + WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); copied = data_skb->len; if (len < copied) { @@ -2236,6 +2237,7 @@ static int netlink_dump(struct sock *sk) struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; + size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; @@ -2258,8 +2260,9 @@ static int netlink_dump(struct sock *sk) cb = &nlk->cb; alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); - if (alloc_min_size < nlk->max_recvmsg_len) { - alloc_size = nlk->max_recvmsg_len; + max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); + if (alloc_min_size < max_recvmsg_len) { + alloc_size = max_recvmsg_len; skb = alloc_skb(alloc_size, (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 348bf561bc9f..b9264e730fd9 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1446,8 +1446,8 @@ static int nfc_se_io(struct nfc_dev *dev, u32 se_idx, return rc; error: - kfree(cb_context); device_unlock(&dev->dev); + kfree(cb_context); return rc; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ca3ebfdb3023..a8cf9a88758e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -913,7 +913,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport)) { + if (likely(vport && netif_carrier_ok(vport->dev))) { u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen; diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 5c2fb992803b..76f0434d3d06 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -393,10 +393,12 @@ static struct qrtr_node *qrtr_node_lookup(unsigned int nid) struct qrtr_node *node; unsigned long flags; + mutex_lock(&qrtr_node_lock); spin_lock_irqsave(&qrtr_nodes_lock, flags); node = radix_tree_lookup(&qrtr_nodes, nid); node = qrtr_node_acquire(node); spin_unlock_irqrestore(&qrtr_nodes_lock, flags); + mutex_unlock(&qrtr_node_lock); return node; } @@ -496,6 +498,11 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!size || len != ALIGN(size, 4) + hdrlen) goto err; + if ((cb->type == QRTR_TYPE_NEW_SERVER || + cb->type == QRTR_TYPE_RESUME_TX) && + size < sizeof(struct qrtr_ctrl_pkt)) + goto err; + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && cb->type != QRTR_TYPE_RESUME_TX) goto err; @@ -508,9 +515,6 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) /* Remote node endpoint can bridge other distant nodes */ const struct qrtr_ctrl_pkt *pkt; - if (size < sizeof(*pkt)) - goto err; - pkt = data + hdrlen; qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); } diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 722936f7dd98..0f25a386138c 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -274,7 +274,7 @@ err: return NULL; } -static int server_del(struct qrtr_node *node, unsigned int port) +static int server_del(struct qrtr_node *node, unsigned int port, bool bcast) { struct qrtr_lookup *lookup; struct qrtr_server *srv; @@ -287,7 +287,7 @@ static int server_del(struct qrtr_node *node, unsigned int port) radix_tree_delete(&node->servers, port); /* Broadcast the removal of local servers */ - if (srv->node == qrtr_ns.local_node) + if (srv->node == qrtr_ns.local_node && bcast) service_announce_del(&qrtr_ns.bcast_sq, srv); /* Announce the service's disappearance to observers */ @@ -373,7 +373,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) } slot = radix_tree_iter_resume(slot, &iter); rcu_read_unlock(); - server_del(node, srv->port); + server_del(node, srv->port, true); rcu_read_lock(); } rcu_read_unlock(); @@ -459,10 +459,13 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, kfree(lookup); } - /* Remove the server belonging to this port */ + /* Remove the server belonging to this port but don't broadcast + * DEL_SERVER. Neighbours would've already removed the server belonging + * to this port due to the DEL_CLIENT broadcast from qrtr_port_remove(). + */ node = node_get(node_id); if (node) - server_del(node, port); + server_del(node, port, false); /* Advertise the removal of this client to all local servers */ local_node = node_get(qrtr_ns.local_node); @@ -567,7 +570,7 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, if (!node) return -ENOENT; - return server_del(node, port); + return server_del(node, port, true); } static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 34c508675041..296fc1afedd8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1589,6 +1589,10 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], t->tca__pad1 = 0; t->tca__pad2 = 0; + if (extack && extack->_msg && + nla_put_string(skb, TCA_ROOT_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); if (!nest) goto out_nlmsg_trim; @@ -1596,10 +1600,6 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], if (tcf_action_dump(skb, actions, bind, ref, false) < 0) goto out_nlmsg_trim; - if (extack && extack->_msg && - nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) - goto out_nlmsg_trim; - nla_nest_end(skb, nest); nlh->nlmsg_len = skb_tail_pointer(skb) - b; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 8dabfb52ea3d..0d7aee8933c5 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -158,6 +158,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, nparms->zone = parm->zone; ret = 0; + } else { + err = ret; + goto out_free; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2a6b6be0811b..35785a36c802 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3235,6 +3235,9 @@ int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action, err_miss_alloc: tcf_exts_destroy(exts); +#ifdef CONFIG_NET_CLS_ACT + exts->actions = NULL; +#endif return err; } EXPORT_SYMBOL(tcf_exts_init_ex); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e960a46b0520..475fe222a855 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2200,8 +2200,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); if (!tc_flags_valid(fnew->flags)) { + kfree(fnew); err = -EINVAL; - goto errout; + goto errout_tb; } } @@ -2226,8 +2227,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } spin_unlock(&tp->lock); - if (err) - goto errout; + if (err) { + kfree(fnew); + goto errout_tb; + } } fnew->handle = handle; @@ -2337,7 +2340,6 @@ errout_mask: fl_mask_put(head, fnew->mask); errout_idr: idr_remove(&head->handle_idr, fnew->handle); -errout: __fl_put(fnew); errout_tb: kfree(tb); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index cf5ebe43b3b4..02098a02943e 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -421,15 +421,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } else weight = 1; - if (tb[TCA_QFQ_LMAX]) { + if (tb[TCA_QFQ_LMAX]) lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - } else + else lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { + pr_notice("qfq: invalid max length %u\n", lmax); + return -EINVAL; + } + inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b91616f819de..218e0982c370 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1830,6 +1830,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) goto err; + if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { + err = -EINVAL; + goto err; + } } if (sctp_state(asoc, CLOSED)) { diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 94727feb07b3..b046b11200c9 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -1154,7 +1154,8 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = chunk->subh.ifwdtsn_hdr->skip; \ - (void *)pos < (void *)chunk->subh.ifwdtsn_hdr->skip + (end); pos++) + (void *)pos <= (void *)chunk->subh.ifwdtsn_hdr->skip + (end) - \ + sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a4cccdfdc00a..50c38b624f77 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2657,16 +2657,14 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct smc_sock *smc; - int rc = -EPIPE; + int rc; smc = smc_sk(sk); lock_sock(sk); - if ((sk->sk_state != SMC_ACTIVE) && - (sk->sk_state != SMC_APPCLOSEWAIT1) && - (sk->sk_state != SMC_INIT)) - goto out; + /* SMC does not support connect with fastopen */ if (msg->msg_flags & MSG_FASTOPEN) { + /* not connected yet, fallback */ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { rc = smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); if (rc) @@ -2675,6 +2673,11 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) rc = -EINVAL; goto out; } + } else if ((sk->sk_state != SMC_ACTIVE) && + (sk->sk_state != SMC_APPCLOSEWAIT1) && + (sk->sk_state != SMC_INIT)) { + rc = -EPIPE; + goto out; } if (smc->use_fallback) { @@ -3267,6 +3270,17 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, sk_common_release(sk); goto out; } + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); } else { smc->clcsock = clcsock; } @@ -3498,6 +3512,7 @@ out_pnet: out_nl: smc_nl_exit(); out_ism: + smc_clc_exit(); smc_ism_exit(); out_pernet_subsys_stat: unregister_pernet_subsys(&smc_net_stat_ops); diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 53f63bfbaf5f..89105e95b452 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -114,6 +114,9 @@ int smc_cdc_msg_send(struct smc_connection *conn, union smc_host_cursor cfed; int rc; + if (unlikely(!READ_ONCE(conn->sndbuf_desc))) + return -ENOBUFS; + smc_cdc_add_pending_send(conn, pend); conn->tx_cdc_seq++; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index d52060b2680c..454356771cda 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1464,7 +1464,7 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) if (lgr->terminating) return; /* lgr already terminating */ /* cancel free_work sync, will terminate when lgr->freeing is set */ - cancel_delayed_work_sync(&lgr->free_work); + cancel_delayed_work(&lgr->free_work); lgr->terminating = 1; /* kill remaining link group connections */ diff --git a/net/socket.c b/net/socket.c index 6bae8ce7059e..9c92c0e6c4da 100644 --- a/net/socket.c +++ b/net/socket.c @@ -450,7 +450,9 @@ static struct file_system_type sock_fs_type = { * * Returns the &file bound with @sock, implicitly storing it * in sock->file. If dname is %NULL, sets to "". - * On failure the return is a ERR pointer (see linux/err.h). + * + * On failure @sock is released, and an ERR pointer is returned. + * * This function uses GFP_KERNEL internally. */ @@ -1638,7 +1640,6 @@ static struct socket *__sys_socket_create(int family, int type, int protocol) struct file *__sys_socket_file(int family, int type, int protocol) { struct socket *sock; - struct file *file; int flags; sock = __sys_socket_create(family, type, protocol); @@ -1649,11 +1650,7 @@ struct file *__sys_socket_file(int family, int type, int protocol) if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - file = sock_alloc_file(sock, flags, NULL); - if (IS_ERR(file)) - sock_release(sock); - - return file; + return sock_alloc_file(sock, flags, NULL); } int __sys_socket(int family, int type, int protocol) diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 6c7c52eeed4f..212c5d57465a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -353,7 +353,9 @@ gss_krb5_checksum(struct crypto_ahash *tfm, char *header, int hdrlen, err = crypto_ahash_final(req); if (err) goto out_free_ahash; - memcpy(cksumout->data, checksumdata, cksumout->len); + + memcpy(cksumout->data, checksumdata, + min_t(int, cksumout->len, crypto_ahash_digestsize(tfm))); out_free_ahash: ahash_request_free(req); @@ -809,8 +811,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, buf->tail[0].iov_len += GSS_KRB5_TOK_HDR_LEN; buf->len += GSS_KRB5_TOK_HDR_LEN; - /* Do the HMAC */ - hmac.len = GSS_KRB5_MAX_CKSUM_LEN; + hmac.len = kctx->gk5e->cksumlength; hmac.data = buf->tail[0].iov_base + buf->tail[0].iov_len; /* @@ -873,8 +874,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, if (ret) goto out_err; - /* Calculate our hmac over the plaintext data */ - our_hmac_obj.len = sizeof(our_hmac); + our_hmac_obj.len = kctx->gk5e->cksumlength; our_hmac_obj.data = our_hmac; ret = gss_krb5_checksum(ahash, NULL, 0, &subbuf, 0, &our_hmac_obj); if (ret) diff --git a/net/sunrpc/auth_gss/gss_krb5_test.c b/net/sunrpc/auth_gss/gss_krb5_test.c index ce0541e32fc9..95ca783795c5 100644 --- a/net/sunrpc/auth_gss/gss_krb5_test.c +++ b/net/sunrpc/auth_gss/gss_krb5_test.c @@ -73,7 +73,6 @@ static void checksum_case(struct kunit *test) { const struct gss_krb5_test_param *param = test->param_value; struct xdr_buf buf = { - .head[0].iov_base = param->plaintext->data, .head[0].iov_len = param->plaintext->len, .len = param->plaintext->len, }; @@ -99,6 +98,10 @@ static void checksum_case(struct kunit *test) err = crypto_ahash_setkey(tfm, Kc.data, Kc.len); KUNIT_ASSERT_EQ(test, err, 0); + buf.head[0].iov_base = kunit_kzalloc(test, buf.head[0].iov_len, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf.head[0].iov_base); + memcpy(buf.head[0].iov_base, param->plaintext->data, buf.head[0].iov_len); + checksum.len = gk5e->cksumlength; checksum.data = kunit_kzalloc(test, checksum.len, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, checksum.data); @@ -1327,6 +1330,7 @@ static void rfc6803_encrypt_case(struct kunit *test) if (!gk5e) kunit_skip(test, "Encryption type is not available"); + memset(usage_data, 0, sizeof(usage_data)); usage.data[3] = param->constant; Ke.len = gk5e->Ke_length; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 1fd3f5e57285..fea7ce8fba14 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -798,6 +798,7 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) static int svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { + struct svc_rqst *rqstp; struct task_struct *task; unsigned int state = serv->sv_nrthreads-1; @@ -806,7 +807,10 @@ svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) task = choose_victim(serv, pool, &state); if (task == NULL) break; - kthread_stop(task); + rqstp = kthread_data(task); + /* Did we lose a race to svo_function threadfn? */ + if (kthread_stop(task) == -EINTR) + svc_exit_thread(rqstp); nrservs++; } while (nrservs < 0); return 0; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 983c5891cb56..4246363cb095 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -416,14 +416,23 @@ static int unix_gid_hash(kuid_t uid) return hash_long(from_kuid(&init_user_ns, uid), GID_HASHBITS); } -static void unix_gid_put(struct kref *kref) +static void unix_gid_free(struct rcu_head *rcu) { - struct cache_head *item = container_of(kref, struct cache_head, ref); - struct unix_gid *ug = container_of(item, struct unix_gid, h); + struct unix_gid *ug = container_of(rcu, struct unix_gid, rcu); + struct cache_head *item = &ug->h; + if (test_bit(CACHE_VALID, &item->flags) && !test_bit(CACHE_NEGATIVE, &item->flags)) put_group_info(ug->gi); - kfree_rcu(ug, rcu); + kfree(ug); +} + +static void unix_gid_put(struct kref *kref) +{ + struct cache_head *item = container_of(kref, struct cache_head, ref); + struct unix_gid *ug = container_of(item, struct unix_gid, h); + + call_rcu(&ug->rcu, unix_gid_free); } static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index adcbedc244d6..6cacd70a15ff 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2158,6 +2158,7 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) switch (skst) { case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: + case TCP_LAST_ACK: break; case TCP_ESTABLISHED: case TCP_CLOSE_WAIT: diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 6c593788dc25..a7cc4f9faac2 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -508,6 +508,8 @@ handle_error: zc_pfrag.offset = iter_offset.offset; zc_pfrag.size = copy; tls_append_frag(record, &zc_pfrag, copy); + + iter_offset.offset += copy; } else if (copy) { copy = min_t(size_t, copy, pfrag->size - pfrag->offset); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 3735cb00905d..b32c112984dd 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -405,13 +405,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(crypto_info_aes_gcm_128->iv, cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); memcpy(crypto_info_aes_gcm_128->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, crypto_info_aes_gcm_128, sizeof(*crypto_info_aes_gcm_128))) @@ -429,13 +427,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(crypto_info_aes_gcm_256->iv, cctx->iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, TLS_CIPHER_AES_GCM_256_IV_SIZE); memcpy(crypto_info_aes_gcm_256->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, crypto_info_aes_gcm_256, sizeof(*crypto_info_aes_gcm_256))) @@ -451,13 +447,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(aes_ccm_128->iv, cctx->iv + TLS_CIPHER_AES_CCM_128_SALT_SIZE, TLS_CIPHER_AES_CCM_128_IV_SIZE); memcpy(aes_ccm_128->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, aes_ccm_128, sizeof(*aes_ccm_128))) rc = -EFAULT; break; @@ -472,13 +466,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(chacha20_poly1305->iv, cctx->iv + TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE, TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE); memcpy(chacha20_poly1305->rec_seq, cctx->rec_seq, TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, chacha20_poly1305, sizeof(*chacha20_poly1305))) rc = -EFAULT; @@ -493,13 +485,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(sm4_gcm_info->iv, cctx->iv + TLS_CIPHER_SM4_GCM_SALT_SIZE, TLS_CIPHER_SM4_GCM_IV_SIZE); memcpy(sm4_gcm_info->rec_seq, cctx->rec_seq, TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, sm4_gcm_info, sizeof(*sm4_gcm_info))) rc = -EFAULT; break; @@ -513,13 +503,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(sm4_ccm_info->iv, cctx->iv + TLS_CIPHER_SM4_CCM_SALT_SIZE, TLS_CIPHER_SM4_CCM_IV_SIZE); memcpy(sm4_ccm_info->rec_seq, cctx->rec_seq, TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, sm4_ccm_info, sizeof(*sm4_ccm_info))) rc = -EFAULT; break; @@ -535,13 +523,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(crypto_info_aria_gcm_128->iv, cctx->iv + TLS_CIPHER_ARIA_GCM_128_SALT_SIZE, TLS_CIPHER_ARIA_GCM_128_IV_SIZE); memcpy(crypto_info_aria_gcm_128->rec_seq, cctx->rec_seq, TLS_CIPHER_ARIA_GCM_128_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, crypto_info_aria_gcm_128, sizeof(*crypto_info_aria_gcm_128))) @@ -559,13 +545,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(crypto_info_aria_gcm_256->iv, cctx->iv + TLS_CIPHER_ARIA_GCM_256_SALT_SIZE, TLS_CIPHER_ARIA_GCM_256_IV_SIZE); memcpy(crypto_info_aria_gcm_256->rec_seq, cctx->rec_seq, TLS_CIPHER_ARIA_GCM_256_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, crypto_info_aria_gcm_256, sizeof(*crypto_info_aria_gcm_256))) @@ -614,11 +598,9 @@ static int do_tls_getsockopt_no_pad(struct sock *sk, char __user *optval, if (len < sizeof(value)) return -EINVAL; - lock_sock(sk); value = -EINVAL; if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) value = ctx->rx_no_pad; - release_sock(sk); if (value < 0) return value; @@ -635,6 +617,8 @@ static int do_tls_getsockopt(struct sock *sk, int optname, { int rc = 0; + lock_sock(sk); + switch (optname) { case TLS_TX: case TLS_RX: @@ -651,6 +635,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, rc = -ENOPROTOOPT; break; } + + release_sock(sk); + return rc; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 782d3701b86f..635b8bf6b937 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -956,7 +956,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) MSG_CMSG_COMPAT)) return -EOPNOTSUPP; - mutex_lock(&tls_ctx->tx_lock); + ret = mutex_lock_interruptible(&tls_ctx->tx_lock); + if (ret) + return ret; lock_sock(sk); if (unlikely(msg->msg_controllen)) { @@ -1290,7 +1292,9 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) return -EOPNOTSUPP; - mutex_lock(&tls_ctx->tx_lock); + ret = mutex_lock_interruptible(&tls_ctx->tx_lock); + if (ret) + return ret; lock_sock(sk); ret = tls_sw_do_sendpage(sk, page, offset, size, flags); release_sock(sk); @@ -2127,7 +2131,7 @@ recv_end: else err = process_rx_list(ctx, msg, &control, 0, async_copy_bytes, is_peek); - decrypted = max(err, 0); + decrypted += max(err, 0); } copied += decrypted; @@ -2435,11 +2439,19 @@ static void tx_work_handler(struct work_struct *work) if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) return; - mutex_lock(&tls_ctx->tx_lock); - lock_sock(sk); - tls_tx_records(sk, -1); - release_sock(sk); - mutex_unlock(&tls_ctx->tx_lock); + + if (mutex_trylock(&tls_ctx->tx_lock)) { + lock_sock(sk); + tls_tx_records(sk, -1); + release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); + } else if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { + /* Someone is holding the tx_lock, they will likely run Tx + * and cancel the work on their way out of the lock section. + * Schedule a long delay just in case. + */ + schedule_delayed_work(&ctx->tx_work.work, msecs_to_jiffies(10)); + } } static bool tls_is_tx_ready(struct tls_sw_context_tx *ctx) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 347122c3575e..0b0f18ecce44 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2105,7 +2105,8 @@ out: #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768)) #if IS_ENABLED(CONFIG_AF_UNIX_OOB) -static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other) +static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other, + struct scm_cookie *scm, bool fds_sent) { struct unix_sock *ousk = unix_sk(other); struct sk_buff *skb; @@ -2116,6 +2117,11 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other if (!skb) return err; + err = unix_scm_to_skb(scm, skb, !fds_sent); + if (err < 0) { + kfree_skb(skb); + return err; + } skb_put(skb, 1); err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, 1); @@ -2243,7 +2249,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (msg->msg_flags & MSG_OOB) { - err = queue_oob(sock, msg, other); + err = queue_oob(sock, msg, other, &scm, fds_sent); if (err) goto out_err; sent++; diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index e9bf15513961..2f9d8271c6ec 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg, struct sk_psock *psock; int copied; + if (!len) + return 0; + psock = sk_psock_get(sk); if (unlikely(!psock)) return __unix_recvmsg(sk, msg, len, flags); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a1581c77cf84..ee78b4082ef9 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -94,6 +94,11 @@ virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, info->op, info->flags); + if (info->vsk && !skb_set_owner_sk_safe(skb, sk_vsock(info->vsk))) { + WARN_ONCE(1, "failed to allocate skb on vsock socket with sk_refcnt == 0\n"); + goto out; + } + return skb; out: @@ -241,21 +246,18 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, } static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, - struct sk_buff *skb) + u32 len) { - if (vvs->rx_bytes + skb->len > vvs->buf_alloc) + if (vvs->rx_bytes + len > vvs->buf_alloc) return false; - vvs->rx_bytes += skb->len; + vvs->rx_bytes += len; return true; } static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, - struct sk_buff *skb) + u32 len) { - int len; - - len = skb_headroom(skb) - sizeof(struct virtio_vsock_hdr) - skb->len; vvs->rx_bytes -= len; vvs->fwd_cnt += len; } @@ -366,8 +368,15 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, u32 free_space; spin_lock_bh(&vvs->rx_lock); + + if (WARN_ONCE(skb_queue_empty(&vvs->rx_queue) && vvs->rx_bytes, + "rx_queue is empty, but rx_bytes is non-zero\n")) { + spin_unlock_bh(&vvs->rx_lock); + return err; + } + while (total < len && !skb_queue_empty(&vvs->rx_queue)) { - skb = __skb_dequeue(&vvs->rx_queue); + skb = skb_peek(&vvs->rx_queue); bytes = len - total; if (bytes > skb->len) @@ -388,10 +397,11 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, skb_pull(skb, bytes); if (skb->len == 0) { - virtio_transport_dec_rx_pkt(vvs, skb); + u32 pkt_len = le32_to_cpu(virtio_vsock_hdr(skb)->len); + + virtio_transport_dec_rx_pkt(vvs, pkt_len); + __skb_unlink(skb, &vvs->rx_queue); consume_skb(skb); - } else { - __skb_queue_head(&vvs->rx_queue, skb); } } @@ -437,17 +447,17 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, while (!msg_ready) { struct virtio_vsock_hdr *hdr; + size_t pkt_len; skb = __skb_dequeue(&vvs->rx_queue); if (!skb) break; hdr = virtio_vsock_hdr(skb); + pkt_len = (size_t)le32_to_cpu(hdr->len); if (dequeued_len >= 0) { - size_t pkt_len; size_t bytes_to_copy; - pkt_len = (size_t)le32_to_cpu(hdr->len); bytes_to_copy = min(user_buf_len, pkt_len); if (bytes_to_copy) { @@ -466,7 +476,6 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, dequeued_len = err; } else { user_buf_len -= bytes_to_copy; - skb_pull(skb, bytes_to_copy); } spin_lock_bh(&vvs->rx_lock); @@ -484,7 +493,7 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, msg->msg_flags |= MSG_EOR; } - virtio_transport_dec_rx_pkt(vvs, skb); + virtio_transport_dec_rx_pkt(vvs, pkt_len); kfree_skb(skb); } @@ -1040,7 +1049,7 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, spin_lock_bh(&vvs->rx_lock); - can_enqueue = virtio_transport_inc_rx_pkt(vvs, skb); + can_enqueue = virtio_transport_inc_rx_pkt(vvs, len); if (!can_enqueue) { free_pkt = true; goto out; @@ -1071,7 +1080,7 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, memcpy(skb_put(last_skb, skb->len), skb->data, skb->len); free_pkt = true; last_hdr->flags |= hdr->flags; - last_hdr->len = cpu_to_le32(last_skb->len); + le32_add_cpu(&last_hdr->len, len); goto out; } } @@ -1299,6 +1308,11 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, goto free_pkt; } + if (!skb_set_owner_sk_safe(skb, sk)) { + WARN_ONCE(1, "receiving vsock socket has sk_refcnt == 0\n"); + goto free_pkt; + } + vsk = vsock_sk(sk); lock_sock(sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 36eb16a40745..95cc4d79ba29 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1842,7 +1842,13 @@ static ssize_t vmci_transport_stream_enqueue( struct msghdr *msg, size_t len) { - return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0); + ssize_t err; + + err = vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0); + if (err < 0) + err = -ENOMEM; + + return err; } static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk) diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 671e03240fc5..89905c092645 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -15,7 +15,6 @@ struct vsock_loopback { struct workqueue_struct *workqueue; - spinlock_t pkt_list_lock; /* protects pkt_list */ struct sk_buff_head pkt_queue; struct work_struct pkt_work; }; @@ -32,9 +31,7 @@ static int vsock_loopback_send_pkt(struct sk_buff *skb) struct vsock_loopback *vsock = &the_vsock_loopback; int len = skb->len; - spin_lock_bh(&vsock->pkt_list_lock); skb_queue_tail(&vsock->pkt_queue, skb); - spin_unlock_bh(&vsock->pkt_list_lock); queue_work(vsock->workqueue, &vsock->pkt_work); @@ -113,9 +110,9 @@ static void vsock_loopback_work(struct work_struct *work) skb_queue_head_init(&pkts); - spin_lock_bh(&vsock->pkt_list_lock); + spin_lock_bh(&vsock->pkt_queue.lock); skb_queue_splice_init(&vsock->pkt_queue, &pkts); - spin_unlock_bh(&vsock->pkt_list_lock); + spin_unlock_bh(&vsock->pkt_queue.lock); while ((skb = __skb_dequeue(&pkts))) { virtio_transport_deliver_tap_pkt(skb); @@ -132,7 +129,6 @@ static int __init vsock_loopback_init(void) if (!vsock->workqueue) return -ENOMEM; - spin_lock_init(&vsock->pkt_list_lock); skb_queue_head_init(&vsock->pkt_queue); INIT_WORK(&vsock->pkt_work, vsock_loopback_work); @@ -156,9 +152,7 @@ static void __exit vsock_loopback_exit(void) flush_work(&vsock->pkt_work); - spin_lock_bh(&vsock->pkt_list_lock); virtio_vsock_skb_queue_purge(&vsock->pkt_queue); - spin_unlock_bh(&vsock->pkt_list_lock); destroy_workqueue(vsock->workqueue); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 112b4bb009c8..4f63059efd81 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -462,6 +462,11 @@ 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 = { + .min = 0, + .max = 0xffff, +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -805,7 +810,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MLD_ADDR] = NLA_POLICY_EXACT_LEN(ETH_ALEN), [NL80211_ATTR_MLO_SUPPORT] = { .type = NLA_FLAG }, [NL80211_ATTR_MAX_NUM_AKM_SUITES] = { .type = NLA_REJECT }, - [NL80211_ATTR_PUNCT_BITMAP] = NLA_POLICY_RANGE(NLA_U8, 0, 0xffff), + [NL80211_ATTR_PUNCT_BITMAP] = + NLA_POLICY_FULL_RANGE(NLA_U32, &nl80211_punct_bitmap_range), }; /* policy for the key attributes */ @@ -8901,7 +8907,7 @@ static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev, struct cfg80211_chan_def *chandef; chandef = wdev_chandef(wdev, link_id); - if (!chandef) + if (!chandef || !chandef->chan) continue; /* @@ -10793,8 +10799,7 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device *rdev, const u8 *ssid, int ssid_len, - struct nlattr **attrs, - const u8 **bssid_out) + struct nlattr **attrs) { struct ieee80211_channel *chan; struct cfg80211_bss *bss; @@ -10821,7 +10826,6 @@ static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device if (!bss) return ERR_PTR(-ENOENT); - *bssid_out = bssid; return bss; } @@ -10831,7 +10835,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) struct net_device *dev = info->user_ptr[1]; struct cfg80211_assoc_request req = {}; struct nlattr **attrs = NULL; - const u8 *bssid, *ssid; + const u8 *ap_addr, *ssid; unsigned int link_id; int err, ssid_len; @@ -10968,6 +10972,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) return -EINVAL; req.ap_mld_addr = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]); + ap_addr = req.ap_mld_addr; attrs = kzalloc(attrsize, GFP_KERNEL); if (!attrs) @@ -10993,8 +10998,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } req.links[link_id].bss = - nl80211_assoc_bss(rdev, ssid, ssid_len, attrs, - &bssid); + nl80211_assoc_bss(rdev, ssid, ssid_len, attrs); if (IS_ERR(req.links[link_id].bss)) { err = PTR_ERR(req.links[link_id].bss); req.links[link_id].bss = NULL; @@ -11045,10 +11049,10 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) if (req.link_id >= 0) return -EINVAL; - req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs, - &bssid); + req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs); if (IS_ERR(req.bss)) return PTR_ERR(req.bss); + ap_addr = req.bss->bssid; } err = nl80211_crypto_settings(rdev, info, &req.crypto, 1); @@ -11061,7 +11065,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) dev->ieee80211_ptr->conn_owner_nlportid = info->snd_portid; memcpy(dev->ieee80211_ptr->disconnect_bssid, - bssid, ETH_ALEN); + ap_addr, ETH_ALEN); } wdev_unlock(dev->ieee80211_ptr); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 28ce13840a88..7bdeb8eea92d 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1500,8 +1500,6 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, connect->key = NULL; connect->key_len = 0; connect->key_idx = 0; - connect->crypto.cipher_group = 0; - connect->crypto.n_ciphers_pairwise = 0; } wdev->connect_keys = connkeys; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 4681e8e8ad94..02207e852d79 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -150,10 +150,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { - u32 npgs_rem, chunk_size = mr->chunk_size, headroom = mr->headroom; bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; - u64 npgs, addr = mr->addr, size = mr->len; - unsigned int chunks, chunks_rem; + u32 chunk_size = mr->chunk_size, headroom = mr->headroom; + u64 addr = mr->addr, size = mr->len; + u32 chunks_rem, npgs_rem; + u64 chunks, npgs; int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { @@ -188,8 +189,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (npgs > U32_MAX) return -EINVAL; - chunks = (unsigned int)div_u64_rem(size, chunk_size, &chunks_rem); - if (chunks == 0) + chunks = div_u64_rem(size, chunk_size, &chunks_rem); + if (!chunks || chunks > U32_MAX) return -EINVAL; if (!unaligned_chunks && chunks_rem) @@ -202,7 +203,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->headroom = headroom; umem->chunk_size = chunk_size; umem->chunks = chunks; - umem->npgs = (u32)npgs; + umem->npgs = npgs; umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 2ab3e09e2227..50baf50dc513 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2815,11 +2815,6 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, goto error; } - if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL)) { - NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate an AF_UNSPEC selector"); - goto error; - } - x->inner_mode = *inner_mode; if (x->props.family == AF_INET) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index cf5172d4ce68..103af2b3e986 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1012,7 +1012,9 @@ static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb) return -EMSGSIZE; ap = nla_data(nla); - memcpy(ap, aead, sizeof(*aead)); + strscpy_pad(ap->alg_name, aead->alg_name, sizeof(ap->alg_name)); + ap->alg_key_len = aead->alg_key_len; + ap->alg_icv_len = aead->alg_icv_len; if (redact_secret && aead->alg_key_len) memset(ap->alg_key, 0, (aead->alg_key_len + 7) / 8); @@ -1032,7 +1034,8 @@ static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb) return -EMSGSIZE; ap = nla_data(nla); - memcpy(ap, ealg, sizeof(*ealg)); + strscpy_pad(ap->alg_name, ealg->alg_name, sizeof(ap->alg_name)); + ap->alg_key_len = ealg->alg_key_len; if (redact_secret && ealg->alg_key_len) memset(ap->alg_key, 0, (ealg->alg_key_len + 7) / 8); @@ -1043,6 +1046,40 @@ static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb) return 0; } +static int copy_to_user_calg(struct xfrm_algo *calg, struct sk_buff *skb) +{ + struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_COMP, sizeof(*calg)); + struct xfrm_algo *ap; + + if (!nla) + return -EMSGSIZE; + + ap = nla_data(nla); + strscpy_pad(ap->alg_name, calg->alg_name, sizeof(ap->alg_name)); + ap->alg_key_len = 0; + + return 0; +} + +static int copy_to_user_encap(struct xfrm_encap_tmpl *ep, struct sk_buff *skb) +{ + struct nlattr *nla = nla_reserve(skb, XFRMA_ENCAP, sizeof(*ep)); + struct xfrm_encap_tmpl *uep; + + if (!nla) + return -EMSGSIZE; + + uep = nla_data(nla); + memset(uep, 0, sizeof(*uep)); + + uep->encap_type = ep->encap_type; + uep->encap_sport = ep->encap_sport; + uep->encap_dport = ep->encap_dport; + uep->encap_oa = ep->encap_oa; + + return 0; +} + static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m) { int ret = 0; @@ -1098,12 +1135,12 @@ static int copy_to_user_state_extra(struct xfrm_state *x, goto out; } if (x->calg) { - ret = nla_put(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg); + ret = copy_to_user_calg(x->calg, skb); if (ret) goto out; } if (x->encap) { - ret = nla_put(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap); + ret = copy_to_user_encap(x->encap, skb); if (ret) goto out; } |