diff options
Diffstat (limited to 'net')
82 files changed, 987 insertions, 572 deletions
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 0899a729a23f..c120c7c6d25f 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -475,6 +475,17 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto free_skb; } + /* GRO might have added fragments to the fragment list instead of + * frags[]. But this is not handled by skb_split and must be + * linearized to avoid incorrect length information after all + * batman-adv fragments were created and submitted to the + * hard-interface + */ + if (skb_has_frag_list(skb) && __skb_linearize(skb)) { + ret = -ENOMEM; + goto free_skb; + } + /* Create one header to be copied to all fragments */ frag_header.packet_type = BATADV_UNICAST_FRAG; frag_header.version = BATADV_COMPAT_VERSION; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 84312c836549..fe803bee419a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -670,7 +670,7 @@ static void le_conn_timeout(struct work_struct *work) /* Disable LE Advertising */ le_disable_advertising(hdev); hci_dev_lock(hdev); - hci_le_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); + hci_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); hci_dev_unlock(hdev); return; } @@ -873,7 +873,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) EXPORT_SYMBOL(hci_get_route); /* This function requires the caller holds hdev->lock */ -void hci_le_conn_failed(struct hci_conn *conn, u8 status) +static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; struct hci_conn_params *params; @@ -886,8 +886,6 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) params->conn = NULL; } - conn->state = BT_CLOSED; - /* 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 @@ -899,10 +897,6 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); - hci_connect_cfm(conn, status); - - hci_conn_del(conn); - /* Since we may have temporarily stopped the background scanning in * favor of connection establishment, we should restart it. */ @@ -914,6 +908,28 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) hci_enable_advertising(hdev); } +/* This function requires the caller holds hdev->lock */ +void hci_conn_failed(struct hci_conn *conn, u8 status) +{ + struct hci_dev *hdev = conn->hdev; + + bt_dev_dbg(hdev, "status 0x%2.2x", status); + + switch (conn->type) { + case LE_LINK: + hci_le_conn_failed(conn, status); + break; + case ACL_LINK: + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + break; + } + + conn->state = BT_CLOSED; + hci_connect_cfm(conn, status); + hci_conn_del(conn); +} + static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b4782a6c1025..45c2dd2e1590 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2555,10 +2555,10 @@ int hci_register_dev(struct hci_dev *hdev) */ switch (hdev->dev_type) { case HCI_PRIMARY: - id = ida_simple_get(&hci_index_ida, 0, 0, GFP_KERNEL); + id = ida_simple_get(&hci_index_ida, 0, HCI_MAX_ID, GFP_KERNEL); break; case HCI_AMP: - id = ida_simple_get(&hci_index_ida, 1, 0, GFP_KERNEL); + id = ida_simple_get(&hci_index_ida, 1, HCI_MAX_ID, GFP_KERNEL); break; default: return -EINVAL; @@ -2567,7 +2567,7 @@ int hci_register_dev(struct hci_dev *hdev) if (id < 0) return id; - sprintf(hdev->name, "hci%d", id); + snprintf(hdev->name, sizeof(hdev->name), "hci%d", id); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index abaabfae19cc..66451661283c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2834,7 +2834,7 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the - * hci_le_conn_failed function which is triggered by the HCI + * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) @@ -2859,7 +2859,7 @@ static void hci_cs_le_ext_create_conn(struct hci_dev *hdev, u8 status) bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the - * hci_le_conn_failed function which is triggered by the HCI + * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) @@ -3067,18 +3067,20 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, { struct hci_ev_conn_complete *ev = data; struct hci_conn *conn; + u8 status = ev->status; - if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for invalid handle"); - return; - } - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { + /* In case of error status and there is no connection pending + * just unlock as there is nothing to cleanup. + */ + if (ev->status) + goto unlock; + /* Connection may not exist if auto-connected. Check the bredr * allowlist to see if this device is allowed to auto connect. * If link is an ACL type, create a connection class @@ -3122,8 +3124,14 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } - if (!ev->status) { + if (!status) { conn->handle = __le16_to_cpu(ev->handle); + if (conn->handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + conn->handle, HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + goto done; + } if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; @@ -3164,19 +3172,14 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, hci_send_cmd(hdev, HCI_OP_CHANGE_CONN_PTYPE, sizeof(cp), &cp); } - } else { - conn->state = BT_CLOSED; - if (conn->type == ACL_LINK) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, ev->status); } if (conn->type == ACL_LINK) hci_sco_setup(conn, ev->status); - if (ev->status) { - hci_connect_cfm(conn, ev->status); - hci_conn_del(conn); +done: + if (status) { + hci_conn_failed(conn, status); } else if (ev->link_type == SCO_LINK) { switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_CVSD: @@ -3185,7 +3188,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, break; } - hci_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, status); } unlock: @@ -4676,6 +4679,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, { struct hci_ev_sync_conn_complete *ev = data; struct hci_conn *conn; + u8 status = ev->status; switch (ev->link_type) { case SCO_LINK: @@ -4690,12 +4694,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, return; } - if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete for invalid handle"); - return; - } - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); @@ -4729,9 +4728,17 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } - switch (ev->status) { + switch (status) { case 0x00: conn->handle = __le16_to_cpu(ev->handle); + if (conn->handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + conn->handle, HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + conn->state = BT_CLOSED; + break; + } + conn->state = BT_CONNECTED; conn->type = ev->link_type; @@ -4775,8 +4782,8 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, } } - hci_connect_cfm(conn, ev->status); - if (ev->status) + hci_connect_cfm(conn, status); + if (status) hci_conn_del(conn); unlock: @@ -5527,11 +5534,6 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, struct smp_irk *irk; u8 addr_type; - if (handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_LE_Connection_Complete for invalid handle"); - return; - } - hci_dev_lock(hdev); /* All controllers implicitly stop advertising in the event of a @@ -5541,6 +5543,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn = hci_lookup_le_connect(hdev); if (!conn) { + /* In case of error status and there is no connection pending + * just unlock as there is nothing to cleanup. + */ + if (status) + goto unlock; + conn = hci_conn_add(hdev, LE_LINK, bdaddr, role); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); @@ -5603,8 +5611,14 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = ev_bdaddr_type(hdev, conn->dst_type, NULL); + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", handle, + HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + } + if (status) { - hci_le_conn_failed(conn, status); + hci_conn_failed(conn, status); goto unlock; } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 8f4c5698913d..13600bf120b0 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4408,12 +4408,21 @@ static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, static int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { + int err; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: return hci_disconnect_sync(hdev, conn, reason); case BT_CONNECT: - return hci_connect_cancel_sync(hdev, conn); + err = hci_connect_cancel_sync(hdev, conn); + /* Cleanup hci_conn object if it cannot be cancelled as it + * likelly means the controller and host stack are out of sync. + */ + if (err) + hci_conn_failed(conn, err); + + return err; case BT_CONNECT2: return hci_reject_conn_sync(hdev, conn, reason); default: diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e7b9c2636d10..af709c182674 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -108,6 +108,7 @@ struct xdp_test_data { struct page_pool *pp; struct xdp_frame **frames; struct sk_buff **skbs; + struct xdp_mem_info mem; u32 batch_size; u32 frame_cnt; }; @@ -147,7 +148,6 @@ static void xdp_test_run_init_page(struct page *page, void *arg) static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_ctx) { - struct xdp_mem_info mem = {}; struct page_pool *pp; int err = -ENOMEM; struct page_pool_params pp_params = { @@ -174,7 +174,7 @@ static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_c } /* will copy 'mem.id' into pp->xdp_mem_id */ - err = xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pp); + err = xdp_reg_mem_model(&xdp->mem, MEM_TYPE_PAGE_POOL, pp); if (err) goto err_mmodel; @@ -202,6 +202,7 @@ err_skbs: static void xdp_test_run_teardown(struct xdp_test_data *xdp) { + xdp_unreg_mem_model(&xdp->mem); page_pool_destroy(xdp->pp); kfree(xdp->frames); kfree(xdp->skbs); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 196417859c4a..68b3e850bcb9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -39,6 +39,13 @@ static int br_pass_frame_up(struct sk_buff *skb) dev_sw_netstats_rx_add(brdev, skb->len); vg = br_vlan_group_rcu(br); + + /* Reset the offload_fwd_mark because there could be a stacked + * bridge above, and it should not think this bridge it doing + * that bridge's work forwarding out its ports. + */ + br_switchdev_frame_unmark(skb); + /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc mode when someone * may be running packet capture. diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 8cc44c367231..18affda2b522 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -353,6 +353,8 @@ static int br_switchdev_vlan_attr_replay(struct net_device *br_dev, attr.orig_dev = br_dev; vg = br_vlan_group(br); + if (!vg) + return 0; list_for_each_entry(v, &vg->vlan_list, vlist) { if (v->msti) { diff --git a/net/can/isotp.c b/net/can/isotp.c index ff5d7870294e..1e7c6a460ef9 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1189,6 +1189,11 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) lock_sock(sk); + if (so->bound) { + err = -EINVAL; + goto out; + } + /* do not register frame reception for functional addressing */ if (so->opt.flags & CAN_ISOTP_SF_BROADCAST) do_rx_reg = 0; @@ -1199,10 +1204,6 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out; } - if (so->bound && addr->can_ifindex == so->ifindex && - rx_id == so->rxid && tx_id == so->txid) - goto out; - dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { err = -ENODEV; @@ -1237,22 +1238,6 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) dev_put(dev); - if (so->bound && do_rx_reg) { - /* unregister old filter */ - if (so->ifindex) { - dev = dev_get_by_index(net, so->ifindex); - if (dev) { - can_rx_unregister(net, dev, so->rxid, - SINGLE_MASK(so->rxid), - isotp_rcv, sk); - can_rx_unregister(net, dev, so->txid, - SINGLE_MASK(so->txid), - isotp_rcv_echo, sk); - dev_put(dev); - } - } - } - /* switch to new settings */ so->ifindex = ifindex; so->rxid = rx_id; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 1c5815530e0d..9d82bb42e958 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -537,43 +537,6 @@ static void request_init(struct ceph_osd_request *req) target_init(&req->r_t); } -/* - * This is ugly, but it allows us to reuse linger registration and ping - * requests, keeping the structure of the code around send_linger{_ping}() - * reasonable. Setting up a min_nr=2 mempool for each linger request - * and dealing with copying ops (this blasts req only, watch op remains - * intact) isn't any better. - */ -static void request_reinit(struct ceph_osd_request *req) -{ - struct ceph_osd_client *osdc = req->r_osdc; - bool mempool = req->r_mempool; - unsigned int num_ops = req->r_num_ops; - u64 snapid = req->r_snapid; - struct ceph_snap_context *snapc = req->r_snapc; - bool linger = req->r_linger; - struct ceph_msg *request_msg = req->r_request; - struct ceph_msg *reply_msg = req->r_reply; - - dout("%s req %p\n", __func__, req); - WARN_ON(kref_read(&req->r_kref) != 1); - request_release_checks(req); - - WARN_ON(kref_read(&request_msg->kref) != 1); - WARN_ON(kref_read(&reply_msg->kref) != 1); - target_destroy(&req->r_t); - - request_init(req); - req->r_osdc = osdc; - req->r_mempool = mempool; - req->r_num_ops = num_ops; - req->r_snapid = snapid; - req->r_snapc = snapc; - req->r_linger = linger; - req->r_request = request_msg; - req->r_reply = reply_msg; -} - struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_ops, @@ -918,14 +881,30 @@ EXPORT_SYMBOL(osd_req_op_xattr_init); * @watch_opcode: CEPH_OSD_WATCH_OP_* */ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which, - u64 cookie, u8 watch_opcode) + u8 watch_opcode, u64 cookie, u32 gen) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0); op->watch.cookie = cookie; op->watch.op = watch_opcode; - op->watch.gen = 0; + op->watch.gen = gen; +} + +/* + * prot_ver, timeout and notify payload (may be empty) should already be + * encoded in @request_pl + */ +static void osd_req_op_notify_init(struct ceph_osd_request *req, int which, + u64 cookie, struct ceph_pagelist *request_pl) +{ + struct ceph_osd_req_op *op; + + op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); + op->notify.cookie = cookie; + + ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl); + op->indata_len = request_pl->length; } /* @@ -2385,7 +2364,11 @@ again: if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) { err = -ENOSPC; } else { - pr_warn_ratelimited("FULL or reached pool quota\n"); + if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) + pr_warn_ratelimited("cluster is full (osdmap FULL)\n"); + else + pr_warn_ratelimited("pool %lld is full or reached quota\n", + req->r_t.base_oloc.pool); req->r_t.paused = true; maybe_request_map(osdc); } @@ -2727,10 +2710,13 @@ static void linger_release(struct kref *kref) WARN_ON(!list_empty(&lreq->pending_lworks)); WARN_ON(lreq->osd); - if (lreq->reg_req) - ceph_osdc_put_request(lreq->reg_req); - if (lreq->ping_req) - ceph_osdc_put_request(lreq->ping_req); + if (lreq->request_pl) + ceph_pagelist_release(lreq->request_pl); + if (lreq->notify_id_pages) + ceph_release_page_vector(lreq->notify_id_pages, 1); + + ceph_osdc_put_request(lreq->reg_req); + ceph_osdc_put_request(lreq->ping_req); target_destroy(&lreq->t); kfree(lreq); } @@ -2999,6 +2985,12 @@ static void linger_commit_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq, lreq->linger_id, req->r_result); linger_reg_commit_complete(lreq, req->r_result); @@ -3022,6 +3014,7 @@ static void linger_commit_cb(struct ceph_osd_request *req) } } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3044,6 +3037,12 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->last_error); if (req->r_result < 0) { @@ -3053,46 +3052,64 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) } } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger(struct ceph_osd_linger_request *lreq) { - struct ceph_osd_request *req = lreq->reg_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_client *osdc = lreq->osdc; + struct ceph_osd_request *req; + int ret; - verify_osdc_wrlocked(req->r_osdc); + verify_osdc_wrlocked(osdc); + mutex_lock(&lreq->lock); dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - if (req->r_osd) - cancel_linger_request(req); + if (lreq->reg_req) { + if (lreq->reg_req->r_osd) + cancel_linger_request(lreq->reg_req); + ceph_osdc_put_request(lreq->reg_req); + } + + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req); - request_reinit(req); target_copy(&req->r_t, &lreq->t); req->r_mtime = lreq->mtime; - mutex_lock(&lreq->lock); if (lreq->is_watch && lreq->committed) { - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id); - op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT; - op->watch.gen = ++lreq->register_gen; + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT, + lreq->linger_id, ++lreq->register_gen); dout("lreq %p reconnect register_gen %u\n", lreq, - op->watch.gen); + req->r_ops[0].watch.gen); req->r_callback = linger_reconnect_cb; } else { - if (!lreq->is_watch) + if (lreq->is_watch) { + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH, + lreq->linger_id, 0); + } else { lreq->notify_id = 0; - else - WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH); + + refcount_inc(&lreq->request_pl->refcnt); + osd_req_op_notify_init(req, 0, lreq->linger_id, + lreq->request_pl); + ceph_osd_data_pages_init( + osd_req_op_data(req, 0, notify, response_data), + lreq->notify_id_pages, PAGE_SIZE, 0, false, false); + } dout("lreq %p register\n", lreq); req->r_callback = linger_commit_cb; } - mutex_unlock(&lreq->lock); + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->reg_req = req; + mutex_unlock(&lreq->lock); submit_request(req, true); } @@ -3102,6 +3119,12 @@ static void linger_ping_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->ping_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->ping_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent, lreq->last_error); @@ -3117,6 +3140,7 @@ static void linger_ping_cb(struct ceph_osd_request *req) lreq->register_gen, req->r_ops[0].watch.gen); } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3124,8 +3148,8 @@ static void linger_ping_cb(struct ceph_osd_request *req) static void send_linger_ping(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; - struct ceph_osd_request *req = lreq->ping_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_request *req; + int ret; if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("%s PAUSERD\n", __func__); @@ -3137,19 +3161,26 @@ static void send_linger_ping(struct ceph_osd_linger_request *lreq) __func__, lreq, lreq->linger_id, lreq->ping_sent, lreq->register_gen); - if (req->r_osd) - cancel_linger_request(req); + if (lreq->ping_req) { + if (lreq->ping_req->r_osd) + cancel_linger_request(lreq->ping_req); + ceph_osdc_put_request(lreq->ping_req); + } - request_reinit(req); - target_copy(&req->r_t, &lreq->t); + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req); - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id || - op->watch.op != CEPH_OSD_WATCH_OP_PING); - op->watch.gen = lreq->register_gen; + target_copy(&req->r_t, &lreq->t); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id, + lreq->register_gen); req->r_callback = linger_ping_cb; + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); + req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->ping_req = req; ceph_osdc_get_request(req); account_request(req); @@ -3165,12 +3196,6 @@ static void linger_submit(struct ceph_osd_linger_request *lreq) down_write(&osdc->lock); linger_register(lreq); - if (lreq->is_watch) { - lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id; - lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id; - } else { - lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id; - } calc_target(osdc, &lreq->t, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); @@ -3202,9 +3227,9 @@ static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq) */ static void __linger_cancel(struct ceph_osd_linger_request *lreq) { - if (lreq->is_watch && lreq->ping_req->r_osd) + if (lreq->ping_req && lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); - if (lreq->reg_req->r_osd) + if (lreq->reg_req && lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); cancel_linger_map_check(lreq); unlink_linger(lreq->osd, lreq); @@ -4566,8 +4591,13 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, EXPORT_SYMBOL(ceph_osdc_start_request); /* - * Unregister a registered request. The request is not completed: - * ->r_result isn't set and __complete_request() isn't called. + * Unregister request. If @req was registered, it isn't completed: + * r_result isn't set and __complete_request() isn't invoked. + * + * If @req wasn't registered, this call may have raced with + * handle_reply(), in which case r_result would already be set and + * __complete_request() would be getting invoked, possibly even + * concurrently with this call. */ void ceph_osdc_cancel_request(struct ceph_osd_request *req) { @@ -4653,43 +4683,6 @@ again: } EXPORT_SYMBOL(ceph_osdc_sync); -static struct ceph_osd_request * -alloc_linger_request(struct ceph_osd_linger_request *lreq) -{ - struct ceph_osd_request *req; - - req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO); - if (!req) - return NULL; - - ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); - ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); - return req; -} - -static struct ceph_osd_request * -alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode) -{ - struct ceph_osd_request *req; - - req = alloc_linger_request(lreq); - if (!req) - return NULL; - - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - osd_req_op_watch_init(req, 0, 0, watch_opcode); - - if (ceph_osdc_alloc_messages(req, GFP_NOIO)) { - ceph_osdc_put_request(req); - return NULL; - } - - return req; -} - /* * Returns a handle, caller owns a ref. */ @@ -4719,18 +4712,6 @@ ceph_osdc_watch(struct ceph_osd_client *osdc, lreq->t.flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&lreq->mtime); - lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH); - if (!lreq->reg_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - - lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING); - if (!lreq->ping_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (ret) { @@ -4768,8 +4749,8 @@ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&req->r_mtime); - osd_req_op_watch_init(req, 0, lreq->linger_id, - CEPH_OSD_WATCH_OP_UNWATCH); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH, + lreq->linger_id, 0); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) @@ -4855,35 +4836,6 @@ out_put_req: } EXPORT_SYMBOL(ceph_osdc_notify_ack); -static int osd_req_op_notify_init(struct ceph_osd_request *req, int which, - u64 cookie, u32 prot_ver, u32 timeout, - void *payload, u32 payload_len) -{ - struct ceph_osd_req_op *op; - struct ceph_pagelist *pl; - int ret; - - op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); - op->notify.cookie = cookie; - - pl = ceph_pagelist_alloc(GFP_NOIO); - if (!pl) - return -ENOMEM; - - ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */ - ret |= ceph_pagelist_encode_32(pl, timeout); - ret |= ceph_pagelist_encode_32(pl, payload_len); - ret |= ceph_pagelist_append(pl, payload, payload_len); - if (ret) { - ceph_pagelist_release(pl); - return -ENOMEM; - } - - ceph_osd_data_pagelist_init(&op->notify.request_data, pl); - op->indata_len = pl->length; - return 0; -} - /* * @timeout: in seconds * @@ -4902,7 +4854,6 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, size_t *preply_len) { struct ceph_osd_linger_request *lreq; - struct page **pages; int ret; WARN_ON(!timeout); @@ -4915,41 +4866,35 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, if (!lreq) return -ENOMEM; - lreq->preply_pages = preply_pages; - lreq->preply_len = preply_len; - - ceph_oid_copy(&lreq->t.base_oid, oid); - ceph_oloc_copy(&lreq->t.base_oloc, oloc); - lreq->t.flags = CEPH_OSD_FLAG_READ; - - lreq->reg_req = alloc_linger_request(lreq); - if (!lreq->reg_req) { + lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO); + if (!lreq->request_pl) { ret = -ENOMEM; goto out_put_lreq; } - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout, - payload, payload_len); - if (ret) + ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */ + ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout); + ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len); + ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len); + if (ret) { + ret = -ENOMEM; goto out_put_lreq; + } /* for notify_id */ - pages = ceph_alloc_page_vector(1, GFP_NOIO); - if (IS_ERR(pages)) { - ret = PTR_ERR(pages); + lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO); + if (IS_ERR(lreq->notify_id_pages)) { + ret = PTR_ERR(lreq->notify_id_pages); + lreq->notify_id_pages = NULL; goto out_put_lreq; } - ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify, - response_data), - pages, PAGE_SIZE, 0, false, true); - ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO); - if (ret) - goto out_put_lreq; + lreq->preply_pages = preply_pages; + lreq->preply_len = preply_len; + + ceph_oid_copy(&lreq->t.base_oid, oid); + ceph_oloc_copy(&lreq->t.base_oloc, oloc); + lreq->t.flags = CEPH_OSD_FLAG_READ; linger_submit(lreq); ret = linger_reg_commit_wait(lreq); diff --git a/net/core/dev.c b/net/core/dev.c index 8c6c08446556..2771fd22dc6a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -681,11 +681,11 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, - .daddr = daddr, }; struct net_device_path *path; int ret = 0; + memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; @@ -10304,7 +10304,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, } EXPORT_SYMBOL(netdev_stats_to_stats64); -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) { struct net_device_core_stats __percpu *p; @@ -10315,11 +10315,7 @@ struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ - p = READ_ONCE(dev->core_stats); - if (!p) - return NULL; - - return this_cpu_ptr(p); + return READ_ONCE(dev->core_stats); } EXPORT_SYMBOL(netdev_core_stats_alloc); @@ -10356,9 +10352,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); - storage->rx_dropped += local_read(&core_stats->rx_dropped); - storage->tx_dropped += local_read(&core_stats->tx_dropped); - storage->rx_nohandler += local_read(&core_stats->rx_nohandler); + storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); + storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); + storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); } } return storage; diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 349480ef68a5..8b6b5e72b217 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -159,10 +159,8 @@ static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb) return dst->lwtstate->orig_output(net, sk, skb); } -static int xmit_check_hhlen(struct sk_buff *skb) +static int xmit_check_hhlen(struct sk_buff *skb, int hh_len) { - int hh_len = skb_dst(skb)->dev->hard_header_len; - if (skb_headroom(skb) < hh_len) { int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); @@ -274,6 +272,7 @@ static int bpf_xmit(struct sk_buff *skb) bpf = bpf_lwt_lwtunnel(dst->lwtstate); if (bpf->xmit.prog) { + int hh_len = dst->dev->hard_header_len; __be16 proto = skb->protocol; int ret; @@ -291,7 +290,7 @@ static int bpf_xmit(struct sk_buff *skb) /* If the header was expanded, headroom might be too * small for L2 header to come, expand as needed. */ - ret = xmit_check_hhlen(skb); + ret = xmit_check_hhlen(skb, hh_len); if (unlikely(ret)) return ret; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 9b8443774449..5f85e01d4093 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -22,6 +22,8 @@ static siphash_aligned_key_t net_secret; static siphash_aligned_key_t ts_secret; +#define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) + static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); @@ -94,17 +96,19 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, } EXPORT_SYMBOL(secure_tcpv6_seq); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) { const struct { struct in6_addr saddr; struct in6_addr daddr; + unsigned int timeseed; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, - .dport = dport + .timeseed = jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, + .dport = dport, }; net_secret_init(); return siphash(&combined, offsetofend(typeof(combined), dport), @@ -142,11 +146,13 @@ u32 secure_tcp_seq(__be32 saddr, __be32 daddr, } EXPORT_SYMBOL_GPL(secure_tcp_seq); -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { net_secret_init(); - return siphash_3u32((__force u32)saddr, (__force u32)daddr, - (__force u16)dport, &net_secret); + return siphash_4u32((__force u32)saddr, (__force u32)daddr, + (__force u16)dport, + jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, + &net_secret); } EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); #endif diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 30b523fa4ad2..c90c74de90d5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3897,7 +3897,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; - int err; + int len_diff, err; skb_push(skb, -skb_network_offset(skb) + offset); @@ -3937,9 +3937,11 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); + len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb); __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); + nskb->transport_header += len_diff; skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ae662567a6cb..0ea29270d7e5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1030,9 +1030,15 @@ static void __net_exit dccp_v4_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v4_ctl_sk); } +static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&dccp_hashinfo, AF_INET); +} + static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, + .exit_batch = dccp_v4_exit_batch, .id = &dccp_v4_pernet_id, .size = sizeof(struct dccp_v4_pernet), }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index eab3bd1ee9a0..fa663518fa0e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1115,9 +1115,15 @@ static void __net_exit dccp_v6_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v6_ctl_sk); } +static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&dccp_hashinfo, AF_INET6); +} + static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, + .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 0ee7d4c0c955..a09ba642b5e7 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -854,7 +854,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) memcpy(msg->neighbor, dn_hiord, ETH_ALEN); if (dn_db->router) { - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; + struct dn_neigh *dn = container_of(dn_db->router, struct dn_neigh, n); dn_dn2eth(msg->neighbor, dn->addr); } @@ -902,7 +902,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) { int n; struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; + struct dn_neigh *dn = container_of(dn_db->router, struct dn_neigh, n); struct sk_buff *skb; size_t size; unsigned char *ptr; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 94b306f6d551..fbd98ac853ea 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -426,7 +426,8 @@ int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb) if (!dn_db->router) { dn_db->router = neigh_clone(neigh); } else { - if (msg->priority > ((struct dn_neigh *)dn_db->router)->priority) + if (msg->priority > container_of(dn_db->router, + struct dn_neigh, n)->priority) neigh_release(xchg(&dn_db->router, neigh_clone(neigh))); } } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 7e85f2a1ae25..d1d78a463a06 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1120,7 +1120,7 @@ source_ok: /* Ok then, we assume its directly connected and move on */ select_source: if (neigh) - gateway = ((struct dn_neigh *)neigh)->addr; + gateway = container_of(neigh, struct dn_neigh, n)->addr; if (gateway == 0) gateway = fld.daddr; if (fld.saddr == 0) { @@ -1429,7 +1429,7 @@ static int dn_route_input_slow(struct sk_buff *skb) /* Use the default router if there is one */ neigh = neigh_clone(dn_db->router); if (neigh) { - gateway = ((struct dn_neigh *)neigh)->addr; + gateway = container_of(neigh, struct dn_neigh, n)->addr; goto make_route; } diff --git a/net/dsa/port.c b/net/dsa/port.c index 32d472a82241..bdccb613285d 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -451,6 +451,7 @@ out_rollback_unoffload: switchdev_bridge_port_unoffload(brport_dev, dp, &dsa_slave_switchdev_notifier, &dsa_slave_switchdev_blocking_notifier); + dsa_flush_workqueue(); out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); out_rollback: @@ -1620,8 +1621,10 @@ int dsa_port_link_register_of(struct dsa_port *dp) if (ds->ops->phylink_mac_link_down) ds->ops->phylink_mac_link_down(ds, port, MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); + of_node_put(phy_np); return dsa_port_phylink_register(dp); } + of_node_put(phy_np); return 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 41c69a6e7854..8022d50584db 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -285,7 +285,7 @@ static void dsa_port_manage_cpu_flood(struct dsa_port *dp) if (other_dp->slave->flags & IFF_ALLMULTI) flags.val |= BR_MCAST_FLOOD; if (other_dp->slave->flags & IFF_PROMISC) - flags.val |= BR_FLOOD; + flags.val |= BR_FLOOD | BR_MCAST_FLOOD; } err = dsa_port_pre_bridge_flags(dp, flags, NULL); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 2ad3c7b42d6d..1d9e6d5e9a76 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2403,9 +2403,10 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } rcu_assign_pointer(pmc->sflist, newpsl); + if (psl) + kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ @@ -2507,11 +2508,13 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); - } else + } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); + } rcu_assign_pointer(pmc->sflist, newpsl); + if (psl) + kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 17440840a791..a5d57fa679ca 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -504,7 +504,7 @@ not_unique: return -EADDRNOTAVAIL; } -static u32 inet_sk_port_offset(const struct sock *sk) +static u64 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -726,15 +726,17 @@ EXPORT_SYMBOL_GPL(inet_unhash); * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this * property might be used by clever attacker. - * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, - * we use 256 instead to really give more isolation and - * privacy, this only consumes 1 KB of kernel memory. + * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though + * attacks were since demonstrated, thus we use 65536 instead to really + * give more isolation and privacy, at the expense of 256kB of kernel + * memory. */ -#define INET_TABLE_PERTURB_SHIFT 8 -static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT]; +#define INET_TABLE_PERTURB_SHIFT 16 +#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT) +static u32 *table_perturb; int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)) { @@ -774,10 +776,13 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U; - net_get_random_once(table_perturb, sizeof(table_perturb)); - index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); + net_get_random_once(table_perturb, + INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); + index = port_offset & (INET_TABLE_PERTURB_SIZE - 1); + + offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); + offset %= remaining; - offset = (READ_ONCE(table_perturb[index]) + port_offset) % remaining; /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. */ @@ -831,11 +836,12 @@ next_port: return -EADDRNOTAVAIL; ok: - /* If our first attempt found a candidate, skip next candidate - * in 1/16 of cases to add some noise. + /* Here we want to add a little bit of randomness to the next source + * port that will be chosen. We use a max() with a random here so that + * on low contention the randomness is maximal and on high contention + * it may be inexistent. */ - if (!i && !(prandom_u32() % 16)) - i = 2; + i = max_t(int, i, (prandom_u32() & 7) * 2); WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ @@ -859,7 +865,7 @@ ok: int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - u32 port_offset = 0; + u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet_sk_port_offset(sk); @@ -909,6 +915,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, low_limit, high_limit); init_hashinfo_lhash2(h); + + /* this one is used for source ports of outgoing connections */ + table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE, + sizeof(*table_perturb), GFP_KERNEL); + if (!table_perturb) + panic("TCP: failed to alloc table_perturb"); } int inet_hashinfo2_init_mod(struct inet_hashinfo *h) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 9e0bbd026560..0ec501845cb3 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -52,7 +52,8 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) spin_unlock(lock); /* Disassociate with bind bucket. */ - bhead = &hashinfo->bhash[tw->tw_bslot]; + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, + hashinfo->bhash_size)]; spin_lock(&bhead->lock); inet_twsk_bind_unhash(tw, hashinfo); @@ -111,12 +112,8 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ - /* Cache inet_bhashfn(), because 'struct net' might be no longer - * available later in inet_twsk_kill(). - */ - tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num, - hashinfo->bhash_size); - bhead = &hashinfo->bhash[tw->tw_bslot]; + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, + hashinfo->bhash_size)]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); @@ -257,3 +254,50 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); + +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) +{ + struct inet_timewait_sock *tw; + struct sock *sk; + struct hlist_nulls_node *node; + unsigned int slot; + + for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; +restart_rcu: + cond_resched(); + rcu_read_lock(); +restart: + sk_nulls_for_each_rcu(sk, node, &head->chain) { + if (sk->sk_state != TCP_TIME_WAIT) + continue; + tw = inet_twsk(sk); + if ((tw->tw_family != family) || + refcount_read(&twsk_net(tw)->ns.count)) + continue; + + if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + continue; + + if (unlikely((tw->tw_family != family) || + refcount_read(&twsk_net(tw)->ns.count))) { + inet_twsk_put(tw); + goto restart; + } + + rcu_read_unlock(); + local_bh_disable(); + inet_twsk_deschedule_put(tw); + local_bh_enable(); + goto restart_rcu; + } + /* If the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto restart; + rcu_read_unlock(); + } +} +EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 365caebf51ab..aacee9dd771b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -459,14 +459,12 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, - tunnel->parms.o_flags, proto, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + flags, proto, tunnel->parms.o_key, + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -504,7 +502,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -581,7 +579,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) } gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ /dev/null diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 3ee947557b88..aa9a11b20d18 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -305,6 +305,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; + u32 tb_id = RT_TABLE_LOCAL; int chk_addr_ret; if (addr_len < sizeof(*addr)) @@ -318,7 +319,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; + chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); if (!inet_addr_valid_or_nonlocal(net, inet_sk(sk), addr->sin_addr.s_addr, @@ -355,6 +357,14 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return -ENODEV; } } + + if (!dev && sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + } has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev, scoped); rcu_read_unlock(); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 98c6f3429593..ed01063d8f30 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1726,6 +1726,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; struct rtable *rth; + bool no_policy; u32 itag = 0; int err; @@ -1736,8 +1737,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (our) flags |= RTCF_LOCAL; + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, - IN_DEV_ORCONF(in_dev, NOPOLICY), false); + no_policy, false); if (!rth) return -ENOBUFS; @@ -1753,6 +1758,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif RT_CACHE_STAT_INC(in_slow_mc); + skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return 0; } @@ -1795,7 +1801,7 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - bool do_cache; + bool do_cache, no_policy; u32 itag = 0; /* get a working reference to the output device */ @@ -1840,6 +1846,10 @@ static int __mkroute_input(struct sk_buff *skb, } } + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) @@ -1852,8 +1862,7 @@ static int __mkroute_input(struct sk_buff *skb, } } - rth = rt_dst_alloc(out_dev->dev, 0, res->type, - IN_DEV_ORCONF(in_dev, NOPOLICY), + rth = rt_dst_alloc(out_dev->dev, 0, res->type, no_policy, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; @@ -2228,6 +2237,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct rtable *rth; struct flowi4 fl4; bool do_cache = true; + bool no_policy; /* IP on this device is disabled. */ @@ -2346,6 +2356,10 @@ brd_input: RT_CACHE_STAT_INC(in_brd); local_input: + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); @@ -2360,7 +2374,7 @@ local_input: rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, - IN_DEV_ORCONF(in_dev, NOPOLICY), false); + no_policy, false); if (!rth) goto e_nobufs; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2cb3b852d148..f33c31dd7366 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -281,6 +281,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, EXPORT_SYMBOL(cookie_ecn_ok); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { @@ -297,6 +298,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return NULL; treq = tcp_rsk(req); + + /* treq->af_specific might be used to perform TCP_MD5 lookup */ + treq->af_specific = af_ops; + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); @@ -364,7 +369,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2088f93fa37b..60f99e9fb6d1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3867,7 +3867,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_process_tlp_ack(sk, ack, flag); if (tcp_ack_is_dubious(sk, flag)) { - if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) { + if (!(flag & (FLAG_SND_UNA_ADVANCED | + FLAG_NOT_DUP | FLAG_DSACKING_ACK))) { num_dupack = 1; /* Consider if pure acks were aggregated in tcp_add_backlog() */ if (!(flag & FLAG_DATA)) @@ -5454,7 +5455,17 @@ static void tcp_new_space(struct sock *sk) INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); } -static void tcp_check_space(struct sock *sk) +/* Caller made space either from: + * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced) + * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt) + * + * We might be able to generate EPOLLOUT to the application if: + * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2 + * 2) notsent amount (tp->write_seq - tp->snd_nxt) became + * small enough that tcp_stream_memory_free() decides it + * is time to generate EPOLLOUT. + */ +void tcp_check_space(struct sock *sk) { /* pairs with tcp_poll() */ smp_mb(); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f9cec624068d..457f5b5d5d4a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3173,6 +3173,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; + inet_twsk_purge(&tcp_hashinfo, AF_INET); + list_for_each_entry(net, net_exit_list, exit_list) tcp_fastopen_ctx_destroy(net); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6366df7aaf2a..6854bb1fb32b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -531,7 +531,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) + if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req))) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9ede847f4199..1ca2f28c9981 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -82,6 +82,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); + tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index fbab921670cc..9a8e014d9b5b 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -74,27 +74,32 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) * * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is * called multiple times. We favor the information from the most recently - * sent skb, i.e., the skb with the highest prior_delivered count. + * sent skb, i.e., the skb with the most recently sent time and the highest + * sequence. */ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + u64 tx_tstamp; if (!scb->tx.delivered_mstamp) return; + tx_tstamp = tcp_skb_timestamp_us(skb); if (!rs->prior_delivered || - after(scb->tx.delivered, rs->prior_delivered)) { + tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp, + scb->end_seq, rs->last_end_seq)) { rs->prior_delivered_ce = scb->tx.delivered_ce; rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; + rs->last_end_seq = scb->end_seq; /* Record send time of most recently ACKed packet: */ - tp->first_tx_mstamp = tcp_skb_timestamp_us(skb); + tp->first_tx_mstamp = tx_tstamp; /* Find the duration of the "send phase" of this window: */ rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp, scb->tx.first_tx_mstamp); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 4740afecf7c6..32ccac10bd62 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -308,7 +308,7 @@ not_unique: return -EADDRNOTAVAIL; } -static u32 inet6_sk_port_offset(const struct sock *sk) +static u64 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -320,7 +320,7 @@ static u32 inet6_sk_port_offset(const struct sock *sk) int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - u32 port_offset = 0; + u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet6_sk_port_offset(sk); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 976236736146..5136959b3dc5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -724,6 +724,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, { struct ip6_tnl *tunnel = netdev_priv(dev); __be16 protocol; + __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -739,7 +740,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, if (tunnel->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; - __be16 flags; int tun_hlen; tun_info = skb_tunnel_info_txcheck(skb); @@ -766,19 +766,19 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; - if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) return -ENOMEM; - gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + flags = tunnel->parms.o_flags; + + gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) + : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -1056,7 +1056,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* Push GRE header. */ proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) : htons(ETH_P_ERSPAN2); - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 909f937befd7..7f695c39d9a8 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -460,10 +460,10 @@ int ip6_mc_source(int add, int omode, struct sock *sk, newpsl->sl_addr[i] = psl->sl_addr[i]; atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); psl = newpsl; - rcu_assign_pointer(pmc->sflist, psl); } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { @@ -565,12 +565,12 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, psl->sl_count, psl->sl_addr, 0); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); } - mutex_unlock(&idev->mc_lock); rcu_assign_pointer(pmc->sflist, newpsl); + mutex_unlock(&idev->mc_lock); + kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 1da332450d98..8ce60ab89015 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,14 +24,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff { const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *sk = sk_to_full_sk(sk_partial); + struct net_device *dev = skb_dst(skb)->dev; struct flow_keys flkeys; unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { - .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, @@ -39,6 +38,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff }; int err; + if (sk && sk->sk_bound_dev_if) + fl6.flowi6_oif = sk->sk_bound_dev_if; + else if (strict) + fl6.flowi6_oif = dev->ifindex; + else + fl6.flowi6_oif = l3mdev_master_ifindex(dev); + fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys); dst = ip6_route_output(net, sk, &fl6); err = dst->error; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index d1b61d00368e..9cc123f000fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 13678d3908fa..faaddaf43c90 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2207,9 +2207,15 @@ static void __net_exit tcpv6_net_exit(struct net *net) inet_ctl_sock_destroy(net->ipv6.tcp_sk); } +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, AF_INET6); +} + static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/key/af_key.c b/net/key/af_key.c index fd51db3be91c..339d95df19d3 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2826,8 +2826,10 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, - BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, + BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + if (err) + return err; memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs); @@ -2898,7 +2900,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg)) + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2916,7 +2918,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg))) + if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; for (k = 1; ; k++) { @@ -2927,7 +2929,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg)) + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 1b30c724ca8d..dc8aec1a5d3d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3657,6 +3657,12 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, cbss->transmitted_bss->bssid); bss_conf->bssid_indicator = cbss->max_bssid_indicator; bss_conf->bssid_index = cbss->bssid_index; + } else { + bss_conf->nontransmitted = false; + memset(bss_conf->transmitter_bssid, 0, + sizeof(bss_conf->transmitter_bssid)); + bss_conf->bssid_indicator = 0; + bss_conf->bssid_index = 0; } /* diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index beb6b92eb780..88d797fa82ff 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1405,8 +1405,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, goto dont_reorder; /* not part of a BA session */ - if (ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK && - ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_NORMAL) + if (ack_policy == IEEE80211_QOS_CTL_ACK_POLICY_NOACK) goto dont_reorder; /* new, potentially un-ordered, ampdu frame - process it */ diff --git a/net/mctp/device.c b/net/mctp/device.c index f49be882e98e..99a3bda8852f 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -313,6 +313,7 @@ void mctp_dev_hold(struct mctp_dev *mdev) void mctp_dev_put(struct mctp_dev *mdev) { if (mdev && refcount_dec_and_test(&mdev->refs)) { + kfree(mdev->addrs); dev_put(mdev->dev); kfree_rcu(mdev, rcu); } @@ -441,7 +442,6 @@ static void mctp_unregister(struct net_device *dev) mctp_route_remove_dev(mdev); mctp_neigh_remove_dev(mdev); - kfree(mdev->addrs); mctp_dev_put(mdev); } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 325383646f5c..b548cec86c9d 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -107,7 +107,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; } if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { - mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum = get_unaligned((__force __sum16 *)ptr); mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } @@ -221,7 +221,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; - mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum = get_unaligned((__force __sum16 *)ptr); ptr += 2; } @@ -1240,7 +1240,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } -u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) +__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) { struct csum_pseudo_header header; __wsum csum; @@ -1256,15 +1256,25 @@ u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) header.csum = 0; csum = csum_partial(&header, sizeof(header), sum); - return (__force u16)csum_fold(csum); + return csum_fold(csum); } -static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +static __sum16 mptcp_make_csum(const struct mptcp_ext *mpext) { return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len, ~csum_unfold(mpext->csum)); } +static void put_len_csum(u16 len, __sum16 csum, void *data) +{ + __sum16 *sumptr = data + 2; + __be16 *ptr = data; + + put_unaligned_be16(len, ptr); + + put_unaligned(csum, sumptr); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { @@ -1340,8 +1350,9 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; if (opts->csum_reqd) { - put_unaligned_be32(mpext->data_len << 16 | - mptcp_make_csum(mpext), ptr); + put_len_csum(mpext->data_len, + mptcp_make_csum(mpext), + ptr); } else { put_unaligned_be32(mpext->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); @@ -1392,11 +1403,12 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, goto mp_capable_done; if (opts->csum_reqd) { - put_unaligned_be32(opts->data_len << 16 | - __mptcp_make_csum(opts->data_seq, - opts->subflow_seq, - opts->data_len, - ~csum_unfold(opts->csum)), ptr); + put_len_csum(opts->data_len, + __mptcp_make_csum(opts->data_seq, + opts->subflow_seq, + opts->data_len, + ~csum_unfold(opts->csum)), + ptr); } else { put_unaligned_be32(opts->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 01809eef29b4..aa51b100e033 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -178,14 +178,13 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, struct mptcp_pm_data *pm = &msk->pm; bool update_subflows; - update_subflows = (ssk->sk_state == TCP_CLOSE) && - (subflow->request_join || subflow->mp_join); + update_subflows = subflow->request_join || subflow->mp_join; if (!READ_ONCE(pm->work_pending) && !update_subflows) return; spin_lock_bh(&pm->lock); if (update_subflows) - pm->subflows--; + __mptcp_pm_close_subflow(msk); /* Even if this subflow is not really established, tell the PM to try * to pick the next ones, if possible. diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3c1a3036550f..5655a63aa6a8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -443,7 +443,8 @@ struct mptcp_subflow_context { can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1; /* local_id is correctly initialized */ + local_id_valid : 1, /* local_id is correctly initialized */ + valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; @@ -723,7 +724,7 @@ void mptcp_token_destroy(struct mptcp_sock *msk); void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn); void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac); -u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum); +__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum); void __init mptcp_pm_init(void); void mptcp_pm_data_init(struct mptcp_sock *msk); @@ -833,6 +834,20 @@ unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk); +/* called under PM lock */ +static inline void __mptcp_pm_close_subflow(struct mptcp_sock *msk) +{ + if (--msk->pm.subflows < mptcp_pm_get_subflows_max(msk)) + WRITE_ONCE(msk->pm.accept_subflow, true); +} + +static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk) +{ + spin_lock_bh(&msk->pm.lock); + __mptcp_pm_close_subflow(msk); + spin_unlock_bh(&msk->pm.lock); +} + void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index aba260f547da..be76ada89d96 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -888,7 +888,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); u32 offset, seq, delta; - u16 csum; + __sum16 csum; int len; if (!csum_reqd) @@ -955,11 +955,14 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * subflow->map_data_csum); if (unlikely(csum)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); - subflow->send_mp_fail = 1; - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); + if (subflow->mp_join || subflow->valid_csum_seen) { + subflow->send_mp_fail = 1; + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); + } return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; } + subflow->valid_csum_seen = 1; return MAPPING_OK; } @@ -1141,6 +1144,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss } } +static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) +{ + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + if (subflow->mp_join) + return false; + else if (READ_ONCE(msk->csum_enabled)) + return !subflow->valid_csum_seen; + else + return !subflow->fully_established; +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1218,7 +1233,7 @@ fallback: return true; } - if (subflow->mp_join || subflow->fully_established) { + if (!subflow_can_fallback(subflow)) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ @@ -1422,20 +1437,20 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, struct sockaddr_storage addr; int remote_id = remote->id; int local_id = loc->id; + int err = -ENOTCONN; struct socket *sf; struct sock *ssk; u32 remote_token; int addrlen; int ifindex; u8 flags; - int err; if (!mptcp_is_fully_established(sk)) - return -ENOTCONN; + goto err_out; err = mptcp_subflow_create_socket(sk, &sf); if (err) - return err; + goto err_out; ssk = sf->sk; subflow = mptcp_subflow_ctx(ssk); @@ -1492,6 +1507,12 @@ failed_unlink: failed: subflow->disposable = 1; sock_release(sf); + +err_out: + /* we account subflows before the creation, and this failures will not + * be caught by sk_state_change() + */ + mptcp_pm_close_subflow(msk); return err; } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 2c467c422dc6..fb67f1ca2495 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,7 +1495,7 @@ int __init ip_vs_conn_init(void) pr_info("Connection hash table configured " "(size=%d, memory=%ldKbytes)\n", ip_vs_conn_tab_size, - (long)(ip_vs_conn_tab_size*sizeof(struct list_head))/1024); + (long)(ip_vs_conn_tab_size*sizeof(*ip_vs_conn_tab))/1024); IP_VS_DBG(0, "Each connection entry needs %zd bytes at least\n", sizeof(struct ip_vs_conn)); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 8ec55cd72572..204a5cdff5b1 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -556,24 +556,14 @@ static bool tcp_in_window(struct nf_conn *ct, } } - } else if (((state->state == TCP_CONNTRACK_SYN_SENT - && dir == IP_CT_DIR_ORIGINAL) - || (state->state == TCP_CONNTRACK_SYN_RECV - && dir == IP_CT_DIR_REPLY)) - && after(end, sender->td_end)) { + } else if (tcph->syn && + after(end, sender->td_end) && + (state->state == TCP_CONNTRACK_SYN_SENT || + state->state == TCP_CONNTRACK_SYN_RECV)) { /* * RFC 793: "if a TCP is reinitialized ... then it need * not wait at all; it must only be sure to use sequence * numbers larger than those recently used." - */ - sender->td_end = - sender->td_maxend = end; - sender->td_maxwin = (win == 0 ? 1 : win); - - tcp_options(skb, dataoff, tcph, sender); - } else if (tcph->syn && dir == IP_CT_DIR_REPLY && - state->state == TCP_CONNTRACK_SYN_SENT) { - /* Retransmitted syn-ack, or syn (simultaneous open). * * Re-init state for this direction, just like for the first * syn(-ack) reply, it might differ in seq, ack or tcp options. @@ -581,7 +571,8 @@ static bool tcp_in_window(struct nf_conn *ct, tcp_init_sender(sender, receiver, skb, dataoff, tcph, end, win); - if (!tcph->ack) + + if (dir == IP_CT_DIR_REPLY && !tcph->ack) return true; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 3e1afd10a9b6..55aa55b252b2 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -823,7 +823,7 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, -#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD) +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = { .procname = "nf_flowtable_udp_timeout", .maxlen = sizeof(unsigned int), diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 3db256da919b..f2def06d1070 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -179,12 +179,11 @@ EXPORT_SYMBOL_GPL(flow_offload_route_init); static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) { - tcp->state = TCP_CONNTRACK_ESTABLISHED; tcp->seen[0].td_maxwin = 0; tcp->seen[1].td_maxwin = 0; } -static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) +static void flow_offload_fixup_ct(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); @@ -193,7 +192,9 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + flow_offload_fixup_tcp(&ct->proto.tcp); + + timeout = tn->timeouts[ct->proto.tcp.state]; timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); @@ -211,18 +212,6 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout); } -static void flow_offload_fixup_ct_state(struct nf_conn *ct) -{ - if (nf_ct_protonum(ct) == IPPROTO_TCP) - flow_offload_fixup_tcp(&ct->proto.tcp); -} - -static void flow_offload_fixup_ct(struct nf_conn *ct) -{ - flow_offload_fixup_ct_state(ct); - flow_offload_fixup_ct_timeout(ct); -} - static void flow_offload_route_release(struct flow_offload *flow) { nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); @@ -335,8 +324,10 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); - if (READ_ONCE(flow->timeout) != timeout) + if (timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); + else + return; if (likely(!nf_flowtable_hw_offload(flow_table))) return; @@ -359,22 +350,14 @@ static void flow_offload_del(struct nf_flowtable *flow_table, rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, nf_flow_offload_rhash_params); - - clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); - - if (nf_flow_has_expired(flow)) - flow_offload_fixup_ct(flow->ct); - else - flow_offload_fixup_ct_timeout(flow->ct); - flow_offload_free(flow); } void flow_offload_teardown(struct flow_offload *flow) { + clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); set_bit(NF_FLOW_TEARDOWN, &flow->flags); - - flow_offload_fixup_ct_state(flow->ct); + flow_offload_fixup_ct(flow->ct); } EXPORT_SYMBOL_GPL(flow_offload_teardown); @@ -438,33 +421,12 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } -static bool flow_offload_stale_dst(struct flow_offload_tuple *tuple) -{ - struct dst_entry *dst; - - if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || - tuple->xmit_type == FLOW_OFFLOAD_XMIT_XFRM) { - dst = tuple->dst_cache; - if (!dst_check(dst, tuple->dst_cookie)) - return true; - } - - return false; -} - -static bool nf_flow_has_stale_dst(struct flow_offload *flow) -{ - return flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple) || - flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple); -} - static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || - nf_ct_is_dying(flow->ct) || - nf_flow_has_stale_dst(flow)) - set_bit(NF_FLOW_TEARDOWN, &flow->flags); + nf_ct_is_dying(flow->ct)) + flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { if (test_bit(NF_FLOW_HW, &flow->flags)) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 32c0eb1b4821..b350fe9d00b0 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -248,6 +248,15 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) return true; } +static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple) +{ + if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH && + tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM) + return true; + + return dst_check(tuple->dst_cache, tuple->dst_cookie); +} + static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, const struct nf_hook_state *state, struct dst_entry *dst) @@ -367,6 +376,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, iph->protocol, skb, thoff)) return NF_ACCEPT; + if (!nf_flow_dst_check(&tuplehash->tuple)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; @@ -624,6 +638,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff)) return NF_ACCEPT; + if (!nf_flow_dst_check(&tuplehash->tuple)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 16c3a39689f4..a096b9fbbbdf 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8342,16 +8342,7 @@ EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work); static bool nft_expr_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { - if (!expr->ops->reduce) { - pr_warn_once("missing reduce for expression %s ", - expr->ops->type->name); - return false; - } - - if (nft_reduce_is_readonly(expr)) - return false; - - return expr->ops->reduce(track, expr); + return false; } static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 900d48c810a1..6f0b07fe648d 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -36,6 +36,15 @@ static void nft_default_forward_path(struct nf_flow_route *route, route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } +static bool nft_is_valid_ether_device(const struct net_device *dev) +{ + if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || + dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) + return false; + + return true; +} + static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, @@ -47,6 +56,9 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, struct neighbour *n; u8 nud_state; + if (!nft_is_valid_ether_device(dev)) + goto out; + n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; @@ -60,6 +72,7 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, if (!(nud_state & NUD_VALID)) return -1; +out: return dev_fill_forward_path(dev, ha, stack); } @@ -78,15 +91,6 @@ struct nft_forward_info { enum flow_offload_xmit_type xmit_type; }; -static bool nft_is_valid_ether_device(const struct net_device *dev) -{ - if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || - dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) - return false; - - return true; -} - static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) @@ -119,7 +123,8 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, info->indev = NULL; break; } - info->outdev = path->dev; + if (!info->outdev) + info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; @@ -293,7 +298,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); - if (unlikely(!tcph || tcph->fin || tcph->rst)) + if (unlikely(!tcph || tcph->fin || tcph->rst || + !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index d600a566da32..7325bee7d144 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -349,7 +349,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, *ext = &rbe->ext; return -EEXIST; } else { - p = &parent->rb_left; + overlap = false; + if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; } } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 6d9e8e0a3a7d..05ae5a338b6f 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -54,6 +54,32 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo } #endif +static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) +{ + const struct net_device *indev = nft_in(pkt); + const struct sk_buff *skb = pkt->skb; + struct sock *sk = NULL; + + if (!indev) + return NULL; + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, indev); + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, indev); + break; +#endif + default: + WARN_ON_ONCE(1); + break; + } + + return sk; +} + static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -67,20 +93,7 @@ static void nft_socket_eval(const struct nft_expr *expr, sk = NULL; if (!sk) - switch(nft_pf(pkt)) { - case NFPROTO_IPV4: - sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt)); - break; -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) - case NFPROTO_IPV6: - sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt)); - break; -#endif - default: - WARN_ON_ONCE(1); - regs->verdict.code = NFT_BREAK; - return; - } + sk = nft_socket_do_lookup(pkt); if (!sk) { regs->verdict.code = NFT_BREAK; @@ -224,6 +237,16 @@ static bool nft_socket_reduce(struct nft_regs_track *track, return nft_expr_reduce_bitwise(track, expr); } +static int nft_socket_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT)); +} + static struct nft_expr_type nft_socket_type; static const struct nft_expr_ops nft_socket_ops = { .type = &nft_socket_type, @@ -231,6 +254,7 @@ static const struct nft_expr_ops nft_socket_ops = { .eval = nft_socket_eval, .init = nft_socket_init, .dump = nft_socket_dump, + .validate = nft_socket_validate, .reduce = nft_socket_reduce, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 05a3795eac8e..73e9c0a9c187 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1975,7 +1975,6 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, copied = len; } - skb_reset_transport_header(data_skb); err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { diff --git a/net/nfc/core.c b/net/nfc/core.c index dc7a2404efdf..5b286e1e0a6f 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -38,7 +38,7 @@ int nfc_fw_download(struct nfc_dev *dev, const char *firmware_name) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -94,7 +94,7 @@ int nfc_dev_up(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -142,7 +142,7 @@ int nfc_dev_down(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -207,7 +207,7 @@ int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -246,7 +246,7 @@ int nfc_stop_poll(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -291,7 +291,7 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -335,7 +335,7 @@ int nfc_dep_link_down(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -401,7 +401,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -448,7 +448,7 @@ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -495,7 +495,7 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb, device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; kfree_skb(skb); goto error; @@ -552,7 +552,7 @@ int nfc_enable_se(struct nfc_dev *dev, u32 se_idx) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -601,7 +601,7 @@ int nfc_disable_se(struct nfc_dev *dev, u32 se_idx) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -1134,6 +1134,7 @@ int nfc_register_device(struct nfc_dev *dev) dev->rfkill = NULL; } } + dev->shutting_down = false; device_unlock(&dev->dev); rc = nfc_genl_device_added(dev); @@ -1166,12 +1167,10 @@ void nfc_unregister_device(struct nfc_dev *dev) rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); } + dev->shutting_down = true; device_unlock(&dev->dev); if (dev->ops->check_presence) { - device_lock(&dev->dev); - dev->shutting_down = true; - device_unlock(&dev->dev); del_timer_sync(&dev->check_pres_timer); cancel_work_sync(&dev->check_pres_work); } diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 6055dc9a82aa..aa5e712adf07 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -118,7 +118,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev, skb_frag = nci_skb_alloc(ndev, (NCI_DATA_HDR_SIZE + frag_len), - GFP_KERNEL); + GFP_ATOMIC); if (skb_frag == NULL) { rc = -ENOMEM; goto free_exit; diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 19703a649b5a..78c4b6addf15 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -153,7 +153,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, i = 0; skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; @@ -184,7 +184,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, if (i < data_len) { skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index f184b0db79d4..7c62417ccfd7 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1244,7 +1244,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; @@ -1260,7 +1260,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, genlmsg_end(msg, hdr); - genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); + genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 5327d130c4b5..73ee2771093d 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -487,14 +487,27 @@ struct rds_tcp_net { /* All module specific customizations to the RDS-TCP socket should be done in * rds_tcp_tune() and applied after socket creation. */ -void rds_tcp_tune(struct socket *sock) +bool rds_tcp_tune(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); - struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + struct rds_tcp_net *rtn; tcp_sock_set_nodelay(sock->sk); lock_sock(sk); + /* TCP timer functions might access net namespace even after + * a process which created this net namespace terminated. + */ + if (!sk->sk_net_refcnt) { + if (!maybe_get_net(net)) { + release_sock(sk); + return false; + } + sk->sk_net_refcnt = 1; + netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); + } + rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { sk->sk_sndbuf = rtn->sndbuf_size; sk->sk_userlocks |= SOCK_SNDBUF_LOCK; @@ -504,6 +517,7 @@ void rds_tcp_tune(struct socket *sock) sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } release_sock(sk); + return true; } static void rds_tcp_accept_worker(struct work_struct *work) diff --git a/net/rds/tcp.h b/net/rds/tcp.h index dc8d745d6857..f8b5930d7b34 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -49,7 +49,7 @@ struct rds_tcp_statistics { }; /* tcp.c */ -void rds_tcp_tune(struct socket *sock); +bool rds_tcp_tune(struct socket *sock); void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp); void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp); void rds_tcp_restore_callbacks(struct socket *sock, diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 5461d77fff4f..f0c477c5d1db 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -124,7 +124,10 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) if (ret < 0) goto out; - rds_tcp_tune(sock); + if (!rds_tcp_tune(sock)) { + ret = -EINVAL; + goto out; + } if (isv6) { sin6.sin6_family = AF_INET6; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 09cadd556d1e..7edf2e69d3fe 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -133,7 +133,10 @@ int rds_tcp_accept_one(struct socket *sock) __module_get(new_sock->ops->owner); rds_tcp_keepalive(new_sock); - rds_tcp_tune(new_sock); + if (!rds_tcp_tune(new_sock)) { + ret = -EINVAL; + goto out; + } inet = inet_sk(new_sock->sk); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index a4111408ffd0..6a1611b0e303 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -117,6 +117,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) local, srx->transport_type, srx->transport.family); udp_conf.family = srx->transport.family; + udp_conf.use_udp_checksums = true; if (udp_conf.family == AF_INET) { udp_conf.local_ip = srx->transport.sin.sin_addr; udp_conf.local_udp_port = srx->transport.sin.sin_port; @@ -124,6 +125,8 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } else { udp_conf.local_ip6 = srx->transport.sin6.sin6_addr; udp_conf.local_udp_port = srx->transport.sin6.sin6_port; + udp_conf.use_udp6_tx_checksums = true; + udp_conf.use_udp6_rx_checksums = true; #endif } ret = udp_sock_create(net, &udp_conf, &local->socket); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 31fcd279c177..211c757bfc3c 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -149,7 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *pattr; struct tcf_pedit *p; int ret = 0, err; - int ksize; + int i, ksize; u32 index; if (!nla) { @@ -228,6 +228,22 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p->tcfp_nkeys = parm->nkeys; } memcpy(p->tcfp_keys, parm->keys, ksize); + p->tcfp_off_max_hint = 0; + for (i = 0; i < p->tcfp_nkeys; ++i) { + u32 cur = p->tcfp_keys[i].off; + + /* sanitize the shift value for any later use */ + p->tcfp_keys[i].shift = min_t(size_t, BITS_PER_TYPE(int) - 1, + p->tcfp_keys[i].shift); + + /* The AT option can read a single byte, we can bound the actual + * value with uchar max. + */ + cur += (0xff & p->tcfp_keys[i].offmask) >> p->tcfp_keys[i].shift; + + /* Each key touches 4 bytes starting from the computed offset */ + p->tcfp_off_max_hint = max(p->tcfp_off_max_hint, cur + 4); + } p->tcfp_flags = parm->flags; goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -308,13 +324,18 @@ static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_pedit *p = to_pedit(a); + u32 max_offset; int i; - if (skb_unclone(skb, GFP_ATOMIC)) - return p->tcf_action; - spin_lock(&p->tcf_lock); + max_offset = (skb_transport_header_was_set(skb) ? + skb_transport_offset(skb) : + skb_network_offset(skb)) + + p->tcfp_off_max_hint; + if (skb_ensure_writable(skb, min(skb->len, max_offset))) + goto unlock; + tcf_lastuse_update(&p->tcf_tm); if (p->tcfp_nkeys > 0) { @@ -403,6 +424,7 @@ bad: p->tcf_qstats.overlimits++; done: bstats_update(&p->tcf_bstats, skb); +unlock: spin_unlock(&p->tcf_lock); return p->tcf_action; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b3815b568e8e..463c4a58d2c3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -458,6 +458,10 @@ void sctp_generate_reconf_event(struct timer_list *t) goto out_unlock; } + /* This happens when the response arrives after the timer is triggered. */ + if (!asoc->strreset_chunk) + goto out_unlock; + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_RECONF), asoc->state, asoc->ep, asoc, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index fc7b6eb22143..fce16b9d6e1a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -243,11 +243,27 @@ struct proto smc_proto6 = { }; EXPORT_SYMBOL_GPL(smc_proto6); +static void smc_fback_restore_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = NULL; + + smc_clcsock_restore_cb(&clcsk->sk_state_change, &smc->clcsk_state_change); + smc_clcsock_restore_cb(&clcsk->sk_data_ready, &smc->clcsk_data_ready); + smc_clcsock_restore_cb(&clcsk->sk_write_space, &smc->clcsk_write_space); + smc_clcsock_restore_cb(&clcsk->sk_error_report, &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); +} + static void smc_restore_fallback_changes(struct smc_sock *smc) { if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ smc->clcsock->file->private_data = smc->sk.sk_socket; smc->clcsock->file = NULL; + smc_fback_restore_callbacks(smc); } } @@ -373,6 +389,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); mutex_init(&smc->clcsock_release_lock); + smc_init_saved_callbacks(smc); return sk; } @@ -744,47 +761,73 @@ out: static void smc_fback_state_change(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_state_change); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_data_ready(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_data_ready); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_write_space(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_write_space); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_error_report(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_error_report); + read_unlock_bh(&clcsk->sk_callback_lock); +} + +static void smc_fback_replace_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + + smc_clcsock_replace_cb(&clcsk->sk_state_change, smc_fback_state_change, + &smc->clcsk_state_change); + smc_clcsock_replace_cb(&clcsk->sk_data_ready, smc_fback_data_ready, + &smc->clcsk_data_ready); + smc_clcsock_replace_cb(&clcsk->sk_write_space, smc_fback_write_space, + &smc->clcsk_write_space); + smc_clcsock_replace_cb(&clcsk->sk_error_report, smc_fback_error_report, + &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); } static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { - struct sock *clcsk; int rc = 0; mutex_lock(&smc->clcsock_release_lock); @@ -792,10 +835,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) rc = -EBADF; goto out; } - clcsk = smc->clcsock->sk; - if (smc->use_fallback) - goto out; smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); @@ -810,18 +850,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * in smc sk->sk_wq and they should be woken up * as clcsock's wait queue is woken up. */ - smc->clcsk_state_change = clcsk->sk_state_change; - smc->clcsk_data_ready = clcsk->sk_data_ready; - smc->clcsk_write_space = clcsk->sk_write_space; - smc->clcsk_error_report = clcsk->sk_error_report; - - clcsk->sk_state_change = smc_fback_state_change; - clcsk->sk_data_ready = smc_fback_data_ready; - clcsk->sk_write_space = smc_fback_write_space; - clcsk->sk_error_report = smc_fback_error_report; - - smc->clcsock->sk->sk_user_data = - (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_fback_replace_callbacks(smc); } out: mutex_unlock(&smc->clcsock_release_lock); @@ -1475,6 +1504,8 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_state = SMC_CLOSED; if (rc == -EPIPE || rc == -EAGAIN) smc->sk.sk_err = EPIPE; + else if (rc == -ECONNREFUSED) + smc->sk.sk_err = ECONNREFUSED; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); sock_put(&smc->sk); /* passive closing */ @@ -1594,6 +1625,19 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) * function; switch it back to the original sk_data_ready function */ new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready; + + /* if new clcsock has also inherited the fallback-specific callback + * functions, switch them back to the original ones. + */ + if (lsmc->use_fallback) { + if (lsmc->clcsk_state_change) + new_clcsock->sk->sk_state_change = lsmc->clcsk_state_change; + if (lsmc->clcsk_write_space) + new_clcsock->sk->sk_write_space = lsmc->clcsk_write_space; + if (lsmc->clcsk_error_report) + new_clcsock->sk->sk_error_report = lsmc->clcsk_error_report; + } + (*new_smc)->clcsock = new_clcsock; out: return rc; @@ -2353,17 +2397,20 @@ out: static void smc_clcsock_data_ready(struct sock *listen_clcsock) { - struct smc_sock *lsmc = - smc_clcsock_user_data(listen_clcsock); + struct smc_sock *lsmc; + read_lock_bh(&listen_clcsock->sk_callback_lock); + lsmc = smc_clcsock_user_data(listen_clcsock); if (!lsmc) - return; + goto out; lsmc->clcsk_data_ready(listen_clcsock); if (lsmc->sk.sk_state == SMC_LISTEN) { sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work)) sock_put(&lsmc->sk); } +out: + read_unlock_bh(&listen_clcsock->sk_callback_lock); } static int smc_listen(struct socket *sock, int backlog) @@ -2395,10 +2442,12 @@ static int smc_listen(struct socket *sock, int backlog) /* save original sk_data_ready function and establish * smc-specific sk_data_ready function */ - smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready; - smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_clcsock_replace_cb(&smc->clcsock->sk->sk_data_ready, + smc_clcsock_data_ready, &smc->clcsk_data_ready); + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); /* save original ops */ smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops; @@ -2413,7 +2462,11 @@ static int smc_listen(struct socket *sock, int backlog) rc = kernel_listen(smc->clcsock, backlog); if (rc) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); + smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); goto out; } sk->sk_max_ack_backlog = backlog; diff --git a/net/smc/smc.h b/net/smc/smc.h index ea0620529ebe..5ed765ea0c73 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -288,12 +288,41 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +static inline void smc_init_saved_callbacks(struct smc_sock *smc) +{ + smc->clcsk_state_change = NULL; + smc->clcsk_data_ready = NULL; + smc->clcsk_write_space = NULL; + smc->clcsk_error_report = NULL; +} + static inline struct smc_sock *smc_clcsock_user_data(const struct sock *clcsk) { return (struct smc_sock *) ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY); } +/* save target_cb in saved_cb, and replace target_cb with new_cb */ +static inline void smc_clcsock_replace_cb(void (**target_cb)(struct sock *), + void (*new_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + /* only save once */ + if (!*saved_cb) + *saved_cb = *target_cb; + *target_cb = new_cb; +} + +/* restore target_cb to saved_cb, and reset saved_cb to NULL */ +static inline void smc_clcsock_restore_cb(void (**target_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + if (!*saved_cb) + return; + *target_cb = *saved_cb; + *saved_cb = NULL; +} + extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ extern struct workqueue_struct *smc_close_wq; /* wq for close work */ diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 676cb2333d3c..31db7438857c 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -214,8 +214,11 @@ again: sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); /* wake up accept */ if (smc->clcsock && smc->clcsock->sk) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } smc_close_cleanup_listen(sk); diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 51e8eb2933ff..338b9ef806e8 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -355,12 +355,12 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, } break; } + if (!timeo) + return -EAGAIN; if (signal_pending(current)) { read_done = sock_intr_errno(timeo); break; } - if (!timeo) - return -EAGAIN; } if (!smc_rx_data_available(conn)) { diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 61c276bddaf2..f549e4c05def 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -98,6 +98,7 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt) * done without the correct namespace: */ .flags = RPC_CLNT_CREATE_NOPING | + RPC_CLNT_CREATE_CONNECTED | RPC_CLNT_CREATE_NO_IDLE_TIMEOUT }; struct rpc_clnt *clnt; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index af0174d7ce5a..e2c6eca0271b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -76,6 +76,7 @@ static int rpc_encode_header(struct rpc_task *task, static int rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr); static int rpc_ping(struct rpc_clnt *clnt); +static int rpc_ping_noreply(struct rpc_clnt *clnt); static void rpc_check_timeout(struct rpc_task *task); static void rpc_register_client(struct rpc_clnt *clnt) @@ -483,6 +484,12 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, rpc_shutdown_client(clnt); return ERR_PTR(err); } + } else if (args->flags & RPC_CLNT_CREATE_CONNECTED) { + int err = rpc_ping_noreply(clnt); + if (err != 0) { + rpc_shutdown_client(clnt); + return ERR_PTR(err); + } } clnt->cl_softrtry = 1; @@ -1065,10 +1072,13 @@ rpc_task_get_next_xprt(struct rpc_clnt *clnt) static void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) { - if (task->tk_xprt && - !(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) && - (task->tk_flags & RPC_TASK_MOVEABLE))) - return; + if (task->tk_xprt) { + if (!(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) && + (task->tk_flags & RPC_TASK_MOVEABLE))) + return; + xprt_release(task); + xprt_put(task->tk_xprt); + } if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN) task->tk_xprt = rpc_task_get_first_xprt(clnt); else @@ -2706,6 +2716,10 @@ static const struct rpc_procinfo rpcproc_null = { .p_decode = rpcproc_decode_null, }; +static const struct rpc_procinfo rpcproc_null_noreply = { + .p_encode = rpcproc_encode_null, +}; + static void rpc_null_call_prepare(struct rpc_task *task, void *data) { @@ -2759,6 +2773,28 @@ static int rpc_ping(struct rpc_clnt *clnt) return status; } +static int rpc_ping_noreply(struct rpc_clnt *clnt) +{ + struct rpc_message msg = { + .rpc_proc = &rpcproc_null_noreply, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .rpc_message = &msg, + .callback_ops = &rpc_null_ops, + .flags = RPC_TASK_SOFT | RPC_TASK_SOFTCONN | RPC_TASK_NULLCREDS, + }; + struct rpc_task *task; + int status; + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = task->tk_status; + rpc_put_task(task); + return status; +} + struct rpc_cb_add_xprt_calldata { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 8ab64ea46870..650102a9c86a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1419,6 +1419,26 @@ static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt) #endif /* CONFIG_SUNRPC_BACKCHANNEL */ /** + * xs_local_state_change - callback to handle AF_LOCAL socket state changes + * @sk: socket whose state has changed + * + */ +static void xs_local_state_change(struct sock *sk) +{ + struct rpc_xprt *xprt; + struct sock_xprt *transport; + + if (!(xprt = xprt_from_sock(sk))) + return; + transport = container_of(xprt, struct sock_xprt, xprt); + if (sk->sk_shutdown & SHUTDOWN_MASK) { + clear_bit(XPRT_CONNECTED, &xprt->state); + /* Trigger the socket release */ + xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT); + } +} + +/** * xs_tcp_state_change - callback to handle TCP socket state changes * @sk: socket whose state has changed * @@ -1866,6 +1886,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_user_data = xprt; sk->sk_data_ready = xs_data_ready; sk->sk_write_space = xs_udp_write_space; + sk->sk_state_change = xs_local_state_change; sk->sk_error_report = xs_error_report; xprt_clear_connected(xprt); @@ -1950,6 +1971,9 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); int ret; + if (transport->file) + goto force_disconnect; + if (RPC_IS_ASYNC(task)) { /* * We want the AF_LOCAL connect to be resolved in the @@ -1962,11 +1986,17 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) */ task->tk_rpc_status = -ENOTCONN; rpc_exit(task, -ENOTCONN); - return; + goto out_wake; } ret = xs_local_setup_socket(transport); if (ret && !RPC_IS_SOFTCONN(task)) msleep_interruptible(15000); + return; +force_disconnect: + xprt_force_disconnect(xprt); +out_wake: + xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, -ENOTCONN); } #if IS_ENABLED(CONFIG_SUNRPC_SWAP) @@ -2845,9 +2875,6 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) } xprt_set_bound(xprt); xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL); - ret = ERR_PTR(xs_local_setup_socket(transport)); - if (ret) - goto out_err; break; default: ret = ERR_PTR(-EAFNOSUPPORT); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 12f7b56771d9..3919fe2c58c5 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -483,11 +483,13 @@ handle_error: copy = min_t(size_t, size, (pfrag->size - pfrag->offset)); copy = min_t(size_t, copy, (max_open_record_len - record->len)); - rc = tls_device_copy_data(page_address(pfrag->page) + - pfrag->offset, copy, msg_iter); - if (rc) - goto handle_error; - tls_append_frag(record, pfrag, copy); + if (copy) { + rc = tls_device_copy_data(page_address(pfrag->page) + + pfrag->offset, copy, msg_iter); + if (rc) + goto handle_error; + tls_append_frag(record, pfrag, copy); + } size -= copy; if (!size) { @@ -1345,7 +1347,10 @@ static int tls_device_down(struct net_device *netdev) /* Device contexts for RX and TX will be freed in on sk_destruct * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. + * Now release the ref taken above. */ + if (refcount_dec_and_test(&ctx->refcount)) + tls_device_free_ctx(ctx); } up_write(&device_offload_lock); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 21e808fcb676..1a3551b6d18b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3173,6 +3173,15 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, } else if (attrs[NL80211_ATTR_CHANNEL_WIDTH]) { chandef->width = nla_get_u32(attrs[NL80211_ATTR_CHANNEL_WIDTH]); + if (chandef->chan->band == NL80211_BAND_S1GHZ) { + /* User input error for channel width doesn't match channel */ + if (chandef->width != ieee80211_s1g_channel_width(chandef->chan)) { + NL_SET_ERR_MSG_ATTR(extack, + attrs[NL80211_ATTR_CHANNEL_WIDTH], + "bad channel width"); + return -EINVAL; + } + } if (attrs[NL80211_ATTR_CENTER_FREQ1]) { chandef->center_freq1 = nla_get_u32(attrs[NL80211_ATTR_CENTER_FREQ1]); @@ -11657,18 +11666,23 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, struct cfg80211_bitrate_mask mask; struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; int err; if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; + wdev_lock(wdev); err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, &mask, dev, true); if (err) - return err; + goto out; - return rdev_set_bitrate_mask(rdev, dev, NULL, &mask); + err = rdev_set_bitrate_mask(rdev, dev, NULL, &mask); +out: + wdev_unlock(wdev); + return err; } static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 4a6d86432910..6d82bd9eaf8c 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1829,7 +1829,7 @@ int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, if (tmp && tmp->datalen >= sizeof(struct ieee80211_s1g_oper_ie)) { struct ieee80211_s1g_oper_ie *s1gop = (void *)tmp->data; - return s1gop->primary_ch; + return s1gop->oper_ch; } } else { tmp = cfg80211_find_elem(WLAN_EID_DS_PARAMS, ie, ielen); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 2c34caee0fd1..3a9348030e20 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -639,7 +639,7 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ - if (xsk_no_wakeup(sk)) + if (xs->zc && xsk_no_wakeup(sk)) return 0; pool = xs->pool; @@ -967,6 +967,19 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xp_get_pool(umem_xs->pool); xs->pool = umem_xs->pool; + + /* If underlying shared umem was created without Tx + * ring, allocate Tx descs array that Tx batching API + * utilizes + */ + if (xs->tx && !xs->pool->tx_descs) { + err = xp_alloc_tx_descs(xs->pool, xs); + if (err) { + xp_put_pool(xs->pool); + sockfd_put(sock); + goto out_unlock; + } + } } xdp_get_umem(umem_xs->umem); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index af040ffa14ff..87bdd71c7bb6 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -42,6 +42,16 @@ void xp_destroy(struct xsk_buff_pool *pool) kvfree(pool); } +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs) +{ + pool->tx_descs = kvcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), + GFP_KERNEL); + if (!pool->tx_descs) + return -ENOMEM; + + return 0; +} + struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem) { @@ -59,11 +69,9 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, if (!pool->heads) goto out; - if (xs->tx) { - pool->tx_descs = kcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), GFP_KERNEL); - if (!pool->tx_descs) + if (xs->tx) + if (xp_alloc_tx_descs(pool, xs)) goto out; - } pool->chunk_mask = ~((u64)umem->chunk_size - 1); pool->addrs_cnt = umem->size; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 00bd0ecff5a1..f1876ea61fdc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3744,7 +3744,7 @@ static int stale_bundle(struct dst_entry *dst) void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { - dst->dev = dev_net(dev)->loopback_dev; + dst->dev = blackhole_netdev; dev_hold(dst->dev); dev_put(dev); } |