diff options
Diffstat (limited to 'net')
131 files changed, 2621 insertions, 1197 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index a3340268ec8d..86bbc7147fc1 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -904,7 +904,7 @@ EXPORT_SYMBOL(do_trace_9p_fid_put); static int p9_client_version(struct p9_client *c) { - int err = 0; + int err; struct p9_req_t *req; char *version = NULL; int msize; @@ -975,7 +975,6 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) struct p9_client *clnt; char *client_id; - err = 0; clnt = kmalloc(sizeof(*clnt), GFP_KERNEL); if (!clnt) return ERR_PTR(-ENOMEM); @@ -1094,7 +1093,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, const char *uname, kuid_t n_uname, const char *aname) { - int err = 0; + int err; struct p9_req_t *req; struct p9_fid *fid; struct p9_qid qid; @@ -1147,7 +1146,6 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, struct p9_req_t *req; u16 nwqids, count; - err = 0; wqids = NULL; clnt = oldfid->clnt; if (clone) { @@ -1224,7 +1222,6 @@ int p9_client_open(struct p9_fid *fid, int mode) clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> %s fid %d mode %d\n", p9_is_proto_dotl(clnt) ? "TLOPEN" : "TOPEN", fid->fid, mode); - err = 0; if (fid->mode != -1) return -EINVAL; @@ -1262,7 +1259,7 @@ EXPORT_SYMBOL(p9_client_open); int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32 mode, kgid_t gid, struct p9_qid *qid) { - int err = 0; + int err; struct p9_client *clnt; struct p9_req_t *req; int iounit; @@ -1314,7 +1311,6 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode, p9_debug(P9_DEBUG_9P, ">>> TCREATE fid %d name %s perm %d mode %d\n", fid->fid, name, perm, mode); - err = 0; clnt = fid->clnt; if (fid->mode != -1) @@ -1350,7 +1346,7 @@ EXPORT_SYMBOL(p9_client_fcreate); int p9_client_symlink(struct p9_fid *dfid, const char *name, const char *symtgt, kgid_t gid, struct p9_qid *qid) { - int err = 0; + int err; struct p9_client *clnt; struct p9_req_t *req; @@ -1402,13 +1398,12 @@ EXPORT_SYMBOL(p9_client_link); int p9_client_fsync(struct p9_fid *fid, int datasync) { - int err; + int err = 0; struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TFSYNC fid %d datasync:%d\n", fid->fid, datasync); - err = 0; clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TFSYNC, "dd", fid->fid, datasync); @@ -1428,7 +1423,7 @@ EXPORT_SYMBOL(p9_client_fsync); int p9_client_clunk(struct p9_fid *fid) { - int err; + int err = 0; struct p9_client *clnt; struct p9_req_t *req; int retries = 0; @@ -1436,7 +1431,6 @@ int p9_client_clunk(struct p9_fid *fid) again: p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid, retries); - err = 0; clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TCLUNK, "d", fid->fid); @@ -1465,12 +1459,11 @@ EXPORT_SYMBOL(p9_client_clunk); int p9_client_remove(struct p9_fid *fid) { - int err; + int err = 0; struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TREMOVE fid %d\n", fid->fid); - err = 0; clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TREMOVE, "d", fid->fid); @@ -1680,7 +1673,6 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) if (!ret) return ERR_PTR(-ENOMEM); - err = 0; clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TSTAT, "d", fid->fid); @@ -1733,7 +1725,6 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, if (!ret) return ERR_PTR(-ENOMEM); - err = 0; clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TGETATTR, "dq", fid->fid, request_mask); @@ -1812,11 +1803,10 @@ static int p9_client_statsize(struct p9_wstat *wst, int proto_version) int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) { - int err; + int err = 0; struct p9_req_t *req; struct p9_client *clnt; - err = 0; clnt = fid->clnt; wst->size = p9_client_statsize(wst, clnt->proto_version); p9_debug(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", @@ -1851,11 +1841,10 @@ EXPORT_SYMBOL(p9_client_wstat); int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr) { - int err; + int err = 0; struct p9_req_t *req; struct p9_client *clnt; - err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TSETATTR fid %d\n", fid->fid); p9_debug(P9_DEBUG_9P, " valid=%x mode=%x uid=%d gid=%d size=%lld\n", @@ -1887,7 +1876,6 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb) struct p9_req_t *req; struct p9_client *clnt; - err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TSTATFS fid %d\n", fid->fid); @@ -1921,11 +1909,10 @@ EXPORT_SYMBOL(p9_client_statfs); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name) { - int err; + int err = 0; struct p9_req_t *req; struct p9_client *clnt; - err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TRENAME fid %d newdirfid %d name %s\n", @@ -1949,11 +1936,10 @@ EXPORT_SYMBOL(p9_client_rename); int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name, struct p9_fid *newdirfid, const char *new_name) { - int err; + int err = 0; struct p9_req_t *req; struct p9_client *clnt; - err = 0; clnt = olddirfid->clnt; p9_debug(P9_DEBUG_9P, @@ -1986,7 +1972,6 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, struct p9_client *clnt; struct p9_fid *attr_fid; - err = 0; clnt = file_fid->clnt; attr_fid = p9_fid_create(clnt); if (!attr_fid) { @@ -2027,14 +2012,13 @@ EXPORT_SYMBOL_GPL(p9_client_xattrwalk); int p9_client_xattrcreate(struct p9_fid *fid, const char *name, u64 attr_size, int flags) { - int err; + int err = 0; struct p9_req_t *req; struct p9_client *clnt; p9_debug(P9_DEBUG_9P, ">>> TXATTRCREATE fid %d name %s size %llu flag %d\n", fid->fid, name, attr_size, flags); - err = 0; clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TXATTRCREATE, "dsqd", fid->fid, name, attr_size, flags); @@ -2063,7 +2047,6 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", fid->fid, offset, count); - err = 0; clnt = fid->clnt; rsize = fid->iounit; @@ -2122,7 +2105,6 @@ int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode, struct p9_client *clnt; struct p9_req_t *req; - err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TMKNOD fid %d name %s mode %d major %d minor %d\n", @@ -2153,7 +2135,6 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode, struct p9_client *clnt; struct p9_req_t *req; - err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TMKDIR fid %d name %s mode %d gid %d\n", fid->fid, name, mode, from_kgid(&init_user_ns, gid)); @@ -2182,7 +2163,6 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status) struct p9_client *clnt; struct p9_req_t *req; - err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TLOCK fid %d type %i flags %d start %lld length %lld proc_id %d client_id %s\n", @@ -2214,7 +2194,6 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock) struct p9_client *clnt; struct p9_req_t *req; - err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TGETLOCK fid %d, type %i start %lld length %lld proc_id %d client_id %s\n", @@ -2251,7 +2230,6 @@ int p9_client_readlink(struct p9_fid *fid, char **target) struct p9_client *clnt; struct p9_req_t *req; - err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TREADLINK fid %d\n", fid->fid); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 3c27ffb781e3..e305071eb7b8 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -384,7 +384,7 @@ static void handle_rerror(struct p9_req_t *req, int in_hdr_len, void *to = req->rc.sdata + in_hdr_len; // Fits entirely into the static data? Nothing to do. - if (req->rc.size < in_hdr_len) + if (req->rc.size < in_hdr_len || !pages) return; // Really long error message? Tough, truncate the reply. Might get @@ -428,7 +428,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, struct page **in_pages = NULL, **out_pages = NULL; struct virtio_chan *chan = client->trans; struct scatterlist *sgs[4]; - size_t offs; + size_t offs = 0; int need_drop = 0; int kicked = 0; @@ -501,8 +501,8 @@ req_retry_pinned: if (in_pages) { sgs[out_sgs + in_sgs++] = chan->sg + out + in; - in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM, - in_pages, in_nr_pages, offs, inlen); + pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM, + in_pages, in_nr_pages, offs, inlen); } BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs)); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 1ef952bda97d..76222565e2df 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -118,7 +118,7 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) */ params->explicit_connect = false; - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); switch (params->auto_connect) { case HCI_AUTO_CONN_EXPLICIT: @@ -127,10 +127,10 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) return; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(¶ms->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; default: break; @@ -775,6 +775,11 @@ static void le_conn_timeout(struct work_struct *work) hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); } +struct iso_cig_params { + struct hci_cp_le_set_cig_params cp; + struct hci_cis_params cis[0x1f]; +}; + struct iso_list_data { union { u8 cig; @@ -786,10 +791,7 @@ struct iso_list_data { u16 sync_handle; }; int count; - struct { - struct hci_cp_le_set_cig_params cp; - struct hci_cis_params cis[0x11]; - } pdu; + struct iso_cig_params pdu; }; static void bis_list(struct hci_conn *conn, void *data) @@ -1424,8 +1426,8 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev, if (params->auto_connect == HCI_AUTO_CONN_DISABLED || params->auto_connect == HCI_AUTO_CONN_REPORT || params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); } params->explicit_connect = true; @@ -1682,7 +1684,7 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, if (!link) { hci_conn_drop(acl); hci_conn_drop(sco); - return NULL; + return ERR_PTR(-ENOLINK); } sco->setting = setting; @@ -1764,10 +1766,33 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) return hci_send_cmd(hdev, HCI_OP_LE_CREATE_BIG, sizeof(cp), &cp); } +static void set_cig_params_complete(struct hci_dev *hdev, void *data, int err) +{ + struct iso_cig_params *pdu = data; + + bt_dev_dbg(hdev, ""); + + if (err) + bt_dev_err(hdev, "Unable to set CIG parameters: %d", err); + + kfree(pdu); +} + +static int set_cig_params_sync(struct hci_dev *hdev, void *data) +{ + struct iso_cig_params *pdu = data; + u32 plen; + + plen = sizeof(pdu->cp) + pdu->cp.num_cis * sizeof(pdu->cis[0]); + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS, plen, pdu, + HCI_CMD_TIMEOUT); +} + static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct iso_list_data data; + struct iso_cig_params *pdu; memset(&data, 0, sizeof(data)); @@ -1837,12 +1862,16 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET || !data.pdu.cp.num_cis) return false; - if (hci_send_cmd(hdev, HCI_OP_LE_SET_CIG_PARAMS, - sizeof(data.pdu.cp) + - (data.pdu.cp.num_cis * sizeof(*data.pdu.cis)), - &data.pdu) < 0) + pdu = kmemdup(&data.pdu, sizeof(*pdu), GFP_KERNEL); + if (!pdu) return false; + if (hci_cmd_sync_queue(hdev, set_cig_params_sync, pdu, + set_cig_params_complete) < 0) { + kfree(pdu); + return false; + } + return true; } @@ -2044,10 +2073,10 @@ static int create_big_sync(struct hci_dev *hdev, void *data) flags |= MGMT_ADV_FLAG_SEC_2M; /* Align intervals */ - interval = qos->bcast.out.interval / 1250; + interval = (qos->bcast.out.interval / 1250) * qos->bcast.sync_factor; if (qos->bcast.bis) - sync_interval = qos->bcast.sync_interval * 1600; + sync_interval = interval * 4; err = hci_start_per_adv_sync(hdev, qos->bcast.bis, conn->le_per_adv_data_len, conn->le_per_adv_data, flags, interval, @@ -2225,7 +2254,7 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, if (!link) { hci_conn_drop(le); hci_conn_drop(cis); - return NULL; + return ERR_PTR(-ENOLINK); } /* If LE is already connected and CIS handle is already set proceed to diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 48917c68358d..1ec83985f1ab 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1972,6 +1972,7 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int status = 0; + int handle; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ @@ -1980,9 +1981,10 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: + handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); bt_dev_dbg(hdev, "%s remove monitor %d msft status %d", - hdev->name, monitor->handle, status); + hdev->name, handle, status); break; } @@ -2249,22 +2251,46 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, return NULL; } -/* This function requires the caller holds hdev->lock */ +/* This function requires the caller holds hdev->lock or rcu_read_lock */ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *param; - list_for_each_entry(param, list, action) { + rcu_read_lock(); + + list_for_each_entry_rcu(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && - param->addr_type == addr_type) + param->addr_type == addr_type) { + rcu_read_unlock(); return param; + } } + rcu_read_unlock(); + return NULL; } /* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_del_init(struct hci_conn_params *param) +{ + if (list_empty(¶m->action)) + return; + + list_del_rcu(¶m->action); + synchronize_rcu(); + INIT_LIST_HEAD(¶m->action); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_add(struct hci_conn_params *param, + struct list_head *list) +{ + list_add_rcu(¶m->action, list); +} + +/* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { @@ -2297,14 +2323,15 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, return params; } -static void hci_conn_params_free(struct hci_conn_params *params) +void hci_conn_params_free(struct hci_conn_params *params) { + hci_pend_le_list_del_init(params); + if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); } - list_del(¶ms->action); list_del(¶ms->list); kfree(params); } @@ -2342,8 +2369,7 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev) continue; } - list_del(¶ms->list); - kfree(params); + hci_conn_params_free(params); } BT_DBG("All LE disabled connection parameters were removed"); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 09ba6d8987ee..31ca320ce38d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1564,7 +1564,7 @@ static u8 hci_cc_le_set_privacy_mode(struct hci_dev *hdev, void *data, params = hci_conn_params_lookup(hdev, &cp->bdaddr, cp->bdaddr_type); if (params) - params->privacy_mode = cp->mode; + WRITE_ONCE(params->privacy_mode, cp->mode); hci_dev_unlock(hdev); @@ -2784,6 +2784,9 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) hci_enable_advertising(hdev); } + /* Inform sockets conn is gone before we delete it */ + hci_disconn_cfm(conn, HCI_ERROR_UNSPECIFIED); + goto done; } @@ -2804,8 +2807,8 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; default: @@ -3423,8 +3426,8 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data, case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); hci_update_passive_scan(hdev); break; @@ -3812,7 +3815,8 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_CIG_PARAMS); - if (!cp || rp->num_handles != cp->num_cis || rp->cig_id != cp->cig_id) { + if (!rp->status && (!cp || rp->num_handles != cp->num_cis || + rp->cig_id != cp->cig_id)) { bt_dev_err(hdev, "unexpected Set CIG Parameters response data"); status = HCI_ERROR_UNSPECIFIED; } @@ -5961,7 +5965,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, conn->dst_type); if (params) { - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); @@ -6316,23 +6320,18 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } - /* When receiving non-connectable or scannable undirected - * advertising reports, this means that the remote device is - * not connectable and then clearly indicate this in the - * device found event. - * - * When receiving a scan response, then there is no way to + /* When receiving a scan response, then there is no way to * know if the remote device is connectable or not. However * since scan responses are merged with a previously seen * advertising report, the flags field from that report * will be used. * - * In the really unlikely case that a controller get confused - * and just sends a scan response event, then it is marked as - * not connectable as well. + * In the unlikely case that a controller just sends a scan + * response event that doesn't match the pending report, then + * it is marked as a standalone SCAN_RSP. */ if (type == LE_ADV_SCAN_RSP) - flags = MGMT_DEV_FOUND_NOT_CONNECTABLE; + flags = MGMT_DEV_FOUND_SCAN_RSP; /* If there's nothing pending either store the data from this * event or send an immediate device found event if the data @@ -6790,6 +6789,7 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, { struct hci_evt_le_cis_established *ev = data; struct hci_conn *conn; + struct bt_iso_qos *qos; u16 handle = __le16_to_cpu(ev->handle); bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -6811,21 +6811,39 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, goto unlock; } - if (conn->role == HCI_ROLE_SLAVE) { - __le32 interval; - - memset(&interval, 0, sizeof(interval)); - - memcpy(&interval, ev->c_latency, sizeof(ev->c_latency)); - conn->iso_qos.ucast.in.interval = le32_to_cpu(interval); - memcpy(&interval, ev->p_latency, sizeof(ev->p_latency)); - conn->iso_qos.ucast.out.interval = le32_to_cpu(interval); - conn->iso_qos.ucast.in.latency = le16_to_cpu(ev->interval); - conn->iso_qos.ucast.out.latency = le16_to_cpu(ev->interval); - conn->iso_qos.ucast.in.sdu = le16_to_cpu(ev->c_mtu); - conn->iso_qos.ucast.out.sdu = le16_to_cpu(ev->p_mtu); - conn->iso_qos.ucast.in.phy = ev->c_phy; - conn->iso_qos.ucast.out.phy = ev->p_phy; + qos = &conn->iso_qos; + + /* Convert ISO Interval (1.25 ms slots) to SDU Interval (us) */ + qos->ucast.in.interval = le16_to_cpu(ev->interval) * 1250; + qos->ucast.out.interval = qos->ucast.in.interval; + + switch (conn->role) { + case HCI_ROLE_SLAVE: + /* Convert Transport Latency (us) to Latency (msec) */ + qos->ucast.in.latency = + DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), + 1000); + qos->ucast.out.latency = + DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), + 1000); + qos->ucast.in.sdu = le16_to_cpu(ev->c_mtu); + qos->ucast.out.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.in.phy = ev->c_phy; + qos->ucast.out.phy = ev->p_phy; + break; + case HCI_ROLE_MASTER: + /* Convert Transport Latency (us) to Latency (msec) */ + qos->ucast.out.latency = + DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), + 1000); + qos->ucast.in.latency = + DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), + 1000); + qos->ucast.out.sdu = le16_to_cpu(ev->c_mtu); + qos->ucast.in.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.out.phy = ev->c_phy; + qos->ucast.in.phy = ev->p_phy; + break; } if (!ev->status) { diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 804cde43b4e0..4d1e32bb6a9c 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2160,15 +2160,23 @@ static int hci_le_del_accept_list_sync(struct hci_dev *hdev, return 0; } +struct conn_params { + bdaddr_t addr; + u8 addr_type; + hci_conn_flags_t flags; + u8 privacy_mode; +}; + /* Adds connection to resolve list if needed. * Setting params to NULL programs local hdev->irk */ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_add_to_resolv_list cp; struct smp_irk *irk; struct bdaddr_list_with_irk *entry; + struct hci_conn_params *p; if (!use_ll_privacy(hdev)) return 0; @@ -2203,6 +2211,16 @@ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, /* Default privacy mode is always Network */ params->privacy_mode = HCI_NETWORK_PRIVACY; + rcu_read_lock(); + p = hci_pend_le_action_lookup(&hdev->pend_le_conns, + ¶ms->addr, params->addr_type); + if (!p) + p = hci_pend_le_action_lookup(&hdev->pend_le_reports, + ¶ms->addr, params->addr_type); + if (p) + WRITE_ONCE(p->privacy_mode, HCI_NETWORK_PRIVACY); + rcu_read_unlock(); + done: if (hci_dev_test_flag(hdev, HCI_PRIVACY)) memcpy(cp.local_irk, hdev->irk, 16); @@ -2215,7 +2233,7 @@ done: /* Set Device Privacy Mode. */ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_set_privacy_mode cp; struct smp_irk *irk; @@ -2240,6 +2258,8 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, bacpy(&cp.bdaddr, &irk->bdaddr); cp.mode = HCI_DEVICE_PRIVACY; + /* Note: params->privacy_mode is not updated since it is a copy */ + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_PRIVACY_MODE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } @@ -2249,7 +2269,7 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, * properly set the privacy mode. */ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params, + struct conn_params *params, u8 *num_entries) { struct hci_cp_le_add_to_accept_list cp; @@ -2447,6 +2467,52 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, return __hci_cmd_sync_sk(hdev, opcode, 0, NULL, 0, HCI_CMD_TIMEOUT, sk); } +static struct conn_params *conn_params_copy(struct list_head *list, size_t *n) +{ + struct hci_conn_params *params; + struct conn_params *p; + size_t i; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) + ++i; + *n = i; + + rcu_read_unlock(); + + p = kvcalloc(*n, sizeof(struct conn_params), GFP_KERNEL); + if (!p) + return NULL; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) { + /* Racing adds are handled in next scan update */ + if (i >= *n) + break; + + /* No hdev->lock, but: addr, addr_type are immutable. + * privacy_mode is only written by us or in + * hci_cc_le_set_privacy_mode that we wait for. + * We should be idempotent so MGMT updating flags + * while we are processing is OK. + */ + bacpy(&p[i].addr, ¶ms->addr); + p[i].addr_type = params->addr_type; + p[i].flags = READ_ONCE(params->flags); + p[i].privacy_mode = READ_ONCE(params->privacy_mode); + ++i; + } + + rcu_read_unlock(); + + *n = i; + return p; +} + /* Device must not be scanning when updating the accept list. * * Update is done using the following sequence: @@ -2466,11 +2532,12 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, */ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) { - struct hci_conn_params *params; + struct conn_params *params; struct bdaddr_list *b, *t; u8 num_entries = 0; bool pend_conn, pend_report; u8 filter_policy; + size_t i, n; int err; /* Pause advertising if resolving list can be used as controllers @@ -2504,6 +2571,7 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) if (hci_conn_hash_lookup_le(hdev, &b->bdaddr, b->bdaddr_type)) continue; + /* Pointers not dereferenced, no locks needed */ pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, &b->bdaddr, b->bdaddr_type); @@ -2532,23 +2600,50 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) * available accept list entries in the controller, then * just abort and return filer policy value to not use the * accept list. + * + * The list and params may be mutated while we wait for events, + * so make a copy and iterate it. */ - list_for_each_entry(params, &hdev->pend_le_conns, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_conns, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, ¶ms[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } } + kvfree(params); + /* After adding all new pending connections, walk through * the list of pending reports and also add these to the * accept list if there is still space. Abort if space runs out. */ - list_for_each_entry(params, &hdev->pend_le_reports, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_reports, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, ¶ms[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } } + kvfree(params); + /* Use the allowlist unless the following conditions are all true: * - We are not currently suspending * - There are 1 or more ADV monitors registered and it's not offloaded @@ -4623,26 +4718,18 @@ static int hci_dev_setup_sync(struct hci_dev *hdev) * BD_ADDR invalid before creating the HCI device or in * its setup callback. */ - invalid_bdaddr = test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); - + invalid_bdaddr = test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) || + test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); if (!ret) { - if (test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks)) { - if (!bacmp(&hdev->public_addr, BDADDR_ANY)) - hci_dev_get_bd_addr_from_property(hdev); - - if (bacmp(&hdev->public_addr, BDADDR_ANY) && - hdev->set_bdaddr) { - ret = hdev->set_bdaddr(hdev, - &hdev->public_addr); - - /* If setting of the BD_ADDR from the device - * property succeeds, then treat the address - * as valid even if the invalid BD_ADDR - * quirk indicates otherwise. - */ - if (!ret) - invalid_bdaddr = false; - } + if (test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks) && + !bacmp(&hdev->public_addr, BDADDR_ANY)) + hci_dev_get_bd_addr_from_property(hdev); + + if (invalid_bdaddr && bacmp(&hdev->public_addr, BDADDR_ANY) && + hdev->set_bdaddr) { + ret = hdev->set_bdaddr(hdev, &hdev->public_addr); + if (!ret) + invalid_bdaddr = false; } } @@ -4845,12 +4932,12 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) struct hci_conn_params *p; list_for_each_entry(p, &hdev->le_conn_params, list) { + hci_pend_le_list_del_init(p); if (p->conn) { hci_conn_drop(p->conn); hci_conn_put(p->conn); p->conn = NULL; } - list_del_init(&p->action); } BT_DBG("All LE pending actions cleared"); diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 2934d7f4d564..15b33579007c 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -6,7 +6,9 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> -static struct class *bt_class; +static const struct class bt_class = { + .name = "bluetooth", +}; static void bt_link_release(struct device *dev) { @@ -36,7 +38,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn) BT_DBG("conn %p", conn); conn->dev.type = &bt_link; - conn->dev.class = bt_class; + conn->dev.class = &bt_class; conn->dev.parent = &hdev->dev; device_initialize(&conn->dev); @@ -104,7 +106,7 @@ void hci_init_sysfs(struct hci_dev *hdev) struct device *dev = &hdev->dev; dev->type = &bt_host; - dev->class = bt_class; + dev->class = &bt_class; __module_get(THIS_MODULE); device_initialize(dev); @@ -112,12 +114,10 @@ void hci_init_sysfs(struct hci_dev *hdev) int __init bt_sysfs_init(void) { - bt_class = class_create("bluetooth"); - - return PTR_ERR_OR_ZERO(bt_class); + return class_register(&bt_class); } void bt_sysfs_cleanup(void) { - class_destroy(bt_class); + class_unregister(&bt_class); } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 34d55a85d8f6..505d62247268 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -123,8 +123,11 @@ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) { struct iso_conn *conn = hcon->iso_data; - if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + } conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) @@ -300,14 +303,13 @@ static int iso_connect_bis(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk); err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -321,7 +323,6 @@ static int iso_connect_bis(struct sock *sk) } release_sock(sk); - return err; unlock: hci_dev_unlock(hdev); @@ -389,14 +390,13 @@ static int iso_connect_cis(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk); err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -413,7 +413,6 @@ static int iso_connect_cis(struct sock *sk) } release_sock(sk); - return err; unlock: hci_dev_unlock(hdev); @@ -704,7 +703,7 @@ static struct bt_iso_qos default_qos = { .bcast = { .big = BT_ISO_QOS_BIG_UNSET, .bis = BT_ISO_QOS_BIS_UNSET, - .sync_interval = 0x00, + .sync_factor = 0x01, .packing = 0x00, .framing = 0x00, .in = DEFAULT_IO_QOS, @@ -1072,8 +1071,8 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct iso_conn *conn = iso_pi(sk)->conn; struct sk_buff *skb, **frag; + size_t mtu; int err; BT_DBG("sock %p, sk %p", sock, sk); @@ -1085,11 +1084,18 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; - if (sk->sk_state != BT_CONNECTED) + lock_sock(sk); + + if (sk->sk_state != BT_CONNECTED) { + release_sock(sk); return -ENOTCONN; + } + + mtu = iso_pi(sk)->conn->hcon->hdev->iso_mtu; + + release_sock(sk); - skb = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - HCI_ISO_DATA_HDR_SIZE, 0); + skb = bt_skb_sendmsg(sk, msg, len, mtu, HCI_ISO_DATA_HDR_SIZE, 0); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -1102,8 +1108,7 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, while (len) { struct sk_buff *tmp; - tmp = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - 0, 0); + tmp = bt_skb_sendmsg(sk, msg, len, mtu, 0, 0); if (IS_ERR(tmp)) { kfree_skb(skb); return PTR_ERR(tmp); @@ -1158,15 +1163,19 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, BT_DBG("sk %p", sk); if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: - lock_sock(sk); iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; case BT_CONNECT: + release_sock(sk); return iso_connect_cis(sk); + default: + release_sock(sk); + break; } } @@ -1213,7 +1222,7 @@ static bool check_ucast_qos(struct bt_iso_qos *qos) static bool check_bcast_qos(struct bt_iso_qos *qos) { - if (qos->bcast.sync_interval > 0x07) + if (qos->bcast.sync_factor == 0x00) return false; if (qos->bcast.packing > 0x01) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index c5e8798e297c..17ca13e8c044 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6374,9 +6374,14 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn, if (!chan) goto done; + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) + goto done; + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNREFUSED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); done: mutex_unlock(&conn->chan_lock); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index eebe256104bc..947ca580bb9a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -46,6 +46,7 @@ static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern); +static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) { @@ -1415,6 +1416,7 @@ static int l2cap_sock_release(struct socket *sock) if (!sk) return 0; + l2cap_sock_cleanup_listen(sk); bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, SHUT_RDWR); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f7b2d0971f24..d4498037fadc 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1297,15 +1297,15 @@ static void restart_le_actions(struct hci_dev *hdev) /* Needed for AUTO_OFF case where might not "really" * have been powered off. */ - list_del_init(&p->action); + hci_pend_le_list_del_init(p); switch (p->auto_connect) { case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(&p->action, &hdev->pend_le_conns); + hci_pend_le_list_add(p, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(&p->action, &hdev->pend_le_reports); + hci_pend_le_list_add(p, &hdev->pend_le_reports); break; default: break; @@ -5169,7 +5169,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - params->flags = current_flags; + WRITE_ONCE(params->flags, current_flags); status = MGMT_STATUS_SUCCESS; /* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY @@ -7285,7 +7285,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - memcpy(&rp.addr, &cp->addr.bdaddr, sizeof(rp.addr)); + memcpy(&rp.addr, &cp->addr, sizeof(rp.addr)); status = mgmt_status(err); if (status == MGMT_STATUS_SUCCESS) { @@ -7580,7 +7580,7 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, if (params->auto_connect == auto_connect) return 0; - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); switch (auto_connect) { case HCI_AUTO_CONN_DISABLED: @@ -7589,18 +7589,18 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, * connect to device, keep connecting. */ if (params->explicit_connect) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: if (params->explicit_connect) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); else - list_add(¶ms->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: if (!is_connected(hdev, addr, addr_type)) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; } @@ -7823,9 +7823,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - list_del(¶ms->action); - list_del(¶ms->list); - kfree(params); + hci_conn_params_free(params); device_removed(sk, hdev, &cp->addr.bdaddr, cp->addr.type); } else { @@ -7856,9 +7854,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, p->auto_connect = HCI_AUTO_CONN_EXPLICIT; continue; } - list_del(&p->action); - list_del(&p->list); - kfree(p); + hci_conn_params_free(p); } bt_dev_dbg(hdev, "All LE connection parameters were removed"); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index cd1a27ac555d..7762604ddfc0 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -126,8 +126,11 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) struct hci_dev *hdev = hcon->hdev; struct sco_conn *conn = hcon->sco_data; - if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + } conn = kzalloc(sizeof(struct sco_conn), GFP_KERNEL); if (!conn) @@ -268,21 +271,21 @@ static int sco_connect(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); - conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); - return -ENOMEM; + err = -ENOMEM; + goto unlock; } - err = sco_chan_add(conn, sk, NULL); - if (err) - return err; - lock_sock(sk); + err = sco_chan_add(conn, sk, NULL); + if (err) { + release_sock(sk); + goto unlock; + } + /* Update source addr of the socket */ bacpy(&sco_pi(sk)->src, &hcon->src); @@ -296,8 +299,6 @@ static int sco_connect(struct sock *sk) release_sock(sk); - return err; - unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 3f04b40f6056..2450690f98cf 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -166,8 +166,9 @@ void br_manage_promisc(struct net_bridge *br) * This lets us disable promiscuous mode and write * this config to hw. */ - if (br->auto_cnt == 0 || - (br->auto_cnt == 1 && br_auto_port(p))) + if ((p->dev->priv_flags & IFF_UNICAST_FLT) && + (br->auto_cnt == 0 || + (br->auto_cnt == 1 && br_auto_port(p)))) br_port_clear_promisc(p); else br_port_set_promisc(p); diff --git a/net/can/bcm.c b/net/can/bcm.c index 9ba35685b043..9168114fc87f 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1526,6 +1526,12 @@ static int bcm_release(struct socket *sock) lock_sock(sk); +#if IS_ENABLED(CONFIG_PROC_FS) + /* remove procfs entry */ + if (net->can.bcmproc_dir && bo->bcm_proc_read) + remove_proc_entry(bo->procname, net->can.bcmproc_dir); +#endif /* CONFIG_PROC_FS */ + list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); @@ -1561,12 +1567,6 @@ static int bcm_release(struct socket *sock) list_for_each_entry_safe(op, next, &bo->rx_ops, list) bcm_remove_op(op); -#if IS_ENABLED(CONFIG_PROC_FS) - /* remove procfs entry */ - if (net->can.bcmproc_dir && bo->bcm_proc_read) - remove_proc_entry(bo->procname, net->can.bcmproc_dir); -#endif /* CONFIG_PROC_FS */ - /* remove device reference */ if (bo->bound) { bo->bound = 0; diff --git a/net/can/raw.c b/net/can/raw.c index 15c79b079184..e10f59375659 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,6 +84,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; struct list_head notifier; int loopback; int recv_own_msgs; @@ -277,7 +278,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (ro->ifindex != dev->ifindex) + if (ro->dev != dev) return; switch (msg) { @@ -292,6 +293,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; release_sock(sk); @@ -337,6 +339,7 @@ static int raw_init(struct sock *sk) ro->bound = 0; ro->ifindex = 0; + ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; @@ -383,21 +386,15 @@ static int raw_release(struct socket *sock) list_del(&ro->notifier); spin_unlock(&raw_notifier_lock); + rtnl_lock(); lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } if (ro->count > 1) @@ -405,6 +402,7 @@ static int raw_release(struct socket *sock) ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); @@ -412,6 +410,8 @@ static int raw_release(struct socket *sock) sock->sk = NULL; release_sock(sk); + rtnl_unlock(); + sock_put(sk); return 0; @@ -422,6 +422,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); + struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; @@ -431,14 +432,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_family != AF_CAN) return -EINVAL; + rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { - struct net_device *dev; - dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; @@ -467,26 +467,20 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), - ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), - dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), + ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } ro->ifindex = ifindex; ro->bound = 1; + ro->dev = dev; } out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -553,9 +547,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; @@ -596,7 +590,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count; out_fil: - dev_put(dev); release_sock(sk); rtnl_unlock(); @@ -614,9 +607,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } @@ -640,7 +633,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask; out_err: - dev_put(dev); release_sock(sk); rtnl_unlock(); @@ -873,7 +865,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) skb->dev = dev; skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index cd7b0bf5369e..5eb4898cccd4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1123,6 +1123,7 @@ bool ceph_addr_is_blank(const struct ceph_entity_addr *addr) return true; } } +EXPORT_SYMBOL(ceph_addr_is_blank); int ceph_addr_port(const struct ceph_entity_addr *addr) { diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 1a888b86a494..1df1d29dee92 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -390,6 +390,8 @@ static int head_onwire_len(int ctrl_len, bool secure) int head_len; int rem_len; + BUG_ON(ctrl_len < 0 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN); + if (secure) { head_len = CEPH_PREAMBLE_SECURE_LEN; if (ctrl_len > CEPH_PREAMBLE_INLINE_LEN) { @@ -408,6 +410,10 @@ static int head_onwire_len(int ctrl_len, bool secure) static int __tail_onwire_len(int front_len, int middle_len, int data_len, bool secure) { + BUG_ON(front_len < 0 || front_len > CEPH_MSG_MAX_FRONT_LEN || + middle_len < 0 || middle_len > CEPH_MSG_MAX_MIDDLE_LEN || + data_len < 0 || data_len > CEPH_MSG_MAX_DATA_LEN); + if (!front_len && !middle_len && !data_len) return 0; @@ -520,29 +526,34 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc) desc->fd_aligns[i] = ceph_decode_16(&p); } - /* - * This would fire for FRAME_TAG_WAIT (it has one empty - * segment), but we should never get it as client. - */ - if (!desc->fd_lens[desc->fd_seg_cnt - 1]) { - pr_err("last segment empty\n"); + if (desc->fd_lens[0] < 0 || + desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) { + pr_err("bad control segment length %d\n", desc->fd_lens[0]); return -EINVAL; } - - if (desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) { - pr_err("control segment too big %d\n", desc->fd_lens[0]); + if (desc->fd_lens[1] < 0 || + desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) { + pr_err("bad front segment length %d\n", desc->fd_lens[1]); return -EINVAL; } - if (desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) { - pr_err("front segment too big %d\n", desc->fd_lens[1]); + if (desc->fd_lens[2] < 0 || + desc->fd_lens[2] > CEPH_MSG_MAX_MIDDLE_LEN) { + pr_err("bad middle segment length %d\n", desc->fd_lens[2]); return -EINVAL; } - if (desc->fd_lens[2] > CEPH_MSG_MAX_MIDDLE_LEN) { - pr_err("middle segment too big %d\n", desc->fd_lens[2]); + if (desc->fd_lens[3] < 0 || + desc->fd_lens[3] > CEPH_MSG_MAX_DATA_LEN) { + pr_err("bad data segment length %d\n", desc->fd_lens[3]); return -EINVAL; } - if (desc->fd_lens[3] > CEPH_MSG_MAX_DATA_LEN) { - pr_err("data segment too big %d\n", desc->fd_lens[3]); + + /* + * This would fire for FRAME_TAG_WAIT (it has one empty + * segment), but we should never get it as client. + */ + if (!desc->fd_lens[desc->fd_seg_cnt - 1]) { + pr_err("last segment empty, segment count %d\n", + desc->fd_seg_cnt); return -EINVAL; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 11c04e7d928e..658a6f2320cf 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3334,17 +3334,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->reg_commit_wait); + ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } -static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq) +static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, + unsigned long timeout) { - int ret; + long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->notify_finish_wait); - return ret ?: lreq->notify_finish_error; + left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, + ceph_timeout_jiffies(timeout)); + if (left <= 0) + left = left ?: -ETIMEDOUT; + else + left = lreq->notify_finish_error; /* completed */ + + return left; } /* @@ -4896,7 +4903,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (!ret) - ret = linger_notify_finish_wait(lreq); + ret = linger_notify_finish_wait(lreq, + msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index d4172534dfa8..cca7594be92e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -496,8 +496,11 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) return ERR_PTR(-EPERM); nla_for_each_nested(nla, nla_stgs, rem) { - if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { + if (nla_len(nla) != sizeof(u32)) + return ERR_PTR(-EINVAL); nr_maps++; + } } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); diff --git a/net/core/filter.c b/net/core/filter.c index 06ba0e56e369..28a59596987a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4116,12 +4116,6 @@ BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) if (unlikely(data_end > data_hard_end)) return -EINVAL; - /* ALL drivers MUST init xdp->frame_sz, chicken check below */ - if (unlikely(xdp->frame_sz > PAGE_SIZE)) { - WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); - return -EINVAL; - } - if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 805b7385dd8d..6aef976bc1da 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -63,4 +63,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum); +EXPORT_TRACEPOINT_SYMBOL_GPL(udp_fail_queue_rcv_skb); + EXPORT_TRACEPOINT_SYMBOL_GPL(sk_data_ready); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3ad4e030846d..aef25aa5cf1d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5140,13 +5140,17 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; have_flags = true; flags = nla_get_u16(attr); - break; + } + + if (nla_type(attr) == IFLA_BRIDGE_MODE) { + if (nla_len(attr) < sizeof(u16)) + return -EINVAL; } } } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6c5915efbc17..a298992060e6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4261,6 +4261,11 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_push(skb, -skb_network_offset(skb) + offset); + /* Ensure the head is writeable before touching the shared info */ + err = skb_unclone(skb, GFP_ATOMIC); + if (err) + goto err_linearize; + skb_shinfo(skb)->frag_list = NULL; while (list_skb) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a29508e1ff35..ef1a2eb6520b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1120,13 +1120,19 @@ static void sk_psock_strp_data_ready(struct sock *sk) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { + int ret; + static const struct strp_callbacks cb = { .rcv_msg = sk_psock_strp_read, .read_sock_done = sk_psock_strp_read_done, .parse_msg = sk_psock_strp_parse, }; - return strp_init(&psock->strp, sk, &cb); + ret = strp_init(&psock->strp, sk, &cb); + if (!ret) + sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + + return ret; } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) @@ -1154,7 +1160,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ - if (psock->progs.stream_parser) + if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED)) strp_done(&psock->strp); } #else diff --git a/net/core/sock.c b/net/core/sock.c index 9370fd50aa2c..732fc37a4771 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -429,6 +429,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, { struct __kernel_sock_timeval tv; int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + long val; if (err) return err; @@ -439,7 +440,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, if (tv.tv_sec < 0) { static int warned __read_mostly; - *timeo_p = 0; + WRITE_ONCE(*timeo_p, 0); if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", @@ -447,11 +448,12 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, } return 0; } - *timeo_p = MAX_SCHEDULE_TIMEOUT; - if (tv.tv_sec == 0 && tv.tv_usec == 0) - return 0; - if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) - *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); + val = MAX_SCHEDULE_TIMEOUT; + if ((tv.tv_sec || tv.tv_usec) && + (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))) + val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, + USEC_PER_SEC / HZ); + WRITE_ONCE(*timeo_p, val); return 0; } @@ -804,7 +806,7 @@ EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { lock_sock(sk); - sk->sk_priority = priority; + WRITE_ONCE(sk->sk_priority, priority); release_sock(sk); } EXPORT_SYMBOL(sock_set_priority); @@ -813,9 +815,9 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs) { lock_sock(sk); if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) - sk->sk_sndtimeo = secs * HZ; + WRITE_ONCE(sk->sk_sndtimeo, secs * HZ); else - sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT); release_sock(sk); } EXPORT_SYMBOL(sock_set_sndtimeo); @@ -988,7 +990,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { - sk->sk_mark = val; + WRITE_ONCE(sk->sk_mark, val); sk_dst_reset(sk); } } @@ -1007,7 +1009,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes) bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); - sk->sk_reserved_mem -= bytes; + WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes); sk_mem_reclaim(sk); } @@ -1044,7 +1046,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes) } sk->sk_forward_alloc += pages << PAGE_SHIFT; - sk->sk_reserved_mem += pages << PAGE_SHIFT; + WRITE_ONCE(sk->sk_reserved_mem, + sk->sk_reserved_mem + (pages << PAGE_SHIFT)); return 0; } @@ -1213,7 +1216,7 @@ set_sndbuf: if ((val >= 0 && val <= 6) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - sk->sk_priority = val; + WRITE_ONCE(sk->sk_priority, val); else ret = -EPERM; break; @@ -1438,7 +1441,8 @@ set_sndbuf: cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = ulval; + /* Pairs with READ_ONCE() from sk_getsockopt() */ + WRITE_ONCE(sk->sk_max_pacing_rate, ulval); sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; } @@ -1533,7 +1537,9 @@ set_sndbuf: } if ((u8)val == SOCK_TXREHASH_DEFAULT) val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* Paired with READ_ONCE() in tcp_rtx_synack() */ + /* Paired with READ_ONCE() in tcp_rtx_synack() + * and sk_getsockopt(). + */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -1633,11 +1639,11 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_SNDBUF: - v.val = sk->sk_sndbuf; + v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: - v.val = sk->sk_rcvbuf; + v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: @@ -1679,7 +1685,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_PRIORITY: - v.val = sk->sk_priority; + v.val = READ_ONCE(sk->sk_priority); break; case SO_LINGER: @@ -1717,16 +1723,18 @@ int sk_getsockopt(struct sock *sk, int level, int optname, case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: - lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); + lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v, + SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: - lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); + lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v, + SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: - v.val = sk->sk_rcvlowat; + v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: @@ -1770,7 +1778,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, spin_unlock(&sk->sk_peer_lock); if (!peer_pid) - return -ESRCH; + return -ENODATA; pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file); put_pid(peer_pid); @@ -1843,7 +1851,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, optval, optlen, len); case SO_MARK: - v.val = sk->sk_mark; + v.val = READ_ONCE(sk->sk_mark); break; case SO_RCVMARK: @@ -1862,7 +1870,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, if (!sock->ops->set_peek_off) return -EOPNOTSUPP; - v.val = sk->sk_peek_off; + v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); @@ -1892,7 +1900,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: - v.val = sk->sk_ll_usec; + v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); @@ -1900,12 +1908,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #endif case SO_MAX_PACING_RATE: + /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); - v.ulval = sk->sk_max_pacing_rate; + v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ - v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U); + v.val = min_t(unsigned long, ~0U, + READ_ONCE(sk->sk_max_pacing_rate)); } break; @@ -1973,11 +1983,12 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RESERVE_MEM: - v.val = sk->sk_reserved_mem; + v.val = READ_ONCE(sk->sk_reserved_mem); break; case SO_TXREHASH: - v.val = sk->sk_txrehash; + /* Paired with WRITE_ONCE() in sk_setsockopt() */ + v.val = READ_ONCE(sk->sk_txrehash); break; default: @@ -3168,7 +3179,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 19538d628714..8f07fea39d9e 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -115,7 +115,6 @@ static void sock_map_sk_acquire(struct sock *sk) __acquires(&sk->sk_lock.slock) { lock_sock(sk); - preempt_disable(); rcu_read_lock(); } @@ -123,7 +122,6 @@ static void sock_map_sk_release(struct sock *sk) __releases(&sk->sk_lock.slock) { rcu_read_unlock(); - preempt_enable(); release_sock(sk); } @@ -148,13 +146,13 @@ static void sock_map_del_link(struct sock *sk, list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; - struct bpf_stab *stab = container_of(map, struct bpf_stab, - map); - if (psock->saved_data_ready && stab->progs.stream_parser) + struct sk_psock_progs *progs = sock_map_progs(map); + + if (psock->saved_data_ready && progs->stream_parser) strp_stop = true; - if (psock->saved_data_ready && stab->progs.stream_verdict) + if (psock->saved_data_ready && progs->stream_verdict) verdict_stop = true; - if (psock->saved_data_ready && stab->progs.skb_verdict) + if (psock->saved_data_ready && progs->skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); diff --git a/net/core/xdp.c b/net/core/xdp.c index 41e5ca8643ec..8362130bf085 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -741,7 +741,7 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, __diag_pop(); BTF_SET8_START(xdp_metadata_kfunc_ids) -#define XDP_METADATA_KFUNC(_, name) BTF_ID_FLAGS(func, name, 0) +#define XDP_METADATA_KFUNC(_, name) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC BTF_SET8_END(xdp_metadata_kfunc_ids) diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index c0c438128575..2e6b8c8fd2de 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -980,7 +980,7 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX, - tb[DCB_ATTR_BCN], dcbnl_pfc_up_nest, + tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 7249ef218178..d29d1163203d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -238,8 +238,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass, - sk->sk_priority); + err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt, + np->tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/dccp/output.c b/net/dccp/output.c index b8a24734385e..fd2eb148d24d 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -187,7 +187,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; - dp->dccps_mss_cache = cur_mps; + WRITE_ONCE(dp->dccps_mss_cache, cur_mps); return cur_mps; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index f331e5977a84..4e3266e4d7c3 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -630,7 +630,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: - val = dp->dccps_mss_cache; + val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); @@ -739,7 +739,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) trace_dccp_probe(sk, len); - if (len > dp->dccps_mss_cache) + if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); @@ -772,6 +772,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out_discard; } + /* We need to check dccps_mss_cache after socket is locked. */ + if (len > dp->dccps_mss_cache) { + rc = -EMSGSIZE; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/dsa/port.c b/net/dsa/port.c index 0ce8fd311c78..2f6195d7b741 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1727,8 +1727,15 @@ int dsa_port_phylink_create(struct dsa_port *dp) ds->ops->phylink_mac_an_restart) dp->pl_config.legacy_pre_march2020 = true; - if (ds->ops->phylink_get_caps) + if (ds->ops->phylink_get_caps) { ds->ops->phylink_get_caps(ds, dp->index, &dp->pl_config); + } else { + /* For legacy drivers */ + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + dp->pl_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_GMII, + dp->pl_config.supported_interfaces); + } pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn), mode, &dsa_port_phylink_mac_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index a5f3b73da417..ade3eeb2f3e6 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -58,11 +58,8 @@ #define SJA1110_TX_TRAILER_LEN 4 #define SJA1110_MAX_PADDING_LEN 15 -#define SJA1105_HWTS_RX_EN 0 - struct sja1105_tagger_private { struct sja1105_tagger_data data; /* Must be first */ - unsigned long state; /* Protects concurrent access to the meta state machine * from taggers running on multiple ports on SMP systems */ @@ -118,8 +115,8 @@ static void sja1105_meta_unpack(const struct sk_buff *skb, * a unified unpacking command for both device series. */ packing(buf, &meta->tstamp, 31, 0, 4, UNPACK, 0); - packing(buf + 4, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0); - packing(buf + 5, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0); + packing(buf + 4, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0); + packing(buf + 5, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0); packing(buf + 6, &meta->source_port, 7, 0, 1, UNPACK, 0); packing(buf + 7, &meta->switch_id, 7, 0, 1, UNPACK, 0); } @@ -392,10 +389,6 @@ static struct sk_buff priv = sja1105_tagger_private(ds); - if (!test_bit(SJA1105_HWTS_RX_EN, &priv->state)) - /* Do normal processing. */ - return skb; - spin_lock(&priv->meta_lock); /* Was this a link-local frame instead of the meta * that we were expecting? @@ -431,12 +424,6 @@ static struct sk_buff priv = sja1105_tagger_private(ds); - /* Drop the meta frame if we're not in the right state - * to process it. - */ - if (!test_bit(SJA1105_HWTS_RX_EN, &priv->state)) - return NULL; - spin_lock(&priv->meta_lock); stampable_skb = priv->stampable_skb; @@ -472,30 +459,6 @@ static struct sk_buff return skb; } -static bool sja1105_rxtstamp_get_state(struct dsa_switch *ds) -{ - struct sja1105_tagger_private *priv = sja1105_tagger_private(ds); - - return test_bit(SJA1105_HWTS_RX_EN, &priv->state); -} - -static void sja1105_rxtstamp_set_state(struct dsa_switch *ds, bool on) -{ - struct sja1105_tagger_private *priv = sja1105_tagger_private(ds); - - if (on) - set_bit(SJA1105_HWTS_RX_EN, &priv->state); - else - clear_bit(SJA1105_HWTS_RX_EN, &priv->state); - - /* Initialize the meta state machine to a known state */ - if (!priv->stampable_skb) - return; - - kfree_skb(priv->stampable_skb); - priv->stampable_skb = NULL; -} - static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) { u16 tpid = ntohs(eth_hdr(skb)->h_proto); @@ -545,33 +508,53 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); - if (sja1105_skb_has_tag_8021q(skb)) { - /* Normal traffic path. */ - sja1105_vlan_rcv(skb, &source_port, &switch_id, &vbid, &vid); - } else if (is_link_local) { + if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of * the incl_srcpt options. */ source_port = hdr->h_dest[3]; switch_id = hdr->h_dest[4]; - /* Clear the DMAC bytes that were mangled by the switch */ - hdr->h_dest[3] = 0; - hdr->h_dest[4] = 0; } else if (is_meta) { sja1105_meta_unpack(skb, &meta); source_port = meta.source_port; switch_id = meta.switch_id; - } else { + } + + /* Normal data plane traffic and link-local frames are tagged with + * a tag_8021q VLAN which we have to strip + */ + if (sja1105_skb_has_tag_8021q(skb)) { + int tmp_source_port = -1, tmp_switch_id = -1; + + sja1105_vlan_rcv(skb, &tmp_source_port, &tmp_switch_id, &vbid, + &vid); + /* Preserve the source information from the INCL_SRCPT option, + * if available. This allows us to not overwrite a valid source + * port and switch ID with zeroes when receiving link-local + * frames from a VLAN-unaware bridged port (non-zero vbid) or a + * VLAN-aware bridged port (non-zero vid). Furthermore, the + * tag_8021q source port information is only of trust when the + * vbid is 0 (precise port). Otherwise, tmp_source_port and + * tmp_switch_id will be zeroes. + */ + if (vbid == 0 && source_port == -1) + source_port = tmp_source_port; + if (vbid == 0 && switch_id == -1) + switch_id = tmp_switch_id; + } else if (source_port == -1 && switch_id == -1) { + /* Packets with no source information have no chance of + * getting accepted, drop them straight away. + */ return NULL; } - if (vbid >= 1) + if (source_port != -1 && switch_id != -1) + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + else if (vbid >= 1) skb->dev = dsa_tag_8021q_find_port_by_vbid(netdev, vbid); - else if (source_port == -1 || switch_id == -1) - skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); else - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); if (!skb->dev) { netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; @@ -762,7 +745,6 @@ static void sja1105_disconnect(struct dsa_switch *ds) static int sja1105_connect(struct dsa_switch *ds) { - struct sja1105_tagger_data *tagger_data; struct sja1105_tagger_private *priv; struct kthread_worker *xmit_worker; int err; @@ -782,10 +764,6 @@ static int sja1105_connect(struct dsa_switch *ds) } priv->xmit_worker = xmit_worker; - /* Export functions for switch driver use */ - tagger_data = &priv->data; - tagger_data->rxtstamp_get_state = sja1105_rxtstamp_get_state; - tagger_data->rxtstamp_set_state = sja1105_rxtstamp_set_state; ds->tagger_data = priv; return 0; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index ba06ed42e428..2be2d4922557 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1132,7 +1132,7 @@ static int esp_init_authenc(struct xfrm_state *x, err = crypto_aead_setkey(aead, key, keylen); free_key: - kfree(key); + kfree_sensitive(key); error: return err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0cc19cfbb673..aeebe8816689 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1019,7 +1019,7 @@ static void reqsk_timer_handler(struct timer_list *t) icsk = inet_csk(sk_listener); net = sock_net(sk_listener); - max_syn_ack_retries = icsk->icsk_syn_retries ? : + max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index b812eb36f0e3..f7426926a104 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -150,7 +150,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif - if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark))) goto errout; if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || @@ -799,7 +799,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.ifindex = sk->sk_bound_dev_if; entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; if (sk_fullsock(sk)) - entry.mark = sk->sk_mark; + entry.mark = READ_ONCE(sk->sk_mark); else if (sk->sk_state == TCP_NEW_SYN_RECV) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; else if (sk->sk_state == TCP_TIME_WAIT) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e7391bf310a7..0819d6001b9a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -650,20 +650,8 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_hashed(osk); - if (ret) { - /* Before deleting the node, we insert a new one to make - * sure that the look-up-sk process would not miss either - * of them and that at least one node would exist in ehash - * table all the time. Otherwise there's a tiny chance - * that lookup process could find nothing in ehash table. - */ - __sk_nulls_add_node_tail_rcu(sk, list); - sk_nulls_del_node_init_rcu(osk); - } - goto unlock; - } - if (found_dup_sk) { + ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -672,7 +660,6 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); -unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 40052414c7c7..2c1b245dba8e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -88,10 +88,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_tail_rcu(&tw->tw_node, list); + hlist_nulls_add_head_rcu(&tw->tw_node, list); } static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -144,7 +144,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - inet_twsk_add_node_tail_rcu(tw, &ehead->chain); + inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 81a1cce1a7d1..22a26d1d29a0 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -548,7 +548,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto err_free_skb; truncate = true; } @@ -689,7 +690,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto free_skb; truncate = true; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6e70839257f7..6ba1a0fafbaa 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -184,9 +184,9 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, ip_options_build(skb, &opt->opt, daddr, rt); } - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); @@ -528,8 +528,8 @@ packet_routed: skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); @@ -1158,10 +1158,15 @@ alloc_new_skb: } copy = datalen - transhdrlen - fraggap - pagedlen; + /* [!] NOTE: copy will be negative if pagedlen>0 + * because then the equation reduces to -fraggap. + */ if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; + } else if (flags & MSG_SPLICE_PAGES) { + copy = 0; } offset += copy; @@ -1209,6 +1214,10 @@ alloc_new_skb: } else if (flags & MSG_SPLICE_PAGES) { struct msghdr *msg = from; + err = -EIO; + if (WARN_ON_ONCE(copy > msg->msg_iter.count)) + goto error; + err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 8e97d8d4cc9d..d41bce8927b2 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -592,7 +592,7 @@ void __ip_sock_set_tos(struct sock *sk, int val) } if (inet_sk(sk)->tos != val) { inet_sk(sk)->tos = val; - sk->sk_priority = rt_tos2priority(val); + WRITE_ONCE(sk->sk_priority, rt_tos2priority(val)); sk_dst_reset(sk); } } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 92c02c886fe7..586b1b3e35b8 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) .un.frag.__unused = 0, .un.frag.mtu = htons(mtu), }; - icmph->checksum = ip_compute_csum(icmph, len); + icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0)); skb_reset_transport_header(skb); niph = skb_push(skb, sizeof(*niph)); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index f95142e56da0..be5498f5dd31 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3221,13 +3221,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) &rtm_dump_nexthop_cb, &filter); if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3367,25 +3363,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, dd->filter.res_bucket_nh_id != nhge->nh->id) continue; + dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); - if (err < 0) { - if (likely(skb->len)) - goto out; - goto out_err; - } + if (err) + return err; } dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; - bucket_index = 0; + dd->ctx->bucket_index = 0; -out: - err = skb->len; -out_err: - dd->ctx->bucket_index = bucket_index; - return err; + return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, @@ -3434,13 +3424,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 7782ff5e6539..cb381f5aa464 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -348,7 +348,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_dst_set(skb, &rt->dst); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 98d7e6ba7493..92fede388d52 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -518,7 +518,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct inet_sock *inet = inet_sk(sk); oif = sk->sk_bound_dev_if; - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; @@ -552,7 +552,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; - flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e03e08745308..8ed52e1e3c99 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3291,7 +3291,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - inet_csk(sk)->icsk_syn_retries = val; + WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); release_sock(sk); return 0; } @@ -3300,7 +3300,7 @@ EXPORT_SYMBOL(tcp_sock_set_syncnt); void tcp_sock_set_user_timeout(struct sock *sk, u32 val) { lock_sock(sk); - inet_csk(sk)->icsk_user_timeout = val; + WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_user_timeout); @@ -3312,7 +3312,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; - tp->keepalive_time = val * HZ; + /* Paired with WRITE_ONCE() in keepalive_time_when() */ + WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); @@ -3344,7 +3345,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_intvl = val * HZ; + WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); release_sock(sk); return 0; } @@ -3356,7 +3357,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_probes = val; + /* Paired with READ_ONCE() in keepalive_probes() */ + WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } @@ -3558,19 +3560,19 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPINTVL) err = -EINVAL; else - tp->keepalive_intvl = val * HZ; + WRITE_ONCE(tp->keepalive_intvl, val * HZ); break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else - tp->keepalive_probes = val; + WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else - icsk->icsk_syn_retries = val; + WRITE_ONCE(icsk->icsk_syn_retries, val); break; case TCP_SAVE_SYN: @@ -3583,18 +3585,18 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; + WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) - tp->linger2 = TCP_FIN_TIMEOUT_MAX; + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ - icsk->icsk_accept_queue.rskq_defer_accept = - secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, - TCP_RTO_MAX / HZ); + WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: @@ -3618,7 +3620,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 0) err = -EINVAL; else - icsk->icsk_user_timeout = val; + WRITE_ONCE(icsk->icsk_user_timeout, val); break; case TCP_FASTOPEN: @@ -3656,13 +3658,13 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp_raw(); + WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -3674,7 +3676,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); - tp->tcp_tx_delay = val; + WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; @@ -3991,17 +3993,18 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : + val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: - val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, - TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); + val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); + val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; @@ -4138,11 +4141,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_USER_TIMEOUT: - val = icsk->icsk_user_timeout; + val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: - val = icsk->icsk_accept_queue.fastopenq.max_qlen; + val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: @@ -4154,14 +4157,14 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TX_DELAY: - val = tp->tcp_tx_delay; + val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + tp->tsoffset; + val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 45cc7f1ca296..85e4953f1182 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -296,6 +296,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; + int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying @@ -308,10 +309,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq->max_qlen == 0) + max_qlen = READ_ONCE(fastopenq->max_qlen); + if (max_qlen == 0) return false; - if (fastopenq->qlen >= fastopenq->max_qlen) { + if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6f072095211e..57c8af1859c1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3590,8 +3590,11 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, u32 *last_oow_ack_time) { - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time); + /* Paired with the WRITE_ONCE() in this function. */ + u32 val = READ_ONCE(*last_oow_ack_time); + + if (val) { + s32 elapsed = (s32)(tcp_jiffies32 - val); if (0 <= elapsed && elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) { @@ -3600,7 +3603,10 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, } } - *last_oow_ack_time = tcp_jiffies32; + /* Paired with the prior READ_ONCE() and with itself, + * as we might be lockless. + */ + WRITE_ONCE(*last_oow_ack_time, tcp_jiffies32); return false; /* not rate-limited: go ahead, send dupack now! */ } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd365de4d5ff..a59cc4b83861 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -307,8 +307,9 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port)); - tp->tsoffset = secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr); + WRITE_ONCE(tp->tsoffset, + secure_tcp_ts_off(net, inet->inet_saddr, + inet->inet_daddr)); } inet->inet_id = get_random_u16(); @@ -930,9 +931,9 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk = this_cpu_read(ipv4_tcp_sk); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_mark : sk->sk_mark; + inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_priority : sk->sk_priority; + inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -988,11 +989,12 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, + READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, - ip_hdr(skb)->tos, tcp_rsk(req)->txhash); + ip_hdr(skb)->tos, + READ_ONCE(tcp_rsk(req)->txhash)); } /* diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 82f4575f9cd9..99ac5efe244d 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -40,7 +40,7 @@ struct tcp_fastopen_metrics { struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; - possible_net_t tcpm_net; + struct net *tcpm_net; struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; @@ -51,34 +51,38 @@ struct tcp_metrics_block { struct rcu_head rcu_head; }; -static inline struct net *tm_net(struct tcp_metrics_block *tm) +static inline struct net *tm_net(const struct tcp_metrics_block *tm) { - return read_pnet(&tm->tcpm_net); + /* Paired with the WRITE_ONCE() in tcpm_new() */ + return READ_ONCE(tm->tcpm_net); } static bool tcp_metric_locked(struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_lock & (1 << idx); + /* Paired with WRITE_ONCE() in tcpm_suck_dst() */ + return READ_ONCE(tm->tcpm_lock) & (1 << idx); } -static u32 tcp_metric_get(struct tcp_metrics_block *tm, +static u32 tcp_metric_get(const struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_vals[idx]; + /* Paired with WRITE_ONCE() in tcp_metric_set() */ + return READ_ONCE(tm->tcpm_vals[idx]); } static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) { - tm->tcpm_vals[idx] = val; + /* Paired with READ_ONCE() in tcp_metric_get() */ + WRITE_ONCE(tm->tcpm_vals[idx], val); } static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - return inetpeer_addr_cmp(a, b) == 0; + return (a->family == b->family) && !inetpeer_addr_cmp(a, b); } struct tcpm_hash_bucket { @@ -89,6 +93,7 @@ static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly; static unsigned int tcp_metrics_hash_log __read_mostly; static DEFINE_SPINLOCK(tcp_metrics_lock); +static DEFINE_SEQLOCK(fastopen_seqlock); static void tcpm_suck_dst(struct tcp_metrics_block *tm, const struct dst_entry *dst, @@ -97,7 +102,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, u32 msval; u32 val; - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); val = 0; if (dst_metric_locked(dst, RTAX_RTT)) @@ -110,30 +115,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, val |= 1 << TCP_METRIC_CWND; if (dst_metric_locked(dst, RTAX_REORDERING)) val |= 1 << TCP_METRIC_REORDERING; - tm->tcpm_lock = val; + /* Paired with READ_ONCE() in tcp_metric_locked() */ + WRITE_ONCE(tm->tcpm_lock, val); msval = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC); msval = dst_metric_raw(dst, RTAX_RTTVAR); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; - tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); - tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); - tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC); + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + dst_metric_raw(dst, RTAX_SSTHRESH)); + tcp_metric_set(tm, TCP_METRIC_CWND, + dst_metric_raw(dst, RTAX_CWND)); + tcp_metric_set(tm, TCP_METRIC_REORDERING, + dst_metric_raw(dst, RTAX_REORDERING)); if (fastopen_clear) { + write_seqlock(&fastopen_seqlock); tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; tm->tcpm_fastopen.try_exp = 0; tm->tcpm_fastopen.cookie.exp = false; tm->tcpm_fastopen.cookie.len = 0; + write_sequnlock(&fastopen_seqlock); } } #define TCP_METRICS_TIMEOUT (60 * 60 * HZ) -static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +static void tcpm_check_stamp(struct tcp_metrics_block *tm, + const struct dst_entry *dst) { - if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + unsigned long limit; + + if (!tm) + return; + limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT; + if (unlikely(time_after(jiffies, limit))) tcpm_suck_dst(tm, dst, false); } @@ -174,20 +191,23 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, oldest = deref_locked(tcp_metrics_hash[hash].chain); for (tm = deref_locked(oldest->tcpm_next); tm; tm = deref_locked(tm->tcpm_next)) { - if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) + if (time_before(READ_ONCE(tm->tcpm_stamp), + READ_ONCE(oldest->tcpm_stamp))) oldest = tm; } tm = oldest; } else { - tm = kmalloc(sizeof(*tm), GFP_ATOMIC); + tm = kzalloc(sizeof(*tm), GFP_ATOMIC); if (!tm) goto out_unlock; } - write_pnet(&tm->tcpm_net, net); + /* Paired with the READ_ONCE() in tm_net() */ + WRITE_ONCE(tm->tcpm_net, net); + tm->tcpm_saddr = *saddr; tm->tcpm_daddr = *daddr; - tcpm_suck_dst(tm, dst, true); + tcpm_suck_dst(tm, dst, reclaim); if (likely(!reclaim)) { tm->tcpm_next = tcp_metrics_hash[hash].chain; @@ -434,7 +454,7 @@ void tcp_update_metrics(struct sock *sk) tp->reordering); } } - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); out_unlock: rcu_read_unlock(); } @@ -539,8 +559,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) return ret; } -static DEFINE_SEQLOCK(fastopen_seqlock); - void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { @@ -647,7 +665,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, } if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE, - jiffies - tm->tcpm_stamp, + jiffies - READ_ONCE(tm->tcpm_stamp), TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; @@ -658,7 +676,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, if (!nest) goto nla_put_failure; for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { - u32 val = tm->tcpm_vals[i]; + u32 val = tcp_metric_get(tm, i); if (!val) continue; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 04fc328727e6..c8f2aa003387 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -528,7 +528,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->lsndtime = tcp_jiffies32; - newsk->sk_txhash = treq->txhash; + newsk->sk_txhash = READ_ONCE(treq->txhash); newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); @@ -555,7 +555,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { @@ -619,7 +619,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { - tmp_opt.ts_recent = req->ts_recent; + tmp_opt.ts_recent = READ_ONCE(req->ts_recent); if (tmp_opt.rcv_tsecr) tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off; /* We do not store true stamp, but it is not required, @@ -758,8 +758,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ + /* TODO: We probably should defer ts_recent change once + * we take ownership of @req. + */ if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - req->ts_recent = tmp_opt.rcv_tsval; + WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2cb39b6dad02..51d8638d4b4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -878,7 +878,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; - opts->tsecr = req->ts_recent; + opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { @@ -3660,7 +3660,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif - skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, @@ -4210,7 +4210,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) - tcp_rsk(req)->txhash = net_tx_rndhash(); + WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 470f581eedd4..206418b6d7c4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -591,7 +591,9 @@ out_reset_timer: tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; - icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX); + icsk->icsk_rto = clamp(__tcp_set_rto(tp), + tcp_rto_min(sk), + TCP_RTO_MAX); } else if (sk->sk_state != TCP_SYN_SENT || icsk->icsk_backoff > READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 42a96b3547c9..abfa860367aa 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -114,6 +114,7 @@ #include <net/sock_reuseport.h> #include <net/addrconf.h> #include <net/udp_tunnel.h> +#include <net/gro.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif @@ -555,10 +556,13 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, { const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet_get_iif_sdif(skb, &iif, &sdif); return __udp4_lib_lookup(net, iph->saddr, sport, - iph->daddr, dport, inet_iif(skb), - inet_sdif(skb), net->ipv4.udp_table, NULL); + iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); } /* Must be called under rcu_read_lock(). diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 75aa4de5b731..0f46b3c2e4ac 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -274,13 +274,20 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, __sum16 check; __be16 newlen; - if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) - return __udp_gso_segment_list(gso_skb, features, is_ipv6); - mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), + mss); + return NULL; + } + + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) + return __udp_gso_segment_list(gso_skb, features, is_ipv6); + skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ @@ -388,8 +395,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; @@ -603,10 +609,13 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, { const struct iphdr *iph = skb_gro_network_header(skb); struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet_get_iif_sdif(skb, &iif, &sdif); return __udp4_lib_lookup(net, iph->saddr, sport, - iph->daddr, dport, inet_iif(skb), - inet_sdif(skb), net->ipv4.udp_table, NULL); + iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5479da08ef40..94cec2075eee 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -318,9 +318,8 @@ static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) static void addrconf_mod_rs_timer(struct inet6_dev *idev, unsigned long when) { - if (!timer_pending(&idev->rs_timer)) + if (!mod_timer(&idev->rs_timer, jiffies + when)) in6_dev_hold(idev); - mod_timer(&idev->rs_timer, jiffies + when); } static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, @@ -2562,12 +2561,18 @@ static void manage_tempaddrs(struct inet6_dev *idev, ipv6_ifa_notify(0, ift); } - if ((create || list_empty(&idev->tempaddr_list)) && - idev->cnf.use_tempaddr > 0) { + /* Also create a temporary address if it's enabled but no temporary + * address currently exists. + * However, we get called with valid_lft == 0, prefered_lft == 0, create == false + * as part of cleanup (ie. deleting the mngtmpaddr). + * We don't want that to result in creating a new temporary ip address. + */ + if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft)) + create = true; + + if (create && idev->cnf.use_tempaddr > 0) { /* When a new public address is created as described * in [ADDRCONF], also create a new temporary address. - * Also create a temporary address if it's enabled but - * no temporary address currently exists. */ read_unlock_bh(&idev->lock); ipv6_create_tempaddr(ifp, false); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 9edf1f45b1ed..65fa5014bc85 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -424,7 +424,10 @@ static struct net_device *icmp6_dev(const struct sk_buff *skb) if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); - if (rt6) + /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.), + * and ip6_null_entry could be set to skb if no route is found. + */ + if (rt6 && rt6->rt6i_idev) dev = rt6->rt6i_idev->dev; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index da80974ad23a..070d87abf7c0 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -955,7 +955,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto tx_err; truncate = true; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index cc3d5ad17257..67a3b8f6e72b 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1073,7 +1073,7 @@ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ - skb_push(skb, -skb_network_offset(pkt)); + __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 18634ebd20a4..a42be96ae209 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64 || diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index f804c11e2146..c2c291827a2c 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -120,7 +120,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init_sk(&ipc6, np); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); fl6.flowi6_oif = oif; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ac1cef094c5f..49381f35b623 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -614,7 +614,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; @@ -774,12 +774,12 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = fl6.flowi6_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 64e873f5895f..56a55585eb79 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2951,7 +2951,8 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); - ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid); + ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), + sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || @@ -3172,8 +3173,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark, - sk->sk_uid); + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + READ_ONCE(sk->sk_mark), sk->sk_uid); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 40dd92a2f480..6e86721e1cdb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -564,8 +564,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, - tclass, sk->sk_priority); + err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark), + opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -939,7 +939,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); skb_set_delivery_time(buff, tcp_transmit_time(sk), true); } if (txhash) { @@ -1126,10 +1126,11 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, sk->sk_bound_dev_if, + READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), - ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, - tcp_rsk(req)->txhash); + ipv6_get_dsfield(ipv6_hdr(skb)), 0, + READ_ONCE(sk->sk_priority), + READ_ONCE(tcp_rsk(req)->txhash)); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 317b01c9bc39..f787e6b8424c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -45,11 +45,13 @@ #include <net/tcp_states.h> #include <net/ip6_checksum.h> #include <net/ip6_tunnel.h> +#include <trace/events/udp.h> #include <net/xfrm.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/busy_poll.h> #include <net/sock_reuseport.h> +#include <net/gro.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -90,7 +92,7 @@ static u32 udp6_ehashfn(const struct net *net, fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, - udp_ipv6_hash_secret + net_hash_mix(net)); + udp6_ehash_secret + net_hash_mix(net)); } int udp_v6_get_port(struct sock *sk, unsigned short snum) @@ -299,10 +301,13 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, { const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet6_get_iif_sdif(skb, &iif, &sdif); return __udp6_lib_lookup(net, &iph->saddr, sport, - &iph->daddr, dport, inet6_iif(skb), - inet6_sdif(skb), net->ipv4.udp_table, NULL); + &iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); } /* Must be called under rcu_read_lock(). @@ -623,7 +628,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == NDISC_REDIRECT) { if (tunnel) { ip6_redirect(skb, sock_net(sk), inet6_iif(skb), - sk->sk_mark, sk->sk_uid); + READ_ONCE(sk->sk_mark), sk->sk_uid); } else { ip6_sk_redirect(skb, sk); } @@ -680,6 +685,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb_reason(skb, drop_reason); + trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } @@ -1354,7 +1360,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); /* destination address check */ if (sin6) { diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ad3b8726873e..6b95ba241ebe 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -43,8 +43,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; @@ -119,10 +118,13 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, { const struct ipv6hdr *iph = skb_gro_network_header(skb); struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet6_get_iif_sdif(skb, &iif, &sdif); return __udp6_lib_lookup(net, &iph->saddr, sport, - &iph->daddr, dport, inet6_iif(skb), - inet6_sdif(skb), net->ipv4.udp_table, NULL); + &iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index b1623f9c4f92..ff78217f0cb1 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -519,7 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Get and verify the address */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 57c35c960b2c..9b06c380866b 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -402,7 +402,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) memcpy(laddr.mac, addr->sllc_mac, IFHWADDRLEN); laddr.lsap = addr->sllc_sap; rc = -EADDRINUSE; /* mac + sap clash. */ - ask = llc_lookup_established(sap, &daddr, &laddr); + ask = llc_lookup_established(sap, &daddr, &laddr, &init_net); if (ask) { sock_put(ask); goto out_put; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 912aa9bd5e29..d037009ee10f 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -453,11 +453,13 @@ static int llc_exec_conn_trans_actions(struct sock *sk, static inline bool llc_estab_match(const struct llc_sap *sap, const struct llc_addr *daddr, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); - return llc->laddr.lsap == laddr->lsap && + return net_eq(sock_net(sk), net) && + llc->laddr.lsap == laddr->lsap && llc->daddr.lsap == daddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac) && ether_addr_equal(llc->daddr.mac, daddr->mac); @@ -468,6 +470,7 @@ static inline bool llc_estab_match(const struct llc_sap *sap, * @sap: SAP * @daddr: address of remote LLC (MAC + SAP) * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection using the remote * mac, remote sap, local mac, and local sap. Returns pointer for @@ -476,7 +479,8 @@ static inline bool llc_estab_match(const struct llc_sap *sap, */ static struct sock *__llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -486,12 +490,12 @@ static struct sock *__llc_lookup_established(struct llc_sap *sap, rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_estab_match(sap, daddr, laddr, rc)) { + if (llc_estab_match(sap, daddr, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_estab_match(sap, daddr, laddr, rc))) { + !llc_estab_match(sap, daddr, laddr, rc, net))) { sock_put(rc); continue; } @@ -513,29 +517,33 @@ found: struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *sk; local_bh_disable(); - sk = __llc_lookup_established(sap, daddr, laddr); + sk = __llc_lookup_established(sap, daddr, laddr, net); local_bh_enable(); return sk; } static inline bool llc_listener_match(const struct llc_sap *sap, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); - return sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && + return net_eq(sock_net(sk), net) && + sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && llc->laddr.lsap == laddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac); } static struct sock *__llc_lookup_listener(struct llc_sap *sap, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -545,12 +553,12 @@ static struct sock *__llc_lookup_listener(struct llc_sap *sap, rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_listener_match(sap, laddr, rc)) { + if (llc_listener_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_listener_match(sap, laddr, rc))) { + !llc_listener_match(sap, laddr, rc, net))) { sock_put(rc); continue; } @@ -574,6 +582,7 @@ found: * llc_lookup_listener - Finds listener for local MAC + SAP * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection listening on * local mac, and local sap. Returns pointer for parent socket found, @@ -581,24 +590,26 @@ found: * Caller has to make sure local_bh is disabled. */ static struct sock *llc_lookup_listener(struct llc_sap *sap, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { + struct sock *rc = __llc_lookup_listener(sap, laddr, net); static struct llc_addr null_addr; - struct sock *rc = __llc_lookup_listener(sap, laddr); if (!rc) - rc = __llc_lookup_listener(sap, &null_addr); + rc = __llc_lookup_listener(sap, &null_addr, net); return rc; } static struct sock *__llc_lookup(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { - struct sock *sk = __llc_lookup_established(sap, daddr, laddr); + struct sock *sk = __llc_lookup_established(sap, daddr, laddr, net); - return sk ? : llc_lookup_listener(sap, laddr); + return sk ? : llc_lookup_listener(sap, laddr, net); } /** @@ -776,7 +787,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) llc_pdu_decode_da(skb, daddr.mac); llc_pdu_decode_dsap(skb, &daddr.lsap); - sk = __llc_lookup(sap, &saddr, &daddr); + sk = __llc_lookup(sap, &saddr, &daddr, dev_net(skb->dev)); if (!sk) goto drop; diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index dde9bf08a593..58a5f419adc6 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -92,7 +92,7 @@ int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, u8 dsap) daddr.lsap = dsap; memcpy(daddr.mac, dmac, sizeof(daddr.mac)); memcpy(laddr.mac, lmac, sizeof(laddr.mac)); - existing = llc_lookup_established(llc->sap, &daddr, &laddr); + existing = llc_lookup_established(llc->sap, &daddr, &laddr, sock_net(sk)); if (existing) { if (existing->sk_state == TCP_ESTABLISHED) { sk = existing; diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index c309b72a5877..7cac441862e2 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -163,9 +163,6 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, void (*sta_handler)(struct sk_buff *skb); void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - /* * When the interface is in promisc. mode, drop all the crap that it * receives, do not try to analyse it. diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 6805ce43a055..116c0e479183 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -294,25 +294,29 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, static inline bool llc_dgram_match(const struct llc_sap *sap, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); return sk->sk_type == SOCK_DGRAM && - llc->laddr.lsap == laddr->lsap && - ether_addr_equal(llc->laddr.mac, laddr->mac); + net_eq(sock_net(sk), net) && + llc->laddr.lsap == laddr->lsap && + ether_addr_equal(llc->laddr.mac, laddr->mac); } /** * llc_lookup_dgram - Finds dgram socket for the local sap/mac * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search socket list of the SAP and finds connection using the local * mac, and local sap. Returns pointer for socket found, %NULL otherwise. */ static struct sock *llc_lookup_dgram(struct llc_sap *sap, - const struct llc_addr *laddr) + const struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -322,12 +326,12 @@ static struct sock *llc_lookup_dgram(struct llc_sap *sap, rcu_read_lock_bh(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_dgram_match(sap, laddr, rc)) { + if (llc_dgram_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_dgram_match(sap, laddr, rc))) { + !llc_dgram_match(sap, laddr, rc, net))) { sock_put(rc); continue; } @@ -429,7 +433,7 @@ void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb) llc_sap_mcast(sap, &laddr, skb); kfree_skb(skb); } else { - struct sock *sk = llc_lookup_dgram(sap, &laddr); + struct sock *sk = llc_lookup_dgram(sap, &laddr, dev_net(skb->dev)); if (sk) { llc_sap_rcv(sap, skb, sk); sock_put(sk); diff --git a/net/mac80211/led.c b/net/mac80211/led.c index 6de8d0ad5497..2dc732147e85 100644 --- a/net/mac80211/led.c +++ b/net/mac80211/led.c @@ -282,7 +282,7 @@ static void tpt_trig_timer(struct timer_list *t) } } - led_trigger_blink(&local->tpt_led, &on, &off); + led_trigger_blink(&local->tpt_led, on, off); } const char * diff --git a/net/mac80211/led.h b/net/mac80211/led.h index b71a1428d883..d25f13346b82 100644 --- a/net/mac80211/led.h +++ b/net/mac80211/led.h @@ -13,22 +13,18 @@ static inline void ieee80211_led_rx(struct ieee80211_local *local) { #ifdef CONFIG_MAC80211_LEDS - unsigned long led_delay = MAC80211_BLINK_DELAY; - if (!atomic_read(&local->rx_led_active)) return; - led_trigger_blink_oneshot(&local->rx_led, &led_delay, &led_delay, 0); + led_trigger_blink_oneshot(&local->rx_led, MAC80211_BLINK_DELAY, MAC80211_BLINK_DELAY, 0); #endif } static inline void ieee80211_led_tx(struct ieee80211_local *local) { #ifdef CONFIG_MAC80211_LEDS - unsigned long led_delay = MAC80211_BLINK_DELAY; - if (!atomic_read(&local->tx_led_active)) return; - led_trigger_blink_oneshot(&local->tx_led, &led_delay, &led_delay, 0); + led_trigger_blink_oneshot(&local->tx_led, MAC80211_BLINK_DELAY, MAC80211_BLINK_DELAY, 0); #endif } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e892673deb73..d80658547836 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2335,7 +2335,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if (flags & MPTCP_CF_FASTCLOSE) { + if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_disconnect() path, * to generate the egress reset */ @@ -2909,10 +2909,10 @@ static void mptcp_check_listen_stop(struct sock *sk) return; lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + tcp_set_state(ssk, TCP_CLOSE); mptcp_subflow_queue_clean(sk, ssk); inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); - tcp_set_state(ssk, TCP_CLOSE); release_sock(ssk); } @@ -3328,7 +3328,7 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); - if (unlikely(&msk->cb_flags)) { + if (unlikely(msk->cb_flags)) { /* be sure to set the current sk state before tacking actions * depending on sk_state, that is processing MPTCP_ERROR_REPORT */ @@ -3703,6 +3703,11 @@ static int mptcp_listen(struct socket *sock, int backlog) pr_debug("msk=%p", msk); lock_sock(sk); + + err = -EINVAL; + if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) + goto unlock; + ssock = __mptcp_nmpc_socket(msk); if (IS_ERR(ssock)) { err = PTR_ERR(ssock); @@ -3718,10 +3723,9 @@ static int mptcp_listen(struct socket *sock, int backlog) if (!err) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); mptcp_copy_inaddrs(sk, ssock->sk); + mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); } - mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); - unlock: release_sock(sk); return err; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 37fbe22e2433..ba2a873a4d2e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -325,7 +325,6 @@ struct mptcp_sock { u32 subflow_id; u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; - struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 63f7a09335c5..a3f1fe810cc9 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -103,7 +103,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in break; case SO_MARK: if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) { - ssk->sk_mark = sk->sk_mark; + WRITE_ONCE(ssk->sk_mark, sk->sk_mark); sk_dst_reset(ssk); } break; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9ee3b7abbaf6..94ae7dd01c65 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1793,16 +1793,31 @@ static void subflow_state_change(struct sock *sk) void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - struct sock *sk; + struct request_sock *req, *head, *tail; + struct mptcp_subflow_context *subflow; + struct sock *sk, *ssk; - /* build a list of all unaccepted mptcp sockets */ + /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. + * Splice the req list, so that accept() can not reach the pending ssk after + * the listener socket is released below. + */ spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; + head = queue->rskq_accept_head; + tail = queue->rskq_accept_tail; + queue->rskq_accept_head = NULL; + queue->rskq_accept_tail = NULL; + spin_unlock_bh(&queue->rskq_lock); + + if (!head) + return; + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (req = head; req; req = req->dl_next) { + ssk = req->sk; if (!sk_is_mptcp(ssk)) continue; @@ -1810,32 +1825,10 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s if (!subflow || !subflow->conn) continue; - /* skip if already in list */ sk = subflow->conn; - msk = mptcp_sk(sk); - if (msk->dl_next || msk == head) - continue; - sock_hold(sk); - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - sk = (struct sock *)msk; lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->dl_next = NULL; - __mptcp_unaccepted_force_close(sk); release_sock(sk); @@ -1859,6 +1852,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); + + /* restore the listener queue, to let the TCP code clean it up */ + spin_lock_bh(&queue->rskq_lock); + WARN_ON_ONCE(queue->rskq_accept_head); + queue->rskq_accept_head = head; + queue->rskq_accept_tail = tail; + spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d119f1d4c2fc..992393102d5f 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -211,24 +211,18 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, unsigned int zoneid, const struct net *net) { - u64 a, b, c, d; + siphash_key_t key; get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd)); - /* The direction must be ignored, handle usable tuplehash members manually */ - a = (u64)tuple->src.u3.all[0] << 32 | tuple->src.u3.all[3]; - b = (u64)tuple->dst.u3.all[0] << 32 | tuple->dst.u3.all[3]; + key = nf_conntrack_hash_rnd; - c = (__force u64)tuple->src.u.all << 32 | (__force u64)tuple->dst.u.all << 16; - c |= tuple->dst.protonum; + key.key[0] ^= zoneid; + key.key[1] ^= net_hash_mix(net); - d = (u64)zoneid << 32 | net_hash_mix(net); - - /* IPv4: u3.all[1,2,3] == 0 */ - c ^= (u64)tuple->src.u3.all[1] << 32 | tuple->src.u3.all[2]; - d += (u64)tuple->dst.u3.all[1] << 32 | tuple->dst.u3.all[2]; - - return (u32)siphash_4u64(a, b, c, d, &nf_conntrack_hash_rnd); + return siphash((void *)tuple, + offsetofend(struct nf_conntrack_tuple, dst.__nfct_hash_offsetend), + &key); } static u32 scale_hash(u32 hash) diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 0c4db2f2ac43..f22691f83853 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -360,6 +360,9 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); + if (!nf_ct_helper_hash) + return -ENOENT; + if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; @@ -515,4 +518,5 @@ int nf_conntrack_helper_init(void) void nf_conntrack_helper_fini(void) { kvfree(nf_ct_helper_hash); + nf_ct_helper_hash = NULL; } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index ad6f0ca40cd2..af369e686fc5 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -205,6 +205,8 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { + unsigned long status; + if (!nf_ct_is_confirmed(ct)) { unsigned int *timeouts = nf_ct_timeout_lookup(ct); @@ -217,11 +219,17 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, ct->proto.gre.timeout = timeouts[GRE_CT_UNREPLIED]; } + status = READ_ONCE(ct->status); /* If we've seen traffic both ways, this is a GRE connection. * Extend timeout. */ - if (ct->status & IPS_SEEN_REPLY) { + if (status & IPS_SEEN_REPLY) { nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.stream_timeout); + + /* never set ASSURED for IPS_NAT_CLASH, they time out soon */ + if (unlikely((status & IPS_NAT_CLASH))) + return NF_ACCEPT; + /* Also, more likely to be important, and not a probe. */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9573a8fcad79..c62227ae7746 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -31,7 +31,9 @@ static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); +static LIST_HEAD(nf_tables_gc_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); +static DEFINE_SPINLOCK(nf_tables_gc_list_lock); enum { NFT_VALIDATE_SKIP = 0, @@ -120,6 +122,9 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); +static void nft_trans_gc_work(struct work_struct *work); +static DECLARE_WORK(trans_gc_work, nft_trans_gc_work); + static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, @@ -253,8 +258,10 @@ int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) if (chain->bound) return -EBUSY; + if (!nft_use_inc(&chain->use)) + return -EMFILE; + chain->bound = true; - chain->use++; nft_chain_trans_bind(ctx, chain); return 0; @@ -437,7 +444,7 @@ static int nft_delchain(struct nft_ctx *ctx) if (IS_ERR(trans)) return PTR_ERR(trans); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nft_deactivate_next(ctx->net, ctx->chain); return 0; @@ -476,7 +483,7 @@ nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) /* You cannot delete the same rule twice */ if (nft_is_active_next(ctx->net, rule)) { nft_deactivate_next(ctx->net, rule); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); return 0; } return -ENOENT; @@ -580,10 +587,6 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return __nft_trans_set_add(ctx, msg_type, set, NULL); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem); - static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, @@ -644,7 +647,7 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -676,7 +679,7 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; nft_deactivate_next(ctx->net, obj); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -711,7 +714,7 @@ static int nft_delflowtable(struct nft_ctx *ctx, return err; nft_deactivate_next(ctx->net, flowtable); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -2396,9 +2399,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_chain *chain; int err; - if (table->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_CHAIN_HOOK]) { struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook = {}; @@ -2494,6 +2494,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (err < 0) goto err_destroy_chain; + if (!nft_use_inc(&table->use)) { + err = -EMFILE; + goto err_use; + } + trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2510,10 +2515,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err_unregister_hook; } - table->use++; - return 0; + err_unregister_hook: + nft_use_dec_restore(&table->use); +err_use: nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -2694,7 +2700,7 @@ err_hooks: static struct nft_chain *nft_chain_lookup_byid(const struct net *net, const struct nft_table *table, - const struct nlattr *nla) + const struct nlattr *nla, u8 genmask) { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); @@ -2705,7 +2711,8 @@ static struct nft_chain *nft_chain_lookup_byid(const struct net *net, if (trans->msg_type == NFT_MSG_NEWCHAIN && chain->table == table && - id == nft_trans_chain_id(trans)) + id == nft_trans_chain_id(trans) && + nft_active_genmask(chain, genmask)) return chain; } return ERR_PTR(-ENOENT); @@ -3679,8 +3686,6 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } - - cond_resched(); } return 0; @@ -3704,6 +3709,8 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) err = nft_chain_validate(&ctx, chain); if (err < 0) return err; + + cond_resched(); } return 0; @@ -3805,11 +3812,10 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) - return -EOPNOTSUPP; } else if (nla[NFTA_RULE_CHAIN_ID]) { - chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID]); + chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID], + genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]); return PTR_ERR(chain); @@ -3818,6 +3824,9 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return -EINVAL; } + if (nft_chain_is_bound(chain)) + return -EOPNOTSUPP; + if (nla[NFTA_RULE_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE])); rule = __nft_rule_lookup(chain, handle); @@ -3840,9 +3849,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return -EINVAL; handle = nf_tables_alloc_handle(table); - if (chain->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); old_rule = __nft_rule_lookup(chain, pos_handle); @@ -3936,6 +3942,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } + if (!nft_use_inc(&chain->use)) { + err = -EMFILE; + goto err_release_rule; + } + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { err = nft_delrule(&ctx, old_rule); if (err < 0) @@ -3967,7 +3978,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } kvfree(expr_info); - chain->use++; if (flow) nft_trans_flow_rule(trans) = flow; @@ -3978,6 +3988,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return 0; err_destroy_flow_rule: + nft_use_dec_restore(&chain->use); if (flow) nft_flow_rule_destroy(flow); err_release_rule: @@ -4078,6 +4089,8 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; ctx.chain = chain; err = nft_delrule_by_chain(&ctx); @@ -5014,9 +5027,15 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, alloc_size = sizeof(*set) + size + udlen; if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; + + if (!nft_use_inc(&table->use)) + return -EMFILE; + set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT); - if (!set) - return -ENOMEM; + if (!set) { + err = -ENOMEM; + goto err_alloc; + } name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT); if (!name) { @@ -5037,6 +5056,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&set->bindings); INIT_LIST_HEAD(&set->catchall_list); + refcount_set(&set->refs, 1); set->table = table; write_pnet(&set->net, net); set->ops = ops; @@ -5074,7 +5094,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); - table->use++; + return 0; err_set_expr_alloc: @@ -5086,6 +5106,9 @@ err_set_init: kfree(set->name); err_set_name: kvfree(set); +err_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -5101,6 +5124,14 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx, } } +static void nft_set_put(struct nft_set *set) +{ + if (refcount_dec_and_test(&set->refs)) { + kfree(set->name); + kvfree(set); + } +} + static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { int i; @@ -5113,8 +5144,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); - kfree(set->name); - kvfree(set); + nft_set_put(set); } static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, @@ -5224,9 +5254,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *i; struct nft_set_iter iter; - if (set->use == UINT_MAX) - return -EOVERFLOW; - if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; @@ -5254,10 +5281,12 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, return iter.err; } bind: + if (!nft_use_inc(&set->use)) + return -EMFILE; + binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); nft_set_trans_bind(ctx, set); - set->use++; return 0; } @@ -5331,7 +5360,7 @@ void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) nft_clear(ctx->net, set); } - set->use++; + nft_use_inc_restore(&set->use); } EXPORT_SYMBOL_GPL(nf_tables_activate_set); @@ -5347,7 +5376,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, else list_del_rcu(&binding->list); - set->use--; + nft_use_dec(&set->use); break; case NFT_TRANS_PREPARE: if (nft_set_is_anonymous(set)) { @@ -5356,7 +5385,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_deactivate_next(ctx->net, set); } - set->use--; + nft_use_dec(&set->use); return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: @@ -5364,7 +5393,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); - set->use--; + nft_use_dec(&set->use); fallthrough; default: nf_tables_unbind_set(ctx, set, binding, @@ -5582,8 +5611,12 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); struct nft_set_dump_args *args; + if (nft_set_elem_expired(ext)) + return 0; + args = container_of(iter, struct nft_set_dump_args, iter); return nf_tables_fill_setelem(args->skb, set, elem, args->reset); } @@ -6155,7 +6188,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -6254,7 +6287,8 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask) && - !nft_set_elem_expired(ext)) + !nft_set_elem_expired(ext) && + !nft_set_elem_is_dead(ext)) return ext; } @@ -6262,29 +6296,6 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, } EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); -void *nft_set_catchall_gc(const struct nft_set *set) -{ - struct nft_set_elem_catchall *catchall, *next; - struct nft_set_ext *ext; - void *elem = NULL; - - list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { - ext = nft_set_elem_ext(set, catchall->elem); - - if (!nft_set_elem_expired(ext) || - nft_set_elem_mark_busy(ext)) - continue; - - elem = catchall->elem; - list_del_rcu(&catchall->list); - kfree_rcu(catchall, rcu); - break; - } - - return elem; -} -EXPORT_SYMBOL_GPL(nft_set_catchall_gc); - static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, @@ -6346,7 +6357,6 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, if (nft_setelem_is_catchall(set, elem)) { nft_set_elem_change_active(net, set, ext); - nft_set_elem_clear_busy(ext); } else { set->ops->activate(net, set, elem); } @@ -6361,8 +6371,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext) || - nft_set_elem_mark_busy(ext)) + if (!nft_is_active(net, ext)) continue; kfree(elem->priv); @@ -6657,8 +6666,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); + obj = NULL; + goto err_parse_key_end; + } + + if (!nft_use_inc(&obj->use)) { + err = -EMFILE; + obj = NULL; goto err_parse_key_end; } + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); if (err < 0) goto err_parse_key_end; @@ -6727,10 +6744,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (flags) *nft_set_ext_flags(ext) = flags; - if (obj) { + if (obj) *nft_set_ext_obj(ext) = obj; - obj->use++; - } + if (ulen > 0) { if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { err = -EINVAL; @@ -6750,7 +6766,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_elem_free; } - ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; + ext->genmask = nft_genmask_cur(ctx->net); err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); if (err) { @@ -6798,12 +6814,13 @@ err_element_clash: kfree(trans); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); - if (obj) - obj->use--; err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); err_parse_key_end: + if (obj) + nft_use_dec_restore(&obj->use); + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: nft_data_release(&elem.key.val, NFT_DATA_VALUE); @@ -6883,7 +6900,7 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use++; + nft_use_inc_restore(&chain->use); break; } } @@ -6898,19 +6915,19 @@ static void nft_setelem_data_activate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use++; + nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, @@ -7067,8 +7084,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask) || - nft_set_elem_mark_busy(ext)) + if (!nft_set_elem_active(ext, genmask)) continue; elem.priv = catchall->elem; @@ -7142,29 +7158,6 @@ static int nf_tables_delsetelem(struct sk_buff *skb, return err; } -void nft_set_gc_batch_release(struct rcu_head *rcu) -{ - struct nft_set_gc_batch *gcb; - unsigned int i; - - gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); - for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); - kfree(gcb); -} - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp) -{ - struct nft_set_gc_batch *gcb; - - gcb = kzalloc(sizeof(*gcb), gfp); - if (gcb == NULL) - return gcb; - gcb->head.set = set; - return gcb; -} - /* * Stateful objects */ @@ -7453,9 +7446,14 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + type = nft_obj_type_get(net, objtype); - if (IS_ERR(type)) - return PTR_ERR(type); + if (IS_ERR(type)) { + err = PTR_ERR(type); + goto err_type; + } obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { @@ -7489,7 +7487,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); - table->use++; + return 0; err_obj_ht: /* queued in transaction log */ @@ -7505,6 +7503,9 @@ err_strdup: kfree(obj); err_init: module_put(type->owner); +err_type: + nft_use_dec_restore(&table->use); + return err; } @@ -7906,7 +7907,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: - flowtable->use--; + nft_use_dec(&flowtable->use); fallthrough; default: return; @@ -8260,9 +8261,14 @@ static int nf_tables_newflowtable(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT); - if (!flowtable) - return -ENOMEM; + if (!flowtable) { + err = -ENOMEM; + goto flowtable_alloc; + } flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); @@ -8317,7 +8323,6 @@ static int nf_tables_newflowtable(struct sk_buff *skb, goto err5; list_add_tail_rcu(&flowtable->list, &table->flowtables); - table->use++; return 0; err5: @@ -8334,6 +8339,9 @@ err2: kfree(flowtable->name); err1: kfree(flowtable); +flowtable_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -9371,6 +9379,207 @@ void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, + struct nft_trans_gc *trans) +{ + void **priv = trans->priv; + unsigned int i; + + for (i = 0; i < trans->count; i++) { + struct nft_set_elem elem = { + .priv = priv[i], + }; + + nft_setelem_data_deactivate(ctx->net, trans->set, &elem); + nft_setelem_remove(ctx->net, trans->set, &elem); + } +} + +void nft_trans_gc_destroy(struct nft_trans_gc *trans) +{ + nft_set_put(trans->set); + put_net(trans->net); + kfree(trans); +} + +static void nft_trans_gc_trans_free(struct rcu_head *rcu) +{ + struct nft_set_elem elem = {}; + struct nft_trans_gc *trans; + struct nft_ctx ctx = {}; + unsigned int i; + + trans = container_of(rcu, struct nft_trans_gc, rcu); + ctx.net = read_pnet(&trans->set->net); + + for (i = 0; i < trans->count; i++) { + elem.priv = trans->priv[i]; + if (!nft_setelem_is_catchall(trans->set, &elem)) + atomic_dec(&trans->set->nelems); + + nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv); + } + + nft_trans_gc_destroy(trans); +} + +static bool nft_trans_gc_work_done(struct nft_trans_gc *trans) +{ + struct nftables_pernet *nft_net; + struct nft_ctx ctx = {}; + + nft_net = nft_pernet(trans->net); + + mutex_lock(&nft_net->commit_mutex); + + /* Check for race with transaction, otherwise this batch refers to + * stale objects that might not be there anymore. Skip transaction if + * set has been destroyed from control plane transaction in case gc + * worker loses race. + */ + if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) { + mutex_unlock(&nft_net->commit_mutex); + return false; + } + + ctx.net = trans->net; + ctx.table = trans->set->table; + + nft_trans_gc_setelem_remove(&ctx, trans); + mutex_unlock(&nft_net->commit_mutex); + + return true; +} + +static void nft_trans_gc_work(struct work_struct *work) +{ + struct nft_trans_gc *trans, *next; + LIST_HEAD(trans_gc_list); + + spin_lock(&nf_tables_destroy_list_lock); + list_splice_init(&nf_tables_gc_list, &trans_gc_list); + spin_unlock(&nf_tables_destroy_list_lock); + + list_for_each_entry_safe(trans, next, &trans_gc_list, list) { + list_del(&trans->list); + if (!nft_trans_gc_work_done(trans)) { + nft_trans_gc_destroy(trans); + continue; + } + call_rcu(&trans->rcu, nft_trans_gc_trans_free); + } +} + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp) +{ + struct net *net = read_pnet(&set->net); + struct nft_trans_gc *trans; + + trans = kzalloc(sizeof(*trans), gfp); + if (!trans) + return NULL; + + refcount_inc(&set->refs); + trans->set = set; + trans->net = get_net(net); + trans->seq = gc_seq; + + return trans; +} + +void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv) +{ + trans->priv[trans->count++] = priv; +} + +static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) +{ + spin_lock(&nf_tables_gc_list_lock); + list_add_tail(&trans->list, &nf_tables_gc_list); + spin_unlock(&nf_tables_gc_list_lock); + + schedule_work(&trans_gc_work); +} + +static int nft_trans_gc_space(struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp) +{ + if (nft_trans_gc_space(gc)) + return gc; + + nft_trans_gc_queue_work(gc); + + return nft_trans_gc_alloc(gc->set, gc_seq, gfp); +} + +void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) +{ + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + nft_trans_gc_queue_work(trans); +} + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) +{ + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) + return NULL; + + if (nft_trans_gc_space(gc)) + return gc; + + call_rcu(&gc->rcu, nft_trans_gc_trans_free); + + return nft_trans_gc_alloc(gc->set, 0, gfp); +} + +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) +{ + WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net)); + + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + call_rcu(&trans->rcu, nft_trans_gc_trans_free); +} + +struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + struct nft_set_elem_catchall *catchall; + const struct nft_set *set = gc->set; + struct nft_set_ext *ext; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext)) + continue; + if (nft_set_elem_is_dead(ext)) + goto dead_elem; + + nft_set_elem_dead(ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + return NULL; + + nft_trans_gc_elem_add(gc, catchall->elem); + } + + return gc; +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -9533,11 +9742,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + unsigned int base_seq, gc_seq; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; - unsigned int base_seq; LIST_HEAD(adl); int err; @@ -9614,6 +9823,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) WRITE_ONCE(nft_net->base_seq, base_seq); + /* Bump gc counter, it becomes odd, this is the busy mark. */ + gc_seq = READ_ONCE(nft_net->gc_seq); + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); @@ -9713,7 +9926,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) - trans->ctx.table->use--; + nft_use_dec(&trans->ctx.table->use); } nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); @@ -9721,6 +9934,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: + nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), trans->msg_type, GFP_KERNEL); @@ -9823,6 +10037,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); + + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); nf_tables_commit_release(net); return 0; @@ -9943,7 +10159,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, @@ -9956,7 +10172,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_chain_hooks(trans), &nft_trans_basechain(trans)->hook_list); } else { - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, trans->ctx.chain); } nft_trans_destroy(trans); @@ -9966,7 +10182,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.chain->use--; + nft_use_dec_restore(&trans->ctx.chain->use); list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), @@ -9976,7 +10192,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: - trans->ctx.chain->use++; + nft_use_inc_restore(&trans->ctx.chain->use); nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) @@ -9989,7 +10205,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; @@ -9998,7 +10214,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_set(trans)); if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(&trans->ctx, nft_trans_set(trans)); @@ -10042,13 +10258,13 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_obj_del(nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; @@ -10057,7 +10273,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); @@ -10069,7 +10285,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); } nft_trans_destroy(trans); @@ -10477,6 +10693,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; + + /* zero padding hole for memcmp */ + memset(data, 0, sizeof(*data)); data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { @@ -10502,7 +10721,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, genmask); } else if (tb[NFTA_VERDICT_CHAIN_ID]) { chain = nft_chain_lookup_byid(ctx->net, ctx->table, - tb[NFTA_VERDICT_CHAIN_ID]); + tb[NFTA_VERDICT_CHAIN_ID], + genmask); if (IS_ERR(chain)) return PTR_ERR(chain); } else { @@ -10518,8 +10738,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; + if (!nft_use_inc(&chain->use)) + return -EMFILE; - chain->use++; data->verdict.chain = chain; break; } @@ -10537,7 +10758,7 @@ static void nft_verdict_uninit(const struct nft_data *data) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use--; + nft_use_dec(&chain->use); break; } } @@ -10706,11 +10927,11 @@ int __nft_release_basechain(struct nft_ctx *ctx) nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } nft_chain_del(ctx->chain); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nf_tables_chain_destroy(ctx); return 0; @@ -10757,21 +10978,24 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_is_bound(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); - chain->use--; + nft_use_dec(&chain->use); nf_tables_rule_release(&ctx, rule); } } list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { list_del(&flowtable->list); - table->use--; + nft_use_dec(&table->use); nf_tables_flowtable_destroy(flowtable); } list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); - table->use--; + nft_use_dec(&table->use); if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(&ctx, set); @@ -10779,13 +11003,13 @@ static void __nft_release_table(struct net *net, struct nft_table *table) } list_for_each_entry_safe(obj, ne, &table->objects, list) { nft_obj_del(obj); - table->use--; + nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { ctx.chain = chain; nft_chain_del(chain); - table->use--; + nft_use_dec(&table->use); nf_tables_chain_destroy(&ctx); } nf_tables_table_destroy(&ctx); @@ -10864,6 +11088,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; + nft_net->gc_seq = 0; return 0; } @@ -10892,10 +11117,16 @@ static void __net_exit nf_tables_exit_net(struct net *net) WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } +static void nf_tables_exit_batch(struct list_head *net_exit_list) +{ + flush_work(&trans_gc_work); +} + static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .exit_batch = nf_tables_exit_batch, .id = &nf_tables_net_id, .size = sizeof(struct nftables_pernet), }; @@ -10967,6 +11198,7 @@ static void __exit nf_tables_module_exit(void) nft_chain_filter_fini(); nft_chain_route_fini(); unregister_pernet_subsys(&nf_tables_net_ops); + cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); rcu_barrier(); rhltable_destroy(&nft_objname_ht); diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 9a85e797ed58..e596d1a842f7 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -30,11 +30,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, const struct nft_byteorder *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; - union { u32 u32; u16 u16; } *s, *d; + u16 *s16, *d16; unsigned int i; - s = (void *)src; - d = (void *)dst; + s16 = (void *)src; + d16 = (void *)dst; switch (priv->size) { case 8: { @@ -62,11 +62,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = ntohl((__force __be32)s[i].u32); + dst[i] = ntohl((__force __be32)src[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = (__force __u32)htonl(s[i].u32); + dst[i] = (__force __u32)htonl(src[i]); break; } break; @@ -74,11 +74,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = ntohs((__force __be16)s[i].u16); + d16[i] = ntohs((__force __be16)s16[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = (__force __u16)htons(s[i].u16); + d16[i] = (__force __u16)htons(s16[i]); break; } break; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 5ef9146e74ad..ab3362c483b4 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -408,8 +408,10 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (IS_ERR(flowtable)) return PTR_ERR(flowtable); + if (!nft_use_inc(&flowtable->use)) + return -EMFILE; + priv->flowtable = flowtable; - flowtable->use++; return nf_ct_netns_get(ctx->net, ctx->family); } @@ -428,7 +430,7 @@ static void nft_flow_offload_activate(const struct nft_ctx *ctx, { struct nft_flow_offload *priv = nft_expr_priv(expr); - priv->flowtable->use++; + nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 3d76ebfe8939..fccb3cf7749c 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -125,15 +125,27 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg)); } +static void nft_immediate_chain_deactivate(const struct nft_ctx *ctx, + struct nft_chain *chain, + enum nft_trans_phase phase) +{ + struct nft_ctx chain_ctx; + struct nft_rule *rule; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_deactivate(&chain_ctx, rule, phase); +} + static void nft_immediate_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); const struct nft_data *data = &priv->data; - struct nft_ctx chain_ctx; struct nft_chain *chain; - struct nft_rule *rule; if (priv->dreg == NFT_REG_VERDICT) { switch (data->verdict.code) { @@ -143,23 +155,20 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, if (!nft_chain_binding(chain)) break; - chain_ctx = *ctx; - chain_ctx.chain = chain; - - list_for_each_entry(rule, &chain->rules, list) - nft_rule_expr_deactivate(&chain_ctx, rule, phase); - switch (phase) { case NFT_TRANS_PREPARE_ERROR: nf_tables_unbind_chain(ctx, chain); - fallthrough; + nft_deactivate_next(ctx->net, chain); + break; case NFT_TRANS_PREPARE: + nft_immediate_chain_deactivate(ctx, chain, phase); nft_deactivate_next(ctx->net, chain); break; default: + nft_immediate_chain_deactivate(ctx, chain, phase); nft_chain_del(chain); chain->bound = false; - chain->table->use--; + nft_use_dec(&chain->table->use); break; } break; @@ -198,7 +207,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, * let the transaction records release this chain and its rules. */ if (chain->bound) { - chain->use--; + nft_use_dec(&chain->use); break; } @@ -206,9 +215,9 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, chain_ctx = *ctx; chain_ctx.chain = chain; - chain->use--; + nft_use_dec(&chain->use); list_for_each_entry_safe(rule, n, &chain->rules, list) { - chain->use--; + nft_use_dec(&chain->use); list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index a48dd5b5d45b..509011b1ef59 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -41,8 +41,10 @@ static int nft_objref_init(const struct nft_ctx *ctx, if (IS_ERR(obj)) return -ENOENT; + if (!nft_use_inc(&obj->use)) + return -EMFILE; + nft_objref_priv(expr) = obj; - obj->use++; return 0; } @@ -72,7 +74,7 @@ static void nft_objref_deactivate(const struct nft_ctx *ctx, if (phase == NFT_TRANS_COMMIT) return; - obj->use--; + nft_use_dec(&obj->use); } static void nft_objref_activate(const struct nft_ctx *ctx, @@ -80,7 +82,7 @@ static void nft_objref_activate(const struct nft_ctx *ctx, { struct nft_object *obj = nft_objref_priv(expr); - obj->use++; + nft_use_inc_restore(&obj->use); } static const struct nft_expr_ops nft_objref_ops = { diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 0b73cb0e752f..cef5df846000 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -59,6 +59,8 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) return 1; + if (nft_set_elem_is_dead(&he->ext)) + return 1; if (nft_set_elem_expired(&he->ext)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) @@ -188,7 +190,6 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, struct nft_rhash_elem *he = elem->priv; nft_set_elem_change_active(net, set, &he->ext); - nft_set_elem_clear_busy(&he->ext); } static bool nft_rhash_flush(const struct net *net, @@ -196,12 +197,9 @@ static bool nft_rhash_flush(const struct net *net, { struct nft_rhash_elem *he = priv; - if (!nft_set_elem_mark_busy(&he->ext) || - !nft_is_active(net, &he->ext)) { - nft_set_elem_change_active(net, set, &he->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &he->ext); + + return true; } static void *nft_rhash_deactivate(const struct net *net, @@ -218,9 +216,8 @@ static void *nft_rhash_deactivate(const struct net *net, rcu_read_lock(); he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); - if (he != NULL && - !nft_rhash_flush(net, set, he)) - he = NULL; + if (he) + nft_set_elem_change_active(net, set, &he->ext); rcu_read_unlock(); @@ -252,7 +249,9 @@ static bool nft_rhash_delete(const struct nft_set *set, if (he == NULL) return false; - return rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params) == 0; + nft_set_elem_dead(&he->ext); + + return true; } static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, @@ -278,8 +277,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&he->ext)) - goto cont; if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; @@ -314,25 +311,48 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set, static void nft_rhash_gc(struct work_struct *work) { + struct nftables_pernet *nft_net; struct nft_set *set; struct nft_rhash_elem *he; struct nft_rhash *priv; - struct nft_set_gc_batch *gcb = NULL; struct rhashtable_iter hti; + struct nft_trans_gc *gc; + struct net *net; + u32 gc_seq; priv = container_of(work, struct nft_rhash, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; rhashtable_walk_enter(&priv->ht, &hti); rhashtable_walk_start(&hti); while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) - break; + if (PTR_ERR(he) != -EAGAIN) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } continue; } + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + + if (nft_set_elem_is_dead(&he->ext)) + goto dead_elem; + if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPRESSIONS) && nft_rhash_expr_needs_gc_run(set, &he->ext)) goto needs_gc_run; @@ -340,26 +360,26 @@ static void nft_rhash_gc(struct work_struct *work) if (!nft_set_elem_expired(&he->ext)) continue; needs_gc_run: - if (nft_set_elem_mark_busy(&he->ext)) - continue; + nft_set_elem_dead(&he->ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb == NULL) - break; - rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, he); + nft_trans_gc_elem_add(gc, he); } + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: + /* catchall list iteration requires rcu read side lock. */ rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); - he = nft_set_catchall_gc(set); - if (he) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, he); - } - nft_set_gc_batch_complete(gcb); + if (gc) + nft_trans_gc_queue_async_done(gc); + +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } @@ -394,7 +414,7 @@ static int nft_rhash_init(const struct nft_set *set, return err; INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); - if (set->flags & NFT_SET_TIMEOUT) + if (set->flags & (NFT_SET_TIMEOUT | NFT_SET_EVAL)) nft_rhash_gc_init(set); return 0; @@ -422,7 +442,6 @@ static void nft_rhash_destroy(const struct nft_ctx *ctx, }; cancel_delayed_work_sync(&priv->gc_work); - rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)&rhash_ctx); } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index db526cb7a485..a5b8301afe4a 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -566,8 +566,7 @@ next_match: goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext) || - (genmask && + if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) goto next_match; @@ -601,8 +600,17 @@ out: static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { - return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + struct nft_pipapo_elem *ret; + + ret = pipapo_get(net, set, (const u8 *)elem->key.val.data, + nft_genmask_cur(net)); + if (IS_ERR(ret)) + return ret; + + if (nft_set_elem_expired(&ret->ext)) + return ERR_PTR(-ENOENT); + + return ret; } /** @@ -1528,16 +1536,34 @@ static void pipapo_drop(struct nft_pipapo_match *m, } } +static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, + struct nft_pipapo_elem *e) + +{ + struct nft_set_elem elem = { + .priv = e, + }; + + nft_setelem_data_deactivate(net, set, &elem); +} + /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) { + struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); + struct net *net = read_pnet(&set->net); int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; + struct nft_trans_gc *gc; + + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; @@ -1561,13 +1587,20 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) f--; i--; e = f->mt[rulemap[i].to].e; - if (nft_set_elem_expired(&e->ext) && - !nft_set_elem_mark_busy(&e->ext)) { + + /* synchronous gc never fails, there is no need to set on + * NFT_SET_ELEM_DEAD_BIT. + */ + if (nft_set_elem_expired(&e->ext)) { priv->dirty = true; - pipapo_drop(m, rulemap); - rcu_barrier(); - nft_set_elem_destroy(set, e, true); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (!gc) + break; + + nft_pipapo_gc_deactivate(net, set, e); + pipapo_drop(m, rulemap); + nft_trans_gc_elem_add(gc, e); /* And check again current first rule, which is now the * first we haven't checked. @@ -1577,11 +1610,11 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) } } - e = nft_set_catchall_gc(set); - if (e) - nft_set_elem_destroy(set, e, true); - - priv->last_gc = jiffies; + gc = nft_trans_gc_catchall(gc, 0); + if (gc) { + nft_trans_gc_queue_sync_done(gc); + priv->last_gc = jiffies; + } } /** @@ -1706,7 +1739,6 @@ static void nft_pipapo_activate(const struct net *net, return; nft_set_elem_change_active(net, set, &e->ext); - nft_set_elem_clear_busy(&e->ext); } /** @@ -1929,7 +1961,11 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, int i, start, rules_fx; match_start = data; - match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + + if (nft_set_ext_exists(&e->ext, NFT_SET_EXT_KEY_END)) + match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + else + match_end = data; start = first_rule; rules_fx = rules_f0; @@ -2001,8 +2037,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, goto cont; e = f->mt[r].e; - if (nft_set_elem_expired(&e->ext)) - goto cont; elem.priv = e; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 5c05c9b990fb..f9d4c8fcbbf8 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -46,6 +46,12 @@ static int nft_rbtree_cmp(const struct nft_set *set, set->klen); } +static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) +{ + return nft_set_elem_expired(&rbe->ext) || + nft_set_elem_is_dead(&rbe->ext); +} + static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) @@ -80,7 +86,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set continue; } - if (nft_set_elem_expired(&rbe->ext)) + if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { @@ -98,7 +104,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && - !nft_set_elem_expired(&interval->ext) && + !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -215,38 +221,70 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set_elem elem = { + .priv = rbe, + }; + + nft_setelem_data_deactivate(net, set, &elem); + rb_erase(&rbe->node, &priv->root); +} + static int nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe) + struct nft_rbtree_elem *rbe, + u8 genmask) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); - struct nft_rbtree_elem *rbe_prev = NULL; - struct nft_set_gc_batch *gcb; + struct net *net = read_pnet(&set->net); + struct nft_rbtree_elem *rbe_prev; + struct nft_trans_gc *gc; - gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); - if (!gcb) + gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); + if (!gc) return -ENOMEM; - /* search for expired end interval coming before this element. */ + /* search for end interval coming before this element. + * end intervals don't carry a timeout extension, they + * are coupled with the interval start element. + */ while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); - if (nft_rbtree_interval_end(rbe_prev)) + if (nft_rbtree_interval_end(rbe_prev) && + nft_set_elem_active(&rbe_prev->ext, genmask)) break; prev = rb_prev(prev); } - if (rbe_prev) { - rb_erase(&rbe_prev->node, &priv->root); - atomic_dec(&set->nelems); + if (prev) { + rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + nft_rbtree_gc_remove(net, set, priv, rbe_prev); + + /* There is always room in this trans gc for this element, + * memory allocation never actually happens, hence, the warning + * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, + * this is synchronous gc which never fails. + */ + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe_prev); } - rb_erase(&rbe->node, &priv->root); - atomic_dec(&set->nelems); + nft_rbtree_gc_remove(net, set, priv, rbe); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe); - nft_set_gc_batch_add(gcb, rbe); - nft_set_gc_batch_complete(gcb); + nft_trans_gc_queue_sync_done(gc); return 0; } @@ -321,7 +359,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, /* perform garbage collection to avoid bogus overlap reports. */ if (nft_set_elem_expired(&rbe->ext)) { - err = nft_rbtree_gc_elem(set, priv, rbe); + err = nft_rbtree_gc_elem(set, priv, rbe, genmask); if (err < 0) return err; @@ -474,7 +512,6 @@ static void nft_rbtree_activate(const struct net *net, struct nft_rbtree_elem *rbe = elem->priv; nft_set_elem_change_active(net, set, &rbe->ext); - nft_set_elem_clear_busy(&rbe->ext); } static bool nft_rbtree_flush(const struct net *net, @@ -482,12 +519,9 @@ static bool nft_rbtree_flush(const struct net *net, { struct nft_rbtree_elem *rbe = priv; - if (!nft_set_elem_mark_busy(&rbe->ext) || - !nft_is_active(net, &rbe->ext)) { - nft_set_elem_change_active(net, set, &rbe->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &rbe->ext); + + return true; } static void *nft_rbtree_deactivate(const struct net *net, @@ -544,8 +578,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&rbe->ext)) - goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; @@ -564,26 +596,40 @@ cont: static void nft_rbtree_gc(struct work_struct *work) { - struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL; - struct nft_set_gc_batch *gcb = NULL; + struct nft_rbtree_elem *rbe, *rbe_end = NULL; + struct nftables_pernet *nft_net; struct nft_rbtree *priv; + struct nft_trans_gc *gc; struct rb_node *node; struct nft_set *set; + unsigned int gc_seq; struct net *net; - u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); net = read_pnet(&set->net); - genmask = nft_genmask_cur(net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (!nft_set_elem_active(&rbe->ext, genmask)) - continue; + if (nft_set_elem_is_dead(&rbe->ext)) + goto dead_elem; /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is @@ -596,46 +642,36 @@ static void nft_rbtree_gc(struct work_struct *work) if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) { - rbe_end = NULL; + nft_set_elem_dead(&rbe->ext); + + if (!rbe_end) continue; - } - if (rbe_prev) { - rb_erase(&rbe_prev->node, &priv->root); - rbe_prev = NULL; - } - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (!gcb) - break; + nft_set_elem_dead(&rbe_end->ext); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe); - rbe_prev = rbe; + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - if (rbe_end) { - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_end); - rb_erase(&rbe_end->node, &priv->root); - rbe_end = NULL; - } - node = rb_next(node); - if (!node) - break; + nft_trans_gc_elem_add(gc, rbe_end); + rbe_end = NULL; +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; + + nft_trans_gc_elem_add(gc, rbe); } - if (rbe_prev) - rb_erase(&rbe_prev->node, &priv->root); + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); - rbe = nft_set_catchall_gc(set); - if (rbe) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, rbe); - } - nft_set_gc_batch_complete(gcb); - + if (gc) + nft_trans_gc_queue_async_done(gc); +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 84def74698b7..9ed85be79452 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -107,7 +107,7 @@ static void nft_socket_eval(const struct nft_expr *expr, break; case NFT_SOCKET_MARK: if (sk_fullsock(sk)) { - *dest = sk->sk_mark; + *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; return; diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c index 66b0f941d8fb..36c9720ad8d6 100644 --- a/net/netfilter/xt_LED.c +++ b/net/netfilter/xt_LED.c @@ -43,7 +43,6 @@ led_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_led_info *ledinfo = par->targinfo; struct xt_led_info_internal *ledinternal = ledinfo->internal_data; - unsigned long led_delay = XT_LED_BLINK_DELAY; /* * If "always blink" is enabled, and there's still some time until the @@ -52,7 +51,7 @@ led_tg(struct sk_buff *skb, const struct xt_action_param *par) if ((ledinfo->delay > 0) && ledinfo->always_blink && timer_pending(&ledinternal->timer)) led_trigger_blink_oneshot(&ledinternal->netfilter_led_trigger, - &led_delay, &led_delay, 1); + XT_LED_BLINK_DELAY, XT_LED_BLINK_DELAY, 1); else led_trigger_event(&ledinternal->netfilter_led_trigger, LED_FULL); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 7013f55f05d1..76e01f292aaf 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -77,7 +77,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); @@ -138,7 +138,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a6d2a0b1aa21..3d7a91e64c88 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1829,7 +1829,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX] - ? nla_get_u32(a[OVS_DP_ATTR_IFINDEX]) : 0; + ? nla_get_s32(a[OVS_DP_ATTR_IFINDEX]) : 0; /* So far only local changes have been made, now need the lock. */ ovs_lock(); @@ -2049,7 +2049,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, [OVS_DP_ATTR_MASKS_CACHE_SIZE] = NLA_POLICY_RANGE(NLA_U32, 0, PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)), - [OVS_DP_ATTR_IFINDEX] = {.type = NLA_U32 }, + [OVS_DP_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), }; static const struct genl_small_ops dp_datapath_genl_ops[] = { @@ -2302,7 +2302,7 @@ restart: parms.port_no = port_no; parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX] - ? nla_get_u32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; + ? nla_get_s32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; vport = new_vport(&parms); err = PTR_ERR(vport); @@ -2539,7 +2539,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, - [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, [OVS_VPORT_ATTR_UPCALL_STATS] = { .type = NLA_NESTED }, }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 85ff90a03b0c..a2935bd18ed9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -401,18 +401,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -429,17 +431,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); @@ -2050,8 +2054,8 @@ retry: skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); @@ -2585,8 +2589,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->protocol = proto; skb->dev = dev; - skb->priority = po->sk.sk_priority; - skb->mark = po->sk.sk_mark; + skb->priority = READ_ONCE(po->sk.sk_priority); + skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -2988,7 +2992,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; sockcm_init(&sockc, sk); - sockc.mark = sk->sk_mark; + sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) @@ -3061,7 +3065,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; @@ -3601,7 +3605,7 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; - memcpy(sll->sll_addr, dev->dev_addr, dev->addr_len); + memcpy(sll->sll_addr_flex, dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f7887f42d542..9d3f26bf0440 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1320,7 +1320,7 @@ struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, return ERR_PTR(err); } } else { - if (strlcpy(act_name, "police", IFNAMSIZ) >= IFNAMSIZ) { + if (strscpy(act_name, "police", IFNAMSIZ) < 0) { NL_SET_ERR_MSG(extack, "TC action name too long"); return ERR_PTR(-EINVAL); } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 5d96ffebd40f..598d6e299152 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -21,6 +21,7 @@ #include <linux/tc_act/tc_ipt.h> #include <net/tc_act/tc_ipt.h> #include <net/tc_wrapper.h> +#include <net/ip.h> #include <linux/netfilter_ipv4/ip_tables.h> @@ -48,7 +49,7 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t, par.entryinfo = &e; par.target = target; par.targinfo = t->data; - par.hook_mask = hook; + par.hook_mask = 1 << hook; par.family = NFPROTO_IPV4; ret = xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); @@ -85,7 +86,8 @@ static void tcf_ipt_release(struct tc_action *a) static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TABLE] = { .type = NLA_STRING, .len = IFNAMSIZ }, - [TCA_IPT_HOOK] = { .type = NLA_U32 }, + [TCA_IPT_HOOK] = NLA_POLICY_RANGE(NLA_U32, NF_INET_PRE_ROUTING, + NF_INET_NUMHOOKS), [TCA_IPT_INDEX] = { .type = NLA_U32 }, [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; @@ -158,15 +160,27 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, return -EEXIST; } } + + err = -EINVAL; hook = nla_get_u32(tb[TCA_IPT_HOOK]); + switch (hook) { + case NF_INET_PRE_ROUTING: + break; + case NF_INET_POST_ROUTING: + break; + default: + goto err1; + } + + if (tb[TCA_IPT_TABLE]) { + /* mangle only for now */ + if (nla_strcmp(tb[TCA_IPT_TABLE], "mangle")) + goto err1; + } - err = -ENOMEM; - tname = kmalloc(IFNAMSIZ, GFP_KERNEL); + tname = kstrdup("mangle", GFP_KERNEL); if (unlikely(!tname)) goto err1; - if (tb[TCA_IPT_TABLE] == NULL || - nla_strscpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ) - strcpy(tname, "mangle"); t = kmemdup(td, td->u.target_size, GFP_KERNEL); if (unlikely(!t)) @@ -217,10 +231,31 @@ static int tcf_xt_init(struct net *net, struct nlattr *nla, a, &act_xt_ops, tp, flags); } +static bool tcf_ipt_act_check(struct sk_buff *skb) +{ + const struct iphdr *iph; + unsigned int nhoff, len; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return false; + + nhoff = skb_network_offset(skb); + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + return false; + + len = skb_ip_totlen(skb); + if (skb->len < nhoff + len || len < (iph->ihl * 4u)) + return false; + + return pskb_may_pull(skb, iph->ihl * 4u); +} + TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { + char saved_cb[sizeof_field(struct sk_buff, cb)]; int ret = 0, result = 0; struct tcf_ipt *ipt = to_ipt(a); struct xt_action_param par; @@ -231,9 +266,24 @@ TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, .pf = NFPROTO_IPV4, }; + if (skb_protocol(skb, false) != htons(ETH_P_IP)) + return TC_ACT_UNSPEC; + if (skb_unclone(skb, GFP_ATOMIC)) return TC_ACT_UNSPEC; + if (!tcf_ipt_act_check(skb)) + return TC_ACT_UNSPEC; + + if (state.hook == NF_INET_POST_ROUTING) { + if (!skb_dst(skb)) + return TC_ACT_UNSPEC; + + state.out = skb->dev; + } + + memcpy(saved_cb, skb->cb, sizeof(saved_cb)); + spin_lock(&ipt->tcf_lock); tcf_lastuse_update(&ipt->tcf_tm); @@ -246,6 +296,9 @@ TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, par.state = &state; par.target = ipt->tcfi_t->u.kernel.target; par.targinfo = ipt->tcfi_t->data; + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + ret = par.target->target(skb, &par); switch (ret) { @@ -266,6 +319,9 @@ TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, break; } spin_unlock(&ipt->tcf_lock); + + memcpy(skb->cb, saved_cb, sizeof(skb->cb)); + return result; } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index b562fc2bb5b1..1ef8fcfa9997 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -29,6 +29,7 @@ static struct tc_action_ops act_pedit_ops; static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, + [TCA_PEDIT_PARMS_EX] = { .len = sizeof(struct tc_pedit) }, [TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED }, }; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 466c26df853a..382c7a71f81f 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -406,56 +406,6 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, return 0; } -static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_bpf_prog *prog, unsigned long base, - struct nlattr **tb, struct nlattr *est, u32 flags, - struct netlink_ext_ack *extack) -{ - bool is_bpf, is_ebpf, have_exts = false; - u32 gen_flags = 0; - int ret; - - is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; - is_ebpf = tb[TCA_BPF_FD]; - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) - return -EINVAL; - - ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, flags, - extack); - if (ret < 0) - return ret; - - if (tb[TCA_BPF_FLAGS]) { - u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); - - if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) - return -EINVAL; - - have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; - } - if (tb[TCA_BPF_FLAGS_GEN]) { - gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); - if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || - !tc_flags_valid(gen_flags)) - return -EINVAL; - } - - prog->exts_integrated = have_exts; - prog->gen_flags = gen_flags; - - ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); - if (ret < 0) - return ret; - - if (tb[TCA_BPF_CLASSID]) { - prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); - tcf_bind_filter(tp, &prog->res, base); - } - - return 0; -} - static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -463,9 +413,12 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); + bool is_bpf, is_ebpf, have_exts = false; struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; + bool bound_to_filter = false; struct cls_bpf_prog *prog; + u32 gen_flags = 0; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -504,11 +457,51 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, goto errout; prog->handle = handle; - ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], flags, - extack); + is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; + is_ebpf = tb[TCA_BPF_FD]; + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { + ret = -EINVAL; + goto errout_idr; + } + + ret = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &prog->exts, + flags, extack); + if (ret < 0) + goto errout_idr; + + if (tb[TCA_BPF_FLAGS]) { + u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); + + if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { + ret = -EINVAL; + goto errout_idr; + } + + have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; + } + if (tb[TCA_BPF_FLAGS_GEN]) { + gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); + if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || + !tc_flags_valid(gen_flags)) { + ret = -EINVAL; + goto errout_idr; + } + } + + prog->exts_integrated = have_exts; + prog->gen_flags = gen_flags; + + ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); if (ret < 0) goto errout_idr; + if (tb[TCA_BPF_CLASSID]) { + prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + tcf_bind_filter(tp, &prog->res, base); + bound_to_filter = true; + } + ret = cls_bpf_offload(tp, prog, oldprog, extack); if (ret) goto errout_parms; @@ -530,6 +523,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, return 0; errout_parms: + if (bound_to_filter) + tcf_unbind_filter(tp, &prog->res); cls_bpf_free_parms(prog); errout_idr: if (!oldprog) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 56065cc5a661..9f0711da9c95 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -776,7 +776,8 @@ mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 }, }; -static const struct nla_policy cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX] = { +static const struct nla_policy +cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX + 1] = { [TCA_FLOWER_KEY_CFM_MD_LEVEL] = NLA_POLICY_MAX(NLA_U8, FLOW_DIS_CFM_MDL_MAX), [TCA_FLOWER_KEY_CFM_OPCODE] = { .type = NLA_U8 }, @@ -812,6 +813,16 @@ static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + if (mask->tp_range.tp_min.dst != mask->tp_range.tp_max.dst) { + NL_SET_ERR_MSG(extack, + "Both min and max destination ports must be specified"); + return -EINVAL; + } + if (mask->tp_range.tp_min.src != mask->tp_range.tp_max.src) { + NL_SET_ERR_MSG(extack, + "Both min and max source ports must be specified"); + return -EINVAL; + } if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && ntohs(key->tp_range.tp_max.dst) <= ntohs(key->tp_range.tp_min.dst)) { @@ -1699,7 +1710,7 @@ static int fl_set_key_cfm(struct nlattr **tb, struct fl_flow_key *mask, struct netlink_ext_ack *extack) { - struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX]; + struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX + 1]; int err; if (!tb[TCA_FLOWER_KEY_CFM]) @@ -2163,53 +2174,6 @@ static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask) return mask->meta.l2_miss; } -static int fl_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_fl_filter *f, struct fl_flow_mask *mask, - unsigned long base, struct nlattr **tb, - struct nlattr *est, - struct fl_flow_tmplt *tmplt, - u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &f->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_FLOWER_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); - if (flags & TCA_ACT_FLAGS_NO_RTNL) - rtnl_lock(); - tcf_bind_filter(tp, &f->res, base); - if (flags & TCA_ACT_FLAGS_NO_RTNL) - rtnl_unlock(); - } - - err = fl_set_key(net, tb, &f->key, &mask->key, extack); - if (err) - return err; - - fl_mask_update_range(mask); - fl_set_masked_key(&f->mkey, &f->key, mask); - - if (!fl_mask_fits_tmplt(tmplt, mask)) { - NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); - return -EINVAL; - } - - /* Enable tc skb extension if filter matches on data extracted from - * this extension. - */ - if (fl_needs_tc_skb_ext(&mask->key)) { - f->needs_tc_skb_ext = 1; - tc_skb_ext_tc_enable(); - } - - return 0; -} - static int fl_ht_insert_unique(struct cls_fl_filter *fnew, struct cls_fl_filter *fold, bool *in_ht) @@ -2241,6 +2205,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_head *head = fl_head_dereference(tp); bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); struct cls_fl_filter *fold = *arg; + bool bound_to_filter = false; struct cls_fl_filter *fnew; struct fl_flow_mask *mask; struct nlattr **tb; @@ -2325,15 +2290,46 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout_idr; - err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], - tp->chain->tmplt_priv, flags, fnew->flags, - extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &fnew->exts, flags, fnew->flags, + extack); + if (err < 0) goto errout_idr; + if (tb[TCA_FLOWER_CLASSID]) { + fnew->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_bind_filter(tp, &fnew->res, base); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + bound_to_filter = true; + } + + err = fl_set_key(net, tb, &fnew->key, &mask->key, extack); + if (err) + goto unbind_filter; + + fl_mask_update_range(mask); + fl_set_masked_key(&fnew->mkey, &fnew->key, mask); + + if (!fl_mask_fits_tmplt(tp->chain->tmplt_priv, mask)) { + NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); + err = -EINVAL; + goto unbind_filter; + } + + /* Enable tc skb extension if filter matches on data extracted from + * this extension. + */ + if (fl_needs_tc_skb_ext(&mask->key)) { + fnew->needs_tc_skb_ext = 1; + tc_skb_ext_tc_enable(); + } + err = fl_check_assign_mask(head, fnew, fold, mask); if (err) - goto errout_idr; + goto unbind_filter; err = fl_ht_insert_unique(fnew, fold, &in_ht); if (err) @@ -2424,6 +2420,16 @@ errout_hw: fnew->mask->filter_ht_params); errout_mask: fl_mask_put(head, fnew->mask); + +unbind_filter: + if (bound_to_filter) { + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_unbind_filter(tp, &fnew->res); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + } + errout_idr: if (!fold) idr_remove(&head->handle_idr, fnew->handle); diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index ae9439a6c56c..c49d6af0e048 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -212,11 +212,6 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, if (err < 0) return err; - if (tb[TCA_FW_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); - tcf_bind_filter(tp, &f->res, base); - } - if (tb[TCA_FW_INDEV]) { int ret; ret = tcf_change_indev(net, tb[TCA_FW_INDEV], extack); @@ -233,6 +228,11 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, } else if (head->mask != 0xFFFFFFFF) return err; + if (tb[TCA_FW_CLASSID]) { + f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); + tcf_bind_filter(tp, &f->res, base); + } + return 0; } @@ -267,7 +267,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; fnew->id = f->id; - fnew->res = f->res; fnew->ifindex = f->ifindex; fnew->tp = f->tp; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index fa3bbd187eb9..c4ed11df6254 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -159,26 +159,6 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, }; -static int mall_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long base, struct nlattr **tb, - struct nlattr *est, u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &head->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_MATCHALL_CLASSID]) { - head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); - tcf_bind_filter(tp, &head->res, base); - } - return 0; -} - static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -187,6 +167,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; + bool bound_to_filter = false; struct cls_mall_head *new; u32 userflags = 0; int err; @@ -226,11 +207,17 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, goto err_alloc_percpu; } - err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], - flags, new->flags, extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &new->exts, flags, new->flags, extack); + if (err < 0) goto err_set_parms; + if (tb[TCA_MATCHALL_CLASSID]) { + new->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); + tcf_bind_filter(tp, &new->res, base); + bound_to_filter = true; + } + if (!tc_skip_hw(new->flags)) { err = mall_replace_hw_filter(tp, new, (unsigned long)new, extack); @@ -246,6 +233,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, return 0; err_replace_hw_filter: + if (bound_to_filter) + tcf_unbind_filter(tp, &new->res); err_set_parms: free_percpu(new->pf); err_alloc_percpu: diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index d0c53724d3e8..1e20bbd687f1 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -513,7 +513,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (fold) { f->id = fold->id; f->iif = fold->iif; - f->res = fold->res; f->handle = fold->handle; f->tp = fold->tp; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d15d50de7980..da4c179a4d41 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -712,8 +712,23 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_FLAGS] = { .type = NLA_U32 }, }; +static void u32_unbind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) + tcf_unbind_filter(tp, &n->res); +} + +static void u32_bind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + unsigned long base, struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) { + n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); + tcf_bind_filter(tp, &n->res, base); + } +} + static int u32_set_parms(struct net *net, struct tcf_proto *tp, - unsigned long base, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) @@ -760,10 +775,6 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, if (ht_old) ht_old->refcnt--; } - if (tb[TCA_U32_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } if (ifindex >= 0) n->ifindex = ifindex; @@ -815,7 +826,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->ifindex = n->ifindex; new->fshift = n->fshift; - new->res = n->res; new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); @@ -903,17 +913,27 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (!new) return -ENOMEM; - err = u32_set_parms(net, tp, base, new, tb, - tca[TCA_RATE], flags, new->flags, - extack); + err = u32_set_parms(net, tp, new, tb, tca[TCA_RATE], + flags, new->flags, extack); if (err) { __u32_destroy_key(new); return err; } + u32_bind_filter(tp, new, base, tb); + err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { + u32_unbind_filter(tp, new, tb); + + if (tb[TCA_U32_LINK]) { + struct tc_u_hnode *ht_old; + + ht_old = rtnl_dereference(n->ht_down); + if (ht_old) + ht_old->refcnt++; + } __u32_destroy_key(new); return err; } @@ -1003,18 +1023,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } + /* At this point, we need to derive the new handle that will be used to + * uniquely map the identity of this table match entry. The + * identity of the entry that we need to construct is 32 bits made of: + * htid(12b):bucketid(8b):node/entryid(12b) + * + * At this point _we have the table(ht)_ in which we will insert this + * entry. We carry the table's id in variable "htid". + * Note that earlier code picked the ht selection either by a) the user + * providing the htid specified via TCA_U32_HASH attribute or b) when + * no such attribute is passed then the root ht, is default to at ID + * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0. + * If OTOH the user passed us the htid, they may also pass a bucketid of + * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is + * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be + * passed via the htid, so even if it was non-zero it will be ignored. + * + * We may also have a handle, if the user passed one. The handle also + * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b). + * Rule: the bucketid on the handle is ignored even if one was passed; + * rather the value on "htid" is always assumed to be the bucketid. + */ if (handle) { + /* Rule: The htid from handle and tableid from htid must match */ if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; } - handle = htid | TC_U32_NODE(handle); - err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle, - GFP_KERNEL); - if (err) - return err; - } else + /* Ok, so far we have a valid htid(12b):bucketid(8b) but we + * need to finalize the table entry identification with the last + * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for + * entries. Rule: nodeid of 0 is reserved only for tables(see + * earlier code which processes TC_U32_DIVISOR attribute). + * Rule: The nodeid can only be derived from the handle (and not + * htid). + * Rule: if the handle specified zero for the node id example + * 0x60000000, then pick a new nodeid from the pool of IDs + * this hash table has been allocating from. + * If OTOH it is specified (i.e for example the user passed a + * handle such as 0x60000123), then we use it generate our final + * handle which is used to uniquely identify the match entry. + */ + if (!TC_U32_NODE(handle)) { + handle = gen_new_kid(ht, htid); + } else { + handle = htid | TC_U32_NODE(handle); + err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, + handle, GFP_KERNEL); + if (err) + return err; + } + } else { + /* The user did not give us a handle; lets just generate one + * from the table's pool of nodeids. + */ handle = gen_new_kid(ht, htid); + } if (tb[TCA_U32_SEL] == NULL) { NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); @@ -1074,15 +1138,18 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], + err = u32_set_parms(net, tp, n, tb, tca[TCA_RATE], flags, n->flags, extack); + + u32_bind_filter(tp, n, base, tb); + if (err == 0) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; err = u32_replace_hw_knode(tp, n, flags, extack); if (err) - goto errhw; + goto errunbind; if (!tc_in_hw(n->flags)) n->flags |= TCA_CLS_FLAGS_NOT_IN_HW; @@ -1100,7 +1167,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return 0; } -errhw: +errunbind: + u32_unbind_filter(tp, n, tb); + #ifdef CONFIG_CLS_U32_MARK free_percpu(n->pcpu_success); #endif diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index af85a73c4c54..6fdba069f6bf 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -568,7 +568,7 @@ META_COLLECTOR(int_sk_rcvtimeo) *err = -1; return; } - dst->value = sk->sk_rcvtimeo / HZ; + dst->value = READ_ONCE(sk->sk_rcvtimeo) / HZ; } META_COLLECTOR(int_sk_sndtimeo) @@ -579,7 +579,7 @@ META_COLLECTOR(int_sk_sndtimeo) *err = -1; return; } - dst->value = sk->sk_sndtimeo / HZ; + dst->value = READ_ONCE(sk->sk_sndtimeo) / HZ; } META_COLLECTOR(int_sk_sendmsg_off) diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index ab69ff7577fc..793009f445c0 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -290,6 +290,13 @@ static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt, "Attribute type expected to be TCA_MQPRIO_MIN_RATE64"); return -EINVAL; } + + if (nla_len(attr) != sizeof(u64)) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute TCA_MQPRIO_MIN_RATE64 expected to have 8 bytes length"); + return -EINVAL; + } + if (i >= qopt->num_tc) break; priv->min_rate[i] = nla_get_u64(attr); @@ -312,6 +319,13 @@ static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt, "Attribute type expected to be TCA_MQPRIO_MAX_RATE64"); return -EINVAL; } + + if (nla_len(attr) != sizeof(u64)) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute TCA_MQPRIO_MAX_RATE64 expected to have 8 bytes length"); + return -EINVAL; + } + if (i >= qopt->num_tc) break; priv->max_rate[i] = nla_get_u64(attr); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index dfd9a99e6257..befaf74b33ca 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -381,8 +381,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, u32 lmax) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight); + struct qfq_aggregate *new_agg; + /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */ + if (lmax > QFQ_MAX_LMAX) + return -EINVAL; + + new_agg = qfq_find_agg(q, lmax, weight); if (new_agg == NULL) { /* create new aggregate */ new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC); if (new_agg == NULL) @@ -423,10 +428,17 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, else weight = 1; - if (tb[TCA_QFQ_LMAX]) + if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - else + } else { + /* MTU size is user controlled */ lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > QFQ_MAX_LMAX) { + NL_SET_ERR_MSG_MOD(extack, + "MTU size out of bounds for qfq"); + return -EINVAL; + } + } inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 717ae51d94a0..8c9cfff7fd05 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1015,6 +1015,11 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { TC_FP_PREEMPTIBLE), }; +static struct netlink_range_validation_signed taprio_cycle_time_range = { + .min = 0, + .max = INT_MAX, +}; + static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) @@ -1023,7 +1028,8 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, - [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = + NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, @@ -1159,6 +1165,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, return -EINVAL; } + if (cycle < 0 || cycle > INT_MAX) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); + return -EINVAL; + } + new->cycle_time = cycle; } @@ -1347,7 +1358,7 @@ static void setup_txtime(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct sched_entry *entry; - u32 interval = 0; + u64 interval = 0; list_for_each_entry(entry, &sched->entries, list) { entry->next_txtime = ktime_add_ns(base, interval); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6554a357fe33..9388d98aebc0 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -364,9 +364,9 @@ static void sctp_auto_asconf_init(struct sctp_sock *sp) struct net *net = sock_net(&sp->inet.sk); if (net->sctp.default_auto_asconf) { - spin_lock(&net->sctp.addr_wq_lock); + spin_lock_bh(&net->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); - spin_unlock(&net->sctp.addr_wq_lock); + spin_unlock_bh(&net->sctp.addr_wq_lock); sp->do_auto_asconf = 1; } } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a7f887d91d89..f5834af5fad5 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -378,8 +378,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; - WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem)); - WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem)); + WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); + WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); @@ -436,24 +436,9 @@ out: return rc; } -static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, - unsigned long mask) -{ - /* options we don't get control via setsockopt for */ - nsk->sk_type = osk->sk_type; - nsk->sk_sndbuf = osk->sk_sndbuf; - nsk->sk_rcvbuf = osk->sk_rcvbuf; - nsk->sk_sndtimeo = osk->sk_sndtimeo; - nsk->sk_rcvtimeo = osk->sk_rcvtimeo; - nsk->sk_mark = osk->sk_mark; - nsk->sk_priority = osk->sk_priority; - nsk->sk_rcvlowat = osk->sk_rcvlowat; - nsk->sk_bound_dev_if = osk->sk_bound_dev_if; - nsk->sk_err = osk->sk_err; - - nsk->sk_flags &= ~mask; - nsk->sk_flags |= osk->sk_flags & mask; -} +/* copy only relevant settings and flags of SOL_SOCKET level from smc to + * clc socket (since smc is not called for these options from net/core) + */ #define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ (1UL << SOCK_KEEPOPEN) | \ @@ -470,9 +455,55 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, (1UL << SOCK_NOFCS) | \ (1UL << SOCK_FILTER_LOCKED) | \ (1UL << SOCK_TSTAMP_NEW)) -/* copy only relevant settings and flags of SOL_SOCKET level from smc to - * clc socket (since smc is not called for these options from net/core) - */ + +/* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */ +static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + struct net *nnet = sock_net(nsk); + + nsk->sk_userlocks = osk->sk_userlocks; + if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) { + nsk->sk_sndbuf = osk->sk_sndbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_sndbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1])); + else + WRITE_ONCE(nsk->sk_sndbuf, + 2 * READ_ONCE(nnet->smc.sysctl_wmem)); + } + if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) { + nsk->sk_rcvbuf = osk->sk_rcvbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_rcvbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1])); + else + WRITE_ONCE(nsk->sk_rcvbuf, + 2 * READ_ONCE(nnet->smc.sysctl_rmem)); + } +} + +static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + /* options we don't get control via setsockopt for */ + nsk->sk_type = osk->sk_type; + nsk->sk_sndtimeo = osk->sk_sndtimeo; + nsk->sk_rcvtimeo = osk->sk_rcvtimeo; + nsk->sk_mark = READ_ONCE(osk->sk_mark); + nsk->sk_priority = osk->sk_priority; + nsk->sk_rcvlowat = osk->sk_rcvlowat; + nsk->sk_bound_dev_if = osk->sk_bound_dev_if; + nsk->sk_err = osk->sk_err; + + nsk->sk_flags &= ~mask; + nsk->sk_flags |= osk->sk_flags & mask; + + smc_adjust_sock_bufsizes(nsk, osk, mask); +} + static void smc_copy_sock_settings_to_clc(struct smc_sock *smc) { smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC); @@ -2479,8 +2510,6 @@ static void smc_tcp_listen_work(struct work_struct *work) sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); - new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; - new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); diff --git a/net/smc/smc.h b/net/smc/smc.h index 2eeea4cdc718..1f2b912c43d1 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -161,7 +161,7 @@ struct smc_connection { struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ - int rmbe_size_short;/* compressed notation */ + int rmbe_size_comp; /* compressed notation */ int rmbe_update_limit; /* lower limit for consumer * cursor update diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index b9b8b07aa702..c90d9e5dda54 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1007,7 +1007,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->d0.gid = conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd); clc->d0.token = conn->rmb_desc->token; - clc->d0.dmbe_size = conn->rmbe_size_short; + clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { @@ -1050,7 +1050,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); break; } - clc->r0.rmbe_size = conn->rmbe_size_short; + clc->r0.rmbe_size = conn->rmbe_size_comp; clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : cpu_to_be64((u64)sg_dma_address diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 3f465faf2b68..6b78075404d7 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -2309,31 +2309,30 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; - int bufsize, bufsize_short; + int bufsize, bufsize_comp; struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - int sk_buf_size; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_rcvbuf; + bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_sndbuf; + bufsize = smc->sk.sk_sndbuf / 2; - for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb); - bufsize_short >= 0; bufsize_short--) { + for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); + bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; - buf_list = &lgr->rmbs[bufsize_short]; + buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; - buf_list = &lgr->sndbufs[bufsize_short]; + buf_list = &lgr->sndbufs[bufsize_comp]; } - bufsize = smc_uncompress_bufsize(bufsize_short); + bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ - buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); + buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); @@ -2377,8 +2376,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_rmb) { conn->rmb_desc = buf_desc; - conn->rmbe_size_short = bufsize_short; - smc->sk.sk_rcvbuf = bufsize; + conn->rmbe_size_comp = bufsize_comp; + smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); @@ -2386,7 +2385,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; - smc->sk.sk_sndbuf = bufsize; + smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index b6f79fabb9d3..0b2a957ca5f5 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -21,6 +21,10 @@ static int min_sndbuf = SMC_BUF_MIN_SIZE; static int min_rcvbuf = SMC_BUF_MIN_SIZE; +static int max_sndbuf = INT_MAX / 2; +static int max_rcvbuf = INT_MAX / 2; +static const int net_smc_wmem_init = (64 * 1024); +static const int net_smc_rmem_init = (64 * 1024); static struct ctl_table smc_table[] = { { @@ -53,6 +57,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, + .extra2 = &max_sndbuf, }, { .procname = "rmem", @@ -61,6 +66,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, + .extra2 = &max_rcvbuf, }, { } }; @@ -88,8 +94,8 @@ int __net_init smc_sysctl_net_init(struct net *net) net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS; net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME; - WRITE_ONCE(net->smc.sysctl_wmem, READ_ONCE(net->ipv4.sysctl_tcp_wmem[1])); - WRITE_ONCE(net->smc.sysctl_rmem, READ_ONCE(net->ipv4.sysctl_tcp_rmem[1])); + WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init); + WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); return 0; diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 1c8de397d6ad..f89c10fe7e6a 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_SUNRPC_GSS) += auth_gss/ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ - auth.o auth_null.o auth_unix.o \ + auth.o auth_null.o auth_tls.o auth_unix.o \ svc.o svcsock.o svcauth.o svcauth_unix.o \ addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o sysfs.o \ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index fb75a883503f..2f16f9d17966 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -32,7 +32,7 @@ static unsigned int auth_hashbits = RPC_CREDCACHE_DEFAULT_HASHBITS; static const struct rpc_authops __rcu *auth_flavors[RPC_AUTH_MAXFLAVOR] = { [RPC_AUTH_NULL] = (const struct rpc_authops __force __rcu *)&authnull_ops, [RPC_AUTH_UNIX] = (const struct rpc_authops __force __rcu *)&authunix_ops, - NULL, /* others can be loadable modules */ + [RPC_AUTH_TLS] = (const struct rpc_authops __force __rcu *)&authtls_ops, }; static LIST_HEAD(cred_unused); diff --git a/net/sunrpc/auth_tls.c b/net/sunrpc/auth_tls.c new file mode 100644 index 000000000000..de7678f8a23d --- /dev/null +++ b/net/sunrpc/auth_tls.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021, 2022 Oracle. All rights reserved. + * + * The AUTH_TLS credential is used only to probe a remote peer + * for RPC-over-TLS support. + */ + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/sunrpc/clnt.h> + +static const char *starttls_token = "STARTTLS"; +static const size_t starttls_len = 8; + +static struct rpc_auth tls_auth; +static struct rpc_cred tls_cred; + +static void tls_encode_probe(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj) +{ +} + +static int tls_decode_probe(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj) +{ + return 0; +} + +static const struct rpc_procinfo rpcproc_tls_probe = { + .p_encode = tls_encode_probe, + .p_decode = tls_decode_probe, +}; + +static void rpc_tls_probe_call_prepare(struct rpc_task *task, void *data) +{ + task->tk_flags &= ~RPC_TASK_NO_RETRANS_TIMEOUT; + rpc_call_start(task); +} + +static void rpc_tls_probe_call_done(struct rpc_task *task, void *data) +{ +} + +static const struct rpc_call_ops rpc_tls_probe_ops = { + .rpc_call_prepare = rpc_tls_probe_call_prepare, + .rpc_call_done = rpc_tls_probe_call_done, +}; + +static int tls_probe(struct rpc_clnt *clnt) +{ + struct rpc_message msg = { + .rpc_proc = &rpcproc_tls_probe, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .rpc_message = &msg, + .rpc_op_cred = &tls_cred, + .callback_ops = &rpc_tls_probe_ops, + .flags = RPC_TASK_SOFT | RPC_TASK_SOFTCONN, + }; + 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; +} + +static struct rpc_auth *tls_create(const struct rpc_auth_create_args *args, + struct rpc_clnt *clnt) +{ + refcount_inc(&tls_auth.au_count); + return &tls_auth; +} + +static void tls_destroy(struct rpc_auth *auth) +{ +} + +static struct rpc_cred *tls_lookup_cred(struct rpc_auth *auth, + struct auth_cred *acred, int flags) +{ + return get_rpccred(&tls_cred); +} + +static void tls_destroy_cred(struct rpc_cred *cred) +{ +} + +static int tls_match(struct auth_cred *acred, struct rpc_cred *cred, int taskflags) +{ + return 1; +} + +static int tls_marshal(struct rpc_task *task, struct xdr_stream *xdr) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4 * XDR_UNIT); + if (!p) + return -EMSGSIZE; + /* Credential */ + *p++ = rpc_auth_tls; + *p++ = xdr_zero; + /* Verifier */ + *p++ = rpc_auth_null; + *p = xdr_zero; + return 0; +} + +static int tls_refresh(struct rpc_task *task) +{ + set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags); + return 0; +} + +static int tls_validate(struct rpc_task *task, struct xdr_stream *xdr) +{ + __be32 *p; + void *str; + + p = xdr_inline_decode(xdr, XDR_UNIT); + if (!p) + return -EIO; + if (*p != rpc_auth_null) + return -EIO; + if (xdr_stream_decode_opaque_inline(xdr, &str, starttls_len) != starttls_len) + return -EIO; + if (memcmp(str, starttls_token, starttls_len)) + return -EIO; + return 0; +} + +const struct rpc_authops authtls_ops = { + .owner = THIS_MODULE, + .au_flavor = RPC_AUTH_TLS, + .au_name = "NULL", + .create = tls_create, + .destroy = tls_destroy, + .lookup_cred = tls_lookup_cred, + .ping = tls_probe, +}; + +static struct rpc_auth tls_auth = { + .au_cslack = NUL_CALLSLACK, + .au_rslack = NUL_REPLYSLACK, + .au_verfsize = NUL_REPLYSLACK, + .au_ralign = NUL_REPLYSLACK, + .au_ops = &authtls_ops, + .au_flavor = RPC_AUTH_TLS, + .au_count = REFCOUNT_INIT(1), +}; + +static const struct rpc_credops tls_credops = { + .cr_name = "AUTH_TLS", + .crdestroy = tls_destroy_cred, + .crmatch = tls_match, + .crmarshal = tls_marshal, + .crwrap_req = rpcauth_wrap_req_encode, + .crrefresh = tls_refresh, + .crvalidate = tls_validate, + .crunwrap_resp = rpcauth_unwrap_resp_decode, +}; + +static struct rpc_cred tls_cred = { + .cr_lru = LIST_HEAD_INIT(tls_cred.cr_lru), + .cr_auth = &tls_auth, + .cr_ops = &tls_credops, + .cr_count = REFCOUNT_INIT(2), + .cr_flags = 1UL << RPCAUTH_CRED_UPTODATE, +}; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d2ee56634308..d7c697af3762 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -385,6 +385,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, if (!clnt) goto out_err; clnt->cl_parent = parent ? : clnt; + clnt->cl_xprtsec = args->xprtsec; err = rpc_alloc_clid(clnt); if (err) @@ -434,7 +435,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, if (parent) refcount_inc(&parent->cl_count); - trace_rpc_clnt_new(clnt, xprt, program->name, args->servername); + trace_rpc_clnt_new(clnt, xprt, args); return clnt; out_no_path: @@ -532,6 +533,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) .addrlen = args->addrsize, .servername = args->servername, .bc_xprt = args->bc_xprt, + .xprtsec = args->xprtsec, }; char servername[48]; struct rpc_clnt *clnt; @@ -565,8 +567,12 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) servername[0] = '\0'; switch (args->address->sa_family) { case AF_LOCAL: - snprintf(servername, sizeof(servername), "%s", - sun->sun_path); + if (sun->sun_path[0]) + snprintf(servername, sizeof(servername), "%s", + sun->sun_path); + else + snprintf(servername, sizeof(servername), "@%s", + sun->sun_path+1); break; case AF_INET: snprintf(servername, sizeof(servername), "%pI4", @@ -727,6 +733,7 @@ int rpc_switch_client_transport(struct rpc_clnt *clnt, struct rpc_clnt *parent; int err; + args->xprtsec = clnt->cl_xprtsec; xprt = xprt_create_transport(args); if (IS_ERR(xprt)) return PTR_ERR(xprt); @@ -1717,6 +1724,11 @@ call_start(struct rpc_task *task) trace_rpc_request(task); + if (task->tk_client->cl_shutdown) { + rpc_call_rpcerror(task, -EIO); + return; + } + /* Increment call count (version might not be valid for ping) */ if (clnt->cl_program->version[clnt->cl_vers]) clnt->cl_program->version[clnt->cl_vers]->counts[idx]++; @@ -2826,6 +2838,9 @@ static int rpc_ping(struct rpc_clnt *clnt) struct rpc_task *task; int status; + if (clnt->cl_auth->au_ops->ping) + return clnt->cl_auth->au_ops->ping(clnt); + task = rpc_call_null_helper(clnt, NULL, NULL, 0, NULL, NULL); if (IS_ERR(task)) return PTR_ERR(task); @@ -3046,6 +3061,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, if (!xprtargs->ident) xprtargs->ident = ident; + xprtargs->xprtsec = clnt->cl_xprtsec; xprt = xprt_create_transport(xprtargs); if (IS_ERR(xprt)) { ret = PTR_ERR(xprt); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 5a8e6d46809a..5988a5c5ff3f 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -36,6 +36,7 @@ #include "netns.h" #define RPCBIND_SOCK_PATHNAME "/var/run/rpcbind.sock" +#define RPCBIND_SOCK_ABSTRACT_NAME "\0/run/rpcbind.sock" #define RPCBIND_PROGRAM (100000u) #define RPCBIND_PORT (111u) @@ -216,21 +217,22 @@ static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, sn->rpcb_users = 1; } +/* Evaluate to actual length of the `sockaddr_un' structure. */ +# define SUN_LEN(ptr) (offsetof(struct sockaddr_un, sun_path) \ + + 1 + strlen((ptr)->sun_path + 1)) + /* * Returns zero on success, otherwise a negative errno value * is returned. */ -static int rpcb_create_local_unix(struct net *net) +static int rpcb_create_af_local(struct net *net, + const struct sockaddr_un *addr) { - static const struct sockaddr_un rpcb_localaddr_rpcbind = { - .sun_family = AF_LOCAL, - .sun_path = RPCBIND_SOCK_PATHNAME, - }; struct rpc_create_args args = { .net = net, .protocol = XPRT_TRANSPORT_LOCAL, - .address = (struct sockaddr *)&rpcb_localaddr_rpcbind, - .addrsize = sizeof(rpcb_localaddr_rpcbind), + .address = (struct sockaddr *)addr, + .addrsize = SUN_LEN(addr), .servername = "localhost", .program = &rpcb_program, .version = RPCBVERS_2, @@ -269,6 +271,26 @@ out: return result; } +static int rpcb_create_local_abstract(struct net *net) +{ + static const struct sockaddr_un rpcb_localaddr_abstract = { + .sun_family = AF_LOCAL, + .sun_path = RPCBIND_SOCK_ABSTRACT_NAME, + }; + + return rpcb_create_af_local(net, &rpcb_localaddr_abstract); +} + +static int rpcb_create_local_unix(struct net *net) +{ + static const struct sockaddr_un rpcb_localaddr_unix = { + .sun_family = AF_LOCAL, + .sun_path = RPCBIND_SOCK_PATHNAME, + }; + + return rpcb_create_af_local(net, &rpcb_localaddr_unix); +} + /* * Returns zero on success, otherwise a negative errno value * is returned. @@ -332,7 +354,8 @@ int rpcb_create_local(struct net *net) if (rpcb_get_local(net)) goto out; - if (rpcb_create_local_unix(net) != 0) + if (rpcb_create_local_abstract(net) != 0 && + rpcb_create_local_unix(net) != 0) result = rpcb_create_local_net(net); out: diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index 0d0db4e1064e..5c8ecdaaa985 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -239,6 +239,7 @@ static ssize_t rpc_sysfs_xprt_dstaddr_store(struct kobject *kobj, if (!xprt) return 0; if (!(xprt->xprt_class->ident == XPRT_TRANSPORT_TCP || + xprt->xprt_class->ident == XPRT_TRANSPORT_TCP_TLS || xprt->xprt_class->ident == XPRT_TRANSPORT_RDMA)) { xprt_put(xprt); return -EOPNOTSUPP; diff --git a/net/sunrpc/sysfs.h b/net/sunrpc/sysfs.h index 6620cebd1037..d2dd77a0a0e9 100644 --- a/net/sunrpc/sysfs.h +++ b/net/sunrpc/sysfs.h @@ -5,13 +5,6 @@ #ifndef __SUNRPC_SYSFS_H #define __SUNRPC_SYSFS_H -struct rpc_sysfs_client { - struct kobject kobject; - struct net *net; - struct rpc_clnt *clnt; - struct rpc_xprt_switch *xprt_switch; -}; - struct rpc_sysfs_xprt_switch { struct kobject kobject; struct net *net; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 5f9030b81c9e..9f010369100a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -47,6 +47,9 @@ #include <net/checksum.h> #include <net/udp.h> #include <net/tcp.h> +#include <net/tls.h> +#include <net/handshake.h> + #include <linux/bvec.h> #include <linux/highmem.h> #include <linux/uio.h> @@ -96,6 +99,7 @@ static struct ctl_table_header *sunrpc_table_header; static struct xprt_class xs_local_transport; static struct xprt_class xs_udp_transport; static struct xprt_class xs_tcp_transport; +static struct xprt_class xs_tcp_tls_transport; static struct xprt_class xs_bc_tcp_transport; /* @@ -187,6 +191,11 @@ static struct ctl_table xs_tunables_table[] = { */ #define XS_IDLE_DISC_TO (5U * 60 * HZ) +/* + * TLS handshake timeout. + */ +#define XS_TLS_HANDSHAKE_TO (10U * HZ) + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # undef RPC_DEBUG_DATA # define RPCDBG_FACILITY RPCDBG_TRANS @@ -253,7 +262,12 @@ static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) switch (sap->sa_family) { case AF_LOCAL: sun = xs_addr_un(xprt); - strscpy(buf, sun->sun_path, sizeof(buf)); + if (sun->sun_path[0]) { + strscpy(buf, sun->sun_path, sizeof(buf)); + } else { + buf[0] = '@'; + strscpy(buf+1, sun->sun_path+1, sizeof(buf)-1); + } xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); break; @@ -342,13 +356,56 @@ xs_alloc_sparse_pages(struct xdr_buf *buf, size_t want, gfp_t gfp) return want; } +static int +xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg, + struct cmsghdr *cmsg, int ret) +{ + if (cmsg->cmsg_level == SOL_TLS && + cmsg->cmsg_type == TLS_GET_RECORD_TYPE) { + u8 content_type = *((u8 *)CMSG_DATA(cmsg)); + + switch (content_type) { + case TLS_RECORD_TYPE_DATA: + /* TLS sets EOR at the end of each application data + * record, even though there might be more frames + * waiting to be decrypted. + */ + msg->msg_flags &= ~MSG_EOR; + break; + case TLS_RECORD_TYPE_ALERT: + ret = -ENOTCONN; + break; + default: + ret = -EAGAIN; + } + } + return ret; +} + +static int +xs_sock_recv_cmsg(struct socket *sock, struct msghdr *msg, int flags) +{ + union { + struct cmsghdr cmsg; + u8 buf[CMSG_SPACE(sizeof(u8))]; + } u; + int ret; + + msg->msg_control = &u; + msg->msg_controllen = sizeof(u); + ret = sock_recvmsg(sock, msg, flags); + if (msg->msg_controllen != sizeof(u)) + ret = xs_sock_process_cmsg(sock, msg, &u.cmsg, ret); + return ret; +} + static ssize_t xs_sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags, size_t seek) { ssize_t ret; if (seek != 0) iov_iter_advance(&msg->msg_iter, seek); - ret = sock_recvmsg(sock, msg, flags); + ret = xs_sock_recv_cmsg(sock, msg, flags); return ret > 0 ? ret + seek : ret; } @@ -374,7 +431,7 @@ xs_read_discard(struct socket *sock, struct msghdr *msg, int flags, size_t count) { iov_iter_discard(&msg->msg_iter, ITER_DEST, count); - return sock_recvmsg(sock, msg, flags); + return xs_sock_recv_cmsg(sock, msg, flags); } #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE @@ -695,6 +752,8 @@ static void xs_poll_check_readable(struct sock_xprt *transport) { clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); + if (test_bit(XPRT_SOCK_IGNORE_RECV, &transport->sock_state)) + return; if (!xs_poll_socket_readable(transport)) return; if (!test_and_set_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) @@ -1191,6 +1250,8 @@ static void xs_reset_transport(struct sock_xprt *transport) if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); + tls_handshake_cancel(sk); + kernel_sock_shutdown(sock, SHUT_RDWR); mutex_lock(&transport->recv_mutex); @@ -1380,6 +1441,10 @@ static void xs_data_ready(struct sock *sk) trace_xs_data_ready(xprt); transport->old_data_ready(sk); + + if (test_bit(XPRT_SOCK_IGNORE_RECV, &transport->sock_state)) + return; + /* Any data means we had a useful conversation, so * then we don't need to delay the next reconnect */ @@ -2360,6 +2425,267 @@ out_unlock: current_restore_flags(pflags, PF_MEMALLOC); } +/* + * Transfer the connected socket to @upper_transport, then mark that + * xprt CONNECTED. + */ +static int xs_tcp_tls_finish_connecting(struct rpc_xprt *lower_xprt, + struct sock_xprt *upper_transport) +{ + struct sock_xprt *lower_transport = + container_of(lower_xprt, struct sock_xprt, xprt); + struct rpc_xprt *upper_xprt = &upper_transport->xprt; + + if (!upper_transport->inet) { + struct socket *sock = lower_transport->sock; + struct sock *sk = sock->sk; + + /* Avoid temporary address, they are bad for long-lived + * connections such as NFS mounts. + * RFC4941, section 3.6 suggests that: + * Individual applications, which have specific + * knowledge about the normal duration of connections, + * MAY override this as appropriate. + */ + if (xs_addr(upper_xprt)->sa_family == PF_INET6) + ip6_sock_set_addr_preferences(sk, IPV6_PREFER_SRC_PUBLIC); + + xs_tcp_set_socket_timeouts(upper_xprt, sock); + tcp_sock_set_nodelay(sk); + + lock_sock(sk); + + /* @sk is already connected, so it now has the RPC callbacks. + * Reach into @lower_transport to save the original ones. + */ + upper_transport->old_data_ready = lower_transport->old_data_ready; + upper_transport->old_state_change = lower_transport->old_state_change; + upper_transport->old_write_space = lower_transport->old_write_space; + upper_transport->old_error_report = lower_transport->old_error_report; + sk->sk_user_data = upper_xprt; + + /* socket options */ + sock_reset_flag(sk, SOCK_LINGER); + + xprt_clear_connected(upper_xprt); + + upper_transport->sock = sock; + upper_transport->inet = sk; + upper_transport->file = lower_transport->file; + + release_sock(sk); + + /* Reset lower_transport before shutting down its clnt */ + mutex_lock(&lower_transport->recv_mutex); + lower_transport->inet = NULL; + lower_transport->sock = NULL; + lower_transport->file = NULL; + + xprt_clear_connected(lower_xprt); + xs_sock_reset_connection_flags(lower_xprt); + xs_stream_reset_connect(lower_transport); + mutex_unlock(&lower_transport->recv_mutex); + } + + if (!xprt_bound(upper_xprt)) + return -ENOTCONN; + + xs_set_memalloc(upper_xprt); + + if (!xprt_test_and_set_connected(upper_xprt)) { + upper_xprt->connect_cookie++; + clear_bit(XPRT_SOCK_CONNECTING, &upper_transport->sock_state); + xprt_clear_connecting(upper_xprt); + + upper_xprt->stat.connect_count++; + upper_xprt->stat.connect_time += (long)jiffies - + upper_xprt->stat.connect_start; + xs_run_error_worker(upper_transport, XPRT_SOCK_WAKE_PENDING); + } + return 0; +} + +/** + * xs_tls_handshake_done - TLS handshake completion handler + * @data: address of xprt to wake + * @status: status of handshake + * @peerid: serial number of key containing the remote's identity + * + */ +static void xs_tls_handshake_done(void *data, int status, key_serial_t peerid) +{ + struct rpc_xprt *lower_xprt = data; + struct sock_xprt *lower_transport = + container_of(lower_xprt, struct sock_xprt, xprt); + + lower_transport->xprt_err = status ? -EACCES : 0; + complete(&lower_transport->handshake_done); + xprt_put(lower_xprt); +} + +static int xs_tls_handshake_sync(struct rpc_xprt *lower_xprt, struct xprtsec_parms *xprtsec) +{ + struct sock_xprt *lower_transport = + container_of(lower_xprt, struct sock_xprt, xprt); + struct tls_handshake_args args = { + .ta_sock = lower_transport->sock, + .ta_done = xs_tls_handshake_done, + .ta_data = xprt_get(lower_xprt), + .ta_peername = lower_xprt->servername, + }; + struct sock *sk = lower_transport->inet; + int rc; + + init_completion(&lower_transport->handshake_done); + set_bit(XPRT_SOCK_IGNORE_RECV, &lower_transport->sock_state); + lower_transport->xprt_err = -ETIMEDOUT; + switch (xprtsec->policy) { + case RPC_XPRTSEC_TLS_ANON: + rc = tls_client_hello_anon(&args, GFP_KERNEL); + if (rc) + goto out_put_xprt; + break; + case RPC_XPRTSEC_TLS_X509: + args.ta_my_cert = xprtsec->cert_serial; + args.ta_my_privkey = xprtsec->privkey_serial; + rc = tls_client_hello_x509(&args, GFP_KERNEL); + if (rc) + goto out_put_xprt; + break; + default: + rc = -EACCES; + goto out_put_xprt; + } + + rc = wait_for_completion_interruptible_timeout(&lower_transport->handshake_done, + XS_TLS_HANDSHAKE_TO); + if (rc <= 0) { + if (!tls_handshake_cancel(sk)) { + if (rc == 0) + rc = -ETIMEDOUT; + goto out_put_xprt; + } + } + + rc = lower_transport->xprt_err; + +out: + xs_stream_reset_connect(lower_transport); + clear_bit(XPRT_SOCK_IGNORE_RECV, &lower_transport->sock_state); + return rc; + +out_put_xprt: + xprt_put(lower_xprt); + goto out; +} + +/** + * xs_tcp_tls_setup_socket - establish a TLS session on a TCP socket + * @work: queued work item + * + * Invoked by a work queue tasklet. + * + * For RPC-with-TLS, there is a two-stage connection process. + * + * The "upper-layer xprt" is visible to the RPC consumer. Once it has + * been marked connected, the consumer knows that a TCP connection and + * a TLS session have been established. + * + * A "lower-layer xprt", created in this function, handles the mechanics + * of connecting the TCP socket, performing the RPC_AUTH_TLS probe, and + * then driving the TLS handshake. Once all that is complete, the upper + * layer xprt is marked connected. + */ +static void xs_tcp_tls_setup_socket(struct work_struct *work) +{ + struct sock_xprt *upper_transport = + container_of(work, struct sock_xprt, connect_worker.work); + struct rpc_clnt *upper_clnt = upper_transport->clnt; + struct rpc_xprt *upper_xprt = &upper_transport->xprt; + struct rpc_create_args args = { + .net = upper_xprt->xprt_net, + .protocol = upper_xprt->prot, + .address = (struct sockaddr *)&upper_xprt->addr, + .addrsize = upper_xprt->addrlen, + .timeout = upper_clnt->cl_timeout, + .servername = upper_xprt->servername, + .program = upper_clnt->cl_program, + .prognumber = upper_clnt->cl_prog, + .version = upper_clnt->cl_vers, + .authflavor = RPC_AUTH_TLS, + .cred = upper_clnt->cl_cred, + .xprtsec = { + .policy = RPC_XPRTSEC_NONE, + }, + }; + unsigned int pflags = current->flags; + struct rpc_clnt *lower_clnt; + struct rpc_xprt *lower_xprt; + int status; + + if (atomic_read(&upper_xprt->swapper)) + current->flags |= PF_MEMALLOC; + + xs_stream_start_connect(upper_transport); + + /* This implicitly sends an RPC_AUTH_TLS probe */ + lower_clnt = rpc_create(&args); + if (IS_ERR(lower_clnt)) { + trace_rpc_tls_unavailable(upper_clnt, upper_xprt); + clear_bit(XPRT_SOCK_CONNECTING, &upper_transport->sock_state); + xprt_clear_connecting(upper_xprt); + xprt_wake_pending_tasks(upper_xprt, PTR_ERR(lower_clnt)); + xs_run_error_worker(upper_transport, XPRT_SOCK_WAKE_PENDING); + goto out_unlock; + } + + /* RPC_AUTH_TLS probe was successful. Try a TLS handshake on + * the lower xprt. + */ + rcu_read_lock(); + lower_xprt = rcu_dereference(lower_clnt->cl_xprt); + rcu_read_unlock(); + status = xs_tls_handshake_sync(lower_xprt, &upper_xprt->xprtsec); + if (status) { + trace_rpc_tls_not_started(upper_clnt, upper_xprt); + goto out_close; + } + + status = xs_tcp_tls_finish_connecting(lower_xprt, upper_transport); + if (status) + goto out_close; + + trace_rpc_socket_connect(upper_xprt, upper_transport->sock, 0); + if (!xprt_test_and_set_connected(upper_xprt)) { + upper_xprt->connect_cookie++; + clear_bit(XPRT_SOCK_CONNECTING, &upper_transport->sock_state); + xprt_clear_connecting(upper_xprt); + + upper_xprt->stat.connect_count++; + upper_xprt->stat.connect_time += (long)jiffies - + upper_xprt->stat.connect_start; + xs_run_error_worker(upper_transport, XPRT_SOCK_WAKE_PENDING); + } + rpc_shutdown_client(lower_clnt); + +out_unlock: + current_restore_flags(pflags, PF_MEMALLOC); + upper_transport->clnt = NULL; + xprt_unlock_connect(upper_xprt, upper_transport); + return; + +out_close: + rpc_shutdown_client(lower_clnt); + + /* xprt_force_disconnect() wakes tasks with a fixed tk_status code. + * Wake them first here to ensure they get our tk_status code. + */ + xprt_wake_pending_tasks(upper_xprt, status); + xs_tcp_force_close(upper_xprt); + xprt_clear_connecting(upper_xprt); + goto out_unlock; +} + /** * xs_connect - connect a socket to a remote endpoint * @xprt: pointer to transport structure @@ -2391,6 +2717,7 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) } else dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); + transport->clnt = task->tk_client; queue_delayed_work(xprtiod_workqueue, &transport->connect_worker, delay); @@ -2858,7 +3185,7 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) switch (sun->sun_family) { case AF_LOCAL: - if (sun->sun_path[0] != '/') { + if (sun->sun_path[0] != '/' && sun->sun_path[0] != '\0') { dprintk("RPC: bad AF_LOCAL address: %s\n", sun->sun_path); ret = ERR_PTR(-EINVAL); @@ -3045,6 +3372,94 @@ out_err: } /** + * xs_setup_tcp_tls - Set up transport to use a TCP with TLS + * @args: rpc transport creation arguments + * + */ +static struct rpc_xprt *xs_setup_tcp_tls(struct xprt_create *args) +{ + struct sockaddr *addr = args->dstaddr; + struct rpc_xprt *xprt; + struct sock_xprt *transport; + struct rpc_xprt *ret; + unsigned int max_slot_table_size = xprt_max_tcp_slot_table_entries; + + if (args->flags & XPRT_CREATE_INFINITE_SLOTS) + max_slot_table_size = RPC_MAX_SLOT_TABLE_LIMIT; + + xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries, + max_slot_table_size); + if (IS_ERR(xprt)) + return xprt; + transport = container_of(xprt, struct sock_xprt, xprt); + + xprt->prot = IPPROTO_TCP; + xprt->xprt_class = &xs_tcp_transport; + xprt->max_payload = RPC_MAX_FRAGMENT_SIZE; + + xprt->bind_timeout = XS_BIND_TO; + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + xprt->idle_timeout = XS_IDLE_DISC_TO; + + xprt->ops = &xs_tcp_ops; + xprt->timeout = &xs_tcp_default_timeout; + + xprt->max_reconnect_timeout = xprt->timeout->to_maxval; + xprt->connect_timeout = xprt->timeout->to_initval * + (xprt->timeout->to_retries + 1); + + INIT_WORK(&transport->recv_worker, xs_stream_data_receive_workfn); + INIT_WORK(&transport->error_worker, xs_error_handle); + + switch (args->xprtsec.policy) { + case RPC_XPRTSEC_TLS_ANON: + case RPC_XPRTSEC_TLS_X509: + xprt->xprtsec = args->xprtsec; + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_tls_setup_socket); + break; + default: + ret = ERR_PTR(-EACCES); + goto out_err; + } + + switch (addr->sa_family) { + case AF_INET: + if (((struct sockaddr_in *)addr)->sin_port != htons(0)) + xprt_set_bound(xprt); + + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); + break; + case AF_INET6: + if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) + xprt_set_bound(xprt); + + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); + break; + default: + ret = ERR_PTR(-EAFNOSUPPORT); + goto out_err; + } + + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); + + if (try_module_get(THIS_MODULE)) + return xprt; + ret = ERR_PTR(-EINVAL); +out_err: + xs_xprt_free(xprt); + return ret; +} + +/** * xs_setup_bc_tcp - Set up transport to use a TCP backchannel socket * @args: rpc transport creation arguments * @@ -3153,6 +3568,15 @@ static struct xprt_class xs_tcp_transport = { .netid = { "tcp", "tcp6", "" }, }; +static struct xprt_class xs_tcp_tls_transport = { + .list = LIST_HEAD_INIT(xs_tcp_tls_transport.list), + .name = "tcp-with-tls", + .owner = THIS_MODULE, + .ident = XPRT_TRANSPORT_TCP_TLS, + .setup = xs_setup_tcp_tls, + .netid = { "tcp", "tcp6", "" }, +}; + static struct xprt_class xs_bc_tcp_transport = { .list = LIST_HEAD_INIT(xs_bc_tcp_transport.list), .name = "tcp NFSv4.1 backchannel", @@ -3174,6 +3598,7 @@ int init_socket_xprt(void) xprt_register_transport(&xs_local_transport); xprt_register_transport(&xs_udp_transport); xprt_register_transport(&xs_tcp_transport); + xprt_register_transport(&xs_tcp_tls_transport); xprt_register_transport(&xs_bc_tcp_transport); return 0; @@ -3193,6 +3618,7 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_local_transport); xprt_unregister_transport(&xs_udp_transport); xprt_unregister_transport(&xs_tcp_transport); + xprt_unregister_transport(&xs_tcp_tls_transport); xprt_unregister_transport(&xs_bc_tcp_transport); } diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 577fa5af33ec..302fd749c424 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1960,7 +1960,8 @@ rcv: skb_reset_network_header(*skb); skb_pull(*skb, tipc_ehdr_size(ehdr)); - pskb_trim(*skb, (*skb)->len - aead->authsize); + if (pskb_trim(*skb, (*skb)->len - aead->authsize)) + goto free_skb; /* Validate TIPCv2 message */ if (unlikely(!tipc_msg_validate(skb))) { diff --git a/net/tipc/node.c b/net/tipc/node.c index 5e000fde8067..a9c5b6594889 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -583,7 +583,7 @@ update: n->capabilities, &n->bc_entry.inputq1, &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) { pr_warn("Broadcast rcv link creation failed, no memory\n"); - kfree(n); + tipc_node_put(n); n = NULL; goto exit; } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 2021fe557e50..529101eb20bd 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); +static struct page *dummy_page; + static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { @@ -312,36 +314,33 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_device_record_close(struct sock *sk, - struct tls_context *ctx, - struct tls_record_info *record, - struct page_frag *pfrag, - unsigned char record_type) +static void tls_device_record_close(struct sock *sk, + struct tls_context *ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; - int ret; + struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) - * if we can't allocate memory now, steal some back from data + * if we can't allocate memory now use the dummy page */ - if (likely(skb_page_frag_refill(prot->tag_size, pfrag, - sk->sk_allocation))) { - ret = 0; - tls_append_frag(record, pfrag, prot->tag_size); - } else { - ret = prot->tag_size; - if (record->len <= prot->overhead_size) - return -ENOMEM; + if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && + !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { + dummy_tag_frag.page = dummy_page; + dummy_tag_frag.offset = 0; + pfrag = &dummy_tag_frag; } + tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); - return ret; } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, @@ -541,18 +540,8 @@ last_record: if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { - rc = tls_device_record_close(sk, tls_ctx, record, - pfrag, record_type); - if (rc) { - if (rc > 0) { - size += rc; - } else { - size = orig_size; - destroy_record(record); - ctx->open_record = NULL; - break; - } - } + tls_device_record_close(sk, tls_ctx, record, + pfrag, record_type); rc = tls_push_record(sk, tls_ctx, @@ -1450,14 +1439,26 @@ int __init tls_device_init(void) { int err; - destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); - if (!destruct_wq) + dummy_page = alloc_page(GFP_KERNEL); + if (!dummy_page) return -ENOMEM; + destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); + if (!destruct_wq) { + err = -ENOMEM; + goto err_free_dummy; + } + err = register_netdevice_notifier(&tls_dev_notifier); if (err) - destroy_workqueue(destruct_wq); + goto err_destroy_wq; + return 0; + +err_destroy_wq: + destroy_workqueue(destruct_wq); +err_free_dummy: + put_page(dummy_page); return err; } @@ -1466,4 +1467,5 @@ void __exit tls_device_cleanup(void) unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); + put_page(dummy_page); } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b6896126bb92..4a8ee2f6badb 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -139,9 +139,6 @@ int tls_push_sg(struct sock *sk, ctx->splicing_pages = true; while (1) { - if (sg_is_last(sg)) - msg.msg_flags = flags; - /* is sending application-limited? */ tcp_rate_check_app_limited(sk); p = sg_page(sg); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 123b35ddfd71..86930a8ed012 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -289,17 +289,29 @@ static int unix_validate_addr(struct sockaddr_un *sunaddr, int addr_len) return 0; } -static void unix_mkname_bsd(struct sockaddr_un *sunaddr, int addr_len) +static int unix_mkname_bsd(struct sockaddr_un *sunaddr, int addr_len) { + struct sockaddr_storage *addr = (struct sockaddr_storage *)sunaddr; + short offset = offsetof(struct sockaddr_storage, __data); + + BUILD_BUG_ON(offset != offsetof(struct sockaddr_un, sun_path)); + /* This may look like an off by one error but it is a bit more * subtle. 108 is the longest valid AF_UNIX path for a binding. * sun_path[108] doesn't as such exist. However in kernel space * we are guaranteed that it is a valid memory location in our * kernel address buffer because syscall functions always pass * a pointer of struct sockaddr_storage which has a bigger buffer - * than 108. + * than 108. Also, we must terminate sun_path for strlen() in + * getname_kernel(). + */ + addr->__data[addr_len - offset] = 0; + + /* Don't pass sunaddr->sun_path to strlen(). Otherwise, 108 will + * cause panic if CONFIG_FORTIFY_SOURCE=y. Let __fortify_strlen() + * know the actual buffer. */ - ((char *)sunaddr)[addr_len] = 0; + return strlen(addr->__data) + offset + 1; } static void __unix_remove_socket(struct sock *sk) @@ -778,7 +790,7 @@ static int unix_set_peek_off(struct sock *sk, int val) if (mutex_lock_interruptible(&u->iolock)) return -EINTR; - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); mutex_unlock(&u->iolock); return 0; @@ -1208,10 +1220,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, struct path parent; int err; - unix_mkname_bsd(sunaddr, addr_len); - addr_len = strlen(sunaddr->sun_path) + - offsetof(struct sockaddr_un, sun_path) + 1; - + addr_len = unix_mkname_bsd(sunaddr, addr_len); addr = unix_create_addr(sunaddr, addr_len); if (!addr) return -ENOMEM; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0da2e6a2a7ea..8bcf8e293308 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5430,8 +5430,11 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) if (!wiphy->mbssid_max_interfaces) return ERR_PTR(-EINVAL); - nla_for_each_nested(nl_elems, attrs, rem_elems) + nla_for_each_nested(nl_elems, attrs, rem_elems) { + if (num_elems >= 255) + return ERR_PTR(-EINVAL); num_elems++; + } elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); if (!elems) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 8bf00caf5d29..0cf1ce7b6934 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -657,7 +657,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp); if (ret) - return ret; + return 0; for_each_element_id(elem, WLAN_EID_REDUCED_NEIGHBOR_REPORT, ies->data, ies->len) { diff --git a/net/wireless/util.c b/net/wireless/util.c index 89c9ad6c886e..1783ab9d57a3 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -580,6 +580,8 @@ int ieee80211_strip_8023_mesh_hdr(struct sk_buff *skb) hdrlen += ETH_ALEN + 2; else if (!pskb_may_pull(skb, hdrlen)) return -EINVAL; + else + payload.eth.h_proto = htons(skb->len - hdrlen); mesh_addr = skb->data + sizeof(payload.eth) + ETH_ALEN; switch (payload.flags & MESH_FLAGS_AE) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 5a8c0dd250af..10ea85c03147 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -505,7 +505,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->dev = dev; skb->priority = xs->sk.sk_priority; - skb->mark = xs->sk.sk_mark; + skb->mark = READ_ONCE(xs->sk.sk_mark); skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr; skb->destructor = xsk_destruct_skb; @@ -886,6 +886,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev; + int bound_dev_if; u32 flags, qid; int err = 0; @@ -899,6 +900,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) XDP_USE_NEED_WAKEUP)) return -EINVAL; + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + if (bound_dev_if && bound_dev_if != sxdp->sxdp_ifindex) + return -EINVAL; + rtnl_lock(); mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { @@ -989,6 +994,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); + xs->pool = NULL; sockfd_put(sock); goto out_unlock; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e7617c9959c3..d6b405782b63 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2250,7 +2250,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { - if ((sk->sk_mark & pol->mark.m) != pol->mark.v || + if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; |