From f54ec58fee837ec847cb8b50593e81bfaa46107f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Oct 2020 21:12:12 +0100 Subject: wimax: move out to staging There are no known users of this driver as of October 2020, and it will be removed unless someone turns out to still need it in future releases. According to https://en.wikipedia.org/wiki/List_of_WiMAX_networks, there have been many public wimax networks, but it appears that many of these have migrated to LTE or discontinued their service altogether. As most PCs and phones lack WiMAX hardware support, the remaining networks tend to use standalone routers. These almost certainly run Linux, but not a modern kernel or the mainline wimax driver stack. NetworkManager appears to have dropped userspace support in 2015 https://bugzilla.gnome.org/show_bug.cgi?id=747846, the www.linuxwimax.org site had already shut down earlier. WiMax is apparently still being deployed on airport campus networks ("AeroMACS"), but in a frequency band that was not supported by the old Intel 2400m (used in Sandy Bridge laptops and earlier), which is the only driver using the kernel's wimax stack. Move all files into drivers/staging/wimax, including the uapi header files and documentation, to make it easier to remove it when it gets to that. Only minimal changes are made to the source files, in order to make it possible to port patches across the move. Also remove the MAINTAINERS entry that refers to a broken mailing list and website. Acked-by: Jakub Kicinski Acked-by: Greg Kroah-Hartman Acked-By: Inaky Perez-Gonzalez Acked-by: Johannes Berg Suggested-by: Inaky Perez-Gonzalez Signed-off-by: Arnd Bergmann --- include/uapi/linux/wimax.h | 239 ---------------- include/uapi/linux/wimax/i2400m.h | 572 -------------------------------------- 2 files changed, 811 deletions(-) delete mode 100644 include/uapi/linux/wimax.h delete mode 100644 include/uapi/linux/wimax/i2400m.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/wimax.h b/include/uapi/linux/wimax.h deleted file mode 100644 index 9f6b77af2f6d..000000000000 --- a/include/uapi/linux/wimax.h +++ /dev/null @@ -1,239 +0,0 @@ -/* - * Linux WiMax - * API for user space - * - * - * Copyright (C) 2007-2008 Intel Corporation. All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * - * Intel Corporation - * Inaky Perez-Gonzalez - * - Initial implementation - * - * - * This file declares the user/kernel protocol that is spoken over - * Generic Netlink, as well as any type declaration that is to be used - * by kernel and user space. - * - * It is intended for user space to clone it verbatim to use it as a - * primary reference for definitions. - * - * Stuff intended for kernel usage as well as full protocol and stack - * documentation is rooted in include/net/wimax.h. - */ - -#ifndef __LINUX__WIMAX_H__ -#define __LINUX__WIMAX_H__ - -#include - -enum { - /** - * Version of the interface (unsigned decimal, MMm, max 25.5) - * M - Major: change if removing or modifying an existing call. - * m - minor: change when adding a new call - */ - WIMAX_GNL_VERSION = 01, - /* Generic NetLink attributes */ - WIMAX_GNL_ATTR_INVALID = 0x00, - WIMAX_GNL_ATTR_MAX = 10, -}; - - -/* - * Generic NetLink operations - * - * Most of these map to an API call; _OP_ stands for operation, _RP_ - * for reply and _RE_ for report (aka: signal). - */ -enum { - WIMAX_GNL_OP_MSG_FROM_USER, /* User to kernel message */ - WIMAX_GNL_OP_MSG_TO_USER, /* Kernel to user message */ - WIMAX_GNL_OP_RFKILL, /* Run wimax_rfkill() */ - WIMAX_GNL_OP_RESET, /* Run wimax_rfkill() */ - WIMAX_GNL_RE_STATE_CHANGE, /* Report: status change */ - WIMAX_GNL_OP_STATE_GET, /* Request for current state */ -}; - - -/* Message from user / to user */ -enum { - WIMAX_GNL_MSG_IFIDX = 1, - WIMAX_GNL_MSG_PIPE_NAME, - WIMAX_GNL_MSG_DATA, -}; - - -/* - * wimax_rfkill() - * - * The state of the radio (ON/OFF) is mapped to the rfkill subsystem's - * switch state (DISABLED/ENABLED). - */ -enum wimax_rf_state { - WIMAX_RF_OFF = 0, /* Radio is off, rfkill on/enabled */ - WIMAX_RF_ON = 1, /* Radio is on, rfkill off/disabled */ - WIMAX_RF_QUERY = 2, -}; - -/* Attributes */ -enum { - WIMAX_GNL_RFKILL_IFIDX = 1, - WIMAX_GNL_RFKILL_STATE, -}; - - -/* Attributes for wimax_reset() */ -enum { - WIMAX_GNL_RESET_IFIDX = 1, -}; - -/* Attributes for wimax_state_get() */ -enum { - WIMAX_GNL_STGET_IFIDX = 1, -}; - -/* - * Attributes for the Report State Change - * - * For now we just have the old and new states; new attributes might - * be added later on. - */ -enum { - WIMAX_GNL_STCH_IFIDX = 1, - WIMAX_GNL_STCH_STATE_OLD, - WIMAX_GNL_STCH_STATE_NEW, -}; - - -/** - * enum wimax_st - The different states of a WiMAX device - * @__WIMAX_ST_NULL: The device structure has been allocated and zeroed, - * but still wimax_dev_add() hasn't been called. There is no state. - * - * @WIMAX_ST_DOWN: The device has been registered with the WiMAX and - * networking stacks, but it is not initialized (normally that is - * done with 'ifconfig DEV up' [or equivalent], which can upload - * firmware and enable communications with the device). - * In this state, the device is powered down and using as less - * power as possible. - * This state is the default after a call to wimax_dev_add(). It - * is ok to have drivers move directly to %WIMAX_ST_UNINITIALIZED - * or %WIMAX_ST_RADIO_OFF in _probe() after the call to - * wimax_dev_add(). - * It is recommended that the driver leaves this state when - * calling 'ifconfig DEV up' and enters it back on 'ifconfig DEV - * down'. - * - * @__WIMAX_ST_QUIESCING: The device is being torn down, so no API - * operations are allowed to proceed except the ones needed to - * complete the device clean up process. - * - * @WIMAX_ST_UNINITIALIZED: [optional] Communication with the device - * is setup, but the device still requires some configuration - * before being operational. - * Some WiMAX API calls might work. - * - * @WIMAX_ST_RADIO_OFF: The device is fully up; radio is off (wether - * by hardware or software switches). - * It is recommended to always leave the device in this state - * after initialization. - * - * @WIMAX_ST_READY: The device is fully up and radio is on. - * - * @WIMAX_ST_SCANNING: [optional] The device has been instructed to - * scan. In this state, the device cannot be actively connected to - * a network. - * - * @WIMAX_ST_CONNECTING: The device is connecting to a network. This - * state exists because in some devices, the connect process can - * include a number of negotiations between user space, kernel - * space and the device. User space needs to know what the device - * is doing. If the connect sequence in a device is atomic and - * fast, the device can transition directly to CONNECTED - * - * @WIMAX_ST_CONNECTED: The device is connected to a network. - * - * @__WIMAX_ST_INVALID: This is an invalid state used to mark the - * maximum numeric value of states. - * - * Description: - * - * Transitions from one state to another one are atomic and can only - * be caused in kernel space with wimax_state_change(). To read the - * state, use wimax_state_get(). - * - * States starting with __ are internal and shall not be used or - * referred to by drivers or userspace. They look ugly, but that's the - * point -- if any use is made non-internal to the stack, it is easier - * to catch on review. - * - * All API operations [with well defined exceptions] will take the - * device mutex before starting and then check the state. If the state - * is %__WIMAX_ST_NULL, %WIMAX_ST_DOWN, %WIMAX_ST_UNINITIALIZED or - * %__WIMAX_ST_QUIESCING, it will drop the lock and quit with - * -%EINVAL, -%ENOMEDIUM, -%ENOTCONN or -%ESHUTDOWN. - * - * The order of the definitions is important, so we can do numerical - * comparisons (eg: < %WIMAX_ST_RADIO_OFF means the device is not ready - * to operate). - */ -/* - * The allowed state transitions are described in the table below - * (states in rows can go to states in columns where there is an X): - * - * UNINI RADIO READY SCAN CONNEC CONNEC - * NULL DOWN QUIESCING TIALIZED OFF NING TING TED - * NULL - x - * DOWN - x x x - * QUIESCING x - - * UNINITIALIZED x - x - * RADIO_OFF x - x - * READY x x - x x x - * SCANNING x x x - x x - * CONNECTING x x x x - x - * CONNECTED x x x - - * - * This table not available in kernel-doc because the formatting messes it up. - */ - enum wimax_st { - __WIMAX_ST_NULL = 0, - WIMAX_ST_DOWN, - __WIMAX_ST_QUIESCING, - WIMAX_ST_UNINITIALIZED, - WIMAX_ST_RADIO_OFF, - WIMAX_ST_READY, - WIMAX_ST_SCANNING, - WIMAX_ST_CONNECTING, - WIMAX_ST_CONNECTED, - __WIMAX_ST_INVALID /* Always keep last */ -}; - - -#endif /* #ifndef __LINUX__WIMAX_H__ */ diff --git a/include/uapi/linux/wimax/i2400m.h b/include/uapi/linux/wimax/i2400m.h deleted file mode 100644 index fd198bc24a3c..000000000000 --- a/include/uapi/linux/wimax/i2400m.h +++ /dev/null @@ -1,572 +0,0 @@ -/* - * Intel Wireless WiMax Connection 2400m - * Host-Device protocol interface definitions - * - * - * Copyright (C) 2007-2008 Intel Corporation. All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * - * Intel Corporation - * Inaky Perez-Gonzalez - * - Initial implementation - * - * - * This header defines the data structures and constants used to - * communicate with the device. - * - * BOOTMODE/BOOTROM/FIRMWARE UPLOAD PROTOCOL - * - * The firmware upload protocol is quite simple and only requires a - * handful of commands. See drivers/net/wimax/i2400m/fw.c for more - * details. - * - * The BCF data structure is for the firmware file header. - * - * - * THE DATA / CONTROL PROTOCOL - * - * This is the normal protocol spoken with the device once the - * firmware is uploaded. It transports data payloads and control - * messages back and forth. - * - * It consists 'messages' that pack one or more payloads each. The - * format is described in detail in drivers/net/wimax/i2400m/rx.c and - * tx.c. - * - * - * THE L3L4 PROTOCOL - * - * The term L3L4 refers to Layer 3 (the device), Layer 4 (the - * driver/host software). - * - * This is the control protocol used by the host to control the i2400m - * device (scan, connect, disconnect...). This is sent to / received - * as control frames. These frames consist of a header and zero or - * more TLVs with information. We call each control frame a "message". - * - * Each message is composed of: - * - * HEADER - * [TLV0 + PAYLOAD0] - * [TLV1 + PAYLOAD1] - * [...] - * [TLVN + PAYLOADN] - * - * The HEADER is defined by 'struct i2400m_l3l4_hdr'. The payloads are - * defined by a TLV structure (Type Length Value) which is a 'header' - * (struct i2400m_tlv_hdr) and then the payload. - * - * All integers are represented as Little Endian. - * - * - REQUESTS AND EVENTS - * - * The requests can be clasified as follows: - * - * COMMAND: implies a request from the host to the device requesting - * an action being performed. The device will reply with a - * message (with the same type as the command), status and - * no (TLV) payload. Execution of a command might cause - * events (of different type) to be sent later on as - * device's state changes. - * - * GET/SET: similar to COMMAND, but will not cause other - * EVENTs. The reply, in the case of GET, will contain - * TLVs with the requested information. - * - * EVENT: asynchronous messages sent from the device, maybe as a - * consequence of previous COMMANDs but disassociated from - * them. - * - * Only one request might be pending at the same time (ie: don't - * parallelize nor post another GET request before the previous - * COMMAND has been acknowledged with it's corresponding reply by the - * device). - * - * The different requests and their formats are described below: - * - * I2400M_MT_* Message types - * I2400M_MS_* Message status (for replies, events) - * i2400m_tlv_* TLVs - * - * data types are named 'struct i2400m_msg_OPNAME', OPNAME matching the - * operation. - */ - -#ifndef __LINUX__WIMAX__I2400M_H__ -#define __LINUX__WIMAX__I2400M_H__ - -#include -#include - -/* - * Host Device Interface (HDI) common to all busses - */ - -/* Boot-mode (firmware upload mode) commands */ - -/* Header for the firmware file */ -struct i2400m_bcf_hdr { - __le32 module_type; - __le32 header_len; - __le32 header_version; - __le32 module_id; - __le32 module_vendor; - __le32 date; /* BCD YYYMMDD */ - __le32 size; /* in dwords */ - __le32 key_size; /* in dwords */ - __le32 modulus_size; /* in dwords */ - __le32 exponent_size; /* in dwords */ - __u8 reserved[88]; -} __attribute__ ((packed)); - -/* Boot mode opcodes */ -enum i2400m_brh_opcode { - I2400M_BRH_READ = 1, - I2400M_BRH_WRITE = 2, - I2400M_BRH_JUMP = 3, - I2400M_BRH_SIGNED_JUMP = 8, - I2400M_BRH_HASH_PAYLOAD_ONLY = 9, -}; - -/* Boot mode command masks and stuff */ -enum i2400m_brh { - I2400M_BRH_SIGNATURE = 0xcbbc0000, - I2400M_BRH_SIGNATURE_MASK = 0xffff0000, - I2400M_BRH_SIGNATURE_SHIFT = 16, - I2400M_BRH_OPCODE_MASK = 0x0000000f, - I2400M_BRH_RESPONSE_MASK = 0x000000f0, - I2400M_BRH_RESPONSE_SHIFT = 4, - I2400M_BRH_DIRECT_ACCESS = 0x00000400, - I2400M_BRH_RESPONSE_REQUIRED = 0x00000200, - I2400M_BRH_USE_CHECKSUM = 0x00000100, -}; - - -/** - * i2400m_bootrom_header - Header for a boot-mode command - * - * @cmd: the above command descriptor - * @target_addr: where on the device memory should the action be performed. - * @data_size: for read/write, amount of data to be read/written - * @block_checksum: checksum value (if applicable) - * @payload: the beginning of data attached to this header - */ -struct i2400m_bootrom_header { - __le32 command; /* Compose with enum i2400_brh */ - __le32 target_addr; - __le32 data_size; - __le32 block_checksum; - char payload[0]; -} __attribute__ ((packed)); - - -/* - * Data / control protocol - */ - -/* Packet types for the host-device interface */ -enum i2400m_pt { - I2400M_PT_DATA = 0, - I2400M_PT_CTRL, - I2400M_PT_TRACE, /* For device debug */ - I2400M_PT_RESET_WARM, /* device reset */ - I2400M_PT_RESET_COLD, /* USB[transport] reset, like reconnect */ - I2400M_PT_EDATA, /* Extended RX data */ - I2400M_PT_ILLEGAL -}; - - -/* - * Payload for a data packet - * - * This is prefixed to each and every outgoing DATA type. - */ -struct i2400m_pl_data_hdr { - __le32 reserved; -} __attribute__((packed)); - - -/* - * Payload for an extended data packet - * - * New in fw v1.4 - * - * @reorder: if this payload has to be reorder or not (and how) - * @cs: the type of data in the packet, as defined per (802.16e - * T11.13.19.1). Currently only 2 (IPv4 packet) supported. - * - * This is prefixed to each and every INCOMING DATA packet. - */ -struct i2400m_pl_edata_hdr { - __le32 reorder; /* bits defined in i2400m_ro */ - __u8 cs; - __u8 reserved[11]; -} __attribute__((packed)); - -enum i2400m_cs { - I2400M_CS_IPV4_0 = 0, - I2400M_CS_IPV4 = 2, -}; - -enum i2400m_ro { - I2400M_RO_NEEDED = 0x01, - I2400M_RO_TYPE = 0x03, - I2400M_RO_TYPE_SHIFT = 1, - I2400M_RO_CIN = 0x0f, - I2400M_RO_CIN_SHIFT = 4, - I2400M_RO_FBN = 0x07ff, - I2400M_RO_FBN_SHIFT = 8, - I2400M_RO_SN = 0x07ff, - I2400M_RO_SN_SHIFT = 21, -}; - -enum i2400m_ro_type { - I2400M_RO_TYPE_RESET = 0, - I2400M_RO_TYPE_PACKET, - I2400M_RO_TYPE_WS, - I2400M_RO_TYPE_PACKET_WS, -}; - - -/* Misc constants */ -enum { - I2400M_PL_ALIGN = 16, /* Payload data size alignment */ - I2400M_PL_SIZE_MAX = 0x3EFF, - I2400M_MAX_PLS_IN_MSG = 60, - /* protocol barkers: sync sequences; for notifications they - * are sent in groups of four. */ - I2400M_H2D_PREVIEW_BARKER = 0xcafe900d, - I2400M_COLD_RESET_BARKER = 0xc01dc01d, - I2400M_WARM_RESET_BARKER = 0x50f750f7, - I2400M_NBOOT_BARKER = 0xdeadbeef, - I2400M_SBOOT_BARKER = 0x0ff1c1a1, - I2400M_SBOOT_BARKER_6050 = 0x80000001, - I2400M_ACK_BARKER = 0xfeedbabe, - I2400M_D2H_MSG_BARKER = 0xbeefbabe, -}; - - -/* - * Hardware payload descriptor - * - * Bitfields encoded in a struct to enforce typing semantics. - * - * Look in rx.c and tx.c for a full description of the format. - */ -struct i2400m_pld { - __le32 val; -} __attribute__ ((packed)); - -#define I2400M_PLD_SIZE_MASK 0x00003fff -#define I2400M_PLD_TYPE_SHIFT 16 -#define I2400M_PLD_TYPE_MASK 0x000f0000 - -/* - * Header for a TX message or RX message - * - * @barker: preamble - * @size: used for management of the FIFO queue buffer; before - * sending, this is converted to be a real preamble. This - * indicates the real size of the TX message that starts at this - * point. If the highest bit is set, then this message is to be - * skipped. - * @sequence: sequence number of this message - * @offset: offset where the message itself starts -- see the comments - * in the file header about message header and payload descriptor - * alignment. - * @num_pls: number of payloads in this message - * @padding: amount of padding bytes at the end of the message to make - * it be of block-size aligned - * - * Look in rx.c and tx.c for a full description of the format. - */ -struct i2400m_msg_hdr { - union { - __le32 barker; - __u32 size; /* same size type as barker!! */ - }; - union { - __le32 sequence; - __u32 offset; /* same size type as barker!! */ - }; - __le16 num_pls; - __le16 rsv1; - __le16 padding; - __le16 rsv2; - struct i2400m_pld pld[0]; -} __attribute__ ((packed)); - - - -/* - * L3/L4 control protocol - */ - -enum { - /* Interface version */ - I2400M_L3L4_VERSION = 0x0100, -}; - -/* Message types */ -enum i2400m_mt { - I2400M_MT_RESERVED = 0x0000, - I2400M_MT_INVALID = 0xffff, - I2400M_MT_REPORT_MASK = 0x8000, - - I2400M_MT_GET_SCAN_RESULT = 0x4202, - I2400M_MT_SET_SCAN_PARAM = 0x4402, - I2400M_MT_CMD_RF_CONTROL = 0x4602, - I2400M_MT_CMD_SCAN = 0x4603, - I2400M_MT_CMD_CONNECT = 0x4604, - I2400M_MT_CMD_DISCONNECT = 0x4605, - I2400M_MT_CMD_EXIT_IDLE = 0x4606, - I2400M_MT_GET_LM_VERSION = 0x5201, - I2400M_MT_GET_DEVICE_INFO = 0x5202, - I2400M_MT_GET_LINK_STATUS = 0x5203, - I2400M_MT_GET_STATISTICS = 0x5204, - I2400M_MT_GET_STATE = 0x5205, - I2400M_MT_GET_MEDIA_STATUS = 0x5206, - I2400M_MT_SET_INIT_CONFIG = 0x5404, - I2400M_MT_CMD_INIT = 0x5601, - I2400M_MT_CMD_TERMINATE = 0x5602, - I2400M_MT_CMD_MODE_OF_OP = 0x5603, - I2400M_MT_CMD_RESET_DEVICE = 0x5604, - I2400M_MT_CMD_MONITOR_CONTROL = 0x5605, - I2400M_MT_CMD_ENTER_POWERSAVE = 0x5606, - I2400M_MT_GET_TLS_OPERATION_RESULT = 0x6201, - I2400M_MT_SET_EAP_SUCCESS = 0x6402, - I2400M_MT_SET_EAP_FAIL = 0x6403, - I2400M_MT_SET_EAP_KEY = 0x6404, - I2400M_MT_CMD_SEND_EAP_RESPONSE = 0x6602, - I2400M_MT_REPORT_SCAN_RESULT = 0xc002, - I2400M_MT_REPORT_STATE = 0xd002, - I2400M_MT_REPORT_POWERSAVE_READY = 0xd005, - I2400M_MT_REPORT_EAP_REQUEST = 0xe002, - I2400M_MT_REPORT_EAP_RESTART = 0xe003, - I2400M_MT_REPORT_ALT_ACCEPT = 0xe004, - I2400M_MT_REPORT_KEY_REQUEST = 0xe005, -}; - - -/* - * Message Ack Status codes - * - * When a message is replied-to, this status is reported. - */ -enum i2400m_ms { - I2400M_MS_DONE_OK = 0, - I2400M_MS_DONE_IN_PROGRESS = 1, - I2400M_MS_INVALID_OP = 2, - I2400M_MS_BAD_STATE = 3, - I2400M_MS_ILLEGAL_VALUE = 4, - I2400M_MS_MISSING_PARAMS = 5, - I2400M_MS_VERSION_ERROR = 6, - I2400M_MS_ACCESSIBILITY_ERROR = 7, - I2400M_MS_BUSY = 8, - I2400M_MS_CORRUPTED_TLV = 9, - I2400M_MS_UNINITIALIZED = 10, - I2400M_MS_UNKNOWN_ERROR = 11, - I2400M_MS_PRODUCTION_ERROR = 12, - I2400M_MS_NO_RF = 13, - I2400M_MS_NOT_READY_FOR_POWERSAVE = 14, - I2400M_MS_THERMAL_CRITICAL = 15, - I2400M_MS_MAX -}; - - -/** - * i2400m_tlv - enumeration of the different types of TLVs - * - * TLVs stand for type-length-value and are the header for a payload - * composed of almost anything. Each payload has a type assigned - * and a length. - */ -enum i2400m_tlv { - I2400M_TLV_L4_MESSAGE_VERSIONS = 129, - I2400M_TLV_SYSTEM_STATE = 141, - I2400M_TLV_MEDIA_STATUS = 161, - I2400M_TLV_RF_OPERATION = 162, - I2400M_TLV_RF_STATUS = 163, - I2400M_TLV_DEVICE_RESET_TYPE = 132, - I2400M_TLV_CONFIG_IDLE_PARAMETERS = 601, - I2400M_TLV_CONFIG_IDLE_TIMEOUT = 611, - I2400M_TLV_CONFIG_D2H_DATA_FORMAT = 614, - I2400M_TLV_CONFIG_DL_HOST_REORDER = 615, -}; - - -struct i2400m_tlv_hdr { - __le16 type; - __le16 length; /* payload's */ - __u8 pl[0]; -} __attribute__((packed)); - - -struct i2400m_l3l4_hdr { - __le16 type; - __le16 length; /* payload's */ - __le16 version; - __le16 resv1; - __le16 status; - __le16 resv2; - struct i2400m_tlv_hdr pl[0]; -} __attribute__((packed)); - - -/** - * i2400m_system_state - different states of the device - */ -enum i2400m_system_state { - I2400M_SS_UNINITIALIZED = 1, - I2400M_SS_INIT, - I2400M_SS_READY, - I2400M_SS_SCAN, - I2400M_SS_STANDBY, - I2400M_SS_CONNECTING, - I2400M_SS_WIMAX_CONNECTED, - I2400M_SS_DATA_PATH_CONNECTED, - I2400M_SS_IDLE, - I2400M_SS_DISCONNECTING, - I2400M_SS_OUT_OF_ZONE, - I2400M_SS_SLEEPACTIVE, - I2400M_SS_PRODUCTION, - I2400M_SS_CONFIG, - I2400M_SS_RF_OFF, - I2400M_SS_RF_SHUTDOWN, - I2400M_SS_DEVICE_DISCONNECT, - I2400M_SS_MAX, -}; - - -/** - * i2400m_tlv_system_state - report on the state of the system - * - * @state: see enum i2400m_system_state - */ -struct i2400m_tlv_system_state { - struct i2400m_tlv_hdr hdr; - __le32 state; -} __attribute__((packed)); - - -struct i2400m_tlv_l4_message_versions { - struct i2400m_tlv_hdr hdr; - __le16 major; - __le16 minor; - __le16 branch; - __le16 reserved; -} __attribute__((packed)); - - -struct i2400m_tlv_detailed_device_info { - struct i2400m_tlv_hdr hdr; - __u8 reserved1[400]; - __u8 mac_address[ETH_ALEN]; - __u8 reserved2[2]; -} __attribute__((packed)); - - -enum i2400m_rf_switch_status { - I2400M_RF_SWITCH_ON = 1, - I2400M_RF_SWITCH_OFF = 2, -}; - -struct i2400m_tlv_rf_switches_status { - struct i2400m_tlv_hdr hdr; - __u8 sw_rf_switch; /* 1 ON, 2 OFF */ - __u8 hw_rf_switch; /* 1 ON, 2 OFF */ - __u8 reserved[2]; -} __attribute__((packed)); - - -enum { - i2400m_rf_operation_on = 1, - i2400m_rf_operation_off = 2 -}; - -struct i2400m_tlv_rf_operation { - struct i2400m_tlv_hdr hdr; - __le32 status; /* 1 ON, 2 OFF */ -} __attribute__((packed)); - - -enum i2400m_tlv_reset_type { - I2400M_RESET_TYPE_COLD = 1, - I2400M_RESET_TYPE_WARM -}; - -struct i2400m_tlv_device_reset_type { - struct i2400m_tlv_hdr hdr; - __le32 reset_type; -} __attribute__((packed)); - - -struct i2400m_tlv_config_idle_parameters { - struct i2400m_tlv_hdr hdr; - __le32 idle_timeout; /* 100 to 300000 ms [5min], 100 increments - * 0 disabled */ - __le32 idle_paging_interval; /* frames */ -} __attribute__((packed)); - - -enum i2400m_media_status { - I2400M_MEDIA_STATUS_LINK_UP = 1, - I2400M_MEDIA_STATUS_LINK_DOWN, - I2400M_MEDIA_STATUS_LINK_RENEW, -}; - -struct i2400m_tlv_media_status { - struct i2400m_tlv_hdr hdr; - __le32 media_status; -} __attribute__((packed)); - - -/* New in v1.4 */ -struct i2400m_tlv_config_idle_timeout { - struct i2400m_tlv_hdr hdr; - __le32 timeout; /* 100 to 300000 ms [5min], 100 increments - * 0 disabled */ -} __attribute__((packed)); - -/* New in v1.4 -- for backward compat, will be removed */ -struct i2400m_tlv_config_d2h_data_format { - struct i2400m_tlv_hdr hdr; - __u8 format; /* 0 old format, 1 enhanced */ - __u8 reserved[3]; -} __attribute__((packed)); - -/* New in v1.4 */ -struct i2400m_tlv_config_dl_host_reorder { - struct i2400m_tlv_hdr hdr; - __u8 reorder; /* 0 disabled, 1 enabled */ - __u8 reserved[3]; -} __attribute__((packed)); - - -#endif /* #ifndef __LINUX__WIMAX__I2400M_H__ */ -- cgit v1.3-15-g9ac1 From fbaedb4129838252570410c65abb2036b5505cbd Mon Sep 17 00:00:00 2001 From: Henrik Bjoernlund Date: Tue, 27 Oct 2020 10:02:44 +0000 Subject: bridge: uapi: cfm: Added EtherType used by the CFM protocol. This EtherType is used by all CFM protocal frames transmitted according to 802.1Q section 12.14. Signed-off-by: Henrik Bjoernlund Reviewed-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index d6de2b167448..a0b637911d3c 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -99,6 +99,7 @@ #define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */ #define ETH_P_NCSI 0x88F8 /* NCSI protocol */ #define ETH_P_PRP 0x88FB /* IEC 62439-3 PRP/HSRv0 */ +#define ETH_P_CFM 0x8902 /* Connectivity Fault Management */ #define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */ #define ETH_P_IBOE 0x8915 /* Infiniband over Ethernet */ #define ETH_P_TDLS 0x890D /* TDLS */ -- cgit v1.3-15-g9ac1 From 86a14b79e1d0fa023f82d7c2dde888fa64af2c65 Mon Sep 17 00:00:00 2001 From: Henrik Bjoernlund Date: Tue, 27 Oct 2020 10:02:45 +0000 Subject: bridge: cfm: Kernel space implementation of CFM. MEP create/delete. This is the first commit of the implementation of the CFM protocol according to 802.1Q section 12.14. It contains MEP instance create, delete and configuration. Connectivity Fault Management (CFM) comprises capabilities for detecting, verifying, and isolating connectivity failures in Virtual Bridged Networks. These capabilities can be used in networks operated by multiple independent organizations, each with restricted management access to each others equipment. CFM functions are partitioned as follows: - Path discovery - Fault detection - Fault verification and isolation - Fault notification - Fault recovery Interface consists of these functions: br_cfm_mep_create() br_cfm_mep_delete() br_cfm_mep_config_set() br_cfm_cc_config_set() br_cfm_cc_peer_mep_add() br_cfm_cc_peer_mep_remove() A MEP instance is created by br_cfm_mep_create() -It is the Maintenance association End Point described in 802.1Q section 19.2. -It is created on a specific level (1-7) and is assuring that no CFM frames are passing through this MEP on lower levels. -It initiates and validates CFM frames on its level. -It can only exist on a port that is related to a bridge. -Attributes given cannot be changed until the instance is deleted. A MEP instance can be deleted by br_cfm_mep_delete(). A created MEP instance has attributes that can be configured by br_cfm_mep_config_set(). A MEP Continuity Check feature can be configured by br_cfm_cc_config_set() The Continuity Check Receiver state machine can be enabled and disabled. According to 802.1Q section 19.2.8 A MEP can have Peer MEPs added and removed by br_cfm_cc_peer_mep_add() and br_cfm_cc_peer_mep_remove() The Continuity Check feature can maintain connectivity status on each added Peer MEP. Signed-off-by: Henrik Bjoernlund Reviewed-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/cfm_bridge.h | 23 ++++ net/bridge/Makefile | 2 + net/bridge/br_cfm.c | 260 ++++++++++++++++++++++++++++++++++++++++ net/bridge/br_if.c | 1 + net/bridge/br_private.h | 10 ++ net/bridge/br_private_cfm.h | 61 ++++++++++ 6 files changed, 357 insertions(+) create mode 100644 include/uapi/linux/cfm_bridge.h create mode 100644 net/bridge/br_cfm.c create mode 100644 net/bridge/br_private_cfm.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cfm_bridge.h b/include/uapi/linux/cfm_bridge.h new file mode 100644 index 000000000000..a262a8c0e085 --- /dev/null +++ b/include/uapi/linux/cfm_bridge.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_CFM_BRIDGE_H_ +#define _UAPI_LINUX_CFM_BRIDGE_H_ + +#include +#include + +#define CFM_MAID_LENGTH 48 + +/* MEP domain */ +enum br_cfm_domain { + BR_CFM_PORT, + BR_CFM_VLAN, +}; + +/* MEP direction */ +enum br_cfm_mep_direction { + BR_CFM_MEP_DIRECTION_DOWN, + BR_CFM_MEP_DIRECTION_UP, +}; + +#endif diff --git a/net/bridge/Makefile b/net/bridge/Makefile index ccb394236fbd..ddc0a9192348 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -27,3 +27,5 @@ bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o obj-$(CONFIG_NETFILTER) += netfilter/ bridge-$(CONFIG_BRIDGE_MRP) += br_mrp_switchdev.o br_mrp.o br_mrp_netlink.o + +bridge-$(CONFIG_BRIDGE_CFM) += br_cfm.o diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c new file mode 100644 index 000000000000..42f35109681a --- /dev/null +++ b/net/bridge/br_cfm.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include +#include "br_private_cfm.h" + +static struct br_cfm_mep *br_mep_find(struct net_bridge *br, u32 instance) +{ + struct br_cfm_mep *mep; + + hlist_for_each_entry(mep, &br->mep_list, head) + if (mep->instance == instance) + return mep; + + return NULL; +} + +static struct br_cfm_mep *br_mep_find_ifindex(struct net_bridge *br, + u32 ifindex) +{ + struct br_cfm_mep *mep; + + hlist_for_each_entry_rcu(mep, &br->mep_list, head, + lockdep_rtnl_is_held()) + if (mep->create.ifindex == ifindex) + return mep; + + return NULL; +} + +static struct br_cfm_peer_mep *br_peer_mep_find(struct br_cfm_mep *mep, + u32 mepid) +{ + struct br_cfm_peer_mep *peer_mep; + + hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head, + lockdep_rtnl_is_held()) + if (peer_mep->mepid == mepid) + return peer_mep; + + return NULL; +} + +static struct net_bridge_port *br_mep_get_port(struct net_bridge *br, + u32 ifindex) +{ + struct net_bridge_port *port; + + list_for_each_entry(port, &br->port_list, list) + if (port->dev->ifindex == ifindex) + return port; + + return NULL; +} + +int br_cfm_mep_create(struct net_bridge *br, + const u32 instance, + struct br_cfm_mep_create *const create, + struct netlink_ext_ack *extack) +{ + struct net_bridge_port *p; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + if (create->domain == BR_CFM_VLAN) { + NL_SET_ERR_MSG_MOD(extack, + "VLAN domain not supported"); + return -EINVAL; + } + if (create->domain != BR_CFM_PORT) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid domain value"); + return -EINVAL; + } + if (create->direction == BR_CFM_MEP_DIRECTION_UP) { + NL_SET_ERR_MSG_MOD(extack, + "Up-MEP not supported"); + return -EINVAL; + } + if (create->direction != BR_CFM_MEP_DIRECTION_DOWN) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid direction value"); + return -EINVAL; + } + p = br_mep_get_port(br, create->ifindex); + if (!p) { + NL_SET_ERR_MSG_MOD(extack, + "Port is not related to bridge"); + return -EINVAL; + } + mep = br_mep_find(br, instance); + if (mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance already exists"); + return -EEXIST; + } + + /* In PORT domain only one instance can be created per port */ + if (create->domain == BR_CFM_PORT) { + mep = br_mep_find_ifindex(br, create->ifindex); + if (mep) { + NL_SET_ERR_MSG_MOD(extack, + "Only one Port MEP on a port allowed"); + return -EINVAL; + } + } + + mep = kzalloc(sizeof(*mep), GFP_KERNEL); + if (!mep) + return -ENOMEM; + + mep->create = *create; + mep->instance = instance; + rcu_assign_pointer(mep->b_port, p); + + INIT_HLIST_HEAD(&mep->peer_mep_list); + + hlist_add_tail_rcu(&mep->head, &br->mep_list); + + return 0; +} + +static void mep_delete_implementation(struct net_bridge *br, + struct br_cfm_mep *mep) +{ + struct br_cfm_peer_mep *peer_mep; + struct hlist_node *n_store; + + ASSERT_RTNL(); + + /* Empty and free peer MEP list */ + hlist_for_each_entry_safe(peer_mep, n_store, &mep->peer_mep_list, head) { + hlist_del_rcu(&peer_mep->head); + kfree_rcu(peer_mep, rcu); + } + + RCU_INIT_POINTER(mep->b_port, NULL); + hlist_del_rcu(&mep->head); + kfree_rcu(mep, rcu); +} + +int br_cfm_mep_delete(struct net_bridge *br, + const u32 instance, + struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + mep_delete_implementation(br, mep); + + return 0; +} + +int br_cfm_mep_config_set(struct net_bridge *br, + const u32 instance, + const struct br_cfm_mep_config *const config, + struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + mep->config = *config; + + return 0; +} + +int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance, + u32 mepid, + struct netlink_ext_ack *extack) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + peer_mep = br_peer_mep_find(mep, mepid); + if (peer_mep) { + NL_SET_ERR_MSG_MOD(extack, + "Peer MEP-ID already exists"); + return -EEXIST; + } + + peer_mep = kzalloc(sizeof(*peer_mep), GFP_KERNEL); + if (!peer_mep) + return -ENOMEM; + + peer_mep->mepid = mepid; + peer_mep->mep = mep; + + hlist_add_tail_rcu(&peer_mep->head, &mep->peer_mep_list); + + return 0; +} + +int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance, + u32 mepid, + struct netlink_ext_ack *extack) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + peer_mep = br_peer_mep_find(mep, mepid); + if (!peer_mep) { + NL_SET_ERR_MSG_MOD(extack, + "Peer MEP-ID does not exists"); + return -ENOENT; + } + + hlist_del_rcu(&peer_mep->head); + kfree_rcu(peer_mep, rcu); + + return 0; +} + +/* Deletes the CFM instances on a specific bridge port + */ +void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *port) +{ + struct hlist_node *n_store; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + hlist_for_each_entry_safe(mep, n_store, &br->mep_list, head) + if (mep->create.ifindex == port->dev->ifindex) + mep_delete_implementation(br, mep); +} diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index a0e9a7937412..f7d2f472ae24 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -334,6 +334,7 @@ static void del_nbp(struct net_bridge_port *p) spin_unlock_bh(&br->lock); br_mrp_port_del(br, p); + br_cfm_port_del(br, p); br_ifinfo_notify(RTM_DELLINK, NULL, p); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 90ead48fa762..f7c41380de4d 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1459,6 +1459,16 @@ static inline int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br) #endif +/* br_mrp.c */ +#if IS_ENABLED(CONFIG_BRIDGE_CFM) +void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p); +#else +static inline void br_cfm_port_del(struct net_bridge *br, + struct net_bridge_port *p) +{ +} +#endif + /* br_netlink.c */ extern struct rtnl_link_ops br_link_ops; int br_netlink_init(void); diff --git a/net/bridge/br_private_cfm.h b/net/bridge/br_private_cfm.h new file mode 100644 index 000000000000..40fe982added --- /dev/null +++ b/net/bridge/br_private_cfm.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _BR_PRIVATE_CFM_H_ +#define _BR_PRIVATE_CFM_H_ + +#include "br_private.h" +#include + +struct br_cfm_mep_create { + enum br_cfm_domain domain; /* Domain for this MEP */ + enum br_cfm_mep_direction direction; /* Up or Down MEP direction */ + u32 ifindex; /* Residence port */ +}; + +int br_cfm_mep_create(struct net_bridge *br, + const u32 instance, + struct br_cfm_mep_create *const create, + struct netlink_ext_ack *extack); + +int br_cfm_mep_delete(struct net_bridge *br, + const u32 instance, + struct netlink_ext_ack *extack); + +struct br_cfm_mep_config { + u32 mdlevel; + u32 mepid; /* MEPID for this MEP */ + struct mac_addr unicast_mac; /* The MEP unicast MAC */ +}; + +int br_cfm_mep_config_set(struct net_bridge *br, + const u32 instance, + const struct br_cfm_mep_config *const config, + struct netlink_ext_ack *extack); + +int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance, + u32 peer_mep_id, + struct netlink_ext_ack *extack); +int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance, + u32 peer_mep_id, + struct netlink_ext_ack *extack); + +struct br_cfm_mep { + /* list header of MEP instances */ + struct hlist_node head; + u32 instance; + struct br_cfm_mep_create create; + struct br_cfm_mep_config config; + /* List of multiple peer MEPs */ + struct hlist_head peer_mep_list; + struct net_bridge_port __rcu *b_port; + struct rcu_head rcu; +}; + +struct br_cfm_peer_mep { + struct hlist_node head; + struct br_cfm_mep *mep; + u32 mepid; + struct rcu_head rcu; +}; + +#endif /* _BR_PRIVATE_CFM_H_ */ -- cgit v1.3-15-g9ac1 From a806ad8ee2aa7826b279c3f92c67956eb101ae42 Mon Sep 17 00:00:00 2001 From: Henrik Bjoernlund Date: Tue, 27 Oct 2020 10:02:46 +0000 Subject: bridge: cfm: Kernel space implementation of CFM. CCM frame TX added. This is the second commit of the implementation of the CFM protocol according to 802.1Q section 12.14. Functionality is extended with CCM frame transmission. Interface is extended with these functions: br_cfm_cc_rdi_set() br_cfm_cc_ccm_tx() br_cfm_cc_config_set() A MEP Continuity Check feature can be configured by br_cfm_cc_config_set() The Continuity Check parameters can be configured to be used when transmitting CCM. A MEP can be configured to start or stop transmission of CCM frames by br_cfm_cc_ccm_tx() The CCM will be transmitted for a selected period in seconds. Must call this function before timeout to keep transmission alive. A MEP transmitting CCM can be configured with inserted RDI in PDU by br_cfm_cc_rdi_set() Signed-off-by: Henrik Bjoernlund Reviewed-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/cfm_bridge.h | 39 +++++- net/bridge/br_cfm.c | 285 ++++++++++++++++++++++++++++++++++++++++ net/bridge/br_private_cfm.h | 54 ++++++++ 3 files changed, 377 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cfm_bridge.h b/include/uapi/linux/cfm_bridge.h index a262a8c0e085..84a3817da90b 100644 --- a/include/uapi/linux/cfm_bridge.h +++ b/include/uapi/linux/cfm_bridge.h @@ -6,7 +6,32 @@ #include #include -#define CFM_MAID_LENGTH 48 +#define ETHER_HEADER_LENGTH (6+6+4+2) +#define CFM_MAID_LENGTH 48 +#define CFM_CCM_PDU_LENGTH 75 +#define CFM_PORT_STATUS_TLV_LENGTH 4 +#define CFM_IF_STATUS_TLV_LENGTH 4 +#define CFM_IF_STATUS_TLV_TYPE 4 +#define CFM_PORT_STATUS_TLV_TYPE 2 +#define CFM_ENDE_TLV_TYPE 0 +#define CFM_CCM_MAX_FRAME_LENGTH (ETHER_HEADER_LENGTH+\ + CFM_CCM_PDU_LENGTH+\ + CFM_PORT_STATUS_TLV_LENGTH+\ + CFM_IF_STATUS_TLV_LENGTH) +#define CFM_FRAME_PRIO 7 +#define CFM_CCM_TLV_OFFSET 70 +#define CFM_CCM_ITU_RESERVED_SIZE 16 + +struct br_cfm_common_hdr { + __u8 mdlevel_version; + __u8 opcode; + __u8 flags; + __u8 tlv_offset; +}; + +enum br_cfm_opcodes { + BR_CFM_OPCODE_CCM = 0x1, +}; /* MEP domain */ enum br_cfm_domain { @@ -20,4 +45,16 @@ enum br_cfm_mep_direction { BR_CFM_MEP_DIRECTION_UP, }; +/* CCM interval supported. */ +enum br_cfm_ccm_interval { + BR_CFM_CCM_INTERVAL_NONE, + BR_CFM_CCM_INTERVAL_3_3_MS, + BR_CFM_CCM_INTERVAL_10_MS, + BR_CFM_CCM_INTERVAL_100_MS, + BR_CFM_CCM_INTERVAL_1_SEC, + BR_CFM_CCM_INTERVAL_10_SEC, + BR_CFM_CCM_INTERVAL_1_MIN, + BR_CFM_CCM_INTERVAL_10_MIN, +}; + #endif diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c index 42f35109681a..382e003f5b92 100644 --- a/net/bridge/br_cfm.c +++ b/net/bridge/br_cfm.c @@ -53,6 +53,185 @@ static struct net_bridge_port *br_mep_get_port(struct net_bridge *br, return NULL; } +/* Calculate the CCM interval in us. */ +static u32 interval_to_us(enum br_cfm_ccm_interval interval) +{ + switch (interval) { + case BR_CFM_CCM_INTERVAL_NONE: + return 0; + case BR_CFM_CCM_INTERVAL_3_3_MS: + return 3300; + case BR_CFM_CCM_INTERVAL_10_MS: + return 10 * 1000; + case BR_CFM_CCM_INTERVAL_100_MS: + return 100 * 1000; + case BR_CFM_CCM_INTERVAL_1_SEC: + return 1000 * 1000; + case BR_CFM_CCM_INTERVAL_10_SEC: + return 10 * 1000 * 1000; + case BR_CFM_CCM_INTERVAL_1_MIN: + return 60 * 1000 * 1000; + case BR_CFM_CCM_INTERVAL_10_MIN: + return 10 * 60 * 1000 * 1000; + } + return 0; +} + +/* Convert the interface interval to CCM PDU value. */ +static u32 interval_to_pdu(enum br_cfm_ccm_interval interval) +{ + switch (interval) { + case BR_CFM_CCM_INTERVAL_NONE: + return 0; + case BR_CFM_CCM_INTERVAL_3_3_MS: + return 1; + case BR_CFM_CCM_INTERVAL_10_MS: + return 2; + case BR_CFM_CCM_INTERVAL_100_MS: + return 3; + case BR_CFM_CCM_INTERVAL_1_SEC: + return 4; + case BR_CFM_CCM_INTERVAL_10_SEC: + return 5; + case BR_CFM_CCM_INTERVAL_1_MIN: + return 6; + case BR_CFM_CCM_INTERVAL_10_MIN: + return 7; + } + return 0; +} + +static struct sk_buff *ccm_frame_build(struct br_cfm_mep *mep, + const struct br_cfm_cc_ccm_tx_info *const tx_info) + +{ + struct br_cfm_common_hdr *common_hdr; + struct net_bridge_port *b_port; + struct br_cfm_maid *maid; + u8 *itu_reserved, *e_tlv; + struct ethhdr *eth_hdr; + struct sk_buff *skb; + __be32 *status_tlv; + __be32 *snumber; + __be16 *mepid; + + skb = dev_alloc_skb(CFM_CCM_MAX_FRAME_LENGTH); + if (!skb) + return NULL; + + rcu_read_lock(); + b_port = rcu_dereference(mep->b_port); + if (!b_port) { + kfree_skb(skb); + rcu_read_unlock(); + return NULL; + } + skb->dev = b_port->dev; + rcu_read_unlock(); + /* The device cannot be deleted until the work_queue functions has + * completed. This function is called from ccm_tx_work_expired() + * that is a work_queue functions. + */ + + skb->protocol = htons(ETH_P_CFM); + skb->priority = CFM_FRAME_PRIO; + + /* Ethernet header */ + eth_hdr = skb_put(skb, sizeof(*eth_hdr)); + ether_addr_copy(eth_hdr->h_dest, tx_info->dmac.addr); + ether_addr_copy(eth_hdr->h_source, mep->config.unicast_mac.addr); + eth_hdr->h_proto = htons(ETH_P_CFM); + + /* Common CFM Header */ + common_hdr = skb_put(skb, sizeof(*common_hdr)); + common_hdr->mdlevel_version = mep->config.mdlevel << 5; + common_hdr->opcode = BR_CFM_OPCODE_CCM; + common_hdr->flags = (mep->rdi << 7) | + interval_to_pdu(mep->cc_config.exp_interval); + common_hdr->tlv_offset = CFM_CCM_TLV_OFFSET; + + /* Sequence number */ + snumber = skb_put(skb, sizeof(*snumber)); + if (tx_info->seq_no_update) { + *snumber = cpu_to_be32(mep->ccm_tx_snumber); + mep->ccm_tx_snumber += 1; + } else { + *snumber = 0; + } + + mepid = skb_put(skb, sizeof(*mepid)); + *mepid = cpu_to_be16((u16)mep->config.mepid); + + maid = skb_put(skb, sizeof(*maid)); + memcpy(maid->data, mep->cc_config.exp_maid.data, sizeof(maid->data)); + + /* ITU reserved (CFM_CCM_ITU_RESERVED_SIZE octets) */ + itu_reserved = skb_put(skb, CFM_CCM_ITU_RESERVED_SIZE); + memset(itu_reserved, 0, CFM_CCM_ITU_RESERVED_SIZE); + + /* Generel CFM TLV format: + * TLV type: one byte + * TLV value length: two bytes + * TLV value: 'TLV value length' bytes + */ + + /* Port status TLV. The value length is 1. Total of 4 bytes. */ + if (tx_info->port_tlv) { + status_tlv = skb_put(skb, sizeof(*status_tlv)); + *status_tlv = cpu_to_be32((CFM_PORT_STATUS_TLV_TYPE << 24) | + (1 << 8) | /* Value length */ + (tx_info->port_tlv_value & 0xFF)); + } + + /* Interface status TLV. The value length is 1. Total of 4 bytes. */ + if (tx_info->if_tlv) { + status_tlv = skb_put(skb, sizeof(*status_tlv)); + *status_tlv = cpu_to_be32((CFM_IF_STATUS_TLV_TYPE << 24) | + (1 << 8) | /* Value length */ + (tx_info->if_tlv_value & 0xFF)); + } + + /* End TLV */ + e_tlv = skb_put(skb, sizeof(*e_tlv)); + *e_tlv = CFM_ENDE_TLV_TYPE; + + return skb; +} + +static void ccm_frame_tx(struct sk_buff *skb) +{ + skb_reset_network_header(skb); + dev_queue_xmit(skb); +} + +/* This function is called with the configured CC 'expected_interval' + * in order to drive CCM transmission when enabled. + */ +static void ccm_tx_work_expired(struct work_struct *work) +{ + struct delayed_work *del_work; + struct br_cfm_mep *mep; + struct sk_buff *skb; + u32 interval_us; + + del_work = to_delayed_work(work); + mep = container_of(del_work, struct br_cfm_mep, ccm_tx_dwork); + + if (time_before_eq(mep->ccm_tx_end, jiffies)) { + /* Transmission period has ended */ + mep->cc_ccm_tx_info.period = 0; + return; + } + + skb = ccm_frame_build(mep, &mep->cc_ccm_tx_info); + if (skb) + ccm_frame_tx(skb); + + interval_us = interval_to_us(mep->cc_config.exp_interval); + queue_delayed_work(system_wq, &mep->ccm_tx_dwork, + usecs_to_jiffies(interval_us)); +} + int br_cfm_mep_create(struct net_bridge *br, const u32 instance, struct br_cfm_mep_create *const create, @@ -115,6 +294,7 @@ int br_cfm_mep_create(struct net_bridge *br, rcu_assign_pointer(mep->b_port, p); INIT_HLIST_HEAD(&mep->peer_mep_list); + INIT_DELAYED_WORK(&mep->ccm_tx_dwork, ccm_tx_work_expired); hlist_add_tail_rcu(&mep->head, &br->mep_list); @@ -135,6 +315,8 @@ static void mep_delete_implementation(struct net_bridge *br, kfree_rcu(peer_mep, rcu); } + cancel_delayed_work_sync(&mep->ccm_tx_dwork); + RCU_INIT_POINTER(mep->b_port, NULL); hlist_del_rcu(&mep->head); kfree_rcu(mep, rcu); @@ -181,6 +363,32 @@ int br_cfm_mep_config_set(struct net_bridge *br, return 0; } +int br_cfm_cc_config_set(struct net_bridge *br, + const u32 instance, + const struct br_cfm_cc_config *const config, + struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + /* Check for no change in configuration */ + if (memcmp(config, &mep->cc_config, sizeof(*config)) == 0) + return 0; + + mep->cc_config = *config; + mep->ccm_tx_snumber = 1; + + return 0; +} + int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance, u32 mepid, struct netlink_ext_ack *extack) @@ -245,6 +453,83 @@ int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance, return 0; } +int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance, + const bool rdi, struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + mep->rdi = rdi; + + return 0; +} + +int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance, + const struct br_cfm_cc_ccm_tx_info *const tx_info, + struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + if (memcmp(tx_info, &mep->cc_ccm_tx_info, sizeof(*tx_info)) == 0) { + /* No change in tx_info. */ + if (mep->cc_ccm_tx_info.period == 0) + /* Transmission is not enabled - just return */ + return 0; + + /* Transmission is ongoing, the end time is recalculated */ + mep->ccm_tx_end = jiffies + + usecs_to_jiffies(tx_info->period * 1000000); + return 0; + } + + if (tx_info->period == 0 && mep->cc_ccm_tx_info.period == 0) + /* Some change in info and transmission is not ongoing */ + goto save; + + if (tx_info->period != 0 && mep->cc_ccm_tx_info.period != 0) { + /* Some change in info and transmission is ongoing + * The end time is recalculated + */ + mep->ccm_tx_end = jiffies + + usecs_to_jiffies(tx_info->period * 1000000); + + goto save; + } + + if (tx_info->period == 0 && mep->cc_ccm_tx_info.period != 0) { + cancel_delayed_work_sync(&mep->ccm_tx_dwork); + goto save; + } + + /* Start delayed work to transmit CCM frames. It is done with zero delay + * to send first frame immediately + */ + mep->ccm_tx_end = jiffies + usecs_to_jiffies(tx_info->period * 1000000); + queue_delayed_work(system_wq, &mep->ccm_tx_dwork, 0); + +save: + mep->cc_ccm_tx_info = *tx_info; + + return 0; +} + /* Deletes the CFM instances on a specific bridge port */ void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *port) diff --git a/net/bridge/br_private_cfm.h b/net/bridge/br_private_cfm.h index 40fe982added..8d1b449acfbf 100644 --- a/net/bridge/br_private_cfm.h +++ b/net/bridge/br_private_cfm.h @@ -32,6 +32,24 @@ int br_cfm_mep_config_set(struct net_bridge *br, const struct br_cfm_mep_config *const config, struct netlink_ext_ack *extack); +struct br_cfm_maid { + u8 data[CFM_MAID_LENGTH]; +}; + +struct br_cfm_cc_config { + /* Expected received CCM PDU MAID. */ + struct br_cfm_maid exp_maid; + + /* Expected received CCM PDU interval. */ + /* Transmitting CCM PDU interval when CCM tx is enabled. */ + enum br_cfm_ccm_interval exp_interval; +}; + +int br_cfm_cc_config_set(struct net_bridge *br, + const u32 instance, + const struct br_cfm_cc_config *const config, + struct netlink_ext_ack *extack); + int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance, u32 peer_mep_id, struct netlink_ext_ack *extack); @@ -39,15 +57,51 @@ int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance, u32 peer_mep_id, struct netlink_ext_ack *extack); +/* Transmitted CCM Remote Defect Indication status set. + * This RDI is inserted in transmitted CCM PDUs if CCM transmission is enabled. + * See br_cfm_cc_ccm_tx() with interval != BR_CFM_CCM_INTERVAL_NONE + */ +int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance, + const bool rdi, struct netlink_ext_ack *extack); + +/* OAM PDU Tx information */ +struct br_cfm_cc_ccm_tx_info { + struct mac_addr dmac; + /* The CCM will be transmitted for this period in seconds. + * Call br_cfm_cc_ccm_tx before timeout to keep transmission alive. + * When period is zero any ongoing transmission will be stopped. + */ + u32 period; + + bool seq_no_update; /* Update Tx CCM sequence number */ + bool if_tlv; /* Insert Interface Status TLV */ + u8 if_tlv_value; /* Interface Status TLV value */ + bool port_tlv; /* Insert Port Status TLV */ + u8 port_tlv_value; /* Port Status TLV value */ + /* Sender ID TLV ?? + * Organization-Specific TLV ?? + */ +}; + +int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance, + const struct br_cfm_cc_ccm_tx_info *const tx_info, + struct netlink_ext_ack *extack); + struct br_cfm_mep { /* list header of MEP instances */ struct hlist_node head; u32 instance; struct br_cfm_mep_create create; struct br_cfm_mep_config config; + struct br_cfm_cc_config cc_config; + struct br_cfm_cc_ccm_tx_info cc_ccm_tx_info; /* List of multiple peer MEPs */ struct hlist_head peer_mep_list; struct net_bridge_port __rcu *b_port; + unsigned long ccm_tx_end; + struct delayed_work ccm_tx_dwork; + u32 ccm_tx_snumber; + bool rdi; struct rcu_head rcu; }; -- cgit v1.3-15-g9ac1 From dc32cbb3dbd7da38c700d6e0fc6354df24920525 Mon Sep 17 00:00:00 2001 From: Henrik Bjoernlund Date: Tue, 27 Oct 2020 10:02:47 +0000 Subject: bridge: cfm: Kernel space implementation of CFM. CCM frame RX added. This is the third commit of the implementation of the CFM protocol according to 802.1Q section 12.14. Functionality is extended with CCM frame reception. The MEP instance now contains CCM based status information. Most important is the CCM defect status indicating if correct CCM frames are received with the expected interval. Signed-off-by: Henrik Bjoernlund Reviewed-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/cfm_bridge.h | 4 + net/bridge/br_cfm.c | 269 ++++++++++++++++++++++++++++++++++++++++ net/bridge/br_private_cfm.h | 32 +++++ 3 files changed, 305 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cfm_bridge.h b/include/uapi/linux/cfm_bridge.h index 84a3817da90b..3c1cbd1db2f5 100644 --- a/include/uapi/linux/cfm_bridge.h +++ b/include/uapi/linux/cfm_bridge.h @@ -20,6 +20,10 @@ CFM_IF_STATUS_TLV_LENGTH) #define CFM_FRAME_PRIO 7 #define CFM_CCM_TLV_OFFSET 70 +#define CFM_CCM_PDU_MAID_OFFSET 10 +#define CFM_CCM_PDU_MEPID_OFFSET 8 +#define CFM_CCM_PDU_SEQNR_OFFSET 4 +#define CFM_CCM_PDU_TLV_OFFSET 74 #define CFM_CCM_ITU_RESERVED_SIZE 16 struct br_cfm_common_hdr { diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c index 382e003f5b92..6331f731024f 100644 --- a/net/bridge/br_cfm.c +++ b/net/bridge/br_cfm.c @@ -101,6 +101,56 @@ static u32 interval_to_pdu(enum br_cfm_ccm_interval interval) return 0; } +/* Convert the CCM PDU value to interval on interface. */ +static u32 pdu_to_interval(u32 value) +{ + switch (value) { + case 0: + return BR_CFM_CCM_INTERVAL_NONE; + case 1: + return BR_CFM_CCM_INTERVAL_3_3_MS; + case 2: + return BR_CFM_CCM_INTERVAL_10_MS; + case 3: + return BR_CFM_CCM_INTERVAL_100_MS; + case 4: + return BR_CFM_CCM_INTERVAL_1_SEC; + case 5: + return BR_CFM_CCM_INTERVAL_10_SEC; + case 6: + return BR_CFM_CCM_INTERVAL_1_MIN; + case 7: + return BR_CFM_CCM_INTERVAL_10_MIN; + } + return BR_CFM_CCM_INTERVAL_NONE; +} + +static void ccm_rx_timer_start(struct br_cfm_peer_mep *peer_mep) +{ + u32 interval_us; + + interval_us = interval_to_us(peer_mep->mep->cc_config.exp_interval); + /* Function ccm_rx_dwork must be called with 1/4 + * of the configured CC 'expected_interval' + * in order to detect CCM defect after 3.25 interval. + */ + queue_delayed_work(system_wq, &peer_mep->ccm_rx_dwork, + usecs_to_jiffies(interval_us / 4)); +} + +static void cc_peer_enable(struct br_cfm_peer_mep *peer_mep) +{ + memset(&peer_mep->cc_status, 0, sizeof(peer_mep->cc_status)); + peer_mep->ccm_rx_count_miss = 0; + + ccm_rx_timer_start(peer_mep); +} + +static void cc_peer_disable(struct br_cfm_peer_mep *peer_mep) +{ + cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork); +} + static struct sk_buff *ccm_frame_build(struct br_cfm_mep *mep, const struct br_cfm_cc_ccm_tx_info *const tx_info) @@ -232,6 +282,200 @@ static void ccm_tx_work_expired(struct work_struct *work) usecs_to_jiffies(interval_us)); } +/* This function is called with 1/4 of the configured CC 'expected_interval' + * in order to detect CCM defect after 3.25 interval. + */ +static void ccm_rx_work_expired(struct work_struct *work) +{ + struct br_cfm_peer_mep *peer_mep; + struct delayed_work *del_work; + + del_work = to_delayed_work(work); + peer_mep = container_of(del_work, struct br_cfm_peer_mep, ccm_rx_dwork); + + /* After 13 counts (4 * 3,25) then 3.25 intervals are expired */ + if (peer_mep->ccm_rx_count_miss < 13) { + /* 3.25 intervals are NOT expired without CCM reception */ + peer_mep->ccm_rx_count_miss++; + + /* Start timer again */ + ccm_rx_timer_start(peer_mep); + } else { + /* 3.25 intervals are expired without CCM reception. + * CCM defect detected + */ + peer_mep->cc_status.ccm_defect = true; + } +} + +static u32 ccm_tlv_extract(struct sk_buff *skb, u32 index, + struct br_cfm_peer_mep *peer_mep) +{ + __be32 *s_tlv; + __be32 _s_tlv; + u32 h_s_tlv; + u8 *e_tlv; + u8 _e_tlv; + + e_tlv = skb_header_pointer(skb, index, sizeof(_e_tlv), &_e_tlv); + if (!e_tlv) + return 0; + + /* TLV is present - get the status TLV */ + s_tlv = skb_header_pointer(skb, + index, + sizeof(_s_tlv), &_s_tlv); + if (!s_tlv) + return 0; + + h_s_tlv = ntohl(*s_tlv); + if ((h_s_tlv >> 24) == CFM_IF_STATUS_TLV_TYPE) { + /* Interface status TLV */ + peer_mep->cc_status.tlv_seen = true; + peer_mep->cc_status.if_tlv_value = (h_s_tlv & 0xFF); + } + + if ((h_s_tlv >> 24) == CFM_PORT_STATUS_TLV_TYPE) { + /* Port status TLV */ + peer_mep->cc_status.tlv_seen = true; + peer_mep->cc_status.port_tlv_value = (h_s_tlv & 0xFF); + } + + /* The Sender ID TLV is not handled */ + /* The Organization-Specific TLV is not handled */ + + /* Return the length of this tlv. + * This is the length of the value field plus 3 bytes for size of type + * field and length field + */ + return ((h_s_tlv >> 8) & 0xFFFF) + 3; +} + +/* note: already called with rcu_read_lock */ +static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb) +{ + u32 mdlevel, interval, size, index, max; + const struct br_cfm_common_hdr *hdr; + struct br_cfm_peer_mep *peer_mep; + const struct br_cfm_maid *maid; + struct br_cfm_common_hdr _hdr; + struct br_cfm_maid _maid; + struct br_cfm_mep *mep; + struct net_bridge *br; + __be32 *snumber; + __be32 _snumber; + __be16 *mepid; + __be16 _mepid; + + if (port->state == BR_STATE_DISABLED) + return 0; + + hdr = skb_header_pointer(skb, 0, sizeof(_hdr), &_hdr); + if (!hdr) + return 1; + + br = port->br; + mep = br_mep_find_ifindex(br, port->dev->ifindex); + if (unlikely(!mep)) + /* No MEP on this port - must be forwarded */ + return 0; + + mdlevel = hdr->mdlevel_version >> 5; + if (mdlevel > mep->config.mdlevel) + /* The level is above this MEP level - must be forwarded */ + return 0; + + if ((hdr->mdlevel_version & 0x1F) != 0) { + /* Invalid version */ + mep->status.version_unexp_seen = true; + return 1; + } + + if (mdlevel < mep->config.mdlevel) { + /* The level is below this MEP level */ + mep->status.rx_level_low_seen = true; + return 1; + } + + if (hdr->opcode == BR_CFM_OPCODE_CCM) { + /* CCM PDU received. */ + /* MA ID is after common header + sequence number + MEP ID */ + maid = skb_header_pointer(skb, + CFM_CCM_PDU_MAID_OFFSET, + sizeof(_maid), &_maid); + if (!maid) + return 1; + if (memcmp(maid->data, mep->cc_config.exp_maid.data, + sizeof(maid->data))) + /* MA ID not as expected */ + return 1; + + /* MEP ID is after common header + sequence number */ + mepid = skb_header_pointer(skb, + CFM_CCM_PDU_MEPID_OFFSET, + sizeof(_mepid), &_mepid); + if (!mepid) + return 1; + peer_mep = br_peer_mep_find(mep, (u32)ntohs(*mepid)); + if (!peer_mep) + return 1; + + /* Interval is in common header flags */ + interval = hdr->flags & 0x07; + if (mep->cc_config.exp_interval != pdu_to_interval(interval)) + /* Interval not as expected */ + return 1; + + /* A valid CCM frame is received */ + if (peer_mep->cc_status.ccm_defect) { + peer_mep->cc_status.ccm_defect = false; + + /* Start CCM RX timer */ + ccm_rx_timer_start(peer_mep); + } + + peer_mep->cc_status.seen = true; + peer_mep->ccm_rx_count_miss = 0; + + /* RDI is in common header flags */ + peer_mep->cc_status.rdi = (hdr->flags & 0x80) ? true : false; + + /* Sequence number is after common header */ + snumber = skb_header_pointer(skb, + CFM_CCM_PDU_SEQNR_OFFSET, + sizeof(_snumber), &_snumber); + if (!snumber) + return 1; + if (ntohl(*snumber) != (mep->ccm_rx_snumber + 1)) + /* Unexpected sequence number */ + peer_mep->cc_status.seq_unexp_seen = true; + + mep->ccm_rx_snumber = ntohl(*snumber); + + /* TLV end is after common header + sequence number + MEP ID + + * MA ID + ITU reserved + */ + index = CFM_CCM_PDU_TLV_OFFSET; + max = 0; + do { /* Handle all TLVs */ + size = ccm_tlv_extract(skb, index, peer_mep); + index += size; + max += 1; + } while (size != 0 && max < 4); /* Max four TLVs possible */ + + return 1; + } + + mep->status.opcode_unexp_seen = true; + + return 1; +} + +static struct br_frame_type cfm_frame_type __read_mostly = { + .type = cpu_to_be16(ETH_P_CFM), + .frame_handler = br_cfm_frame_rx, +}; + int br_cfm_mep_create(struct net_bridge *br, const u32 instance, struct br_cfm_mep_create *const create, @@ -296,6 +540,9 @@ int br_cfm_mep_create(struct net_bridge *br, INIT_HLIST_HEAD(&mep->peer_mep_list); INIT_DELAYED_WORK(&mep->ccm_tx_dwork, ccm_tx_work_expired); + if (hlist_empty(&br->mep_list)) + br_add_frame(br, &cfm_frame_type); + hlist_add_tail_rcu(&mep->head, &br->mep_list); return 0; @@ -311,6 +558,7 @@ static void mep_delete_implementation(struct net_bridge *br, /* Empty and free peer MEP list */ hlist_for_each_entry_safe(peer_mep, n_store, &mep->peer_mep_list, head) { + cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork); hlist_del_rcu(&peer_mep->head); kfree_rcu(peer_mep, rcu); } @@ -320,6 +568,9 @@ static void mep_delete_implementation(struct net_bridge *br, RCU_INIT_POINTER(mep->b_port, NULL); hlist_del_rcu(&mep->head); kfree_rcu(mep, rcu); + + if (hlist_empty(&br->mep_list)) + br_del_frame(br, &cfm_frame_type); } int br_cfm_mep_delete(struct net_bridge *br, @@ -368,6 +619,7 @@ int br_cfm_cc_config_set(struct net_bridge *br, const struct br_cfm_cc_config *const config, struct netlink_ext_ack *extack) { + struct br_cfm_peer_mep *peer_mep; struct br_cfm_mep *mep; ASSERT_RTNL(); @@ -383,7 +635,18 @@ int br_cfm_cc_config_set(struct net_bridge *br, if (memcmp(config, &mep->cc_config, sizeof(*config)) == 0) return 0; + if (config->enable && !mep->cc_config.enable) + /* CC is enabled */ + hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head) + cc_peer_enable(peer_mep); + + if (!config->enable && mep->cc_config.enable) + /* CC is disabled */ + hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head) + cc_peer_disable(peer_mep); + mep->cc_config = *config; + mep->ccm_rx_snumber = 0; mep->ccm_tx_snumber = 1; return 0; @@ -418,6 +681,10 @@ int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance, peer_mep->mepid = mepid; peer_mep->mep = mep; + INIT_DELAYED_WORK(&peer_mep->ccm_rx_dwork, ccm_rx_work_expired); + + if (mep->cc_config.enable) + cc_peer_enable(peer_mep); hlist_add_tail_rcu(&peer_mep->head, &mep->peer_mep_list); @@ -447,6 +714,8 @@ int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance, return -ENOENT; } + cc_peer_disable(peer_mep); + hlist_del_rcu(&peer_mep->head); kfree_rcu(peer_mep, rcu); diff --git a/net/bridge/br_private_cfm.h b/net/bridge/br_private_cfm.h index 8d1b449acfbf..a43a5e7fa2c3 100644 --- a/net/bridge/br_private_cfm.h +++ b/net/bridge/br_private_cfm.h @@ -43,6 +43,8 @@ struct br_cfm_cc_config { /* Expected received CCM PDU interval. */ /* Transmitting CCM PDU interval when CCM tx is enabled. */ enum br_cfm_ccm_interval exp_interval; + + bool enable; /* Enable/disable CCM PDU handling */ }; int br_cfm_cc_config_set(struct net_bridge *br, @@ -87,6 +89,31 @@ int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance, const struct br_cfm_cc_ccm_tx_info *const tx_info, struct netlink_ext_ack *extack); +struct br_cfm_mep_status { + /* Indications that an OAM PDU has been seen. */ + bool opcode_unexp_seen; /* RX of OAM PDU with unexpected opcode */ + bool version_unexp_seen; /* RX of OAM PDU with unexpected version */ + bool rx_level_low_seen; /* Rx of OAM PDU with level low */ +}; + +struct br_cfm_cc_peer_status { + /* This CCM related status is based on the latest received CCM PDU. */ + u8 port_tlv_value; /* Port Status TLV value */ + u8 if_tlv_value; /* Interface Status TLV value */ + + /* CCM has not been received for 3.25 intervals */ + u8 ccm_defect:1; + + /* (RDI == 1) for last received CCM PDU */ + u8 rdi:1; + + /* Indications that a CCM PDU has been seen. */ + u8 seen:1; /* CCM PDU received */ + u8 tlv_seen:1; /* CCM PDU with TLV received */ + /* CCM PDU with unexpected sequence number received */ + u8 seq_unexp_seen:1; +}; + struct br_cfm_mep { /* list header of MEP instances */ struct hlist_node head; @@ -101,6 +128,8 @@ struct br_cfm_mep { unsigned long ccm_tx_end; struct delayed_work ccm_tx_dwork; u32 ccm_tx_snumber; + u32 ccm_rx_snumber; + struct br_cfm_mep_status status; bool rdi; struct rcu_head rcu; }; @@ -108,7 +137,10 @@ struct br_cfm_mep { struct br_cfm_peer_mep { struct hlist_node head; struct br_cfm_mep *mep; + struct delayed_work ccm_rx_dwork; u32 mepid; + struct br_cfm_cc_peer_status cc_status; + u32 ccm_rx_count_miss; struct rcu_head rcu; }; -- cgit v1.3-15-g9ac1 From 2be665c3940d367e0a2a8128eb4985ce323f99a3 Mon Sep 17 00:00:00 2001 From: Henrik Bjoernlund Date: Tue, 27 Oct 2020 10:02:48 +0000 Subject: bridge: cfm: Netlink SET configuration Interface. This is the implementation of CFM netlink configuration set information interface. Add new nested netlink attributes. These attributes are used by the user space to create/delete/configure CFM instances. SETLINK: IFLA_BRIDGE_CFM: Indicate that the following attributes are CFM. IFLA_BRIDGE_CFM_MEP_CREATE: This indicate that a MEP instance must be created. IFLA_BRIDGE_CFM_MEP_DELETE: This indicate that a MEP instance must be deleted. IFLA_BRIDGE_CFM_MEP_CONFIG: This indicate that a MEP instance must be configured. IFLA_BRIDGE_CFM_CC_CONFIG: This indicate that a MEP instance Continuity Check (CC) functionality must be configured. IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD: This indicate that a CC Peer MEP must be added. IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE: This indicate that a CC Peer MEP must be removed. IFLA_BRIDGE_CFM_CC_CCM_TX: This indicate that the CC transmitted CCM PDU must be configured. IFLA_BRIDGE_CFM_CC_RDI: This indicate that the CC transmitted CCM PDU RDI must be configured. CFM nested attribute has the following attributes in next level. SETLINK RTEXT_FILTER_CFM_CONFIG: IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE: The created MEP instance number. The type is u32. IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN: The created MEP domain. The type is u32 (br_cfm_domain). It must be BR_CFM_PORT. This means that CFM frames are transmitted and received directly on the port - untagged. Not in a VLAN. IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION: The created MEP direction. The type is u32 (br_cfm_mep_direction). It must be BR_CFM_MEP_DIRECTION_DOWN. This means that CFM frames are transmitted and received on the port. Not in the bridge. IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX: The created MEP residence port ifindex. The type is u32 (ifindex). IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE: The deleted MEP instance number. The type is u32. IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC: The configured MEP unicast MAC address. The type is 6*u8 (array). This is used as SMAC in all transmitted CFM frames. IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL: The configured MEP unicast MD level. The type is u32. It must be in the range 1-7. No CFM frames are passing through this MEP on lower levels. IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID: The configured MEP ID. The type is u32. It must be in the range 0-0x1FFF. This MEP ID is inserted in any transmitted CCM frame. IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE: The Continuity Check (CC) functionality is enabled or disabled. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL: The CC expected receive interval of CCM frames. The type is u32 (br_cfm_ccm_interval). This is also the transmission interval of CCM frames when enabled. IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID: The CC expected receive MAID in CCM frames. The type is CFM_MAID_LENGTH*u8. This is MAID is also inserted in transmitted CCM frames. IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_CC_PEER_MEPID: The CC Peer MEP ID added. The type is u32. When a Peer MEP ID is added and CC is enabled it is expected to receive CCM frames from that Peer MEP. IFLA_BRIDGE_CFM_CC_RDI_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_CC_RDI_RDI: The RDI that is inserted in transmitted CCM PDU. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC: The transmitted CCM frame destination MAC address. The type is 6*u8 (array). This is used as DMAC in all transmitted CFM frames. IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE: The transmitted CCM frame update (increment) of sequence number is enabled or disabled. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD: The period of time where CCM frame are transmitted. The type is u32. The time is given in seconds. SETLINK IFLA_BRIDGE_CFM_CC_CCM_TX must be done before timeout to keep transmission alive. When period is zero any ongoing CCM frame transmission will be stopped. IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV: The transmitted CCM frame update with Interface Status TLV is enabled or disabled. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE: The transmitted Interface Status TLV value field. The type is u8. IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV: The transmitted CCM frame update with Port Status TLV is enabled or disabled. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE: The transmitted Port Status TLV value field. The type is u8. Signed-off-by: Henrik Bjoernlund Reviewed-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 90 ++++++++ include/uapi/linux/rtnetlink.h | 1 + net/bridge/Makefile | 2 +- net/bridge/br_cfm.c | 5 + net/bridge/br_cfm_netlink.c | 453 +++++++++++++++++++++++++++++++++++++++++ net/bridge/br_netlink.c | 5 + net/bridge/br_private.h | 17 +- 7 files changed, 571 insertions(+), 2 deletions(-) create mode 100644 net/bridge/br_cfm_netlink.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 4c687686aa8f..94cc9444d749 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -121,6 +121,7 @@ enum { IFLA_BRIDGE_VLAN_INFO, IFLA_BRIDGE_VLAN_TUNNEL_INFO, IFLA_BRIDGE_MRP, + IFLA_BRIDGE_CFM, __IFLA_BRIDGE_MAX, }; #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1) @@ -328,6 +329,95 @@ struct br_mrp_start_in_test { __u16 in_id; }; +enum { + IFLA_BRIDGE_CFM_UNSPEC, + IFLA_BRIDGE_CFM_MEP_CREATE, + IFLA_BRIDGE_CFM_MEP_DELETE, + IFLA_BRIDGE_CFM_MEP_CONFIG, + IFLA_BRIDGE_CFM_CC_CONFIG, + IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD, + IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE, + IFLA_BRIDGE_CFM_CC_RDI, + IFLA_BRIDGE_CFM_CC_CCM_TX, + __IFLA_BRIDGE_CFM_MAX, +}; + +#define IFLA_BRIDGE_CFM_MAX (__IFLA_BRIDGE_CFM_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC, + IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE, + IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN, + IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION, + IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX, + __IFLA_BRIDGE_CFM_MEP_CREATE_MAX, +}; + +#define IFLA_BRIDGE_CFM_MEP_CREATE_MAX (__IFLA_BRIDGE_CFM_MEP_CREATE_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC, + IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE, + __IFLA_BRIDGE_CFM_MEP_DELETE_MAX, +}; + +#define IFLA_BRIDGE_CFM_MEP_DELETE_MAX (__IFLA_BRIDGE_CFM_MEP_DELETE_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC, + IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE, + IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC, + IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL, + IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID, + __IFLA_BRIDGE_CFM_MEP_CONFIG_MAX, +}; + +#define IFLA_BRIDGE_CFM_MEP_CONFIG_MAX (__IFLA_BRIDGE_CFM_MEP_CONFIG_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC, + IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE, + IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE, + IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL, + IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID, + __IFLA_BRIDGE_CFM_CC_CONFIG_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_CONFIG_MAX (__IFLA_BRIDGE_CFM_CC_CONFIG_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC, + IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE, + IFLA_BRIDGE_CFM_CC_PEER_MEPID, + __IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX (__IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_RDI_UNSPEC, + IFLA_BRIDGE_CFM_CC_RDI_INSTANCE, + IFLA_BRIDGE_CFM_CC_RDI_RDI, + __IFLA_BRIDGE_CFM_CC_RDI_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_RDI_MAX (__IFLA_BRIDGE_CFM_CC_RDI_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC, + IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE, + IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC, + IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE, + IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD, + IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV, + IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE, + IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV, + IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE, + __IFLA_BRIDGE_CFM_CC_CCM_TX_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_CCM_TX_MAX (__IFLA_BRIDGE_CFM_CC_CCM_TX_MAX - 1) + struct bridge_stp_xstats { __u64 transition_blk; __u64 transition_fwd; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 9b814c92de12..ffc9ca1f2bdb 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -779,6 +779,7 @@ enum { #define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2) #define RTEXT_FILTER_SKIP_STATS (1 << 3) #define RTEXT_FILTER_MRP (1 << 4) +#define RTEXT_FILTER_CFM_CONFIG (1 << 5) /* End of information exported to user level */ diff --git a/net/bridge/Makefile b/net/bridge/Makefile index ddc0a9192348..4702702a74d3 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -28,4 +28,4 @@ obj-$(CONFIG_NETFILTER) += netfilter/ bridge-$(CONFIG_BRIDGE_MRP) += br_mrp_switchdev.o br_mrp.o br_mrp_netlink.o -bridge-$(CONFIG_BRIDGE_CFM) += br_cfm.o +bridge-$(CONFIG_BRIDGE_CFM) += br_cfm.o br_cfm_netlink.o diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c index 6331f731024f..3912fedfd289 100644 --- a/net/bridge/br_cfm.c +++ b/net/bridge/br_cfm.c @@ -799,6 +799,11 @@ save: return 0; } +bool br_cfm_created(struct net_bridge *br) +{ + return !hlist_empty(&br->mep_list); +} + /* Deletes the CFM instances on a specific bridge port */ void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *port) diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c new file mode 100644 index 000000000000..c75f4c788eac --- /dev/null +++ b/net/bridge/br_cfm_netlink.c @@ -0,0 +1,453 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include + +#include "br_private.h" +#include "br_private_cfm.h" + +static const struct nla_policy +br_cfm_mep_create_policy[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1] = { + [IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +br_cfm_mep_delete_policy[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1] = { + [IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +br_cfm_mep_config_policy[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1] = { + [IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC] = NLA_POLICY_ETH_ADDR, + [IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL] = NLA_POLICY_MAX(NLA_U32, 7), + [IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID] = NLA_POLICY_MAX(NLA_U32, 0x1FFF), +}; + +static const struct nla_policy +br_cfm_cc_config_policy[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1] = { + [IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID] = { + .type = NLA_BINARY, .len = CFM_MAID_LENGTH }, +}; + +static const struct nla_policy +br_cfm_cc_peer_mep_policy[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1] = { + [IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_PEER_MEPID] = NLA_POLICY_MAX(NLA_U32, 0x1FFF), +}; + +static const struct nla_policy +br_cfm_cc_rdi_policy[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1] = { + [IFLA_BRIDGE_CFM_CC_RDI_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_CC_RDI_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_RDI_RDI] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +br_cfm_cc_ccm_tx_policy[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1] = { + [IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC] = NLA_POLICY_ETH_ADDR, + [IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE] = { .type = NLA_U8 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE] = { .type = NLA_U8 }, +}; + +static const struct nla_policy +br_cfm_policy[IFLA_BRIDGE_CFM_MAX + 1] = { + [IFLA_BRIDGE_CFM_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_MEP_CREATE] = + NLA_POLICY_NESTED(br_cfm_mep_create_policy), + [IFLA_BRIDGE_CFM_MEP_DELETE] = + NLA_POLICY_NESTED(br_cfm_mep_delete_policy), + [IFLA_BRIDGE_CFM_MEP_CONFIG] = + NLA_POLICY_NESTED(br_cfm_mep_config_policy), + [IFLA_BRIDGE_CFM_CC_CONFIG] = + NLA_POLICY_NESTED(br_cfm_cc_config_policy), + [IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD] = + NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy), + [IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE] = + NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy), + [IFLA_BRIDGE_CFM_CC_RDI] = + NLA_POLICY_NESTED(br_cfm_cc_rdi_policy), + [IFLA_BRIDGE_CFM_CC_CCM_TX] = + NLA_POLICY_NESTED(br_cfm_cc_ccm_tx_policy), +}; + +static int br_mep_create_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1]; + struct br_cfm_mep_create create; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CREATE_MAX, attr, + br_cfm_mep_create_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]) { + NL_SET_ERR_MSG_MOD(extack, "Missing DOMAIN attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]) { + NL_SET_ERR_MSG_MOD(extack, "Missing DIRECTION attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]) { + NL_SET_ERR_MSG_MOD(extack, "Missing IFINDEX attribute"); + return -EINVAL; + } + + memset(&create, 0, sizeof(create)); + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]); + create.domain = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]); + create.direction = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]); + create.ifindex = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]); + + return br_cfm_mep_create(br, instance, &create, extack); +} + +static int br_mep_delete_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1]; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_DELETE_MAX, attr, + br_cfm_mep_delete_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, + "Missing INSTANCE attribute"); + return -EINVAL; + } + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]); + + return br_cfm_mep_delete(br, instance, extack); +} + +static int br_mep_config_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1]; + struct br_cfm_mep_config config; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CONFIG_MAX, attr, + br_cfm_mep_config_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC]) { + NL_SET_ERR_MSG_MOD(extack, "Missing UNICAST_MAC attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]) { + NL_SET_ERR_MSG_MOD(extack, "Missing MDLEVEL attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing MEPID attribute"); + return -EINVAL; + } + + memset(&config, 0, sizeof(config)); + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]); + nla_memcpy(&config.unicast_mac.addr, + tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC], + sizeof(config.unicast_mac.addr)); + config.mdlevel = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]); + config.mepid = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]); + + return br_cfm_mep_config_set(br, instance, &config, extack); +} + +static int br_cc_config_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1]; + struct br_cfm_cc_config config; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CONFIG_MAX, attr, + br_cfm_cc_config_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing ENABLE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INTERVAL attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing MAID attribute"); + return -EINVAL; + } + + memset(&config, 0, sizeof(config)); + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]); + config.enable = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]); + config.exp_interval = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]); + nla_memcpy(&config.exp_maid.data, tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID], + sizeof(config.exp_maid.data)); + + return br_cfm_cc_config_set(br, instance, &config, extack); +} + +static int br_cc_peer_mep_add_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1]; + u32 instance, peer_mep_id; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr, + br_cfm_cc_peer_mep_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute"); + return -EINVAL; + } + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]); + peer_mep_id = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]); + + return br_cfm_cc_peer_mep_add(br, instance, peer_mep_id, extack); +} + +static int br_cc_peer_mep_remove_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1]; + u32 instance, peer_mep_id; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr, + br_cfm_cc_peer_mep_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute"); + return -EINVAL; + } + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]); + peer_mep_id = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]); + + return br_cfm_cc_peer_mep_remove(br, instance, peer_mep_id, extack); +} + +static int br_cc_rdi_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1]; + u32 instance, rdi; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_RDI_MAX, attr, + br_cfm_cc_rdi_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]) { + NL_SET_ERR_MSG_MOD(extack, "Missing RDI attribute"); + return -EINVAL; + } + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]); + rdi = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]); + + return br_cfm_cc_rdi_set(br, instance, rdi, extack); +} + +static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1]; + struct br_cfm_cc_ccm_tx_info tx_info; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CCM_TX_MAX, attr, + br_cfm_cc_ccm_tx_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC]) { + NL_SET_ERR_MSG_MOD(extack, "Missing DMAC attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing SEQ_NO_UPDATE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PERIOD attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]) { + NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV_VALUE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV_VALUE attribute"); + return -EINVAL; + } + + memset(&tx_info, 0, sizeof(tx_info)); + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]); + nla_memcpy(&tx_info.dmac.addr, + tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC], + sizeof(tx_info.dmac.addr)); + tx_info.seq_no_update = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]); + tx_info.period = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]); + tx_info.if_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]); + tx_info.if_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]); + tx_info.port_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]); + tx_info.port_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]); + + return br_cfm_cc_ccm_tx(br, instance, &tx_info, extack); +} + +int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, + struct nlattr *attr, int cmd, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_MAX + 1]; + int err; + + /* When this function is called for a port then the br pointer is + * invalid, therefor set the br to point correctly + */ + if (p) + br = p->br; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MAX, attr, + br_cfm_policy, extack); + if (err) + return err; + + if (tb[IFLA_BRIDGE_CFM_MEP_CREATE]) { + err = br_mep_create_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CREATE], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_MEP_DELETE]) { + err = br_mep_delete_parse(br, tb[IFLA_BRIDGE_CFM_MEP_DELETE], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_MEP_CONFIG]) { + err = br_mep_config_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CONFIG], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_CONFIG]) { + err = br_cc_config_parse(br, tb[IFLA_BRIDGE_CFM_CC_CONFIG], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD]) { + err = br_cc_peer_mep_add_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE]) { + err = br_cc_peer_mep_remove_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_RDI]) { + err = br_cc_rdi_parse(br, tb[IFLA_BRIDGE_CFM_CC_RDI], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_CCM_TX]) { + err = br_cc_ccm_tx_parse(br, tb[IFLA_BRIDGE_CFM_CC_CCM_TX], + extack); + if (err) + return err; + } + + return 0; +} diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 92d64abffa87..431ee2b06dc1 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -700,6 +700,11 @@ static int br_afspec(struct net_bridge *br, if (err) return err; break; + case IFLA_BRIDGE_CFM: + err = br_cfm_parse(br, p, attr, cmd, extack); + if (err) + return err; + break; } } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index f7c41380de4d..6a5db0553f19 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1459,10 +1459,25 @@ static inline int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br) #endif -/* br_mrp.c */ +/* br_cfm.c */ #if IS_ENABLED(CONFIG_BRIDGE_CFM) +int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, + struct nlattr *attr, int cmd, struct netlink_ext_ack *extack); +bool br_cfm_created(struct net_bridge *br); void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p); #else +static inline int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, + struct nlattr *attr, int cmd, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline bool br_cfm_created(struct net_bridge *br) +{ + return false; +} + static inline void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p) { -- cgit v1.3-15-g9ac1 From 5e312fc0e7fbd11716c0b976d83f4392522c4f83 Mon Sep 17 00:00:00 2001 From: Henrik Bjoernlund Date: Tue, 27 Oct 2020 10:02:49 +0000 Subject: bridge: cfm: Netlink GET configuration Interface. This is the implementation of CFM netlink configuration get information interface. Add new nested netlink attributes. These attributes are used by the user space to get configuration information. GETLINK: Request filter RTEXT_FILTER_CFM_CONFIG: Indicating that CFM configuration information must be delivered. IFLA_BRIDGE_CFM: Points to the CFM information. IFLA_BRIDGE_CFM_MEP_CREATE_INFO: This indicate that MEP instance create parameters are following. IFLA_BRIDGE_CFM_MEP_CONFIG_INFO: This indicate that MEP instance config parameters are following. IFLA_BRIDGE_CFM_CC_CONFIG_INFO: This indicate that MEP instance CC functionality parameters are following. IFLA_BRIDGE_CFM_CC_RDI_INFO: This indicate that CC transmitted CCM PDU RDI parameters are following. IFLA_BRIDGE_CFM_CC_CCM_TX_INFO: This indicate that CC transmitted CCM PDU parameters are following. IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO: This indicate that the added peer MEP IDs are following. CFM nested attribute has the following attributes in next level. GETLINK RTEXT_FILTER_CFM_CONFIG: IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE: The created MEP instance number. The type is u32. IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN: The created MEP domain. The type is u32 (br_cfm_domain). It must be BR_CFM_PORT. This means that CFM frames are transmitted and received directly on the port - untagged. Not in a VLAN. IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION: The created MEP direction. The type is u32 (br_cfm_mep_direction). It must be BR_CFM_MEP_DIRECTION_DOWN. This means that CFM frames are transmitted and received on the port. Not in the bridge. IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX: The created MEP residence port ifindex. The type is u32 (ifindex). IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE: The deleted MEP instance number. The type is u32. IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC: The configured MEP unicast MAC address. The type is 6*u8 (array). This is used as SMAC in all transmitted CFM frames. IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL: The configured MEP unicast MD level. The type is u32. It must be in the range 1-7. No CFM frames are passing through this MEP on lower levels. IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID: The configured MEP ID. The type is u32. It must be in the range 0-0x1FFF. This MEP ID is inserted in any transmitted CCM frame. IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE: The Continuity Check (CC) functionality is enabled or disabled. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL: The CC expected receive interval of CCM frames. The type is u32 (br_cfm_ccm_interval). This is also the transmission interval of CCM frames when enabled. IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID: The CC expected receive MAID in CCM frames. The type is CFM_MAID_LENGTH*u8. This is MAID is also inserted in transmitted CCM frames. IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_CC_PEER_MEPID: The CC Peer MEP ID added. The type is u32. When a Peer MEP ID is added and CC is enabled it is expected to receive CCM frames from that Peer MEP. IFLA_BRIDGE_CFM_CC_RDI_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_CC_RDI_RDI: The RDI that is inserted in transmitted CCM PDU. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE: The configured MEP instance number. The type is u32. IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC: The transmitted CCM frame destination MAC address. The type is 6*u8 (array). This is used as DMAC in all transmitted CFM frames. IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE: The transmitted CCM frame update (increment) of sequence number is enabled or disabled. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD: The period of time where CCM frame are transmitted. The type is u32. The time is given in seconds. SETLINK IFLA_BRIDGE_CFM_CC_CCM_TX must be done before timeout to keep transmission alive. When period is zero any ongoing CCM frame transmission will be stopped. IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV: The transmitted CCM frame update with Interface Status TLV is enabled or disabled. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE: The transmitted Interface Status TLV value field. The type is u8. IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV: The transmitted CCM frame update with Port Status TLV is enabled or disabled. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE: The transmitted Port Status TLV value field. The type is u8. Signed-off-by: Henrik Bjoernlund Reviewed-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 6 ++ net/bridge/br_cfm_netlink.c | 161 +++++++++++++++++++++++++++++++++++++++++ net/bridge/br_netlink.c | 29 +++++++- net/bridge/br_private.h | 6 ++ 4 files changed, 200 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 94cc9444d749..b8b4491922d9 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -339,6 +339,12 @@ enum { IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE, IFLA_BRIDGE_CFM_CC_RDI, IFLA_BRIDGE_CFM_CC_CCM_TX, + IFLA_BRIDGE_CFM_MEP_CREATE_INFO, + IFLA_BRIDGE_CFM_MEP_CONFIG_INFO, + IFLA_BRIDGE_CFM_CC_CONFIG_INFO, + IFLA_BRIDGE_CFM_CC_RDI_INFO, + IFLA_BRIDGE_CFM_CC_CCM_TX_INFO, + IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO, __IFLA_BRIDGE_CFM_MAX, }; diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c index c75f4c788eac..dee1e0dea39e 100644 --- a/net/bridge/br_cfm_netlink.c +++ b/net/bridge/br_cfm_netlink.c @@ -451,3 +451,164 @@ int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, return 0; } + +int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + struct nlattr *tb; + + hlist_for_each_entry_rcu(mep, &br->mep_list, head) { + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INFO); + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN, + mep->create.domain)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION, + mep->create.direction)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX, + mep->create.ifindex)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC, + sizeof(mep->config.unicast_mac.addr), + mep->config.unicast_mac.addr)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL, + mep->config.mdlevel)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID, + mep->config.mepid)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE, + mep->cc_config.enable)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL, + mep->cc_config.exp_interval)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID, + sizeof(mep->cc_config.exp_maid.data), + mep->cc_config.exp_maid.data)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_RDI_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_RDI, + mep->rdi)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC, + sizeof(mep->cc_ccm_tx_info.dmac), + mep->cc_ccm_tx_info.dmac.addr)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE, + mep->cc_ccm_tx_info.seq_no_update)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD, + mep->cc_ccm_tx_info.period)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV, + mep->cc_ccm_tx_info.if_tlv)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE, + mep->cc_ccm_tx_info.if_tlv_value)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV, + mep->cc_ccm_tx_info.port_tlv)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE, + mep->cc_ccm_tx_info.port_tlv_value)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) { + tb = nla_nest_start(skb, + IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_MEPID, + peer_mep->mepid)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + } + } + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, tb); + +nla_info_failure: + return -EMSGSIZE; +} diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 431ee2b06dc1..69bfe165ff7f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -16,6 +16,7 @@ #include "br_private.h" #include "br_private_stp.h" +#include "br_private_cfm.h" #include "br_private_tunnel.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, @@ -426,7 +427,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, if (filter_mask & (RTEXT_FILTER_BRVLAN | RTEXT_FILTER_BRVLAN_COMPRESSED | - RTEXT_FILTER_MRP)) { + RTEXT_FILTER_MRP | + RTEXT_FILTER_CFM_CONFIG)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; @@ -475,6 +477,28 @@ static int br_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } + if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { + struct nlattr *cfm_nest = NULL; + int err; + + if (!br_cfm_created(br) || port) + goto done; + + cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM); + if (!cfm_nest) + goto nla_put_failure; + + if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { + rcu_read_lock(); + err = br_cfm_config_fill_info(skb, br); + rcu_read_unlock(); + if (err) + goto nla_put_failure; + } + + nla_nest_end(skb, cfm_nest); + } + done: if (af) nla_nest_end(skb, af); @@ -538,7 +562,8 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) && - !(filter_mask & RTEXT_FILTER_MRP)) + !(filter_mask & RTEXT_FILTER_MRP) && + !(filter_mask & RTEXT_FILTER_CFM_CONFIG)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 6a5db0553f19..f571bdeb5d83 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1465,6 +1465,7 @@ int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, struct netlink_ext_ack *extack); bool br_cfm_created(struct net_bridge *br); void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p); +int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br); #else static inline int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, @@ -1482,6 +1483,11 @@ static inline void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p) { } + +static inline int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br) +{ + return -EOPNOTSUPP; +} #endif /* br_netlink.c */ -- cgit v1.3-15-g9ac1 From e77824d81dff5e6f9244c201537a47f418eb36cb Mon Sep 17 00:00:00 2001 From: Henrik Bjoernlund Date: Tue, 27 Oct 2020 10:02:50 +0000 Subject: bridge: cfm: Netlink GET status Interface. This is the implementation of CFM netlink status get information interface. Add new nested netlink attributes. These attributes are used by the user space to get status information. GETLINK: Request filter RTEXT_FILTER_CFM_STATUS: Indicating that CFM status information must be delivered. IFLA_BRIDGE_CFM: Points to the CFM information. IFLA_BRIDGE_CFM_MEP_STATUS_INFO: This indicate that the MEP instance status are following. IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO: This indicate that the peer MEP status are following. CFM nested attribute has the following attributes in next level. GETLINK RTEXT_FILTER_CFM_STATUS: IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE: The MEP instance number of the delivered status. The type is u32. IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN: The MEP instance received CFM PDU with unexpected Opcode. The type is u32 (bool). IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN: The MEP instance received CFM PDU with unexpected version. The type is u32 (bool). IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN: The MEP instance received CCM PDU with MD level lower than configured level. This frame is discarded. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE: The MEP instance number of the delivered status. The type is u32. IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID: The added Peer MEP ID of the delivered status. The type is u32. IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT: The CCM defect status. The type is u32 (bool). True means no CCM frame is received for 3.25 intervals. IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL. IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI: The last received CCM PDU RDI. The type is u32 (bool). IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE: The last received CCM PDU Port Status TLV value field. The type is u8. IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE: The last received CCM PDU Interface Status TLV value field. The type is u8. IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN: A CCM frame has been received from Peer MEP. The type is u32 (bool). This is cleared after GETLINK IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO. IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN: A CCM frame with TLV has been received from Peer MEP. The type is u32 (bool). This is cleared after GETLINK IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO. IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN: A CCM frame with unexpected sequence number has been received from Peer MEP. The type is u32 (bool). When a sequence number is not one higher than previously received then it is unexpected. This is cleared after GETLINK IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO. Signed-off-by: Henrik Bjoernlund Reviewed-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 29 ++++++++++++ include/uapi/linux/rtnetlink.h | 1 + net/bridge/br_cfm_netlink.c | 105 +++++++++++++++++++++++++++++++++++++++++ net/bridge/br_netlink.c | 16 +++++-- net/bridge/br_private.h | 6 +++ 5 files changed, 154 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index b8b4491922d9..d975e1223884 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -345,6 +345,8 @@ enum { IFLA_BRIDGE_CFM_CC_RDI_INFO, IFLA_BRIDGE_CFM_CC_CCM_TX_INFO, IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO, + IFLA_BRIDGE_CFM_MEP_STATUS_INFO, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO, __IFLA_BRIDGE_CFM_MAX, }; @@ -424,6 +426,33 @@ enum { #define IFLA_BRIDGE_CFM_CC_CCM_TX_MAX (__IFLA_BRIDGE_CFM_CC_CCM_TX_MAX - 1) +enum { + IFLA_BRIDGE_CFM_MEP_STATUS_UNSPEC, + IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE, + IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN, + IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN, + IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN, + __IFLA_BRIDGE_CFM_MEP_STATUS_MAX, +}; + +#define IFLA_BRIDGE_CFM_MEP_STATUS_MAX (__IFLA_BRIDGE_CFM_MEP_STATUS_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_PEER_STATUS_UNSPEC, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN, + __IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX (__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX - 1) + struct bridge_stp_xstats { __u64 transition_blk; __u64 transition_fwd; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index ffc9ca1f2bdb..fdd408f6a5d2 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -780,6 +780,7 @@ enum { #define RTEXT_FILTER_SKIP_STATS (1 << 3) #define RTEXT_FILTER_MRP (1 << 4) #define RTEXT_FILTER_CFM_CONFIG (1 << 5) +#define RTEXT_FILTER_CFM_STATUS (1 << 6) /* End of information exported to user level */ diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c index dee1e0dea39e..c8b5ff0825a3 100644 --- a/net/bridge/br_cfm_netlink.c +++ b/net/bridge/br_cfm_netlink.c @@ -612,3 +612,108 @@ nla_put_failure: nla_info_failure: return -EMSGSIZE; } + +int br_cfm_status_fill_info(struct sk_buff *skb, struct net_bridge *br) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + struct nlattr *tb; + + hlist_for_each_entry_rcu(mep, &br->mep_list, head) { + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INFO); + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN, + mep->status.opcode_unexp_seen)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN, + mep->status.version_unexp_seen)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN, + mep->status.rx_level_low_seen)) + goto nla_put_failure; + + /* Clear all 'seen' indications */ + mep->status.opcode_unexp_seen = false; + mep->status.version_unexp_seen = false; + mep->status.rx_level_low_seen = false; + + nla_nest_end(skb, tb); + + hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) { + tb = nla_nest_start(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO); + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID, + peer_mep->mepid)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT, + peer_mep->cc_status.ccm_defect)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI, + peer_mep->cc_status.rdi)) + goto nla_put_failure; + + if (nla_put_u8(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE, + peer_mep->cc_status.port_tlv_value)) + goto nla_put_failure; + + if (nla_put_u8(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE, + peer_mep->cc_status.if_tlv_value)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN, + peer_mep->cc_status.seen)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN, + peer_mep->cc_status.tlv_seen)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN, + peer_mep->cc_status.seq_unexp_seen)) + goto nla_put_failure; + + /* Clear all 'seen' indications */ + peer_mep->cc_status.seen = false; + peer_mep->cc_status.tlv_seen = false; + peer_mep->cc_status.seq_unexp_seen = false; + + nla_nest_end(skb, tb); + } + } + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, tb); + +nla_info_failure: + return -EMSGSIZE; +} diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 69bfe165ff7f..68c2ed87e26b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -428,7 +428,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, if (filter_mask & (RTEXT_FILTER_BRVLAN | RTEXT_FILTER_BRVLAN_COMPRESSED | RTEXT_FILTER_MRP | - RTEXT_FILTER_CFM_CONFIG)) { + RTEXT_FILTER_CFM_CONFIG | + RTEXT_FILTER_CFM_STATUS)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; @@ -477,7 +478,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } - if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { + if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) { struct nlattr *cfm_nest = NULL; int err; @@ -496,6 +497,14 @@ static int br_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } + if (filter_mask & RTEXT_FILTER_CFM_STATUS) { + rcu_read_lock(); + err = br_cfm_status_fill_info(skb, br); + rcu_read_unlock(); + if (err) + goto nla_put_failure; + } + nla_nest_end(skb, cfm_nest); } @@ -563,7 +572,8 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) && !(filter_mask & RTEXT_FILTER_MRP) && - !(filter_mask & RTEXT_FILTER_CFM_CONFIG)) + !(filter_mask & RTEXT_FILTER_CFM_CONFIG) && + !(filter_mask & RTEXT_FILTER_CFM_STATUS)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index f571bdeb5d83..228635b350a2 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1466,6 +1466,7 @@ int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, bool br_cfm_created(struct net_bridge *br); void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p); int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br); +int br_cfm_status_fill_info(struct sk_buff *skb, struct net_bridge *br); #else static inline int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, @@ -1488,6 +1489,11 @@ static inline int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge { return -EOPNOTSUPP; } + +static inline int br_cfm_status_fill_info(struct sk_buff *skb, struct net_bridge *br) +{ + return -EOPNOTSUPP; +} #endif /* br_netlink.c */ -- cgit v1.3-15-g9ac1 From 8dba29603b5c8bfca2bf90aeb83d05a236df967b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 29 Oct 2020 15:05:02 +0800 Subject: sctp: add SCTP_REMOTE_UDP_ENCAPS_PORT sockopt This patch is to implement: rfc6951#section-6.1: Get or Set the Remote UDP Encapsulation Port Number with the param of the struct: struct sctp_udpencaps { sctp_assoc_t sue_assoc_id; struct sockaddr_storage sue_address; uint16_t sue_port; }; the encap_port of sock, assoc or transport can be changed by users, which also means it allows the different transports of the same asoc to have different encap_port value. v1->v2: - no change. v2->v3: - fix the endian warning when setting values between encap_port and sue_port. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: Jakub Kicinski --- include/uapi/linux/sctp.h | 7 +++ net/sctp/socket.c | 114 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 121 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 28ad40d9acba..cb78e7a739da 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -140,6 +140,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_ECN_SUPPORTED 130 #define SCTP_EXPOSE_POTENTIALLY_FAILED_STATE 131 #define SCTP_EXPOSE_PF_STATE SCTP_EXPOSE_POTENTIALLY_FAILED_STATE +#define SCTP_REMOTE_UDP_ENCAPS_PORT 132 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -1197,6 +1198,12 @@ struct sctp_event { uint8_t se_on; }; +struct sctp_udpencaps { + sctp_assoc_t sue_assoc_id; + struct sockaddr_storage sue_address; + uint16_t sue_port; +}; + /* SCTP Stream schedulers */ enum sctp_sched_type { SCTP_SS_FCFS, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 09b94cd7ca37..2a9ee9b3e46c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4417,6 +4417,55 @@ out: return retval; } +static int sctp_setsockopt_encap_port(struct sock *sk, + struct sctp_udpencaps *encap, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_transport *t; + __be16 encap_port; + + if (optlen != sizeof(*encap)) + return -EINVAL; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + encap_port = (__force __be16)encap->sue_port; + if (!sctp_is_any(sk, (union sctp_addr *)&encap->sue_address)) { + t = sctp_addr_id2transport(sk, &encap->sue_address, + encap->sue_assoc_id); + if (!t) + return -EINVAL; + + t->encap_port = encap_port; + return 0; + } + + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. + */ + asoc = sctp_id2assoc(sk, encap->sue_assoc_id); + if (!asoc && encap->sue_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + /* If changes are for association, also apply encap_port to + * each transport. + */ + if (asoc) { + list_for_each_entry(t, &asoc->peer.transport_addr_list, + transports) + t->encap_port = encap_port; + + return 0; + } + + sctp_sk(sk)->encap_port = encap_port; + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4636,6 +4685,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: retval = sctp_setsockopt_pf_expose(sk, kopt, optlen); break; + case SCTP_REMOTE_UDP_ENCAPS_PORT: + retval = sctp_setsockopt_encap_port(sk, kopt, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7791,6 +7843,65 @@ out: return retval; } +static int sctp_getsockopt_encap_port(struct sock *sk, int len, + char __user *optval, int __user *optlen) +{ + struct sctp_association *asoc; + struct sctp_udpencaps encap; + struct sctp_transport *t; + __be16 encap_port; + + if (len < sizeof(encap)) + return -EINVAL; + + len = sizeof(encap); + if (copy_from_user(&encap, optval, len)) + return -EFAULT; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + if (!sctp_is_any(sk, (union sctp_addr *)&encap.sue_address)) { + t = sctp_addr_id2transport(sk, &encap.sue_address, + encap.sue_assoc_id); + if (!t) { + pr_debug("%s: failed no transport\n", __func__); + return -EINVAL; + } + + encap_port = t->encap_port; + goto out; + } + + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. + */ + asoc = sctp_id2assoc(sk, encap.sue_assoc_id); + if (!asoc && encap.sue_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { + pr_debug("%s: failed no association\n", __func__); + return -EINVAL; + } + + if (asoc) { + encap_port = asoc->encap_port; + goto out; + } + + encap_port = sctp_sk(sk)->encap_port; + +out: + encap.sue_port = (__force uint16_t)encap_port; + if (copy_to_user(optval, &encap, len)) + return -EFAULT; + + if (put_user(len, optlen)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -8011,6 +8122,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen); break; + case SCTP_REMOTE_UDP_ENCAPS_PORT: + retval = sctp_getsockopt_encap_port(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; -- cgit v1.3-15-g9ac1 From 955062b03fa62b802a1ee34fbb04e39f7a70ae73 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 29 Oct 2020 01:38:31 +0200 Subject: net: bridge: mcast: add support for raw L2 multicast groups Extend the bridge multicast control and data path to configure routes for L2 (non-IP) multicast groups. The uapi struct br_mdb_entry union u is extended with another variant, mac_addr, which does not change the structure size, and which is valid when the proto field is zero. To be compatible with the forwarding code that is already in place, which acts as an IGMP/MLD snooping bridge with querier capabilities, we need to declare that for L2 MDB entries (for which there exists no such thing as IGMP/MLD snooping/querying), that there is always a querier. Otherwise, these entries would be flooded to all bridge ports and not just to those that are members of the L2 multicast group. Needless to say, only permanent L2 multicast groups can be installed on a bridge port. Signed-off-by: Nikolay Aleksandrov Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20201028233831.610076-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_bridge.h | 1 + net/bridge/br_device.c | 2 +- net/bridge/br_input.c | 2 +- net/bridge/br_mdb.c | 24 ++++++++++++++++++++++-- net/bridge/br_multicast.c | 13 +++++++++---- net/bridge/br_private.h | 10 ++++++++-- 7 files changed, 43 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 556caed00258..b979005ea39c 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -25,6 +25,7 @@ struct br_ip { #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ip6; #endif + unsigned char mac_addr[ETH_ALEN]; } dst; __be16 proto; __u16 vid; diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index d975e1223884..13d59c51ef5b 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -651,6 +651,7 @@ struct br_mdb_entry { union { __be32 ip4; struct in6_addr ip6; + unsigned char mac_addr[ETH_ALEN]; } u; __be16 proto; } addr; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 9b5d62744acc..2400a66fe76e 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -93,7 +93,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) mdst = br_mdb_get(br, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && - br_multicast_querier_exists(br, eth_hdr(skb))) + br_multicast_querier_exists(br, eth_hdr(skb), mdst)) br_multicast_flood(mdst, skb, false, true); else br_flood(br, skb, BR_PKT_MULTICAST, false, true); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index bece03bf83c4..21808985f268 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -134,7 +134,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb case BR_PKT_MULTICAST: mdst = br_mdb_get(br, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && - br_multicast_querier_exists(br, eth_hdr(skb))) { + br_multicast_querier_exists(br, eth_hdr(skb), mdst)) { if ((mdst && mdst->host_joined) || br_multicast_is_router(br)) { local_rcv = true; diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index e15bab19a012..3c8863418d0b 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -87,6 +87,8 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip, ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]); break; #endif + default: + ether_addr_copy(ip->dst.mac_addr, entry->addr.u.mac_addr); } } @@ -174,9 +176,11 @@ static int __mdb_fill_info(struct sk_buff *skb, if (mp->addr.proto == htons(ETH_P_IP)) e.addr.u.ip4 = mp->addr.dst.ip4; #if IS_ENABLED(CONFIG_IPV6) - if (mp->addr.proto == htons(ETH_P_IPV6)) + else if (mp->addr.proto == htons(ETH_P_IPV6)) e.addr.u.ip6 = mp->addr.dst.ip6; #endif + else + ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); e.addr.proto = mp->addr.proto; nest_ent = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY_INFO); @@ -210,6 +214,8 @@ static int __mdb_fill_info(struct sk_buff *skb, } break; #endif + default: + ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); } if (p) { if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol)) @@ -562,9 +568,12 @@ void br_mdb_notify(struct net_device *dev, if (mp->addr.proto == htons(ETH_P_IP)) ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr); #if IS_ENABLED(CONFIG_IPV6) - else + else if (mp->addr.proto == htons(ETH_P_IPV6)) ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr); #endif + else + ether_addr_copy(mdb.addr, mp->addr.dst.mac_addr); + mdb.obj.orig_dev = pg->key.port->dev; switch (type) { case RTM_NEWMDB: @@ -693,6 +702,12 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry, return false; } #endif + } else if (entry->addr.proto == 0) { + /* L2 mdb */ + if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) { + NL_SET_ERR_MSG_MOD(extack, "L2 entry group is not multicast"); + return false; + } } else { NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol"); return false; @@ -849,6 +864,11 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, } } + if (br_group_is_l2(&group) && entry->state != MDB_PERMANENT) { + NL_SET_ERR_MSG_MOD(extack, "Only permanent L2 entries allowed"); + return -EINVAL; + } + mp = br_mdb_ip_get(br, &group); if (!mp) { mp = br_multicast_new_group(br, &group); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index eae898c3cff7..484820c223a3 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -179,7 +179,8 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, break; #endif default: - return NULL; + ip.proto = 0; + ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest); } return br_mdb_ip_get_rcu(br, &ip); @@ -1203,6 +1204,10 @@ void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify) if (notify) br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB); } + + if (br_group_is_l2(&mp->addr)) + return; + mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval); } @@ -1254,8 +1259,8 @@ __br_multicast_add_group(struct net_bridge *br, break; } - p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode, - RTPROT_KERNEL); + p = br_multicast_new_port_group(port, group, *pp, 0, src, + filter_mode, RTPROT_KERNEL); if (unlikely(!p)) { p = ERR_PTR(-ENOMEM); goto out; @@ -3690,7 +3695,7 @@ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto) memset(ð, 0, sizeof(eth)); eth.h_proto = htons(proto); - ret = br_multicast_querier_exists(br, ð); + ret = br_multicast_querier_exists(br, ð, NULL); unlock: rcu_read_unlock(); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 905d406a2fc7..4c691c371884 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -854,6 +854,11 @@ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, struct net_bridge_port_group *sg); +static inline bool br_group_is_l2(const struct br_ip *group) +{ + return group->proto == 0; +} + #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) @@ -885,7 +890,8 @@ __br_multicast_querier_exists(struct net_bridge *br, } static inline bool br_multicast_querier_exists(struct net_bridge *br, - struct ethhdr *eth) + struct ethhdr *eth, + const struct net_bridge_mdb_entry *mdb) { switch (eth->h_proto) { case (htons(ETH_P_IP)): @@ -897,7 +903,7 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br, &br->ip6_other_query, true); #endif default: - return false; + return !!mdb && br_group_is_l2(&mdb->addr); } } -- cgit v1.3-15-g9ac1 From ccf0a4b7fc688561428290265e4effde41446668 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 29 Oct 2020 16:39:48 +0100 Subject: netfilter: ipset: Add bucketsize parameter to all hash types The parameter defines the upper limit in any hash bucket at adding new entries from userspace - if the limit would be exceeded, ipset doubles the hash size and rehashes. It means the set may consume more memory but gives faster evaluation at matching in the set. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 5 ++++ include/uapi/linux/netfilter/ipset/ip_set.h | 4 ++- net/netfilter/ipset/ip_set_core.c | 2 ++ net/netfilter/ipset/ip_set_hash_gen.h | 38 +++++++++++++++++----------- net/netfilter/ipset/ip_set_hash_ip.c | 6 +++-- net/netfilter/ipset/ip_set_hash_ipmac.c | 5 ++-- net/netfilter/ipset/ip_set_hash_ipmark.c | 6 +++-- net/netfilter/ipset/ip_set_hash_ipport.c | 6 +++-- net/netfilter/ipset/ip_set_hash_ipportip.c | 6 +++-- net/netfilter/ipset/ip_set_hash_ipportnet.c | 6 +++-- net/netfilter/ipset/ip_set_hash_mac.c | 5 ++-- net/netfilter/ipset/ip_set_hash_net.c | 6 +++-- net/netfilter/ipset/ip_set_hash_netiface.c | 6 +++-- net/netfilter/ipset/ip_set_hash_netnet.c | 6 +++-- net/netfilter/ipset/ip_set_hash_netport.c | 6 +++-- net/netfilter/ipset/ip_set_hash_netportnet.c | 6 +++-- 16 files changed, 79 insertions(+), 40 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index ab192720e2d6..46d9a0c26c67 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -198,6 +198,9 @@ struct ip_set_region { u32 elements; /* Number of elements vs timeout */ }; +/* The max revision number supported by any set type + 1 */ +#define IPSET_REVISION_MAX 9 + /* The core set type structure */ struct ip_set_type { struct list_head list; @@ -215,6 +218,8 @@ struct ip_set_type { u8 family; /* Type revisions */ u8 revision_min, revision_max; + /* Revision-specific supported (create) flags */ + u8 create_flags[IPSET_REVISION_MAX+1]; /* Set features to control swapping */ u16 features; diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index 11a72a938eb1..398f7b909b7d 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -96,7 +96,7 @@ enum { IPSET_ATTR_HASHSIZE, IPSET_ATTR_MAXELEM, IPSET_ATTR_NETMASK, - IPSET_ATTR_PROBES, + IPSET_ATTR_BUCKETSIZE, /* was unused IPSET_ATTR_PROBES */ IPSET_ATTR_RESIZE, IPSET_ATTR_SIZE, /* Kernel-only */ @@ -214,6 +214,8 @@ enum ipset_cadt_flags { enum ipset_create_flags { IPSET_CREATE_FLAG_BIT_FORCEADD = 0, IPSET_CREATE_FLAG_FORCEADD = (1 << IPSET_CREATE_FLAG_BIT_FORCEADD), + IPSET_CREATE_FLAG_BIT_BUCKETSIZE = 1, + IPSET_CREATE_FLAG_BUCKETSIZE = (1 << IPSET_CREATE_FLAG_BIT_BUCKETSIZE), IPSET_CREATE_FLAG_BIT_MAX = 7, }; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e3c00dacec5c..e76bfca2d3ef 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1109,6 +1109,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl, ret = -IPSET_ERR_PROTOCOL; goto put_out; } + /* Set create flags depending on the type revision */ + set->flags |= set->type->create_flags[revision]; ret = set->type->create(net, set, tb, flags); if (ret != 0) diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 521e970be402..4e3544442b26 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -37,18 +37,18 @@ */ /* Number of elements to store in an initial array block */ -#define AHASH_INIT_SIZE 4 +#define AHASH_INIT_SIZE 2 /* Max number of elements to store in an array block */ -#define AHASH_MAX_SIZE (3 * AHASH_INIT_SIZE) +#define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE) /* Max muber of elements in the array block when tuned */ #define AHASH_MAX_TUNED 64 +#define AHASH_MAX(h) ((h)->bucketsize) + /* Max number of elements can be tuned */ #ifdef IP_SET_HASH_WITH_MULTI -#define AHASH_MAX(h) ((h)->ahash_max) - static u8 -tune_ahash_max(u8 curr, u32 multi) +tune_bucketsize(u8 curr, u32 multi) { u32 n; @@ -61,12 +61,10 @@ tune_ahash_max(u8 curr, u32 multi) */ return n > curr && n <= AHASH_MAX_TUNED ? n : curr; } - -#define TUNE_AHASH_MAX(h, multi) \ - ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi)) +#define TUNE_BUCKETSIZE(h, multi) \ + ((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi)) #else -#define AHASH_MAX(h) AHASH_MAX_SIZE -#define TUNE_AHASH_MAX(h, multi) +#define TUNE_BUCKETSIZE(h, multi) #endif /* A hash bucket */ @@ -321,9 +319,7 @@ struct htype { #ifdef IP_SET_HASH_WITH_MARKMASK u32 markmask; /* markmask value for mark mask to store */ #endif -#ifdef IP_SET_HASH_WITH_MULTI - u8 ahash_max; /* max elements in an array block */ -#endif + u8 bucketsize; /* max elements in an array block */ #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif @@ -950,7 +946,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto set_full; /* Create a new slot */ if (n->pos >= n->size) { - TUNE_AHASH_MAX(h, multi); + TUNE_BUCKETSIZE(h, multi); if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); @@ -1305,6 +1301,9 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask)) goto nla_put_failure; #endif + if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE && + nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize)) + goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) @@ -1548,7 +1547,16 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, h->markmask = markmask; #endif get_random_bytes(&h->initval, sizeof(h->initval)); - + h->bucketsize = AHASH_MAX_SIZE; + if (tb[IPSET_ATTR_BUCKETSIZE]) { + h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]); + if (h->bucketsize < AHASH_INIT_SIZE) + h->bucketsize = AHASH_INIT_SIZE; + else if (h->bucketsize > AHASH_MAX_SIZE) + h->bucketsize = AHASH_MAX_SIZE; + else if (h->bucketsize % 2) + h->bucketsize += 1; + } t->htable_bits = hbits; t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 5d6d68eaf6a9..0495d515c498 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -23,7 +23,8 @@ /* 1 Counters support */ /* 2 Comments support */ /* 3 Forceadd support */ -#define IPSET_TYPE_REV_MAX 4 /* skbinfo support */ +/* 4 skbinfo support */ +#define IPSET_TYPE_REV_MAX 5 /* bucketsize support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -277,11 +278,12 @@ static struct ip_set_type hash_ip_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index eceb7bc4a93a..2655501f9fe3 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -23,7 +23,7 @@ #include #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 0 +#define IPSET_TYPE_REV_MAX 1 /* bucketsize support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Tomasz Chilinski "); @@ -268,11 +268,12 @@ static struct ip_set_type hash_ipmac_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipmac_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index aba1df617d6e..5bbed85d0e47 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -21,7 +21,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support */ -#define IPSET_TYPE_REV_MAX 2 /* skbinfo support */ +/* 2 skbinfo support */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vytas Dauksa "); @@ -274,12 +275,13 @@ static struct ip_set_type hash_ipmark_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipmark_create, .create_policy = { [IPSET_ATTR_MARKMASK] = { .type = NLA_U32 }, [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 1ff228717e29..c1ac2e89e2d3 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -25,7 +25,8 @@ /* 2 Counters support added */ /* 3 Comments support added */ /* 4 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */ +/* 5 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 6 /* bucketsize support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -341,11 +342,12 @@ static struct ip_set_type hash_ipport_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index fa88afd812fa..d3f4a672986e 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -25,7 +25,8 @@ /* 2 Counters support added */ /* 3 Comments support added */ /* 4 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */ +/* 5 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 6 /* bucketsize support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -356,11 +357,12 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipportip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index eef6ecfcb409..8f7fe360736a 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -27,7 +27,8 @@ /* 4 Counters support added */ /* 5 Comments support added */ /* 6 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 7 /* skbinfo support added */ +/* 7 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -513,11 +514,12 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c index 0b61593165ef..00dd7e20df3c 100644 --- a/net/netfilter/ipset/ip_set_hash_mac.c +++ b/net/netfilter/ipset/ip_set_hash_mac.c @@ -16,7 +16,7 @@ #include #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 0 +#define IPSET_TYPE_REV_MAX 1 /* bucketsize support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -125,11 +125,12 @@ static struct ip_set_type hash_mac_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_mac_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 136cf0781d3a..d366e816b6ed 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -24,7 +24,8 @@ /* 3 Counters support added */ /* 4 Comments support added */ /* 5 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 6 /* skbinfo mapping support added */ +/* 6 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 7 /* bucketsize support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -354,11 +355,12 @@ static struct ip_set_type hash_net_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_net_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index be5e95a0d876..38b1d77584d4 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -26,7 +26,8 @@ /* 4 Comments support added */ /* 5 Forceadd support added */ /* 6 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 7 /* interface wildcard support added */ +/* 7 interface wildcard support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -470,11 +471,12 @@ static struct ip_set_type hash_netiface_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netiface_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index da4ef910b12d..0cc7970f36e9 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -22,7 +22,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 2 /* skbinfo support added */ +/* 2 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith "); @@ -459,11 +460,12 @@ static struct ip_set_type hash_netnet_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 34448df80fb9..b356d7d85e34 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -26,7 +26,8 @@ /* 4 Counters support added */ /* 5 Comments support added */ /* 6 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 7 /* skbinfo support added */ +/* 7 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -460,11 +461,12 @@ static struct ip_set_type hash_netport_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 934c1712cba8..eeb39688f26f 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -23,7 +23,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 0 Comments support added */ /* 1 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 2 /* skbinfo support added */ +/* 2 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith "); @@ -558,11 +559,12 @@ static struct ip_set_type hash_netportnet_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, -- cgit v1.3-15-g9ac1 From 3976ca101990ca11ddf51f38bec7b86c19d0ca6f Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 29 Oct 2020 16:39:49 +0100 Subject: netfilter: ipset: Expose the initval hash parameter to userspace It makes possible to reproduce exactly the same set after a save/restore. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/ipset/ip_set.h | 2 +- net/netfilter/ipset/ip_set_hash_gen.h | 13 +++++++++---- net/netfilter/ipset/ip_set_hash_ip.c | 3 ++- net/netfilter/ipset/ip_set_hash_ipmac.c | 3 ++- net/netfilter/ipset/ip_set_hash_ipmark.c | 3 ++- net/netfilter/ipset/ip_set_hash_ipport.c | 3 ++- net/netfilter/ipset/ip_set_hash_ipportip.c | 3 ++- net/netfilter/ipset/ip_set_hash_ipportnet.c | 3 ++- net/netfilter/ipset/ip_set_hash_mac.c | 3 ++- net/netfilter/ipset/ip_set_hash_net.c | 3 ++- net/netfilter/ipset/ip_set_hash_netiface.c | 3 ++- net/netfilter/ipset/ip_set_hash_netnet.c | 3 ++- net/netfilter/ipset/ip_set_hash_netport.c | 3 ++- net/netfilter/ipset/ip_set_hash_netportnet.c | 3 ++- 14 files changed, 34 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index 398f7b909b7d..6397d75899bc 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -92,7 +92,7 @@ enum { /* Reserve empty slots */ IPSET_ATTR_CADT_MAX = 16, /* Create-only specific attributes */ - IPSET_ATTR_GC, + IPSET_ATTR_INITVAL, /* was unused IPSET_ATTR_GC */ IPSET_ATTR_HASHSIZE, IPSET_ATTR_MAXELEM, IPSET_ATTR_NETMASK, diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 4e3544442b26..5f1208ad049e 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1301,9 +1301,11 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask)) goto nla_put_failure; #endif - if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE && - nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize)) - goto nla_put_failure; + if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) { + if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) || + nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval))) + goto nla_put_failure; + } if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) @@ -1546,7 +1548,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifdef IP_SET_HASH_WITH_MARKMASK h->markmask = markmask; #endif - get_random_bytes(&h->initval, sizeof(h->initval)); + if (tb[IPSET_ATTR_INITVAL]) + h->initval = ntohl(nla_get_be32(tb[IPSET_ATTR_INITVAL])); + else + get_random_bytes(&h->initval, sizeof(h->initval)); h->bucketsize = AHASH_MAX_SIZE; if (tb[IPSET_ATTR_BUCKETSIZE]) { h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]); diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 0495d515c498..d1bef23fd4f5 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -24,7 +24,7 @@ /* 2 Comments support */ /* 3 Forceadd support */ /* 4 skbinfo support */ -#define IPSET_TYPE_REV_MAX 5 /* bucketsize support */ +#define IPSET_TYPE_REV_MAX 5 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -283,6 +283,7 @@ static struct ip_set_type hash_ip_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index 2655501f9fe3..467c59a83c0a 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -23,7 +23,7 @@ #include #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 1 /* bucketsize support */ +#define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Tomasz Chilinski "); @@ -273,6 +273,7 @@ static struct ip_set_type hash_ipmac_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 5bbed85d0e47..18346d18aa16 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -22,7 +22,7 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support */ /* 2 skbinfo support */ -#define IPSET_TYPE_REV_MAX 3 /* bucketsize support */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vytas Dauksa "); @@ -281,6 +281,7 @@ static struct ip_set_type hash_ipmark_type __read_mostly = { [IPSET_ATTR_MARKMASK] = { .type = NLA_U32 }, [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index c1ac2e89e2d3..e1ca11196515 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -26,7 +26,7 @@ /* 3 Comments support added */ /* 4 Forceadd support added */ /* 5 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 6 /* bucketsize support added */ +#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -347,6 +347,7 @@ static struct ip_set_type hash_ipport_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index d3f4a672986e..ab179e064597 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -26,7 +26,7 @@ /* 3 Comments support added */ /* 4 Forceadd support added */ /* 5 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 6 /* bucketsize support added */ +#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -362,6 +362,7 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 8f7fe360736a..8f075b44cf64 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -28,7 +28,7 @@ /* 5 Comments support added */ /* 6 Forceadd support added */ /* 7 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 8 /* bucketsize support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -519,6 +519,7 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c index 00dd7e20df3c..718814730acf 100644 --- a/net/netfilter/ipset/ip_set_hash_mac.c +++ b/net/netfilter/ipset/ip_set_hash_mac.c @@ -16,7 +16,7 @@ #include #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 1 /* bucketsize support */ +#define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -130,6 +130,7 @@ static struct ip_set_type hash_mac_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index d366e816b6ed..c1a11f041ac6 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -25,7 +25,7 @@ /* 4 Comments support added */ /* 5 Forceadd support added */ /* 6 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 7 /* bucketsize support added */ +#define IPSET_TYPE_REV_MAX 7 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -360,6 +360,7 @@ static struct ip_set_type hash_net_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 38b1d77584d4..3d74169b794c 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -27,7 +27,7 @@ /* 5 Forceadd support added */ /* 6 skbinfo support added */ /* 7 interface wildcard support added */ -#define IPSET_TYPE_REV_MAX 8 /* bucketsize support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -476,6 +476,7 @@ static struct ip_set_type hash_netiface_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 0cc7970f36e9..6532f0505e66 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -23,7 +23,7 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support added */ /* 2 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 3 /* bucketsize support added */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith "); @@ -465,6 +465,7 @@ static struct ip_set_type hash_netnet_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index b356d7d85e34..ec1564a1cb5a 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -27,7 +27,7 @@ /* 5 Comments support added */ /* 6 Forceadd support added */ /* 7 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 8 /* bucketsize support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -466,6 +466,7 @@ static struct ip_set_type hash_netport_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index eeb39688f26f..0e91d1e82f1c 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -24,7 +24,7 @@ /* 0 Comments support added */ /* 1 Forceadd support added */ /* 2 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 3 /* bucketsize support added */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith "); @@ -564,6 +564,7 @@ static struct ip_set_type hash_netportnet_type __read_mostly = { .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, -- cgit v1.3-15-g9ac1 From 94f44f28836de320a318730f4952fde8601f4b58 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 2 Nov 2020 22:12:43 +0200 Subject: net: sched: implement action-specific terse dump Allow user to request action terse dump with new flag value TCA_FLAG_TERSE_DUMP. Only output essential action info in terse dump (kind, stats, index and cookie, if set by the user when creating the action). This is different from filter terse dump where index is excluded (filter can be identified by its own handle). Move tcf_action_dump_terse() function to the beginning of source file in order to call it from tcf_dump_walker(). Signed-off-by: Vlad Buslov Suggested-by: Jamal Hadi Salim Acked-by: Cong Wang Link: https://lore.kernel.org/r/20201102201243.287486-1-vlad@buslov.dev Signed-off-by: Jakub Kicinski --- include/uapi/linux/rtnetlink.h | 4 +++ net/sched/act_api.c | 69 ++++++++++++++++++++++-------------------- 2 files changed, 41 insertions(+), 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index fdd408f6a5d2..d1325ffb0060 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -770,8 +770,12 @@ enum { * actions in a dump. All dump responses will contain the number of actions * being dumped stored in for user app's consumption in TCA_ROOT_COUNT * + * TCA_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only + * includes essential action info (kind, index, etc.) + * */ #define TCA_FLAG_LARGE_DUMP_ON (1 << 0) +#define TCA_FLAG_TERSE_DUMP (1 << 1) /* New extended info filters for IFLA_EXT_MASK */ #define RTEXT_FILTER_VF (1 << 0) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f66417d5d2c3..1341c59c2f40 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -215,6 +215,36 @@ static size_t tcf_action_fill_size(const struct tc_action *act) return sz; } +static int +tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a, bool from_act) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tc_cookie *cookie; + + if (nla_put_string(skb, TCA_KIND, a->ops->kind)) + goto nla_put_failure; + if (tcf_action_copy_stats(skb, a, 0)) + goto nla_put_failure; + if (from_act && nla_put_u32(skb, TCA_ACT_INDEX, a->tcfa_index)) + goto nla_put_failure; + + rcu_read_lock(); + cookie = rcu_dereference(a->act_cookie); + if (cookie) { + if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) { + rcu_read_unlock(); + goto nla_put_failure; + } + } + rcu_read_unlock(); + + return 0; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct netlink_callback *cb) { @@ -248,7 +278,9 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, index--; goto nla_put_failure; } - err = tcf_action_dump_1(skb, p, 0, 0); + err = (act_flags & TCA_FLAG_TERSE_DUMP) ? + tcf_action_dump_terse(skb, p, true) : + tcf_action_dump_1(skb, p, 0, 0); if (err < 0) { index--; nlmsg_trim(skb, nest); @@ -752,34 +784,6 @@ tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) return a->ops->dump(skb, a, bind, ref); } -static int -tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cookie *cookie; - - if (nla_put_string(skb, TCA_KIND, a->ops->kind)) - goto nla_put_failure; - if (tcf_action_copy_stats(skb, a, 0)) - goto nla_put_failure; - - rcu_read_lock(); - cookie = rcu_dereference(a->act_cookie); - if (cookie) { - if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) { - rcu_read_unlock(); - goto nla_put_failure; - } - } - rcu_read_unlock(); - - return 0; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -787,7 +791,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - if (tcf_action_dump_terse(skb, a)) + if (tcf_action_dump_terse(skb, a, false)) goto nla_put_failure; if (a->hw_stats != TCA_ACT_HW_STATS_ANY && @@ -832,7 +836,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; - err = terse ? tcf_action_dump_terse(skb, a) : + err = terse ? tcf_action_dump_terse(skb, a, false) : tcf_action_dump_1(skb, a, bind, ref); if (err < 0) goto errout; @@ -1469,7 +1473,8 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, } static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = { - [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON), + [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON | + TCA_FLAG_TERSE_DUMP), [TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 }, }; -- cgit v1.3-15-g9ac1 From 9f0ffa418483938d25a15f6ad3891389f333bc59 Mon Sep 17 00:00:00 2001 From: Rohan Dutta Date: Tue, 27 Oct 2020 12:09:10 +0200 Subject: cfg80211: Add support to configure SAE PWE value to drivers Add support to configure SAE PWE preference from userspace to drivers in both AP and STA modes. This is needed for cases where the driver takes care of Authentication frame processing (SME in the driver) so that correct enforcement of the acceptable PWE derivation mechanism can be performed. The userspace applications can pass the sae_pwe value using the NL80211_ATTR_SAE_PWE attribute in the NL80211_CMD_CONNECT and NL80211_CMD_START_AP commands to the driver. This allows selection between the hunting-and-pecking loop and hash-to-element options for PWE derivation. For backwards compatibility, this new attribute is optional and if not included, the driver is notified of the value being unspecified. Signed-off-by: Rohan Dutta Signed-off-by: Jouni Malinen Link: https://lore.kernel.org/r/20201027100910.22283-1-jouni@codeaurora.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 9 +++++++++ include/uapi/linux/nl80211.h | 26 ++++++++++++++++++++++++++ net/wireless/nl80211.c | 9 +++++++++ 3 files changed, 44 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 661edfc8722e..0ba8d1fa6eb9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1008,6 +1008,14 @@ struct survey_info { * @sae_pwd: password for SAE authentication (for devices supporting SAE * offload) * @sae_pwd_len: length of SAE password (for devices supporting SAE offload) + * @sae_pwe: The mechanisms allowed for SAE PWE derivation + * NL80211_SAE_PWE_UNSPECIFIED: Not-specified, used to indicate userspace + * did not specify any preference. The driver should follow its + * internal policy in such a scenario. + * NL80211_SAE_PWE_HUNT_AND_PECK: Allow hunting-and-pecking loop only + * NL80211_SAE_PWE_HASH_TO_ELEMENT: Allow hash-to-element only + * NL80211_SAE_PWE_BOTH: Allow either hunting-and-pecking loop + * or hash-to-element */ struct cfg80211_crypto_settings { u32 wpa_versions; @@ -1026,6 +1034,7 @@ struct cfg80211_crypto_settings { const u8 *psk; const u8 *sae_pwd; u8 sae_pwd_len; + enum nl80211_sae_pwe_mechanism sae_pwe; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 47700a2b9af9..2d733effcdaf 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2527,6 +2527,11 @@ enum nl80211_commands { * override mask. Used with NL80211_ATTR_S1G_CAPABILITY in * NL80211_CMD_ASSOCIATE or NL80211_CMD_CONNECT. * + * @NL80211_ATTR_SAE_PWE: Indicates the mechanism(s) allowed for SAE PWE + * derivation in WPA3-Personal networks which are using SAE authentication. + * This is a u8 attribute that encapsulates one of the values from + * &enum nl80211_sae_pwe_mechanism. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3016,6 +3021,8 @@ enum nl80211_attrs { NL80211_ATTR_S1G_CAPABILITY, NL80211_ATTR_S1G_CAPABILITY_MASK, + NL80211_ATTR_SAE_PWE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -7124,4 +7131,23 @@ enum nl80211_unsol_bcast_probe_resp_attributes { NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX = __NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST - 1 }; + +/** + * enum nl80211_sae_pwe_mechanism - The mechanism(s) allowed for SAE PWE + * derivation. Applicable only when WPA3-Personal SAE authentication is + * used. + * + * @NL80211_SAE_PWE_UNSPECIFIED: not specified, used internally to indicate that + * attribute is not present from userspace. + * @NL80211_SAE_PWE_HUNT_AND_PECK: hunting-and-pecking loop only + * @NL80211_SAE_PWE_HASH_TO_ELEMENT: hash-to-element only + * @NL80211_SAE_PWE_BOTH: both hunting-and-pecking loop and hash-to-element + * can be used. + */ +enum nl80211_sae_pwe_mechanism { + NL80211_SAE_PWE_UNSPECIFIED, + NL80211_SAE_PWE_HUNT_AND_PECK, + NL80211_SAE_PWE_HASH_TO_ELEMENT, + NL80211_SAE_PWE_BOTH, +}; #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 554796a6c6fe..0928ecbe5bd6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -715,6 +715,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN), [NL80211_ATTR_S1G_CAPABILITY_MASK] = NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN), + [NL80211_ATTR_SAE_PWE] = + NLA_POLICY_RANGE(NLA_U8, NL80211_SAE_PWE_HUNT_AND_PECK, + NL80211_SAE_PWE_BOTH), }; /* policy for the key attributes */ @@ -9731,6 +9734,12 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, nla_len(info->attrs[NL80211_ATTR_SAE_PASSWORD]); } + if (info->attrs[NL80211_ATTR_SAE_PWE]) + settings->sae_pwe = + nla_get_u8(info->attrs[NL80211_ATTR_SAE_PWE]); + else + settings->sae_pwe = NL80211_SAE_PWE_UNSPECIFIED; + return 0; } -- cgit v1.3-15-g9ac1 From c4a30446a92a222d2f368254dcc4ab2fda0ba924 Mon Sep 17 00:00:00 2001 From: Rajkumar Manoharan Date: Fri, 16 Oct 2020 13:15:27 -0700 Subject: cfg80211: add support to configure HE MCS for beacon rate This allows an option to configure a single HE MCS beacon tx rate. Signed-off-by: Rajkumar Manoharan Link: https://lore.kernel.org/r/1602879327-29488-2-git-send-email-rmanohar@codeaurora.org Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 9 +++++++-- net/wireless/nl80211.c | 25 +++++++++++++++++++++++-- 2 files changed, 30 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 2d733effcdaf..e1e5b3d4dd81 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1750,8 +1750,9 @@ enum nl80211_commands { * specify just a single bitrate, which is to be used for the beacon. * The driver must also specify support for this with the extended * features NL80211_EXT_FEATURE_BEACON_RATE_LEGACY, - * NL80211_EXT_FEATURE_BEACON_RATE_HT and - * NL80211_EXT_FEATURE_BEACON_RATE_VHT. + * NL80211_EXT_FEATURE_BEACON_RATE_HT, + * NL80211_EXT_FEATURE_BEACON_RATE_VHT and + * NL80211_EXT_FEATURE_BEACON_RATE_HE. * * @NL80211_ATTR_FRAME_MATCH: A binary attribute which typically must contain * at least one byte, currently used with @NL80211_CMD_REGISTER_FRAME. @@ -5903,6 +5904,9 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP: Driver/device supports * unsolicited broadcast probe response transmission * + * @NL80211_EXT_FEATURE_BEACON_RATE_HE: Driver supports beacon rate + * configuration (AP/mesh) with HE rates. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5963,6 +5967,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SAE_OFFLOAD_AP, NL80211_EXT_FEATURE_FILS_DISCOVERY, NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP, + NL80211_EXT_FEATURE_BEACON_RATE_HE, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 3c73eb35b1e5..aad37e7c7f91 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4683,6 +4683,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, mask->control[band].ht_mcs)) return -EINVAL; } + if (tb[NL80211_TXRATE_VHT]) { if (!vht_set_mcs_mask( sband, @@ -4690,6 +4691,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, mask->control[band].vht_mcs)) return -EINVAL; } + if (tb[NL80211_TXRATE_GI]) { mask->control[band].gi = nla_get_u8(tb[NL80211_TXRATE_GI]); @@ -4701,6 +4703,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, nla_data(tb[NL80211_TXRATE_HE]), mask->control[band].he_mcs)) return -EINVAL; + if (tb[NL80211_TXRATE_HE_GI]) mask->control[band].he_gi = nla_get_u8(tb[NL80211_TXRATE_HE_GI]); @@ -4742,7 +4745,7 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev, enum nl80211_band band, struct cfg80211_bitrate_mask *beacon_rate) { - u32 count_ht, count_vht, i; + u32 count_ht, count_vht, count_he, i; u32 rate = beacon_rate->control[band].legacy; /* Allow only one rate */ @@ -4775,7 +4778,21 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev, return -EINVAL; } - if ((count_ht && count_vht) || (!rate && !count_ht && !count_vht)) + count_he = 0; + for (i = 0; i < NL80211_HE_NSS_MAX; i++) { + if (hweight16(beacon_rate->control[band].he_mcs[i]) > 1) { + return -EINVAL; + } else if (beacon_rate->control[band].he_mcs[i]) { + count_he++; + if (count_he > 1) + return -EINVAL; + } + if (count_he && rate) + return -EINVAL; + } + + if ((count_ht && count_vht && count_he) || + (!rate && !count_ht && !count_vht && !count_he)) return -EINVAL; if (rate && @@ -4790,6 +4807,10 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev, !wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_BEACON_RATE_VHT)) return -EINVAL; + if (count_he && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_RATE_HE)) + return -EINVAL; return 0; } -- cgit v1.3-15-g9ac1 From 4cf1bc1f10452065a29d576fc5693fc4fab5b919 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Fri, 6 Nov 2020 10:37:40 +0000 Subject: bpf: Implement task local storage Similar to bpf_local_storage for sockets and inodes add local storage for task_struct. The life-cycle of storage is managed with the life-cycle of the task_struct. i.e. the storage is destroyed along with the owning task with a callback to the bpf_task_storage_free from the task_free LSM hook. The BPF LSM allocates an __rcu pointer to the bpf_local_storage in the security blob which are now stackable and can co-exist with other LSMs. The userspace map operations can be done by using a pid fd as a key passed to the lookup, update and delete operations. Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201106103747.2780972-3-kpsingh@chromium.org --- include/linux/bpf_lsm.h | 23 +++ include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 39 +++++ kernel/bpf/Makefile | 1 + kernel/bpf/bpf_lsm.c | 4 + kernel/bpf/bpf_task_storage.c | 315 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 3 +- kernel/bpf/verifier.c | 10 ++ security/bpf/hooks.c | 2 + tools/include/uapi/linux/bpf.h | 39 +++++ 10 files changed, 436 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/bpf_task_storage.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index aaacb6aafc87..73226181b744 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -7,6 +7,7 @@ #ifndef _LINUX_BPF_LSM_H #define _LINUX_BPF_LSM_H +#include #include #include @@ -35,9 +36,21 @@ static inline struct bpf_storage_blob *bpf_inode( return inode->i_security + bpf_lsm_blob_sizes.lbs_inode; } +static inline struct bpf_storage_blob *bpf_task( + const struct task_struct *task) +{ + if (unlikely(!task->security)) + return NULL; + + return task->security + bpf_lsm_blob_sizes.lbs_task; +} + extern const struct bpf_func_proto bpf_inode_storage_get_proto; extern const struct bpf_func_proto bpf_inode_storage_delete_proto; +extern const struct bpf_func_proto bpf_task_storage_get_proto; +extern const struct bpf_func_proto bpf_task_storage_delete_proto; void bpf_inode_storage_free(struct inode *inode); +void bpf_task_storage_free(struct task_struct *task); #else /* !CONFIG_BPF_LSM */ @@ -53,10 +66,20 @@ static inline struct bpf_storage_blob *bpf_inode( return NULL; } +static inline struct bpf_storage_blob *bpf_task( + const struct task_struct *task) +{ + return NULL; +} + static inline void bpf_inode_storage_free(struct inode *inode) { } +static inline void bpf_task_storage_free(struct task_struct *task) +{ +} + #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 2e6f568377f1..99f7fd657d87 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -109,6 +109,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) #endif #ifdef CONFIG_BPF_LSM BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e6ceac3f7d62..f4037b2161a6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -157,6 +157,7 @@ enum bpf_map_type { BPF_MAP_TYPE_STRUCT_OPS, BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, + BPF_MAP_TYPE_TASK_STORAGE, }; /* Note that tracing related programs such as @@ -3742,6 +3743,42 @@ union bpf_attr { * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. + * + * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *task*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *task* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this + * helper enforces the key must be an task_struct and the map must also + * be a **BPF_MAP_TYPE_TASK_STORAGE**. + * + * Underneath, the value is stored locally at *task* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *task*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task) + * Description + * Delete a bpf_local_storage from a *task*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3900,6 +3937,8 @@ union bpf_attr { FN(bpf_per_cpu_ptr), \ FN(bpf_this_cpu_ptr), \ FN(redirect_peer), \ + FN(task_storage_get), \ + FN(task_storage_delete), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index bdc8cd1b6767..f0b93ced5a7f 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_i obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o +obj-${CONFIG_BPF_LSM} += bpf_task_storage.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index cd8a617f2109..e92c51bebb47 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -63,6 +63,10 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: return &bpf_spin_unlock_proto; + case BPF_FUNC_task_storage_get: + return &bpf_task_storage_get_proto; + case BPF_FUNC_task_storage_delete: + return &bpf_task_storage_delete_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c new file mode 100644 index 000000000000..39a45fba4fb0 --- /dev/null +++ b/kernel/bpf/bpf_task_storage.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 Facebook + * Copyright 2020 Google LLC. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +DEFINE_BPF_STORAGE_CACHE(task_cache); + +static struct bpf_local_storage __rcu **task_storage_ptr(void *owner) +{ + struct task_struct *task = owner; + struct bpf_storage_blob *bsb; + + bsb = bpf_task(task); + if (!bsb) + return NULL; + return &bsb->storage; +} + +static struct bpf_local_storage_data * +task_storage_lookup(struct task_struct *task, struct bpf_map *map, + bool cacheit_lockit) +{ + struct bpf_local_storage *task_storage; + struct bpf_local_storage_map *smap; + struct bpf_storage_blob *bsb; + + bsb = bpf_task(task); + if (!bsb) + return NULL; + + task_storage = rcu_dereference(bsb->storage); + if (!task_storage) + return NULL; + + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(task_storage, smap, cacheit_lockit); +} + +void bpf_task_storage_free(struct task_struct *task) +{ + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *local_storage; + bool free_task_storage = false; + struct bpf_storage_blob *bsb; + struct hlist_node *n; + + bsb = bpf_task(task); + if (!bsb) + return; + + rcu_read_lock(); + + local_storage = rcu_dereference(bsb->storage); + if (!local_storage) { + rcu_read_unlock(); + return; + } + + /* Neither the bpf_prog nor the bpf-map's syscall + * could be modifying the local_storage->list now. + * Thus, no elem can be added-to or deleted-from the + * local_storage->list by the bpf_prog or by the bpf-map's syscall. + * + * It is racing with bpf_local_storage_map_free() alone + * when unlinking elem from the local_storage->list and + * the map's bucket->list. + */ + raw_spin_lock_bh(&local_storage->lock); + hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { + /* Always unlink from map before unlinking from + * local_storage. + */ + bpf_selem_unlink_map(selem); + free_task_storage = bpf_selem_unlink_storage_nolock( + local_storage, selem, false); + } + raw_spin_unlock_bh(&local_storage->lock); + rcu_read_unlock(); + + /* free_task_storage should always be true as long as + * local_storage->list was non-empty. + */ + if (free_task_storage) + kfree_rcu(local_storage, rcu); +} + +static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_local_storage_data *sdata; + struct task_struct *task; + unsigned int f_flags; + struct pid *pid; + int fd, err; + + fd = *(int *)key; + pid = pidfd_get_pid(fd, &f_flags); + if (IS_ERR(pid)) + return ERR_CAST(pid); + + /* We should be in an RCU read side critical section, it should be safe + * to call pid_task. + */ + WARN_ON_ONCE(!rcu_read_lock_held()); + task = pid_task(pid, PIDTYPE_PID); + if (!task) { + err = -ENOENT; + goto out; + } + + sdata = task_storage_lookup(task, map, true); + put_pid(pid); + return sdata ? sdata->data : NULL; +out: + put_pid(pid); + return ERR_PTR(err); +} + +static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct bpf_local_storage_data *sdata; + struct task_struct *task; + unsigned int f_flags; + struct pid *pid; + int fd, err; + + fd = *(int *)key; + pid = pidfd_get_pid(fd, &f_flags); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + /* We should be in an RCU read side critical section, it should be safe + * to call pid_task. + */ + WARN_ON_ONCE(!rcu_read_lock_held()); + task = pid_task(pid, PIDTYPE_PID); + if (!task) { + err = -ENOENT; + goto out; + } + + sdata = bpf_local_storage_update( + task, (struct bpf_local_storage_map *)map, value, map_flags); + + err = PTR_ERR_OR_ZERO(sdata); +out: + put_pid(pid); + return err; +} + +static int task_storage_delete(struct task_struct *task, struct bpf_map *map) +{ + struct bpf_local_storage_data *sdata; + + sdata = task_storage_lookup(task, map, false); + if (!sdata) + return -ENOENT; + + bpf_selem_unlink(SELEM(sdata)); + + return 0; +} + +static int bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct task_struct *task; + unsigned int f_flags; + struct pid *pid; + int fd, err; + + fd = *(int *)key; + pid = pidfd_get_pid(fd, &f_flags); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + /* We should be in an RCU read side critical section, it should be safe + * to call pid_task. + */ + WARN_ON_ONCE(!rcu_read_lock_held()); + task = pid_task(pid, PIDTYPE_PID); + if (!task) { + err = -ENOENT; + goto out; + } + + err = task_storage_delete(task, map); +out: + put_pid(pid); + return err; +} + +BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, + task, void *, value, u64, flags) +{ + struct bpf_local_storage_data *sdata; + + if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) + return (unsigned long)NULL; + + /* explicitly check that the task_storage_ptr is not + * NULL as task_storage_lookup returns NULL in this case and + * bpf_local_storage_update expects the owner to have a + * valid storage pointer. + */ + if (!task_storage_ptr(task)) + return (unsigned long)NULL; + + sdata = task_storage_lookup(task, map, true); + if (sdata) + return (unsigned long)sdata->data; + + /* This helper must only be called from places where the lifetime of the task + * is guaranteed. Either by being refcounted or by being protected + * by an RCU read-side critical section. + */ + if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { + sdata = bpf_local_storage_update( + task, (struct bpf_local_storage_map *)map, value, + BPF_NOEXIST); + return IS_ERR(sdata) ? (unsigned long)NULL : + (unsigned long)sdata->data; + } + + return (unsigned long)NULL; +} + +BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, + task) +{ + /* This helper must only be called from places where the lifetime of the task + * is guaranteed. Either by being refcounted or by being protected + * by an RCU read-side critical section. + */ + return task_storage_delete(task, map); +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -ENOTSUPP; +} + +static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr) +{ + struct bpf_local_storage_map *smap; + + smap = bpf_local_storage_map_alloc(attr); + if (IS_ERR(smap)) + return ERR_CAST(smap); + + smap->cache_idx = bpf_local_storage_cache_idx_get(&task_cache); + return &smap->map; +} + +static void task_storage_map_free(struct bpf_map *map) +{ + struct bpf_local_storage_map *smap; + + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(&task_cache, smap->cache_idx); + bpf_local_storage_map_free(smap); +} + +static int task_storage_map_btf_id; +const struct bpf_map_ops task_storage_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = task_storage_map_alloc, + .map_free = task_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_pid_task_storage_lookup_elem, + .map_update_elem = bpf_pid_task_storage_update_elem, + .map_delete_elem = bpf_pid_task_storage_delete_elem, + .map_check_btf = bpf_local_storage_map_check_btf, + .map_btf_name = "bpf_local_storage_map", + .map_btf_id = &task_storage_map_btf_id, + .map_owner_storage_ptr = task_storage_ptr, +}; + +BTF_ID_LIST_SINGLE(bpf_task_storage_btf_ids, struct, task_struct) + +const struct bpf_func_proto bpf_task_storage_get_proto = { + .func = bpf_task_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_btf_id = &bpf_task_storage_btf_ids[0], + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_func_proto bpf_task_storage_delete_proto = { + .func = bpf_task_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_btf_id = &bpf_task_storage_btf_ids[0], +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8f50c9c19f1b..f3fe9f53f93c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -773,7 +773,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && - map->map_type != BPF_MAP_TYPE_INODE_STORAGE) + map->map_type != BPF_MAP_TYPE_INODE_STORAGE && + map->map_type != BPF_MAP_TYPE_TASK_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f863aa84d0a2..00960f6a83ec 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4469,6 +4469,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_inode_storage_delete) goto error; break; + case BPF_MAP_TYPE_TASK_STORAGE: + if (func_id != BPF_FUNC_task_storage_get && + func_id != BPF_FUNC_task_storage_delete) + goto error; + break; default: break; } @@ -4547,6 +4552,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE) goto error; break; + case BPF_FUNC_task_storage_get: + case BPF_FUNC_task_storage_delete: + if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) + goto error; + break; default: break; } diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c index 788667d582ae..e5971fa74fd7 100644 --- a/security/bpf/hooks.c +++ b/security/bpf/hooks.c @@ -12,6 +12,7 @@ static struct security_hook_list bpf_lsm_hooks[] __lsm_ro_after_init = { #include #undef LSM_HOOK LSM_HOOK_INIT(inode_free_security, bpf_inode_storage_free), + LSM_HOOK_INIT(task_free, bpf_task_storage_free), }; static int __init bpf_lsm_init(void) @@ -23,6 +24,7 @@ static int __init bpf_lsm_init(void) struct lsm_blob_sizes bpf_lsm_blob_sizes __lsm_ro_after_init = { .lbs_inode = sizeof(struct bpf_storage_blob), + .lbs_task = sizeof(struct bpf_storage_blob), }; DEFINE_LSM(bpf) = { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e6ceac3f7d62..f4037b2161a6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -157,6 +157,7 @@ enum bpf_map_type { BPF_MAP_TYPE_STRUCT_OPS, BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, + BPF_MAP_TYPE_TASK_STORAGE, }; /* Note that tracing related programs such as @@ -3742,6 +3743,42 @@ union bpf_attr { * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. + * + * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *task*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *task* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this + * helper enforces the key must be an task_struct and the map must also + * be a **BPF_MAP_TYPE_TASK_STORAGE**. + * + * Underneath, the value is stored locally at *task* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *task*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task) + * Description + * Delete a bpf_local_storage from a *task*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3900,6 +3937,8 @@ union bpf_attr { FN(bpf_per_cpu_ptr), \ FN(bpf_this_cpu_ptr), \ FN(redirect_peer), \ + FN(task_storage_get), \ + FN(task_storage_delete), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.3-15-g9ac1 From 3ca1032ab7ab010eccb107aa515598788f7d93bb Mon Sep 17 00:00:00 2001 From: KP Singh Date: Fri, 6 Nov 2020 10:37:43 +0000 Subject: bpf: Implement get_current_task_btf and RET_PTR_TO_BTF_ID The currently available bpf_get_current_task returns an unsigned integer which can be used along with BPF_CORE_READ to read data from the task_struct but still cannot be used as an input argument to a helper that accepts an ARG_PTR_TO_BTF_ID of type task_struct. In order to implement this helper a new return type, RET_PTR_TO_BTF_ID, is added. This is similar to RET_PTR_TO_BTF_ID_OR_NULL but does not require checking the nullness of returned pointer. Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201106103747.2780972-6-kpsingh@chromium.org --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 9 +++++++++ kernel/bpf/verifier.c | 7 +++++-- kernel/trace/bpf_trace.c | 16 ++++++++++++++++ tools/include/uapi/linux/bpf.h | 9 +++++++++ 5 files changed, 40 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2fffd30e13ac..73d5381a5d5c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -310,6 +310,7 @@ enum bpf_return_type { RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */ RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ + RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f4037b2161a6..9879d6793e90 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3779,6 +3779,14 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf_local_storage cannot be found. + * + * struct task_struct *bpf_get_current_task_btf(void) + * Description + * Return a BTF pointer to the "current" task. + * This pointer can also be used in helpers that accept an + * *ARG_PTR_TO_BTF_ID* of type *task_struct*. + * Return + * Pointer to the current task. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3939,6 +3947,7 @@ union bpf_attr { FN(redirect_peer), \ FN(task_storage_get), \ FN(task_storage_delete), \ + FN(get_current_task_btf), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 00960f6a83ec..10da26e55130 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5186,11 +5186,14 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } - } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) { + } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL || + fn->ret_type == RET_PTR_TO_BTF_ID) { int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL; + regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ? + PTR_TO_BTF_ID : + PTR_TO_BTF_ID_OR_NULL; ret_btf_id = *fn->ret_btf_id; if (ret_btf_id == 0) { verbose(env, "invalid return type %d of func %s#%d\n", diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4517c8b66518..e4515b0f62a8 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1022,6 +1022,20 @@ const struct bpf_func_proto bpf_get_current_task_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_get_current_task_btf) +{ + return (unsigned long) current; +} + +BTF_ID_LIST_SINGLE(bpf_get_current_btf_ids, struct, task_struct) + +static const struct bpf_func_proto bpf_get_current_task_btf_proto = { + .func = bpf_get_current_task_btf, + .gpl_only = true, + .ret_type = RET_PTR_TO_BTF_ID, + .ret_btf_id = &bpf_get_current_btf_ids[0], +}; + BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); @@ -1265,6 +1279,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; + case BPF_FUNC_get_current_task_btf: + return &bpf_get_current_task_btf_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f4037b2161a6..9879d6793e90 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3779,6 +3779,14 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf_local_storage cannot be found. + * + * struct task_struct *bpf_get_current_task_btf(void) + * Description + * Return a BTF pointer to the "current" task. + * This pointer can also be used in helpers that accept an + * *ARG_PTR_TO_BTF_ID* of type *task_struct*. + * Return + * Pointer to the current task. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3939,6 +3947,7 @@ union bpf_attr { FN(redirect_peer), \ FN(task_storage_get), \ FN(task_storage_delete), \ + FN(get_current_task_btf), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.3-15-g9ac1 From 968a83f8cf6fd5a107289c57ee3197a52c72f02c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 4 Nov 2020 15:30:27 +0200 Subject: rtnetlink: Add RTNH_F_TRAP flag The flag indicates to user space that the nexthop is not programmed to forward packets in hardware, but rather to trap them to the CPU. This is needed, for example, when the MAC of the nexthop neighbour is not resolved and packets should reach the CPU to trigger neighbour resolution. The flag will be used in subsequent patches by netdevsim to test nexthop objects programming to device drivers and in the future by mlxsw as well. Changes since RFC: * Reword commit message Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/uapi/linux/rtnetlink.h | 6 ++++-- net/ipv4/fib_semantics.c | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index d1325ffb0060..2ffbef5da6c1 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -396,11 +396,13 @@ struct rtnexthop { #define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */ #define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */ #define RTNH_F_ONLINK 4 /* Gateway is forced on link */ -#define RTNH_F_OFFLOAD 8 /* offloaded route */ +#define RTNH_F_OFFLOAD 8 /* Nexthop is offloaded */ #define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */ #define RTNH_F_UNRESOLVED 32 /* The entry is unresolved (ipmr) */ +#define RTNH_F_TRAP 64 /* Nexthop is trapping packets */ -#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD) +#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | \ + RTNH_F_OFFLOAD | RTNH_F_TRAP) /* Macros to handle hexthops */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 1f75dc686b6b..f70b9a0c4957 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1644,6 +1644,8 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc, *flags |= (nhc->nhc_flags & RTNH_F_ONLINK); if (nhc->nhc_flags & RTNH_F_OFFLOAD) *flags |= RTNH_F_OFFLOAD; + if (nhc->nhc_flags & RTNH_F_TRAP) + *flags |= RTNH_F_TRAP; if (!skip_oif && nhc->nhc_dev && nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex)) -- cgit v1.3-15-g9ac1 From a3ce2b109a59ee9670706ae8126dcc04cfe261cd Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 5 Nov 2020 20:49:14 -0500 Subject: net: udp: introduce UDP_MIB_MEMERRORS for udp_mem When udp_memory_allocated is at the limit, __udp_enqueue_schedule_skb will return a -ENOBUFS, and skb will be dropped in __udp_queue_rcv_skb without any counters being done. It's hard to find out what happened once this happen. So we introduce a UDP_MIB_MEMERRORS to do this job. Well, this change looks friendly to the existing users, such as netstat: $ netstat -u -s Udp: 0 packets received 639 packets to unknown port received. 158689 packet receive errors 180022 packets sent RcvbufErrors: 20930 MemErrors: 137759 UdpLite: IpExt: InOctets: 257426235 OutOctets: 257460598 InNoECTPkts: 181177 v2: - Fix some alignment problems Signed-off-by: Menglong Dong Link: https://lore.kernel.org/r/1604627354-43207-1-git-send-email-dong.menglong@zte.com.cn Signed-off-by: Jakub Kicinski --- include/uapi/linux/snmp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/udp.c | 3 +++ net/ipv6/proc.c | 2 ++ net/ipv6/udp.c | 3 +++ 5 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index f84e7bcad6de..26fc60ce9298 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -159,6 +159,7 @@ enum UDP_MIB_SNDBUFERRORS, /* SndbufErrors */ UDP_MIB_CSUMERRORS, /* InCsumErrors */ UDP_MIB_IGNOREDMULTI, /* IgnoredMulti */ + UDP_MIB_MEMERRORS, /* MemErrors */ __UDP_MIB_MAX }; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 8d5e1695b9aa..63cd370ea29d 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -167,6 +167,7 @@ static const struct snmp_mib snmp4_udp_list[] = { SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS), SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS), SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI), + SNMP_MIB_ITEM("MemErrors", UDP_MIB_MEMERRORS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ca04a8a35e52..1e2e73accd11 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2038,6 +2038,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (rc == -ENOMEM) UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); + else + UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS, + is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); trace_udp_fail_queue_rcv_skb(rc, sk); diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index bbff3e02e302..d6306aa46bb1 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -126,6 +126,7 @@ static const struct snmp_mib snmp6_udp6_list[] = { SNMP_MIB_ITEM("Udp6SndbufErrors", UDP_MIB_SNDBUFERRORS), SNMP_MIB_ITEM("Udp6InCsumErrors", UDP_MIB_CSUMERRORS), SNMP_MIB_ITEM("Udp6IgnoredMulti", UDP_MIB_IGNOREDMULTI), + SNMP_MIB_ITEM("Udp6MemErrors", UDP_MIB_MEMERRORS), SNMP_MIB_SENTINEL }; @@ -137,6 +138,7 @@ static const struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_ITEM("UdpLite6RcvbufErrors", UDP_MIB_RCVBUFERRORS), SNMP_MIB_ITEM("UdpLite6SndbufErrors", UDP_MIB_SNDBUFERRORS), SNMP_MIB_ITEM("UdpLite6InCsumErrors", UDP_MIB_CSUMERRORS), + SNMP_MIB_ITEM("UdpLite6MemErrors", UDP_MIB_MEMERRORS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index cde9b8874d4b..559611bef0e6 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -637,6 +637,9 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (rc == -ENOMEM) UDP6_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); + else + UDP6_INC_STATS(sock_net(sk), + UDP_MIB_MEMERRORS, is_udplite); UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; -- cgit v1.3-15-g9ac1 From 9c661b0b85444e426d3f23250305eeb16f6ffe88 Mon Sep 17 00:00:00 2001 From: Tanner Love Date: Fri, 6 Nov 2020 13:07:40 -0500 Subject: net/packet: make packet_fanout.arr size configurable up to 64K One use case of PACKET_FANOUT is lockless reception with one socket per CPU. 256 is a practical limit on increasingly many machines. Increase PACKET_FANOUT_MAX to 64K. Expand setsockopt PACKET_FANOUT to take an extra argument max_num_members. Also explicitly define a fanout_args struct, instead of implicitly casting to an integer. This documents the API and simplifies the control flow. If max_num_members is not specified or is set to 0, then 256 is used, same as before. Signed-off-by: Tanner Love Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_packet.h | 12 ++++++++++++ net/packet/af_packet.c | 37 +++++++++++++++++++++++++------------ net/packet/internal.h | 5 +++-- 3 files changed, 40 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 3d884d68eb30..c07caf7b40db 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -2,6 +2,7 @@ #ifndef __LINUX_IF_PACKET_H #define __LINUX_IF_PACKET_H +#include #include struct sockaddr_pkt { @@ -296,6 +297,17 @@ struct packet_mreq { unsigned char mr_address[8]; }; +struct fanout_args { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u16 id; + __u16 type_flags; +#else + __u16 type_flags; + __u16 id; +#endif + __u32 max_num_members; +}; + #define PACKET_MR_MULTICAST 0 #define PACKET_MR_PROMISC 1 #define PACKET_MR_ALLMULTI 2 diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index cefbd50c1090..62ebfaa7adcb 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1636,13 +1636,15 @@ static bool fanout_find_new_id(struct sock *sk, u16 *new_id) return false; } -static int fanout_add(struct sock *sk, u16 id, u16 type_flags) +static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); + u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; + u16 id = args->id; int err; switch (type) { @@ -1700,11 +1702,21 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) } } err = -EINVAL; - if (match && match->flags != flags) - goto out; - if (!match) { + if (match) { + if (match->flags != flags) + goto out; + if (args->max_num_members && + args->max_num_members != match->max_num_members) + goto out; + } else { + if (args->max_num_members > PACKET_FANOUT_MAX) + goto out; + if (!args->max_num_members) + /* legacy PACKET_FANOUT_MAX */ + args->max_num_members = 256; err = -ENOMEM; - match = kzalloc(sizeof(*match), GFP_KERNEL); + match = kvzalloc(struct_size(match, arr, args->max_num_members), + GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); @@ -1720,6 +1732,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.id_match = match_fanout_group; + match->max_num_members = args->max_num_members; list_add(&match->list, &fanout_list); } err = -EINVAL; @@ -1730,7 +1743,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; - if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) { + if (refcount_read(&match->sk_ref) < match->max_num_members) { __dev_remove_pack(&po->prot_hook); po->fanout = match; po->rollover = rollover; @@ -1744,7 +1757,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); - kfree(match); + kvfree(match); } out: @@ -3075,7 +3088,7 @@ static int packet_release(struct socket *sock) kfree(po->rollover); if (f) { fanout_release_data(f); - kfree(f); + kvfree(f); } /* * Now the socket is dead. No more input will appear. @@ -3866,14 +3879,14 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, } case PACKET_FANOUT: { - int val; + struct fanout_args args = { 0 }; - if (optlen != sizeof(val)) + if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; - if (copy_from_sockptr(&val, optval, sizeof(val))) + if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; - return fanout_add(sk, val & 0xffff, val >> 16); + return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { diff --git a/net/packet/internal.h b/net/packet/internal.h index fd41ecb7f605..baafc3f3fa25 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -77,11 +77,12 @@ struct packet_ring_buffer { }; extern struct mutex fanout_mutex; -#define PACKET_FANOUT_MAX 256 +#define PACKET_FANOUT_MAX (1 << 16) struct packet_fanout { possible_net_t net; unsigned int num_members; + u32 max_num_members; u16 id; u8 type; u8 flags; @@ -90,10 +91,10 @@ struct packet_fanout { struct bpf_prog __rcu *bpf_prog; }; struct list_head list; - struct sock *arr[PACKET_FANOUT_MAX]; spinlock_t lock; refcount_t sk_ref; struct packet_type prot_hook ____cacheline_aligned_in_smp; + struct sock *arr[]; }; struct packet_rollover { -- cgit v1.3-15-g9ac1 From 5329722057d41aebc31e391907a501feaa42f7d9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 9 Nov 2020 17:19:29 -0800 Subject: bpf: Assign ID to vmlinux BTF and return extra info for BTF in GET_OBJ_INFO Allocate ID for vmlinux BTF. This makes it visible when iterating over all BTF objects in the system. To allow distinguishing vmlinux BTF (and later kernel module BTF) from user-provided BTFs, expose extra kernel_btf flag, as well as BTF name ("vmlinux" for vmlinux BTF, will equal to module's name for module BTF). We might want to later allow specifying BTF name for user-provided BTFs as well, if that makes sense. But currently this is reserved only for in-kernel BTFs. Having in-kernel BTFs exposed IDs will allow to extend BPF APIs that require in-kernel BTF type with ability to specify BTF types from kernel modules, not just vmlinux BTF. This will be implemented in a follow up patch set for fentry/fexit/fmod_ret/lsm/etc. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201110011932.3201430-3-andrii@kernel.org --- include/uapi/linux/bpf.h | 3 +++ kernel/bpf/btf.c | 43 +++++++++++++++++++++++++++++++++++++++--- tools/include/uapi/linux/bpf.h | 3 +++ 3 files changed, 46 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9879d6793e90..162999b12790 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4466,6 +4466,9 @@ struct bpf_btf_info { __aligned_u64 btf; __u32 btf_size; __u32 id; + __aligned_u64 name; + __u32 name_len; + __u32 kernel_btf; } __attribute__((aligned(8))); struct bpf_link_info { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 727c1c27053f..856585db7aa7 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -214,6 +214,8 @@ struct btf { struct btf *base_btf; u32 start_id; /* first type ID in this BTF (0 for base BTF) */ u32 start_str_off; /* first string offset (0 for base BTF) */ + char name[MODULE_NAME_LEN]; + bool kernel_btf; }; enum verifier_phase { @@ -4429,6 +4431,8 @@ struct btf *btf_parse_vmlinux(void) btf->data = __start_BTF; btf->data_size = __stop_BTF - __start_BTF; + btf->kernel_btf = true; + snprintf(btf->name, sizeof(btf->name), "vmlinux"); err = btf_parse_hdr(env); if (err) @@ -4454,8 +4458,13 @@ struct btf *btf_parse_vmlinux(void) bpf_struct_ops_init(btf, log); - btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); + + err = btf_alloc_id(btf); + if (err) + goto errout; + + btf_verifier_env_free(env); return btf; errout: @@ -5553,7 +5562,9 @@ int btf_get_info_by_fd(const struct btf *btf, struct bpf_btf_info info; u32 info_copy, btf_copy; void __user *ubtf; - u32 uinfo_len; + char __user *uname; + u32 uinfo_len, uname_len, name_len; + int ret = 0; uinfo = u64_to_user_ptr(attr->info.info); uinfo_len = attr->info.info_len; @@ -5570,11 +5581,37 @@ int btf_get_info_by_fd(const struct btf *btf, return -EFAULT; info.btf_size = btf->data_size; + info.kernel_btf = btf->kernel_btf; + + uname = u64_to_user_ptr(info.name); + uname_len = info.name_len; + if (!uname ^ !uname_len) + return -EINVAL; + + name_len = strlen(btf->name); + info.name_len = name_len; + + if (uname) { + if (uname_len >= name_len + 1) { + if (copy_to_user(uname, btf->name, name_len + 1)) + return -EFAULT; + } else { + char zero = '\0'; + + if (copy_to_user(uname, btf->name, uname_len - 1)) + return -EFAULT; + if (put_user(zero, uname + uname_len - 1)) + return -EFAULT; + /* let user-space know about too short buffer */ + ret = -ENOSPC; + } + } + if (copy_to_user(uinfo, &info, info_copy) || put_user(info_copy, &uattr->info.info_len)) return -EFAULT; - return 0; + return ret; } int btf_get_fd_by_id(u32 id) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9879d6793e90..162999b12790 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4466,6 +4466,9 @@ struct bpf_btf_info { __aligned_u64 btf; __u32 btf_size; __u32 id; + __aligned_u64 name; + __u32 name_len; + __u32 kernel_btf; } __attribute__((aligned(8))); struct bpf_link_info { -- cgit v1.3-15-g9ac1 From e7e0517c1004991908bc7f20b4c9a7b678277358 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 9 Nov 2020 10:57:47 +0100 Subject: cfg80211: remove WDS code Remove all the code that was there to configure WDS interfaces, now that there's no way to reach it anymore. Link: https://lore.kernel.org/r/20201109105103.8f5b98e4068d.I5f5129041649ef2862b69683574bb3344743727b@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 5 ----- include/uapi/linux/nl80211.h | 3 ++- net/wireless/chan.c | 6 +++--- net/wireless/core.c | 8 +------ net/wireless/nl80211.c | 36 ++----------------------------- net/wireless/rdev-ops.h | 10 --------- net/wireless/trace.h | 5 ----- net/wireless/util.c | 5 ++--- net/wireless/wext-compat.c | 51 -------------------------------------------- 9 files changed, 10 insertions(+), 119 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0ba8d1fa6eb9..4ff804a8bc1d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3745,8 +3745,6 @@ struct mgmt_frame_regs { * @get_tx_power: store the current TX power into the dbm variable; * return 0 if successful * - * @set_wds_peer: set the WDS peer for a WDS interface - * * @rfkill_poll: polls the hw rfkill line, use cfg80211 reporting * functions to adjust rfkill hw state * @@ -4067,9 +4065,6 @@ struct cfg80211_ops { int (*get_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev, int *dbm); - int (*set_wds_peer)(struct wiphy *wiphy, struct net_device *dev, - const u8 *addr); - void (*rfkill_poll)(struct wiphy *wiphy); #ifdef CONFIG_NL80211_TESTMODE diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e1e5b3d4dd81..3e0d4a038ab6 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -757,7 +757,8 @@ * of any other interfaces, and other interfaces will again take * precedence when they are used. * - * @NL80211_CMD_SET_WDS_PEER: Set the MAC address of the peer on a WDS interface. + * @NL80211_CMD_SET_WDS_PEER: Set the MAC address of the peer on a WDS interface + * (no longer supported). * * @NL80211_CMD_SET_MULTICAST_TO_UNICAST: Configure if this AP should perform * multicast to unicast conversion. When enabled, all multicast packets diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 22d1779ab2b1..e4030f1fbc60 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -530,10 +530,10 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: break; + case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: WARN_ON(1); @@ -677,12 +677,12 @@ bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev) case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_P2P_DEVICE: /* Can NAN type be considered as beaconing interface? */ case NL80211_IFTYPE_NAN: break; case NL80211_IFTYPE_UNSPECIFIED: + case NL80211_IFTYPE_WDS: case NUM_NL80211_IFTYPES: WARN_ON(1); } @@ -1324,12 +1324,12 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, break; case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: /* these interface types don't really have a channel */ return; case NL80211_IFTYPE_UNSPECIFIED: + case NL80211_IFTYPE_WDS: case NUM_NL80211_IFTYPES: WARN_ON(1); } diff --git a/net/wireless/core.c b/net/wireless/core.c index 9f23923e8d29..f6b744e91ff4 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -631,10 +631,8 @@ static int wiphy_verify_combinations(struct wiphy *wiphy) return -EINVAL; } -#ifndef CONFIG_WIRELESS_WDS if (WARN_ON(all_iftypes & BIT(NL80211_IFTYPE_WDS))) return -EINVAL; -#endif /* You can't even choose that many! */ if (WARN_ON(cnt < c->max_interfaces)) @@ -675,10 +673,8 @@ int wiphy_register(struct wiphy *wiphy) !(wiphy->nan_supported_bands & BIT(NL80211_BAND_2GHZ))))) return -EINVAL; -#ifndef CONFIG_WIRELESS_WDS if (WARN_ON(wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS))) return -EINVAL; -#endif if (WARN_ON(wiphy->pmsr_capa && !wiphy->pmsr_capa->ftm.supported)) return -EINVAL; @@ -1202,9 +1198,6 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_OCB: __cfg80211_leave_ocb(rdev, dev); break; - case NL80211_IFTYPE_WDS: - /* must be handled by mac80211/driver, has no APIs */ - break; case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: /* cannot happen, has no netdev */ @@ -1214,6 +1207,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, /* nothing to do */ break; case NL80211_IFTYPE_UNSPECIFIED: + case NL80211_IFTYPE_WDS: case NUM_NL80211_IFTYPES: /* invalid */ break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index aad37e7c7f91..b76bdc8417c4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1885,7 +1885,6 @@ static int nl80211_add_commands_unsplit(struct cfg80211_registered_device *rdev, if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL)) goto nla_put_failure; } - CMD(set_wds_peer, SET_WDS_PEER); if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) { CMD(tdls_mgmt, TDLS_MGMT); CMD(tdls_oper, TDLS_OPER); @@ -2863,8 +2862,8 @@ static int parse_txq_params(struct nlattr *tb[], static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) { /* - * You can only set the channel explicitly for WDS interfaces, - * all others have their channel managed via their respective + * You can only set the channel explicitly for some interfaces, + * most have their channel managed via their respective * "establish a connection" command (connect, join, ...) * * For AP/GO and mesh mode, the channel can be set with the @@ -3069,29 +3068,6 @@ static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info) return __nl80211_set_channel(rdev, netdev, info); } -static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info) -{ - struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct net_device *dev = info->user_ptr[1]; - struct wireless_dev *wdev = dev->ieee80211_ptr; - const u8 *bssid; - - if (!info->attrs[NL80211_ATTR_MAC]) - return -EINVAL; - - if (netif_running(dev)) - return -EBUSY; - - if (!rdev->ops->set_wds_peer) - return -EOPNOTSUPP; - - if (wdev->iftype != NL80211_IFTYPE_WDS) - return -EOPNOTSUPP; - - bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - return rdev_set_wds_peer(rdev, dev, bssid); -} - static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev; @@ -15173,14 +15149,6 @@ static const struct genl_small_ops nl80211_small_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, }, - { - .cmd = NL80211_CMD_SET_WDS_PEER, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = nl80211_set_wds_peer, - .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, - }, { .cmd = NL80211_CMD_JOIN_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 950d57494168..5e2f349c92a8 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -582,16 +582,6 @@ static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev, return ret; } -static inline int rdev_set_wds_peer(struct cfg80211_registered_device *rdev, - struct net_device *dev, const u8 *addr) -{ - int ret; - trace_rdev_set_wds_peer(&rdev->wiphy, dev, addr); - ret = rdev->ops->set_wds_peer(&rdev->wiphy, dev, addr); - trace_rdev_return_int(&rdev->wiphy, ret); - return ret; -} - static inline int rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev, struct net_device *dev, diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 6e218a0acd4e..817c6fef13be 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -838,11 +838,6 @@ DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_del_mpath, TP_ARGS(wiphy, netdev, mac) ); -DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_set_wds_peer, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac), - TP_ARGS(wiphy, netdev, mac) -); - TRACE_EVENT(rdev_dump_station, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx, u8 *mac), diff --git a/net/wireless/util.c b/net/wireless/util.c index 5b6c80ae564a..5af88037f1fb 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -550,8 +550,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, return -1; break; case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS): - if (unlikely(iftype != NL80211_IFTYPE_WDS && - iftype != NL80211_IFTYPE_MESH_POINT && + if (unlikely(iftype != NL80211_IFTYPE_MESH_POINT && iftype != NL80211_IFTYPE_AP_VLAN && iftype != NL80211_IFTYPE_STATION)) return -1; @@ -1051,7 +1050,6 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MESH_POINT: /* bridging OK */ break; @@ -1063,6 +1061,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, /* not happening */ break; case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_NAN: WARN_ON(1); break; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 78f2927ead7f..b84a345b2653 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -49,9 +49,6 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, case IW_MODE_ADHOC: type = NL80211_IFTYPE_ADHOC; break; - case IW_MODE_REPEAT: - type = NL80211_IFTYPE_WDS; - break; case IW_MODE_MONITOR: type = NL80211_IFTYPE_MONITOR; break; @@ -1150,50 +1147,6 @@ static int cfg80211_wext_giwpower(struct net_device *dev, return 0; } -static int cfg80211_wds_wext_siwap(struct net_device *dev, - struct iw_request_info *info, - struct sockaddr *addr, char *extra) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - int err; - - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS)) - return -EINVAL; - - if (addr->sa_family != ARPHRD_ETHER) - return -EINVAL; - - if (netif_running(dev)) - return -EBUSY; - - if (!rdev->ops->set_wds_peer) - return -EOPNOTSUPP; - - err = rdev_set_wds_peer(rdev, dev, (u8 *)&addr->sa_data); - if (err) - return err; - - memcpy(&wdev->wext.bssid, (u8 *) &addr->sa_data, ETH_ALEN); - - return 0; -} - -static int cfg80211_wds_wext_giwap(struct net_device *dev, - struct iw_request_info *info, - struct sockaddr *addr, char *extra) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS)) - return -EINVAL; - - addr->sa_family = ARPHRD_ETHER; - memcpy(&addr->sa_data, wdev->wext.bssid, ETH_ALEN); - - return 0; -} - static int cfg80211_wext_siwrate(struct net_device *dev, struct iw_request_info *info, struct iw_param *rate, char *extra) @@ -1371,8 +1324,6 @@ static int cfg80211_wext_siwap(struct net_device *dev, return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); case NL80211_IFTYPE_STATION: return cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); - case NL80211_IFTYPE_WDS: - return cfg80211_wds_wext_siwap(dev, info, ap_addr, extra); default: return -EOPNOTSUPP; } @@ -1389,8 +1340,6 @@ static int cfg80211_wext_giwap(struct net_device *dev, return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); case NL80211_IFTYPE_STATION: return cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); - case NL80211_IFTYPE_WDS: - return cfg80211_wds_wext_giwap(dev, info, ap_addr, extra); default: return -EOPNOTSUPP; } -- cgit v1.3-15-g9ac1 From f73659192b0bdf7bad826587b3530cef43cc048d Mon Sep 17 00:00:00 2001 From: Xie He Date: Sat, 14 Nov 2020 07:09:21 -0800 Subject: net: wan: Delete the DLCI / SDLA drivers The DLCI driver (dlci.c) implements the Frame Relay protocol. However, we already have another newer and better implementation of Frame Relay provided by the HDLC_FR driver (hdlc_fr.c). The DLCI driver's implementation of Frame Relay is used by only one hardware driver in the kernel - the SDLA driver (sdla.c). The SDLA driver provides Frame Relay support for the Sangoma S50x devices. However, the vendor provides their own driver (along with their own multi-WAN-protocol implementations including Frame Relay), called WANPIPE. I believe most users of the hardware would use the vendor-provided WANPIPE driver instead. (The WANPIPE driver was even once in the kernel, but was deleted in commit 8db60bcf3021 ("[WAN]: Remove broken and unmaintained Sangoma drivers.") because the vendor no longer updated the in-kernel WANPIPE driver.) Cc: Mike McLagan Signed-off-by: Xie He Link: https://lore.kernel.org/r/20201114150921.685594-1-xie.he.0141@gmail.com Signed-off-by: Jakub Kicinski --- CREDITS | 9 - Documentation/networking/framerelay.rst | 44 - MAINTAINERS | 6 - arch/arm/configs/ixp4xx_defconfig | 1 - arch/mips/configs/gpr_defconfig | 1 - arch/mips/configs/mtx1_defconfig | 1 - drivers/net/wan/Kconfig | 45 - drivers/net/wan/Makefile | 2 - drivers/net/wan/dlci.c | 541 ---------- drivers/net/wan/sdla.c | 1655 ------------------------------- include/linux/if_frad.h | 92 -- include/linux/sdla.h | 240 ----- include/uapi/linux/if_frad.h | 123 --- include/uapi/linux/sdla.h | 117 --- net/socket.c | 25 - 15 files changed, 2902 deletions(-) delete mode 100644 Documentation/networking/framerelay.rst delete mode 100644 drivers/net/wan/dlci.c delete mode 100644 drivers/net/wan/sdla.c delete mode 100644 include/linux/if_frad.h delete mode 100644 include/linux/sdla.h delete mode 100644 include/uapi/linux/if_frad.h delete mode 100644 include/uapi/linux/sdla.h (limited to 'include/uapi/linux') diff --git a/CREDITS b/CREDITS index 8592e45e3932..67421adb747c 100644 --- a/CREDITS +++ b/CREDITS @@ -2499,15 +2499,6 @@ W: http://www.rdrop.com/users/paulmck/ D: RCU and variants D: rcutorture module -N: Mike McLagan -E: mike.mclagan@linux.org -W: http://www.invlogic.com/~mmclagan -D: DLCI/FRAD drivers for Sangoma SDLAs -S: Innovative Logic Corp -S: Post Office Box 1068 -S: Laurel, Maryland 20732 -S: USA - N: Bradley McLean E: brad@bradpc.gaylord.com D: Device driver hacker diff --git a/Documentation/networking/framerelay.rst b/Documentation/networking/framerelay.rst deleted file mode 100644 index 6d904399ec6d..000000000000 --- a/Documentation/networking/framerelay.rst +++ /dev/null @@ -1,44 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -================ -Frame Relay (FR) -================ - -Frame Relay (FR) support for linux is built into a two tiered system of device -drivers. The upper layer implements RFC1490 FR specification, and uses the -Data Link Connection Identifier (DLCI) as its hardware address. Usually these -are assigned by your network supplier, they give you the number/numbers of -the Virtual Connections (VC) assigned to you. - -Each DLCI is a point-to-point link between your machine and a remote one. -As such, a separate device is needed to accommodate the routing. Within the -net-tools archives is 'dlcicfg'. This program will communicate with the -base "DLCI" device, and create new net devices named 'dlci00', 'dlci01'... -The configuration script will ask you how many DLCIs you need, as well as -how many DLCIs you want to assign to each Frame Relay Access Device (FRAD). - -The DLCI uses a number of function calls to communicate with the FRAD, all -of which are stored in the FRAD's private data area. assoc/deassoc, -activate/deactivate and dlci_config. The DLCI supplies a receive function -to the FRAD to accept incoming packets. - -With this initial offering, only 1 FRAD driver is available. With many thanks -to Sangoma Technologies, David Mandelstam & Gene Kozin, the S502A, S502E & -S508 are supported. This driver is currently set up for only FR, but as -Sangoma makes more firmware modules available, it can be updated to provide -them as well. - -Configuration of the FRAD makes use of another net-tools program, 'fradcfg'. -This program makes use of a configuration file (which dlcicfg can also read) -to specify the types of boards to be configured as FRADs, as well as perform -any board specific configuration. The Sangoma module of fradcfg loads the -FR firmware into the card, sets the irq/port/memory information, and provides -an initial configuration. - -Additional FRAD device drivers can be added as hardware is available. - -At this time, the dlcicfg and fradcfg programs have not been incorporated into -the net-tools distribution. They can be found at ftp.invlogic.com, in -/pub/linux. Note that with OS/2 FTPD, you end up in /pub by default, so just -use 'cd linux'. v0.10 is for use on pre-2.0.3 and earlier, v0.15 is for -pre-2.0.4 and later. diff --git a/MAINTAINERS b/MAINTAINERS index af9f6a3ab100..3341959af0c7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6905,12 +6905,6 @@ S: Maintained W: http://floatingpoint.sourceforge.net/emulator/index.html F: arch/x86/math-emu/ -FRAME RELAY DLCI/FRAD (Sangoma drivers too) -L: netdev@vger.kernel.org -S: Orphan -F: drivers/net/wan/dlci.c -F: drivers/net/wan/sdla.c - FRAMEBUFFER LAYER M: Bartlomiej Zolnierkiewicz L: dri-devel@lists.freedesktop.org diff --git a/arch/arm/configs/ixp4xx_defconfig b/arch/arm/configs/ixp4xx_defconfig index 27e7c0714b96..0d6edeb27659 100644 --- a/arch/arm/configs/ixp4xx_defconfig +++ b/arch/arm/configs/ixp4xx_defconfig @@ -141,7 +141,6 @@ CONFIG_HDLC_CISCO=m CONFIG_HDLC_FR=m CONFIG_HDLC_PPP=m CONFIG_HDLC_X25=m -CONFIG_DLCI=m CONFIG_WAN_ROUTER_DRIVERS=m CONFIG_ATM_TCP=m # CONFIG_INPUT_KEYBOARD is not set diff --git a/arch/mips/configs/gpr_defconfig b/arch/mips/configs/gpr_defconfig index 599d5604aabe..8a921c8ac233 100644 --- a/arch/mips/configs/gpr_defconfig +++ b/arch/mips/configs/gpr_defconfig @@ -228,7 +228,6 @@ CONFIG_FARSYNC=m CONFIG_DSCC4=m CONFIG_DSCC4_PCISYNC=y CONFIG_DSCC4_PCI_RST=y -CONFIG_DLCI=m CONFIG_LAPBETHER=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index dc69b054181c..30dacce94198 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -378,7 +378,6 @@ CONFIG_FARSYNC=m CONFIG_DSCC4=m CONFIG_DSCC4_PCISYNC=y CONFIG_DSCC4_PCI_RST=y -CONFIG_DLCI=m CONFIG_LAPBETHER=m # CONFIG_KEYBOARD_ATKBD is not set CONFIG_KEYBOARD_GPIO=y diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig index 2cf98a732a26..4029fde71a9e 100644 --- a/drivers/net/wan/Kconfig +++ b/drivers/net/wan/Kconfig @@ -321,51 +321,6 @@ config IXP4XX_HSS Say Y here if you want to use built-in HSS ports on IXP4xx processor. -config DLCI - tristate "Frame Relay DLCI support" - help - Support for the Frame Relay protocol. - - Frame Relay is a fast low-cost way to connect to a remote Internet - access provider or to form a private wide area network. The one - physical line from your box to the local "switch" (i.e. the entry - point to the Frame Relay network, usually at the phone company) can - carry several logical point-to-point connections to other computers - connected to the Frame Relay network. For a general explanation of - the protocol, check out . - - To use frame relay, you need supporting hardware (called FRAD) and - certain programs from the net-tools package as explained in - . - - To compile this driver as a module, choose M here: the - module will be called dlci. - -config DLCI_MAX - int "Max DLCI per device" - depends on DLCI - default "8" - help - How many logical point-to-point frame relay connections (the - identifiers of which are called DCLIs) should be handled by each - of your hardware frame relay access devices. - - Go with the default. - -config SDLA - tristate "SDLA (Sangoma S502/S508) support" - depends on DLCI && ISA - help - Driver for the Sangoma S502A, S502E, and S508 Frame Relay Access - Devices. - - These are multi-protocol cards, but only Frame Relay is supported - by the driver at this time. Please read - . - - To compile this driver as a module, choose M here: the - module will be called sdla. - # X.25 network drivers config LAPBETHER tristate "LAPB over Ethernet driver" diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile index 5b9dc85eae34..081666c36ca2 100644 --- a/drivers/net/wan/Makefile +++ b/drivers/net/wan/Makefile @@ -21,8 +21,6 @@ obj-$(CONFIG_FARSYNC) += farsync.o obj-$(CONFIG_LANMEDIA) += lmc/ -obj-$(CONFIG_DLCI) += dlci.o -obj-$(CONFIG_SDLA) += sdla.o obj-$(CONFIG_LAPBETHER) += lapbether.o obj-$(CONFIG_SBNI) += sbni.o obj-$(CONFIG_N2) += n2.o diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c deleted file mode 100644 index 3ca4daf63389..000000000000 --- a/drivers/net/wan/dlci.c +++ /dev/null @@ -1,541 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * DLCI Implementation of Frame Relay protocol for Linux, according to - * RFC 1490. This generic device provides en/decapsulation for an - * underlying hardware driver. Routes & IPs are assigned to these - * interfaces. Requires 'dlcicfg' program to create usable - * interfaces, the initial one, 'dlci' is for IOCTL use only. - * - * Version: @(#)dlci.c 0.35 4 Jan 1997 - * - * Author: Mike McLagan - * - * Changes: - * - * 0.15 Mike Mclagan Packet freeing, bug in kmalloc call - * DLCI_RET handling - * 0.20 Mike McLagan More conservative on which packets - * are returned for retry and which are - * are dropped. If DLCI_RET_DROP is - * returned from the FRAD, the packet is - * sent back to Linux for re-transmission - * 0.25 Mike McLagan Converted to use SIOC IOCTL calls - * 0.30 Jim Freeman Fixed to allow IPX traffic - * 0.35 Michael Elizabeth Fixed incorrect memcpy_fromfs - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -#include -#include -#include - -static const char version[] = "DLCI driver v0.35, 4 Jan 1997, mike.mclagan@linux.org"; - -static LIST_HEAD(dlci_devs); - -static void dlci_setup(struct net_device *); - -/* - * these encapsulate the RFC 1490 requirements as well as - * deal with packet transmission and reception, working with - * the upper network layers - */ - -static int dlci_header(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *daddr, - const void *saddr, unsigned len) -{ - struct frhdr hdr; - unsigned int hlen; - char *dest; - - hdr.control = FRAD_I_UI; - switch (type) - { - case ETH_P_IP: - hdr.IP_NLPID = FRAD_P_IP; - hlen = sizeof(hdr.control) + sizeof(hdr.IP_NLPID); - break; - - /* feel free to add other types, if necessary */ - - default: - hdr.pad = FRAD_P_PADDING; - hdr.NLPID = FRAD_P_SNAP; - memset(hdr.OUI, 0, sizeof(hdr.OUI)); - hdr.PID = htons(type); - hlen = sizeof(hdr); - break; - } - - dest = skb_push(skb, hlen); - if (!dest) - return 0; - - memcpy(dest, &hdr, hlen); - - return hlen; -} - -static void dlci_receive(struct sk_buff *skb, struct net_device *dev) -{ - struct frhdr *hdr; - int process, header; - - if (!pskb_may_pull(skb, sizeof(*hdr))) { - netdev_notice(dev, "invalid data no header\n"); - dev->stats.rx_errors++; - kfree_skb(skb); - return; - } - - hdr = (struct frhdr *) skb->data; - process = 0; - header = 0; - skb->dev = dev; - - if (hdr->control != FRAD_I_UI) - { - netdev_notice(dev, "Invalid header flag 0x%02X\n", - hdr->control); - dev->stats.rx_errors++; - } - else - switch (hdr->IP_NLPID) - { - case FRAD_P_PADDING: - if (hdr->NLPID != FRAD_P_SNAP) - { - netdev_notice(dev, "Unsupported NLPID 0x%02X\n", - hdr->NLPID); - dev->stats.rx_errors++; - break; - } - - if (hdr->OUI[0] + hdr->OUI[1] + hdr->OUI[2] != 0) - { - netdev_notice(dev, "Unsupported organizationally unique identifier 0x%02X-%02X-%02X\n", - hdr->OUI[0], - hdr->OUI[1], - hdr->OUI[2]); - dev->stats.rx_errors++; - break; - } - - /* at this point, it's an EtherType frame */ - header = sizeof(struct frhdr); - /* Already in network order ! */ - skb->protocol = hdr->PID; - process = 1; - break; - - case FRAD_P_IP: - header = sizeof(hdr->control) + sizeof(hdr->IP_NLPID); - skb->protocol = htons(ETH_P_IP); - process = 1; - break; - - case FRAD_P_SNAP: - case FRAD_P_Q933: - case FRAD_P_CLNP: - netdev_notice(dev, "Unsupported NLPID 0x%02X\n", - hdr->pad); - dev->stats.rx_errors++; - break; - - default: - netdev_notice(dev, "Invalid pad byte 0x%02X\n", - hdr->pad); - dev->stats.rx_errors++; - break; - } - - if (process) - { - /* we've set up the protocol, so discard the header */ - skb_reset_mac_header(skb); - skb_pull(skb, header); - dev->stats.rx_bytes += skb->len; - netif_rx(skb); - dev->stats.rx_packets++; - } - else - dev_kfree_skb(skb); -} - -static netdev_tx_t dlci_transmit(struct sk_buff *skb, struct net_device *dev) -{ - struct dlci_local *dlp = netdev_priv(dev); - - if (skb) { - struct netdev_queue *txq = skb_get_tx_queue(dev, skb); - netdev_start_xmit(skb, dlp->slave, txq, false); - } - return NETDEV_TX_OK; -} - -static int dlci_config(struct net_device *dev, struct dlci_conf __user *conf, int get) -{ - struct dlci_conf config; - struct dlci_local *dlp; - struct frad_local *flp; - int err; - - dlp = netdev_priv(dev); - - flp = netdev_priv(dlp->slave); - - if (!get) - { - if (copy_from_user(&config, conf, sizeof(struct dlci_conf))) - return -EFAULT; - if (config.flags & ~DLCI_VALID_FLAGS) - return -EINVAL; - memcpy(&dlp->config, &config, sizeof(struct dlci_conf)); - dlp->configured = 1; - } - - err = (*flp->dlci_conf)(dlp->slave, dev, get); - if (err) - return err; - - if (get) - { - if (copy_to_user(conf, &dlp->config, sizeof(struct dlci_conf))) - return -EFAULT; - } - - return 0; -} - -static int dlci_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct dlci_local *dlp; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - dlp = netdev_priv(dev); - - switch (cmd) - { - case DLCI_GET_SLAVE: - if (!*(short *)(dev->dev_addr)) - return -EINVAL; - - strncpy(ifr->ifr_slave, dlp->slave->name, sizeof(ifr->ifr_slave)); - break; - - case DLCI_GET_CONF: - case DLCI_SET_CONF: - if (!*(short *)(dev->dev_addr)) - return -EINVAL; - - return dlci_config(dev, ifr->ifr_data, cmd == DLCI_GET_CONF); - - default: - return -EOPNOTSUPP; - } - return 0; -} - -static int dlci_change_mtu(struct net_device *dev, int new_mtu) -{ - struct dlci_local *dlp = netdev_priv(dev); - - return dev_set_mtu(dlp->slave, new_mtu); -} - -static int dlci_open(struct net_device *dev) -{ - struct dlci_local *dlp; - struct frad_local *flp; - int err; - - dlp = netdev_priv(dev); - - if (!*(short *)(dev->dev_addr)) - return -EINVAL; - - if (!netif_running(dlp->slave)) - return -ENOTCONN; - - flp = netdev_priv(dlp->slave); - err = (*flp->activate)(dlp->slave, dev); - if (err) - return err; - - netif_start_queue(dev); - - return 0; -} - -static int dlci_close(struct net_device *dev) -{ - struct dlci_local *dlp; - struct frad_local *flp; - - netif_stop_queue(dev); - - dlp = netdev_priv(dev); - - flp = netdev_priv(dlp->slave); - (*flp->deactivate)(dlp->slave, dev); - - return 0; -} - -static int dlci_add(struct dlci_add *dlci) -{ - struct net_device *master, *slave; - struct dlci_local *dlp; - struct frad_local *flp; - int err = -EINVAL; - - - /* validate slave device */ - slave = dev_get_by_name(&init_net, dlci->devname); - if (!slave) - return -ENODEV; - - if (slave->type != ARPHRD_FRAD || netdev_priv(slave) == NULL) - goto err1; - - /* create device name */ - master = alloc_netdev(sizeof(struct dlci_local), "dlci%d", - NET_NAME_UNKNOWN, dlci_setup); - if (!master) { - err = -ENOMEM; - goto err1; - } - - /* make sure same slave not already registered */ - rtnl_lock(); - list_for_each_entry(dlp, &dlci_devs, list) { - if (dlp->slave == slave) { - err = -EBUSY; - goto err2; - } - } - - *(short *)(master->dev_addr) = dlci->dlci; - - dlp = netdev_priv(master); - dlp->slave = slave; - dlp->master = master; - - flp = netdev_priv(slave); - err = (*flp->assoc)(slave, master); - if (err < 0) - goto err2; - - err = register_netdevice(master); - if (err < 0) - goto err2; - - strcpy(dlci->devname, master->name); - - list_add(&dlp->list, &dlci_devs); - rtnl_unlock(); - - return 0; - - err2: - rtnl_unlock(); - free_netdev(master); - err1: - dev_put(slave); - return err; -} - -static int dlci_del(struct dlci_add *dlci) -{ - struct dlci_local *dlp; - struct frad_local *flp; - struct net_device *master, *slave; - int err; - bool found = false; - - rtnl_lock(); - - /* validate slave device */ - master = __dev_get_by_name(&init_net, dlci->devname); - if (!master) { - err = -ENODEV; - goto out; - } - - list_for_each_entry(dlp, &dlci_devs, list) { - if (dlp->master == master) { - found = true; - break; - } - } - if (!found) { - err = -ENODEV; - goto out; - } - - if (netif_running(master)) { - err = -EBUSY; - goto out; - } - - dlp = netdev_priv(master); - slave = dlp->slave; - flp = netdev_priv(slave); - - err = (*flp->deassoc)(slave, master); - if (!err) { - list_del(&dlp->list); - - unregister_netdevice(master); - - dev_put(slave); - } -out: - rtnl_unlock(); - return err; -} - -static int dlci_ioctl(unsigned int cmd, void __user *arg) -{ - struct dlci_add add; - int err; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (copy_from_user(&add, arg, sizeof(struct dlci_add))) - return -EFAULT; - - switch (cmd) - { - case SIOCADDDLCI: - err = dlci_add(&add); - - if (!err) - if (copy_to_user(arg, &add, sizeof(struct dlci_add))) - return -EFAULT; - break; - - case SIOCDELDLCI: - err = dlci_del(&add); - break; - - default: - err = -EINVAL; - } - - return err; -} - -static const struct header_ops dlci_header_ops = { - .create = dlci_header, -}; - -static const struct net_device_ops dlci_netdev_ops = { - .ndo_open = dlci_open, - .ndo_stop = dlci_close, - .ndo_do_ioctl = dlci_dev_ioctl, - .ndo_start_xmit = dlci_transmit, - .ndo_change_mtu = dlci_change_mtu, -}; - -static void dlci_setup(struct net_device *dev) -{ - struct dlci_local *dlp = netdev_priv(dev); - - dev->flags = 0; - dev->header_ops = &dlci_header_ops; - dev->netdev_ops = &dlci_netdev_ops; - dev->needs_free_netdev = true; - - dlp->receive = dlci_receive; - - dev->type = ARPHRD_DLCI; - dev->hard_header_len = sizeof(struct frhdr); - dev->addr_len = sizeof(short); - -} - -/* if slave is unregistering, then cleanup master */ -static int dlci_dev_event(struct notifier_block *unused, - unsigned long event, void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - - if (dev_net(dev) != &init_net) - return NOTIFY_DONE; - - if (event == NETDEV_UNREGISTER) { - struct dlci_local *dlp; - - list_for_each_entry(dlp, &dlci_devs, list) { - if (dlp->slave == dev) { - list_del(&dlp->list); - unregister_netdevice(dlp->master); - dev_put(dlp->slave); - break; - } - } - } - return NOTIFY_DONE; -} - -static struct notifier_block dlci_notifier = { - .notifier_call = dlci_dev_event, -}; - -static int __init init_dlci(void) -{ - dlci_ioctl_set(dlci_ioctl); - register_netdevice_notifier(&dlci_notifier); - - printk("%s.\n", version); - - return 0; -} - -static void __exit dlci_exit(void) -{ - struct dlci_local *dlp, *nxt; - - dlci_ioctl_set(NULL); - unregister_netdevice_notifier(&dlci_notifier); - - rtnl_lock(); - list_for_each_entry_safe(dlp, nxt, &dlci_devs, list) { - unregister_netdevice(dlp->master); - dev_put(dlp->slave); - } - rtnl_unlock(); -} - -module_init(init_dlci); -module_exit(dlci_exit); - -MODULE_AUTHOR("Mike McLagan"); -MODULE_DESCRIPTION("Frame Relay DLCI layer"); -MODULE_LICENSE("GPL"); diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c deleted file mode 100644 index bc2c1c7fb1a4..000000000000 --- a/drivers/net/wan/sdla.c +++ /dev/null @@ -1,1655 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * SDLA An implementation of a driver for the Sangoma S502/S508 series - * multi-protocol PC interface card. Initial offering is with - * the DLCI driver, providing Frame Relay support for linux. - * - * Global definitions for the Frame relay interface. - * - * Version: @(#)sdla.c 0.30 12 Sep 1996 - * - * Credits: Sangoma Technologies, for the use of 2 cards for an extended - * period of time. - * David Mandelstam for getting me started on - * this project, and incentive to complete it. - * Gene Kozen <74604.152@compuserve.com> for providing me with - * important information about the cards. - * - * Author: Mike McLagan - * - * Changes: - * 0.15 Mike McLagan Improved error handling, packet dropping - * 0.20 Mike McLagan New transmit/receive flags for config - * If in FR mode, don't accept packets from - * non DLCI devices. - * 0.25 Mike McLagan Fixed problem with rejecting packets - * from non DLCI devices. - * 0.30 Mike McLagan Fixed kernel panic when used with modified - * ifconfig - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -static const char* version = "SDLA driver v0.30, 12 Sep 1996, mike.mclagan@linux.org"; - -static unsigned int valid_port[] = { 0x250, 0x270, 0x280, 0x300, 0x350, 0x360, 0x380, 0x390}; - -static unsigned int valid_mem[] = { - 0xA0000, 0xA2000, 0xA4000, 0xA6000, 0xA8000, 0xAA000, 0xAC000, 0xAE000, - 0xB0000, 0xB2000, 0xB4000, 0xB6000, 0xB8000, 0xBA000, 0xBC000, 0xBE000, - 0xC0000, 0xC2000, 0xC4000, 0xC6000, 0xC8000, 0xCA000, 0xCC000, 0xCE000, - 0xD0000, 0xD2000, 0xD4000, 0xD6000, 0xD8000, 0xDA000, 0xDC000, 0xDE000, - 0xE0000, 0xE2000, 0xE4000, 0xE6000, 0xE8000, 0xEA000, 0xEC000, 0xEE000}; - -static DEFINE_SPINLOCK(sdla_lock); - -/********************************************************* - * - * these are the core routines that access the card itself - * - *********************************************************/ - -#define SDLA_WINDOW(dev,addr) outb((((addr) >> 13) & 0x1F), (dev)->base_addr + SDLA_REG_Z80_WINDOW) - -static void __sdla_read(struct net_device *dev, int addr, void *buf, short len) -{ - char *temp; - const void *base; - int offset, bytes; - - temp = buf; - while(len) - { - offset = addr & SDLA_ADDR_MASK; - bytes = offset + len > SDLA_WINDOW_SIZE ? SDLA_WINDOW_SIZE - offset : len; - base = (const void *) (dev->mem_start + offset); - - SDLA_WINDOW(dev, addr); - memcpy(temp, base, bytes); - - addr += bytes; - temp += bytes; - len -= bytes; - } -} - -static void sdla_read(struct net_device *dev, int addr, void *buf, short len) -{ - unsigned long flags; - spin_lock_irqsave(&sdla_lock, flags); - __sdla_read(dev, addr, buf, len); - spin_unlock_irqrestore(&sdla_lock, flags); -} - -static void __sdla_write(struct net_device *dev, int addr, - const void *buf, short len) -{ - const char *temp; - void *base; - int offset, bytes; - - temp = buf; - while(len) - { - offset = addr & SDLA_ADDR_MASK; - bytes = offset + len > SDLA_WINDOW_SIZE ? SDLA_WINDOW_SIZE - offset : len; - base = (void *) (dev->mem_start + offset); - - SDLA_WINDOW(dev, addr); - memcpy(base, temp, bytes); - - addr += bytes; - temp += bytes; - len -= bytes; - } -} - -static void sdla_write(struct net_device *dev, int addr, - const void *buf, short len) -{ - unsigned long flags; - - spin_lock_irqsave(&sdla_lock, flags); - __sdla_write(dev, addr, buf, len); - spin_unlock_irqrestore(&sdla_lock, flags); -} - - -static void sdla_clear(struct net_device *dev) -{ - unsigned long flags; - char *base; - int len, addr, bytes; - - len = 65536; - addr = 0; - bytes = SDLA_WINDOW_SIZE; - base = (void *) dev->mem_start; - - spin_lock_irqsave(&sdla_lock, flags); - while(len) - { - SDLA_WINDOW(dev, addr); - memset(base, 0, bytes); - - addr += bytes; - len -= bytes; - } - spin_unlock_irqrestore(&sdla_lock, flags); - -} - -static char sdla_byte(struct net_device *dev, int addr) -{ - unsigned long flags; - char byte, *temp; - - temp = (void *) (dev->mem_start + (addr & SDLA_ADDR_MASK)); - - spin_lock_irqsave(&sdla_lock, flags); - SDLA_WINDOW(dev, addr); - byte = *temp; - spin_unlock_irqrestore(&sdla_lock, flags); - - return byte; -} - -static void sdla_stop(struct net_device *dev) -{ - struct frad_local *flp; - - flp = netdev_priv(dev); - switch(flp->type) - { - case SDLA_S502A: - outb(SDLA_S502A_HALT, dev->base_addr + SDLA_REG_CONTROL); - flp->state = SDLA_HALT; - break; - case SDLA_S502E: - outb(SDLA_HALT, dev->base_addr + SDLA_REG_Z80_CONTROL); - outb(SDLA_S502E_ENABLE, dev->base_addr + SDLA_REG_CONTROL); - flp->state = SDLA_S502E_ENABLE; - break; - case SDLA_S507: - flp->state &= ~SDLA_CPUEN; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - break; - case SDLA_S508: - flp->state &= ~SDLA_CPUEN; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - break; - } -} - -static void sdla_start(struct net_device *dev) -{ - struct frad_local *flp; - - flp = netdev_priv(dev); - switch(flp->type) - { - case SDLA_S502A: - outb(SDLA_S502A_NMI, dev->base_addr + SDLA_REG_CONTROL); - outb(SDLA_S502A_START, dev->base_addr + SDLA_REG_CONTROL); - flp->state = SDLA_S502A_START; - break; - case SDLA_S502E: - outb(SDLA_S502E_CPUEN, dev->base_addr + SDLA_REG_Z80_CONTROL); - outb(0x00, dev->base_addr + SDLA_REG_CONTROL); - flp->state = 0; - break; - case SDLA_S507: - flp->state |= SDLA_CPUEN; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - break; - case SDLA_S508: - flp->state |= SDLA_CPUEN; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - break; - } -} - -/**************************************************** - * - * this is used for the S502A/E cards to determine - * the speed of the onboard CPU. Calibration is - * necessary for the Frame Relay code uploaded - * later. Incorrect results cause timing problems - * with link checks & status messages - * - ***************************************************/ - -static int sdla_z80_poll(struct net_device *dev, int z80_addr, int jiffs, char resp1, char resp2) -{ - unsigned long start, done, now; - char resp, *temp; - - start = now = jiffies; - done = jiffies + jiffs; - - temp = (void *)dev->mem_start; - temp += z80_addr & SDLA_ADDR_MASK; - - resp = ~resp1; - while (time_before(jiffies, done) && (resp != resp1) && (!resp2 || (resp != resp2))) - { - if (jiffies != now) - { - SDLA_WINDOW(dev, z80_addr); - now = jiffies; - resp = *temp; - } - } - return time_before(jiffies, done) ? jiffies - start : -1; -} - -/* constants for Z80 CPU speed */ -#define Z80_READY '1' /* Z80 is ready to begin */ -#define LOADER_READY '2' /* driver is ready to begin */ -#define Z80_SCC_OK '3' /* SCC is on board */ -#define Z80_SCC_BAD '4' /* SCC was not found */ - -static int sdla_cpuspeed(struct net_device *dev, struct ifreq *ifr) -{ - int jiffs; - char data; - - sdla_start(dev); - if (sdla_z80_poll(dev, 0, 3*HZ, Z80_READY, 0) < 0) - return -EIO; - - data = LOADER_READY; - sdla_write(dev, 0, &data, 1); - - if ((jiffs = sdla_z80_poll(dev, 0, 8*HZ, Z80_SCC_OK, Z80_SCC_BAD)) < 0) - return -EIO; - - sdla_stop(dev); - sdla_read(dev, 0, &data, 1); - - if (data == Z80_SCC_BAD) - { - printk("%s: SCC bad\n", dev->name); - return -EIO; - } - - if (data != Z80_SCC_OK) - return -EINVAL; - - if (jiffs < 165) - ifr->ifr_mtu = SDLA_CPU_16M; - else if (jiffs < 220) - ifr->ifr_mtu = SDLA_CPU_10M; - else if (jiffs < 258) - ifr->ifr_mtu = SDLA_CPU_8M; - else if (jiffs < 357) - ifr->ifr_mtu = SDLA_CPU_7M; - else if (jiffs < 467) - ifr->ifr_mtu = SDLA_CPU_5M; - else - ifr->ifr_mtu = SDLA_CPU_3M; - - return 0; -} - -/************************************************ - * - * Direct interaction with the Frame Relay code - * starts here. - * - ************************************************/ - -struct _dlci_stat -{ - short dlci; - char flags; -} __packed; - -struct _frad_stat -{ - char flags; - struct _dlci_stat dlcis[SDLA_MAX_DLCI]; -}; - -static void sdla_errors(struct net_device *dev, int cmd, int dlci, int ret, int len, void *data) -{ - struct _dlci_stat *pstatus; - short *pdlci; - int i; - char *state, line[30]; - - switch (ret) - { - case SDLA_RET_MODEM: - state = data; - if (*state & SDLA_MODEM_DCD_LOW) - netdev_info(dev, "Modem DCD unexpectedly low!\n"); - if (*state & SDLA_MODEM_CTS_LOW) - netdev_info(dev, "Modem CTS unexpectedly low!\n"); - /* I should probably do something about this! */ - break; - - case SDLA_RET_CHANNEL_OFF: - netdev_info(dev, "Channel became inoperative!\n"); - /* same here */ - break; - - case SDLA_RET_CHANNEL_ON: - netdev_info(dev, "Channel became operative!\n"); - /* same here */ - break; - - case SDLA_RET_DLCI_STATUS: - netdev_info(dev, "Status change reported by Access Node\n"); - len /= sizeof(struct _dlci_stat); - for(pstatus = data, i=0;i < len;i++,pstatus++) - { - if (pstatus->flags & SDLA_DLCI_NEW) - state = "new"; - else if (pstatus->flags & SDLA_DLCI_DELETED) - state = "deleted"; - else if (pstatus->flags & SDLA_DLCI_ACTIVE) - state = "active"; - else - { - sprintf(line, "unknown status: %02X", pstatus->flags); - state = line; - } - netdev_info(dev, "DLCI %i: %s\n", - pstatus->dlci, state); - /* same here */ - } - break; - - case SDLA_RET_DLCI_UNKNOWN: - netdev_info(dev, "Received unknown DLCIs:"); - len /= sizeof(short); - for(pdlci = data,i=0;i < len;i++,pdlci++) - pr_cont(" %i", *pdlci); - pr_cont("\n"); - break; - - case SDLA_RET_TIMEOUT: - netdev_err(dev, "Command timed out!\n"); - break; - - case SDLA_RET_BUF_OVERSIZE: - netdev_info(dev, "Bc/CIR overflow, acceptable size is %i\n", - len); - break; - - case SDLA_RET_BUF_TOO_BIG: - netdev_info(dev, "Buffer size over specified max of %i\n", - len); - break; - - case SDLA_RET_CHANNEL_INACTIVE: - case SDLA_RET_DLCI_INACTIVE: - case SDLA_RET_CIR_OVERFLOW: - case SDLA_RET_NO_BUFS: - if (cmd == SDLA_INFORMATION_WRITE) - break; - fallthrough; - - default: - netdev_dbg(dev, "Cmd 0x%02X generated return code 0x%02X\n", - cmd, ret); - /* Further processing could be done here */ - break; - } -} - -static int sdla_cmd(struct net_device *dev, int cmd, short dlci, short flags, - void *inbuf, short inlen, void *outbuf, short *outlen) -{ - static struct _frad_stat status; - struct frad_local *flp; - struct sdla_cmd *cmd_buf; - unsigned long pflags; - unsigned long jiffs; - int ret, waiting, len; - long window; - - flp = netdev_priv(dev); - window = flp->type == SDLA_S508 ? SDLA_508_CMD_BUF : SDLA_502_CMD_BUF; - cmd_buf = (struct sdla_cmd *)(dev->mem_start + (window & SDLA_ADDR_MASK)); - ret = 0; - len = 0; - jiffs = jiffies + HZ; /* 1 second is plenty */ - - spin_lock_irqsave(&sdla_lock, pflags); - SDLA_WINDOW(dev, window); - cmd_buf->cmd = cmd; - cmd_buf->dlci = dlci; - cmd_buf->flags = flags; - - if (inbuf) - memcpy(cmd_buf->data, inbuf, inlen); - - cmd_buf->length = inlen; - - cmd_buf->opp_flag = 1; - spin_unlock_irqrestore(&sdla_lock, pflags); - - waiting = 1; - len = 0; - while (waiting && time_before_eq(jiffies, jiffs)) - { - if (waiting++ % 3) - { - spin_lock_irqsave(&sdla_lock, pflags); - SDLA_WINDOW(dev, window); - waiting = ((volatile int)(cmd_buf->opp_flag)); - spin_unlock_irqrestore(&sdla_lock, pflags); - } - } - - if (!waiting) - { - - spin_lock_irqsave(&sdla_lock, pflags); - SDLA_WINDOW(dev, window); - ret = cmd_buf->retval; - len = cmd_buf->length; - if (outbuf && outlen) - { - *outlen = *outlen >= len ? len : *outlen; - - if (*outlen) - memcpy(outbuf, cmd_buf->data, *outlen); - } - - /* This is a local copy that's used for error handling */ - if (ret) - memcpy(&status, cmd_buf->data, len > sizeof(status) ? sizeof(status) : len); - - spin_unlock_irqrestore(&sdla_lock, pflags); - } - else - ret = SDLA_RET_TIMEOUT; - - if (ret != SDLA_RET_OK) - sdla_errors(dev, cmd, dlci, ret, len, &status); - - return ret; -} - -/*********************************************** - * - * these functions are called by the DLCI driver - * - ***********************************************/ - -static int sdla_reconfig(struct net_device *dev); - -static int sdla_activate(struct net_device *slave, struct net_device *master) -{ - struct frad_local *flp; - int i; - - flp = netdev_priv(slave); - - for(i=0;imaster[i] == master) - break; - - if (i == CONFIG_DLCI_MAX) - return -ENODEV; - - flp->dlci[i] = abs(flp->dlci[i]); - - if (netif_running(slave) && (flp->config.station == FRAD_STATION_NODE)) - sdla_cmd(slave, SDLA_ACTIVATE_DLCI, 0, 0, &flp->dlci[i], sizeof(short), NULL, NULL); - - return 0; -} - -static int sdla_deactivate(struct net_device *slave, struct net_device *master) -{ - struct frad_local *flp; - int i; - - flp = netdev_priv(slave); - - for(i=0;imaster[i] == master) - break; - - if (i == CONFIG_DLCI_MAX) - return -ENODEV; - - flp->dlci[i] = -abs(flp->dlci[i]); - - if (netif_running(slave) && (flp->config.station == FRAD_STATION_NODE)) - sdla_cmd(slave, SDLA_DEACTIVATE_DLCI, 0, 0, &flp->dlci[i], sizeof(short), NULL, NULL); - - return 0; -} - -static int sdla_assoc(struct net_device *slave, struct net_device *master) -{ - struct frad_local *flp; - int i; - - if (master->type != ARPHRD_DLCI) - return -EINVAL; - - flp = netdev_priv(slave); - - for(i=0;imaster[i]) - break; - if (abs(flp->dlci[i]) == *(short *)(master->dev_addr)) - return -EADDRINUSE; - } - - if (i == CONFIG_DLCI_MAX) - return -EMLINK; /* #### Alan: Comments on this ?? */ - - - flp->master[i] = master; - flp->dlci[i] = -*(short *)(master->dev_addr); - master->mtu = slave->mtu; - - if (netif_running(slave)) { - if (flp->config.station == FRAD_STATION_CPE) - sdla_reconfig(slave); - else - sdla_cmd(slave, SDLA_ADD_DLCI, 0, 0, master->dev_addr, sizeof(short), NULL, NULL); - } - - return 0; -} - -static int sdla_deassoc(struct net_device *slave, struct net_device *master) -{ - struct frad_local *flp; - int i; - - flp = netdev_priv(slave); - - for(i=0;imaster[i] == master) - break; - - if (i == CONFIG_DLCI_MAX) - return -ENODEV; - - flp->master[i] = NULL; - flp->dlci[i] = 0; - - - if (netif_running(slave)) { - if (flp->config.station == FRAD_STATION_CPE) - sdla_reconfig(slave); - else - sdla_cmd(slave, SDLA_DELETE_DLCI, 0, 0, master->dev_addr, sizeof(short), NULL, NULL); - } - - return 0; -} - -static int sdla_dlci_conf(struct net_device *slave, struct net_device *master, int get) -{ - struct frad_local *flp; - struct dlci_local *dlp; - int i; - short len, ret; - - flp = netdev_priv(slave); - - for(i=0;imaster[i] == master) - break; - - if (i == CONFIG_DLCI_MAX) - return -ENODEV; - - dlp = netdev_priv(master); - - ret = SDLA_RET_OK; - len = sizeof(struct dlci_conf); - if (netif_running(slave)) { - if (get) - ret = sdla_cmd(slave, SDLA_READ_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0, - NULL, 0, &dlp->config, &len); - else - ret = sdla_cmd(slave, SDLA_SET_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0, - &dlp->config, sizeof(struct dlci_conf) - 4 * sizeof(short), NULL, NULL); - } - - return ret == SDLA_RET_OK ? 0 : -EIO; -} - -/************************** - * - * now for the Linux driver - * - **************************/ - -/* NOTE: the DLCI driver deals with freeing the SKB!! */ -static netdev_tx_t sdla_transmit(struct sk_buff *skb, - struct net_device *dev) -{ - struct frad_local *flp; - int ret, addr, accept, i; - short size; - unsigned long flags; - struct buf_entry *pbuf; - - flp = netdev_priv(dev); - ret = 0; - accept = 1; - - netif_stop_queue(dev); - - /* - * stupid GateD insists on setting up the multicast router thru us - * and we're ill equipped to handle a non Frame Relay packet at this - * time! - */ - - accept = 1; - switch (dev->type) - { - case ARPHRD_FRAD: - if (skb->dev->type != ARPHRD_DLCI) - { - netdev_warn(dev, "Non DLCI device, type %i, tried to send on FRAD module\n", - skb->dev->type); - accept = 0; - } - break; - default: - netdev_warn(dev, "unknown firmware type 0x%04X\n", - dev->type); - accept = 0; - break; - } - if (accept) - { - /* this is frame specific, but till there's a PPP module, it's the default */ - switch (flp->type) - { - case SDLA_S502A: - case SDLA_S502E: - ret = sdla_cmd(dev, SDLA_INFORMATION_WRITE, *(short *)(skb->dev->dev_addr), 0, skb->data, skb->len, NULL, NULL); - break; - case SDLA_S508: - size = sizeof(addr); - ret = sdla_cmd(dev, SDLA_INFORMATION_WRITE, *(short *)(skb->dev->dev_addr), 0, NULL, skb->len, &addr, &size); - if (ret == SDLA_RET_OK) - { - - spin_lock_irqsave(&sdla_lock, flags); - SDLA_WINDOW(dev, addr); - pbuf = (void *)(dev->mem_start + (addr & SDLA_ADDR_MASK)); - __sdla_write(dev, pbuf->buf_addr, skb->data, skb->len); - SDLA_WINDOW(dev, addr); - pbuf->opp_flag = 1; - spin_unlock_irqrestore(&sdla_lock, flags); - } - break; - } - - switch (ret) - { - case SDLA_RET_OK: - dev->stats.tx_packets++; - break; - - case SDLA_RET_CIR_OVERFLOW: - case SDLA_RET_BUF_OVERSIZE: - case SDLA_RET_NO_BUFS: - dev->stats.tx_dropped++; - break; - - default: - dev->stats.tx_errors++; - break; - } - } - netif_wake_queue(dev); - for(i=0;imaster[i]!=NULL) - netif_wake_queue(flp->master[i]); - } - - dev_kfree_skb(skb); - return NETDEV_TX_OK; -} - -static void sdla_receive(struct net_device *dev) -{ - struct net_device *master; - struct frad_local *flp; - struct dlci_local *dlp; - struct sk_buff *skb; - - struct sdla_cmd *cmd; - struct buf_info *pbufi; - struct buf_entry *pbuf; - - unsigned long flags; - int i=0, received, success, addr, buf_base, buf_top; - short dlci, len, len2, split; - - flp = netdev_priv(dev); - success = 1; - received = addr = buf_top = buf_base = 0; - len = dlci = 0; - skb = NULL; - master = NULL; - cmd = NULL; - pbufi = NULL; - pbuf = NULL; - - spin_lock_irqsave(&sdla_lock, flags); - - switch (flp->type) - { - case SDLA_S502A: - case SDLA_S502E: - cmd = (void *) (dev->mem_start + (SDLA_502_RCV_BUF & SDLA_ADDR_MASK)); - SDLA_WINDOW(dev, SDLA_502_RCV_BUF); - success = cmd->opp_flag; - if (!success) - break; - - dlci = cmd->dlci; - len = cmd->length; - break; - - case SDLA_S508: - pbufi = (void *) (dev->mem_start + (SDLA_508_RXBUF_INFO & SDLA_ADDR_MASK)); - SDLA_WINDOW(dev, SDLA_508_RXBUF_INFO); - pbuf = (void *) (dev->mem_start + ((pbufi->rse_base + flp->buffer * sizeof(struct buf_entry)) & SDLA_ADDR_MASK)); - success = pbuf->opp_flag; - if (!success) - break; - - buf_top = pbufi->buf_top; - buf_base = pbufi->buf_base; - dlci = pbuf->dlci; - len = pbuf->length; - addr = pbuf->buf_addr; - break; - } - - /* common code, find the DLCI and get the SKB */ - if (success) - { - for (i=0;idlci[i] == dlci) - break; - - if (i == CONFIG_DLCI_MAX) - { - netdev_notice(dev, "Received packet from invalid DLCI %i, ignoring\n", - dlci); - dev->stats.rx_errors++; - success = 0; - } - } - - if (success) - { - master = flp->master[i]; - skb = dev_alloc_skb(len + sizeof(struct frhdr)); - if (skb == NULL) - { - netdev_notice(dev, "Memory squeeze, dropping packet\n"); - dev->stats.rx_dropped++; - success = 0; - } - else - skb_reserve(skb, sizeof(struct frhdr)); - } - - /* pick up the data */ - switch (flp->type) - { - case SDLA_S502A: - case SDLA_S502E: - if (success) - __sdla_read(dev, SDLA_502_RCV_BUF + SDLA_502_DATA_OFS, skb_put(skb,len), len); - - SDLA_WINDOW(dev, SDLA_502_RCV_BUF); - cmd->opp_flag = 0; - break; - - case SDLA_S508: - if (success) - { - /* is this buffer split off the end of the internal ring buffer */ - split = addr + len > buf_top + 1 ? len - (buf_top - addr + 1) : 0; - len2 = len - split; - - __sdla_read(dev, addr, skb_put(skb, len2), len2); - if (split) - __sdla_read(dev, buf_base, skb_put(skb, split), split); - } - - /* increment the buffer we're looking at */ - SDLA_WINDOW(dev, SDLA_508_RXBUF_INFO); - flp->buffer = (flp->buffer + 1) % pbufi->rse_num; - pbuf->opp_flag = 0; - break; - } - - if (success) - { - dev->stats.rx_packets++; - dlp = netdev_priv(master); - (*dlp->receive)(skb, master); - } - - spin_unlock_irqrestore(&sdla_lock, flags); -} - -static irqreturn_t sdla_isr(int dummy, void *dev_id) -{ - struct net_device *dev; - struct frad_local *flp; - char byte; - - dev = dev_id; - - flp = netdev_priv(dev); - - if (!flp->initialized) - { - netdev_warn(dev, "irq %d for uninitialized device\n", dev->irq); - return IRQ_NONE; - } - - byte = sdla_byte(dev, flp->type == SDLA_S508 ? SDLA_508_IRQ_INTERFACE : SDLA_502_IRQ_INTERFACE); - switch (byte) - { - case SDLA_INTR_RX: - sdla_receive(dev); - break; - - /* the command will get an error return, which is processed above */ - case SDLA_INTR_MODEM: - case SDLA_INTR_STATUS: - sdla_cmd(dev, SDLA_READ_DLC_STATUS, 0, 0, NULL, 0, NULL, NULL); - break; - - case SDLA_INTR_TX: - case SDLA_INTR_COMPLETE: - case SDLA_INTR_TIMER: - netdev_warn(dev, "invalid irq flag 0x%02X\n", byte); - break; - } - - /* the S502E requires a manual acknowledgement of the interrupt */ - if (flp->type == SDLA_S502E) - { - flp->state &= ~SDLA_S502E_INTACK; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - flp->state |= SDLA_S502E_INTACK; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - } - - /* this clears the byte, informing the Z80 we're done */ - byte = 0; - sdla_write(dev, flp->type == SDLA_S508 ? SDLA_508_IRQ_INTERFACE : SDLA_502_IRQ_INTERFACE, &byte, sizeof(byte)); - return IRQ_HANDLED; -} - -static void sdla_poll(struct timer_list *t) -{ - struct frad_local *flp = from_timer(flp, t, timer); - struct net_device *dev = flp->dev; - - if (sdla_byte(dev, SDLA_502_RCV_BUF)) - sdla_receive(dev); - - flp->timer.expires = 1; - add_timer(&flp->timer); -} - -static int sdla_close(struct net_device *dev) -{ - struct frad_local *flp; - struct intr_info intr; - int len, i; - short dlcis[CONFIG_DLCI_MAX]; - - flp = netdev_priv(dev); - - len = 0; - for(i=0;idlci[i]) - dlcis[len++] = abs(flp->dlci[i]); - len *= 2; - - if (flp->config.station == FRAD_STATION_NODE) - { - for(i=0;idlci[i] > 0) - sdla_cmd(dev, SDLA_DEACTIVATE_DLCI, 0, 0, dlcis, len, NULL, NULL); - sdla_cmd(dev, SDLA_DELETE_DLCI, 0, 0, &flp->dlci[i], sizeof(flp->dlci[i]), NULL, NULL); - } - - memset(&intr, 0, sizeof(intr)); - /* let's start up the reception */ - switch(flp->type) - { - case SDLA_S502A: - del_timer(&flp->timer); - break; - - case SDLA_S502E: - sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(char) + sizeof(short), NULL, NULL); - flp->state &= ~SDLA_S502E_INTACK; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - break; - - case SDLA_S507: - break; - - case SDLA_S508: - sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(struct intr_info), NULL, NULL); - flp->state &= ~SDLA_S508_INTEN; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - break; - } - - sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL); - - netif_stop_queue(dev); - - return 0; -} - -struct conf_data { - struct frad_conf config; - short dlci[CONFIG_DLCI_MAX]; -}; - -static int sdla_open(struct net_device *dev) -{ - struct frad_local *flp; - struct dlci_local *dlp; - struct conf_data data; - struct intr_info intr; - int len, i; - char byte; - - flp = netdev_priv(dev); - - if (!flp->initialized) - return -EPERM; - - if (!flp->configured) - return -EPERM; - - /* time to send in the configuration */ - len = 0; - for(i=0;idlci[i]) - data.dlci[len++] = abs(flp->dlci[i]); - len *= 2; - - memcpy(&data.config, &flp->config, sizeof(struct frad_conf)); - len += sizeof(struct frad_conf); - - sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL); - sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, 0, 0, &data, len, NULL, NULL); - - if (flp->type == SDLA_S508) - flp->buffer = 0; - - sdla_cmd(dev, SDLA_ENABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL); - - /* let's start up the reception */ - memset(&intr, 0, sizeof(intr)); - switch(flp->type) - { - case SDLA_S502A: - flp->timer.expires = 1; - add_timer(&flp->timer); - break; - - case SDLA_S502E: - flp->state |= SDLA_S502E_ENABLE; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - flp->state |= SDLA_S502E_INTACK; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - byte = 0; - sdla_write(dev, SDLA_502_IRQ_INTERFACE, &byte, sizeof(byte)); - intr.flags = SDLA_INTR_RX | SDLA_INTR_STATUS | SDLA_INTR_MODEM; - sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(char) + sizeof(short), NULL, NULL); - break; - - case SDLA_S507: - break; - - case SDLA_S508: - flp->state |= SDLA_S508_INTEN; - outb(flp->state, dev->base_addr + SDLA_REG_CONTROL); - byte = 0; - sdla_write(dev, SDLA_508_IRQ_INTERFACE, &byte, sizeof(byte)); - intr.flags = SDLA_INTR_RX | SDLA_INTR_STATUS | SDLA_INTR_MODEM; - intr.irq = dev->irq; - sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(struct intr_info), NULL, NULL); - break; - } - - if (flp->config.station == FRAD_STATION_CPE) - { - byte = SDLA_ICS_STATUS_ENQ; - sdla_cmd(dev, SDLA_ISSUE_IN_CHANNEL_SIGNAL, 0, 0, &byte, sizeof(byte), NULL, NULL); - } - else - { - sdla_cmd(dev, SDLA_ADD_DLCI, 0, 0, data.dlci, len - sizeof(struct frad_conf), NULL, NULL); - for(i=0;idlci[i] > 0) - sdla_cmd(dev, SDLA_ACTIVATE_DLCI, 0, 0, &flp->dlci[i], 2*sizeof(flp->dlci[i]), NULL, NULL); - } - - /* configure any specific DLCI settings */ - for(i=0;idlci[i]) - { - dlp = netdev_priv(flp->master[i]); - if (dlp->configured) - sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0, &dlp->config, sizeof(struct dlci_conf), NULL, NULL); - } - - netif_start_queue(dev); - - return 0; -} - -static int sdla_config(struct net_device *dev, struct frad_conf __user *conf, int get) -{ - struct frad_local *flp; - struct conf_data data; - int i; - short size; - - if (dev->type == 0xFFFF) - return -EUNATCH; - - flp = netdev_priv(dev); - - if (!get) - { - if (netif_running(dev)) - return -EBUSY; - - if(copy_from_user(&data.config, conf, sizeof(struct frad_conf))) - return -EFAULT; - - if (data.config.station & ~FRAD_STATION_NODE) - return -EINVAL; - - if (data.config.flags & ~FRAD_VALID_FLAGS) - return -EINVAL; - - if ((data.config.kbaud < 0) || - ((data.config.kbaud > 128) && (flp->type != SDLA_S508))) - return -EINVAL; - - if (data.config.clocking & ~(FRAD_CLOCK_INT | SDLA_S508_PORT_RS232)) - return -EINVAL; - - if ((data.config.mtu < 0) || (data.config.mtu > SDLA_MAX_MTU)) - return -EINVAL; - - if ((data.config.T391 < 5) || (data.config.T391 > 30)) - return -EINVAL; - - if ((data.config.T392 < 5) || (data.config.T392 > 30)) - return -EINVAL; - - if ((data.config.N391 < 1) || (data.config.N391 > 255)) - return -EINVAL; - - if ((data.config.N392 < 1) || (data.config.N392 > 10)) - return -EINVAL; - - if ((data.config.N393 < 1) || (data.config.N393 > 10)) - return -EINVAL; - - memcpy(&flp->config, &data.config, sizeof(struct frad_conf)); - flp->config.flags |= SDLA_DIRECT_RECV; - - if (flp->type == SDLA_S508) - flp->config.flags |= SDLA_TX70_RX30; - - if (dev->mtu != flp->config.mtu) - { - /* this is required to change the MTU */ - dev->mtu = flp->config.mtu; - for(i=0;imaster[i]) - flp->master[i]->mtu = flp->config.mtu; - } - - flp->config.mtu += sizeof(struct frhdr); - - /* off to the races! */ - if (!flp->configured) - sdla_start(dev); - - flp->configured = 1; - } - else - { - /* no sense reading if the CPU isn't started */ - if (netif_running(dev)) - { - size = sizeof(data); - if (sdla_cmd(dev, SDLA_READ_DLCI_CONFIGURATION, 0, 0, NULL, 0, &data, &size) != SDLA_RET_OK) - return -EIO; - } - else - if (flp->configured) - memcpy(&data.config, &flp->config, sizeof(struct frad_conf)); - else - memset(&data.config, 0, sizeof(struct frad_conf)); - - memcpy(&flp->config, &data.config, sizeof(struct frad_conf)); - data.config.flags &= FRAD_VALID_FLAGS; - data.config.mtu -= data.config.mtu > sizeof(struct frhdr) ? sizeof(struct frhdr) : data.config.mtu; - return copy_to_user(conf, &data.config, sizeof(struct frad_conf))?-EFAULT:0; - } - - return 0; -} - -static int sdla_xfer(struct net_device *dev, struct sdla_mem __user *info, int read) -{ - struct sdla_mem mem; - char *temp; - - if(copy_from_user(&mem, info, sizeof(mem))) - return -EFAULT; - - if (read) - { - temp = kzalloc(mem.len, GFP_KERNEL); - if (!temp) - return -ENOMEM; - sdla_read(dev, mem.addr, temp, mem.len); - if(copy_to_user(mem.data, temp, mem.len)) - { - kfree(temp); - return -EFAULT; - } - kfree(temp); - } - else - { - temp = memdup_user(mem.data, mem.len); - if (IS_ERR(temp)) - return PTR_ERR(temp); - sdla_write(dev, mem.addr, temp, mem.len); - kfree(temp); - } - return 0; -} - -static int sdla_reconfig(struct net_device *dev) -{ - struct frad_local *flp; - struct conf_data data; - int i, len; - - flp = netdev_priv(dev); - - len = 0; - for(i=0;idlci[i]) - data.dlci[len++] = flp->dlci[i]; - len *= 2; - - memcpy(&data, &flp->config, sizeof(struct frad_conf)); - len += sizeof(struct frad_conf); - - sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL); - sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, 0, 0, &data, len, NULL, NULL); - sdla_cmd(dev, SDLA_ENABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL); - - return 0; -} - -static int sdla_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct frad_local *flp; - - if(!capable(CAP_NET_ADMIN)) - return -EPERM; - - flp = netdev_priv(dev); - - if (!flp->initialized) - return -EINVAL; - - switch (cmd) - { - case FRAD_GET_CONF: - case FRAD_SET_CONF: - return sdla_config(dev, ifr->ifr_data, cmd == FRAD_GET_CONF); - - case SDLA_IDENTIFY: - ifr->ifr_flags = flp->type; - break; - - case SDLA_CPUSPEED: - return sdla_cpuspeed(dev, ifr); - -/* ========================================================== -NOTE: This is rather a useless action right now, as the - current driver does not support protocols other than - FR. However, Sangoma has modules for a number of - other protocols in the works. -============================================================*/ - case SDLA_PROTOCOL: - if (flp->configured) - return -EALREADY; - - switch (ifr->ifr_flags) - { - case ARPHRD_FRAD: - dev->type = ifr->ifr_flags; - break; - default: - return -ENOPROTOOPT; - } - break; - - case SDLA_CLEARMEM: - sdla_clear(dev); - break; - - case SDLA_WRITEMEM: - case SDLA_READMEM: - if(!capable(CAP_SYS_RAWIO)) - return -EPERM; - return sdla_xfer(dev, ifr->ifr_data, cmd == SDLA_READMEM); - - case SDLA_START: - sdla_start(dev); - break; - - case SDLA_STOP: - sdla_stop(dev); - break; - - default: - return -EOPNOTSUPP; - } - return 0; -} - -static int sdla_change_mtu(struct net_device *dev, int new_mtu) -{ - if (netif_running(dev)) - return -EBUSY; - - /* for now, you can't change the MTU! */ - return -EOPNOTSUPP; -} - -static int sdla_set_config(struct net_device *dev, struct ifmap *map) -{ - struct frad_local *flp; - int i; - char byte; - unsigned base; - int err = -EINVAL; - - flp = netdev_priv(dev); - - if (flp->initialized) - return -EINVAL; - - for(i=0; i < ARRAY_SIZE(valid_port); i++) - if (valid_port[i] == map->base_addr) - break; - - if (i == ARRAY_SIZE(valid_port)) - return -EINVAL; - - if (!request_region(map->base_addr, SDLA_IO_EXTENTS, dev->name)){ - pr_warn("io-port 0x%04lx in use\n", dev->base_addr); - return -EINVAL; - } - base = map->base_addr; - - /* test for card types, S502A, S502E, S507, S508 */ - /* these tests shut down the card completely, so clear the state */ - flp->type = SDLA_UNKNOWN; - flp->state = 0; - - for(i=1;itype = SDLA_S502E; - goto got_type; - } - } - } - - for(byte=inb(base),i=0;itype = SDLA_S507; - goto got_type; - } - } - } - - outb(SDLA_HALT, base + SDLA_REG_CONTROL); - if ((inb(base + SDLA_S508_STS) & 0x3F) == 0x00) { - outb(SDLA_S508_INTEN, base + SDLA_REG_CONTROL); - if ((inb(base + SDLA_S508_STS) & 0x3F) == 0x10) { - outb(SDLA_HALT, base + SDLA_REG_CONTROL); - flp->type = SDLA_S508; - goto got_type; - } - } - - outb(SDLA_S502A_HALT, base + SDLA_REG_CONTROL); - if (inb(base + SDLA_S502_STS) == 0x40) { - outb(SDLA_S502A_START, base + SDLA_REG_CONTROL); - if (inb(base + SDLA_S502_STS) == 0x40) { - outb(SDLA_S502A_INTEN, base + SDLA_REG_CONTROL); - if (inb(base + SDLA_S502_STS) == 0x44) { - outb(SDLA_S502A_START, base + SDLA_REG_CONTROL); - flp->type = SDLA_S502A; - goto got_type; - } - } - } - - netdev_notice(dev, "Unknown card type\n"); - err = -ENODEV; - goto fail; - -got_type: - switch(base) { - case 0x270: - case 0x280: - case 0x380: - case 0x390: - if (flp->type != SDLA_S508 && flp->type != SDLA_S507) - goto fail; - } - - switch (map->irq) { - case 2: - if (flp->type != SDLA_S502E) - goto fail; - break; - - case 10: - case 11: - case 12: - case 15: - case 4: - if (flp->type != SDLA_S508 && flp->type != SDLA_S507) - goto fail; - break; - case 3: - case 5: - case 7: - if (flp->type == SDLA_S502A) - goto fail; - break; - - default: - goto fail; - } - - err = -EAGAIN; - if (request_irq(dev->irq, sdla_isr, 0, dev->name, dev)) - goto fail; - - if (flp->type == SDLA_S507) { - switch(dev->irq) { - case 3: - flp->state = SDLA_S507_IRQ3; - break; - case 4: - flp->state = SDLA_S507_IRQ4; - break; - case 5: - flp->state = SDLA_S507_IRQ5; - break; - case 7: - flp->state = SDLA_S507_IRQ7; - break; - case 10: - flp->state = SDLA_S507_IRQ10; - break; - case 11: - flp->state = SDLA_S507_IRQ11; - break; - case 12: - flp->state = SDLA_S507_IRQ12; - break; - case 15: - flp->state = SDLA_S507_IRQ15; - break; - } - } - - for(i=0; i < ARRAY_SIZE(valid_mem); i++) - if (valid_mem[i] == map->mem_start) - break; - - err = -EINVAL; - if (i == ARRAY_SIZE(valid_mem)) - goto fail2; - - if (flp->type == SDLA_S502A && (map->mem_start & 0xF000) >> 12 == 0x0E) - goto fail2; - - if (flp->type != SDLA_S507 && map->mem_start >> 16 == 0x0B) - goto fail2; - - if (flp->type == SDLA_S507 && map->mem_start >> 16 == 0x0D) - goto fail2; - - byte = flp->type != SDLA_S508 ? SDLA_8K_WINDOW : 0; - byte |= (map->mem_start & 0xF000) >> (12 + (flp->type == SDLA_S508 ? 1 : 0)); - switch(flp->type) { - case SDLA_S502A: - case SDLA_S502E: - switch (map->mem_start >> 16) { - case 0x0A: - byte |= SDLA_S502_SEG_A; - break; - case 0x0C: - byte |= SDLA_S502_SEG_C; - break; - case 0x0D: - byte |= SDLA_S502_SEG_D; - break; - case 0x0E: - byte |= SDLA_S502_SEG_E; - break; - } - break; - case SDLA_S507: - switch (map->mem_start >> 16) { - case 0x0A: - byte |= SDLA_S507_SEG_A; - break; - case 0x0B: - byte |= SDLA_S507_SEG_B; - break; - case 0x0C: - byte |= SDLA_S507_SEG_C; - break; - case 0x0E: - byte |= SDLA_S507_SEG_E; - break; - } - break; - case SDLA_S508: - switch (map->mem_start >> 16) { - case 0x0A: - byte |= SDLA_S508_SEG_A; - break; - case 0x0C: - byte |= SDLA_S508_SEG_C; - break; - case 0x0D: - byte |= SDLA_S508_SEG_D; - break; - case 0x0E: - byte |= SDLA_S508_SEG_E; - break; - } - break; - } - - /* set the memory bits, and enable access */ - outb(byte, base + SDLA_REG_PC_WINDOW); - - switch(flp->type) - { - case SDLA_S502E: - flp->state = SDLA_S502E_ENABLE; - break; - case SDLA_S507: - flp->state |= SDLA_MEMEN; - break; - case SDLA_S508: - flp->state = SDLA_MEMEN; - break; - } - outb(flp->state, base + SDLA_REG_CONTROL); - - dev->irq = map->irq; - dev->base_addr = base; - dev->mem_start = map->mem_start; - dev->mem_end = dev->mem_start + 0x2000; - flp->initialized = 1; - return 0; - -fail2: - free_irq(map->irq, dev); -fail: - release_region(base, SDLA_IO_EXTENTS); - return err; -} - -static const struct net_device_ops sdla_netdev_ops = { - .ndo_open = sdla_open, - .ndo_stop = sdla_close, - .ndo_do_ioctl = sdla_ioctl, - .ndo_set_config = sdla_set_config, - .ndo_start_xmit = sdla_transmit, - .ndo_change_mtu = sdla_change_mtu, -}; - -static void setup_sdla(struct net_device *dev) -{ - struct frad_local *flp = netdev_priv(dev); - - netdev_boot_setup_check(dev); - - dev->netdev_ops = &sdla_netdev_ops; - dev->flags = 0; - dev->type = 0xFFFF; - dev->hard_header_len = 0; - dev->addr_len = 0; - dev->mtu = SDLA_MAX_MTU; - - flp->activate = sdla_activate; - flp->deactivate = sdla_deactivate; - flp->assoc = sdla_assoc; - flp->deassoc = sdla_deassoc; - flp->dlci_conf = sdla_dlci_conf; - flp->dev = dev; - - timer_setup(&flp->timer, sdla_poll, 0); - flp->timer.expires = 1; -} - -static struct net_device *sdla; - -static int __init init_sdla(void) -{ - int err; - - printk("%s.\n", version); - - sdla = alloc_netdev(sizeof(struct frad_local), "sdla0", - NET_NAME_UNKNOWN, setup_sdla); - if (!sdla) - return -ENOMEM; - - err = register_netdev(sdla); - if (err) - free_netdev(sdla); - - return err; -} - -static void __exit exit_sdla(void) -{ - struct frad_local *flp = netdev_priv(sdla); - - unregister_netdev(sdla); - if (flp->initialized) { - free_irq(sdla->irq, sdla); - release_region(sdla->base_addr, SDLA_IO_EXTENTS); - } - del_timer_sync(&flp->timer); - free_netdev(sdla); -} - -MODULE_LICENSE("GPL"); - -module_init(init_sdla); -module_exit(exit_sdla); diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h deleted file mode 100644 index 52224de798aa..000000000000 --- a/include/linux/if_frad.h +++ /dev/null @@ -1,92 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * DLCI/FRAD Definitions for Frame Relay Access Devices. DLCI devices are - * created for each DLCI associated with a FRAD. The FRAD driver - * is not truly a network device, but the lower level device - * handler. This allows other FRAD manufacturers to use the DLCI - * code, including its RFC1490 encapsulation alongside the current - * implementation for the Sangoma cards. - * - * Version: @(#)if_ifrad.h 0.15 31 Mar 96 - * - * Author: Mike McLagan - * - * Changes: - * 0.15 Mike McLagan changed structure defs (packed) - * re-arranged flags - * added DLCI_RET vars - */ -#ifndef _FRAD_H_ -#define _FRAD_H_ - -#include - - -#if defined(CONFIG_DLCI) || defined(CONFIG_DLCI_MODULE) - -/* these are the fields of an RFC 1490 header */ -struct frhdr -{ - unsigned char control; - - /* for IP packets, this can be the NLPID */ - unsigned char pad; - - unsigned char NLPID; - unsigned char OUI[3]; - __be16 PID; - -#define IP_NLPID pad -} __packed; - -/* see RFC 1490 for the definition of the following */ -#define FRAD_I_UI 0x03 - -#define FRAD_P_PADDING 0x00 -#define FRAD_P_Q933 0x08 -#define FRAD_P_SNAP 0x80 -#define FRAD_P_CLNP 0x81 -#define FRAD_P_IP 0xCC - -struct dlci_local -{ - struct net_device *master; - struct net_device *slave; - struct dlci_conf config; - int configured; - struct list_head list; - - /* callback function */ - void (*receive)(struct sk_buff *skb, struct net_device *); -}; - -struct frad_local -{ - /* devices which this FRAD is slaved to */ - struct net_device *master[CONFIG_DLCI_MAX]; - short dlci[CONFIG_DLCI_MAX]; - - struct frad_conf config; - int configured; /* has this device been configured */ - int initialized; /* mem_start, port, irq set ? */ - - /* callback functions */ - int (*activate)(struct net_device *, struct net_device *); - int (*deactivate)(struct net_device *, struct net_device *); - int (*assoc)(struct net_device *, struct net_device *); - int (*deassoc)(struct net_device *, struct net_device *); - int (*dlci_conf)(struct net_device *, struct net_device *, int get); - - /* fields that are used by the Sangoma SDLA cards */ - struct timer_list timer; - struct net_device *dev; - int type; /* adapter type */ - int state; /* state of the S502/8 control latch */ - int buffer; /* current buffer for S508 firmware */ -}; - -#endif /* CONFIG_DLCI || CONFIG_DLCI_MODULE */ - -extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *)); - -#endif diff --git a/include/linux/sdla.h b/include/linux/sdla.h deleted file mode 100644 index 00e8b3b614f0..000000000000 --- a/include/linux/sdla.h +++ /dev/null @@ -1,240 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. INET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * Global definitions for the Frame relay interface. - * - * Version: @(#)if_ifrad.h 0.20 13 Apr 96 - * - * Author: Mike McLagan - * - * Changes: - * 0.15 Mike McLagan Structure packing - * - * 0.20 Mike McLagan New flags for S508 buffer handling - */ -#ifndef SDLA_H -#define SDLA_H - -#include - - -/* important Z80 window addresses */ -#define SDLA_CONTROL_WND 0xE000 - -#define SDLA_502_CMD_BUF 0xEF60 -#define SDLA_502_RCV_BUF 0xA900 -#define SDLA_502_TXN_AVAIL 0xFFF1 -#define SDLA_502_RCV_AVAIL 0xFFF2 -#define SDLA_502_EVENT_FLAGS 0xFFF3 -#define SDLA_502_MDM_STATUS 0xFFF4 -#define SDLA_502_IRQ_INTERFACE 0xFFFD -#define SDLA_502_IRQ_PERMISSION 0xFFFE -#define SDLA_502_DATA_OFS 0x0010 - -#define SDLA_508_CMD_BUF 0xE000 -#define SDLA_508_TXBUF_INFO 0xF100 -#define SDLA_508_RXBUF_INFO 0xF120 -#define SDLA_508_EVENT_FLAGS 0xF003 -#define SDLA_508_MDM_STATUS 0xF004 -#define SDLA_508_IRQ_INTERFACE 0xF010 -#define SDLA_508_IRQ_PERMISSION 0xF011 -#define SDLA_508_TSE_OFFSET 0xF012 - -/* Event flags */ -#define SDLA_EVENT_STATUS 0x01 -#define SDLA_EVENT_DLCI_STATUS 0x02 -#define SDLA_EVENT_BAD_DLCI 0x04 -#define SDLA_EVENT_LINK_DOWN 0x40 - -/* IRQ Trigger flags */ -#define SDLA_INTR_RX 0x01 -#define SDLA_INTR_TX 0x02 -#define SDLA_INTR_MODEM 0x04 -#define SDLA_INTR_COMPLETE 0x08 -#define SDLA_INTR_STATUS 0x10 -#define SDLA_INTR_TIMER 0x20 - -/* DLCI status bits */ -#define SDLA_DLCI_DELETED 0x01 -#define SDLA_DLCI_ACTIVE 0x02 -#define SDLA_DLCI_WAITING 0x04 -#define SDLA_DLCI_NEW 0x08 -#define SDLA_DLCI_INCLUDED 0x40 - -/* valid command codes */ -#define SDLA_INFORMATION_WRITE 0x01 -#define SDLA_INFORMATION_READ 0x02 -#define SDLA_ISSUE_IN_CHANNEL_SIGNAL 0x03 -#define SDLA_SET_DLCI_CONFIGURATION 0x10 -#define SDLA_READ_DLCI_CONFIGURATION 0x11 -#define SDLA_DISABLE_COMMUNICATIONS 0x12 -#define SDLA_ENABLE_COMMUNICATIONS 0x13 -#define SDLA_READ_DLC_STATUS 0x14 -#define SDLA_READ_DLC_STATISTICS 0x15 -#define SDLA_FLUSH_DLC_STATISTICS 0x16 -#define SDLA_LIST_ACTIVE_DLCI 0x17 -#define SDLA_FLUSH_INFORMATION_BUFFERS 0x18 -#define SDLA_ADD_DLCI 0x20 -#define SDLA_DELETE_DLCI 0x21 -#define SDLA_ACTIVATE_DLCI 0x22 -#define SDLA_DEACTIVATE_DLCI 0x23 -#define SDLA_READ_MODEM_STATUS 0x30 -#define SDLA_SET_MODEM_STATUS 0x31 -#define SDLA_READ_COMMS_ERR_STATS 0x32 -#define SDLA_FLUSH_COMMS_ERR_STATS 0x33 -#define SDLA_READ_CODE_VERSION 0x40 -#define SDLA_SET_IRQ_TRIGGER 0x50 -#define SDLA_GET_IRQ_TRIGGER 0x51 - -/* In channel signal types */ -#define SDLA_ICS_LINK_VERIFY 0x02 -#define SDLA_ICS_STATUS_ENQ 0x03 - -/* modem status flags */ -#define SDLA_MODEM_DTR_HIGH 0x01 -#define SDLA_MODEM_RTS_HIGH 0x02 -#define SDLA_MODEM_DCD_HIGH 0x08 -#define SDLA_MODEM_CTS_HIGH 0x20 - -/* used for RET_MODEM interpretation */ -#define SDLA_MODEM_DCD_LOW 0x01 -#define SDLA_MODEM_CTS_LOW 0x02 - -/* return codes */ -#define SDLA_RET_OK 0x00 -#define SDLA_RET_COMMUNICATIONS 0x01 -#define SDLA_RET_CHANNEL_INACTIVE 0x02 -#define SDLA_RET_DLCI_INACTIVE 0x03 -#define SDLA_RET_DLCI_CONFIG 0x04 -#define SDLA_RET_BUF_TOO_BIG 0x05 -#define SDLA_RET_NO_DATA 0x05 -#define SDLA_RET_BUF_OVERSIZE 0x06 -#define SDLA_RET_CIR_OVERFLOW 0x07 -#define SDLA_RET_NO_BUFS 0x08 -#define SDLA_RET_TIMEOUT 0x0A -#define SDLA_RET_MODEM 0x10 -#define SDLA_RET_CHANNEL_OFF 0x11 -#define SDLA_RET_CHANNEL_ON 0x12 -#define SDLA_RET_DLCI_STATUS 0x13 -#define SDLA_RET_DLCI_UNKNOWN 0x14 -#define SDLA_RET_COMMAND_INVALID 0x1F - -/* Configuration flags */ -#define SDLA_DIRECT_RECV 0x0080 -#define SDLA_TX_NO_EXCEPT 0x0020 -#define SDLA_NO_ICF_MSGS 0x1000 -#define SDLA_TX50_RX50 0x0000 -#define SDLA_TX70_RX30 0x2000 -#define SDLA_TX30_RX70 0x4000 - -/* IRQ selection flags */ -#define SDLA_IRQ_RECEIVE 0x01 -#define SDLA_IRQ_TRANSMIT 0x02 -#define SDLA_IRQ_MODEM_STAT 0x04 -#define SDLA_IRQ_COMMAND 0x08 -#define SDLA_IRQ_CHANNEL 0x10 -#define SDLA_IRQ_TIMER 0x20 - -/* definitions for PC memory mapping */ -#define SDLA_8K_WINDOW 0x01 -#define SDLA_S502_SEG_A 0x10 -#define SDLA_S502_SEG_C 0x20 -#define SDLA_S502_SEG_D 0x00 -#define SDLA_S502_SEG_E 0x30 -#define SDLA_S507_SEG_A 0x00 -#define SDLA_S507_SEG_B 0x40 -#define SDLA_S507_SEG_C 0x80 -#define SDLA_S507_SEG_E 0xC0 -#define SDLA_S508_SEG_A 0x00 -#define SDLA_S508_SEG_C 0x10 -#define SDLA_S508_SEG_D 0x08 -#define SDLA_S508_SEG_E 0x18 - -/* SDLA adapter port constants */ -#define SDLA_IO_EXTENTS 0x04 - -#define SDLA_REG_CONTROL 0x00 -#define SDLA_REG_PC_WINDOW 0x01 /* offset for PC window select latch */ -#define SDLA_REG_Z80_WINDOW 0x02 /* offset for Z80 window select latch */ -#define SDLA_REG_Z80_CONTROL 0x03 /* offset for Z80 control latch */ - -#define SDLA_S502_STS 0x00 /* status reg for 502, 502E, 507 */ -#define SDLA_S508_GNRL 0x00 /* general purp. reg for 508 */ -#define SDLA_S508_STS 0x01 /* status reg for 508 */ -#define SDLA_S508_IDR 0x02 /* ID reg for 508 */ - -/* control register flags */ -#define SDLA_S502A_START 0x00 /* start the CPU */ -#define SDLA_S502A_INTREQ 0x02 -#define SDLA_S502A_INTEN 0x04 -#define SDLA_S502A_HALT 0x08 /* halt the CPU */ -#define SDLA_S502A_NMI 0x10 /* issue an NMI to the CPU */ - -#define SDLA_S502E_CPUEN 0x01 -#define SDLA_S502E_ENABLE 0x02 -#define SDLA_S502E_INTACK 0x04 - -#define SDLA_S507_ENABLE 0x01 -#define SDLA_S507_IRQ3 0x00 -#define SDLA_S507_IRQ4 0x20 -#define SDLA_S507_IRQ5 0x40 -#define SDLA_S507_IRQ7 0x60 -#define SDLA_S507_IRQ10 0x80 -#define SDLA_S507_IRQ11 0xA0 -#define SDLA_S507_IRQ12 0xC0 -#define SDLA_S507_IRQ15 0xE0 - -#define SDLA_HALT 0x00 -#define SDLA_CPUEN 0x02 -#define SDLA_MEMEN 0x04 -#define SDLA_S507_EPROMWR 0x08 -#define SDLA_S507_EPROMCLK 0x10 -#define SDLA_S508_INTRQ 0x08 -#define SDLA_S508_INTEN 0x10 - -struct sdla_cmd { - char opp_flag; - char cmd; - short length; - char retval; - short dlci; - char flags; - short rxlost_int; - long rxlost_app; - char reserve[2]; - char data[SDLA_MAX_DATA]; /* transfer data buffer */ -} __attribute__((packed)); - -struct intr_info { - char flags; - short txlen; - char irq; - char flags2; - short timeout; -} __attribute__((packed)); - -/* found in the 508's control window at RXBUF_INFO */ -struct buf_info { - unsigned short rse_num; - unsigned long rse_base; - unsigned long rse_next; - unsigned long buf_base; - unsigned short reserved; - unsigned long buf_top; -} __attribute__((packed)); - -/* structure pointed to by rse_base in RXBUF_INFO struct */ -struct buf_entry { - char opp_flag; - short length; - short dlci; - char flags; - short timestamp; - short reserved[2]; - long buf_addr; -} __attribute__((packed)); - -#endif diff --git a/include/uapi/linux/if_frad.h b/include/uapi/linux/if_frad.h deleted file mode 100644 index 3c6ee85f6262..000000000000 --- a/include/uapi/linux/if_frad.h +++ /dev/null @@ -1,123 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* - * DLCI/FRAD Definitions for Frame Relay Access Devices. DLCI devices are - * created for each DLCI associated with a FRAD. The FRAD driver - * is not truly a network device, but the lower level device - * handler. This allows other FRAD manufacturers to use the DLCI - * code, including its RFC1490 encapsulation alongside the current - * implementation for the Sangoma cards. - * - * Version: @(#)if_ifrad.h 0.15 31 Mar 96 - * - * Author: Mike McLagan - * - * Changes: - * 0.15 Mike McLagan changed structure defs (packed) - * re-arranged flags - * added DLCI_RET vars - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _UAPI_FRAD_H_ -#define _UAPI_FRAD_H_ - -#include - -/* Structures and constants associated with the DLCI device driver */ - -struct dlci_add -{ - char devname[IFNAMSIZ]; - short dlci; -}; - -#define DLCI_GET_CONF (SIOCDEVPRIVATE + 2) -#define DLCI_SET_CONF (SIOCDEVPRIVATE + 3) - -/* - * These are related to the Sangoma SDLA and should remain in order. - * Code within the SDLA module is based on the specifics of this - * structure. Change at your own peril. - */ -struct dlci_conf { - short flags; - short CIR_fwd; - short Bc_fwd; - short Be_fwd; - short CIR_bwd; - short Bc_bwd; - short Be_bwd; - -/* these are part of the status read */ - short Tc_fwd; - short Tc_bwd; - short Tf_max; - short Tb_max; - -/* add any new fields here above is a mirror of sdla_dlci_conf */ -}; - -#define DLCI_GET_SLAVE (SIOCDEVPRIVATE + 4) - -/* configuration flags for DLCI */ -#define DLCI_IGNORE_CIR_OUT 0x0001 -#define DLCI_ACCOUNT_CIR_IN 0x0002 -#define DLCI_BUFFER_IF 0x0008 - -#define DLCI_VALID_FLAGS 0x000B - -/* defines for the actual Frame Relay hardware */ -#define FRAD_GET_CONF (SIOCDEVPRIVATE) -#define FRAD_SET_CONF (SIOCDEVPRIVATE + 1) - -#define FRAD_LAST_IOCTL FRAD_SET_CONF - -/* - * Based on the setup for the Sangoma SDLA. If changes are - * necessary to this structure, a routine will need to be - * added to that module to copy fields. - */ -struct frad_conf -{ - short station; - short flags; - short kbaud; - short clocking; - short mtu; - short T391; - short T392; - short N391; - short N392; - short N393; - short CIR_fwd; - short Bc_fwd; - short Be_fwd; - short CIR_bwd; - short Bc_bwd; - short Be_bwd; - -/* Add new fields here, above is a mirror of the sdla_conf */ - -}; - -#define FRAD_STATION_CPE 0x0000 -#define FRAD_STATION_NODE 0x0001 - -#define FRAD_TX_IGNORE_CIR 0x0001 -#define FRAD_RX_ACCOUNT_CIR 0x0002 -#define FRAD_DROP_ABORTED 0x0004 -#define FRAD_BUFFERIF 0x0008 -#define FRAD_STATS 0x0010 -#define FRAD_MCI 0x0100 -#define FRAD_AUTODLCI 0x8000 -#define FRAD_VALID_FLAGS 0x811F - -#define FRAD_CLOCK_INT 0x0001 -#define FRAD_CLOCK_EXT 0x0000 - - -#endif /* _UAPI_FRAD_H_ */ diff --git a/include/uapi/linux/sdla.h b/include/uapi/linux/sdla.h deleted file mode 100644 index 1e3735be6511..000000000000 --- a/include/uapi/linux/sdla.h +++ /dev/null @@ -1,117 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. INET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * Global definitions for the Frame relay interface. - * - * Version: @(#)if_ifrad.h 0.20 13 Apr 96 - * - * Author: Mike McLagan - * - * Changes: - * 0.15 Mike McLagan Structure packing - * - * 0.20 Mike McLagan New flags for S508 buffer handling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _UAPISDLA_H -#define _UAPISDLA_H - -/* adapter type */ -#define SDLA_TYPES -#define SDLA_S502A 5020 -#define SDLA_S502E 5021 -#define SDLA_S503 5030 -#define SDLA_S507 5070 -#define SDLA_S508 5080 -#define SDLA_S509 5090 -#define SDLA_UNKNOWN -1 - -/* port selection flags for the S508 */ -#define SDLA_S508_PORT_V35 0x00 -#define SDLA_S508_PORT_RS232 0x02 - -/* Z80 CPU speeds */ -#define SDLA_CPU_3M 0x00 -#define SDLA_CPU_5M 0x01 -#define SDLA_CPU_7M 0x02 -#define SDLA_CPU_8M 0x03 -#define SDLA_CPU_10M 0x04 -#define SDLA_CPU_16M 0x05 -#define SDLA_CPU_12M 0x06 - -/* some private IOCTLs */ -#define SDLA_IDENTIFY (FRAD_LAST_IOCTL + 1) -#define SDLA_CPUSPEED (FRAD_LAST_IOCTL + 2) -#define SDLA_PROTOCOL (FRAD_LAST_IOCTL + 3) - -#define SDLA_CLEARMEM (FRAD_LAST_IOCTL + 4) -#define SDLA_WRITEMEM (FRAD_LAST_IOCTL + 5) -#define SDLA_READMEM (FRAD_LAST_IOCTL + 6) - -struct sdla_mem { - int addr; - int len; - void __user *data; -}; - -#define SDLA_START (FRAD_LAST_IOCTL + 7) -#define SDLA_STOP (FRAD_LAST_IOCTL + 8) - -/* some offsets in the Z80's memory space */ -#define SDLA_NMIADDR 0x0000 -#define SDLA_CONF_ADDR 0x0010 -#define SDLA_S502A_NMIADDR 0x0066 -#define SDLA_CODE_BASEADDR 0x0100 -#define SDLA_WINDOW_SIZE 0x2000 -#define SDLA_ADDR_MASK 0x1FFF - -/* largest handleable block of data */ -#define SDLA_MAX_DATA 4080 -#define SDLA_MAX_MTU 4072 /* MAX_DATA - sizeof(fradhdr) */ -#define SDLA_MAX_DLCI 24 - -/* this should be the same as frad_conf */ -struct sdla_conf { - short station; - short config; - short kbaud; - short clocking; - short max_frm; - short T391; - short T392; - short N391; - short N392; - short N393; - short CIR_fwd; - short Bc_fwd; - short Be_fwd; - short CIR_bwd; - short Bc_bwd; - short Be_bwd; -}; - -/* this should be the same as dlci_conf */ -struct sdla_dlci_conf { - short config; - short CIR_fwd; - short Bc_fwd; - short Be_fwd; - short CIR_bwd; - short Bc_bwd; - short Be_bwd; - short Tc_fwd; - short Tc_bwd; - short Tf_max; - short Tb_max; -}; - - -#endif /* _UAPISDLA_H */ diff --git a/net/socket.c b/net/socket.c index 6e6cccc2104f..152b1dcf93c6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -64,7 +64,6 @@ #include #include #include -#include #include #include #include @@ -1027,17 +1026,6 @@ void vlan_ioctl_set(int (*hook) (struct net *, void __user *)) } EXPORT_SYMBOL(vlan_ioctl_set); -static DEFINE_MUTEX(dlci_ioctl_mutex); -static int (*dlci_ioctl_hook) (unsigned int, void __user *); - -void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) -{ - mutex_lock(&dlci_ioctl_mutex); - dlci_ioctl_hook = hook; - mutex_unlock(&dlci_ioctl_mutex); -} -EXPORT_SYMBOL(dlci_ioctl_set); - static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { @@ -1156,17 +1144,6 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = vlan_ioctl_hook(net, argp); mutex_unlock(&vlan_ioctl_mutex); break; - case SIOCADDDLCI: - case SIOCDELDLCI: - err = -ENOPKG; - if (!dlci_ioctl_hook) - request_module("dlci"); - - mutex_lock(&dlci_ioctl_mutex); - if (dlci_ioctl_hook) - err = dlci_ioctl_hook(cmd, argp); - mutex_unlock(&dlci_ioctl_mutex); - break; case SIOCGSKNS: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) @@ -3427,8 +3404,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBRDELBR: case SIOCGIFVLAN: case SIOCSIFVLAN: - case SIOCADDDLCI: - case SIOCDELDLCI: case SIOCGSKNS: case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: -- cgit v1.3-15-g9ac1 From 3f6719c7b62f0327c9091e26d0da10e65668229e Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 17 Nov 2020 23:29:28 +0000 Subject: bpf: Add bpf_bprm_opts_set helper The helper allows modification of certain bits on the linux_binprm struct starting with the secureexec bit which can be updated using the BPF_F_BPRM_SECUREEXEC flag. secureexec can be set by the LSM for privilege gaining executions to set the AT_SECURE auxv for glibc. When set, the dynamic linker disables the use of certain environment variables (like LD_PRELOAD). Signed-off-by: KP Singh Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201117232929.2156341-1-kpsingh@chromium.org --- include/uapi/linux/bpf.h | 16 ++++++++++++++++ kernel/bpf/bpf_lsm.c | 26 ++++++++++++++++++++++++++ scripts/bpf_helpers_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++ 4 files changed, 60 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 162999b12790..a52299b80b9d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3787,6 +3787,16 @@ union bpf_attr { * *ARG_PTR_TO_BTF_ID* of type *task_struct*. * Return * Pointer to the current task. + * + * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) + * Description + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * Return + * **-EINVAL** if invalid *flags* are passed, zero otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3948,6 +3958,7 @@ union bpf_attr { FN(task_storage_get), \ FN(task_storage_delete), \ FN(get_current_task_btf), \ + FN(bprm_opts_set), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4119,6 +4130,11 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_IP, }; +/* Flags for bpf_bprm_opts_set helper */ +enum { + BPF_F_BPRM_SECUREEXEC = (1ULL << 0), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 553107f4706a..b4f27a874092 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -51,6 +52,29 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return 0; } +/* Mask for all the currently supported BPRM option flags */ +#define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC + +BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags) +{ + if (flags & ~BPF_F_BRPM_OPTS_MASK) + return -EINVAL; + + bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC); + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm) + +const static struct bpf_func_proto bpf_bprm_opts_set_proto = { + .func = bpf_bprm_opts_set, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0], + .arg2_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -71,6 +95,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_storage_get_proto; case BPF_FUNC_task_storage_delete: return &bpf_task_storage_delete_proto; + case BPF_FUNC_bprm_opts_set: + return &bpf_bprm_opts_set_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 31484377b8b1..c5bc947a70ad 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -418,6 +418,7 @@ class PrinterHelpers(Printer): 'struct bpf_tcp_sock', 'struct bpf_tunnel_key', 'struct bpf_xfrm_state', + 'struct linux_binprm', 'struct pt_regs', 'struct sk_reuseport_md', 'struct sockaddr', @@ -465,6 +466,7 @@ class PrinterHelpers(Printer): 'struct bpf_tcp_sock', 'struct bpf_tunnel_key', 'struct bpf_xfrm_state', + 'struct linux_binprm', 'struct pt_regs', 'struct sk_reuseport_md', 'struct sockaddr', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 162999b12790..a52299b80b9d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3787,6 +3787,16 @@ union bpf_attr { * *ARG_PTR_TO_BTF_ID* of type *task_struct*. * Return * Pointer to the current task. + * + * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) + * Description + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * Return + * **-EINVAL** if invalid *flags* are passed, zero otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3948,6 +3958,7 @@ union bpf_attr { FN(task_storage_get), \ FN(task_storage_delete), \ FN(get_current_task_btf), \ + FN(bprm_opts_set), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4119,6 +4130,11 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_IP, }; +/* Flags for bpf_bprm_opts_set helper */ +enum { + BPF_F_BPRM_SECUREEXEC = (1ULL << 0), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ -- cgit v1.3-15-g9ac1 From d055126180564a57fe533728a4e93d0cb53d49b3 Mon Sep 17 00:00:00 2001 From: Dmitrii Banshchikov Date: Tue, 17 Nov 2020 18:45:49 +0000 Subject: bpf: Add bpf_ktime_get_coarse_ns helper The helper uses CLOCK_MONOTONIC_COARSE source of time that is less accurate but more performant. We have a BPF CGROUP_SKB firewall that supports event logging through bpf_perf_event_output(). Each event has a timestamp and currently we use bpf_ktime_get_ns() for it. Use of bpf_ktime_get_coarse_ns() saves ~15-20 ns in time required for event logging. bpf_ktime_get_ns(): EgressLogByRemoteEndpoint 113.82ns 8.79M bpf_ktime_get_coarse_ns(): EgressLogByRemoteEndpoint 95.40ns 10.48M Signed-off-by: Dmitrii Banshchikov Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201117184549.257280-1-me@ubique.spb.ru --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 13 +++++++++++++ kernel/trace/bpf_trace.c | 2 ++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 6 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 581b2a2e78eb..e1bcb6d7345c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1842,6 +1842,7 @@ extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; +extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a52299b80b9d..3ca6146f001a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3797,6 +3797,16 @@ union bpf_attr { * is cleared if the flag is not specified. * Return * **-EINVAL** if invalid *flags* are passed, zero otherwise. + * + * u64 bpf_ktime_get_coarse_ns(void) + * Description + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3959,6 +3969,7 @@ union bpf_attr { FN(task_storage_delete), \ FN(get_current_task_btf), \ FN(bprm_opts_set), \ + FN(ktime_get_coarse_ns), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 55454d2278b1..ff55cbcfbab4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2211,6 +2211,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; +const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 25520f5eeaf6..2c395deae279 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -167,6 +167,17 @@ const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_ktime_get_coarse_ns) +{ + return ktime_get_coarse_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = { + .func = bpf_ktime_get_coarse_ns, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + BPF_CALL_0(bpf_get_current_pid_tgid) { struct task_struct *task = current; @@ -685,6 +696,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 02986c7b90eb..d255bc9b2bfa 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1280,6 +1280,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a52299b80b9d..3ca6146f001a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3797,6 +3797,16 @@ union bpf_attr { * is cleared if the flag is not specified. * Return * **-EINVAL** if invalid *flags* are passed, zero otherwise. + * + * u64 bpf_ktime_get_coarse_ns(void) + * Description + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3959,6 +3969,7 @@ union bpf_attr { FN(task_storage_delete), \ FN(get_current_task_btf), \ FN(bprm_opts_set), \ + FN(ktime_get_coarse_ns), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.3-15-g9ac1 From ea7800565a128c1adafa1791ce80afd6016fe21c Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 10 Nov 2020 11:18:45 +0100 Subject: can: add optional DLC element to Classical CAN frame structure ISO 11898-1 Chapter 8.4.2.3 defines a 4 bit data length code (DLC) table which maps the DLC to the payload length of the CAN frame in bytes: DLC -> payload length 0 .. 8 -> 0 .. 8 9 .. 15 -> 8 Although the DLC values 8 .. 15 in Classical CAN always result in a payload length of 8 bytes these DLC values are transparently transmitted on the CAN bus. As the struct can_frame only provides a 'len' element (formerly 'can_dlc') which contains the plain payload length ( 0 .. 8 ) of the CAN frame, the raw DLC is not visible to the application programmer, e.g. for testing use-cases. To access the raw DLC values 9 .. 15 the len8_dlc element is introduced, which is only valid when the payload length 'len' is 8 and the DLC is greater than 8. The len8_dlc element is filled by the CAN interface driver and used for CAN frame creation by the CAN driver when the CAN_CTRLMODE_CC_LEN8_DLC flag is supported by the driver and enabled via netlink configuration interface. Reported-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20201110101852.1973-2-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can.h | 38 ++++++++++++++++++++++++-------------- include/uapi/linux/can/netlink.h | 1 + 2 files changed, 25 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index 6a6d2c7655ff..f75238ac6dce 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -84,6 +84,7 @@ typedef __u32 can_err_mask_t; /* CAN payload length and DLC definitions according to ISO 11898-1 */ #define CAN_MAX_DLC 8 +#define CAN_MAX_RAW_DLC 15 #define CAN_MAX_DLEN 8 /* CAN FD payload length and DLC definitions according to ISO 11898-7 */ @@ -91,23 +92,32 @@ typedef __u32 can_err_mask_t; #define CANFD_MAX_DLEN 64 /** - * struct can_frame - basic CAN frame structure - * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition - * @can_dlc: frame payload length in byte (0 .. 8) aka data length code - * N.B. the DLC field from ISO 11898-1 Chapter 8.4.2.3 has a 1:1 - * mapping of the 'data length code' to the real payload length - * @__pad: padding - * @__res0: reserved / padding - * @__res1: reserved / padding - * @data: CAN frame payload (up to 8 byte) + * struct can_frame - Classical CAN frame structure (aka CAN 2.0B) + * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition + * @len: CAN frame payload length in byte (0 .. 8) + * @can_dlc: deprecated name for CAN frame payload length in byte (0 .. 8) + * @__pad: padding + * @__res0: reserved / padding + * @len8_dlc: optional DLC value (9 .. 15) at 8 byte payload length + * len8_dlc contains values from 9 .. 15 when the payload length is + * 8 bytes but the DLC value (see ISO 11898-1) is greater then 8. + * CAN_CTRLMODE_CC_LEN8_DLC flag has to be enabled in CAN driver. + * @data: CAN frame payload (up to 8 byte) */ struct can_frame { canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */ - __u8 can_dlc; /* frame payload length in byte (0 .. CAN_MAX_DLEN) */ - __u8 __pad; /* padding */ - __u8 __res0; /* reserved / padding */ - __u8 __res1; /* reserved / padding */ - __u8 data[CAN_MAX_DLEN] __attribute__((aligned(8))); + union { + /* CAN frame payload length in byte (0 .. CAN_MAX_DLEN) + * was previously named can_dlc so we need to carry that + * name for legacy support + */ + __u8 len; + __u8 can_dlc; /* deprecated */ + }; + __u8 __pad; /* padding */ + __u8 __res0; /* reserved / padding */ + __u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */ + __u8 data[CAN_MAX_DLEN] __attribute__((aligned(8))); }; /* diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 6f598b73839e..f730d443b918 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -100,6 +100,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */ #define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */ #define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */ +#define CAN_CTRLMODE_CC_LEN8_DLC 0x100 /* Classic CAN DLC option */ /* * CAN device statistics -- cgit v1.3-15-g9ac1 From 94c23097f991cd4568388564b3d2816b0b83f924 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 19 Nov 2020 09:49:21 +0100 Subject: can: gw: support modification of Classical CAN DLCs Add support for data length code modifications for Classical CAN. The netlink configuration interface always allowed to pass any value that fits into a byte, therefore only the modification process had to be extended to handle the raw DLC represenation of Classical CAN frames. When a DLC value from 0 .. F is provided for Classical CAN frame modifications the 'len' value is modified as-is with the exception that potentially existing 9 .. F DLC values in the len8_dlc element are moved to the 'len' element for the modification operation by mod_retrieve_ccdlc(). After the modification the Classical CAN frame DLC information is brought back into the correct format by mod_store_ccdlc() which is filling 'len' and 'len8_dlc' accordingly. Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20201119084921.2621-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/gw.h | 4 +-- net/can/gw.c | 78 ++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 72 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/gw.h b/include/uapi/linux/can/gw.h index c2190bbe21d8..e4f0957554f3 100644 --- a/include/uapi/linux/can/gw.h +++ b/include/uapi/linux/can/gw.h @@ -98,8 +98,8 @@ enum { /* CAN frame elements that are affected by curr. 3 CAN frame modifications */ #define CGW_MOD_ID 0x01 -#define CGW_MOD_DLC 0x02 /* contains the data length in bytes */ -#define CGW_MOD_LEN CGW_MOD_DLC /* CAN FD length representation */ +#define CGW_MOD_DLC 0x02 /* Classical CAN data length code */ +#define CGW_MOD_LEN CGW_MOD_DLC /* CAN FD (plain) data length */ #define CGW_MOD_DATA 0x04 #define CGW_MOD_FLAGS 0x08 /* CAN FD flags */ diff --git a/net/can/gw.c b/net/can/gw.c index de5e8859ec9b..8598d9da0e5f 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -199,6 +199,68 @@ static void mod_set_fddata(struct canfd_frame *cf, struct cf_mod *mod) memcpy(cf->data, mod->modframe.set.data, CANFD_MAX_DLEN); } +/* retrieve valid CC DLC value and store it into 'len' */ +static void mod_retrieve_ccdlc(struct canfd_frame *cf) +{ + struct can_frame *ccf = (struct can_frame *)cf; + + /* len8_dlc is only valid if len == CAN_MAX_DLEN */ + if (ccf->len != CAN_MAX_DLEN) + return; + + /* do we have a valid len8_dlc value from 9 .. 15 ? */ + if (ccf->len8_dlc > CAN_MAX_DLEN && ccf->len8_dlc <= CAN_MAX_RAW_DLC) + ccf->len = ccf->len8_dlc; +} + +/* convert valid CC DLC value in 'len' into struct can_frame elements */ +static void mod_store_ccdlc(struct canfd_frame *cf) +{ + struct can_frame *ccf = (struct can_frame *)cf; + + /* clear potential leftovers */ + ccf->len8_dlc = 0; + + /* plain data length 0 .. 8 - that was easy */ + if (ccf->len <= CAN_MAX_DLEN) + return; + + /* potentially broken values are catched in can_can_gw_rcv() */ + if (ccf->len > CAN_MAX_RAW_DLC) + return; + + /* we have a valid dlc value from 9 .. 15 in ccf->len */ + ccf->len8_dlc = ccf->len; + ccf->len = CAN_MAX_DLEN; +} + +static void mod_and_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) +{ + mod_retrieve_ccdlc(cf); + mod_and_len(cf, mod); + mod_store_ccdlc(cf); +} + +static void mod_or_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) +{ + mod_retrieve_ccdlc(cf); + mod_or_len(cf, mod); + mod_store_ccdlc(cf); +} + +static void mod_xor_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) +{ + mod_retrieve_ccdlc(cf); + mod_xor_len(cf, mod); + mod_store_ccdlc(cf); +} + +static void mod_set_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) +{ + mod_set_len(cf, mod); + mod_store_ccdlc(cf); +} + static void canframecpy(struct canfd_frame *dst, struct can_frame *src) { /* Copy the struct members separately to ensure that no uninitialized @@ -842,8 +904,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; - if (mb.modtype & CGW_MOD_LEN) - mod->modfunc[modidx++] = mod_and_len; + if (mb.modtype & CGW_MOD_DLC) + mod->modfunc[modidx++] = mod_and_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_data; @@ -858,8 +920,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; - if (mb.modtype & CGW_MOD_LEN) - mod->modfunc[modidx++] = mod_or_len; + if (mb.modtype & CGW_MOD_DLC) + mod->modfunc[modidx++] = mod_or_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_data; @@ -874,8 +936,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; - if (mb.modtype & CGW_MOD_LEN) - mod->modfunc[modidx++] = mod_xor_len; + if (mb.modtype & CGW_MOD_DLC) + mod->modfunc[modidx++] = mod_xor_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_data; @@ -890,8 +952,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; - if (mb.modtype & CGW_MOD_LEN) - mod->modfunc[modidx++] = mod_set_len; + if (mb.modtype & CGW_MOD_DLC) + mod->modfunc[modidx++] = mod_set_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_data; -- cgit v1.3-15-g9ac1 From f460019b4c9e0389b932e1ca2c01b598c7ae769e Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 24 Nov 2020 18:40:54 +0200 Subject: net: sched: alias action flags with TCA_ACT_ prefix Currently both filter and action flags use same "TCA_" prefix which makes them hard to distinguish to code and confusing for users. Create aliases for existing action flags constants with "TCA_ACT_" prefix. Signed-off-by: Vlad Buslov Link: https://lore.kernel.org/r/20201124164054.893168-1-vlad@buslov.dev Signed-off-by: Jakub Kicinski --- include/uapi/linux/rtnetlink.h | 12 +++++++----- net/sched/act_api.c | 10 +++++----- 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 2ffbef5da6c1..b841caa4657e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -768,16 +768,18 @@ enum { #define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg)) /* tcamsg flags stored in attribute TCA_ROOT_FLAGS * - * TCA_FLAG_LARGE_DUMP_ON user->kernel to request for larger than TCA_ACT_MAX_PRIO - * actions in a dump. All dump responses will contain the number of actions - * being dumped stored in for user app's consumption in TCA_ROOT_COUNT + * TCA_ACT_FLAG_LARGE_DUMP_ON user->kernel to request for larger than + * TCA_ACT_MAX_PRIO actions in a dump. All dump responses will contain the + * number of actions being dumped stored in for user app's consumption in + * TCA_ROOT_COUNT * - * TCA_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only + * TCA_ACT_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only * includes essential action info (kind, index, etc.) * */ #define TCA_FLAG_LARGE_DUMP_ON (1 << 0) -#define TCA_FLAG_TERSE_DUMP (1 << 1) +#define TCA_ACT_FLAG_LARGE_DUMP_ON TCA_FLAG_LARGE_DUMP_ON +#define TCA_ACT_FLAG_TERSE_DUMP (1 << 1) /* New extended info filters for IFLA_EXT_MASK */ #define RTEXT_FILTER_VF (1 << 0) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index fc23f46a315c..99db1c77426b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -278,7 +278,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, index--; goto nla_put_failure; } - err = (act_flags & TCA_FLAG_TERSE_DUMP) ? + err = (act_flags & TCA_ACT_FLAG_TERSE_DUMP) ? tcf_action_dump_terse(skb, p, true) : tcf_action_dump_1(skb, p, 0, 0); if (err < 0) { @@ -288,7 +288,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, } nla_nest_end(skb, nest); n_i++; - if (!(act_flags & TCA_FLAG_LARGE_DUMP_ON) && + if (!(act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) && n_i >= TCA_ACT_MAX_PRIO) goto done; } @@ -298,7 +298,7 @@ done: mutex_unlock(&idrinfo->lock); if (n_i) { - if (act_flags & TCA_FLAG_LARGE_DUMP_ON) + if (act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) cb->args[1] = n_i; } return n_i; @@ -1473,8 +1473,8 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, } static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = { - [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON | - TCA_FLAG_TERSE_DUMP), + [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAG_LARGE_DUMP_ON | + TCA_ACT_FLAG_TERSE_DUMP), [TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 }, }; -- cgit v1.3-15-g9ac1 From bfd042321a7afa769c855c37f2bbe2703dc72ef2 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 24 Nov 2020 09:25:25 +0100 Subject: bridge: mrp: Implement LC mode for MRP Extend MRP to support LC mode(link check) for the interconnect port. This applies only to the interconnect ring. Opposite to RC mode(ring check) the LC mode is using CFM frames to detect when the link goes up or down and based on that the userspace will need to react. One advantage of the LC mode over RC mode is that there will be fewer frames in the normal rings. Because RC mode generates InTest on all ports while LC mode sends CFM frame only on the interconnect port. All 4 nodes part of the interconnect ring needs to have the same mode. And it is not possible to have running LC and RC mode at the same time on a node. Whenever the MIM starts it needs to detect the status of the other 3 nodes in the interconnect ring so it would send a frame called InLinkStatus, on which the clients needs to reply with their link status. This patch adds InLinkStatus frame type and extends existing rules on how to forward this frame. Acked-by: Nikolay Aleksandrov Signed-off-by: Horatiu Vultur Link: https://lore.kernel.org/r/20201124082525.273820-1-horatiu.vultur@microchip.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/mrp_bridge.h | 1 + net/bridge/br_mrp.c | 18 +++++++++++++++--- 2 files changed, 16 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h index 6aeb13ef0b1e..9744773de5ff 100644 --- a/include/uapi/linux/mrp_bridge.h +++ b/include/uapi/linux/mrp_bridge.h @@ -61,6 +61,7 @@ enum br_mrp_tlv_header_type { BR_MRP_TLV_HEADER_IN_TOPO = 0x7, BR_MRP_TLV_HEADER_IN_LINK_DOWN = 0x8, BR_MRP_TLV_HEADER_IN_LINK_UP = 0x9, + BR_MRP_TLV_HEADER_IN_LINK_STATUS = 0xa, BR_MRP_TLV_HEADER_OPTION = 0x7f, }; diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index bb12fbf9aaf2..cec2c4e4561d 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -858,7 +858,8 @@ static bool br_mrp_in_frame(struct sk_buff *skb) if (hdr->type == BR_MRP_TLV_HEADER_IN_TEST || hdr->type == BR_MRP_TLV_HEADER_IN_TOPO || hdr->type == BR_MRP_TLV_HEADER_IN_LINK_DOWN || - hdr->type == BR_MRP_TLV_HEADER_IN_LINK_UP) + hdr->type == BR_MRP_TLV_HEADER_IN_LINK_UP || + hdr->type == BR_MRP_TLV_HEADER_IN_LINK_STATUS) return true; return false; @@ -1126,9 +1127,9 @@ static int br_mrp_rcv(struct net_bridge_port *p, goto no_forward; } } else { - /* MIM should forward IntLinkChange and + /* MIM should forward IntLinkChange/Status and * IntTopoChange between ring ports but MIM - * should not forward IntLinkChange and + * should not forward IntLinkChange/Status and * IntTopoChange if the frame was received at * the interconnect port */ @@ -1155,6 +1156,17 @@ static int br_mrp_rcv(struct net_bridge_port *p, in_type == BR_MRP_TLV_HEADER_IN_LINK_DOWN)) goto forward; + /* MIC should forward IntLinkStatus frames only to + * interconnect port if it was received on a ring port. + * If it is received on interconnect port then, it + * should be forward on both ring ports + */ + if (br_mrp_is_ring_port(p_port, s_port, p) && + in_type == BR_MRP_TLV_HEADER_IN_LINK_STATUS) { + p_dst = NULL; + s_dst = NULL; + } + /* Should forward the InTopo frames only between the * ring ports */ -- cgit v1.3-15-g9ac1 From 27672f0d280a3f286a410a8db2004f46ace72a17 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 24 Nov 2020 15:12:09 +0000 Subject: bpf: Add a BPF helper for getting the IMA hash of an inode Provide a wrapper function to get the IMA hash of an inode. This helper is useful in fingerprinting files (e.g executables on execution) and using these fingerprints in detections like an executable unlinking itself. Since the ima_inode_hash can sleep, it's only allowed for sleepable LSM hooks. Signed-off-by: KP Singh Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201124151210.1081188-3-kpsingh@chromium.org --- include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/bpf_lsm.c | 26 ++++++++++++++++++++++++++ scripts/bpf_helpers_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 4 files changed, 50 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3ca6146f001a..c3458ec1f30a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3807,6 +3807,16 @@ union bpf_attr { * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) * Return * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's avaialable). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3970,6 +3980,7 @@ union bpf_attr { FN(get_current_task_btf), \ FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ + FN(ima_inode_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index b4f27a874092..70e5e0b6d69d 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -15,6 +15,7 @@ #include #include #include +#include /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -75,6 +76,29 @@ const static struct bpf_func_proto bpf_bprm_opts_set_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size) +{ + return ima_inode_hash(inode, dst, size); +} + +static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog) +{ + return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); +} + +BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) + +const static struct bpf_func_proto bpf_ima_inode_hash_proto = { + .func = bpf_ima_inode_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, + .allowed = bpf_ima_inode_hash_allowed, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -97,6 +121,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_storage_delete_proto; case BPF_FUNC_bprm_opts_set: return &bpf_bprm_opts_set_proto; + case BPF_FUNC_ima_inode_hash: + return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index c5bc947a70ad..8b829748d488 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -436,6 +436,7 @@ class PrinterHelpers(Printer): 'struct xdp_md', 'struct path', 'struct btf_ptr', + 'struct inode', ] known_types = { '...', @@ -480,6 +481,7 @@ class PrinterHelpers(Printer): 'struct task_struct', 'struct path', 'struct btf_ptr', + 'struct inode', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3ca6146f001a..c3458ec1f30a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3807,6 +3807,16 @@ union bpf_attr { * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) * Return * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's avaialable). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3970,6 +3980,7 @@ union bpf_attr { FN(get_current_task_btf), \ FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ + FN(ima_inode_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.3-15-g9ac1 From 923c40c4651ed8b30cbd9fbac0f0ab612216cccc Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Tue, 24 Nov 2020 18:24:47 +0300 Subject: net/tls: add CHACHA20-POLY1305 specific defines and structures To provide support for ChaCha-Poly cipher we need to define specific constants and structures. Signed-off-by: Vadim Fedorenko Signed-off-by: Jakub Kicinski --- include/net/tls.h | 1 + include/uapi/linux/tls.h | 15 +++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/tls.h b/include/net/tls.h index d04ce73e54c9..e4e9c2ae689e 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -211,6 +211,7 @@ union tls_crypto_context { union { struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; struct tls12_crypto_info_aes_gcm_256 aes_gcm_256; + struct tls12_crypto_info_chacha20_poly1305 chacha20_poly1305; }; }; diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index bcd2869ed472..0d54baea1d8d 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -77,6 +77,13 @@ #define TLS_CIPHER_AES_CCM_128_TAG_SIZE 16 #define TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE 8 +#define TLS_CIPHER_CHACHA20_POLY1305 54 +#define TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE 12 +#define TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE 32 +#define TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE 0 +#define TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE 16 +#define TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE 8 + #define TLS_SET_RECORD_TYPE 1 #define TLS_GET_RECORD_TYPE 2 @@ -109,6 +116,14 @@ struct tls12_crypto_info_aes_ccm_128 { unsigned char rec_seq[TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE]; }; +struct tls12_crypto_info_chacha20_poly1305 { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE]; + unsigned char key[TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE]; +}; + enum { TLS_INFO_UNSPEC, TLS_INFO_VERSION, -- cgit v1.3-15-g9ac1 From e8372d9d21451a2f2947c2b63b5184f3d4d0bff9 Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Tue, 1 Dec 2020 20:20:43 +0100 Subject: net/smc: Introduce generic netlink interface for diagnostic purposes Introduce generic netlink interface infrastructure to expose the diagnostic information regarding smc linkgroups, links and devices. Signed-off-by: Guvenc Gulce Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- include/uapi/linux/smc.h | 11 ++++++++++ net/smc/Makefile | 2 +- net/smc/af_smc.c | 10 ++++++++- net/smc/smc_netlink.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_netlink.h | 23 +++++++++++++++++++++ 5 files changed, 97 insertions(+), 2 deletions(-) create mode 100644 net/smc/smc_netlink.c create mode 100644 net/smc/smc_netlink.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 0e11ca421ca4..b604d64542e8 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -33,4 +33,15 @@ enum { /* SMC PNET Table commands */ #define SMCR_GENL_FAMILY_NAME "SMC_PNETID" #define SMCR_GENL_FAMILY_VERSION 1 +/* gennetlink interface to access non-socket information from SMC module */ +#define SMC_GENL_FAMILY_NAME "SMC_GEN_NETLINK" +#define SMC_GENL_FAMILY_VERSION 1 + +/* SMC_GENL_FAMILY top level attributes */ +enum { + SMC_GEN_UNSPEC, + __SMC_GEN_MAX, + SMC_GEN_MAX = __SMC_GEN_MAX - 1 +}; + #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/Makefile b/net/smc/Makefile index cb1254541f37..77e54fe42b1c 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -2,4 +2,4 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o -smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o +smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index f79b59a972f0..47340b3b514f 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -45,6 +45,7 @@ #include "smc_ib.h" #include "smc_ism.h" #include "smc_pnet.h" +#include "smc_netlink.h" #include "smc_tx.h" #include "smc_rx.h" #include "smc_close.h" @@ -2495,10 +2496,14 @@ static int __init smc_init(void) smc_ism_init(); smc_clc_init(); - rc = smc_pnet_init(); + rc = smc_nl_init(); if (rc) goto out_pernet_subsys; + rc = smc_pnet_init(); + if (rc) + goto out_nl; + rc = -ENOMEM; smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0); if (!smc_hs_wq) @@ -2569,6 +2574,8 @@ out_alloc_hs_wq: destroy_workqueue(smc_hs_wq); out_pnet: smc_pnet_exit(); +out_nl: + smc_nl_exit(); out_pernet_subsys: unregister_pernet_subsys(&smc_net_ops); @@ -2586,6 +2593,7 @@ static void __exit smc_exit(void) proto_unregister(&smc_proto6); proto_unregister(&smc_proto); smc_pnet_exit(); + smc_nl_exit(); unregister_pernet_subsys(&smc_net_ops); rcu_barrier(); } diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c new file mode 100644 index 000000000000..4f964d03b372 --- /dev/null +++ b/net/smc/smc_netlink.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Generic netlink support functions to interact with SMC module + * + * Copyright IBM Corp. 2020 + * + * Author(s): Guvenc Gulce + */ + +#include +#include +#include +#include +#include +#include + +#include "smc_core.h" +#include "smc_netlink.h" + +#define SMC_CMD_MAX_ATTR 1 + +/* SMC_GENL generic netlink operation definition */ +static const struct genl_ops smc_gen_nl_ops[] = { +}; + +static const struct nla_policy smc_gen_nl_policy[2] = { + [SMC_CMD_MAX_ATTR] = { .type = NLA_REJECT, }, +}; + +/* SMC_GENL family definition */ +struct genl_family smc_gen_nl_family __ro_after_init = { + .hdrsize = 0, + .name = SMC_GENL_FAMILY_NAME, + .version = SMC_GENL_FAMILY_VERSION, + .maxattr = SMC_CMD_MAX_ATTR, + .policy = smc_gen_nl_policy, + .netnsok = true, + .module = THIS_MODULE, + .ops = smc_gen_nl_ops, + .n_ops = ARRAY_SIZE(smc_gen_nl_ops) +}; + +int __init smc_nl_init(void) +{ + return genl_register_family(&smc_gen_nl_family); +} + +void smc_nl_exit(void) +{ + genl_unregister_family(&smc_gen_nl_family); +} diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h new file mode 100644 index 000000000000..0c757232c0d0 --- /dev/null +++ b/net/smc/smc_netlink.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * SMC Generic netlink operations + * + * Copyright IBM Corp. 2020 + * + * Author(s): Guvenc Gulce + */ + +#ifndef _SMC_NETLINK_H +#define _SMC_NETLINK_H + +#include +#include + +extern struct genl_family smc_gen_nl_family; + +int smc_nl_init(void) __init; +void smc_nl_exit(void); + +#endif -- cgit v1.3-15-g9ac1 From 099b990bd11a3a96b5d59973f482018e5cbde6c3 Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Tue, 1 Dec 2020 20:20:44 +0100 Subject: net/smc: Add support for obtaining system information Add new netlink command to obtain system information of the smc module. Signed-off-by: Guvenc Gulce Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- include/uapi/linux/smc.h | 18 +++++++++++++++ net/smc/smc_clc.c | 5 ++++ net/smc/smc_clc.h | 1 + net/smc/smc_core.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_core.h | 2 ++ net/smc/smc_netlink.c | 5 ++++ net/smc/smc_netlink.h | 9 ++++++++ 7 files changed, 100 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index b604d64542e8..1b8d4e770be9 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -37,11 +37,29 @@ enum { /* SMC PNET Table commands */ #define SMC_GENL_FAMILY_NAME "SMC_GEN_NETLINK" #define SMC_GENL_FAMILY_VERSION 1 +/* SMC_GENL_FAMILY commands */ +enum { + SMC_NETLINK_GET_SYS_INFO = 1, +}; + /* SMC_GENL_FAMILY top level attributes */ enum { SMC_GEN_UNSPEC, + SMC_GEN_SYS_INFO, /* nest */ __SMC_GEN_MAX, SMC_GEN_MAX = __SMC_GEN_MAX - 1 }; +/* SMC_GEN_SYS_INFO attributes */ +enum { + SMC_NLA_SYS_UNSPEC, + SMC_NLA_SYS_VER, /* u8 */ + SMC_NLA_SYS_REL, /* u8 */ + SMC_NLA_SYS_IS_ISM_V2, /* u8 */ + SMC_NLA_SYS_LOCAL_HOST, /* string */ + SMC_NLA_SYS_SEID, /* string */ + __SMC_NLA_SYS_MAX, + SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1 +}; + #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 696d89c2dce4..e286dafd6e88 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -772,6 +772,11 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, return len > 0 ? 0 : len; } +void smc_clc_get_hostname(u8 **host) +{ + *host = &smc_hostname[0]; +} + void __init smc_clc_init(void) { struct new_utsname *u; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 49752c997c51..32d37f7b70f2 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -334,5 +334,6 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact, u8 version); void smc_clc_init(void) __init; +void smc_clc_get_hostname(u8 **host); #endif diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 0088511e30bf..c7b1c62c2f2e 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -16,6 +16,8 @@ #include #include #include +#include +#include #include #include #include @@ -30,6 +32,7 @@ #include "smc_cdc.h" #include "smc_close.h" #include "smc_ism.h" +#include "smc_netlink.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) @@ -214,6 +217,63 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) conn->lgr = NULL; } +int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + char hostname[SMC_MAX_HOSTNAME_LEN + 1]; + char smc_seid[SMC_MAX_EID_LEN + 1]; + struct smcd_dev *smcd_dev; + struct nlattr *attrs; + u8 *seid = NULL; + u8 *host = NULL; + void *nlh; + + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_SYS_INFO); + if (!nlh) + goto errmsg; + if (cb_ctx->pos[0]) + goto errout; + attrs = nla_nest_start(skb, SMC_GEN_SYS_INFO); + if (!attrs) + goto errout; + if (nla_put_u8(skb, SMC_NLA_SYS_VER, SMC_V2)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_SYS_REL, SMC_RELEASE)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) + goto errattr; + smc_clc_get_hostname(&host); + if (host) { + snprintf(hostname, sizeof(hostname), "%s", host); + if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname)) + goto errattr; + } + mutex_lock(&smcd_dev_list.mutex); + smcd_dev = list_first_entry_or_null(&smcd_dev_list.list, + struct smcd_dev, list); + if (smcd_dev) + smc_ism_get_system_eid(smcd_dev, &seid); + mutex_unlock(&smcd_dev_list.mutex); + if (seid && smc_ism_is_v2_capable()) { + snprintf(smc_seid, sizeof(smc_seid), "%s", seid); + if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid)) + goto errattr; + } + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + cb_ctx->pos[0] = 1; + return skb->len; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return skb->len; +} + void smc_lgr_cleanup_early(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 3a1bb8e4b81f..eaed25d4e76b 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -14,6 +14,7 @@ #include #include +#include #include "smc.h" #include "smc_ib.h" @@ -413,6 +414,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr, struct smc_link *from_lnk, bool is_dev_err); void smcr_link_down_cond(struct smc_link *lnk); void smcr_link_down_cond_sched(struct smc_link *lnk); +int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) { diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 4f964d03b372..ce06d269a54b 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -23,6 +23,11 @@ /* SMC_GENL generic netlink operation definition */ static const struct genl_ops smc_gen_nl_ops[] = { + { + .cmd = SMC_NETLINK_GET_SYS_INFO, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_get_sys_info, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h index 0c757232c0d0..3477265cba6c 100644 --- a/net/smc/smc_netlink.h +++ b/net/smc/smc_netlink.h @@ -17,6 +17,15 @@ extern struct genl_family smc_gen_nl_family; +struct smc_nl_dmp_ctx { + int pos[2]; +}; + +static inline struct smc_nl_dmp_ctx *smc_nl_dmp_ctx(struct netlink_callback *c) +{ + return (struct smc_nl_dmp_ctx *)c->ctx; +} + int smc_nl_init(void) __init; void smc_nl_exit(void); -- cgit v1.3-15-g9ac1 From e9b8c845cb342a3ab3d92235a54d0d1ad06d7204 Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Tue, 1 Dec 2020 20:20:45 +0100 Subject: net/smc: Introduce SMCR get linkgroup command Introduce get linkgroup command which loops through all available SMCR linkgroups. It uses the SMC-R linkgroup list as entry point, not the socket list, which makes linkgroup diagnosis possible, in case linkgroup does not contain active connections anymore. Signed-off-by: Guvenc Gulce Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- include/uapi/linux/smc.h | 15 +++++++++ net/smc/smc_core.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_core.h | 1 + net/smc/smc_netlink.c | 5 +++ 4 files changed, 106 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 1b8d4e770be9..3ae8ca4e5256 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -40,12 +40,14 @@ enum { /* SMC PNET Table commands */ /* SMC_GENL_FAMILY commands */ enum { SMC_NETLINK_GET_SYS_INFO = 1, + SMC_NETLINK_GET_LGR_SMCR, }; /* SMC_GENL_FAMILY top level attributes */ enum { SMC_GEN_UNSPEC, SMC_GEN_SYS_INFO, /* nest */ + SMC_GEN_LGR_SMCR, /* nest */ __SMC_GEN_MAX, SMC_GEN_MAX = __SMC_GEN_MAX - 1 }; @@ -62,4 +64,17 @@ enum { SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1 }; +/* SMC_GEN_LGR_SMCR attributes */ +enum { + SMC_NLA_LGR_R_UNSPEC, + SMC_NLA_LGR_R_ID, /* u32 */ + SMC_NLA_LGR_R_ROLE, /* u8 */ + SMC_NLA_LGR_R_TYPE, /* u8 */ + SMC_NLA_LGR_R_PNETID, /* string */ + SMC_NLA_LGR_R_VLAN_ID, /* u8 */ + SMC_NLA_LGR_R_CONNS_NUM, /* u32 */ + __SMC_NLA_LGR_R_MAX, + SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 +}; + #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index c7b1c62c2f2e..e21d068191ad 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -274,6 +274,91 @@ errmsg: return skb->len; } +static int smc_nl_fill_lgr(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_target[SMC_MAX_PNETID_LEN + 1]; + struct nlattr *attrs; + + attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); + if (!attrs) + goto errout; + + if (nla_put_u32(skb, SMC_NLA_LGR_R_ID, *((u32 *)&lgr->id))) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LGR_R_CONNS_NUM, lgr->conns_num)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_ROLE, lgr->role)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id)) + goto errattr; + snprintf(smc_target, sizeof(smc_target), "%s", lgr->pnet_id); + if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_handle_lgr(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + void *nlh; + + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_LGR_SMCR); + if (!nlh) + goto errmsg; + if (smc_nl_fill_lgr(lgr, skb, cb)) + goto errout; + + genlmsg_end(skb, nlh); + return 0; + +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct smc_link_group *lgr; + int snum = cb_ctx->pos[0]; + int num = 0; + + spin_lock_bh(&smc_lgr->lock); + list_for_each_entry(lgr, &smc_lgr->list, list) { + if (num < snum) + goto next; + if (smc_nl_handle_lgr(lgr, skb, cb)) + goto errout; +next: + num++; + } +errout: + spin_unlock_bh(&smc_lgr->lock); + cb_ctx->pos[0] = num; +} + +int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) +{ + smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb); + return skb->len; +} + void smc_lgr_cleanup_early(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index eaed25d4e76b..662315beb605 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -415,6 +415,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr, void smcr_link_down_cond(struct smc_link *lnk); void smcr_link_down_cond_sched(struct smc_link *lnk); int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb); +int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) { diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index ce06d269a54b..490da56c8d3c 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -28,6 +28,11 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smc_nl_get_sys_info, }, + { + .cmd = SMC_NETLINK_GET_LGR_SMCR, + /* can be retrieved by unprivileged users */ + .dumpit = smcr_nl_get_lgr, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { -- cgit v1.3-15-g9ac1 From 5a7e09d58f3fe2f0d5e8f0da4b1f686491245eb5 Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Tue, 1 Dec 2020 20:20:46 +0100 Subject: net/smc: Introduce SMCR get link command Introduce get link command which loops through all available links of all available link groups. It uses the SMC-R linkgroup list as entry point, not the socket list, which makes linkgroup diagnosis possible, in case linkgroup does not contain active connections anymore. Signed-off-by: Guvenc Gulce Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- include/uapi/linux/smc.h | 18 ++++++++++ net/smc/smc_core.c | 91 +++++++++++++++++++++++++++++++++++++++++++++--- net/smc/smc_core.h | 14 ++++++++ net/smc/smc_diag.c | 13 ------- net/smc/smc_netlink.c | 5 +++ 5 files changed, 124 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 3ae8ca4e5256..ed638dbfff08 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -41,6 +41,7 @@ enum { /* SMC PNET Table commands */ enum { SMC_NETLINK_GET_SYS_INFO = 1, SMC_NETLINK_GET_LGR_SMCR, + SMC_NETLINK_GET_LINK_SMCR, }; /* SMC_GENL_FAMILY top level attributes */ @@ -48,6 +49,7 @@ enum { SMC_GEN_UNSPEC, SMC_GEN_SYS_INFO, /* nest */ SMC_GEN_LGR_SMCR, /* nest */ + SMC_GEN_LINK_SMCR, /* nest */ __SMC_GEN_MAX, SMC_GEN_MAX = __SMC_GEN_MAX - 1 }; @@ -77,4 +79,20 @@ enum { SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; +/* SMC_GEN_LINK_SMCR attributes */ +enum { + SMC_NLA_LINK_UNSPEC, + SMC_NLA_LINK_ID, /* u8 */ + SMC_NLA_LINK_IB_DEV, /* string */ + SMC_NLA_LINK_IB_PORT, /* u8 */ + SMC_NLA_LINK_GID, /* string */ + SMC_NLA_LINK_PEER_GID, /* string */ + SMC_NLA_LINK_CONN_CNT, /* u32 */ + SMC_NLA_LINK_NET_DEV, /* u32 */ + SMC_NLA_LINK_UID, /* u32 */ + SMC_NLA_LINK_PEER_UID, /* u32 */ + SMC_NLA_LINK_STATE, /* u32 */ + __SMC_NLA_LINK_MAX, + SMC_NLA_LINK_MAX = __SMC_NLA_LINK_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index e21d068191ad..5ad4b742dcc1 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -307,11 +307,74 @@ errout: return -EMSGSIZE; } +static int smc_nl_fill_lgr_link(struct smc_link_group *lgr, + struct smc_link *link, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_ibname[IB_DEVICE_NAME_MAX + 1]; + u8 smc_gid_target[41]; + struct nlattr *attrs; + u32 link_uid = 0; + void *nlh; + + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_LINK_SMCR); + if (!nlh) + goto errmsg; + + attrs = nla_nest_start(skb, SMC_GEN_LINK_SMCR); + if (!attrs) + goto errout; + + if (nla_put_u8(skb, SMC_NLA_LINK_ID, link->link_id)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LINK_STATE, link->state)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LINK_CONN_CNT, + atomic_read(&link->conn_cnt))) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LINK_IB_PORT, link->ibport)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LINK_NET_DEV, link->ndev_ifidx)) + goto errattr; + snprintf(smc_ibname, sizeof(smc_ibname), "%s", link->ibname); + if (nla_put_string(skb, SMC_NLA_LINK_IB_DEV, smc_ibname)) + goto errattr; + memcpy(&link_uid, link->link_uid, sizeof(link_uid)); + if (nla_put_u32(skb, SMC_NLA_LINK_UID, link_uid)) + goto errattr; + memcpy(&link_uid, link->peer_link_uid, sizeof(link_uid)); + if (nla_put_u32(skb, SMC_NLA_LINK_PEER_UID, link_uid)) + goto errattr; + memset(smc_gid_target, 0, sizeof(smc_gid_target)); + smc_gid_be16_convert(smc_gid_target, link->gid); + if (nla_put_string(skb, SMC_NLA_LINK_GID, smc_gid_target)) + goto errattr; + memset(smc_gid_target, 0, sizeof(smc_gid_target)); + smc_gid_be16_convert(smc_gid_target, link->peer_gid); + if (nla_put_string(skb, SMC_NLA_LINK_PEER_GID, smc_gid_target)) + goto errattr; + + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return 0; +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + static int smc_nl_handle_lgr(struct smc_link_group *lgr, struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb, + bool list_links) { void *nlh; + int i; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, @@ -322,6 +385,15 @@ static int smc_nl_handle_lgr(struct smc_link_group *lgr, goto errout; genlmsg_end(skb, nlh); + if (!list_links) + goto out; + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (!smc_link_usable(&lgr->lnk[i])) + continue; + if (smc_nl_fill_lgr_link(lgr, &lgr->lnk[i], skb, cb)) + goto errout; + } +out: return 0; errout: @@ -332,7 +404,8 @@ errmsg: static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr, struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb, + bool list_links) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smc_link_group *lgr; @@ -343,7 +416,7 @@ static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr, list_for_each_entry(lgr, &smc_lgr->list, list) { if (num < snum) goto next; - if (smc_nl_handle_lgr(lgr, skb, cb)) + if (smc_nl_handle_lgr(lgr, skb, cb, list_links)) goto errout; next: num++; @@ -355,7 +428,17 @@ errout: int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) { - smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb); + bool list_links = false; + + smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); + return skb->len; +} + +int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb) +{ + bool list_links = true; + + smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); return skb->len; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 662315beb605..7995621f318d 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -367,6 +367,19 @@ static inline bool smc_link_active(struct smc_link *lnk) return lnk->state == SMC_LNK_ACTIVE; } +static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) +{ + sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", + be16_to_cpu(((__be16 *)gid_raw)[0]), + be16_to_cpu(((__be16 *)gid_raw)[1]), + be16_to_cpu(((__be16 *)gid_raw)[2]), + be16_to_cpu(((__be16 *)gid_raw)[3]), + be16_to_cpu(((__be16 *)gid_raw)[4]), + be16_to_cpu(((__be16 *)gid_raw)[5]), + be16_to_cpu(((__be16 *)gid_raw)[6]), + be16_to_cpu(((__be16 *)gid_raw)[7])); +} + struct smc_sock; struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; @@ -416,6 +429,7 @@ void smcr_link_down_cond(struct smc_link *lnk); void smcr_link_down_cond_sched(struct smc_link *lnk); int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb); int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); +int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) { diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index c2225231f679..c952986a6aca 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -31,19 +31,6 @@ static struct smc_diag_dump_ctx *smc_dump_context(struct netlink_callback *cb) return (struct smc_diag_dump_ctx *)cb->ctx; } -static void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) -{ - sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", - be16_to_cpu(((__be16 *)gid_raw)[0]), - be16_to_cpu(((__be16 *)gid_raw)[1]), - be16_to_cpu(((__be16 *)gid_raw)[2]), - be16_to_cpu(((__be16 *)gid_raw)[3]), - be16_to_cpu(((__be16 *)gid_raw)[4]), - be16_to_cpu(((__be16 *)gid_raw)[5]), - be16_to_cpu(((__be16 *)gid_raw)[6]), - be16_to_cpu(((__be16 *)gid_raw)[7])); -} - static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) { struct smc_sock *smc = smc_sk(sk); diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 490da56c8d3c..a41f78f488a2 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -33,6 +33,11 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smcr_nl_get_lgr, }, + { + .cmd = SMC_NETLINK_GET_LINK_SMCR, + /* can be retrieved by unprivileged users */ + .dumpit = smcr_nl_get_link, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { -- cgit v1.3-15-g9ac1 From 8f9dde4bf230f5c54a24c42a989dd9d88ec95695 Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Tue, 1 Dec 2020 20:20:47 +0100 Subject: net/smc: Add SMC-D Linkgroup diagnostic support Deliver SMCD Linkgroup information via netlink based diagnostic interface. Signed-off-by: Guvenc Gulce Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- include/uapi/linux/smc.h | 27 ++++++++++ net/smc/smc_core.c | 130 +++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_core.h | 1 + net/smc/smc_netlink.c | 5 ++ 4 files changed, 163 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index ed638dbfff08..707e8af4f0c8 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -42,6 +42,7 @@ enum { SMC_NETLINK_GET_SYS_INFO = 1, SMC_NETLINK_GET_LGR_SMCR, SMC_NETLINK_GET_LINK_SMCR, + SMC_NETLINK_GET_LGR_SMCD, }; /* SMC_GENL_FAMILY top level attributes */ @@ -50,6 +51,7 @@ enum { SMC_GEN_SYS_INFO, /* nest */ SMC_GEN_LGR_SMCR, /* nest */ SMC_GEN_LINK_SMCR, /* nest */ + SMC_GEN_LGR_SMCD, /* nest */ __SMC_GEN_MAX, SMC_GEN_MAX = __SMC_GEN_MAX - 1 }; @@ -66,6 +68,15 @@ enum { SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1 }; +/* SMC_NLA_LGR_V2 nested attributes */ +enum { + SMC_NLA_LGR_V2_VER, /* u8 */ + SMC_NLA_LGR_V2_REL, /* u8 */ + SMC_NLA_LGR_V2_OS, /* u8 */ + SMC_NLA_LGR_V2_NEG_EID, /* string */ + SMC_NLA_LGR_V2_PEER_HOST, /* string */ +}; + /* SMC_GEN_LGR_SMCR attributes */ enum { SMC_NLA_LGR_R_UNSPEC, @@ -95,4 +106,20 @@ enum { __SMC_NLA_LINK_MAX, SMC_NLA_LINK_MAX = __SMC_NLA_LINK_MAX - 1 }; + +/* SMC_GEN_LGR_SMCD attributes */ +enum { + SMC_NLA_LGR_D_UNSPEC, + SMC_NLA_LGR_D_ID, /* u32 */ + SMC_NLA_LGR_D_GID, /* u64 */ + SMC_NLA_LGR_D_PEER_GID, /* u64 */ + SMC_NLA_LGR_D_VLAN_ID, /* u8 */ + SMC_NLA_LGR_D_CONNS_NUM, /* u32 */ + SMC_NLA_LGR_D_PNETID, /* string */ + SMC_NLA_LGR_D_CHID, /* u16 */ + SMC_NLA_LGR_D_PAD, /* flag */ + SMC_NLA_LGR_V2, /* nest */ + __SMC_NLA_LGR_D_MAX, + SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 5ad4b742dcc1..ac2cc593f25f 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -426,6 +426,130 @@ errout: cb_ctx->pos[0] = num; } +static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; + char smc_pnet[SMC_MAX_PNETID_LEN + 1]; + char smc_eid[SMC_MAX_EID_LEN + 1]; + struct nlattr *v2_attrs; + struct nlattr *attrs; + void *nlh; + + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_LGR_SMCD); + if (!nlh) + goto errmsg; + + attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCD); + if (!attrs) + goto errout; + + if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id))) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, lgr->smcd->local_gid, + SMC_NLA_LGR_D_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid, + SMC_NLA_LGR_D_PAD)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd))) + goto errattr; + snprintf(smc_pnet, sizeof(smc_pnet), "%s", lgr->smcd->pnetid); + if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) + goto errattr; + + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_V2); + if (!v2_attrs) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) + goto errv2attr; + snprintf(smc_host, sizeof(smc_host), "%s", lgr->peer_hostname); + if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) + goto errv2attr; + snprintf(smc_eid, sizeof(smc_eid), "%s", lgr->negotiated_eid); + if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +static int smc_nl_handle_smcd_lgr(struct smcd_dev *dev, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct smc_link_group *lgr; + int snum = cb_ctx->pos[1]; + int rc = 0, num = 0; + + spin_lock_bh(&dev->lgr_lock); + list_for_each_entry(lgr, &dev->lgr_list, list) { + if (!lgr->is_smcd) + continue; + if (num < snum) + goto next; + rc = smc_nl_fill_smcd_lgr(lgr, skb, cb); + if (rc) + goto errout; +next: + num++; + } +errout: + spin_unlock_bh(&dev->lgr_lock); + cb_ctx->pos[1] = num; + return rc; +} + +static int smc_nl_fill_smcd_dev(struct smcd_dev_list *dev_list, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct smcd_dev *smcd_dev; + int snum = cb_ctx->pos[0]; + int rc = 0, num = 0; + + mutex_lock(&dev_list->mutex); + list_for_each_entry(smcd_dev, &dev_list->list, list) { + if (list_empty(&smcd_dev->lgr_list)) + continue; + if (num < snum) + goto next; + rc = smc_nl_handle_smcd_lgr(smcd_dev, skb, cb); + if (rc) + goto errout; +next: + num++; + } +errout: + mutex_unlock(&dev_list->mutex); + cb_ctx->pos[0] = num; + return rc; +} + int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) { bool list_links = false; @@ -442,6 +566,12 @@ int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) +{ + smc_nl_fill_smcd_dev(&smcd_dev_list, skb, cb); + return skb->len; +} + void smc_lgr_cleanup_early(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 7995621f318d..0b6899a7f634 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -430,6 +430,7 @@ void smcr_link_down_cond_sched(struct smc_link *lnk); int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb); int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb); +int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) { diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index a41f78f488a2..95bce936534f 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -38,6 +38,11 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smcr_nl_get_link, }, + { + .cmd = SMC_NETLINK_GET_LGR_SMCD, + /* can be retrieved by unprivileged users */ + .dumpit = smcd_nl_get_lgr, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { -- cgit v1.3-15-g9ac1 From aaf95523d5824ebc2c8c185a2de51063a750c446 Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Tue, 1 Dec 2020 20:20:48 +0100 Subject: net/smc: Add support for obtaining SMCD device list Deliver SMCD device information via netlink based diagnostic interface. Signed-off-by: Guvenc Gulce Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- include/uapi/linux/smc.h | 28 +++++++++++++++ net/smc/smc_core.h | 28 +++++++++++++++ net/smc/smc_ism.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_ism.h | 1 + net/smc/smc_netlink.c | 6 ++++ 5 files changed, 154 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 707e8af4f0c8..3cb40ab049d9 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -37,12 +37,15 @@ enum { /* SMC PNET Table commands */ #define SMC_GENL_FAMILY_NAME "SMC_GEN_NETLINK" #define SMC_GENL_FAMILY_VERSION 1 +#define SMC_PCI_ID_STR_LEN 16 /* Max length of pci id string */ + /* SMC_GENL_FAMILY commands */ enum { SMC_NETLINK_GET_SYS_INFO = 1, SMC_NETLINK_GET_LGR_SMCR, SMC_NETLINK_GET_LINK_SMCR, SMC_NETLINK_GET_LGR_SMCD, + SMC_NETLINK_GET_DEV_SMCD, }; /* SMC_GENL_FAMILY top level attributes */ @@ -52,6 +55,7 @@ enum { SMC_GEN_LGR_SMCR, /* nest */ SMC_GEN_LINK_SMCR, /* nest */ SMC_GEN_LGR_SMCD, /* nest */ + SMC_GEN_DEV_SMCD, /* nest */ __SMC_GEN_MAX, SMC_GEN_MAX = __SMC_GEN_MAX - 1 }; @@ -122,4 +126,28 @@ enum { __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; + +/* SMC_NLA_DEV_PORT attributes */ +enum { + SMC_NLA_DEV_PORT_UNSPEC, + SMC_NLA_DEV_PORT_PNET_USR, /* u8 */ + SMC_NLA_DEV_PORT_PNETID, /* string */ + __SMC_NLA_DEV_PORT_MAX, + SMC_NLA_DEV_PORT_MAX = __SMC_NLA_DEV_PORT_MAX - 1 +}; + +/* SMC_GEN_DEV_SMCD attributes */ +enum { + SMC_NLA_DEV_UNSPEC, + SMC_NLA_DEV_USE_CNT, /* u32 */ + SMC_NLA_DEV_IS_CRIT, /* u8 */ + SMC_NLA_DEV_PCI_FID, /* u32 */ + SMC_NLA_DEV_PCI_CHID, /* u16 */ + SMC_NLA_DEV_PCI_VENDOR, /* u16 */ + SMC_NLA_DEV_PCI_DEVICE, /* u16 */ + SMC_NLA_DEV_PCI_ID, /* string */ + SMC_NLA_DEV_PORT, /* nest */ + __SMC_NLA_DEV_MAX, + SMC_NLA_DEV_MAX = __SMC_NLA_DEV_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 0b6899a7f634..e8e448771f85 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -13,6 +13,8 @@ #define _SMC_CORE_H #include +#include +#include #include #include @@ -380,6 +382,32 @@ static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) be16_to_cpu(((__be16 *)gid_raw)[7])); } +struct smc_pci_dev { + __u32 pci_fid; + __u16 pci_pchid; + __u16 pci_vendor; + __u16 pci_device; + __u8 pci_id[SMC_PCI_ID_STR_LEN]; +}; + +static inline void smc_set_pci_values(struct pci_dev *pci_dev, + struct smc_pci_dev *smc_dev) +{ + smc_dev->pci_vendor = pci_dev->vendor; + smc_dev->pci_device = pci_dev->device; + snprintf(smc_dev->pci_id, sizeof(smc_dev->pci_id), "%s", + pci_name(pci_dev)); +#if IS_ENABLED(CONFIG_S390) + { /* Set s390 specific PCI information */ + struct zpci_dev *zdev; + + zdev = to_zpci(pci_dev); + smc_dev->pci_fid = zdev->fid; + smc_dev->pci_pchid = zdev->pchid; + } +#endif +} + struct smc_sock; struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 2456ee8228cd..524ef64a191a 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -15,6 +15,7 @@ #include "smc_core.h" #include "smc_ism.h" #include "smc_pnet.h" +#include "smc_netlink.h" struct smcd_dev_list smcd_dev_list = { .list = LIST_HEAD_INIT(smcd_dev_list.list), @@ -207,6 +208,96 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, return rc; } +static int smc_nl_handle_smcd_dev(struct smcd_dev *smcd, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_pnet[SMC_MAX_PNETID_LEN + 1]; + struct smc_pci_dev smc_pci_dev; + struct nlattr *port_attrs; + struct nlattr *attrs; + int use_cnt = 0; + void *nlh; + + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_DEV_SMCD); + if (!nlh) + goto errmsg; + attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCD); + if (!attrs) + goto errout; + use_cnt = atomic_read(&smcd->lgr_cnt); + if (nla_put_u32(skb, SMC_NLA_DEV_USE_CNT, use_cnt)) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, use_cnt > 0)) + goto errattr; + memset(&smc_pci_dev, 0, sizeof(smc_pci_dev)); + smc_set_pci_values(to_pci_dev(smcd->dev.parent), &smc_pci_dev); + if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev.pci_fid)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev.pci_pchid)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev.pci_vendor)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev.pci_device)) + goto errattr; + if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev.pci_id)) + goto errattr; + + port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT); + if (!port_attrs) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, smcd->pnetid_by_user)) + goto errportattr; + snprintf(smc_pnet, sizeof(smc_pnet), "%s", smcd->pnetid); + if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet)) + goto errportattr; + + nla_nest_end(skb, port_attrs); + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return 0; + +errportattr: + nla_nest_cancel(skb, port_attrs); +errattr: + nla_nest_cancel(skb, attrs); +errout: + nlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +static void smc_nl_prep_smcd_dev(struct smcd_dev_list *dev_list, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + int snum = cb_ctx->pos[0]; + struct smcd_dev *smcd; + int num = 0; + + mutex_lock(&dev_list->mutex); + list_for_each_entry(smcd, &dev_list->list, list) { + if (num < snum) + goto next; + if (smc_nl_handle_smcd_dev(smcd, skb, cb)) + goto errout; +next: + num++; + } +errout: + mutex_unlock(&dev_list->mutex); + cb_ctx->pos[0] = num; +} + +int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb) +{ + smc_nl_prep_smcd_dev(&smcd_dev_list, skb, cb); + return skb->len; +} + struct smc_ism_event_work { struct work_struct work; struct smcd_dev *smcd; diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 481a4b7df30b..113efc7352ed 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -52,4 +52,5 @@ void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid); u16 smc_ism_get_chid(struct smcd_dev *dev); bool smc_ism_is_v2_capable(void); void smc_ism_init(void); +int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); #endif diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 95bce936534f..debdeec53728 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -17,6 +17,7 @@ #include #include "smc_core.h" +#include "smc_ism.h" #include "smc_netlink.h" #define SMC_CMD_MAX_ATTR 1 @@ -43,6 +44,11 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smcd_nl_get_lgr, }, + { + .cmd = SMC_NETLINK_GET_DEV_SMCD, + /* can be retrieved by unprivileged users */ + .dumpit = smcd_nl_get_device, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { -- cgit v1.3-15-g9ac1 From a3db10efcc4cc9c03a6375920179ade75ea2df7a Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Tue, 1 Dec 2020 20:20:49 +0100 Subject: net/smc: Add support for obtaining SMCR device list Deliver SMCR device information via netlink based diagnostic interface. Signed-off-by: Guvenc Gulce Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- include/uapi/linux/smc.h | 13 +++- net/smc/smc_core.c | 2 +- net/smc/smc_ib.c | 156 +++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_ib.h | 2 + net/smc/smc_netlink.c | 6 ++ 5 files changed, 176 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 3cb40ab049d9..3e68da07fba2 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -46,6 +46,7 @@ enum { SMC_NETLINK_GET_LINK_SMCR, SMC_NETLINK_GET_LGR_SMCD, SMC_NETLINK_GET_DEV_SMCD, + SMC_NETLINK_GET_DEV_SMCR, }; /* SMC_GENL_FAMILY top level attributes */ @@ -56,6 +57,7 @@ enum { SMC_GEN_LINK_SMCR, /* nest */ SMC_GEN_LGR_SMCD, /* nest */ SMC_GEN_DEV_SMCD, /* nest */ + SMC_GEN_DEV_SMCR, /* nest */ __SMC_GEN_MAX, SMC_GEN_MAX = __SMC_GEN_MAX - 1 }; @@ -127,16 +129,20 @@ enum { SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; -/* SMC_NLA_DEV_PORT attributes */ +/* SMC_NLA_DEV_PORT nested attributes */ enum { SMC_NLA_DEV_PORT_UNSPEC, SMC_NLA_DEV_PORT_PNET_USR, /* u8 */ SMC_NLA_DEV_PORT_PNETID, /* string */ + SMC_NLA_DEV_PORT_NETDEV, /* u32 */ + SMC_NLA_DEV_PORT_STATE, /* u8 */ + SMC_NLA_DEV_PORT_VALID, /* u8 */ + SMC_NLA_DEV_PORT_LNK_CNT, /* u32 */ __SMC_NLA_DEV_PORT_MAX, SMC_NLA_DEV_PORT_MAX = __SMC_NLA_DEV_PORT_MAX - 1 }; -/* SMC_GEN_DEV_SMCD attributes */ +/* SMC_GEN_DEV_SMCD and SMC_GEN_DEV_SMCR attributes */ enum { SMC_NLA_DEV_UNSPEC, SMC_NLA_DEV_USE_CNT, /* u32 */ @@ -147,7 +153,10 @@ enum { SMC_NLA_DEV_PCI_DEVICE, /* u16 */ SMC_NLA_DEV_PCI_ID, /* string */ SMC_NLA_DEV_PORT, /* nest */ + SMC_NLA_DEV_PORT2, /* nest */ + SMC_NLA_DEV_IB_NAME, /* string */ __SMC_NLA_DEV_MAX, SMC_NLA_DEV_MAX = __SMC_NLA_DEV_MAX - 1 }; + #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index ac2cc593f25f..59342b519e34 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -38,7 +38,7 @@ #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) #define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) -static struct smc_lgr_list smc_lgr_list = { /* established link groups */ +struct smc_lgr_list smc_lgr_list = { /* established link groups */ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), .list = LIST_HEAD_INIT(smc_lgr_list.list), .num = 0, diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 61b025c912a9..89ea10675a7d 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -25,6 +25,7 @@ #include "smc_core.h" #include "smc_wr.h" #include "smc.h" +#include "smc_netlink.h" #define SMC_MAX_CQE 32766 /* max. # of completion queue elements */ @@ -326,6 +327,161 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) return rc; } +static bool smcr_diag_is_dev_critical(struct smc_lgr_list *smc_lgr, + struct smc_ib_device *smcibdev) +{ + struct smc_link_group *lgr; + bool rc = false; + int i; + + spin_lock_bh(&smc_lgr->lock); + list_for_each_entry(lgr, &smc_lgr->list, list) { + if (lgr->is_smcd) + continue; + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (lgr->lnk[i].state == SMC_LNK_UNUSED || + lgr->lnk[i].smcibdev != smcibdev) + continue; + if (lgr->type == SMC_LGR_SINGLE || + lgr->type == SMC_LGR_ASYMMETRIC_LOCAL) { + rc = true; + goto out; + } + } + } +out: + spin_unlock_bh(&smc_lgr->lock); + return rc; +} + +static int smc_nl_handle_dev_port(struct sk_buff *skb, + struct ib_device *ibdev, + struct smc_ib_device *smcibdev, + int port) +{ + char smc_pnet[SMC_MAX_PNETID_LEN + 1]; + struct nlattr *port_attrs; + unsigned char port_state; + int lnk_count = 0; + + port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT + port); + if (!port_attrs) + goto errout; + + if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, + smcibdev->pnetid_by_user[port])) + goto errattr; + snprintf(smc_pnet, sizeof(smc_pnet), "%s", + (char *)&smcibdev->pnetid[port]); + if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV, + smcibdev->ndev_ifidx[port])) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_DEV_PORT_VALID, 1)) + goto errattr; + port_state = smc_ib_port_active(smcibdev, port + 1); + if (nla_put_u8(skb, SMC_NLA_DEV_PORT_STATE, port_state)) + goto errattr; + lnk_count = atomic_read(&smcibdev->lnk_cnt_by_port[port]); + if (nla_put_u32(skb, SMC_NLA_DEV_PORT_LNK_CNT, lnk_count)) + goto errattr; + nla_nest_end(skb, port_attrs); + return 0; +errattr: + nla_nest_cancel(skb, port_attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_handle_smcr_dev(struct smc_ib_device *smcibdev, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_ibname[IB_DEVICE_NAME_MAX + 1]; + struct smc_pci_dev smc_pci_dev; + struct pci_dev *pci_dev; + unsigned char is_crit; + struct nlattr *attrs; + void *nlh; + int i; + + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_DEV_SMCR); + if (!nlh) + goto errmsg; + attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCR); + if (!attrs) + goto errout; + is_crit = smcr_diag_is_dev_critical(&smc_lgr_list, smcibdev); + if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, is_crit)) + goto errattr; + memset(&smc_pci_dev, 0, sizeof(smc_pci_dev)); + pci_dev = to_pci_dev(smcibdev->ibdev->dev.parent); + smc_set_pci_values(pci_dev, &smc_pci_dev); + if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev.pci_fid)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev.pci_pchid)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev.pci_vendor)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev.pci_device)) + goto errattr; + if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev.pci_id)) + goto errattr; + snprintf(smc_ibname, sizeof(smc_ibname), "%s", smcibdev->ibdev->name); + if (nla_put_string(skb, SMC_NLA_DEV_IB_NAME, smc_ibname)) + goto errattr; + for (i = 1; i <= SMC_MAX_PORTS; i++) { + if (!rdma_is_port_valid(smcibdev->ibdev, i)) + continue; + if (smc_nl_handle_dev_port(skb, smcibdev->ibdev, + smcibdev, i - 1)) + goto errattr; + } + + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +static void smc_nl_prep_smcr_dev(struct smc_ib_devices *dev_list, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct smc_ib_device *smcibdev; + int snum = cb_ctx->pos[0]; + int num = 0; + + mutex_lock(&dev_list->mutex); + list_for_each_entry(smcibdev, &dev_list->list, list) { + if (num < snum) + goto next; + if (smc_nl_handle_smcr_dev(smcibdev, skb, cb)) + goto errout; +next: + num++; + } +errout: + mutex_unlock(&dev_list->mutex); + cb_ctx->pos[0] = num; +} + +int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb) +{ + smc_nl_prep_smcr_dev(&smc_ib_devices, skb, cb); + return skb->len; +} + static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { struct smc_link *lnk = (struct smc_link *)priv; diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index ab37da341fa8..3085f5180da7 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -30,6 +30,7 @@ struct smc_ib_devices { /* list of smc ib devices definition */ }; extern struct smc_ib_devices smc_ib_devices; /* list of smc ib devices */ +extern struct smc_lgr_list smc_lgr_list; /* list of linkgroups */ struct smc_ib_device { /* ib-device infos for smc */ struct list_head list; @@ -91,4 +92,5 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk, int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index); bool smc_ib_is_valid_local_systemid(void); +int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); #endif diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index debdeec53728..140419a19dbf 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -18,6 +18,7 @@ #include "smc_core.h" #include "smc_ism.h" +#include "smc_ib.h" #include "smc_netlink.h" #define SMC_CMD_MAX_ATTR 1 @@ -49,6 +50,11 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smcd_nl_get_device, }, + { + .cmd = SMC_NETLINK_GET_DEV_SMCR, + /* can be retrieved by unprivileged users */ + .dumpit = smcr_nl_get_device, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { -- cgit v1.3-15-g9ac1 From d4bff72c8401e6f56194ecf455db70ebc22929e2 Mon Sep 17 00:00:00 2001 From: Thomas Karlsson Date: Wed, 2 Dec 2020 19:49:58 +0100 Subject: macvlan: Support for high multicast packet rate Background: Broadcast and multicast packages are enqueued for later processing. This queue was previously hardcoded to 1000. This proved insufficient for handling very high packet rates. This resulted in packet drops for multicast. While at the same time unicast worked fine. The change: This patch make the queue length adjustable to accommodate for environments with very high multicast packet rate. But still keeps the default value of 1000 unless specified. The queue length is specified as a request per macvlan using the IFLA_MACVLAN_BC_QUEUE_LEN parameter. The actual used queue length will then be the maximum of any macvlan connected to the same port. The actual used queue length for the port can be retrieved (read only) by the IFLA_MACVLAN_BC_QUEUE_LEN_USED parameter for verification. This will be followed up by a patch to iproute2 in order to adjust the parameter from userspace. Signed-off-by: Thomas Karlsson Link: https://lore.kernel.org/r/dd4673b2-7eab-edda-6815-85c67ce87f63@paneda.se Signed-off-by: Jakub Kicinski --- drivers/net/macvlan.c | 40 ++++++++++++++++++++++++++++++++++++-- include/linux/if_macvlan.h | 1 + include/uapi/linux/if_link.h | 2 ++ tools/include/uapi/linux/if_link.h | 2 ++ 4 files changed, 43 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index d9b6c44a5911..fb51329f8964 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -35,7 +35,7 @@ #define MACVLAN_HASH_BITS 8 #define MACVLAN_HASH_SIZE (1<cb[0])) static void macvlan_port_destroy(struct net_device *dev); +static void update_port_bc_queue_len(struct macvlan_port *port); static inline bool macvlan_passthru(const struct macvlan_port *port) { @@ -354,7 +356,7 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port, MACVLAN_SKB_CB(nskb)->src = src; spin_lock(&port->bc_queue.lock); - if (skb_queue_len(&port->bc_queue) < MACVLAN_BC_QUEUE_LEN) { + if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) { if (src) dev_hold(src->dev); __skb_queue_tail(&port->bc_queue, nskb); @@ -1218,6 +1220,7 @@ static int macvlan_port_create(struct net_device *dev) for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_source_hash[i]); + port->bc_queue_len_used = 0; skb_queue_head_init(&port->bc_queue); INIT_WORK(&port->bc_work, macvlan_process_broadcast); @@ -1486,6 +1489,10 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, goto destroy_macvlan_port; } + vlan->bc_queue_len_req = MACVLAN_DEFAULT_BC_QUEUE_LEN; + if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) + vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); + err = register_netdevice(dev); if (err < 0) goto destroy_macvlan_port; @@ -1496,6 +1503,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, goto unregister_netdev; list_add_tail_rcu(&vlan->list, &port->vlans); + update_port_bc_queue_len(vlan->port); netif_stacked_transfer_operstate(lowerdev, dev); linkwatch_fire_event(dev); @@ -1529,6 +1537,7 @@ void macvlan_dellink(struct net_device *dev, struct list_head *head) if (vlan->mode == MACVLAN_MODE_SOURCE) macvlan_flush_sources(vlan->port, vlan); list_del_rcu(&vlan->list); + update_port_bc_queue_len(vlan->port); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(vlan->lowerdev, dev); } @@ -1572,6 +1581,12 @@ static int macvlan_changelink(struct net_device *dev, } vlan->flags = flags; } + + if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) { + vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); + update_port_bc_queue_len(vlan->port); + } + if (set_mode) vlan->mode = mode; if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { @@ -1602,6 +1617,8 @@ static size_t macvlan_get_size(const struct net_device *dev) + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */ + macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */ + + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN */ + + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN_USED */ ); } @@ -1625,6 +1642,7 @@ static int macvlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); + struct macvlan_port *port = vlan->port; int i; struct nlattr *nest; @@ -1645,6 +1663,10 @@ static int macvlan_fill_info(struct sk_buff *skb, } nla_nest_end(skb, nest); } + if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, port->bc_queue_len_used)) + goto nla_put_failure; return 0; nla_put_failure: @@ -1658,6 +1680,8 @@ static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = { [IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED }, [IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 }, + [IFLA_MACVLAN_BC_QUEUE_LEN] = { .type = NLA_U32 }, + [IFLA_MACVLAN_BC_QUEUE_LEN_USED] = { .type = NLA_REJECT }, }; int macvlan_link_register(struct rtnl_link_ops *ops) @@ -1688,6 +1712,18 @@ static struct rtnl_link_ops macvlan_link_ops = { .priv_size = sizeof(struct macvlan_dev), }; +static void update_port_bc_queue_len(struct macvlan_port *port) +{ + u32 max_bc_queue_len_req = 0; + struct macvlan_dev *vlan; + + list_for_each_entry(vlan, &port->vlans, list) { + if (vlan->bc_queue_len_req > max_bc_queue_len_req) + max_bc_queue_len_req = vlan->bc_queue_len_req; + } + port->bc_queue_len_used = max_bc_queue_len_req; +} + static int macvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index a367ead4bf4b..96556c64c95d 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -30,6 +30,7 @@ struct macvlan_dev { enum macvlan_mode mode; u16 flags; unsigned int macaddr_count; + u32 bc_queue_len_req; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c4b23f06f69e..874cc12a34d9 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -588,6 +588,8 @@ enum { IFLA_MACVLAN_MACADDR, IFLA_MACVLAN_MACADDR_DATA, IFLA_MACVLAN_MACADDR_COUNT, + IFLA_MACVLAN_BC_QUEUE_LEN, + IFLA_MACVLAN_BC_QUEUE_LEN_USED, __IFLA_MACVLAN_MAX, }; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 781e482dc499..d208b2af697f 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -409,6 +409,8 @@ enum { IFLA_MACVLAN_MACADDR, IFLA_MACVLAN_MACADDR_DATA, IFLA_MACVLAN_MACADDR_COUNT, + IFLA_MACVLAN_BC_QUEUE_LEN, + IFLA_MACVLAN_BC_QUEUE_LEN_USED, __IFLA_MACVLAN_MAX, }; -- cgit v1.3-15-g9ac1 From 290248a5b7d829871b3ea3c62578613a580a1744 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 3 Dec 2020 12:46:30 -0800 Subject: bpf: Allow to specify kernel module BTFs when attaching BPF programs Add ability for user-space programs to specify non-vmlinux BTF when attaching BTF-powered BPF programs: raw_tp, fentry/fexit/fmod_ret, LSM, etc. For this, attach_prog_fd (now with the alias name attach_btf_obj_fd) should specify FD of a module or vmlinux BTF object. For backwards compatibility reasons, 0 denotes vmlinux BTF. Only kernel BTF (vmlinux or module) can be specified. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201203204634.1325171-11-andrii@kernel.org --- include/linux/btf.h | 1 + include/uapi/linux/bpf.h | 7 +++- kernel/bpf/btf.c | 5 +++ kernel/bpf/syscall.c | 82 ++++++++++++++++++++++++++---------------- tools/include/uapi/linux/bpf.h | 7 +++- 5 files changed, 69 insertions(+), 33 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index fb608e4de076..4c200f5d242b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -90,6 +90,7 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, int btf_get_fd_by_id(u32 id); u32 btf_obj_id(const struct btf *btf); +bool btf_is_kernel(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c3458ec1f30a..1233f14f659f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -557,7 +557,12 @@ union bpf_attr { __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ - __u32 attach_prog_fd; /* 0 to attach to vmlinux */ + union { + /* valid prog_fd to attach to bpf prog */ + __u32 attach_prog_fd; + /* or valid module BTF object fd or 0 to attach to vmlinux */ + __u32 attach_btf_obj_fd; + }; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7a19bf5bfe97..8d6bdb4f4d61 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5738,6 +5738,11 @@ u32 btf_obj_id(const struct btf *btf) return btf->id; } +bool btf_is_kernel(const struct btf *btf) +{ + return btf->kernel_btf; +} + static int btf_id_cmp_func(const void *a, const void *b) { const int *pa = a, *pb = b; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 184204169949..0cd3cc2af9c1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1926,12 +1926,16 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, - u32 btf_id, u32 prog_fd) + struct btf *attach_btf, u32 btf_id, + struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; + if (!attach_btf && !dst_prog) + return -EINVAL; + switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: @@ -1943,7 +1947,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, } } - if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING && + if (attach_btf && (!btf_id || dst_prog)) + return -EINVAL; + + if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; @@ -2060,7 +2067,8 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { enum bpf_prog_type type = attr->prog_type; - struct bpf_prog *prog; + struct bpf_prog *prog, *dst_prog = NULL; + struct btf *attach_btf = NULL; int err; char license[128]; bool is_gpl; @@ -2102,44 +2110,56 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (is_perfmon_prog_type(type) && !perfmon_capable()) return -EPERM; + /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog + * or btf, we need to check which one it is + */ + if (attr->attach_prog_fd) { + dst_prog = bpf_prog_get(attr->attach_prog_fd); + if (IS_ERR(dst_prog)) { + dst_prog = NULL; + attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); + if (IS_ERR(attach_btf)) + return -EINVAL; + if (!btf_is_kernel(attach_btf)) { + btf_put(attach_btf); + return -EINVAL; + } + } + } else if (attr->attach_btf_id) { + /* fall back to vmlinux BTF, if BTF type ID is specified */ + attach_btf = bpf_get_btf_vmlinux(); + if (IS_ERR(attach_btf)) + return PTR_ERR(attach_btf); + if (!attach_btf) + return -EINVAL; + btf_get(attach_btf); + } + bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, - attr->attach_btf_id, - attr->attach_prog_fd)) + attach_btf, attr->attach_btf_id, + dst_prog)) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); return -EINVAL; + } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); - if (!prog) + if (!prog) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); return -ENOMEM; + } prog->expected_attach_type = attr->expected_attach_type; + prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; - - if (attr->attach_btf_id && !attr->attach_prog_fd) { - struct btf *btf; - - btf = bpf_get_btf_vmlinux(); - if (IS_ERR(btf)) - return PTR_ERR(btf); - if (!btf) - return -EINVAL; - - btf_get(btf); - prog->aux->attach_btf = btf; - } - - if (attr->attach_prog_fd) { - struct bpf_prog *dst_prog; - - dst_prog = bpf_prog_get(attr->attach_prog_fd); - if (IS_ERR(dst_prog)) { - err = PTR_ERR(dst_prog); - goto free_prog; - } - prog->aux->dst_prog = dst_prog; - } - + prog->aux->dst_prog = dst_prog; prog->aux->offload_requested = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c3458ec1f30a..1233f14f659f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -557,7 +557,12 @@ union bpf_attr { __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ - __u32 attach_prog_fd; /* 0 to attach to vmlinux */ + union { + /* valid prog_fd to attach to bpf prog */ + __u32 attach_prog_fd; + /* or valid module BTF object fd or 0 to attach to vmlinux */ + __u32 attach_btf_obj_fd; + }; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ -- cgit v1.3-15-g9ac1 From 128254ceea6ffe59300d3cca6fc83b842048f4c4 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 11 Oct 2020 12:25:23 +0200 Subject: batman-adv: Prepare infrastructure for newlink settings The batadv generic netlink family can be used to retrieve the current state and set various configuration settings. But there are also settings which must be set before the actual interface is created. The rtnetlink already uses IFLA_INFO_DATA to allow net_device families to transfer such configurations. The minimal required functionality for this is now available for the batadv rtnl_link_ops. Also a new IFLA class of attributes will be attached to it because rtnetlink only allows 51 different attributes but batadv_nl_attrs already contains 62 attributes. Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 20 ++++++++++++++++++++ net/batman-adv/soft-interface.c | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index bb0ae945b36a..b05399d8a127 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -675,4 +675,24 @@ enum batadv_tp_meter_reason { BATADV_TP_REASON_TOO_MANY = 133, }; +/** + * enum batadv_ifla_attrs - batman-adv ifla nested attributes + */ +enum batadv_ifla_attrs { + /** + * @IFLA_BATADV_UNSPEC: unspecified attribute which is not parsed by + * rtnetlink + */ + IFLA_BATADV_UNSPEC, + + /* add attributes above here, update the policy in soft-interface.c */ + + /** + * @__IFLA_BATADV_MAX: internal use + */ + __IFLA_BATADV_MAX, +}; + +#define IFLA_BATADV_MAX (__IFLA_BATADV_MAX - 1) + #endif /* _UAPI_LINUX_BATMAN_ADV_H_ */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 82e7ca886605..9c7b89689c97 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -1073,6 +1074,37 @@ static void batadv_softif_init_early(struct net_device *dev) dev->ethtool_ops = &batadv_ethtool_ops; } +/** + * batadv_softif_validate() - validate configuration of new batadv link + * @tb: IFLA_INFO_DATA netlink attributes + * @data: enum batadv_ifla_attrs attributes + * @extack: extended ACK report struct + * + * Return: 0 if successful or error otherwise. + */ +static int batadv_softif_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + return 0; +} + +/** + * batadv_softif_newlink() - pre-initialize and register new batadv link + * @src_net: the applicable net namespace + * @dev: network device to register + * @tb: IFLA_INFO_DATA netlink attributes + * @data: enum batadv_ifla_attrs attributes + * @extack: extended ACK report struct + * + * Return: 0 if successful or error otherwise. + */ +static int batadv_softif_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + return register_netdevice(dev); +} + /** * batadv_softif_create() - Create and register soft interface * @net: the applicable net namespace @@ -1171,9 +1203,16 @@ bool batadv_softif_is_valid(const struct net_device *net_dev) return false; } +static const struct nla_policy batadv_ifla_policy[IFLA_BATADV_MAX + 1] = { +}; + struct rtnl_link_ops batadv_link_ops __read_mostly = { .kind = "batadv", .priv_size = sizeof(struct batadv_priv), .setup = batadv_softif_init_early, + .maxtype = IFLA_BATADV_MAX, + .policy = batadv_ifla_policy, + .validate = batadv_softif_validate, + .newlink = batadv_softif_newlink, .dellink = batadv_softif_destroy_netlink, }; -- cgit v1.3-15-g9ac1 From a5ad457eea41ef7209f3a1765f853a2c7f191131 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 11 Oct 2020 12:25:24 +0200 Subject: batman-adv: Allow selection of routing algorithm over rtnetlink A batadv net_device is associated to a B.A.T.M.A.N. routing algorithm. This algorithm has to be selected before the interface is initialized and cannot be changed after that. The only way to select this algorithm was a module parameter which specifies the default algorithm used during the creation of the net_device. This module parameter is writeable over /sys/module/batman_adv/parameters/routing_algo and thus allows switching of the routing algorithm: 1. change routing_algo parameter 2. create new batadv net_device But this is not race free because another process can be scheduled between 1 + 2 and in that time frame change the routing_algo parameter again. It is much cleaner to directly provide this information inside the rtnetlink's RTM_NEWLINK message. The two processes would be (in regards of the creation parameter of their batadv interfaces) be isolated. This also eases the integration of batadv devices inside tools like network-manager or systemd-networkd which are not expecting to operate on /sys before a new net_device is created. Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 6 ++++++ net/batman-adv/bat_algo.c | 10 ++++++++-- net/batman-adv/bat_algo.h | 3 ++- net/batman-adv/soft-interface.c | 31 ++++++++++++++++++++++++++++--- 4 files changed, 44 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index b05399d8a127..bdb317faa1dc 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -685,6 +685,12 @@ enum batadv_ifla_attrs { */ IFLA_BATADV_UNSPEC, + /** + * @IFLA_BATADV_ALGO_NAME: routing algorithm (name) which should be + * used by the newly registered batadv net_device. + */ + IFLA_BATADV_ALGO_NAME, + /* add attributes above here, update the policy in soft-interface.c */ /** diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index 382fbe51fd34..500db94a6b50 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -34,7 +34,13 @@ void batadv_algo_init(void) INIT_HLIST_HEAD(&batadv_algo_list); } -static struct batadv_algo_ops *batadv_algo_get(char *name) +/** + * batadv_algo_get() - Search for algorithm with specific name + * @name: algorithm name to find + * + * Return: Pointer to batadv_algo_ops on success, NULL otherwise + */ +struct batadv_algo_ops *batadv_algo_get(const char *name) { struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp; @@ -97,7 +103,7 @@ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) * * Return: 0 on success or negative error number in case of failure */ -int batadv_algo_select(struct batadv_priv *bat_priv, char *name) +int batadv_algo_select(struct batadv_priv *bat_priv, const char *name) { struct batadv_algo_ops *bat_algo_ops; diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 686a60bc9492..2ae140eac45d 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -18,8 +18,9 @@ extern char batadv_routing_algo[]; extern struct list_head batadv_hardif_list; void batadv_algo_init(void); +struct batadv_algo_ops *batadv_algo_get(const char *name); int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops); -int batadv_algo_select(struct batadv_priv *bat_priv, char *name); +int batadv_algo_select(struct batadv_priv *bat_priv, const char *name); int batadv_algo_seq_print_text(struct seq_file *seq, void *offset); int batadv_algo_dump(struct sk_buff *msg, struct netlink_callback *cb); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 9c7b89689c97..8116631c11c5 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -846,9 +846,11 @@ static int batadv_softif_init_late(struct net_device *dev) batadv_nc_init_bat_priv(bat_priv); - ret = batadv_algo_select(bat_priv, batadv_routing_algo); - if (ret < 0) - goto free_bat_counters; + if (!bat_priv->algo_ops) { + ret = batadv_algo_select(bat_priv, batadv_routing_algo); + if (ret < 0) + goto free_bat_counters; + } ret = batadv_debugfs_add_meshif(dev); if (ret < 0) @@ -1085,6 +1087,17 @@ static void batadv_softif_init_early(struct net_device *dev) static int batadv_softif_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { + struct batadv_algo_ops *algo_ops; + + if (!data) + return 0; + + if (data[IFLA_BATADV_ALGO_NAME]) { + algo_ops = batadv_algo_get(nla_data(data[IFLA_BATADV_ALGO_NAME])); + if (!algo_ops) + return -EINVAL; + } + return 0; } @@ -1102,6 +1115,17 @@ static int batadv_softif_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { + struct batadv_priv *bat_priv = netdev_priv(dev); + const char *algo_name; + int err; + + if (data && data[IFLA_BATADV_ALGO_NAME]) { + algo_name = nla_data(data[IFLA_BATADV_ALGO_NAME]); + err = batadv_algo_select(bat_priv, algo_name); + if (err) + return -EINVAL; + } + return register_netdevice(dev); } @@ -1204,6 +1228,7 @@ bool batadv_softif_is_valid(const struct net_device *net_dev) } static const struct nla_policy batadv_ifla_policy[IFLA_BATADV_MAX + 1] = { + [IFLA_BATADV_ALGO_NAME] = { .type = NLA_NUL_STRING }, }; struct rtnl_link_ops batadv_link_ops __read_mostly = { -- cgit v1.3-15-g9ac1 From 664d6f86868bacbfdb3926a975dff29ca9ebe0d0 Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Wed, 2 Dec 2020 14:05:14 +0100 Subject: seg6: add support for the SRv6 End.DT4 behavior SRv6 End.DT4 is defined in the SRv6 Network Programming [1]. The SRv6 End.DT4 is used to implement IPv4 L3VPN use-cases in multi-tenants environments. It decapsulates the received packets and it performs IPv4 routing lookup in the routing table of the tenant. The SRv6 End.DT4 Linux implementation leverages a VRF device in order to force the routing lookup into the associated routing table. To make the End.DT4 work properly, it must be guaranteed that the routing table used for routing lookup operations is bound to one and only one VRF during the tunnel creation. Such constraint has to be enforced by enabling the VRF strict_mode sysctl parameter, i.e: $ sysctl -wq net.vrf.strict_mode=1. At JANOG44, LINE corporation presented their multi-tenant DC architecture using SRv6 [2]. In the slides, they reported that the Linux kernel is missing the support of SRv6 End.DT4 behavior. The SRv6 End.DT4 behavior can be instantiated using a command similar to the following: $ ip route add 2001:db8::1 encap seg6local action End.DT4 vrftable 100 dev eth0 We introduce the "vrftable" extension in iproute2 in a following patch. [1] https://tools.ietf.org/html/draft-ietf-spring-srv6-network-programming [2] https://speakerdeck.com/line_developers/line-data-center-networking-with-srv6 Signed-off-by: Andrea Mayer Signed-off-by: Jakub Kicinski --- include/uapi/linux/seg6_local.h | 1 + net/ipv6/seg6_local.c | 287 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 288 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h index edc138bdc56d..3b39ef1dbb46 100644 --- a/include/uapi/linux/seg6_local.h +++ b/include/uapi/linux/seg6_local.h @@ -26,6 +26,7 @@ enum { SEG6_LOCAL_IIF, SEG6_LOCAL_OIF, SEG6_LOCAL_BPF, + SEG6_LOCAL_VRFTABLE, __SEG6_LOCAL_MAX, }; #define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1) diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index da5bf4167a52..24c2616c8c11 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -69,6 +69,28 @@ struct bpf_lwt_prog { char *name; }; +enum seg6_end_dt_mode { + DT_INVALID_MODE = -EINVAL, + DT_LEGACY_MODE = 0, + DT_VRF_MODE = 1, +}; + +struct seg6_end_dt_info { + enum seg6_end_dt_mode mode; + + struct net *net; + /* VRF device associated to the routing table used by the SRv6 + * End.DT4/DT6 behavior for routing IPv4/IPv6 packets. + */ + int vrf_ifindex; + int vrf_table; + + /* tunneled packet proto and family (IPv4 or IPv6) */ + __be16 proto; + u16 family; + int hdrlen; +}; + struct seg6_local_lwt { int action; struct ipv6_sr_hdr *srh; @@ -78,6 +100,9 @@ struct seg6_local_lwt { int iif; int oif; struct bpf_lwt_prog bpf; +#ifdef CONFIG_NET_L3_MASTER_DEV + struct seg6_end_dt_info dt_info; +#endif int headroom; struct seg6_action_desc *desc; @@ -429,6 +454,203 @@ drop: return -EINVAL; } +#ifdef CONFIG_NET_L3_MASTER_DEV +static struct net *fib6_config_get_net(const struct fib6_config *fib6_cfg) +{ + const struct nl_info *nli = &fib6_cfg->fc_nlinfo; + + return nli->nl_net; +} + +static int __seg6_end_dt_vrf_build(struct seg6_local_lwt *slwt, const void *cfg, + u16 family, struct netlink_ext_ack *extack) +{ + struct seg6_end_dt_info *info = &slwt->dt_info; + int vrf_ifindex; + struct net *net; + + net = fib6_config_get_net(cfg); + + /* note that vrf_table was already set by parse_nla_vrftable() */ + vrf_ifindex = l3mdev_ifindex_lookup_by_table_id(L3MDEV_TYPE_VRF, net, + info->vrf_table); + if (vrf_ifindex < 0) { + if (vrf_ifindex == -EPERM) { + NL_SET_ERR_MSG(extack, + "Strict mode for VRF is disabled"); + } else if (vrf_ifindex == -ENODEV) { + NL_SET_ERR_MSG(extack, + "Table has no associated VRF device"); + } else { + pr_debug("seg6local: SRv6 End.DT* creation error=%d\n", + vrf_ifindex); + } + + return vrf_ifindex; + } + + info->net = net; + info->vrf_ifindex = vrf_ifindex; + + switch (family) { + case AF_INET: + info->proto = htons(ETH_P_IP); + info->hdrlen = sizeof(struct iphdr); + break; + default: + return -EINVAL; + } + + info->family = family; + info->mode = DT_VRF_MODE; + + return 0; +} + +/* The SRv6 End.DT4/DT6 behavior extracts the inner (IPv4/IPv6) packet and + * routes the IPv4/IPv6 packet by looking at the configured routing table. + * + * In the SRv6 End.DT4/DT6 use case, we can receive traffic (IPv6+Segment + * Routing Header packets) from several interfaces and the outer IPv6 + * destination address (DA) is used for retrieving the specific instance of the + * End.DT4/DT6 behavior that should process the packets. + * + * However, the inner IPv4/IPv6 packet is not really bound to any receiving + * interface and thus the End.DT4/DT6 sets the VRF (associated with the + * corresponding routing table) as the *receiving* interface. + * In other words, the End.DT4/DT6 processes a packet as if it has been received + * directly by the VRF (and not by one of its slave devices, if any). + * In this way, the VRF interface is used for routing the IPv4/IPv6 packet in + * according to the routing table configured by the End.DT4/DT6 instance. + * + * This design allows you to get some interesting features like: + * 1) the statistics on rx packets; + * 2) the possibility to install a packet sniffer on the receiving interface + * (the VRF one) for looking at the incoming packets; + * 3) the possibility to leverage the netfilter prerouting hook for the inner + * IPv4 packet. + * + * This function returns: + * - the sk_buff* when the VRF rcv handler has processed the packet correctly; + * - NULL when the skb is consumed by the VRF rcv handler; + * - a pointer which encodes a negative error number in case of error. + * Note that in this case, the function takes care of freeing the skb. + */ +static struct sk_buff *end_dt_vrf_rcv(struct sk_buff *skb, u16 family, + struct net_device *dev) +{ + /* based on l3mdev_ip_rcv; we are only interested in the master */ + if (unlikely(!netif_is_l3_master(dev) && !netif_has_l3_rx_handler(dev))) + goto drop; + + if (unlikely(!dev->l3mdev_ops->l3mdev_l3_rcv)) + goto drop; + + /* the decap packet IPv4/IPv6 does not come with any mac header info. + * We must unset the mac header to allow the VRF device to rebuild it, + * just in case there is a sniffer attached on the device. + */ + skb_unset_mac_header(skb); + + skb = dev->l3mdev_ops->l3mdev_l3_rcv(dev, skb, family); + if (!skb) + /* the skb buffer was consumed by the handler */ + return NULL; + + /* when a packet is received by a VRF or by one of its slaves, the + * master device reference is set into the skb. + */ + if (unlikely(skb->dev != dev || skb->skb_iif != dev->ifindex)) + goto drop; + + return skb; + +drop: + kfree_skb(skb); + return ERR_PTR(-EINVAL); +} + +static struct net_device *end_dt_get_vrf_rcu(struct sk_buff *skb, + struct seg6_end_dt_info *info) +{ + int vrf_ifindex = info->vrf_ifindex; + struct net *net = info->net; + + if (unlikely(vrf_ifindex < 0)) + goto error; + + if (unlikely(!net_eq(dev_net(skb->dev), net))) + goto error; + + return dev_get_by_index_rcu(net, vrf_ifindex); + +error: + return NULL; +} + +static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + struct seg6_end_dt_info *info = &slwt->dt_info; + struct net_device *vrf; + + vrf = end_dt_get_vrf_rcu(skb, info); + if (unlikely(!vrf)) + goto drop; + + skb->protocol = info->proto; + + skb_dst_drop(skb); + + skb_set_transport_header(skb, info->hdrlen); + + return end_dt_vrf_rcv(skb, info->family, vrf); + +drop: + kfree_skb(skb); + return ERR_PTR(-EINVAL); +} + +static int input_action_end_dt4(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + struct iphdr *iph; + int err; + + if (!decap_and_validate(skb, IPPROTO_IPIP)) + goto drop; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto drop; + + skb = end_dt_vrf_core(skb, slwt); + if (!skb) + /* packet has been processed and consumed by the VRF */ + return 0; + + if (IS_ERR(skb)) + return PTR_ERR(skb); + + iph = ip_hdr(skb); + + err = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev); + if (unlikely(err)) + goto drop; + + return dst_input(skb); + +drop: + kfree_skb(skb); + return -EINVAL; +} + +static int seg6_end_dt4_build(struct seg6_local_lwt *slwt, const void *cfg, + struct netlink_ext_ack *extack) +{ + return __seg6_end_dt_vrf_build(slwt, cfg, AF_INET, extack); +} +#endif + static int input_action_end_dt6(struct sk_buff *skb, struct seg6_local_lwt *slwt) { @@ -617,6 +839,16 @@ static struct seg6_action_desc seg6_action_table[] = { .attrs = (1 << SEG6_LOCAL_NH4), .input = input_action_end_dx4, }, + { + .action = SEG6_LOCAL_ACTION_END_DT4, + .attrs = (1 << SEG6_LOCAL_VRFTABLE), +#ifdef CONFIG_NET_L3_MASTER_DEV + .input = input_action_end_dt4, + .slwt_ops = { + .build_state = seg6_end_dt4_build, + }, +#endif + }, { .action = SEG6_LOCAL_ACTION_END_DT6, .attrs = (1 << SEG6_LOCAL_TABLE), @@ -677,6 +909,7 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = { [SEG6_LOCAL_ACTION] = { .type = NLA_U32 }, [SEG6_LOCAL_SRH] = { .type = NLA_BINARY }, [SEG6_LOCAL_TABLE] = { .type = NLA_U32 }, + [SEG6_LOCAL_VRFTABLE] = { .type = NLA_U32 }, [SEG6_LOCAL_NH4] = { .type = NLA_BINARY, .len = sizeof(struct in_addr) }, [SEG6_LOCAL_NH6] = { .type = NLA_BINARY, @@ -766,6 +999,53 @@ static int cmp_nla_table(struct seg6_local_lwt *a, struct seg6_local_lwt *b) return 0; } +static struct +seg6_end_dt_info *seg6_possible_end_dt_info(struct seg6_local_lwt *slwt) +{ +#ifdef CONFIG_NET_L3_MASTER_DEV + return &slwt->dt_info; +#else + return ERR_PTR(-EOPNOTSUPP); +#endif +} + +static int parse_nla_vrftable(struct nlattr **attrs, + struct seg6_local_lwt *slwt) +{ + struct seg6_end_dt_info *info = seg6_possible_end_dt_info(slwt); + + if (IS_ERR(info)) + return PTR_ERR(info); + + info->vrf_table = nla_get_u32(attrs[SEG6_LOCAL_VRFTABLE]); + + return 0; +} + +static int put_nla_vrftable(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + struct seg6_end_dt_info *info = seg6_possible_end_dt_info(slwt); + + if (IS_ERR(info)) + return PTR_ERR(info); + + if (nla_put_u32(skb, SEG6_LOCAL_VRFTABLE, info->vrf_table)) + return -EMSGSIZE; + + return 0; +} + +static int cmp_nla_vrftable(struct seg6_local_lwt *a, struct seg6_local_lwt *b) +{ + struct seg6_end_dt_info *info_a = seg6_possible_end_dt_info(a); + struct seg6_end_dt_info *info_b = seg6_possible_end_dt_info(b); + + if (info_a->vrf_table != info_b->vrf_table) + return 1; + + return 0; +} + static int parse_nla_nh4(struct nlattr **attrs, struct seg6_local_lwt *slwt) { memcpy(&slwt->nh4, nla_data(attrs[SEG6_LOCAL_NH4]), @@ -984,6 +1264,10 @@ static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = { .cmp = cmp_nla_bpf, .destroy = destroy_attr_bpf }, + [SEG6_LOCAL_VRFTABLE] = { .parse = parse_nla_vrftable, + .put = put_nla_vrftable, + .cmp = cmp_nla_vrftable }, + }; /* call the destroy() callback (if available) for each set attribute in @@ -1283,6 +1567,9 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt) nla_total_size(MAX_PROG_NAME) + nla_total_size(4); + if (attrs & (1 << SEG6_LOCAL_VRFTABLE)) + nlsize += nla_total_size(4); + return nlsize; } -- cgit v1.3-15-g9ac1 From 4f19cab76136e800a3f04d8c9aa4d8e770e3d3d8 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Fri, 4 Dec 2020 12:36:05 +0100 Subject: bpf: Add a bpf_sock_from_file helper While eBPF programs can check whether a file is a socket by file->f_op == &socket_file_ops, they cannot convert the void private_data pointer to a struct socket BTF pointer. In order to do this a new helper wrapping sock_from_file is added. This is useful to tracing programs but also other program types inheriting this set of helpers such as iterators or LSM programs. Signed-off-by: Florent Revest Signed-off-by: Daniel Borkmann Acked-by: KP Singh Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201204113609.1850150-2-revest@google.com --- include/uapi/linux/bpf.h | 9 +++++++++ kernel/trace/bpf_trace.c | 20 ++++++++++++++++++++ scripts/bpf_helpers_doc.py | 4 ++++ tools/include/uapi/linux/bpf.h | 9 +++++++++ 4 files changed, 42 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1233f14f659f..30b477a26482 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3822,6 +3822,14 @@ union bpf_attr { * The **hash_algo** is returned on success, * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. + * + * struct socket *bpf_sock_from_file(struct file *file) + * Description + * If the given file represents a socket, returns the associated + * socket. + * Return + * A pointer to a struct socket on success or NULL if the file is + * not a socket. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3986,6 +3994,7 @@ union bpf_attr { FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ FN(ima_inode_hash), \ + FN(sock_from_file), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cb9d7478ef0c..0cf0a6331482 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1270,6 +1270,24 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { .arg5_type = ARG_ANYTHING, }; +BPF_CALL_1(bpf_sock_from_file, struct file *, file) +{ + return (unsigned long) sock_from_file(file); +} + +BTF_ID_LIST(bpf_sock_from_file_btf_ids) +BTF_ID(struct, socket) +BTF_ID(struct, file) + +static const struct bpf_func_proto bpf_sock_from_file_proto = { + .func = bpf_sock_from_file, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .ret_btf_id = &bpf_sock_from_file_btf_ids[0], + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_sock_from_file_btf_ids[1], +}; + const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1366,6 +1384,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_per_cpu_ptr_proto; case BPF_FUNC_bpf_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; + case BPF_FUNC_sock_from_file: + return &bpf_sock_from_file_proto; default: return NULL; } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 8b829748d488..867ada23281c 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -437,6 +437,8 @@ class PrinterHelpers(Printer): 'struct path', 'struct btf_ptr', 'struct inode', + 'struct socket', + 'struct file', ] known_types = { '...', @@ -482,6 +484,8 @@ class PrinterHelpers(Printer): 'struct path', 'struct btf_ptr', 'struct inode', + 'struct socket', + 'struct file', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1233f14f659f..30b477a26482 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3822,6 +3822,14 @@ union bpf_attr { * The **hash_algo** is returned on success, * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. + * + * struct socket *bpf_sock_from_file(struct file *file) + * Description + * If the given file represents a socket, returns the associated + * socket. + * Return + * A pointer to a struct socket on success or NULL if the file is + * not a socket. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3986,6 +3994,7 @@ union bpf_attr { FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ FN(ima_inode_hash), \ + FN(sock_from_file), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.3-15-g9ac1 From 18fb76ed53865c1b5d5f0157b1b825704590beb5 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:42 -0800 Subject: net-zerocopy: Copy straggler unaligned data for TCP Rx. zerocopy. When TCP receive zerocopy does not successfully map the entire requested space, it outputs a 'hint' that the caller should recvmsg(). Augment zerocopy to accept a user buffer that it tries to copy this hint into - if it is possible to copy the entire hint, it will do so. This elides a recvmsg() call for received traffic that isn't exactly page-aligned in size. This was tested with RPC-style traffic of arbitrary sizes. Normally, each received message required at least one getsockopt() call, and one recvmsg() call for the remaining unaligned data. With this change, almost all of the recvmsg() calls are eliminated, leading to a savings of about 25%-50% in number of system calls for RPC-style workloads. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 84 +++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 70 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index cfcb10b75483..62db78b9c1a0 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -349,5 +349,7 @@ struct tcp_zerocopy_receive { __u32 recv_skip_hint; /* out: amount of bytes to skip */ __u32 inq; /* out: amount of bytes in read queue */ __s32 err; /* out: socket error */ + __u64 copybuf_address; /* in: copybuf address (small reads) */ + __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 75a28b8f4470..0ad70097da59 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1758,6 +1758,52 @@ int tcp_mmap(struct file *file, struct socket *sock, } EXPORT_SYMBOL(tcp_mmap); +static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, + struct sk_buff *skb, u32 copylen, + u32 *offset, u32 *seq) +{ + unsigned long copy_address = (unsigned long)zc->copybuf_address; + struct msghdr msg = {}; + struct iovec iov; + int err; + + if (copy_address != zc->copybuf_address) + return -EINVAL; + + err = import_single_range(READ, (void __user *)copy_address, + copylen, &iov, &msg.msg_iter); + if (err) + return err; + err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); + if (err) + return err; + zc->recv_skip_hint -= copylen; + *offset += copylen; + *seq += copylen; + return (__s32)copylen; +} + +static int tcp_zerocopy_handle_leftover_data(struct tcp_zerocopy_receive *zc, + struct sock *sk, + struct sk_buff *skb, + u32 *seq, + s32 copybuf_len) +{ + u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); + + if (!copylen) + return 0; + /* skb is null if inq < PAGE_SIZE. */ + if (skb) + offset = *seq - TCP_SKB_CB(skb)->seq; + else + skb = tcp_recv_skb(sk, *seq, &offset); + + zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, + seq); + return zc->copybuf_len < 0 ? 0 : copylen; +} + static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, unsigned long pages_to_map, @@ -1791,8 +1837,10 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc) { + u32 length = 0, offset, vma_len, avail_len, aligned_len, copylen = 0; unsigned long address = (unsigned long)zc->address; - u32 length = 0, seq, offset, zap_len; + s32 copybuf_len = zc->copybuf_len; + struct tcp_sock *tp = tcp_sk(sk); #define PAGE_BATCH_SIZE 8 struct page *pages[PAGE_BATCH_SIZE]; const skb_frag_t *frags = NULL; @@ -1800,10 +1848,12 @@ static int tcp_zerocopy_receive(struct sock *sk, struct sk_buff *skb = NULL; unsigned long pg_idx = 0; unsigned long curr_addr; - struct tcp_sock *tp; - int inq; + u32 seq = tp->copied_seq; + int inq = tcp_inq(sk); int ret; + zc->copybuf_len = 0; + if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; @@ -1812,8 +1862,6 @@ static int tcp_zerocopy_receive(struct sock *sk, sock_rps_record_flow(sk); - tp = tcp_sk(sk); - mmap_read_lock(current->mm); vma = find_vma(current->mm, address); @@ -1821,17 +1869,16 @@ static int tcp_zerocopy_receive(struct sock *sk, mmap_read_unlock(current->mm); return -EINVAL; } - zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); - - seq = tp->copied_seq; - inq = tcp_inq(sk); - zc->length = min_t(u32, zc->length, inq); - zap_len = zc->length & ~(PAGE_SIZE - 1); - if (zap_len) { - zap_page_range(vma, address, zap_len); + vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); + avail_len = min_t(u32, vma_len, inq); + aligned_len = avail_len & ~(PAGE_SIZE - 1); + if (aligned_len) { + zap_page_range(vma, address, aligned_len); + zc->length = aligned_len; zc->recv_skip_hint = 0; } else { - zc->recv_skip_hint = zc->length; + zc->length = avail_len; + zc->recv_skip_hint = avail_len; } ret = 0; curr_addr = address; @@ -1900,13 +1947,18 @@ static int tcp_zerocopy_receive(struct sock *sk, } out: mmap_read_unlock(current->mm); - if (length) { + /* Try to copy straggler data. */ + if (!ret) + copylen = tcp_zerocopy_handle_leftover_data(zc, sk, skb, &seq, + copybuf_len); + + if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ tcp_recv_skb(sk, seq, &offset); - tcp_cleanup_rbuf(sk, length); + tcp_cleanup_rbuf(sk, length + copylen); ret = 0; if (length == zc->length) zc->recv_skip_hint = 0; -- cgit v1.3-15-g9ac1 From 94ab9eb9b234ddf23af04a4bc7e8db68e67b8778 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:49 -0800 Subject: net-zerocopy: Defer vm zap unless actually needed. Zapping pages is required only if we are calling vm_insert_page into a region where pages had previously been mapped. Receive zerocopy allows reusing such regions, and hitherto called zap_page_range() before calling vm_insert_page() in that range. zap_page_range() can also be triggered from userspace with madvise(MADV_DONTNEED). If userspace is configured to call this before reusing a segment, or if there was nothing mapped at this virtual address to begin with, we can avoid calling zap_page_range() under the socket lock. That said, if userspace does not do that, then we are still responsible for calling zap_page_range(). This patch adds a flag that the user can use to hint to the kernel that a zap is not required. If the flag is not set, or if an older user application does not have a flags field at all, then the kernel calls zap_page_range as before. Also, if the flag is set but a zap is still required, the kernel performs that zap as necessary. Thus incorrectly indicating that a zap can be avoided does not change the correctness of operation. It also increases the batchsize for vm_insert_pages and prefetches the page struct for the batch since we're about to bump the refcount. An alternative mechanism could be to not have a flag, assume by default a zap is not needed, and fall back to zapping if needed. However, this would harm performance for older applications for which a zap is necessary, and thus we implement it with an explicit flag so newer applications can opt in. When using RPC-style traffic with medium sized (tens of KB) RPCs, this change yields an efficency improvement of about 30% for QPS/CPU usage. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 2 + net/ipv4/tcp.c | 147 +++++++++++++++++++++++++++++++---------------- 2 files changed, 99 insertions(+), 50 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 62db78b9c1a0..13ceeb395eb8 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -343,6 +343,7 @@ struct tcp_diag_md5sig { /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ +#define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1 struct tcp_zerocopy_receive { __u64 address; /* in: address of mapping */ __u32 length; /* in/out: number of bytes to map/mapped */ @@ -351,5 +352,6 @@ struct tcp_zerocopy_receive { __s32 err; /* out: socket error */ __u64 copybuf_address; /* in: copybuf address (small reads) */ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */ + __u32 flags; /* in: flags */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index df6dd15a5988..3c99d48b65d8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1924,51 +1924,101 @@ static int tcp_zerocopy_handle_leftover_data(struct tcp_zerocopy_receive *zc, return zc->copybuf_len < 0 ? 0 : copylen; } +static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, + struct page **pending_pages, + unsigned long pages_remaining, + unsigned long *address, + u32 *length, + u32 *seq, + struct tcp_zerocopy_receive *zc, + u32 total_bytes_to_map, + int err) +{ + /* At least one page did not map. Try zapping if we skipped earlier. */ + if (err == -EBUSY && + zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) { + u32 maybe_zap_len; + + maybe_zap_len = total_bytes_to_map - /* All bytes to map */ + *length + /* Mapped or pending */ + (pages_remaining * PAGE_SIZE); /* Failed map. */ + zap_page_range(vma, *address, maybe_zap_len); + err = 0; + } + + if (!err) { + unsigned long leftover_pages = pages_remaining; + int bytes_mapped; + + /* We called zap_page_range, try to reinsert. */ + err = vm_insert_pages(vma, *address, + pending_pages, + &pages_remaining); + bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining); + *seq += bytes_mapped; + *address += bytes_mapped; + } + if (err) { + /* Either we were unable to zap, OR we zapped, retried an + * insert, and still had an issue. Either ways, pages_remaining + * is the number of pages we were unable to map, and we unroll + * some state we speculatively touched before. + */ + const int bytes_not_mapped = PAGE_SIZE * pages_remaining; + + *length -= bytes_not_mapped; + zc->recv_skip_hint += bytes_not_mapped; + } + return err; +} + static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, - unsigned long pages_to_map, - unsigned long *insert_addr, - u32 *length_with_pending, + unsigned int pages_to_map, + unsigned long *address, + u32 *length, u32 *seq, - struct tcp_zerocopy_receive *zc) + struct tcp_zerocopy_receive *zc, + u32 total_bytes_to_map) { unsigned long pages_remaining = pages_to_map; - int bytes_mapped; - int ret; + unsigned int pages_mapped; + unsigned int bytes_mapped; + int err; - ret = vm_insert_pages(vma, *insert_addr, pages, &pages_remaining); - bytes_mapped = PAGE_SIZE * (pages_to_map - pages_remaining); + err = vm_insert_pages(vma, *address, pages, &pages_remaining); + pages_mapped = pages_to_map - (unsigned int)pages_remaining; + bytes_mapped = PAGE_SIZE * pages_mapped; /* Even if vm_insert_pages fails, it may have partially succeeded in * mapping (some but not all of the pages). */ *seq += bytes_mapped; - *insert_addr += bytes_mapped; - if (ret) { - /* But if vm_insert_pages did fail, we have to unroll some state - * we speculatively touched before. - */ - const int bytes_not_mapped = PAGE_SIZE * pages_remaining; - *length_with_pending -= bytes_not_mapped; - zc->recv_skip_hint += bytes_not_mapped; - } - return ret; + *address += bytes_mapped; + + if (likely(!err)) + return 0; + + /* Error: maybe zap and retry + rollback state for failed inserts. */ + return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped, + pages_remaining, address, length, seq, zc, total_bytes_to_map, + err); } +#define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc) { - u32 length = 0, offset, vma_len, avail_len, aligned_len, copylen = 0; + u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; + struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE]; s32 copybuf_len = zc->copybuf_len; struct tcp_sock *tp = tcp_sk(sk); - #define PAGE_BATCH_SIZE 8 - struct page *pages[PAGE_BATCH_SIZE]; const skb_frag_t *frags = NULL; + unsigned int pages_to_map = 0; struct vm_area_struct *vma; struct sk_buff *skb = NULL; - unsigned long pg_idx = 0; - unsigned long curr_addr; u32 seq = tp->copied_seq; + u32 total_bytes_to_map; int inq = tcp_inq(sk); int ret; @@ -2002,34 +2052,24 @@ static int tcp_zerocopy_receive(struct sock *sk, } vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); avail_len = min_t(u32, vma_len, inq); - aligned_len = avail_len & ~(PAGE_SIZE - 1); - if (aligned_len) { - zap_page_range(vma, address, aligned_len); - zc->length = aligned_len; + total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1); + if (total_bytes_to_map) { + if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT)) + zap_page_range(vma, address, total_bytes_to_map); + zc->length = total_bytes_to_map; zc->recv_skip_hint = 0; } else { zc->length = avail_len; zc->recv_skip_hint = avail_len; } ret = 0; - curr_addr = address; while (length + PAGE_SIZE <= zc->length) { int mappable_offset; + struct page *page; if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; - /* If we're here, finish the current batch. */ - if (pg_idx) { - ret = tcp_zerocopy_vm_insert_batch(vma, pages, - pg_idx, - &curr_addr, - &length, - &seq, zc); - if (ret) - goto out; - pg_idx = 0; - } if (skb) { if (zc->recv_skip_hint > 0) break; @@ -2050,24 +2090,31 @@ static int tcp_zerocopy_receive(struct sock *sk, zc->recv_skip_hint = mappable_offset; break; } - pages[pg_idx] = skb_frag_page(frags); - pg_idx++; + page = skb_frag_page(frags); + prefetchw(page); + pages[pages_to_map++] = page; length += PAGE_SIZE; zc->recv_skip_hint -= PAGE_SIZE; frags++; - if (pg_idx == PAGE_BATCH_SIZE) { - ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx, - &curr_addr, &length, - &seq, zc); + if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE || + zc->recv_skip_hint < PAGE_SIZE) { + /* Either full batch, or we're about to go to next skb + * (and we cannot unroll failed ops across skbs). + */ + ret = tcp_zerocopy_vm_insert_batch(vma, pages, + pages_to_map, + &address, &length, + &seq, zc, + total_bytes_to_map); if (ret) goto out; - pg_idx = 0; + pages_to_map = 0; } } - if (pg_idx) { - ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx, - &curr_addr, &length, &seq, - zc); + if (pages_to_map) { + ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, + &address, &length, &seq, + zc, total_bytes_to_map); } out: mmap_read_unlock(current->mm); -- cgit v1.3-15-g9ac1 From 921ca574cd382142add8b12d0a7117f495510de5 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sun, 6 Dec 2020 15:47:31 +0100 Subject: can: isotp: add SF_BROADCAST support for functional addressing When CAN_ISOTP_SF_BROADCAST is set in the CAN_ISOTP_OPTS flags the CAN_ISOTP socket is switched into functional addressing mode, where only single frame (SF) protocol data units can be send on the specified CAN interface and the given tp.tx_id after bind(). In opposite to normal and extended addressing this socket does not register a CAN-ID for reception which would be needed for a 1-to-1 ISOTP connection with a segmented bi-directional data transfer. Sending SFs on this socket is therefore a TX-only 'broadcast' operation. Signed-off-by: Oliver Hartkopp Signed-off-by: Thomas Wagner Link: https://lore.kernel.org/r/20201206144731.4609-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 2 +- net/can/isotp.c | 42 +++++++++++++++++++++++++++++------------- 2 files changed, 30 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index 7793b26aa154..c55935b64ccc 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -135,7 +135,7 @@ struct can_isotp_ll_options { #define CAN_ISOTP_FORCE_RXSTMIN 0x100 /* ignore CFs depending on rx stmin */ #define CAN_ISOTP_RX_EXT_ADDR 0x200 /* different rx extended addressing */ #define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */ - +#define CAN_ISOTP_SF_BROADCAST 0x800 /* 1-to-N functional addressing */ /* default values */ diff --git a/net/can/isotp.c b/net/can/isotp.c index d78ab13bd8be..09f781b63d66 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -865,6 +865,14 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (!size || size > MAX_MSG_LENGTH) return -EINVAL; + /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ + off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; + + /* does the given data fit into a single frame for SF_BROADCAST? */ + if ((so->opt.flags & CAN_ISOTP_SF_BROADCAST) && + (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) + return -EINVAL; + err = memcpy_from_msg(so->tx.buf, msg, size); if (err < 0) return err; @@ -891,9 +899,6 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) cf = (struct canfd_frame *)skb->data; skb_put(skb, so->ll.mtu); - /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ - off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; - /* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { /* The message size generally fits into a SingleFrame - good. @@ -1016,7 +1021,7 @@ static int isotp_release(struct socket *sock) hrtimer_cancel(&so->rxtimer); /* remove current filters & unregister */ - if (so->bound) { + if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST))) { if (so->ifindex) { struct net_device *dev; @@ -1052,15 +1057,25 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct net_device *dev; int err = 0; int notify_enetdown = 0; + int do_rx_reg = 1; if (len < CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp)) return -EINVAL; - if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) - return -EADDRNOTAVAIL; + /* do not register frame reception for functional addressing */ + if (so->opt.flags & CAN_ISOTP_SF_BROADCAST) + do_rx_reg = 0; + + /* do not validate rx address for functional addressing */ + if (do_rx_reg) { + if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) + return -EADDRNOTAVAIL; + + if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) + return -EADDRNOTAVAIL; + } - if ((addr->can_addr.tp.rx_id | addr->can_addr.tp.tx_id) & - (CAN_ERR_FLAG | CAN_RTR_FLAG)) + if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) return -EADDRNOTAVAIL; if (!addr->can_ifindex) @@ -1093,13 +1108,14 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) ifindex = dev->ifindex; - can_rx_register(net, dev, addr->can_addr.tp.rx_id, - SINGLE_MASK(addr->can_addr.tp.rx_id), isotp_rcv, sk, - "isotp", sk); + if (do_rx_reg) + can_rx_register(net, dev, addr->can_addr.tp.rx_id, + SINGLE_MASK(addr->can_addr.tp.rx_id), + isotp_rcv, sk, "isotp", sk); dev_put(dev); - if (so->bound) { + if (so->bound && do_rx_reg) { /* unregister old filter */ if (so->ifindex) { dev = dev_get_by_index(net, so->ifindex); @@ -1299,7 +1315,7 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (so->bound) + if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST))) can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); -- cgit v1.3-15-g9ac1 From 4cf476ced45d7f12df30a68e833b263e7a2202d1 Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Thu, 10 Dec 2020 15:50:57 +0000 Subject: ppp: add PPPIOCBRIDGECHAN and PPPIOCUNBRIDGECHAN ioctls This new ioctl pair allows two ppp channels to be bridged together: frames arriving in one channel are transmitted in the other channel and vice versa. The practical use for this is primarily to support the L2TP Access Concentrator use-case. The end-user session is presented as a ppp channel (typically PPPoE, although it could be e.g. PPPoA, or even PPP over a serial link) and is switched into a PPPoL2TP session for transmission to the LNS. At the LNS the PPP session is terminated in the ISP's network. When a PPP channel is bridged to another it takes a reference on the other's struct ppp_file. This reference is dropped when the channels are unbridged, which can occur either explicitly on userspace calling the PPPIOCUNBRIDGECHAN ioctl, or implicitly when either channel in the bridge is unregistered. In order to implement the channel bridge, struct channel is extended with a new field, 'bridge', which points to the other struct channel making up the bridge. This pointer is RCU protected to avoid adding another lock to the data path. To guard against concurrent writes to the pointer, the existing struct channel lock 'upl' coverage is extended rather than adding a new lock. The 'upl' lock is used to protect the existing unit pointer. Since the bridge effectively replaces the unit (they're mutually exclusive for a channel) it makes coding easier to use the same lock to cover them both. Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- drivers/net/ppp/ppp_generic.c | 152 ++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/ppp-ioctl.h | 2 + 2 files changed, 151 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 7d005896a0f9..09c27f7773f9 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -174,7 +174,8 @@ struct channel { struct ppp *ppp; /* ppp unit we're connected to */ struct net *chan_net; /* the net channel belongs to */ struct list_head clist; /* link in list of channels per unit */ - rwlock_t upl; /* protects `ppp' */ + rwlock_t upl; /* protects `ppp' and 'bridge' */ + struct channel __rcu *bridge; /* "bridged" ppp channel */ #ifdef CONFIG_PPP_MULTILINK u8 avail; /* flag used in multilink stuff */ u8 had_frag; /* >= 1 fragments have been sent */ @@ -606,6 +607,83 @@ static struct bpf_prog *compat_ppp_get_filter(struct sock_fprog32 __user *p) #endif #endif +/* Bridge one PPP channel to another. + * When two channels are bridged, ppp_input on one channel is redirected to + * the other's ops->start_xmit handler. + * In order to safely bridge channels we must reject channels which are already + * part of a bridge instance, or which form part of an existing unit. + * Once successfully bridged, each channel holds a reference on the other + * to prevent it being freed while the bridge is extant. + */ +static int ppp_bridge_channels(struct channel *pch, struct channel *pchb) +{ + write_lock_bh(&pch->upl); + if (pch->ppp || + rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) { + write_unlock_bh(&pch->upl); + return -EALREADY; + } + rcu_assign_pointer(pch->bridge, pchb); + write_unlock_bh(&pch->upl); + + write_lock_bh(&pchb->upl); + if (pchb->ppp || + rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl))) { + write_unlock_bh(&pchb->upl); + goto err_unset; + } + rcu_assign_pointer(pchb->bridge, pch); + write_unlock_bh(&pchb->upl); + + refcount_inc(&pch->file.refcnt); + refcount_inc(&pchb->file.refcnt); + + return 0; + +err_unset: + write_lock_bh(&pch->upl); + RCU_INIT_POINTER(pch->bridge, NULL); + write_unlock_bh(&pch->upl); + synchronize_rcu(); + return -EALREADY; +} + +static int ppp_unbridge_channels(struct channel *pch) +{ + struct channel *pchb, *pchbb; + + write_lock_bh(&pch->upl); + pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); + if (!pchb) { + write_unlock_bh(&pch->upl); + return -EINVAL; + } + RCU_INIT_POINTER(pch->bridge, NULL); + write_unlock_bh(&pch->upl); + + /* Only modify pchb if phcb->bridge points back to pch. + * If not, it implies that there has been a race unbridging (and possibly + * even rebridging) pchb. We should leave pchb alone to avoid either a + * refcount underflow, or breaking another established bridge instance. + */ + write_lock_bh(&pchb->upl); + pchbb = rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl)); + if (pchbb == pch) + RCU_INIT_POINTER(pchb->bridge, NULL); + write_unlock_bh(&pchb->upl); + + synchronize_rcu(); + + if (pchbb == pch) + if (refcount_dec_and_test(&pch->file.refcnt)) + ppp_destroy_channel(pch); + + if (refcount_dec_and_test(&pchb->file.refcnt)) + ppp_destroy_channel(pchb); + + return 0; +} + static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; @@ -641,8 +719,9 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } if (pf->kind == CHANNEL) { - struct channel *pch; + struct channel *pch, *pchb; struct ppp_channel *chan; + struct ppp_net *pn; pch = PF_TO_CHANNEL(pf); @@ -657,6 +736,31 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) err = ppp_disconnect_channel(pch); break; + case PPPIOCBRIDGECHAN: + if (get_user(unit, p)) + break; + err = -ENXIO; + pn = ppp_pernet(current->nsproxy->net_ns); + spin_lock_bh(&pn->all_channels_lock); + pchb = ppp_find_channel(pn, unit); + /* Hold a reference to prevent pchb being freed while + * we establish the bridge. + */ + if (pchb) + refcount_inc(&pchb->file.refcnt); + spin_unlock_bh(&pn->all_channels_lock); + if (!pchb) + break; + err = ppp_bridge_channels(pch, pchb); + /* Drop earlier refcount now bridge establishment is complete */ + if (refcount_dec_and_test(&pchb->file.refcnt)) + ppp_destroy_channel(pchb); + break; + + case PPPIOCUNBRIDGECHAN: + err = ppp_unbridge_channels(pch); + break; + default: down_read(&pch->chan_sem); chan = pch->chan; @@ -2089,6 +2193,40 @@ static bool ppp_decompress_proto(struct sk_buff *skb) return pskb_may_pull(skb, 2); } +/* Attempt to handle a frame via. a bridged channel, if one exists. + * If the channel is bridged, the frame is consumed by the bridge. + * If not, the caller must handle the frame by normal recv mechanisms. + * Returns true if the frame is consumed, false otherwise. + */ +static bool ppp_channel_bridge_input(struct channel *pch, struct sk_buff *skb) +{ + struct channel *pchb; + + rcu_read_lock(); + pchb = rcu_dereference(pch->bridge); + if (!pchb) + goto out_rcu; + + spin_lock(&pchb->downl); + if (!pchb->chan) { + /* channel got unregistered */ + kfree_skb(skb); + goto outl; + } + + skb_scrub_packet(skb, !net_eq(pch->chan_net, pchb->chan_net)); + if (!pchb->chan->ops->start_xmit(pchb->chan, skb)) + kfree_skb(skb); + +outl: + spin_unlock(&pchb->downl); +out_rcu: + rcu_read_unlock(); + + /* If pchb is set then we've consumed the packet */ + return !!pchb; +} + void ppp_input(struct ppp_channel *chan, struct sk_buff *skb) { @@ -2100,6 +2238,10 @@ ppp_input(struct ppp_channel *chan, struct sk_buff *skb) return; } + /* If the channel is bridged, transmit via. bridge */ + if (ppp_channel_bridge_input(pch, skb)) + return; + read_lock_bh(&pch->upl); if (!ppp_decompress_proto(skb)) { kfree_skb(skb); @@ -2796,8 +2938,11 @@ ppp_unregister_channel(struct ppp_channel *chan) list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); + ppp_unbridge_channels(pch); + pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); + if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); } @@ -3270,7 +3415,8 @@ ppp_connect_channel(struct channel *pch, int unit) goto out; write_lock_bh(&pch->upl); ret = -EINVAL; - if (pch->ppp) + if (pch->ppp || + rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) goto outl; ppp_lock(ppp); diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h index 7bd2a5a75348..8dbecb3ad036 100644 --- a/include/uapi/linux/ppp-ioctl.h +++ b/include/uapi/linux/ppp-ioctl.h @@ -115,6 +115,8 @@ struct pppol2tp_ioc_stats { #define PPPIOCATTCHAN _IOW('t', 56, int) /* attach to ppp channel */ #define PPPIOCGCHAN _IOR('t', 55, int) /* get ppp channel number */ #define PPPIOCGL2TPSTATS _IOR('t', 54, struct pppol2tp_ioc_stats) +#define PPPIOCBRIDGECHAN _IOW('t', 53, int) /* bridge one channel to another */ +#define PPPIOCUNBRIDGECHAN _IO('t', 54) /* unbridge channel */ #define SIOCGPPPSTATS (SIOCDEVPRIVATE + 0) #define SIOCGPPPVER (SIOCDEVPRIVATE + 1) /* NEVER change this!! */ -- cgit v1.3-15-g9ac1 From 14486c82612a177cb910980c70ba900827ca0894 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Wed, 4 Nov 2020 15:46:41 +0200 Subject: rfkill: add a reason to the HW rfkill state The WLAN device may exist yet not be usable. This can happen when the WLAN device is controllable by both the host and some platform internal component. We need some arbritration that is vendor specific, but when the device is not available for the host, we need to reflect this state towards the user space. Add a reason field to the rfkill object (and event) so that userspace can know why the device is in rfkill: because some other platform component currently owns the device, or because the actual hw rfkill signal is asserted. Capable userspace can now determine the reason for the rfkill and possibly do some negotiation on a side band channel using a proprietary protocol to gain ownership on the device in case the device is owned by some other component. When the host gains ownership on the device, the kernel can remove the RFKILL_HARD_BLOCK_NOT_OWNER reason and the hw rfkill state will be off. Then, the userspace can bring the device up and start normal operation. The rfkill_event structure is enlarged to include the additional byte, it is now 9 bytes long. Old user space will ask to read only 8 bytes so that the kernel can know not to feed them with more data. When the user space writes 8 bytes, new kernels will just read what is present in the file descriptor. This new byte is read only from the userspace standpoint anyway. If a new user space uses an old kernel, it'll ask to read 9 bytes but will get only 8, and it'll know that it didn't get the new state. When it'll write 9 bytes, the kernel will again ignore this new byte which is read only from the userspace standpoint. Signed-off-by: Emmanuel Grumbach Link: https://lore.kernel.org/r/20201104134641.28816-1-emmanuel.grumbach@intel.com Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 24 +++++++++++++++++++++++- include/uapi/linux/rfkill.h | 16 +++++++++++++++- net/rfkill/core.c | 41 ++++++++++++++++++++++++++++++++++------- 3 files changed, 72 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 8ad2487a86d5..231e06b74b50 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -137,6 +137,17 @@ void rfkill_unregister(struct rfkill *rfkill); */ void rfkill_destroy(struct rfkill *rfkill); +/** + * rfkill_set_hw_state_reason - Set the internal rfkill hardware block state + * with a reason + * @rfkill: pointer to the rfkill class to modify. + * @blocked: the current hardware block state to set + * @reason: one of &enum rfkill_hard_block_reasons + * + * Prefer to use rfkill_set_hw_state if you don't need any special reason. + */ +bool rfkill_set_hw_state_reason(struct rfkill *rfkill, + bool blocked, unsigned long reason); /** * rfkill_set_hw_state - Set the internal rfkill hardware block state * @rfkill: pointer to the rfkill class to modify. @@ -156,7 +167,11 @@ void rfkill_destroy(struct rfkill *rfkill); * should be blocked) so that drivers need not keep track of the soft * block state -- which they might not be able to. */ -bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked); +static inline bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked) +{ + return rfkill_set_hw_state_reason(rfkill, blocked, + RFKILL_HARD_BLOCK_SIGNAL); +} /** * rfkill_set_sw_state - Set the internal rfkill software block state @@ -256,6 +271,13 @@ static inline void rfkill_destroy(struct rfkill *rfkill) { } +static inline bool rfkill_set_hw_state_reason(struct rfkill *rfkill, + bool blocked, + unsigned long reason) +{ + return blocked; +} + static inline bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked) { return blocked; diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 2e00dcebebd0..03e8af87b364 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -69,6 +69,16 @@ enum rfkill_operation { RFKILL_OP_CHANGE_ALL, }; +/** + * enum rfkill_hard_block_reasons - hard block reasons + * @RFKILL_HARD_BLOCK_SIGNAL: the hardware rfkill signal is active + * @RFKILL_HARD_BLOCK_NOT_OWNER: the NIC is not owned by the host + */ +enum rfkill_hard_block_reasons { + RFKILL_HARD_BLOCK_SIGNAL = 1 << 0, + RFKILL_HARD_BLOCK_NOT_OWNER = 1 << 1, +}; + /** * struct rfkill_event - events for userspace on /dev/rfkill * @idx: index of dev rfkill @@ -76,6 +86,8 @@ enum rfkill_operation { * @op: operation code * @hard: hard state (0/1) * @soft: soft state (0/1) + * @hard_block_reasons: valid if hard is set. One or several reasons from + * &enum rfkill_hard_block_reasons. * * Structure used for userspace communication on /dev/rfkill, * used for events from the kernel and control to the kernel. @@ -84,7 +96,9 @@ struct rfkill_event { __u32 idx; __u8 type; __u8 op; - __u8 soft, hard; + __u8 soft; + __u8 hard; + __u8 hard_block_reasons; } __attribute__((packed)); /* diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 97101c55763d..68d6ef9e59fc 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -40,6 +40,7 @@ struct rfkill { enum rfkill_type type; unsigned long state; + unsigned long hard_block_reasons; u32 idx; @@ -265,6 +266,7 @@ static void rfkill_fill_event(struct rfkill_event *ev, struct rfkill *rfkill, ev->hard = !!(rfkill->state & RFKILL_BLOCK_HW); ev->soft = !!(rfkill->state & (RFKILL_BLOCK_SW | RFKILL_BLOCK_SW_PREV)); + ev->hard_block_reasons = rfkill->hard_block_reasons; spin_unlock_irqrestore(&rfkill->lock, flags); } @@ -522,19 +524,29 @@ bool rfkill_get_global_sw_state(const enum rfkill_type type) } #endif -bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked) +bool rfkill_set_hw_state_reason(struct rfkill *rfkill, + bool blocked, unsigned long reason) { unsigned long flags; bool ret, prev; BUG_ON(!rfkill); + if (WARN(reason & + ~(RFKILL_HARD_BLOCK_SIGNAL | RFKILL_HARD_BLOCK_NOT_OWNER), + "hw_state reason not supported: 0x%lx", reason)) + return blocked; + spin_lock_irqsave(&rfkill->lock, flags); - prev = !!(rfkill->state & RFKILL_BLOCK_HW); - if (blocked) + prev = !!(rfkill->hard_block_reasons & reason); + if (blocked) { rfkill->state |= RFKILL_BLOCK_HW; - else - rfkill->state &= ~RFKILL_BLOCK_HW; + rfkill->hard_block_reasons |= reason; + } else { + rfkill->hard_block_reasons &= ~reason; + if (!rfkill->hard_block_reasons) + rfkill->state &= ~RFKILL_BLOCK_HW; + } ret = !!(rfkill->state & RFKILL_BLOCK_ANY); spin_unlock_irqrestore(&rfkill->lock, flags); @@ -546,7 +558,7 @@ bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked) return ret; } -EXPORT_SYMBOL(rfkill_set_hw_state); +EXPORT_SYMBOL(rfkill_set_hw_state_reason); static void __rfkill_set_sw_state(struct rfkill *rfkill, bool blocked) { @@ -744,6 +756,16 @@ static ssize_t soft_store(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RW(soft); +static ssize_t hard_block_reasons_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct rfkill *rfkill = to_rfkill(dev); + + return sprintf(buf, "0x%lx\n", rfkill->hard_block_reasons); +} +static DEVICE_ATTR_RO(hard_block_reasons); + static u8 user_state_from_blocked(unsigned long state) { if (state & RFKILL_BLOCK_HW) @@ -796,6 +818,7 @@ static struct attribute *rfkill_dev_attrs[] = { &dev_attr_state.attr, &dev_attr_soft.attr, &dev_attr_hard.attr, + &dev_attr_hard_block_reasons.attr, NULL, }; ATTRIBUTE_GROUPS(rfkill_dev); @@ -811,6 +834,7 @@ static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env) { struct rfkill *rfkill = to_rfkill(dev); unsigned long flags; + unsigned long reasons; u32 state; int error; @@ -823,10 +847,13 @@ static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env) return error; spin_lock_irqsave(&rfkill->lock, flags); state = rfkill->state; + reasons = rfkill->hard_block_reasons; spin_unlock_irqrestore(&rfkill->lock, flags); error = add_uevent_var(env, "RFKILL_STATE=%d", user_state_from_blocked(state)); - return error; + if (error) + return error; + return add_uevent_var(env, "RFKILL_HW_BLOCK_REASON=0x%lx", reasons); } void rfkill_pause_polling(struct rfkill *rfkill) -- cgit v1.3-15-g9ac1 From 669b84134a2be14d333d4f82b65943d467404f87 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 29 Nov 2020 17:30:55 +0200 Subject: cfg80211: include block-tx flag in channel switch started event In the NL80211_CMD_CH_SWITCH_STARTED_NOTIFY event, include the NL80211_ATTR_CH_SWITCH_BLOCK_TX flag attribute if block-tx was requested by the AP. Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20201129172929.8953ef22cc64.Ifee9cab337a4369938545920ba5590559e91327a@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 3 ++- include/uapi/linux/nl80211.h | 3 ++- net/mac80211/cfg.c | 2 +- net/mac80211/mlme.c | 2 +- net/wireless/nl80211.c | 17 +++++++++++------ 5 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f3dfb26b50b9..d9b67eed4f75 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7532,6 +7532,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev, * @dev: the device on which the channel switch started * @chandef: the future channel definition * @count: the number of TBTTs until the channel switch happens + * @quiet: whether or not immediate quiet was requested by the AP * * Inform the userspace about the channel switch that has just * started, so that it can take appropriate actions (eg. starting @@ -7539,7 +7540,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev, */ void cfg80211_ch_switch_started_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, - u8 count); + u8 count, bool quiet); /** * ieee80211_operating_class_to_band - convert operating class to band diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 3e0d4a038ab6..83c860395dd6 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2079,7 +2079,8 @@ enum nl80211_commands { * until the channel switch event. * @NL80211_ATTR_CH_SWITCH_BLOCK_TX: flag attribute specifying that transmission * must be blocked on the current channel (before the channel switch - * operation). + * operation). Also included in the channel switch started event if quiet + * was requested by the AP. * @NL80211_ATTR_CSA_IES: Nested set of attributes containing the IE information * for the time while performing a channel switch. * @NL80211_ATTR_CNTDWN_OFFS_BEACON: An array of offsets (u16) to the channel diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c0d0b15c10fd..7da343efd090 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3450,7 +3450,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, IEEE80211_QUEUE_STOP_REASON_CSA); cfg80211_ch_switch_started_notify(sdata->dev, &sdata->csa_chandef, - params->count); + params->count, params->block_tx); if (changed) { ieee80211_bss_info_change_notify(sdata, changed); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 67829667d394..d4da9822a111 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1509,7 +1509,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, mutex_unlock(&local->mtx); cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chandef, - csa_ie.count); + csa_ie.count, csa_ie.mode); if (local->ops->channel_switch) { /* use driver's channel switch callback */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4a7ef3b584be..c8d31181a660 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17062,7 +17062,7 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef, gfp_t gfp, enum nl80211_commands notif, - u8 count) + u8 count, bool quiet) { struct sk_buff *msg; void *hdr; @@ -17083,9 +17083,13 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, if (nl80211_send_chandef(msg, chandef)) goto nla_put_failure; - if ((notif == NL80211_CMD_CH_SWITCH_STARTED_NOTIFY) && - (nla_put_u32(msg, NL80211_ATTR_CH_SWITCH_COUNT, count))) + if (notif == NL80211_CMD_CH_SWITCH_STARTED_NOTIFY) { + if (nla_put_u32(msg, NL80211_ATTR_CH_SWITCH_COUNT, count)) goto nla_put_failure; + if (quiet && + nla_put_flag(msg, NL80211_ATTR_CH_SWITCH_BLOCK_TX)) + goto nla_put_failure; + } genlmsg_end(msg, hdr); @@ -17118,13 +17122,13 @@ void cfg80211_ch_switch_notify(struct net_device *dev, cfg80211_sched_dfs_chan_update(rdev); nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL, - NL80211_CMD_CH_SWITCH_NOTIFY, 0); + NL80211_CMD_CH_SWITCH_NOTIFY, 0, false); } EXPORT_SYMBOL(cfg80211_ch_switch_notify); void cfg80211_ch_switch_started_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, - u8 count) + u8 count, bool quiet) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; @@ -17133,7 +17137,8 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev, trace_cfg80211_ch_switch_started_notify(dev, chandef); nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL, - NL80211_CMD_CH_SWITCH_STARTED_NOTIFY, count); + NL80211_CMD_CH_SWITCH_STARTED_NOTIFY, + count, quiet); } EXPORT_SYMBOL(cfg80211_ch_switch_started_notify); -- cgit v1.3-15-g9ac1 From 3bb02143ff55fec55558da4ad48425bf368eb8ed Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 6 Dec 2020 14:54:42 +0200 Subject: cfg80211: support immediate reconnect request hint There are cases where it's necessary to disconnect, but an immediate reconnection is desired. Support a hint to userspace that this is the case, by including a new attribute in the deauth or disassoc event. Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20201206145305.58d33941fb9d.I0e7168c205c7949529c8e3b86f3c9b12c01a7017@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 +++- include/uapi/linux/nl80211.h | 6 ++++++ net/mac80211/mlme.c | 5 +++-- net/wireless/mlme.c | 26 +++++++++++++++----------- net/wireless/nl80211.c | 23 +++++++++++++++-------- net/wireless/nl80211.h | 8 +++++--- net/wireless/trace.h | 12 ++++++++---- 7 files changed, 55 insertions(+), 29 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1a79d6baa254..f7470eac2fc8 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6406,13 +6406,15 @@ void cfg80211_abandon_assoc(struct net_device *dev, struct cfg80211_bss *bss); * @dev: network device * @buf: 802.11 frame (header + body) * @len: length of the frame data + * @reconnect: immediate reconnect is desired (include the nl80211 attribute) * * This function is called whenever deauthentication has been processed in * station mode. This includes both received deauthentication frames and * locally generated ones. This function may sleep. The caller must hold the * corresponding wdev's mutex. */ -void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len); +void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len, + bool reconnect); /** * cfg80211_rx_unprot_mlme_mgmt - notification of unprotected mlme mgmt frame diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 83c860395dd6..c5b729e91068 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2535,6 +2535,10 @@ enum nl80211_commands { * This is a u8 attribute that encapsulates one of the values from * &enum nl80211_sae_pwe_mechanism. * + * @NL80211_ATTR_RECONNECT_REQUESTED: flag attribute, used with deauth and + * disassoc events to indicate that an immediate reconnect to the AP + * is desired. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3026,6 +3030,8 @@ enum nl80211_attrs { NL80211_ATTR_SAE_PWE, + NL80211_ATTR_RECONNECT_REQUESTED, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index d4da9822a111..5a2828dccfa5 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2741,7 +2741,7 @@ static void ieee80211_report_disconnect(struct ieee80211_sub_if_data *sdata, }; if (tx) - cfg80211_tx_mlme_mgmt(sdata->dev, buf, len); + cfg80211_tx_mlme_mgmt(sdata->dev, buf, len, false); else cfg80211_rx_mlme_mgmt(sdata->dev, buf, len); @@ -4721,7 +4721,8 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata) if (ifmgd->auth_data) ieee80211_destroy_auth_data(sdata, false); cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); + IEEE80211_DEAUTH_FRAME_LEN, + false); } /* This is a bit of a hack - we should find a better and more generic diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 0ac820780437..e1e90761dc00 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -4,7 +4,7 @@ * * Copyright (c) 2009, Jouni Malinen * Copyright (c) 2015 Intel Deutschland GmbH - * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2019-2020 Intel Corporation */ #include @@ -81,7 +81,8 @@ static void cfg80211_process_auth(struct wireless_dev *wdev, } static void cfg80211_process_deauth(struct wireless_dev *wdev, - const u8 *buf, size_t len) + const u8 *buf, size_t len, + bool reconnect) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; @@ -89,7 +90,7 @@ static void cfg80211_process_deauth(struct wireless_dev *wdev, u16 reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); bool from_ap = !ether_addr_equal(mgmt->sa, wdev->netdev->dev_addr); - nl80211_send_deauth(rdev, wdev->netdev, buf, len, GFP_KERNEL); + nl80211_send_deauth(rdev, wdev->netdev, buf, len, reconnect, GFP_KERNEL); if (!wdev->current_bss || !ether_addr_equal(wdev->current_bss->pub.bssid, bssid)) @@ -100,7 +101,8 @@ static void cfg80211_process_deauth(struct wireless_dev *wdev, } static void cfg80211_process_disassoc(struct wireless_dev *wdev, - const u8 *buf, size_t len) + const u8 *buf, size_t len, + bool reconnect) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; @@ -108,7 +110,8 @@ static void cfg80211_process_disassoc(struct wireless_dev *wdev, u16 reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); bool from_ap = !ether_addr_equal(mgmt->sa, wdev->netdev->dev_addr); - nl80211_send_disassoc(rdev, wdev->netdev, buf, len, GFP_KERNEL); + nl80211_send_disassoc(rdev, wdev->netdev, buf, len, reconnect, + GFP_KERNEL); if (WARN_ON(!wdev->current_bss || !ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) @@ -133,9 +136,9 @@ void cfg80211_rx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len) if (ieee80211_is_auth(mgmt->frame_control)) cfg80211_process_auth(wdev, buf, len); else if (ieee80211_is_deauth(mgmt->frame_control)) - cfg80211_process_deauth(wdev, buf, len); + cfg80211_process_deauth(wdev, buf, len, false); else if (ieee80211_is_disassoc(mgmt->frame_control)) - cfg80211_process_disassoc(wdev, buf, len); + cfg80211_process_disassoc(wdev, buf, len, false); } EXPORT_SYMBOL(cfg80211_rx_mlme_mgmt); @@ -180,22 +183,23 @@ void cfg80211_abandon_assoc(struct net_device *dev, struct cfg80211_bss *bss) } EXPORT_SYMBOL(cfg80211_abandon_assoc); -void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len) +void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len, + bool reconnect) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_mgmt *mgmt = (void *)buf; ASSERT_WDEV_LOCK(wdev); - trace_cfg80211_tx_mlme_mgmt(dev, buf, len); + trace_cfg80211_tx_mlme_mgmt(dev, buf, len, reconnect); if (WARN_ON(len < 2)) return; if (ieee80211_is_deauth(mgmt->frame_control)) - cfg80211_process_deauth(wdev, buf, len); + cfg80211_process_deauth(wdev, buf, len, reconnect); else - cfg80211_process_disassoc(wdev, buf, len); + cfg80211_process_disassoc(wdev, buf, len, reconnect); } EXPORT_SYMBOL(cfg80211_tx_mlme_mgmt); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 910872974f2d..390e6e0f23ac 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -718,6 +718,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_SAE_PWE] = NLA_POLICY_RANGE(NLA_U8, NL80211_SAE_PWE_HUNT_AND_PECK, NL80211_SAE_PWE_BOTH), + [NL80211_ATTR_RECONNECT_REQUESTED] = { .type = NLA_REJECT }, }; /* policy for the key attributes */ @@ -15855,7 +15856,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, const u8 *buf, size_t len, enum nl80211_commands cmd, gfp_t gfp, int uapsd_queues, const u8 *req_ies, - size_t req_ies_len) + size_t req_ies_len, bool reconnect) { struct sk_buff *msg; void *hdr; @@ -15877,6 +15878,9 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_REQ_IE, req_ies_len, req_ies))) goto nla_put_failure; + if (reconnect && nla_put_flag(msg, NL80211_ATTR_RECONNECT_REQUESTED)) + goto nla_put_failure; + if (uapsd_queues >= 0) { struct nlattr *nla_wmm = nla_nest_start_noflag(msg, NL80211_ATTR_STA_WME); @@ -15905,7 +15909,8 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, size_t len, gfp_t gfp) { nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_AUTHENTICATE, gfp, -1, NULL, 0); + NL80211_CMD_AUTHENTICATE, gfp, -1, NULL, 0, + false); } void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, @@ -15915,23 +15920,25 @@ void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, { nl80211_send_mlme_event(rdev, netdev, buf, len, NL80211_CMD_ASSOCIATE, gfp, uapsd_queues, - req_ies, req_ies_len); + req_ies, req_ies_len, false); } void nl80211_send_deauth(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, - size_t len, gfp_t gfp) + size_t len, bool reconnect, gfp_t gfp) { nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_DEAUTHENTICATE, gfp, -1, NULL, 0); + NL80211_CMD_DEAUTHENTICATE, gfp, -1, NULL, 0, + reconnect); } void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, - size_t len, gfp_t gfp) + size_t len, bool reconnect, gfp_t gfp) { nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_DISASSOCIATE, gfp, -1, NULL, 0); + NL80211_CMD_DISASSOCIATE, gfp, -1, NULL, 0, + reconnect); } void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf, @@ -15962,7 +15969,7 @@ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf, trace_cfg80211_rx_unprot_mlme_mgmt(dev, buf, len); nl80211_send_mlme_event(rdev, dev, buf, len, cmd, GFP_ATOMIC, -1, - NULL, 0); + NULL, 0, false); } EXPORT_SYMBOL(cfg80211_rx_unprot_mlme_mgmt); diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index d3e8e426c486..a3f387770f1b 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018, 2020 Intel Corporation */ #ifndef __NET_WIRELESS_NL80211_H #define __NET_WIRELESS_NL80211_H @@ -69,10 +69,12 @@ void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, const u8 *req_ies, size_t req_ies_len); void nl80211_send_deauth(struct cfg80211_registered_device *rdev, struct net_device *netdev, - const u8 *buf, size_t len, gfp_t gfp); + const u8 *buf, size_t len, + bool reconnect, gfp_t gfp); void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, - const u8 *buf, size_t len, gfp_t gfp); + const u8 *buf, size_t len, + bool reconnect, gfp_t gfp); void nl80211_send_auth_timeout(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *addr, gfp_t gfp); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 817c6fef13be..d75cd23aea02 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2679,19 +2679,23 @@ DEFINE_EVENT(netdev_frame_event, cfg80211_rx_mlme_mgmt, ); TRACE_EVENT(cfg80211_tx_mlme_mgmt, - TP_PROTO(struct net_device *netdev, const u8 *buf, int len), - TP_ARGS(netdev, buf, len), + TP_PROTO(struct net_device *netdev, const u8 *buf, int len, + bool reconnect), + TP_ARGS(netdev, buf, len, reconnect), TP_STRUCT__entry( NETDEV_ENTRY __dynamic_array(u8, frame, len) + __field(int, reconnect) ), TP_fast_assign( NETDEV_ASSIGN; memcpy(__get_dynamic_array(frame), buf, len); + __entry->reconnect = reconnect; ), - TP_printk(NETDEV_PR_FMT ", ftype:0x%.2x", + TP_printk(NETDEV_PR_FMT ", ftype:0x%.2x reconnect:%d", NETDEV_PR_ARG, - le16_to_cpup((__le16 *)__get_dynamic_array(frame))) + le16_to_cpup((__le16 *)__get_dynamic_array(frame)), + __entry->reconnect) ); DECLARE_EVENT_CLASS(netdev_mac_evt, -- cgit v1.3-15-g9ac1 From 6bdb68cef7bf57cdb3f8d1498623556d6823ff3a Mon Sep 17 00:00:00 2001 From: Carl Huang Date: Thu, 3 Dec 2020 05:37:26 -0500 Subject: nl80211: add common API to configure SAR power limitations NL80211_CMD_SET_SAR_SPECS is added to configure SAR from user space. NL80211_ATTR_SAR_SPEC is used to pass the SAR power specification when used with NL80211_CMD_SET_SAR_SPECS. Wireless driver needs to register SAR type, supported frequency ranges to wiphy, so user space can query it. The index in frequency range is used to specify which sub band the power limitation applies to. The SAR type is for compatibility, so later other SAR mechanism can be implemented without breaking the user space SAR applications. Normal process is user space queries the SAR capability, and gets the index of supported frequency ranges and associates the power limitation with this index and sends to kernel. Here is an example of message send to kernel: 8c 00 00 00 08 00 01 00 00 00 00 00 38 00 2b 81 08 00 01 00 00 00 00 00 2c 00 02 80 14 00 00 80 08 00 02 00 00 00 00 00 08 00 01 00 38 00 00 00 14 00 01 80 08 00 02 00 01 00 00 00 08 00 01 00 48 00 00 00 NL80211_CMD_SET_SAR_SPECS: 0x8c NL80211_ATTR_WIPHY: 0x01(phy idx is 0) NL80211_ATTR_SAR_SPEC: 0x812b (NLA_NESTED) NL80211_SAR_ATTR_TYPE: 0x00 (NL80211_SAR_TYPE_POWER) NL80211_SAR_ATTR_SPECS: 0x8002 (NLA_NESTED) freq range 0 power: 0x38 in 0.25dbm unit (14dbm) freq range 1 power: 0x48 in 0.25dbm unit (18dbm) Signed-off-by: Carl Huang Reviewed-by: Brian Norris Reviewed-by: Abhishek Kumar Link: https://lore.kernel.org/r/20201203103728.3034-2-cjhuang@codeaurora.org [minor edits, NLA parse cleanups] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 52 ++++++++++++ include/uapi/linux/nl80211.h | 105 +++++++++++++++++++++++++ net/wireless/nl80211.c | 183 +++++++++++++++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 12 +++ net/wireless/trace.h | 19 +++++ 5 files changed, 371 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f7470eac2fc8..9a4bbccddc7f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1732,6 +1732,54 @@ struct station_info { u8 connected_to_as; }; +/** + * struct cfg80211_sar_sub_specs - sub specs limit + * @power: power limitation in 0.25dbm + * @freq_range_index: index the power limitation applies to + */ +struct cfg80211_sar_sub_specs { + s32 power; + u32 freq_range_index; +}; + +/** + * struct cfg80211_sar_specs - sar limit specs + * @type: it's set with power in 0.25dbm or other types + * @num_sub_specs: number of sar sub specs + * @sub_specs: memory to hold the sar sub specs + */ +struct cfg80211_sar_specs { + enum nl80211_sar_type type; + u32 num_sub_specs; + struct cfg80211_sar_sub_specs sub_specs[]; +}; + + +/** + * @struct cfg80211_sar_chan_ranges - sar frequency ranges + * @start_freq: start range edge frequency + * @end_freq: end range edge frequency + */ +struct cfg80211_sar_freq_ranges { + u32 start_freq; + u32 end_freq; +}; + +/** + * struct cfg80211_sar_capa - sar limit capability + * @type: it's set via power in 0.25dbm or other types + * @num_freq_ranges: number of frequency ranges + * @freq_ranges: memory to hold the freq ranges. + * + * Note: WLAN driver may append new ranges or split an existing + * range to small ones and then append them. + */ +struct cfg80211_sar_capa { + enum nl80211_sar_type type; + u32 num_freq_ranges; + const struct cfg80211_sar_freq_ranges *freq_ranges; +}; + #if IS_ENABLED(CONFIG_CFG80211) /** * cfg80211_get_station - retrieve information about a given station @@ -4249,6 +4297,8 @@ struct cfg80211_ops { struct cfg80211_tid_config *tid_conf); int (*reset_tid_config)(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u8 tids); + int (*set_sar_specs)(struct wiphy *wiphy, + struct cfg80211_sar_specs *sar); }; /* @@ -5017,6 +5067,8 @@ struct wiphy { u8 max_data_retry_count; + const struct cfg80211_sar_capa *sar_capa; + char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c5b729e91068..40832d13c2f1 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1178,6 +1178,10 @@ * includes the contents of the frame. %NL80211_ATTR_ACK flag is included * if the recipient acknowledged the frame. * + * @NL80211_CMD_SET_SAR_SPECS: SAR power limitation configuration is + * passed using %NL80211_ATTR_SAR_SPEC. %NL80211_ATTR_WIPHY is used to + * specify the wiphy index to be applied to. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1408,6 +1412,8 @@ enum nl80211_commands { NL80211_CMD_CONTROL_PORT_FRAME_TX_STATUS, + NL80211_CMD_SET_SAR_SPECS, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2535,6 +2541,11 @@ enum nl80211_commands { * This is a u8 attribute that encapsulates one of the values from * &enum nl80211_sae_pwe_mechanism. * + * @NL80211_ATTR_SAR_SPEC: SAR power limitation specification when + * used with %NL80211_CMD_SET_SAR_SPECS. The message contains fields + * of %nl80211_sar_attrs which specifies the sar type and related + * sar specs. Sar specs contains array of %nl80211_sar_specs_attrs. + * * @NL80211_ATTR_RECONNECT_REQUESTED: flag attribute, used with deauth and * disassoc events to indicate that an immediate reconnect to the AP * is desired. @@ -3032,6 +3043,8 @@ enum nl80211_attrs { NL80211_ATTR_RECONNECT_REQUESTED, + NL80211_ATTR_SAR_SPEC, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -7163,4 +7176,96 @@ enum nl80211_sae_pwe_mechanism { NL80211_SAE_PWE_HASH_TO_ELEMENT, NL80211_SAE_PWE_BOTH, }; + +/** + * enum nl80211_sar_type - type of SAR specs + * + * @NL80211_SAR_TYPE_POWER: power limitation specified in 0.25dBm unit + * + */ +enum nl80211_sar_type { + NL80211_SAR_TYPE_POWER, + + /* add new type here */ + + /* Keep last */ + NUM_NL80211_SAR_TYPE, +}; + +/** + * enum nl80211_sar_attrs - Attributes for SAR spec + * + * @NL80211_SAR_ATTR_TYPE: the SAR type as defined in &enum nl80211_sar_type. + * + * @NL80211_SAR_ATTR_SPECS: Nested array of SAR power + * limit specifications. Each specification contains a set + * of %nl80211_sar_specs_attrs. + * + * For SET operation, it contains array of %NL80211_SAR_ATTR_SPECS_POWER + * and %NL80211_SAR_ATTR_SPECS_RANGE_INDEX. + * + * For sar_capa dump, it contains array of + * %NL80211_SAR_ATTR_SPECS_START_FREQ + * and %NL80211_SAR_ATTR_SPECS_END_FREQ. + * + * @__NL80211_SAR_ATTR_LAST: Internal + * @NL80211_SAR_ATTR_MAX: highest sar attribute + * + * These attributes are used with %NL80211_CMD_SET_SAR_SPEC + */ +enum nl80211_sar_attrs { + __NL80211_SAR_ATTR_INVALID, + + NL80211_SAR_ATTR_TYPE, + NL80211_SAR_ATTR_SPECS, + + __NL80211_SAR_ATTR_LAST, + NL80211_SAR_ATTR_MAX = __NL80211_SAR_ATTR_LAST - 1, +}; + +/** + * enum nl80211_sar_specs_attrs - Attributes for SAR power limit specs + * + * @NL80211_SAR_ATTR_SPECS_POWER: Required (s32)value to specify the actual + * power limit value in units of 0.25 dBm if type is + * NL80211_SAR_TYPE_POWER. (i.e., a value of 44 represents 11 dBm). + * 0 means userspace doesn't have SAR limitation on this associated range. + * + * @NL80211_SAR_ATTR_SPECS_RANGE_INDEX: Required (u32) value to specify the + * index of exported freq range table and the associated power limitation + * is applied to this range. + * + * Userspace isn't required to set all the ranges advertised by WLAN driver, + * and userspace can skip some certain ranges. These skipped ranges don't + * have SAR limitations, and they are same as setting the + * %NL80211_SAR_ATTR_SPECS_POWER to any unreasonable high value because any + * value higher than regulatory allowed value just means SAR power + * limitation is removed, but it's required to set at least one range. + * It's not allowed to set duplicated range in one SET operation. + * + * Every SET operation overwrites previous SET operation. + * + * @NL80211_SAR_ATTR_SPECS_START_FREQ: Required (u32) value to specify the start + * frequency of this range edge when registering SAR capability to wiphy. + * It's not a channel center frequency. The unit is kHz. + * + * @NL80211_SAR_ATTR_SPECS_END_FREQ: Required (u32) value to specify the end + * frequency of this range edge when registering SAR capability to wiphy. + * It's not a channel center frequency. The unit is kHz. + * + * @__NL80211_SAR_ATTR_SPECS_LAST: Internal + * @NL80211_SAR_ATTR_SPECS_MAX: highest sar specs attribute + */ +enum nl80211_sar_specs_attrs { + __NL80211_SAR_ATTR_SPECS_INVALID, + + NL80211_SAR_ATTR_SPECS_POWER, + NL80211_SAR_ATTR_SPECS_RANGE_INDEX, + NL80211_SAR_ATTR_SPECS_START_FREQ, + NL80211_SAR_ATTR_SPECS_END_FREQ, + + __NL80211_SAR_ATTR_SPECS_LAST, + NL80211_SAR_ATTR_SPECS_MAX = __NL80211_SAR_ATTR_SPECS_LAST - 1, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 390e6e0f23ac..7db6079fab04 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -399,6 +399,18 @@ nl80211_unsol_bcast_probe_resp_policy[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX + .len = IEEE80211_MAX_DATA_LEN } }; +static const struct nla_policy +sar_specs_policy[NL80211_SAR_ATTR_SPECS_MAX + 1] = { + [NL80211_SAR_ATTR_SPECS_POWER] = { .type = NLA_S32 }, + [NL80211_SAR_ATTR_SPECS_RANGE_INDEX] = {.type = NLA_U32 }, +}; + +static const struct nla_policy +sar_policy[NL80211_SAR_ATTR_MAX + 1] = { + [NL80211_SAR_ATTR_TYPE] = NLA_POLICY_MAX(NLA_U32, NUM_NL80211_SAR_TYPE), + [NL80211_SAR_ATTR_SPECS] = NLA_POLICY_NESTED_ARRAY(sar_specs_policy), +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -719,6 +731,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NLA_POLICY_RANGE(NLA_U8, NL80211_SAE_PWE_HUNT_AND_PECK, NL80211_SAE_PWE_BOTH), [NL80211_ATTR_RECONNECT_REQUESTED] = { .type = NLA_REJECT }, + [NL80211_ATTR_SAR_SPEC] = NLA_POLICY_NESTED(sar_policy), }; /* policy for the key attributes */ @@ -2095,6 +2108,56 @@ fail: return -ENOBUFS; } +static int +nl80211_put_sar_specs(struct cfg80211_registered_device *rdev, + struct sk_buff *msg) +{ + struct nlattr *sar_capa, *specs, *sub_freq_range; + u8 num_freq_ranges; + int i; + + if (!rdev->wiphy.sar_capa) + return 0; + + num_freq_ranges = rdev->wiphy.sar_capa->num_freq_ranges; + + sar_capa = nla_nest_start(msg, NL80211_ATTR_SAR_SPEC); + if (!sar_capa) + return -ENOSPC; + + if (nla_put_u32(msg, NL80211_SAR_ATTR_TYPE, rdev->wiphy.sar_capa->type)) + goto fail; + + specs = nla_nest_start(msg, NL80211_SAR_ATTR_SPECS); + if (!specs) + goto fail; + + /* report supported freq_ranges */ + for (i = 0; i < num_freq_ranges; i++) { + sub_freq_range = nla_nest_start(msg, i + 1); + if (!sub_freq_range) + goto fail; + + if (nla_put_u32(msg, NL80211_SAR_ATTR_SPECS_START_FREQ, + rdev->wiphy.sar_capa->freq_ranges[i].start_freq)) + goto fail; + + if (nla_put_u32(msg, NL80211_SAR_ATTR_SPECS_END_FREQ, + rdev->wiphy.sar_capa->freq_ranges[i].end_freq)) + goto fail; + + nla_nest_end(msg, sub_freq_range); + } + + nla_nest_end(msg, specs); + nla_nest_end(msg, sar_capa); + + return 0; +fail: + nla_nest_cancel(msg, sar_capa); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2344,6 +2407,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, CMD(set_multicast_to_unicast, SET_MULTICAST_TO_UNICAST); CMD(update_connect_params, UPDATE_CONNECT_PARAMS); CMD(update_ft_ies, UPDATE_FT_IES); + if (rdev->wiphy.sar_capa) + CMD(set_sar_specs, SET_SAR_SPECS); } #undef CMD @@ -2669,6 +2734,11 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_put_tid_config_support(rdev, msg)) goto nla_put_failure; + state->split_start++; + break; + case 16: + if (nl80211_put_sar_specs(rdev, msg)) + goto nla_put_failure; /* done */ state->split_start = 0; @@ -14668,6 +14738,111 @@ static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, } } +static int nl80211_set_sar_sub_specs(struct cfg80211_registered_device *rdev, + struct cfg80211_sar_specs *sar_specs, + struct nlattr *spec[], int index) +{ + u32 range_index, i; + + if (!sar_specs || !spec) + return -EINVAL; + + if (!spec[NL80211_SAR_ATTR_SPECS_POWER] || + !spec[NL80211_SAR_ATTR_SPECS_RANGE_INDEX]) + return -EINVAL; + + range_index = nla_get_u32(spec[NL80211_SAR_ATTR_SPECS_RANGE_INDEX]); + + /* check if range_index exceeds num_freq_ranges */ + if (range_index >= rdev->wiphy.sar_capa->num_freq_ranges) + return -EINVAL; + + /* check if range_index duplicates */ + for (i = 0; i < index; i++) { + if (sar_specs->sub_specs[i].freq_range_index == range_index) + return -EINVAL; + } + + sar_specs->sub_specs[index].power = + nla_get_s32(spec[NL80211_SAR_ATTR_SPECS_POWER]); + + sar_specs->sub_specs[index].freq_range_index = range_index; + + return 0; +} + +static int nl80211_set_sar_specs(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct nlattr *spec[NL80211_SAR_ATTR_SPECS_MAX + 1]; + struct nlattr *tb[NL80211_SAR_ATTR_MAX + 1]; + struct cfg80211_sar_specs *sar_spec; + enum nl80211_sar_type type; + struct nlattr *spec_list; + u32 specs; + int rem, err; + + if (!rdev->wiphy.sar_capa || !rdev->ops->set_sar_specs) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_SAR_SPEC]) + return -EINVAL; + + nla_parse_nested(tb, NL80211_SAR_ATTR_MAX, + info->attrs[NL80211_ATTR_SAR_SPEC], + NULL, NULL); + + if (!tb[NL80211_SAR_ATTR_TYPE] || !tb[NL80211_SAR_ATTR_SPECS]) + return -EINVAL; + + type = nla_get_u32(tb[NL80211_SAR_ATTR_TYPE]); + if (type != rdev->wiphy.sar_capa->type) + return -EINVAL; + + specs = 0; + nla_for_each_nested(spec_list, tb[NL80211_SAR_ATTR_SPECS], rem) + specs++; + + if (specs > rdev->wiphy.sar_capa->num_freq_ranges) + return -EINVAL; + + sar_spec = kzalloc(sizeof(*sar_spec) + + specs * sizeof(struct cfg80211_sar_sub_specs), + GFP_KERNEL); + if (!sar_spec) + return -ENOMEM; + + sar_spec->type = type; + specs = 0; + nla_for_each_nested(spec_list, tb[NL80211_SAR_ATTR_SPECS], rem) { + nla_parse_nested(spec, NL80211_SAR_ATTR_SPECS_MAX, + spec_list, NULL, NULL); + + switch (type) { + case NL80211_SAR_TYPE_POWER: + if (nl80211_set_sar_sub_specs(rdev, sar_spec, + spec, specs)) { + err = -EINVAL; + goto error; + } + break; + default: + err = -EINVAL; + goto error; + } + specs++; + } + + sar_spec->num_sub_specs = specs; + + rdev->cur_cmd_info = info; + err = rdev_set_sar_specs(rdev, sar_spec); + rdev->cur_cmd_info = NULL; +error: + kfree(sar_spec); + return err; +} + static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_WIPHY, @@ -15521,6 +15696,14 @@ static const struct genl_small_ops nl80211_small_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_SAR_SPECS, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = nl80211_set_sar_specs, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WIPHY | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 5e2f349c92a8..8b1358d04ca2 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1346,4 +1346,16 @@ static inline int rdev_reset_tid_config(struct cfg80211_registered_device *rdev, return ret; } +static inline int rdev_set_sar_specs(struct cfg80211_registered_device *rdev, + struct cfg80211_sar_specs *sar) +{ + int ret; + + trace_rdev_set_sar_specs(&rdev->wiphy, sar); + ret = rdev->ops->set_sar_specs(&rdev->wiphy, sar); + trace_rdev_return_int(&rdev->wiphy, ret); + + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/trace.h b/net/wireless/trace.h index d75cd23aea02..76b777d5903f 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3546,6 +3546,25 @@ TRACE_EVENT(rdev_reset_tid_config, TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT ", tids: 0x%x", WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->tids) ); + +TRACE_EVENT(rdev_set_sar_specs, + TP_PROTO(struct wiphy *wiphy, struct cfg80211_sar_specs *sar), + TP_ARGS(wiphy, sar), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(u16, type) + __field(u16, num) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->type = sar->type; + __entry->num = sar->num_sub_specs; + + ), + TP_printk(WIPHY_PR_FMT ", Set type:%d, num_specs:%d", + WIPHY_PR_ARG, __entry->type, __entry->num) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH -- cgit v1.3-15-g9ac1 From 48b0ae046ee96eac999839f6d26c624b8c93ed66 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 7 Dec 2020 17:37:14 +0100 Subject: netfilter: nftables: netlink support for several set element expressions This patch adds three new netlink attributes to encapsulate a list of expressions per set elements: - NFTA_SET_EXPRESSIONS: this attribute provides the set definition in terms of expressions. New set elements get attached the list of expressions that is specified by this new netlink attribute. - NFTA_SET_ELEM_EXPRESSIONS: this attribute allows users to restore (or initialize) the stateful information of set elements when adding an element to the set. - NFTA_DYNSET_EXPRESSIONS: this attribute specifies the list of expressions that the set element gets when it is inserted from the packet path. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 6 +++ net/netfilter/nf_tables_api.c | 93 ++++++++++++++++++++++++++++++-- net/netfilter/nft_dynset.c | 56 +++++++++++++++++-- 3 files changed, 149 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 98272cb5f617..28b6ee53305f 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -361,6 +361,7 @@ enum nft_set_field_attributes { * @NFTA_SET_OBJ_TYPE: stateful object type (NLA_U32: NFT_OBJECT_*) * @NFTA_SET_HANDLE: set handle (NLA_U64) * @NFTA_SET_EXPR: set expression (NLA_NESTED: nft_expr_attributes) + * @NFTA_SET_EXPRESSIONS: list of expressions (NLA_NESTED: nft_list_attributes) */ enum nft_set_attributes { NFTA_SET_UNSPEC, @@ -381,6 +382,7 @@ enum nft_set_attributes { NFTA_SET_OBJ_TYPE, NFTA_SET_HANDLE, NFTA_SET_EXPR, + NFTA_SET_EXPRESSIONS, __NFTA_SET_MAX }; #define NFTA_SET_MAX (__NFTA_SET_MAX - 1) @@ -406,6 +408,7 @@ enum nft_set_elem_flags { * @NFTA_SET_ELEM_EXPR: expression (NLA_NESTED: nft_expr_attributes) * @NFTA_SET_ELEM_OBJREF: stateful object reference (NLA_STRING) * @NFTA_SET_ELEM_KEY_END: closing key value (NLA_NESTED: nft_data) + * @NFTA_SET_ELEM_EXPRESSIONS: list of expressions (NLA_NESTED: nft_list_attributes) */ enum nft_set_elem_attributes { NFTA_SET_ELEM_UNSPEC, @@ -419,6 +422,7 @@ enum nft_set_elem_attributes { NFTA_SET_ELEM_PAD, NFTA_SET_ELEM_OBJREF, NFTA_SET_ELEM_KEY_END, + NFTA_SET_ELEM_EXPRESSIONS, __NFTA_SET_ELEM_MAX }; #define NFTA_SET_ELEM_MAX (__NFTA_SET_ELEM_MAX - 1) @@ -715,6 +719,7 @@ enum nft_dynset_flags { * @NFTA_DYNSET_TIMEOUT: timeout value for the new element (NLA_U64) * @NFTA_DYNSET_EXPR: expression (NLA_NESTED: nft_expr_attributes) * @NFTA_DYNSET_FLAGS: flags (NLA_U32) + * @NFTA_DYNSET_EXPRESSIONS: list of expressions (NLA_NESTED: nft_list_attributes) */ enum nft_dynset_attributes { NFTA_DYNSET_UNSPEC, @@ -727,6 +732,7 @@ enum nft_dynset_attributes { NFTA_DYNSET_EXPR, NFTA_DYNSET_PAD, NFTA_DYNSET_FLAGS, + NFTA_DYNSET_EXPRESSIONS, __NFTA_DYNSET_MAX, }; #define NFTA_DYNSET_MAX (__NFTA_DYNSET_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a3d5014dd246..243e3c2c7629 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3566,6 +3566,7 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_SET_HANDLE] = { .type = NLA_U64 }, [NFTA_SET_EXPR] = { .type = NLA_NESTED }, + [NFTA_SET_EXPRESSIONS] = { .type = NLA_NESTED }, }; static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { @@ -3773,6 +3774,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, u32 portid = ctx->portid; struct nlattr *nest; u32 seq = ctx->seq; + int i; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), @@ -3847,6 +3849,17 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; nla_nest_end(skb, nest); + } else if (set->num_exprs > 1) { + nest = nla_nest_start_noflag(skb, NFTA_SET_EXPRESSIONS); + if (nest == NULL) + goto nla_put_failure; + + for (i = 0; i < set->num_exprs; i++) { + if (nft_expr_dump(skb, NFTA_LIST_ELEM, + set->exprs[i]) < 0) + goto nla_put_failure; + } + nla_nest_end(skb, nest); } nlmsg_end(skb, nlh); @@ -4215,7 +4228,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, return err; } - if (nla[NFTA_SET_EXPR]) + if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS]) desc.expr = true; table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask); @@ -4281,6 +4294,29 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, } set->exprs[0] = expr; set->num_exprs++; + } else if (nla[NFTA_SET_EXPRESSIONS]) { + struct nft_expr *expr; + struct nlattr *tmp; + int left; + + i = 0; + nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { + if (i == NFT_SET_EXPR_MAX) { + err = -E2BIG; + goto err_set_init; + } + if (nla_type(tmp) != NFTA_LIST_ELEM) { + err = -EINVAL; + goto err_set_init; + } + expr = nft_set_elem_expr_alloc(&ctx, set, tmp); + if (IS_ERR(expr)) { + err = PTR_ERR(expr); + goto err_set_init; + } + set->exprs[i++] = expr; + set->num_exprs++; + } } udata = NULL; @@ -4540,6 +4576,7 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = { [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING, .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_KEY_END] = { .type = NLA_NESTED }, + [NFTA_SET_ELEM_EXPRESSIONS] = { .type = NLA_NESTED }, }; static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = { @@ -4580,6 +4617,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, struct nft_set_elem_expr *elem_expr; u32 size, num_exprs = 0; struct nft_expr *expr; + struct nlattr *nest; elem_expr = nft_set_ext_expr(ext); nft_setelem_expr_foreach(expr, elem_expr, size) @@ -4591,9 +4629,22 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, return -1; return 0; - } + } else if (num_exprs > 1) { + nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_EXPRESSIONS); + if (nest == NULL) + goto nla_put_failure; + nft_setelem_expr_foreach(expr, elem_expr, size) { + expr = nft_setelem_expr_at(elem_expr, size); + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } return 0; + +nla_put_failure: + return -1; } static int nf_tables_fill_setelem(struct sk_buff *skb, @@ -5268,7 +5319,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, nla[NFTA_SET_ELEM_TIMEOUT] || nla[NFTA_SET_ELEM_EXPIRATION] || nla[NFTA_SET_ELEM_USERDATA] || - nla[NFTA_SET_ELEM_EXPR])) + nla[NFTA_SET_ELEM_EXPR] || + nla[NFTA_SET_ELEM_EXPRESSIONS])) return -EINVAL; timeout = 0; @@ -5310,6 +5362,41 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EOPNOTSUPP; goto err_set_elem_expr; } + } else if (nla[NFTA_SET_ELEM_EXPRESSIONS]) { + struct nft_expr *expr; + struct nlattr *tmp; + int left; + + if (set->num_exprs == 0) + return -EOPNOTSUPP; + + i = 0; + nla_for_each_nested(tmp, nla[NFTA_SET_ELEM_EXPRESSIONS], left) { + if (i == set->num_exprs) { + err = -E2BIG; + goto err_set_elem_expr; + } + if (nla_type(tmp) != NFTA_LIST_ELEM) { + err = -EINVAL; + goto err_set_elem_expr; + } + expr = nft_set_elem_expr_alloc(ctx, set, tmp); + if (IS_ERR(expr)) { + err = PTR_ERR(expr); + goto err_set_elem_expr; + } + expr_array[i] = expr; + + if (expr->ops != set->exprs[i]->ops) { + err = -EOPNOTSUPP; + goto err_set_elem_expr; + } + i++; + } + if (set->num_exprs != i) { + err = -EOPNOTSUPP; + goto err_set_elem_expr; + } } else if (set->num_exprs > 0) { err = nft_set_elem_expr_clone(ctx, set, expr_array); if (err < 0) diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index d9e609b2e5d4..13c426d5dcf9 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -153,6 +153,7 @@ static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = { [NFTA_DYNSET_TIMEOUT] = { .type = NLA_U64 }, [NFTA_DYNSET_EXPR] = { .type = NLA_NESTED }, [NFTA_DYNSET_FLAGS] = { .type = NLA_U32 }, + [NFTA_DYNSET_EXPRESSIONS] = { .type = NLA_NESTED }, }; static int nft_dynset_init(const struct nft_ctx *ctx, @@ -232,12 +233,13 @@ static int nft_dynset_init(const struct nft_ctx *ctx, } else if (set->flags & NFT_SET_MAP) return -EINVAL; + if ((tb[NFTA_DYNSET_EXPR] || tb[NFTA_DYNSET_EXPRESSIONS]) && + !(set->flags & NFT_SET_EVAL)) + return -EINVAL; + if (tb[NFTA_DYNSET_EXPR]) { struct nft_expr *dynset_expr; - if (!(set->flags & NFT_SET_EVAL)) - return -EINVAL; - dynset_expr = nft_dynset_expr_alloc(ctx, set, tb[NFTA_DYNSET_EXPR], 0); if (IS_ERR(dynset_expr)) @@ -252,6 +254,40 @@ static int nft_dynset_init(const struct nft_ctx *ctx, err = -EOPNOTSUPP; goto err_expr_free; } + } else if (tb[NFTA_DYNSET_EXPRESSIONS]) { + struct nft_expr *dynset_expr; + struct nlattr *tmp; + int left; + + i = 0; + nla_for_each_nested(tmp, tb[NFTA_DYNSET_EXPRESSIONS], left) { + if (i == NFT_SET_EXPR_MAX) { + err = -E2BIG; + goto err_expr_free; + } + if (nla_type(tmp) != NFTA_LIST_ELEM) { + err = -EINVAL; + goto err_expr_free; + } + dynset_expr = nft_dynset_expr_alloc(ctx, set, tmp, i); + if (IS_ERR(dynset_expr)) { + err = PTR_ERR(dynset_expr); + goto err_expr_free; + } + priv->expr_array[i] = dynset_expr; + priv->num_exprs++; + + if (set->num_exprs && + dynset_expr->ops != set->exprs[i]->ops) { + err = -EOPNOTSUPP; + goto err_expr_free; + } + i++; + } + if (set->num_exprs && set->num_exprs != i) { + err = -EOPNOTSUPP; + goto err_expr_free; + } } nft_set_ext_prepare(&priv->tmpl); @@ -318,6 +354,7 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_dynset *priv = nft_expr_priv(expr); u32 flags = priv->invert ? NFT_DYNSET_F_INV : 0; + int i; if (nft_dump_register(skb, NFTA_DYNSET_SREG_KEY, priv->sreg_key)) goto nla_put_failure; @@ -335,6 +372,19 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) if (priv->num_exprs == 1) { if (nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr_array[0])) goto nla_put_failure; + } else if (priv->num_exprs > 1) { + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, NFTA_DYNSET_EXPRESSIONS); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < priv->num_exprs; i++) { + if (nft_expr_dump(skb, NFTA_LIST_ELEM, + priv->expr_array[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); } if (nla_put_be32(skb, NFTA_DYNSET_FLAGS, htonl(flags))) goto nla_put_failure; -- cgit v1.3-15-g9ac1 From dc8eeef73b63ed8988224ba6b5ed19a615163a7f Mon Sep 17 00:00:00 2001 From: Andra Paraschiv Date: Mon, 14 Dec 2020 18:11:18 +0200 Subject: vm_sockets: Add flags field in the vsock address data structure vsock enables communication between virtual machines and the host they are running on. With the multi transport support (guest->host and host->guest), nested VMs can also use vsock channels for communication. In addition to this, by default, all the vsock packets are forwarded to the host, if no host->guest transport is loaded. This behavior can be implicitly used for enabling vsock communication between sibling VMs. Add a flags field in the vsock address data structure that can be used to explicitly mark the vsock connection as being targeted for a certain type of communication. This way, can distinguish between different use cases such as nested VMs and sibling VMs. This field can be set when initializing the vsock address variable used for the connect() call. Changelog v3 -> v4 * Update the size of "svm_flags" field to be 1 byte instead of 2 bytes. v2 -> v3 * Add "svm_flags" as a new field, not reusing "svm_reserved1". v1 -> v2 * Update the field name to "svm_flags". * Split the current patch in 2 patches. Signed-off-by: Andra Paraschiv Reviewed-by: Stefano Garzarella Signed-off-by: Jakub Kicinski --- include/uapi/linux/vm_sockets.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index fd0ed7221645..c2eac3d0a9f0 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -18,6 +18,7 @@ #define _UAPI_VM_SOCKETS_H #include +#include /* Option name for STREAM socket buffer size. Use as the option name in * setsockopt(3) or getsockopt(3) to set or get an unsigned long long that @@ -148,10 +149,13 @@ struct sockaddr_vm { unsigned short svm_reserved1; unsigned int svm_port; unsigned int svm_cid; + __u8 svm_flags; unsigned char svm_zero[sizeof(struct sockaddr) - sizeof(sa_family_t) - sizeof(unsigned short) - - sizeof(unsigned int) - sizeof(unsigned int)]; + sizeof(unsigned int) - + sizeof(unsigned int) - + sizeof(__u8)]; }; #define IOCTL_VM_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9) -- cgit v1.3-15-g9ac1 From caaf95e0f23f9ed240b02251aab0f6fdb652b33d Mon Sep 17 00:00:00 2001 From: Andra Paraschiv Date: Mon, 14 Dec 2020 18:11:19 +0200 Subject: vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag Add VMADDR_FLAG_TO_HOST vsock flag that is used to setup a vsock connection where all the packets are forwarded to the host. Then, using this type of vsock channel, vsock communication between sibling VMs can be built on top of it. Changelog v3 -> v4 * Update the "VMADDR_FLAG_TO_HOST" value, as the size of the field has been updated to 1 byte. v2 -> v3 * Update comments to mention when the flag is set in the connect and listen paths. v1 -> v2 * New patch in v2, it was split from the first patch in the series. * Remove the default value for the vsock flags field. * Update the naming for the vsock flag to "VMADDR_FLAG_TO_HOST". Signed-off-by: Andra Paraschiv Reviewed-by: Stefano Garzarella Signed-off-by: Jakub Kicinski --- include/uapi/linux/vm_sockets.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index c2eac3d0a9f0..46918a1852d7 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -115,6 +115,26 @@ #define VMADDR_CID_HOST 2 +/* The current default use case for the vsock channel is the following: + * local vsock communication between guest and host and nested VMs setup. + * In addition to this, implicitly, the vsock packets are forwarded to the host + * if no host->guest vsock transport is set. + * + * Set this flag value in the sockaddr_vm corresponding field if the vsock + * packets need to be always forwarded to the host. Using this behavior, + * vsock communication between sibling VMs can be setup. + * + * This way can explicitly distinguish between vsock channels created for + * different use cases, such as nested VMs (or local communication between + * guest and host) and sibling VMs. + * + * The flag can be set in the connect logic in the user space application flow. + * In the listen logic (from kernel space) the flag is set on the remote peer + * address. This happens for an incoming connection when it is routed from the + * host and comes from the guest (local CID and remote CID > VMADDR_CID_HOST). + */ +#define VMADDR_FLAG_TO_HOST 0x01 + /* Invalid vSockets version. */ #define VM_SOCKETS_INVALID_VERSION -1U -- cgit v1.3-15-g9ac1