@@ -3,14 +3,32 @@
*
* Unified network-device I/O interface for Xen guest OSes.
*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
* Copyright (c) 2003-2004, Keir Fraser
*/
#ifndef __XEN_PUBLIC_IO_NETIF_H__
#define __XEN_PUBLIC_IO_NETIF_H__
-#include <xen/interface/io/ring.h>
-#include <xen/interface/grant_table.h>
+#include "ring.h"
+#include "../grant_table.h"
/*
* Older implementation of Xen network frontend / backend has an
@@ -38,10 +56,10 @@
* that it cannot safely queue packets (as it may not be kicked to send them).
*/
- /*
+/*
* "feature-split-event-channels" is introduced to separate guest TX
- * and RX notificaion. Backend either doesn't support this feature or
- * advertise it via xenstore as 0 (disabled) or 1 (enabled).
+ * and RX notification. Backend either doesn't support this feature or
+ * advertises it via xenstore as 0 (disabled) or 1 (enabled).
*
* To make use of this feature, frontend should allocate two event
* channels for TX and RX, advertise them to backend as
@@ -118,151 +136,709 @@
*/
/*
- * This is the 'wire' format for packets:
- * Request 1: xen_netif_tx_request -- XEN_NETTXF_* (any flags)
- * [Request 2: xen_netif_extra_info] (only if request 1 has XEN_NETTXF_extra_info)
- * [Request 3: xen_netif_extra_info] (only if request 2 has XEN_NETIF_EXTRA_MORE)
- * Request 4: xen_netif_tx_request -- XEN_NETTXF_more_data
- * Request 5: xen_netif_tx_request -- XEN_NETTXF_more_data
+ * "feature-multicast-control" and "feature-dynamic-multicast-control"
+ * advertise the capability to filter ethernet multicast packets in the
+ * backend. If the frontend wishes to take advantage of this feature then
+ * it may set "request-multicast-control". If the backend only advertises
+ * "feature-multicast-control" then "request-multicast-control" must be set
+ * before the frontend moves into the connected state. The backend will
+ * sample the value on this state transition and any subsequent change in
+ * value will have no effect. However, if the backend also advertises
+ * "feature-dynamic-multicast-control" then "request-multicast-control"
+ * may be set by the frontend at any time. In this case, the backend will
+ * watch the value and re-sample on watch events.
+ *
+ * If the sampled value of "request-multicast-control" is set then the
+ * backend transmit side should no longer flood multicast packets to the
+ * frontend, it should instead drop any multicast packet that does not
+ * match in a filter list.
+ * The list is amended by the frontend by sending dummy transmit requests
+ * containing XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL} extra-info fragments as
+ * specified below.
+ * Note that the filter list may be amended even if the sampled value of
+ * "request-multicast-control" is not set, however the filter should only
+ * be applied if it is set.
+ */
+
+/*
+ * Control ring
+ * ============
+ *
+ * Some features, such as toeplitz hashing (detailed below), require a
+ * significant amount of out-of-band data to be passed from frontend to
+ * backend. Use of xenstore is not suitable for large quantities of data
+ * because of quota limitations and so a dedicated 'control ring' is used.
+ * The ability of the backend to use a control ring is advertised by
+ * setting:
+ *
+ * /local/domain/X/backend/<domid>/<vif>/feature-ctrl-ring = "1"
+ *
+ * The frontend provides a control ring to the backend by setting:
+ *
+ * /local/domain/<domid>/device/vif/<vif>/ctrl-ring-ref = <gref>
+ * /local/domain/<domid>/device/vif/<vif>/event-channel-ctrl = <port>
+ *
+ * where <gref> is the grant reference of the shared page used to
+ * implement the control ring and <port> is an event channel to be used
+ * as a mailbox interrupt. These keys must be set before the frontend
+ * moves into the connected state.
+ *
+ * The control ring uses a fixed request/response message size and is
+ * balanced (i.e. one request to one response), so operationally it is much
+ * the same as a transmit or receive ring.
+ * Note that there is no requirement that responses are issued in the same
+ * order as requests.
+ */
+
+/*
+ * Toeplitz hash types
+ * ===================
+ *
+ * For the purposes of the definitions below, 'Packet[]' is an array of
+ * octets containing an IP packet without options, 'Array[X..Y]' means a
+ * sub-array of 'Array' containing bytes X thru Y inclusive, and '+' is
+ * used to indicate concatenation of arrays.
+ */
+
+/*
+ * A hash calculated over an IP version 4 header as follows:
+ *
+ * Buffer[0..8] = Packet[12..15] (source address) +
+ * Packet[16..19] (destination address)
+ *
+ * Result = ToeplitzHash(Buffer, 8)
+ */
+#define _XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV4 0
+#define XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV4 (1 << _XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV4)
+
+/*
+ * A hash calculated over an IP version 4 header and TCP header as
+ * follows:
+ *
+ * Buffer[0..12] = Packet[12..15] (source address) +
+ * Packet[16..19] (destination address) +
+ * Packet[20..21] (source port) +
+ * Packet[22..23] (destination port)
+ *
+ * Result = ToeplitzHash(Buffer, 12)
+ */
+#define _XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV4_TCP 1
+#define XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV4_TCP (1 << _XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV4_TCP)
+
+/*
+ * A hash calculated over an IP version 6 header as follows:
+ *
+ * Buffer[0..32] = Packet[8..23] (source address ) +
+ * Packet[24..39] (destination address)
+ *
+ * Result = ToeplitzHash(Buffer, 32)
+ */
+#define _XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV6 2
+#define XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV6 (1 << _XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV6)
+
+/*
+ * A hash calculated over an IP version 6 header and TCP header as
+ * follows:
+ *
+ * Buffer[0..36] = Packet[8..23] (source address) +
+ * Packet[24..39] (destination address) +
+ * Packet[40..41] (source port) +
+ * Packet[42..43] (destination port)
+ *
+ * Result = ToeplitzHash(Buffer, 36)
+ */
+#define _XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV6_TCP 3
+#define XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV6_TCP (1 << _XEN_NETIF_CTRL_TOEPLITZ_HASH_IPV6_TCP)
+
+/*
+ * Control requests (xen_netif_ctrl_request_t)
+ * =======================================
+ *
+ * All requests have the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | type | data[0] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | data[1] | data[2] |
+ * +-----+-----+-----+-----+-----------------------+
+ *
+ * id: the request identifier, echoed in response.
+ * type: the type of request (see below)
+ * data[]: any data associated with the request (determined by type)
+ */
+
+struct xen_netif_ctrl_request {
+ uint16_t id;
+ uint16_t type;
+
+#define XEN_NETIF_CTRL_TYPE_INVALID 0
+#define XEN_NETIF_CTRL_TYPE_GET_TOEPLITZ_FLAGS 1
+#define XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_FLAGS 2
+#define XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_KEY 3
+#define XEN_NETIF_CTRL_TYPE_GET_TOEPLITZ_MAPPING_ORDER 4
+#define XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_MAPPING_ORDER 5
+#define XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_MAPPING 6
+
+ uint32_t data[3];
+};
+typedef struct xen_netif_ctrl_request xen_netif_ctrl_request_t;
+
+/*
+ * Control responses (xen_netif_ctrl_response_t)
+ * =========================================
+ *
+ * All responses have the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | type | status |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | data |
+ * +-----+-----+-----+-----+
+ *
+ * id: the corresponding request identifier
+ * type: the type of the corresponding request
+ * status: the status of request processing
+ * data: any data associated with the response (determined by type and
+ * status)
+ */
+
+struct xen_netif_ctrl_response {
+ uint16_t id;
+ uint16_t type;
+ uint32_t status;
+
+#define XEN_NETIF_CTRL_STATUS_SUCCESS 0
+#define XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED 1
+#define XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER 2
+#define XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW 3
+
+ uint32_t data;
+};
+typedef struct xen_netif_ctrl_response xen_netif_ctrl_response_t;
+
+/*
+ * Control messages
+ * ================
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_TOEPLITZ_FLAGS
+ * ----------------------------------
+ *
+ * This is sent by the frontend to query the types of toeplitz
+ * hash supported by the backend.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_GET_TOEPLITZ_FLAGS
+ * data[0] = 0
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = supported hash types (if operation was successful)
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_FLAGS
+ * ----------------------------------
+ *
+ * This is sent by the frontend to set the types of toeplitz hash that
+ * the backend should calculate. (See above for hash type definitions).
+ * Note that the 'maximal' type of hash should always be chosen. For
+ * example, if the frontend sets both IPV4 and IPV4_TCP hash types then
+ * the latter hash type should be calculated for any TCP packet and the
+ * former only calculated for non-TCP packets.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_FLAGS
+ * data[0] = bitwise OR of XEN_NETIF_CTRL_TOEPLITZ_HASH_* values
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - One or more flag value
+ * is invalid or
+ * unsupported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: Setting data[0] to zero disables toeplitz hashing and the backend
+ * is free to choose how it steers packets to queues (which is the
+ * default behaviour).
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_KEY
+ * --------------------------------
+ *
+ * This is sent by the frontend to set the key of the toeplitz hash that
+ * the backend should calculate. The toeplitz algorithm is illustrated
+ * by the following pseudo-code:
+ *
+ * (Buffer[] and Key[] are treated as shift-registers where the MSB of
+ * Buffer/Key[0] is considered 'left-most' and the LSB of Buffer/Key[N-1]
+ * is the 'right-most').
+ *
+ * Value = 0
+ * For number of bits in Buffer[]
+ * If (left-most bit of Buffer[] is 1)
+ * Value ^= left-most 32 bits of Key[]
+ * Key[] << 1
+ * Buffer[] << 1
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_KEY
+ * data[0] = grant reference of page containing the key (assumed to
+ * start at beginning of grant)
+ * data[1] = size of key in octets
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Key size is invalid
+ * XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW - Key size is larger than
+ * the backend supports
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: Any key octets not specified are assumed to be zero (the key
+ * is assumed to be empty by default) and specifying a new key
+ * invalidates any previous key, hence specifying a key size of
+ * zero will clear the key (which ensures that the calculated hash
+ * will always be zero).
+ * The maximum size of key is backend specific, but is also limited
+ * by the single grant reference.
+ * The grant reference may be read-only and must remain valid until
+ * the response has been processed.
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_TOEPLITZ_MAPPING_ORDER
+ * ------------------------------------------
+ *
+ * This is sent by the frontend to query the maximum order of mapping
+ * table supported by the backend. The order is specified in terms of
+ * table entries i.e. the table may contain up to 2^order entries.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_GET_TOEPLITZ_MAPPING_ORDER
+ * data[0] = 0
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = maximum order of mapping table (if operation was successful)
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_MAPPING_ORDER
+ * ------------------------------------------
+ *
+ * This is sent by the frontend to set the actual order of the mapping
+ * table to be used by the backend. The order is specified in terms of
+ * table entries i.e. the table will contain to 2^order entries.
+ * Any previous table is invalidated by this message and any new table
+ * is assumed to be zero filled. The default order is zero and hence the
+ * default table contains a single entry mapping all hashes to queue-0.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_MAPPING_ORDER
+ * data[0] = order of mapping table
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Table order is invalid
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_MAPPING
+ * ------------------------------------
+ *
+ * This is sent by the frontend to set the content of the table mapping
+ * toeplitz hash value to queue number. The backend should calculate the
+ * hash from the packet header, use it as an index into the table (modulo
+ * the size of the table) and then steer the packet to the queue number
+ * found at that index.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_MAPPING
+ * data[0] = grant reference of page containing the mapping (sub-)table
+ * (assumed to start at beginning of grant)
+ * data[1] = size of (sub-)table in entries
+ * data[2] = offset, in entries, of sub-table within overall table
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Table size or content is
+ * invalid
+ * XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW - Table size is larger than
+ * the backend supports
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: The overall table has the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | mapping[0] | mapping[1] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | . |
+ * | . |
+ * | . |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | mapping[N-2] | mapping[N-1] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * where N == 2^order as specified by a
+ * XEN_NETIF_CTRL_TYPE_SET_TOEPLITZ_MAPPING_ORDER message and each
+ * mapping must specifies a queue between 0 and
+ * "multi-queue-num-queues" (see above).
+ * The backend may support a mapping table larger than can be
+ * mapped by a single grant reference. Thus sub-tables within a
+ * larger table can be individually set by sending multiple messages
+ * with differing offset values. Specifying a new sub-table does not
+ * invalidate any table data outside that range.
+ * The grant reference may be read-only and must remain valid until
+ * the response has been processed.
+ */
+
+DEFINE_RING_TYPES(xen_netif_ctrl, struct xen_netif_ctrl_request,
+ struct xen_netif_ctrl_response);
+
+/*
+ * Guest transmit
+ * ==============
+ *
+ * This is the 'wire' format for transmit (frontend -> backend) packets:
+ *
+ * Fragment 1: xen_netif_tx_request_t - flags = XEN_NETTXF_*
+ * size = total packet size
+ * [Extra 1: xen_netif_extra_info_t] - (only if fragment 1 flags include
+ * XEN_NETTXF_extra_info)
+ * ...
+ * [Extra N: xen_netif_extra_info_t] - (only if extra N-1 flags include
+ * XEN_NETIF_EXTRA_MORE)
+ * ...
+ * Fragment N: xen_netif_tx_request_t - (only if fragment N-1 flags include
+ * XEN_NETTXF_more_data - flags on preceding
+ * extras are not relevent here)
+ * flags = 0
+ * size = fragment size
+ *
+ * NOTE:
+ *
+ * This format slightly is different from that used for receive
+ * (backend -> frontend) packets. Specifically, in a multi-fragment
+ * packet the actual size of fragment 1 can only be determined by
+ * subtracting the sizes of fragments 2..N from the total packet size.
+ *
+ * Ring slot size is 12 octets, however not all request/response
+ * structs use the full size.
+ *
+ * tx request data (xen_netif_tx_request_t)
+ * ------------------------------------
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | grant ref | offset | flags |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | size |
+ * +-----+-----+-----+-----+
+ *
+ * grant ref: Reference to buffer page.
+ * offset: Offset within buffer page.
+ * flags: XEN_NETTXF_*.
+ * id: request identifier, echoed in response.
+ * size: packet size in bytes.
+ *
+ * tx response (xen_netif_tx_response_t)
+ * ---------------------------------
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | status | unused |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | unused |
+ * +-----+-----+-----+-----+
+ *
+ * id: reflects id in transmit request
+ * status: XEN_NETIF_RSP_*
+ *
+ * Guest receive
+ * =============
+ *
+ * This is the 'wire' format for receive (backend -> frontend) packets:
+ *
+ * Fragment 1: xen_netif_rx_request_t - flags = XEN_NETRXF_*
+ * size = fragment size
+ * [Extra 1: xen_netif_extra_info_t] - (only if fragment 1 flags include
+ * XEN_NETRXF_extra_info)
+ * ...
+ * [Extra N: xen_netif_extra_info_t] - (only if extra N-1 flags include
+ * XEN_NETIF_EXTRA_MORE)
* ...
- * Request N: xen_netif_tx_request -- 0
+ * Fragment N: xen_netif_rx_request_t - (only if fragment N-1 flags include
+ * XEN_NETRXF_more_data - flags on preceding
+ * extras are not relevent here)
+ * flags = 0
+ * size = fragment size
+ *
+ * NOTE:
+ *
+ * This format slightly is different from that used for transmit
+ * (frontend -> backend) packets. Specifically, in a multi-fragment
+ * packet the size of the packet can only be determined by summing the
+ * sizes of fragments 1..N.
+ *
+ * Ring slot size is 8 octets.
+ *
+ * rx request (xen_netif_rx_request_t)
+ * -------------------------------
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | pad | gref |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * id: request identifier, echoed in response.
+ * gref: reference to incoming granted frame.
+ *
+ * rx response (xen_netif_rx_response_t)
+ * ---------------------------------
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | offset | flags | status |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * id: reflects id in receive request
+ * offset: offset in page of start of received packet
+ * flags: XEN_NETRXF_*
+ * status: -ve: XEN_NETIF_RSP_*; +ve: Rx'ed pkt size.
+ *
+ * NOTE: Historically, to support GSO on the frontend receive side, Linux
+ * netfront does not make use of the rx response id (because, as
+ * described below, extra info structures overlay the id field).
+ * Instead it assumes that responses always appear in the same ring
+ * slot as their corresponding request. Thus, to maintain
+ * compatibilty, backends must make sure this is the case.
+ *
+ * Extra Info
+ * ==========
+ *
+ * Can be present if initial request or response has NET{T,R}XF_extra_info,
+ * or previous extra request has XEN_NETIF_EXTRA_MORE.
+ *
+ * The struct therefore needs to fit into either a tx or rx slot and
+ * is therefore limited to 8 octets.
+ *
+ * NOTE: Because extra info data overlays the usual request/response
+ * structures, there is no id information in the opposite direction.
+ * So, if an extra info overlays an rx response the frontend can
+ * assume that it is in the same ring slot as the request that was
+ * consumed to make the slot available, and the backend must ensure
+ * this assumption is true.
+ *
+ * extra info (xen_netif_extra_info_t)
+ * -------------------------------
+ *
+ * General format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags| type specific data |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | padding for tx |
+ * +-----+-----+-----+-----+
+ *
+ * type: XEN_NETIF_EXTRA_TYPE_*
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * padding for tx: present only in the tx case due to 8 octet limit
+ * from rx case. Not shown in type specific entries
+ * below.
+ *
+ * XEN_NETIF_EXTRA_TYPE_GSO:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags| size |type | pad | features |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * type: Must be XEN_NETIF_EXTRA_TYPE_GSO
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * size: Maximum payload size of each segment. For example,
+ * for TCP this is just the path MSS.
+ * type: XEN_NETIF_GSO_TYPE_*: This determines the protocol of
+ * the packet and any extra features required to segment the
+ * packet properly.
+ * features: EN_NETIF_GSO_FEAT_*: This specifies any extra GSO
+ * features required to process this packet, such as ECN
+ * support for TCPv4.
+ *
+ * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags| addr |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * type: Must be XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * addr: address to add/remove
+ *
+ * XEN_NETIF_EXTRA_TYPE_TOEPLITZ:
+ *
+ * A backend that supports teoplitz hashing is assumed to accept
+ * this type of extra info in transmit packets.
+ * A frontend that enables toeplitz hashing is assumed to accept
+ * this type of extra info in receive packets.
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags|htype| pad |LSB ---- value ---- MSB|
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * type: Must be XEN_NETIF_EXTRA_TYPE_TOEPLITZ
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * htype: Hash type (one of _XEN_NETIF_CTRL_TOEPLITZ_HASH_* - see above)
+ * value: Hash value
*/
/* Protocol checksum field is blank in the packet (hardware offload)? */
-#define _XEN_NETTXF_csum_blank (0)
-#define XEN_NETTXF_csum_blank (1U<<_XEN_NETTXF_csum_blank)
+#define _XEN_NETTXF_csum_blank (0)
+#define XEN_NETTXF_csum_blank (1U<<_XEN_NETTXF_csum_blank)
/* Packet data has been validated against protocol checksum. */
-#define _XEN_NETTXF_data_validated (1)
-#define XEN_NETTXF_data_validated (1U<<_XEN_NETTXF_data_validated)
+#define _XEN_NETTXF_data_validated (1)
+#define XEN_NETTXF_data_validated (1U<<_XEN_NETTXF_data_validated)
/* Packet continues in the next request descriptor. */
-#define _XEN_NETTXF_more_data (2)
-#define XEN_NETTXF_more_data (1U<<_XEN_NETTXF_more_data)
+#define _XEN_NETTXF_more_data (2)
+#define XEN_NETTXF_more_data (1U<<_XEN_NETTXF_more_data)
/* Packet to be followed by extra descriptor(s). */
-#define _XEN_NETTXF_extra_info (3)
-#define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info)
+#define _XEN_NETTXF_extra_info (3)
+#define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info)
#define XEN_NETIF_MAX_TX_SIZE 0xFFFF
struct xen_netif_tx_request {
- grant_ref_t gref; /* Reference to buffer page */
- uint16_t offset; /* Offset within buffer page */
- uint16_t flags; /* XEN_NETTXF_* */
- uint16_t id; /* Echoed in response message. */
- uint16_t size; /* Packet size in bytes. */
+ grant_ref_t gref;
+ uint16_t offset;
+ uint16_t flags;
+ uint16_t id;
+ uint16_t size;
};
+typedef struct xen_netif_tx_request xen_netif_tx_request_t;
/* Types of xen_netif_extra_info descriptors. */
-#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */
-#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */
-#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD (2) /* u.mcast */
-#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3) /* u.mcast */
-#define XEN_NETIF_EXTRA_TYPE_MAX (4)
+#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */
+#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */
+#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD (2) /* u.mcast */
+#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3) /* u.mcast */
+#define XEN_NETIF_EXTRA_TYPE_TOEPLITZ (4) /* u.toeplitz */
+#define XEN_NETIF_EXTRA_TYPE_MAX (5)
-/* xen_netif_extra_info flags. */
-#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
-#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
+/* xen_netif_extra_info_t flags. */
+#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
+#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
/* GSO types */
-#define XEN_NETIF_GSO_TYPE_NONE (0)
-#define XEN_NETIF_GSO_TYPE_TCPV4 (1)
-#define XEN_NETIF_GSO_TYPE_TCPV6 (2)
+#define XEN_NETIF_GSO_TYPE_NONE (0)
+#define XEN_NETIF_GSO_TYPE_TCPV4 (1)
+#define XEN_NETIF_GSO_TYPE_TCPV6 (2)
/*
- * This structure needs to fit within both netif_tx_request and
- * netif_rx_response for compatibility.
+ * This structure needs to fit within both xen_netif_tx_request_t and
+ * xen_netif_rx_response_t for compatibility.
*/
struct xen_netif_extra_info {
- uint8_t type; /* XEN_NETIF_EXTRA_TYPE_* */
- uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */
-
+ uint8_t type;
+ uint8_t flags;
union {
struct {
- /*
- * Maximum payload size of each segment. For
- * example, for TCP this is just the path MSS.
- */
uint16_t size;
-
- /*
- * GSO type. This determines the protocol of
- * the packet and any extra features required
- * to segment the packet properly.
- */
- uint8_t type; /* XEN_NETIF_GSO_TYPE_* */
-
- /* Future expansion. */
+ uint8_t type;
uint8_t pad;
-
- /*
- * GSO features. This specifies any extra GSO
- * features required to process this packet,
- * such as ECN support for TCPv4.
- */
- uint16_t features; /* XEN_NETIF_GSO_FEAT_* */
+ uint16_t features;
} gso;
-
struct {
- uint8_t addr[6]; /* Address to add/remove. */
+ uint8_t addr[6];
} mcast;
-
+ struct {
+ uint8_t type;
+ uint8_t pad;
+ uint8_t value[4];
+ } toeplitz;
uint16_t pad[3];
} u;
};
+typedef struct xen_netif_extra_info xen_netif_extra_info_t;
struct xen_netif_tx_response {
uint16_t id;
- int16_t status; /* XEN_NETIF_RSP_* */
+ int16_t status;
};
+typedef struct xen_netif_tx_response xen_netif_tx_response_t;
struct xen_netif_rx_request {
- uint16_t id; /* Echoed in response message. */
- grant_ref_t gref; /* Reference to incoming granted frame */
+ uint16_t id; /* Echoed in response message. */
+ uint16_t pad;
+ grant_ref_t gref;
};
+typedef struct xen_netif_rx_request xen_netif_rx_request_t;
/* Packet data has been validated against protocol checksum. */
-#define _XEN_NETRXF_data_validated (0)
-#define XEN_NETRXF_data_validated (1U<<_XEN_NETRXF_data_validated)
+#define _XEN_NETRXF_data_validated (0)
+#define XEN_NETRXF_data_validated (1U<<_XEN_NETRXF_data_validated)
/* Protocol checksum field is blank in the packet (hardware offload)? */
-#define _XEN_NETRXF_csum_blank (1)
-#define XEN_NETRXF_csum_blank (1U<<_XEN_NETRXF_csum_blank)
+#define _XEN_NETRXF_csum_blank (1)
+#define XEN_NETRXF_csum_blank (1U<<_XEN_NETRXF_csum_blank)
/* Packet continues in the next request descriptor. */
-#define _XEN_NETRXF_more_data (2)
-#define XEN_NETRXF_more_data (1U<<_XEN_NETRXF_more_data)
+#define _XEN_NETRXF_more_data (2)
+#define XEN_NETRXF_more_data (1U<<_XEN_NETRXF_more_data)
/* Packet to be followed by extra descriptor(s). */
-#define _XEN_NETRXF_extra_info (3)
-#define XEN_NETRXF_extra_info (1U<<_XEN_NETRXF_extra_info)
+#define _XEN_NETRXF_extra_info (3)
+#define XEN_NETRXF_extra_info (1U<<_XEN_NETRXF_extra_info)
-/* GSO Prefix descriptor. */
-#define _XEN_NETRXF_gso_prefix (4)
-#define XEN_NETRXF_gso_prefix (1U<<_XEN_NETRXF_gso_prefix)
+/* Packet has GSO prefix. Deprecated but included for compatibility */
+#define _XEN_NETRXF_gso_prefix (4)
+#define XEN_NETRXF_gso_prefix (1U<<_XEN_NETRXF_gso_prefix)
struct xen_netif_rx_response {
- uint16_t id;
- uint16_t offset; /* Offset in page of start of received packet */
- uint16_t flags; /* XEN_NETRXF_* */
- int16_t status; /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */
+ uint16_t id;
+ uint16_t offset;
+ uint16_t flags;
+ int16_t status;
};
+typedef struct xen_netif_rx_response xen_netif_rx_response_t;
/*
* Generate netif ring structures and types.
*/
-DEFINE_RING_TYPES(xen_netif_tx,
- struct xen_netif_tx_request,
+DEFINE_RING_TYPES(xen_netif_tx, struct xen_netif_tx_request,
struct xen_netif_tx_response);
-DEFINE_RING_TYPES(xen_netif_rx,
- struct xen_netif_rx_request,
+DEFINE_RING_TYPES(xen_netif_rx, struct xen_netif_rx_request,
struct xen_netif_rx_response);
-#define XEN_NETIF_RSP_DROPPED -2
-#define XEN_NETIF_RSP_ERROR -1
-#define XEN_NETIF_RSP_OKAY 0
-/* No response: used for auxiliary requests (e.g., xen_netif_extra_info). */
-#define XEN_NETIF_RSP_NULL 1
+#define XEN_NETIF_RSP_DROPPED -2
+#define XEN_NETIF_RSP_ERROR -1
+#define XEN_NETIF_RSP_OKAY 0
+/* No response: used for auxiliary requests (e.g., xen_netif_extra_info_t). */
+#define XEN_NETIF_RSP_NULL 1
#endif
The canonical netif header (in the Xen source repo) and the Linux variant have diverged significantly. Recently much documentation has been added to the canonical header and new definitions and types to support packet hash configuration. Subsequent patches in this series add support for packet hash configuration in xen-netback so this patch re-imports the canonical header in readiness. To maintain compatibility and some style consistency with the old Linux variant, the header was stripped of its emacs boilerplate, and post-processed and copied into place with the following commands: ed -s netif.h << EOF H ,s/NETTXF_/XEN_NETTXF_/g ,s/NETRXF_/XEN_NETRXF_/g ,s/NETIF_RSP/XEN_NETIF_RSP/g ,s/NETIF_CTRL/XEN_NETIF_CTRL/g ,s/netif_tx/xen_netif_tx/g ,s/netif_rx/xen_netif_rx/g ,s/netif_ctrl/xen_netif_ctrl/g ,s/netif_extra_info/xen_netif_extra_info/g $ w EOF indent --line-length 80 --linux-style netif.h \ -o include/xen/interface/io/netif.h Signed-off-by: Paul Durrant <paul.durrant@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Wei Liu <wei.liu2@citrix.com> --- include/xen/interface/io/netif.h | 758 ++++++++++++++++++++++++++++++++++----- 1 file changed, 667 insertions(+), 91 deletions(-)