[xen] Update to current Xen headersxen

Signed-off-by: Michael Brown <mcb30@ipxe.org>

1 files changed, 864 insertions, 78 deletions

diff --git a/src/include/xen/io/netif.h b/src/include/xen/io/netif.h
index ae12eab73..bec61ab3e 100644
--- a/src/include/xen/io/netif.h
+++ b/src/include/xen/io/netif.h
@@ -1,26 +1,9 @@
+/* SPDX-License-Identifier: MIT */
 /******************************************************************************
  * netif.h
  *
  * 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
  */
 
@@ -138,14 +121,839 @@ FILE_LICENCE ( MIT );
  */
 
 /*
- * This is the 'wire' format for packets:
- *  Request 1: netif_tx_request -- NETTXF_* (any flags)
- * [Request 2: netif_tx_extra]  (only if request 1 has NETTXF_extra_info)
- * [Request 3: netif_tx_extra]  (only if request 2 has XEN_NETIF_EXTRA_MORE)
- *  Request 4: netif_tx_request -- NETTXF_more_data
- *  Request 5: netif_tx_request -- 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.
+ */
+
+/*
+ * The setting of "trusted" node to "0" in the frontend path signals that the
+ * frontend should not trust the backend, and should deploy whatever measures
+ * available to protect from a malicious backend on the other end.
+ */
+
+/*
+ * Control ring
+ * ============
+ *
+ * Some features, such as 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/vif/<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.
+ */
+
+/*
+ * Link state
+ * ==========
+ *
+ * The backend can advertise its current link (carrier) state to the
+ * frontend using the /local/domain/X/backend/vif/<domid>/<vif>/carrier
+ * node. If this node is not present, then the frontend should assume that
+ * the link is up (for compatibility with backends that do not implement
+ * this feature). If this node is present, then a value of "0" should be
+ * interpreted by the frontend as the link being down (no carrier) and a
+ * value of "1" should be interpreted as the link being up (carrier
+ * present).
+ */
+
+/*
+ * MTU
+ * ===
+ *
+ * The toolstack may set a value of MTU for the frontend by setting the
+ * /local/domain/<domid>/device/vif/<vif>/mtu node with the MTU value in
+ * octets. If this node is absent the frontend should assume an MTU value
+ * of 1500 octets. A frontend is also at liberty to ignore this value so
+ * it is only suitable for informing the frontend that a packet payload
+ * >1500 octets is permitted.
+ */
+
+/*
+ * 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 = Hash(Buffer, 8)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV4 0
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV4 \
+    (1 << _XEN_NETIF_CTRL_HASH_TYPE_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 = Hash(Buffer, 12)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP 1
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP \
+    (1 << _XEN_NETIF_CTRL_HASH_TYPE_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 = Hash(Buffer, 32)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV6 2
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV6 \
+    (1 << _XEN_NETIF_CTRL_HASH_TYPE_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 = Hash(Buffer, 36)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP 3
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP \
+    (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP)
+
+/*
+ * Hash algorithms
+ * ===============
+ */
+
+#define XEN_NETIF_CTRL_HASH_ALGORITHM_NONE 0
+
+/*
+ * Toeplitz hash:
+ */
+
+#define XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ 1
+
+/*
+ * This algorithm uses a 'key' as well as the data buffer itself.
+ * (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
+ *
+ * The code below is provided for convenience where an operating system
+ * does not already provide an implementation.
+ */
+#ifdef XEN_NETIF_DEFINE_TOEPLITZ
+static uint32_t xen_netif_toeplitz_hash(const uint8_t *key,
+                                        unsigned int keylen,
+                                        const uint8_t *buf,
+                                        unsigned int buflen)
+{
+    unsigned int keyi, bufi;
+    uint64_t prefix = 0;
+    uint64_t hash = 0;
+
+    /* Pre-load prefix with the first 8 bytes of the key */
+    for (keyi = 0; keyi < 8; keyi++) {
+        prefix <<= 8;
+        prefix |= (keyi < keylen) ? key[keyi] : 0;
+    }
+
+    for (bufi = 0; bufi < buflen; bufi++) {
+        uint8_t byte = buf[bufi];
+        unsigned int bit;
+
+        for (bit = 0; bit < 8; bit++) {
+            if (byte & 0x80)
+                hash ^= prefix;
+            prefix <<= 1;
+            byte <<=1;
+        }
+
+        /*
+         * 'prefix' has now been left-shifted by 8, so
+         * OR in the next byte.
+         */
+        prefix |= (keyi < keylen) ? key[keyi] : 0;
+        keyi++;
+    }
+
+    /* The valid part of the hash is in the upper 32 bits. */
+    return hash >> 32;
+}
+#endif /* XEN_NETIF_DEFINE_TOEPLITZ */
+
+/*
+ * Control requests (struct xen_netif_ctrl_request)
+ * ================================================
+ *
+ * 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_HASH_FLAGS        1
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS        2
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_KEY          3
+#define XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE 4
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE 5
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING      6
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM    7
+#define XEN_NETIF_CTRL_TYPE_GET_GREF_MAPPING_SIZE 8
+#define XEN_NETIF_CTRL_TYPE_ADD_GREF_MAPPING      9
+#define XEN_NETIF_CTRL_TYPE_DEL_GREF_MAPPING     10
+
+    uint32_t data[3];
+};
+
+/*
+ * Control responses (struct xen_netif_ctrl_response)
+ * ==================================================
+ *
+ * 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;
+};
+
+/*
+ * Static Grants (struct xen_netif_gref)
+ * =====================================
+ *
+ * A frontend may provide a fixed set of grant references to be mapped on
+ * the backend. The message of type XEN_NETIF_CTRL_TYPE_ADD_GREF_MAPPING
+ * prior its usage in the command ring allows for creation of these mappings.
+ * The backend will maintain a fixed amount of these mappings.
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_GREF_MAPPING_SIZE lets a frontend query how many
+ * of these mappings can be kept.
+ *
+ * Each entry in the XEN_NETIF_CTRL_TYPE_{ADD,DEL}_GREF_MAPPING input table has
+ * the following format:
+ *
+ *    0     1     2     3     4     5     6     7  octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | grant ref             |  flags    |  status   |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * grant ref: grant reference (IN)
+ * flags: flags describing the control operation (IN)
+ * status: XEN_NETIF_CTRL_STATUS_* (OUT)
+ *
+ * 'status' is an output parameter which does not require to be set to zero
+ * prior to its usage in the corresponding control messages.
+ */
+
+struct xen_netif_gref {
+       grant_ref_t ref;
+       uint16_t flags;
+
+#define _XEN_NETIF_CTRLF_GREF_readonly    0
+#define XEN_NETIF_CTRLF_GREF_readonly    (1U<<_XEN_NETIF_CTRLF_GREF_readonly)
+
+       uint16_t status;
+};
+
+/*
+ * Control messages
+ * ================
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM
+ * --------------------------------------
+ *
+ * This is sent by the frontend to set the desired hash algorithm.
+ *
+ * Request:
+ *
+ *  type    = XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM
+ *  data[0] = a XEN_NETIF_CTRL_HASH_ALGORITHM_* value
+ *  data[1] = 0
+ *  data[2] = 0
+ *
+ * Response:
+ *
+ *  status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED     - Operation not
+ *                                                     supported
+ *           XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - The algorithm is not
+ *                                                     supported
+ *           XEN_NETIF_CTRL_STATUS_SUCCESS           - Operation successful
+ *
+ * NOTE: Setting data[0] to XEN_NETIF_CTRL_HASH_ALGORITHM_NONE disables
+ *       hashing and the backend is free to choose how it steers packets
+ *       to queues (which is the default behaviour).
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS
+ * ----------------------------------
+ *
+ * This is sent by the frontend to query the types of hash supported by
+ * the backend.
+ *
+ * Request:
+ *
+ *  type    = XEN_NETIF_CTRL_TYPE_GET_HASH_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)
+ *
+ * NOTE: A valid hash algorithm must be selected before this operation can
+ *       succeed.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS
+ * ----------------------------------
+ *
+ * This is sent by the frontend to set the types of 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_HASH_FLAGS
+ *  data[0] = bitwise OR of XEN_NETIF_CTRL_HASH_TYPE_* 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: A valid hash algorithm must be selected before this operation can
+ *       succeed.
+ *       Also, setting data[0] to zero disables hashing and the backend
+ *       is free to choose how it steers packets to queues.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_KEY
+ * --------------------------------
+ *
+ * This is sent by the frontend to set the key of the hash if the algorithm
+ * requires it. (See hash algorithms above).
+ *
+ * Request:
+ *
+ *  type    = XEN_NETIF_CTRL_TYPE_SET_HASH_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 algorithm and 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_HASH_MAPPING_SIZE
+ * -----------------------------------------
+ *
+ * This is sent by the frontend to query the maximum size of mapping
+ * table supported by the backend. The size is specified in terms of
+ * table entries.
+ *
+ * Request:
+ *
+ *  type    = XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE
+ *  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 number of entries allowed in the mapping table
+ *           (if operation was successful) or zero if a mapping table is
+ *           not supported (i.e. hash mapping is done only by modular
+ *           arithmetic).
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ * -------------------------------------
+ *
+ * This is sent by the frontend to set the actual size of the mapping
+ * table to be used by the backend. The size is specified in terms of
+ * table entries.
+ * Any previous table is invalidated by this message and any new table
+ * is assumed to be zero filled.
+ *
+ * Request:
+ *
+ *  type    = XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ *  data[0] = number of entries in 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 size is invalid
+ *           XEN_NETIF_CTRL_STATUS_SUCCESS           - Operation successful
+ *  data   = 0
+ *
+ * NOTE: Setting data[0] to 0 means that hash mapping should be done
+ *       using modular arithmetic.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING
+ * ------------------------------------
+ *
+ * This is sent by the frontend to set the content of the table mapping
+ * 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_HASH_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 is specified by a XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ *       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.
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_GREF_MAPPING_SIZE
+ * -----------------------------------------
+ *
+ * This is sent by the frontend to fetch the number of grefs that can be kept
+ * mapped in the backend.
+ *
+ * Request:
+ *
+ *  type    = XEN_NETIF_CTRL_TYPE_GET_GREF_MAPPING_SIZE
+ *  data[0] = queue index (assumed 0 for single queue)
+ *  data[1] = 0
+ *  data[2] = 0
+ *
+ * Response:
+ *
+ *  status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED     - Operation not
+ *                                                     supported
+ *           XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - The queue index is
+ *                                                     out of range
+ *           XEN_NETIF_CTRL_STATUS_SUCCESS           - Operation successful
+ *  data   = maximum number of entries allowed in the gref mapping table
+ *           (if operation was successful) or zero if it is not supported.
+ *
+ * XEN_NETIF_CTRL_TYPE_ADD_GREF_MAPPING
+ * ------------------------------------
+ *
+ * This is sent by the frontend for backend to map a list of grant
+ * references.
+ *
+ * Request:
+ *
+ *  type    = XEN_NETIF_CTRL_TYPE_ADD_GREF_MAPPING
+ *  data[0] = queue index
+ *  data[1] = grant reference of page containing the mapping list
+ *            (r/w and assumed to start at beginning of page)
+ *  data[2] = size of list in entries
+ *
+ * Response:
+ *
+ *  status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED     - Operation not
+ *                                                     supported
+ *           XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Operation failed
+ *           XEN_NETIF_CTRL_STATUS_SUCCESS           - Operation successful
+ *
+ * NOTE: Each entry in the input table has the format outlined
+ *       in struct xen_netif_gref.
+ *       Contrary to XEN_NETIF_CTRL_TYPE_DEL_GREF_MAPPING, the struct
+ *       xen_netif_gref 'status' field is not used and therefore the response
+ *       'status' determines the success of this operation. In case of
+ *       failure none of grants mappings get added in the backend.
+ *
+ * XEN_NETIF_CTRL_TYPE_DEL_GREF_MAPPING
+ * ------------------------------------
+ *
+ * This is sent by the frontend for backend to unmap a list of grant
+ * references.
+ *
+ * Request:
+ *
+ *  type    = XEN_NETIF_CTRL_TYPE_DEL_GREF_MAPPING
+ *  data[0] = queue index
+ *  data[1] = grant reference of page containing the mapping list
+ *            (r/w and assumed to start at beginning of page)
+ *  data[2] = size of list in entries
+ *
+ * Response:
+ *
+ *  status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED     - Operation not
+ *                                                     supported
+ *           XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Operation failed
+ *           XEN_NETIF_CTRL_STATUS_SUCCESS           - Operation successful
+ *  data   = number of entries that were unmapped
+ *
+ * NOTE: Each entry in the input table has the format outlined in struct
+ *       xen_netif_gref.
+ *       The struct xen_netif_gref 'status' field determines if the entry
+ *       was successfully removed.
+ *       The entries used are only the ones representing grant references that
+ *       were previously the subject of a XEN_NETIF_CTRL_TYPE_ADD_GREF_MAPPING
+ *       operation. Any other entries will have their status set to
+ *       XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER upon completion.
+ */
+
+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: netif_tx_request_t  - flags = NETTXF_*
+ *                                    size = total packet size
+ * [Extra 1: netif_extra_info_t]    - (only if fragment 1 flags include
+ *                                     NETTXF_extra_info)
+ *  ...
+ * [Extra N: netif_extra_info_t]    - (only if extra N-1 flags include
+ *                                     XEN_NETIF_EXTRA_MORE)
+ *  ...
+ *  Fragment N: netif_tx_request_t  - (only if fragment N-1 flags include
+ *                                     NETTXF_more_data - flags on preceding
+ *                                     extras are not relevant 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 (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: NETTXF_*.
+ * id: request identifier, echoed in response.
+ * size: packet size in bytes.
+ *
+ * tx response (netif_tx_response_t)
+ * ---------------------------------
+ *
+ *    0     1     2     3     4     5     6     7  octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id        | status    | unused                |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | unused                |
+ * +-----+-----+-----+-----+
+ *
+ * id: reflects id in transmit request
+ * status: NETIF_RSP_*
+ *
+ * Guest receive
+ * =============
+ *
+ * This is the 'wire' format for receive (backend -> frontend) packets:
+ *
+ *  Fragment 1: netif_rx_request_t  - flags = NETRXF_*
+ *                                    size = fragment size
+ * [Extra 1: netif_extra_info_t]    - (only if fragment 1 flags include
+ *                                     NETRXF_extra_info)
  *  ...
- *  Request N: netif_tx_request -- 0
+ * [Extra N: netif_extra_info_t]    - (only if extra N-1 flags include
+ *                                     XEN_NETIF_EXTRA_MORE)
+ *  ...
+ *  Fragment N: netif_rx_request_t  - (only if fragment N-1 flags include
+ *                                     NETRXF_more_data - flags on preceding
+ *                                     extras are not relevant 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 (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 (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: NETRXF_*
+ * status: -ve: 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
+ *       compatibility, 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 (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_HASH:
+ *
+ * A backend that supports teoplitz hashing is assumed to accept
+ * this type of extra info in transmit packets.
+ * A frontend that enables 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| alg |LSB ---- value ---- MSB|
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * type: Must be XEN_NETIF_EXTRA_TYPE_HASH
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * htype: Hash type (one of _XEN_NETIF_CTRL_HASH_TYPE_* - see above)
+ * alg: The algorithm used to calculate the hash (one of
+ *      XEN_NETIF_CTRL_HASH_TYPE_ALGORITHM_* - see above)
+ * value: Hash value
  */
 
 /* Protocol checksum field is blank in the packet (hardware offload)? */
@@ -166,11 +974,11 @@ FILE_LICENCE ( MIT );
 
 #define XEN_NETIF_MAX_TX_SIZE 0xFFFF
 struct netif_tx_request {
-    grant_ref_t gref;      /* Reference to buffer page */
-    uint16_t offset;       /* Offset within buffer page */
-    uint16_t flags;        /* 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 netif_tx_request netif_tx_request_t;
 
@@ -179,9 +987,10 @@ typedef struct netif_tx_request netif_tx_request_t;
 #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_HASH      (4)  /* u.hash */
+#define XEN_NETIF_EXTRA_TYPE_MAX       (5)
 
-/* netif_extra_info flags. */
+/* netif_extra_info_t flags. */
 #define _XEN_NETIF_EXTRA_FLAG_MORE (0)
 #define XEN_NETIF_EXTRA_FLAG_MORE  (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
 
@@ -191,55 +1000,27 @@ typedef struct netif_tx_request netif_tx_request_t;
 #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 netif_tx_request_t and
+ * netif_rx_response_t for compatibility.
  */
 struct netif_extra_info {
-    uint8_t type;  /* XEN_NETIF_EXTRA_TYPE_* */
-    uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */
-
+    uint8_t type;
+    uint8_t flags;
     union {
-        /*
-         * XEN_NETIF_EXTRA_TYPE_GSO:
-         */
         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;
-
-        /*
-         * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}:
-         * Backend advertises availability via 'feature-multicast-control'
-         * xenbus node containing value '1'.
-         * Frontend requests this feature by advertising
-         * 'request-multicast-control' xenbus node containing value '1'.
-         * If multicast control is requested then multicast flooding is
-         * disabled and the frontend must explicitly register its interest
-         * in multicast groups using dummy transmit requests containing
-         * MCAST_{ADD,DEL} extra-info fragments.
-         */
         struct {
-            uint8_t addr[6]; /* Address to add/remove. */
+            uint8_t addr[6];
         } mcast;
-
+        struct {
+            uint8_t type;
+            uint8_t algorithm;
+            uint8_t value[4];
+        } hash;
         uint16_t pad[3];
     } u;
 };
@@ -247,13 +1028,14 @@ typedef struct netif_extra_info netif_extra_info_t;
 
 struct netif_tx_response {
     uint16_t id;
-    int16_t  status;       /* NETIF_RSP_* */
+    int16_t  status;
 };
 typedef struct netif_tx_response netif_tx_response_t;
 
 struct netif_rx_request {
     uint16_t    id;        /* Echoed in response message.        */
-    grant_ref_t gref;      /* Reference to incoming granted frame */
+    uint16_t    pad;
+    grant_ref_t gref;
 };
 typedef struct netif_rx_request netif_rx_request_t;
 
@@ -273,11 +1055,15 @@ typedef struct netif_rx_request netif_rx_request_t;
 #define _NETRXF_extra_info     (3)
 #define  NETRXF_extra_info     (1U<<_NETRXF_extra_info)
 
+/* Packet has GSO prefix. Deprecated but included for compatibility */
+#define _NETRXF_gso_prefix     (4)
+#define  NETRXF_gso_prefix     (1U<<_NETRXF_gso_prefix)
+
 struct netif_rx_response {
     uint16_t id;
-    uint16_t offset;       /* Offset in page of start of received packet  */
-    uint16_t flags;        /* NETRXF_* */
-    int16_t  status;       /* -ve: NETIF_RSP_* ; +ve: Rx'ed pkt size. */
+    uint16_t offset;
+    uint16_t flags;
+    int16_t  status;
 };
 typedef struct netif_rx_response netif_rx_response_t;
 
@@ -291,7 +1077,7 @@ DEFINE_RING_TYPES(netif_rx, struct netif_rx_request, struct netif_rx_response);
 #define NETIF_RSP_DROPPED         -2
 #define NETIF_RSP_ERROR           -1
 #define NETIF_RSP_OKAY             0
-/* No response: used for auxiliary requests (e.g., netif_tx_extra). */
+/* No response: used for auxiliary requests (e.g., netif_extra_info_t). */
 #define NETIF_RSP_NULL             1
 
 #endif