interface/io/netif.h

17  * Older implementation of Xen network frontend / backend has an
20  * expected when frontend and backend have different MAX_SKB_FRAGS.
29  * which doesn't negotiate with frontend should expect frontend to
47  * To make use of this feature, frontend should allocate two event
49  * "event-channel-tx" and "event-channel-rx" respectively. If frontend
73  * to avoid distinguishing between a frontend that doesn't understand the
80  * are indexed from zero. For example, a frontend with two queues and split
98  * requested than the frontend provided details for.
101  * transmitting system (backend or frontend) and is not negotiated
124  * backend. If the frontend wishes to take advantage of this feature then
127  * before the frontend moves into the connected state. The backend will
131  * may be set by the frontend at any time. In this case, the backend will
136  * frontend, it should instead drop any multicast packet that does not
138  * The list is amended by the frontend by sending dummy transmit requests
147  * The setting of "trusted" node to "0" in the frontend path signals that the
148  * frontend should not trust the backend, and should deploy whatever measures
157  * significant amount of out-of-band data to be passed from frontend to
165  * The frontend provides a control ring to the backend by setting:
172  * as a mailbox interrupt. These keys must be set before the frontend
187  * frontend using the /local/domain/X/backend/vif/<domid>/<vif>/carrier
188  * node. If this node is not present, then the frontend should assume that
191  * interpreted by the frontend as the link being down (no carrier) and a
200  * The toolstack may set a value of MTU for the frontend by setting the
202  * octets. If this node is absent the frontend should assume an MTU value
203  * of 1500 octets. A frontend is also at liberty to ignore this value so
204  * it is only suitable for informing the frontend that a packet payload
415  * A frontend may provide a fixed set of grant references to be mapped on
420  * XEN_NETIF_CTRL_TYPE_GET_GREF_MAPPING_SIZE lets a frontend query how many
456  * This is sent by the frontend to set the desired hash algorithm.
480  * This is sent by the frontend to query the types of hash supported by
502  * This is sent by the frontend to set the types of hash that the backend
505  * example, if the frontend sets both IPV4 and IPV4_TCP hash types then
534  * This is sent by the frontend to set the key of the hash if the algorithm
569  * This is sent by the frontend to query the maximum size of mapping
592  * This is sent by the frontend to set the actual size of the mapping
619  * This is sent by the frontend to set the content of the table mapping
672  * This is sent by the frontend to fetch the number of grefs that can be kept
695  * This is sent by the frontend for backend to map a list of grant
723  * This is sent by the frontend for backend to unmap a list of grant
760  * This is the 'wire' format for transmit (frontend -> backend) packets:
779  * (backend -> frontend) packets. Specifically, in a multi-fragment
818  * This is the 'wire' format for receive (backend -> frontend) packets:
837  * (frontend -> backend) packets. Specifically, in a multi-fragment
867  * NOTE: Historically, to support GSO on the frontend receive side, Linux
885  *       So, if an extra info overlays an rx response the frontend can
941  * A frontend that enables hashing is assumed to accept