OpenCloudOS-Kernel/include/linux/virtio_net.h

132 lines
5.1 KiB
C
Raw Normal View History

#ifndef _LINUX_VIRTIO_NET_H
#define _LINUX_VIRTIO_NET_H
/* This header is BSD licensed so anyone can use the definitions to implement
* compatible drivers/servers. */
#include <linux/types.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
#include <linux/if_ether.h>
/* The feature bitmap for virtio net */
#define VIRTIO_NET_F_CSUM 0 /* Host handles pkts w/ partial csum */
#define VIRTIO_NET_F_GUEST_CSUM 1 /* Guest handles pkts w/ partial csum */
#define VIRTIO_NET_F_MAC 5 /* Host has given MAC address. */
#define VIRTIO_NET_F_GSO 6 /* Host handles pkts w/ any GSO type */
#define VIRTIO_NET_F_GUEST_TSO4 7 /* Guest can handle TSOv4 in. */
#define VIRTIO_NET_F_GUEST_TSO6 8 /* Guest can handle TSOv6 in. */
#define VIRTIO_NET_F_GUEST_ECN 9 /* Guest can handle TSO[6] w/ ECN in. */
#define VIRTIO_NET_F_GUEST_UFO 10 /* Guest can handle UFO in. */
#define VIRTIO_NET_F_HOST_TSO4 11 /* Host can handle TSOv4 in. */
#define VIRTIO_NET_F_HOST_TSO6 12 /* Host can handle TSOv6 in. */
#define VIRTIO_NET_F_HOST_ECN 13 /* Host can handle TSO[6] w/ ECN in. */
#define VIRTIO_NET_F_HOST_UFO 14 /* Host can handle UFO in. */
virtio_net: VIRTIO_NET_F_MSG_RXBUF (imprive rcv buffer allocation) If segmentation offload is enabled by the host, we currently allocate maximum sized packet buffers and pass them to the host. This uses up 20 ring entries, allowing us to supply only 20 packet buffers to the host with a 256 entry ring. This is a huge overhead when receiving small packets, and is most keenly felt when receiving MTU sized packets from off-host. The VIRTIO_NET_F_MRG_RXBUF feature flag is set by hosts which support using receive buffers which are smaller than the maximum packet size. In order to transfer large packets to the guest, the host merges together multiple receive buffers to form a larger logical buffer. The number of merged buffers is returned to the guest via a field in the virtio_net_hdr. Make use of this support by supplying single page receive buffers to the host. On receive, we extract the virtio_net_hdr, copy 128 bytes of the payload to the skb's linear data buffer and adjust the fragment offset to point to the remaining data. This ensures proper alignment and allows us to not use any paged data for small packets. If the payload occupies multiple pages, we simply append those pages as fragments and free the associated skbs. This scheme allows us to be efficient in our use of ring entries while still supporting large packets. Benchmarking using netperf from an external machine to a guest over a 10Gb/s network shows a 100% improvement from ~1Gb/s to ~2Gb/s. With a local host->guest benchmark with GSO disabled on the host side, throughput was seen to increase from 700Mb/s to 1.7Gb/s. Based on a patch from Herbert Xu. Signed-off-by: Mark McLoughlin <markmc@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (use netdev_priv) Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-17 14:41:34 +08:00
#define VIRTIO_NET_F_MRG_RXBUF 15 /* Host can merge receive buffers. */
#define VIRTIO_NET_F_STATUS 16 /* virtio_net_config.status available */
#define VIRTIO_NET_F_CTRL_VQ 17 /* Control channel available */
#define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */
#define VIRTIO_NET_F_CTRL_VLAN 19 /* Control channel VLAN filtering */
#define VIRTIO_NET_F_CTRL_RX_EXTRA 20 /* Extra RX mode control support */
#define VIRTIO_NET_S_LINK_UP 1 /* Link is up */
struct virtio_net_config {
/* The config defining mac address (if VIRTIO_NET_F_MAC) */
__u8 mac[6];
/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
__u16 status;
} __attribute__((packed));
/* This is the first element of the scatter-gather list. If you don't
* specify GSO or CSUM features, you can simply ignore the header. */
struct virtio_net_hdr {
#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 // Use csum_start, csum_offset
__u8 flags;
#define VIRTIO_NET_HDR_GSO_NONE 0 // Not a GSO frame
#define VIRTIO_NET_HDR_GSO_TCPV4 1 // GSO frame, IPv4 TCP (TSO)
#define VIRTIO_NET_HDR_GSO_UDP 3 // GSO frame, IPv4 UDP (UFO)
#define VIRTIO_NET_HDR_GSO_TCPV6 4 // GSO frame, IPv6 TCP
#define VIRTIO_NET_HDR_GSO_ECN 0x80 // TCP has ECN set
__u8 gso_type;
__u16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */
__u16 gso_size; /* Bytes to append to hdr_len per frame */
__u16 csum_start; /* Position to start checksumming from */
__u16 csum_offset; /* Offset after that to place checksum */
};
virtio_net: VIRTIO_NET_F_MSG_RXBUF (imprive rcv buffer allocation) If segmentation offload is enabled by the host, we currently allocate maximum sized packet buffers and pass them to the host. This uses up 20 ring entries, allowing us to supply only 20 packet buffers to the host with a 256 entry ring. This is a huge overhead when receiving small packets, and is most keenly felt when receiving MTU sized packets from off-host. The VIRTIO_NET_F_MRG_RXBUF feature flag is set by hosts which support using receive buffers which are smaller than the maximum packet size. In order to transfer large packets to the guest, the host merges together multiple receive buffers to form a larger logical buffer. The number of merged buffers is returned to the guest via a field in the virtio_net_hdr. Make use of this support by supplying single page receive buffers to the host. On receive, we extract the virtio_net_hdr, copy 128 bytes of the payload to the skb's linear data buffer and adjust the fragment offset to point to the remaining data. This ensures proper alignment and allows us to not use any paged data for small packets. If the payload occupies multiple pages, we simply append those pages as fragments and free the associated skbs. This scheme allows us to be efficient in our use of ring entries while still supporting large packets. Benchmarking using netperf from an external machine to a guest over a 10Gb/s network shows a 100% improvement from ~1Gb/s to ~2Gb/s. With a local host->guest benchmark with GSO disabled on the host side, throughput was seen to increase from 700Mb/s to 1.7Gb/s. Based on a patch from Herbert Xu. Signed-off-by: Mark McLoughlin <markmc@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (use netdev_priv) Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-17 14:41:34 +08:00
/* This is the version of the header to use when the MRG_RXBUF
* feature has been negotiated. */
struct virtio_net_hdr_mrg_rxbuf {
struct virtio_net_hdr hdr;
__u16 num_buffers; /* Number of merged rx buffers */
};
/*
* Control virtqueue data structures
*
* The control virtqueue expects a header in the first sg entry
* and an ack/status response in the last entry. Data for the
* command goes in between.
*/
struct virtio_net_ctrl_hdr {
__u8 class;
__u8 cmd;
} __attribute__((packed));
typedef __u8 virtio_net_ctrl_ack;
#define VIRTIO_NET_OK 0
#define VIRTIO_NET_ERR 1
/*
* Control the RX mode, ie. promisucous, allmulti, etc...
* All commands require an "out" sg entry containing a 1 byte
* state value, zero = disable, non-zero = enable. Commands
* 0 and 1 are supported with the VIRTIO_NET_F_CTRL_RX feature.
* Commands 2-5 are added with VIRTIO_NET_F_CTRL_RX_EXTRA.
*/
#define VIRTIO_NET_CTRL_RX 0
#define VIRTIO_NET_CTRL_RX_PROMISC 0
#define VIRTIO_NET_CTRL_RX_ALLMULTI 1
#define VIRTIO_NET_CTRL_RX_ALLUNI 2
#define VIRTIO_NET_CTRL_RX_NOMULTI 3
#define VIRTIO_NET_CTRL_RX_NOUNI 4
#define VIRTIO_NET_CTRL_RX_NOBCAST 5
/*
* Control the MAC filter table.
*
* The MAC filter table is managed by the hypervisor, the guest should
* assume the size is infinite. Filtering should be considered
* non-perfect, ie. based on hypervisor resources, the guest may
* received packets from sources not specified in the filter list.
*
* In addition to the class/cmd header, the TABLE_SET command requires
* two out scatterlists. Each contains a 4 byte count of entries followed
* by a concatenated byte stream of the ETH_ALEN MAC addresses. The
* first sg list contains unicast addresses, the second is for multicast.
* This functionality is present if the VIRTIO_NET_F_CTRL_RX feature
* is available.
*/
struct virtio_net_ctrl_mac {
__u32 entries;
__u8 macs[][ETH_ALEN];
} __attribute__((packed));
#define VIRTIO_NET_CTRL_MAC 1
#define VIRTIO_NET_CTRL_MAC_TABLE_SET 0
/*
* Control VLAN filtering
*
* The VLAN filter table is controlled via a simple ADD/DEL interface.
* VLAN IDs not added may be filterd by the hypervisor. Del is the
* opposite of add. Both commands expect an out entry containing a 2
* byte VLAN ID. VLAN filterting is available with the
* VIRTIO_NET_F_CTRL_VLAN feature bit.
*/
#define VIRTIO_NET_CTRL_VLAN 2
#define VIRTIO_NET_CTRL_VLAN_ADD 0
#define VIRTIO_NET_CTRL_VLAN_DEL 1
#endif /* _LINUX_VIRTIO_NET_H */