fc3d66212f
With fixed avail ring, we don't need to get desc idx from avail ring. virtio driver only has to deal with desc ring. This patch uses vector instruction to accelerate processing desc ring. Signed-off-by: Huawei Xie <huawei.xie@intel.com> Acked-by: Jianfeng Tan <jianfeng.tan@intel.com>
325 lines
11 KiB
C
325 lines
11 KiB
C
/*-
|
|
* BSD LICENSE
|
|
*
|
|
* Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
|
|
* 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.
|
|
*/
|
|
|
|
#ifndef _VIRTQUEUE_H_
|
|
#define _VIRTQUEUE_H_
|
|
|
|
#include <stdint.h>
|
|
|
|
#include <rte_atomic.h>
|
|
#include <rte_memory.h>
|
|
#include <rte_memzone.h>
|
|
#include <rte_mempool.h>
|
|
|
|
#include "virtio_pci.h"
|
|
#include "virtio_ring.h"
|
|
#include "virtio_logs.h"
|
|
|
|
struct rte_mbuf;
|
|
|
|
/*
|
|
* Per virtio_config.h in Linux.
|
|
* For virtio_pci on SMP, we don't need to order with respect to MMIO
|
|
* accesses through relaxed memory I/O windows, so smp_mb() et al are
|
|
* sufficient.
|
|
*
|
|
* This driver is for virtio_pci on SMP and therefore can assume
|
|
* weaker (compiler barriers)
|
|
*/
|
|
#define virtio_mb() rte_mb()
|
|
#define virtio_rmb() rte_compiler_barrier()
|
|
#define virtio_wmb() rte_compiler_barrier()
|
|
|
|
#ifdef RTE_PMD_PACKET_PREFETCH
|
|
#define rte_packet_prefetch(p) rte_prefetch1(p)
|
|
#else
|
|
#define rte_packet_prefetch(p) do {} while(0)
|
|
#endif
|
|
|
|
#define VIRTQUEUE_MAX_NAME_SZ 32
|
|
|
|
#define RTE_MBUF_DATA_DMA_ADDR(mb) \
|
|
(uint64_t) ((mb)->buf_physaddr + (mb)->data_off)
|
|
|
|
#define VTNET_SQ_RQ_QUEUE_IDX 0
|
|
#define VTNET_SQ_TQ_QUEUE_IDX 1
|
|
#define VTNET_SQ_CQ_QUEUE_IDX 2
|
|
|
|
enum { VTNET_RQ = 0, VTNET_TQ = 1, VTNET_CQ = 2 };
|
|
/**
|
|
* The maximum virtqueue size is 2^15. Use that value as the end of
|
|
* descriptor chain terminator since it will never be a valid index
|
|
* in the descriptor table. This is used to verify we are correctly
|
|
* handling vq_free_cnt.
|
|
*/
|
|
#define VQ_RING_DESC_CHAIN_END 32768
|
|
|
|
/**
|
|
* Control the RX mode, ie. promiscuous, 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
|
|
*
|
|
* 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.
|
|
*
|
|
* The ADDR_SET command requests one out scatterlist, it contains a
|
|
* 6 bytes MAC address. This functionality is present if the
|
|
* VIRTIO_NET_F_CTRL_MAC_ADDR feature is available.
|
|
*/
|
|
struct virtio_net_ctrl_mac {
|
|
uint32_t entries;
|
|
uint8_t macs[][ETHER_ADDR_LEN];
|
|
} __attribute__((__packed__));
|
|
|
|
#define VIRTIO_NET_CTRL_MAC 1
|
|
#define VIRTIO_NET_CTRL_MAC_TABLE_SET 0
|
|
#define VIRTIO_NET_CTRL_MAC_ADDR_SET 1
|
|
|
|
/**
|
|
* Control VLAN filtering
|
|
*
|
|
* The VLAN filter table is controlled via a simple ADD/DEL interface.
|
|
* VLAN IDs not added may be filtered by the hypervisor. Del is the
|
|
* opposite of add. Both commands expect an out entry containing a 2
|
|
* byte VLAN ID. VLAN filtering 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
|
|
|
|
struct virtio_net_ctrl_hdr {
|
|
uint8_t class;
|
|
uint8_t cmd;
|
|
} __attribute__((packed));
|
|
|
|
typedef uint8_t virtio_net_ctrl_ack;
|
|
|
|
#define VIRTIO_NET_OK 0
|
|
#define VIRTIO_NET_ERR 1
|
|
|
|
#define VIRTIO_MAX_CTRL_DATA 2048
|
|
|
|
struct virtio_pmd_ctrl {
|
|
struct virtio_net_ctrl_hdr hdr;
|
|
virtio_net_ctrl_ack status;
|
|
uint8_t data[VIRTIO_MAX_CTRL_DATA];
|
|
};
|
|
|
|
struct virtqueue {
|
|
struct virtio_hw *hw; /**< virtio_hw structure pointer. */
|
|
const struct rte_memzone *mz; /**< mem zone to populate RX ring. */
|
|
const struct rte_memzone *virtio_net_hdr_mz; /**< memzone to populate hdr. */
|
|
struct rte_mempool *mpool; /**< mempool for mbuf allocation */
|
|
uint16_t queue_id; /**< DPDK queue index. */
|
|
uint8_t port_id; /**< Device port identifier. */
|
|
uint16_t vq_queue_index; /**< PCI queue index */
|
|
|
|
void *vq_ring_virt_mem; /**< linear address of vring*/
|
|
unsigned int vq_ring_size;
|
|
phys_addr_t vq_ring_mem; /**< physical address of vring */
|
|
|
|
struct vring vq_ring; /**< vring keeping desc, used and avail */
|
|
uint16_t vq_free_cnt; /**< num of desc available */
|
|
uint16_t vq_nentries; /**< vring desc numbers */
|
|
uint16_t vq_free_thresh; /**< free threshold */
|
|
/**
|
|
* Head of the free chain in the descriptor table. If
|
|
* there are no free descriptors, this will be set to
|
|
* VQ_RING_DESC_CHAIN_END.
|
|
*/
|
|
uint16_t vq_desc_head_idx;
|
|
uint16_t vq_desc_tail_idx;
|
|
/**
|
|
* Last consumed descriptor in the used table,
|
|
* trails vq_ring.used->idx.
|
|
*/
|
|
uint16_t vq_used_cons_idx;
|
|
uint16_t vq_avail_idx;
|
|
uint64_t mbuf_initializer; /**< value to init mbufs. */
|
|
phys_addr_t virtio_net_hdr_mem; /**< hdr for each xmit packet */
|
|
|
|
struct rte_mbuf **sw_ring; /**< RX software ring. */
|
|
/* dummy mbuf, for wraparound when processing RX ring. */
|
|
struct rte_mbuf fake_mbuf;
|
|
|
|
/* Statistics */
|
|
uint64_t packets;
|
|
uint64_t bytes;
|
|
uint64_t errors;
|
|
|
|
struct vq_desc_extra {
|
|
void *cookie;
|
|
uint16_t ndescs;
|
|
} vq_descx[0];
|
|
};
|
|
|
|
/* If multiqueue is provided by host, then we suppport it. */
|
|
#define VIRTIO_NET_CTRL_MQ 4
|
|
#define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET 0
|
|
#define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN 1
|
|
#define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX 0x8000
|
|
|
|
#define VIRTIO_NET_CTRL_MAC_ADDR_SET 1
|
|
|
|
/**
|
|
* 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*/
|
|
uint8_t 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 */
|
|
uint8_t gso_type;
|
|
uint16_t hdr_len; /**< Ethernet + IP + tcp/udp hdrs */
|
|
uint16_t gso_size; /**< Bytes to append to hdr_len per frame */
|
|
uint16_t csum_start; /**< Position to start checksumming from */
|
|
uint16_t csum_offset; /**< Offset after that to place checksum */
|
|
};
|
|
|
|
/**
|
|
* 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;
|
|
uint16_t num_buffers; /**< Number of merged rx buffers */
|
|
};
|
|
|
|
/**
|
|
* Tell the backend not to interrupt us.
|
|
*/
|
|
void virtqueue_disable_intr(struct virtqueue *vq);
|
|
/**
|
|
* Dump virtqueue internal structures, for debug purpose only.
|
|
*/
|
|
void virtqueue_dump(struct virtqueue *vq);
|
|
/**
|
|
* Get all mbufs to be freed.
|
|
*/
|
|
struct rte_mbuf *virtqueue_detatch_unused(struct virtqueue *vq);
|
|
|
|
static inline int
|
|
virtqueue_full(const struct virtqueue *vq)
|
|
{
|
|
return vq->vq_free_cnt == 0;
|
|
}
|
|
|
|
#define VIRTQUEUE_NUSED(vq) ((uint16_t)((vq)->vq_ring.used->idx - (vq)->vq_used_cons_idx))
|
|
|
|
static inline void
|
|
vq_update_avail_idx(struct virtqueue *vq)
|
|
{
|
|
virtio_wmb();
|
|
vq->vq_ring.avail->idx = vq->vq_avail_idx;
|
|
}
|
|
|
|
static inline void
|
|
vq_update_avail_ring(struct virtqueue *vq, uint16_t desc_idx)
|
|
{
|
|
uint16_t avail_idx;
|
|
/*
|
|
* Place the head of the descriptor chain into the next slot and make
|
|
* it usable to the host. The chain is made available now rather than
|
|
* deferring to virtqueue_notify() in the hopes that if the host is
|
|
* currently running on another CPU, we can keep it processing the new
|
|
* descriptor.
|
|
*/
|
|
avail_idx = (uint16_t)(vq->vq_avail_idx & (vq->vq_nentries - 1));
|
|
vq->vq_ring.avail->ring[avail_idx] = desc_idx;
|
|
vq->vq_avail_idx++;
|
|
}
|
|
|
|
static inline int
|
|
virtqueue_kick_prepare(struct virtqueue *vq)
|
|
{
|
|
return !(vq->vq_ring.used->flags & VRING_USED_F_NO_NOTIFY);
|
|
}
|
|
|
|
static inline void
|
|
virtqueue_notify(struct virtqueue *vq)
|
|
{
|
|
/*
|
|
* Ensure updated avail->idx is visible to host.
|
|
* For virtio on IA, the notificaiton is through io port operation
|
|
* which is a serialization instruction itself.
|
|
*/
|
|
VIRTIO_WRITE_REG_2(vq->hw, VIRTIO_PCI_QUEUE_NOTIFY, vq->vq_queue_index);
|
|
}
|
|
|
|
#ifdef RTE_LIBRTE_VIRTIO_DEBUG_DUMP
|
|
#define VIRTQUEUE_DUMP(vq) do { \
|
|
uint16_t used_idx, nused; \
|
|
used_idx = (vq)->vq_ring.used->idx; \
|
|
nused = (uint16_t)(used_idx - (vq)->vq_used_cons_idx); \
|
|
PMD_INIT_LOG(DEBUG, \
|
|
"VQ: - size=%d; free=%d; used=%d; desc_head_idx=%d;" \
|
|
" avail.idx=%d; used_cons_idx=%d; used.idx=%d;" \
|
|
" avail.flags=0x%x; used.flags=0x%x", \
|
|
(vq)->vq_nentries, (vq)->vq_free_cnt, nused, \
|
|
(vq)->vq_desc_head_idx, (vq)->vq_ring.avail->idx, \
|
|
(vq)->vq_used_cons_idx, (vq)->vq_ring.used->idx, \
|
|
(vq)->vq_ring.avail->flags, (vq)->vq_ring.used->flags); \
|
|
} while (0)
|
|
#else
|
|
#define VIRTQUEUE_DUMP(vq) do { } while (0)
|
|
#endif
|
|
|
|
#endif /* _VIRTQUEUE_H_ */
|