rte_vhost.h

Go to the documentation of this file.

/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2017 Intel Corporation
 */

#ifndef _RTE_VHOST_H_
#define _RTE_VHOST_H_

#include <stdbool.h>
#include <stdint.h>
#include <sys/eventfd.h>

#include <rte_compat.h>
#include <rte_memory.h>
#include <rte_mempool.h>

#ifdef __cplusplus
extern "C" {
#endif

#ifndef __cplusplus
/* These are not C++-aware. */
#include <linux/vhost.h>
#include <linux/virtio_ring.h>
#include <linux/virtio_net.h>
#endif

#define RTE_VHOST_USER_CLIENT       (1ULL << 0)
#define RTE_VHOST_USER_NO_RECONNECT (1ULL << 1)
#define RTE_VHOST_USER_RESERVED_1   (1ULL << 2)
#define RTE_VHOST_USER_IOMMU_SUPPORT    (1ULL << 3)
#define RTE_VHOST_USER_POSTCOPY_SUPPORT     (1ULL << 4)
/* support mbuf with external buffer attached */
#define RTE_VHOST_USER_EXTBUF_SUPPORT   (1ULL << 5)
/* support only linear buffers (no chained mbufs) */
#define RTE_VHOST_USER_LINEARBUF_SUPPORT    (1ULL << 6)
#define RTE_VHOST_USER_ASYNC_COPY   (1ULL << 7)
#define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS   (1ULL << 8)
#define RTE_VHOST_USER_NET_STATS_ENABLE (1ULL << 9)

/* Features. */
#ifndef VIRTIO_NET_F_GUEST_ANNOUNCE
 #define VIRTIO_NET_F_GUEST_ANNOUNCE 21
#endif

#ifndef VIRTIO_NET_F_MQ
 #define VIRTIO_NET_F_MQ        22
#endif

#ifndef VIRTIO_NET_F_MTU
 #define VIRTIO_NET_F_MTU 3
#endif

#ifndef VIRTIO_F_ANY_LAYOUT
 #define VIRTIO_F_ANY_LAYOUT        27
#endif

#ifndef VHOST_USER_PROTOCOL_F_MQ
#define VHOST_USER_PROTOCOL_F_MQ    0
#endif

#ifndef VHOST_USER_PROTOCOL_F_LOG_SHMFD
#define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1
#endif

#ifndef VHOST_USER_PROTOCOL_F_RARP
#define VHOST_USER_PROTOCOL_F_RARP  2
#endif

#ifndef VHOST_USER_PROTOCOL_F_REPLY_ACK
#define VHOST_USER_PROTOCOL_F_REPLY_ACK 3
#endif

#ifndef VHOST_USER_PROTOCOL_F_NET_MTU
#define VHOST_USER_PROTOCOL_F_NET_MTU   4
#endif

#ifndef VHOST_USER_PROTOCOL_F_BACKEND_REQ
#define VHOST_USER_PROTOCOL_F_BACKEND_REQ   5
#endif

#ifndef VHOST_USER_PROTOCOL_F_CRYPTO_SESSION
#define VHOST_USER_PROTOCOL_F_CRYPTO_SESSION 7
#endif

#ifndef VHOST_USER_PROTOCOL_F_PAGEFAULT
#define VHOST_USER_PROTOCOL_F_PAGEFAULT 8
#endif

#ifndef VHOST_USER_PROTOCOL_F_CONFIG
#define VHOST_USER_PROTOCOL_F_CONFIG 9
#endif

#ifndef VHOST_USER_PROTOCOL_F_BACKEND_SEND_FD
#define VHOST_USER_PROTOCOL_F_BACKEND_SEND_FD 10
#endif

#ifndef VHOST_USER_PROTOCOL_F_HOST_NOTIFIER
#define VHOST_USER_PROTOCOL_F_HOST_NOTIFIER 11
#endif

#ifndef VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD
#define VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD 12
#endif

#ifndef VHOST_USER_PROTOCOL_F_STATUS
#define VHOST_USER_PROTOCOL_F_STATUS 16
#endif

#ifndef VHOST_USER_F_PROTOCOL_FEATURES
#define VHOST_USER_F_PROTOCOL_FEATURES  30
#endif

#define RTE_MAX_VHOST_DEVICE    1024

#define RTE_VHOST_VDPA_DEVICE_TYPE_NET 0
#define RTE_VHOST_VDPA_DEVICE_TYPE_BLK 1

struct rte_vdpa_device;

struct rte_vhost_mem_region {
    uint64_t guest_phys_addr;
    uint64_t guest_user_addr;
    uint64_t host_user_addr;
    uint64_t size;
    void     *mmap_addr;
    uint64_t mmap_size;
    int fd;
};

struct rte_vhost_memory {
    uint32_t nregions;
    struct rte_vhost_mem_region regions[];
};

struct rte_vhost_inflight_desc_split {
    uint8_t inflight;
    uint8_t padding[5];
    uint16_t next;
    uint64_t counter;
};

struct rte_vhost_inflight_info_split {
    uint64_t features;
    uint16_t version;
    uint16_t desc_num;
    uint16_t last_inflight_io;
    uint16_t used_idx;
    struct rte_vhost_inflight_desc_split desc[];
};

struct rte_vhost_inflight_desc_packed {
    uint8_t inflight;
    uint8_t padding;
    uint16_t next;
    uint16_t last;
    uint16_t num;
    uint64_t counter;
    uint16_t id;
    uint16_t flags;
    uint32_t len;
    uint64_t addr;
};

struct rte_vhost_inflight_info_packed {
    uint64_t features;
    uint16_t version;
    uint16_t desc_num;
    uint16_t free_head;
    uint16_t old_free_head;
    uint16_t used_idx;
    uint16_t old_used_idx;
    uint8_t used_wrap_counter;
    uint8_t old_used_wrap_counter;
    uint8_t padding[7];
    struct rte_vhost_inflight_desc_packed desc[];
};

struct rte_vhost_resubmit_desc {
    uint16_t index;
    uint64_t counter;
};

struct rte_vhost_resubmit_info {
    struct rte_vhost_resubmit_desc *resubmit_list;
    uint16_t resubmit_num;
};

struct rte_vhost_ring_inflight {
    union {
        struct rte_vhost_inflight_info_split *inflight_split;
        struct rte_vhost_inflight_info_packed *inflight_packed;
    };

    struct rte_vhost_resubmit_info *resubmit_inflight;
};

struct rte_vhost_vring {
    union {
        struct vring_desc *desc;
        struct vring_packed_desc *desc_packed;
    };
    union {
        struct vring_avail *avail;
        struct vring_packed_desc_event *driver_event;
    };
    union {
        struct vring_used *used;
        struct vring_packed_desc_event *device_event;
    };
    uint64_t        log_guest_addr;

    int         callfd;

    int         kickfd;
    uint16_t        size;
};

enum rte_vhost_msg_result {
    /* Message handling failed */
    RTE_VHOST_MSG_RESULT_ERR = -1,
    /* Message handling successful */
    RTE_VHOST_MSG_RESULT_OK =  0,
    /* Message handling successful and reply prepared */
    RTE_VHOST_MSG_RESULT_REPLY =  1,
    /* Message not handled */
    RTE_VHOST_MSG_RESULT_NOT_HANDLED,
};

typedef enum rte_vhost_msg_result (*rte_vhost_msg_handle)(int vid, void *msg);

struct rte_vhost_user_extern_ops {
    /* Called prior to the frontend message handling. */
    rte_vhost_msg_handle pre_msg_handle;
    /* Called after the frontend message handling. */
    rte_vhost_msg_handle post_msg_handle;
};

struct rte_vhost_device_ops {
    int (*new_device)(int vid);     
    void (*destroy_device)(int vid);    
    int (*vring_state_changed)(int vid, uint16_t queue_id, int enable); 
    int (*features_changed)(int vid, uint64_t features);

    int (*new_connection)(int vid);
    void (*destroy_connection)(int vid);

    void (*guest_notified)(int vid);

    bool (*guest_notify)(int vid, uint16_t queue_id);
};

struct rte_vhost_power_monitor_cond {
    volatile void *addr;
    uint64_t val;
    uint64_t mask;
    uint8_t size;
    uint8_t match;
};

#define RTE_VHOST_STATS_NAME_SIZE 64

struct rte_vhost_stat {
    uint64_t id;    
    uint64_t value; 
};

struct rte_vhost_stat_name {
    char name[RTE_VHOST_STATS_NAME_SIZE]; 
};

static __rte_always_inline uint64_t
rte_vhost_va_from_guest_pa(struct rte_vhost_memory *mem,
                           uint64_t gpa, uint64_t *len)
{
    struct rte_vhost_mem_region *r;
    uint32_t i;

    for (i = 0; i < mem->nregions; i++) {
        r = &mem->regions[i];
        if (gpa >= r->guest_phys_addr &&
            gpa <  r->guest_phys_addr + r->size) {

            if (unlikely(*len > r->guest_phys_addr + r->size - gpa))
                *len = r->guest_phys_addr + r->size - gpa;

            return gpa - r->guest_phys_addr +
                   r->host_user_addr;
        }
    }
    *len = 0;

    return 0;
}

#define RTE_VHOST_NEED_LOG(features)    ((features) & (1ULL << VHOST_F_LOG_ALL))

void rte_vhost_log_write(int vid, uint64_t addr, uint64_t len);

void rte_vhost_log_used_vring(int vid, uint16_t vring_idx,
                  uint64_t offset, uint64_t len);

int rte_vhost_enable_guest_notification(int vid, uint16_t queue_id, int enable);

__rte_experimental
void rte_vhost_notify_guest(int vid, uint16_t queue_id);

int rte_vhost_driver_register(const char *path, uint64_t flags);

/* Unregister vhost driver. This is only meaningful to vhost user. */
int rte_vhost_driver_unregister(const char *path);

int
rte_vhost_driver_attach_vdpa_device(const char *path,
        struct rte_vdpa_device *dev);

int
rte_vhost_driver_detach_vdpa_device(const char *path);

struct rte_vdpa_device *
rte_vhost_driver_get_vdpa_device(const char *path);

__rte_experimental
int
rte_vhost_driver_get_vdpa_dev_type(const char *path, uint32_t *type);

int rte_vhost_driver_set_features(const char *path, uint64_t features);

int rte_vhost_driver_enable_features(const char *path, uint64_t features);

int rte_vhost_driver_disable_features(const char *path, uint64_t features);

int rte_vhost_driver_get_features(const char *path, uint64_t *features);

int
rte_vhost_driver_set_protocol_features(const char *path,
        uint64_t protocol_features);

int
rte_vhost_driver_get_protocol_features(const char *path,
        uint64_t *protocol_features);

int
rte_vhost_driver_get_queue_num(const char *path, uint32_t *queue_num);

__rte_experimental
int
rte_vhost_driver_set_max_queue_num(const char *path, uint32_t max_queue_pairs);

int rte_vhost_get_negotiated_features(int vid, uint64_t *features);

__rte_experimental
int
rte_vhost_get_negotiated_protocol_features(int vid,
                       uint64_t *protocol_features);

/* Register callbacks. */
int rte_vhost_driver_callback_register(const char *path,
    struct rte_vhost_device_ops const * const ops);

int rte_vhost_driver_start(const char *path);

int rte_vhost_get_mtu(int vid, uint16_t *mtu);

int rte_vhost_get_numa_node(int vid);

uint16_t rte_vhost_get_vring_num(int vid);

int rte_vhost_get_ifname(int vid, char *buf, size_t len);

uint16_t rte_vhost_avail_entries(int vid, uint16_t queue_id);

struct rte_mbuf;
struct rte_mempool;
uint16_t rte_vhost_enqueue_burst(int vid, uint16_t queue_id,
    struct rte_mbuf **pkts, uint16_t count);

uint16_t rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
    struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count);

int rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem);

int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
                  struct rte_vhost_vring *vring);

int
rte_vhost_get_vhost_ring_inflight(int vid, uint16_t vring_idx,
    struct rte_vhost_ring_inflight *vring);

int
rte_vhost_set_inflight_desc_split(int vid, uint16_t vring_idx,
    uint16_t idx);

int
rte_vhost_set_inflight_desc_packed(int vid, uint16_t vring_idx,
    uint16_t head, uint16_t last, uint16_t *inflight_entry);

int
rte_vhost_set_last_inflight_io_split(int vid,
    uint16_t vring_idx, uint16_t idx);

int
rte_vhost_set_last_inflight_io_packed(int vid,
    uint16_t vring_idx, uint16_t head);

int
rte_vhost_clr_inflight_desc_split(int vid, uint16_t vring_idx,
    uint16_t last_used_idx, uint16_t idx);

int
rte_vhost_clr_inflight_desc_packed(int vid, uint16_t vring_idx,
    uint16_t head);

int rte_vhost_vring_call(int vid, uint16_t vring_idx);

__rte_experimental
int rte_vhost_vring_call_nonblock(int vid, uint16_t vring_idx);

uint32_t rte_vhost_rx_queue_count(int vid, uint16_t qid);

__rte_experimental
int
rte_vhost_get_monitor_addr(int vid, uint16_t queue_id,
        struct rte_vhost_power_monitor_cond *pmc);

int
rte_vhost_get_log_base(int vid, uint64_t *log_base, uint64_t *log_size);

int
rte_vhost_get_vring_base(int vid, uint16_t queue_id,
        uint16_t *last_avail_idx, uint16_t *last_used_idx);

int
rte_vhost_get_vring_base_from_inflight(int vid,
    uint16_t queue_id, uint16_t *last_avail_idx, uint16_t *last_used_idx);

int
rte_vhost_set_vring_base(int vid, uint16_t queue_id,
        uint16_t last_avail_idx, uint16_t last_used_idx);

int
rte_vhost_extern_callback_register(int vid,
        struct rte_vhost_user_extern_ops const * const ops, void *ctx);

struct rte_vdpa_device *
rte_vhost_get_vdpa_device(int vid);

__rte_experimental
int
rte_vhost_backend_config_change(int vid, bool need_reply);

int
rte_vhost_vring_stats_get_names(int vid, uint16_t queue_id,
        struct rte_vhost_stat_name *name, unsigned int size);

int
rte_vhost_vring_stats_get(int vid, uint16_t queue_id,
        struct rte_vhost_stat *stats, unsigned int n);

int
rte_vhost_vring_stats_reset(int vid, uint16_t queue_id);

#ifdef __cplusplus
}
#endif

#endif /* _RTE_VHOST_H_ */