linux_dsm_epyc7002/drivers/vhost/vhost.h
Jason Wang 6b1e6cc785 vhost: new device IOTLB API
This patch tries to implement an device IOTLB for vhost. This could be
used with userspace(qemu) implementation of DMA remapping
to emulate an IOMMU for the guest.

The idea is simple, cache the translation in a software device IOTLB
(which is implemented as an interval tree) in vhost and use vhost_net
file descriptor for reporting IOTLB miss and IOTLB
update/invalidation. When vhost meets an IOTLB miss, the fault
address, size and access can be read from the file. After userspace
finishes the translation, it writes the translated address to the
vhost_net file to update the device IOTLB.

When device IOTLB is enabled by setting VIRTIO_F_IOMMU_PLATFORM all vq
addresses set by ioctl are treated as iova instead of virtual address and
the accessing can only be done through IOTLB instead of direct userspace
memory access. Before each round or vq processing, all vq metadata is
prefetched in device IOTLB to make sure no translation fault happens
during vq processing.

In most cases, virtqueues are contiguous even in virtual address space.
The IOTLB translation for virtqueue itself may make it a little
slower. We might add fast path cache on top of this patch.

Signed-off-by: Jason Wang <jasowang@redhat.com>
[mst: use virtio feature bit: VHOST_F_DEVICE_IOTLB -> VIRTIO_F_IOMMU_PLATFORM ]
[mst: fix build warnings ]
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
[ weiyj.lk: missing unlock on error ]
Signed-off-by: Wei Yongjun <weiyj.lk@gmail.com>
2016-08-02 16:53:54 +03:00

282 lines
8.1 KiB
C

#ifndef _VHOST_H
#define _VHOST_H
#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/virtio_config.h>
#include <linux/virtio_ring.h>
#include <linux/atomic.h>
struct vhost_work;
typedef void (*vhost_work_fn_t)(struct vhost_work *work);
#define VHOST_WORK_QUEUED 1
struct vhost_work {
struct llist_node node;
vhost_work_fn_t fn;
wait_queue_head_t done;
int flushing;
unsigned queue_seq;
unsigned done_seq;
unsigned long flags;
};
/* Poll a file (eventfd or socket) */
/* Note: there's nothing vhost specific about this structure. */
struct vhost_poll {
poll_table table;
wait_queue_head_t *wqh;
wait_queue_t wait;
struct vhost_work work;
unsigned long mask;
struct vhost_dev *dev;
};
void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work);
bool vhost_has_work(struct vhost_dev *dev);
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
unsigned long mask, struct vhost_dev *dev);
int vhost_poll_start(struct vhost_poll *poll, struct file *file);
void vhost_poll_stop(struct vhost_poll *poll);
void vhost_poll_flush(struct vhost_poll *poll);
void vhost_poll_queue(struct vhost_poll *poll);
void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work);
long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp);
struct vhost_log {
u64 addr;
u64 len;
};
#define START(node) ((node)->start)
#define LAST(node) ((node)->last)
struct vhost_umem_node {
struct rb_node rb;
struct list_head link;
__u64 start;
__u64 last;
__u64 size;
__u64 userspace_addr;
__u32 perm;
__u32 flags_padding;
__u64 __subtree_last;
};
struct vhost_umem {
struct rb_root umem_tree;
struct list_head umem_list;
int numem;
};
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
/* The actual ring of buffers. */
struct mutex mutex;
unsigned int num;
struct vring_desc __user *desc;
struct vring_avail __user *avail;
struct vring_used __user *used;
struct file *kick;
struct file *call;
struct file *error;
struct eventfd_ctx *call_ctx;
struct eventfd_ctx *error_ctx;
struct eventfd_ctx *log_ctx;
struct vhost_poll poll;
/* The routine to call when the Guest pings us, or timeout. */
vhost_work_fn_t handle_kick;
/* Last available index we saw. */
u16 last_avail_idx;
/* Caches available index value from user. */
u16 avail_idx;
/* Last index we used. */
u16 last_used_idx;
/* Used flags */
u16 used_flags;
/* Last used index value we have signalled on */
u16 signalled_used;
/* Last used index value we have signalled on */
bool signalled_used_valid;
/* Log writes to used structure. */
bool log_used;
u64 log_addr;
struct iovec iov[UIO_MAXIOV];
struct iovec iotlb_iov[64];
struct iovec *indirect;
struct vring_used_elem *heads;
/* Protected by virtqueue mutex. */
struct vhost_umem *umem;
struct vhost_umem *iotlb;
void *private_data;
u64 acked_features;
/* Log write descriptors */
void __user *log_base;
struct vhost_log *log;
/* Ring endianness. Defaults to legacy native endianness.
* Set to true when starting a modern virtio device. */
bool is_le;
#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
/* Ring endianness requested by userspace for cross-endian support. */
bool user_be;
#endif
u32 busyloop_timeout;
};
struct vhost_msg_node {
struct vhost_msg msg;
struct vhost_virtqueue *vq;
struct list_head node;
};
struct vhost_dev {
struct mm_struct *mm;
struct mutex mutex;
struct vhost_virtqueue **vqs;
int nvqs;
struct file *log_file;
struct eventfd_ctx *log_ctx;
struct llist_head work_list;
struct task_struct *worker;
struct vhost_umem *umem;
struct vhost_umem *iotlb;
spinlock_t iotlb_lock;
struct list_head read_list;
struct list_head pending_list;
wait_queue_head_t wait;
};
void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
long vhost_dev_set_owner(struct vhost_dev *dev);
bool vhost_dev_has_owner(struct vhost_dev *dev);
long vhost_dev_check_owner(struct vhost_dev *);
struct vhost_umem *vhost_dev_reset_owner_prepare(void);
void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_umem *);
void vhost_dev_cleanup(struct vhost_dev *, bool locked);
void vhost_dev_stop(struct vhost_dev *);
long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp);
long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp);
int vhost_vq_access_ok(struct vhost_virtqueue *vq);
int vhost_log_access_ok(struct vhost_dev *);
int vhost_get_vq_desc(struct vhost_virtqueue *,
struct iovec iov[], unsigned int iov_count,
unsigned int *out_num, unsigned int *in_num,
struct vhost_log *log, unsigned int *log_num);
void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
int vhost_vq_init_access(struct vhost_virtqueue *);
int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
unsigned count);
void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
unsigned int id, int len);
void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
struct vring_used_elem *heads, unsigned count);
void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
unsigned int log_num, u64 len);
int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
void vhost_enqueue_msg(struct vhost_dev *dev,
struct list_head *head,
struct vhost_msg_node *node);
struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
struct list_head *head);
unsigned int vhost_chr_poll(struct file *file, struct vhost_dev *dev,
poll_table *wait);
ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
int noblock);
ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
struct iov_iter *from);
int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled);
#define vq_err(vq, fmt, ...) do { \
pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
if ((vq)->error_ctx) \
eventfd_signal((vq)->error_ctx, 1);\
} while (0)
enum {
VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
(1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
(1ULL << VIRTIO_RING_F_EVENT_IDX) |
(1ULL << VHOST_F_LOG_ALL) |
(1ULL << VIRTIO_F_ANY_LAYOUT) |
(1ULL << VIRTIO_F_VERSION_1)
};
static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
{
return vq->acked_features & (1ULL << bit);
}
#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
{
return vq->is_le;
}
#else
static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
{
return virtio_legacy_is_little_endian() || vq->is_le;
}
#endif
/* Memory accessors */
static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val)
{
return __virtio16_to_cpu(vhost_is_little_endian(vq), val);
}
static inline __virtio16 cpu_to_vhost16(struct vhost_virtqueue *vq, u16 val)
{
return __cpu_to_virtio16(vhost_is_little_endian(vq), val);
}
static inline u32 vhost32_to_cpu(struct vhost_virtqueue *vq, __virtio32 val)
{
return __virtio32_to_cpu(vhost_is_little_endian(vq), val);
}
static inline __virtio32 cpu_to_vhost32(struct vhost_virtqueue *vq, u32 val)
{
return __cpu_to_virtio32(vhost_is_little_endian(vq), val);
}
static inline u64 vhost64_to_cpu(struct vhost_virtqueue *vq, __virtio64 val)
{
return __virtio64_to_cpu(vhost_is_little_endian(vq), val);
}
static inline __virtio64 cpu_to_vhost64(struct vhost_virtqueue *vq, u64 val)
{
return __cpu_to_virtio64(vhost_is_little_endian(vq), val);
}
#endif