mini-riscv-os/08-BlockDeviceDriver/virtio.c

#include "virtio.h"
#include "os.h"
#define R(addr) ((volatile uint32_t *)(VIRTIO_MMIO_BASE + (addr)))

static struct disk
{
  char pages[2 * PGSIZE];
  /* descriptor */
  virtq_desc_t *desc;
  /* AvailableRing */
  virtq_avail_t *avail;
  /* UsedRing */
  virtq_used_t *used;
  /* For decord each descriptor is free or not */
  char free[NUM];
  /* Disk command headers */
  virtio_blk_req_t ops[NUM];

  struct lock vdisk_lock;
} __attribute__((aligned(PGSIZE))) disk;

void virtio_disk_init(){
    uint32_t status = 0;

    lock_init(&disk.vdisk_lock);

    if(*R(VIRTIO_MMIO_MAGIC_VALUE) != 0x74726976 ||
     *R(VIRTIO_MMIO_VERSION) != 1 ||
     *R(VIRTIO_MMIO_DEVICE_ID) != 2 ||
     *R(VIRTIO_MMIO_VENDOR_ID) != 0x554d4551){
    panic("could not find virtio disk");
    }
    /* Set the ACKNOWLEDGE status bit to the status register. */
    status |= VIRTIO_CONFIG_S_ACKNOWLEDGE;
    *R(VIRTIO_MMIO_STATUS) = status;
    /* Set the DRIVER status bit to the status register. */
    status |= VIRTIO_CONFIG_S_DRIVER;
    *R(VIRTIO_MMIO_STATUS) = status;
    /* negotiate features */
    uint64 features = *R(VIRTIO_MMIO_DEVICE_FEATURES);
    features &= ~(1 << VIRTIO_BLK_F_RO);
    features &= ~(1 << VIRTIO_BLK_F_SCSI);
    features &= ~(1 << VIRTIO_BLK_F_CONFIG_WCE);
    features &= ~(1 << VIRTIO_BLK_F_MQ);
    features &= ~(1 << VIRTIO_F_ANY_LAYOUT);
    features &= ~(1 << VIRTIO_RING_F_EVENT_IDX);
    features &= ~(1 << VIRTIO_RING_F_INDIRECT_DESC);
    *R(VIRTIO_MMIO_DRIVER_FEATURES) = features;

    /* tell device that feature negotiation is complete. */
    status |= VIRTIO_CONFIG_S_FEATURES_OK;
    *R(VIRTIO_MMIO_STATUS) = status;

    /* tell device we're completely ready. */
    status |= VIRTIO_CONFIG_S_DRIVER_OK;
    *R(VIRTIO_MMIO_STATUS) = status;

    *R(VIRTIO_MMIO_GUEST_PAGE_SIZE) = PGSIZE;
    /* initialize queue 0. */
    *R(VIRTIO_MMIO_QUEUE_SEL) = 0;
    uint32 max = *R(VIRTIO_MMIO_QUEUE_NUM_MAX);
    if (max == 0)
      lib_puts("virtio disk has no queue 0\n");
    if (max < NUM)
      lib_puts("virtio disk max queue too short\n");
    *R(VIRTIO_MMIO_QUEUE_NUM) = NUM;
    memset(disk.pages, 0, sizeof(disk.pages));
    *R(VIRTIO_MMIO_QUEUE_PFN) = ((uint64)disk.pages) >> PGSHIFT;

    // desc = pages -- num * virtq_desc
    // avail = pages + 0x40 -- 2 * uint16, then num * uint16
    // used = pages + 4096 -- 2 * uint16, then num * vRingUsedElem

    disk.desc = (struct virtq_desc *)disk.pages;
    disk.avail = (struct virtq_avail *)(disk.pages + NUM * sizeof(struct virtq_desc));
    disk.used = (struct virtq_used *)(disk.pages + PGSIZE);

    // all NUM descriptors start out unused.
    for (int i = 0; i < NUM; i++)
      disk.free[i] = 1;
    lib_puts("Disk init work is success!\n");
}

// find a free descriptor, mark it non-free, return its index.
static int
alloc_desc()
{
  for(int i = 0; i < NUM; i++){
    if(disk.free[i]){
      disk.free[i] = 0;
      return i;
    }
  }
  return -1;
}

// mark a descriptor as free.
static void
free_desc(int i)
{
  if(i >= NUM)
    panic("free_desc 1");
  if(disk.free[i])
    panic("free_desc 2");
  disk.desc[i].addr = 0;
  disk.desc[i].len = 0;
  disk.desc[i].flags = 0;
  disk.desc[i].next = 0;
  disk.free[i] = 1;
  wakeup(&disk.free[0]);
}

// free a chain of descriptors.
static void
free_chain(int i)
{
  while(1){
    int flag = disk.desc[i].flags;
    int nxt = disk.desc[i].next;
    free_desc(i);
    if(flag & VRING_DESC_F_NEXT)
      i = nxt;
    else
      break;
  }
}

// allocate three descriptors (they need not be contiguous).
// disk transfers always use three descriptors.
static int
alloc3_desc(int *idx)
{
  for(int i = 0; i < 3; i++){
    idx[i] = alloc_desc();
    if(idx[i] < 0){
      for(int j = 0; j < i; j++)
        free_desc(idx[j]);
      return -1;
    }
  }
  return 0;
}

void
virtio_disk_rw(struct buf *b, int write)
{
  uint64 sector = b->blockno * (BSIZE / 512);

  lock_acquire(&disk.vdisk_lock);

  // the spec's Section 5.2 says that legacy block operations use
  // three descriptors: one for type/reserved/sector, one for the
  // data, one for a 1-byte status result.

  // allocate the three descriptors.
  int idx[3];
  while(1){
    if(alloc3_desc(idx) == 0) {
      break;
    }
  }

  // format the three descriptors.
  // qemu's virtio-blk.c reads them.

  struct virtio_blk_req *buf0 = &disk.ops[idx[0]];

  if(write)
    buf0->type = VIRTIO_BLK_T_OUT; // write the disk
  else
    buf0->type = VIRTIO_BLK_T_IN; // read the disk
  buf0->reserved = 0;
  buf0->sector = sector;

  disk.desc[idx[0]].addr = (uint64) buf0;
  disk.desc[idx[0]].len = sizeof(struct virtio_blk_req);
  disk.desc[idx[0]].flags = VRING_DESC_F_NEXT;
  disk.desc[idx[0]].next = idx[1];

  disk.desc[idx[1]].addr = (uint64) b->data;
  disk.desc[idx[1]].len = BSIZE;
  if(write)
    disk.desc[idx[1]].flags = 0; // device reads b->data
  else
    disk.desc[idx[1]].flags = VRING_DESC_F_WRITE; // device writes b->data
  disk.desc[idx[1]].flags |= VRING_DESC_F_NEXT;
  disk.desc[idx[1]].next = idx[2];

  disk.info[idx[0]].status = 0xff; // device writes 0 on success
  disk.desc[idx[2]].addr = (uint64) &disk.info[idx[0]].status;
  disk.desc[idx[2]].len = 1;
  disk.desc[idx[2]].flags = VRING_DESC_F_WRITE; // device writes the status
  disk.desc[idx[2]].next = 0;

  // record struct buf for virtio_disk_intr().
  b->disk = 1;
  disk.info[idx[0]].b = b;

  // tell the device the first index in our chain of descriptors.
  disk.avail->ring[disk.avail->idx % NUM] = idx[0];

  __sync_synchronize();

  // tell the device another avail ring entry is available.
  disk.avail->idx += 1; // not % NUM ...

  __sync_synchronize();

  *R(VIRTIO_MMIO_QUEUE_NOTIFY) = 0; // value is queue number

  // Wait for virtio_disk_intr() to say request has finished.
  while(b->disk == 1) {
  }

  disk.info[idx[0]].b = 0;
  free_chain(idx[0]);

  lock_free(&disk.vdisk_lock);
}

void
virtio_disk_intr()
{
  lock_acquire(&disk.vdisk_lock);

  // the device won't raise another interrupt until we tell it
  // we've seen this interrupt, which the following line does.
  // this may race with the device writing new entries to
  // the "used" ring, in which case we may process the new
  // completion entries in this interrupt, and have nothing to do
  // in the next interrupt, which is harmless.
  *R(VIRTIO_MMIO_INTERRUPT_ACK) = *R(VIRTIO_MMIO_INTERRUPT_STATUS) & 0x3;

  __sync_synchronize();

  // the device increments disk.used->idx when it
  // adds an entry to the used ring.

  while(disk.used_idx != disk.used->idx){
    __sync_synchronize();
    int id = disk.used->ring[disk.used_idx % NUM].id;

    if(disk.info[id].status != 0)
      panic("virtio_disk_intr status");

    struct buf *b = disk.info[id].b;
    b->disk = 0;   // disk is done with buf
    wakeup(b);

    disk.used_idx += 1;
  }

  lock_free(&disk.vdisk_lock);
}