/*
* translate request into iovec + start offset
* do sanity checks along the way
*/
static int xen_block_parse_request(XenBlockRequest *request)
{
XenBlockDataPlane *dataplane = request->dataplane;
size_t len;
int i;
switch (request->req.operation) {
case BLKIF_OP_READ:
break;
case BLKIF_OP_FLUSH_DISKCACHE:
request->presync = 1;
if (!request->req.nr_segments) {
return 0;
}
/* fall through */
case BLKIF_OP_WRITE:
break;
case BLKIF_OP_DISCARD:
return 0;
default:
error_report("error: unknown operation (%d)", request->req.operation);
goto err;
};
if (request->req.operation != BLKIF_OP_READ &&
blk_is_read_only(dataplane->blk)) {
error_report("error: write req for ro device");
goto err;
}
request->start = request->req.sector_number * XEN_BLKIF_SECTOR_SIZE;
for (i = 0; i < request->req.nr_segments; i++) {
if (i == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
error_report("error: nr_segments too big");
goto err;
}
if (request->req.seg[i].first_sect > request->req.seg[i].last_sect) {
error_report("error: first > last sector");
goto err;
}
if (request->req.seg[i].last_sect * XEN_BLKIF_SECTOR_SIZE >=
XC_PAGE_SIZE) {
error_report("error: page crossing");
goto err;
}
len = (request->req.seg[i].last_sect -
request->req.seg[i].first_sect + 1) * XEN_BLKIF_SECTOR_SIZE;
request->size += len;
}
if (request->start + request->size > blk_getlength(dataplane->blk)) {
error_report("error: access beyond end of file");
goto err;
}
return 0;
err:
request->status = BLKIF_RSP_ERROR;
return -1;
}
static void m25p80_realize(SSISlave *ss, Error **errp)
{
Flash *s = M25P80(ss);
M25P80Class *mc = M25P80_GET_CLASS(s);
int ret;
s->pi = mc->pi;
s->size = s->pi->sector_size * s->pi->n_sectors;
s->dirty_page = -1;
if (s->blk) {
uint64_t perm = BLK_PERM_CONSISTENT_READ |
(blk_is_read_only(s->blk) ? 0 : BLK_PERM_WRITE);
ret = blk_set_perm(s->blk, perm, BLK_PERM_ALL, errp);
if (ret < 0) {
return;
}
DB_PRINT_L(0, "Binding to IF_MTD drive\n");
s->storage = blk_blockalign(s->blk, s->size);
if (blk_pread(s->blk, 0, s->storage, s->size) != s->size) {
error_setg(errp, "failed to read the initial flash content");
return;
}
} else {
DB_PRINT_L(0, "No BDRV - binding to RAM\n");
s->storage = blk_blockalign(NULL, s->size);
memset(s->storage, 0xFF, s->size);
}
}
static void nand_realize(DeviceState *dev, Error **errp)
{
int pagesize;
NANDFlashState *s = NAND(dev);
s->buswidth = nand_flash_ids[s->chip_id].width >> 3;
s->size = nand_flash_ids[s->chip_id].size << 20;
if (nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP) {
s->page_shift = 11;
s->erase_shift = 6;
} else {
s->page_shift = nand_flash_ids[s->chip_id].page_shift;
s->erase_shift = nand_flash_ids[s->chip_id].erase_shift;
}
switch (1 << s->page_shift) {
case 256:
nand_init_256(s);
break;
case 512:
nand_init_512(s);
break;
case 2048:
nand_init_2048(s);
break;
default:
error_setg(errp, "Unsupported NAND block size %#x\n",
1 << s->page_shift);
return;
}
pagesize = 1 << s->oob_shift;
s->mem_oob = 1;
if (s->blk) {
if (blk_is_read_only(s->blk)) {
error_setg(errp, "Can't use a read-only drive");
return;
}
if (blk_getlength(s->blk) >=
(s->pages << s->page_shift) + (s->pages << s->oob_shift)) {
pagesize = 0;
s->mem_oob = 0;
}
} else {
pagesize += 1 << s->page_shift;
}
if (pagesize) {
s->storage = (uint8_t *) memset(g_malloc(s->pages * pagesize),
0xff, s->pages * pagesize);
}
/* Give s->ioaddr a sane value in case we save state before it is used. */
s->ioaddr = s->io;
}
static void scsi_read_complete(void * opaque, int ret)
{
SCSIGenericReq *r = (SCSIGenericReq *)opaque;
SCSIDevice *s = r->req.dev;
int len;
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
if (ret || r->req.io_canceled) {
scsi_command_complete_noio(r, ret);
return;
}
len = r->io_header.dxfer_len - r->io_header.resid;
DPRINTF("Data ready tag=0x%x len=%d\n", r->req.tag, len);
r->len = -1;
if (len == 0) {
scsi_command_complete_noio(r, 0);
return;
}
/* Snoop READ CAPACITY output to set the blocksize. */
if (r->req.cmd.buf[0] == READ_CAPACITY_10 &&
(ldl_be_p(&r->buf[0]) != 0xffffffffU || s->max_lba == 0)) {
s->blocksize = ldl_be_p(&r->buf[4]);
s->max_lba = ldl_be_p(&r->buf[0]) & 0xffffffffULL;
} else if (r->req.cmd.buf[0] == SERVICE_ACTION_IN_16 &&
(r->req.cmd.buf[1] & 31) == SAI_READ_CAPACITY_16) {
s->blocksize = ldl_be_p(&r->buf[8]);
s->max_lba = ldq_be_p(&r->buf[0]);
}
blk_set_guest_block_size(s->conf.blk, s->blocksize);
/* Patch MODE SENSE device specific parameters if the BDS is opened
* readonly.
*/
if ((s->type == TYPE_DISK || s->type == TYPE_TAPE) &&
blk_is_read_only(s->conf.blk) &&
(r->req.cmd.buf[0] == MODE_SENSE ||
r->req.cmd.buf[0] == MODE_SENSE_10) &&
(r->req.cmd.buf[1] & 0x8) == 0) {
if (r->req.cmd.buf[0] == MODE_SENSE) {
r->buf[2] |= 0x80;
} else {
r->buf[3] |= 0x80;
}
}
scsi_req_data(&r->req, len);
scsi_req_unref(&r->req);
}
static inline void flash_sync_area(Flash *s, int64_t off, int64_t len)
{
QEMUIOVector *iov;
if (!s->blk || blk_is_read_only(s->blk)) {
return;
}
assert(!(len % BDRV_SECTOR_SIZE));
iov = g_new(QEMUIOVector, 1);
qemu_iovec_init(iov, 1);
qemu_iovec_add(iov, s->storage + off, len);
blk_aio_pwritev(s->blk, off, iov, 0, blk_sync_complete, iov);
}
static void flash_sync_page(Flash *s, int page)
{
QEMUIOVector *iov;
if (!s->blk || blk_is_read_only(s->blk)) {
return;
}
iov = g_new(QEMUIOVector, 1);
qemu_iovec_init(iov, 1);
qemu_iovec_add(iov, s->storage + page * s->pi->page_size,
s->pi->page_size);
blk_aio_pwritev(s->blk, page * s->pi->page_size, iov, 0,
blk_sync_complete, iov);
}
static void flash_sync_page(Flash *s, int page)
{
int blk_sector, nb_sectors;
QEMUIOVector iov;
if (!s->blk || blk_is_read_only(s->blk)) {
return;
}
blk_sector = (page * s->pi->page_size) / BDRV_SECTOR_SIZE;
nb_sectors = DIV_ROUND_UP(s->pi->page_size, BDRV_SECTOR_SIZE);
qemu_iovec_init(&iov, 1);
qemu_iovec_add(&iov, s->storage + blk_sector * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE);
blk_aio_writev(s->blk, blk_sector, &iov, nb_sectors, blk_sync_complete,
NULL);
}
static inline void flash_sync_area(Flash *s, int64_t off, int64_t len)
{
int64_t start, end, nb_sectors;
QEMUIOVector iov;
if (!s->blk || blk_is_read_only(s->blk)) {
return;
}
assert(!(len % BDRV_SECTOR_SIZE));
start = off / BDRV_SECTOR_SIZE;
end = (off + len) / BDRV_SECTOR_SIZE;
nb_sectors = end - start;
qemu_iovec_init(&iov, 1);
qemu_iovec_add(&iov, s->storage + (start * BDRV_SECTOR_SIZE),
nb_sectors * BDRV_SECTOR_SIZE);
blk_aio_writev(s->blk, start, &iov, nb_sectors, blk_sync_complete, NULL);
}
static void scsi_generic_realize(SCSIDevice *s, Error **errp)
{
int rc;
int sg_version;
struct sg_scsi_id scsiid;
if (!s->conf.blk) {
error_setg(errp, "drive property not set");
return;
}
if (blk_get_on_error(s->conf.blk, 0) != BLOCKDEV_ON_ERROR_ENOSPC) {
error_setg(errp, "Device doesn't support drive option werror");
return;
}
if (blk_get_on_error(s->conf.blk, 1) != BLOCKDEV_ON_ERROR_REPORT) {
error_setg(errp, "Device doesn't support drive option rerror");
return;
}
/* check we are using a driver managing SG_IO (version 3 and after */
rc = blk_ioctl(s->conf.blk, SG_GET_VERSION_NUM, &sg_version);
if (rc < 0) {
error_setg_errno(errp, -rc, "cannot get SG_IO version number");
if (rc != -EPERM) {
error_append_hint(errp, "Is this a SCSI device?\n");
}
return;
}
if (sg_version < 30000) {
error_setg(errp, "scsi generic interface too old");
return;
}
/* get LUN of the /dev/sg? */
if (blk_ioctl(s->conf.blk, SG_GET_SCSI_ID, &scsiid)) {
error_setg(errp, "SG_GET_SCSI_ID ioctl failed");
return;
}
if (!blkconf_apply_backend_options(&s->conf,
blk_is_read_only(s->conf.blk),
true, errp)) {
return;
}
/* define device state */
s->type = scsiid.scsi_type;
DPRINTF("device type %d\n", s->type);
switch (s->type) {
case TYPE_TAPE:
s->blocksize = get_stream_blocksize(s->conf.blk);
if (s->blocksize == -1) {
s->blocksize = 0;
}
break;
/* Make a guess for block devices, we'll fix it when the guest sends.
* READ CAPACITY. If they don't, they likely would assume these sizes
* anyway. (TODO: they could also send MODE SENSE).
*/
case TYPE_ROM:
case TYPE_WORM:
s->blocksize = 2048;
break;
default:
s->blocksize = 512;
break;
}
DPRINTF("block size %d\n", s->blocksize);
scsi_generic_read_device_identification(s);
}
static void scsi_read_complete(void * opaque, int ret)
{
SCSIGenericReq *r = (SCSIGenericReq *)opaque;
SCSIDevice *s = r->req.dev;
int len;
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
aio_context_acquire(blk_get_aio_context(s->conf.blk));
if (ret || r->req.io_canceled) {
scsi_command_complete_noio(r, ret);
goto done;
}
len = r->io_header.dxfer_len - r->io_header.resid;
DPRINTF("Data ready tag=0x%x len=%d\n", r->req.tag, len);
r->len = -1;
if (len == 0) {
scsi_command_complete_noio(r, 0);
goto done;
}
/* Snoop READ CAPACITY output to set the blocksize. */
if (r->req.cmd.buf[0] == READ_CAPACITY_10 &&
(ldl_be_p(&r->buf[0]) != 0xffffffffU || s->max_lba == 0)) {
s->blocksize = ldl_be_p(&r->buf[4]);
s->max_lba = ldl_be_p(&r->buf[0]) & 0xffffffffULL;
} else if (r->req.cmd.buf[0] == SERVICE_ACTION_IN_16 &&
(r->req.cmd.buf[1] & 31) == SAI_READ_CAPACITY_16) {
s->blocksize = ldl_be_p(&r->buf[8]);
s->max_lba = ldq_be_p(&r->buf[0]);
}
blk_set_guest_block_size(s->conf.blk, s->blocksize);
/* Patch MODE SENSE device specific parameters if the BDS is opened
* readonly.
*/
if ((s->type == TYPE_DISK || s->type == TYPE_TAPE) &&
blk_is_read_only(s->conf.blk) &&
(r->req.cmd.buf[0] == MODE_SENSE ||
r->req.cmd.buf[0] == MODE_SENSE_10) &&
(r->req.cmd.buf[1] & 0x8) == 0) {
if (r->req.cmd.buf[0] == MODE_SENSE) {
r->buf[2] |= 0x80;
} else {
r->buf[3] |= 0x80;
}
}
if (s->type == TYPE_DISK &&
r->req.cmd.buf[0] == INQUIRY &&
r->req.cmd.buf[2] == 0xb0) {
uint32_t max_transfer =
blk_get_max_transfer(s->conf.blk) / s->blocksize;
assert(max_transfer);
stl_be_p(&r->buf[8], max_transfer);
/* Also take care of the opt xfer len. */
stl_be_p(&r->buf[12],
MIN_NON_ZERO(max_transfer, ldl_be_p(&r->buf[12])));
}
scsi_req_data(&r->req, len);
scsi_req_unref(&r->req);
done:
aio_context_release(blk_get_aio_context(s->conf.blk));
}
static int blk_connect(struct XenDevice *xendev)
{
struct XenBlkDev *blkdev = container_of(xendev, struct XenBlkDev, xendev);
int index, qflags;
bool readonly = true;
bool writethrough = true;
int order, ring_ref;
unsigned int ring_size, max_grants;
unsigned int i;
trace_xen_disk_connect(xendev->name);
/* read-only ? */
if (blkdev->directiosafe) {
qflags = BDRV_O_NOCACHE | BDRV_O_NATIVE_AIO;
} else {
qflags = 0;
writethrough = false;
}
if (strcmp(blkdev->mode, "w") == 0) {
qflags |= BDRV_O_RDWR;
readonly = false;
}
if (blkdev->feature_discard) {
qflags |= BDRV_O_UNMAP;
}
/* init qemu block driver */
index = (xendev->dev - 202 * 256) / 16;
blkdev->dinfo = drive_get(IF_XEN, 0, index);
if (!blkdev->dinfo) {
Error *local_err = NULL;
QDict *options = NULL;
if (strcmp(blkdev->fileproto, "<unset>")) {
options = qdict_new();
qdict_put_str(options, "driver", blkdev->fileproto);
}
/* setup via xenbus -> create new block driver instance */
xen_pv_printf(xendev, 2, "create new bdrv (xenbus setup)\n");
blkdev->blk = blk_new_open(blkdev->filename, NULL, options,
qflags, &local_err);
if (!blkdev->blk) {
xen_pv_printf(xendev, 0, "error: %s\n",
error_get_pretty(local_err));
error_free(local_err);
return -1;
}
blk_set_enable_write_cache(blkdev->blk, !writethrough);
} else {
/* setup via qemu cmdline -> already setup for us */
xen_pv_printf(xendev, 2,
"get configured bdrv (cmdline setup)\n");
blkdev->blk = blk_by_legacy_dinfo(blkdev->dinfo);
if (blk_is_read_only(blkdev->blk) && !readonly) {
xen_pv_printf(xendev, 0, "Unexpected read-only drive");
blkdev->blk = NULL;
return -1;
}
/* blkdev->blk is not create by us, we get a reference
* so we can blk_unref() unconditionally */
blk_ref(blkdev->blk);
}
blk_attach_dev_legacy(blkdev->blk, blkdev);
blkdev->file_size = blk_getlength(blkdev->blk);
if (blkdev->file_size < 0) {
BlockDriverState *bs = blk_bs(blkdev->blk);
const char *drv_name = bs ? bdrv_get_format_name(bs) : NULL;
xen_pv_printf(xendev, 1, "blk_getlength: %d (%s) | drv %s\n",
(int)blkdev->file_size, strerror(-blkdev->file_size),
drv_name ?: "-");
blkdev->file_size = 0;
}
