static int coroutine_fn
raw_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
QEMUIOVector *qiov, int flags)
{
void *buf = NULL;
BlockDriver *drv;
QEMUIOVector local_qiov;
int ret;
if (bs->probed && sector_num == 0) {
/* As long as these conditions are true, we can't get partial writes to
* the probe buffer and can just directly check the request. */
QEMU_BUILD_BUG_ON(BLOCK_PROBE_BUF_SIZE != 512);
QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != 512);
if (nb_sectors == 0) {
/* qemu_iovec_to_buf() would fail, but we want to return success
* instead of -EINVAL in this case. */
return 0;
}
buf = qemu_try_blockalign(bs->file->bs, 512);
if (!buf) {
ret = -ENOMEM;
goto fail;
}
ret = qemu_iovec_to_buf(qiov, 0, buf, 512);
if (ret != 512) {
ret = -EINVAL;
goto fail;
}
drv = bdrv_probe_all(buf, 512, NULL);
if (drv != bs->drv) {
ret = -EPERM;
goto fail;
}
/* Use the checked buffer, a malicious guest might be overwriting its
* original buffer in the background. */
qemu_iovec_init(&local_qiov, qiov->niov + 1);
qemu_iovec_add(&local_qiov, buf, 512);
qemu_iovec_concat(&local_qiov, qiov, 512, qiov->size - 512);
qiov = &local_qiov;
}
BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
ret = bdrv_co_do_pwritev(bs->file->bs, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE, qiov, flags);
fail:
if (qiov == &local_qiov) {
qemu_iovec_destroy(&local_qiov);
}
qemu_vfree(buf);
return ret;
}
static int
iscsi_aio_writev_acb(IscsiAIOCB *acb)
{
struct iscsi_context *iscsi = acb->iscsilun->iscsi;
size_t size;
uint32_t num_sectors;
uint64_t lba;
#if !defined(LIBISCSI_FEATURE_IOVECTOR)
struct iscsi_data data;
#endif
int ret;
acb->canceled = 0;
acb->bh = NULL;
acb->status = -EINPROGRESS;
acb->buf = NULL;
/* this will allow us to get rid of 'buf' completely */
size = acb->nb_sectors * BDRV_SECTOR_SIZE;
#if !defined(LIBISCSI_FEATURE_IOVECTOR)
data.size = MIN(size, acb->qiov->size);
/* if the iovec only contains one buffer we can pass it directly */
if (acb->qiov->niov == 1) {
data.data = acb->qiov->iov[0].iov_base;
} else {
acb->buf = g_malloc(data.size);
qemu_iovec_to_buf(acb->qiov, 0, acb->buf, data.size);
data.data = acb->buf;
}
#endif
acb->task = malloc(sizeof(struct scsi_task));
if (acb->task == NULL) {
error_report("iSCSI: Failed to allocate task for scsi WRITE16 "
"command. %s", iscsi_get_error(iscsi));
return -1;
}
memset(acb->task, 0, sizeof(struct scsi_task));
acb->task->xfer_dir = SCSI_XFER_WRITE;
acb->task->cdb_size = 16;
acb->task->cdb[0] = 0x8a;
lba = sector_qemu2lun(acb->sector_num, acb->iscsilun);
*(uint32_t *)&acb->task->cdb[2] = htonl(lba >> 32);
*(uint32_t *)&acb->task->cdb[6] = htonl(lba & 0xffffffff);
num_sectors = sector_qemu2lun(acb->nb_sectors, acb->iscsilun);
*(uint32_t *)&acb->task->cdb[10] = htonl(num_sectors);
acb->task->expxferlen = size;
#if defined(LIBISCSI_FEATURE_IOVECTOR)
ret = iscsi_scsi_command_async(iscsi, acb->iscsilun->lun, acb->task,
iscsi_aio_write16_cb,
NULL,
acb);
#else
ret = iscsi_scsi_command_async(iscsi, acb->iscsilun->lun, acb->task,
iscsi_aio_write16_cb,
&data,
acb);
#endif
if (ret != 0) {
scsi_free_scsi_task(acb->task);
g_free(acb->buf);
return -1;
}
#if defined(LIBISCSI_FEATURE_IOVECTOR)
scsi_task_set_iov_out(acb->task, (struct scsi_iovec*) acb->qiov->iov, acb->qiov->niov);
#endif
return 0;
}
static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque,
RBDAIOCmd cmd)
{
RBDAIOCB *acb;
RADOSCB *rcb;
rbd_completion_t c;
int64_t off, size;
char *buf;
int r;
BDRVRBDState *s = bs->opaque;
acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
acb->cmd = cmd;
acb->qiov = qiov;
if (cmd == RBD_AIO_DISCARD) {
acb->bounce = NULL;
} else {
acb->bounce = qemu_blockalign(bs, qiov->size);
}
acb->ret = 0;
acb->error = 0;
acb->s = s;
acb->cancelled = 0;
acb->bh = NULL;
if (cmd == RBD_AIO_WRITE) {
qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
}
buf = acb->bounce;
off = sector_num * BDRV_SECTOR_SIZE;
size = nb_sectors * BDRV_SECTOR_SIZE;
s->qemu_aio_count++; /* All the RADOSCB */
rcb = g_malloc(sizeof(RADOSCB));
rcb->done = 0;
rcb->acb = acb;
rcb->buf = buf;
rcb->s = acb->s;
rcb->size = size;
r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
if (r < 0) {
goto failed;
}
switch (cmd) {
case RBD_AIO_WRITE:
r = rbd_aio_write(s->image, off, size, buf, c);
break;
case RBD_AIO_READ:
r = rbd_aio_read(s->image, off, size, buf, c);
break;
case RBD_AIO_DISCARD:
r = rbd_aio_discard_wrapper(s->image, off, size, c);
break;
default:
r = -EINVAL;
}
if (r < 0) {
goto failed;
}
return &acb->common;
failed:
g_free(rcb);
s->qemu_aio_count--;
qemu_aio_release(acb);
return NULL;
}
static int archipelago_submit_request(BDRVArchipelagoState *s,
uint64_t bufidx,
size_t count,
off_t offset,
ArchipelagoAIOCB *aio_cb,
ArchipelagoSegmentedRequest *segreq,
int op)
{
int ret, targetlen;
char *target;
void *data = NULL;
struct xseg_request *req;
AIORequestData *reqdata = g_new(AIORequestData, 1);
targetlen = strlen(s->volname);
req = xseg_get_request(s->xseg, s->srcport, s->vportno, X_ALLOC);
if (!req) {
archipelagolog("Cannot get XSEG request\n");
goto err_exit2;
}
ret = xseg_prep_request(s->xseg, req, targetlen, count);
if (ret < 0) {
archipelagolog("Cannot prepare XSEG request\n");
goto err_exit;
}
target = xseg_get_target(s->xseg, req);
if (!target) {
archipelagolog("Cannot get XSEG target\n");
goto err_exit;
}
memcpy(target, s->volname, targetlen);
req->size = count;
req->offset = offset;
switch (op) {
case ARCHIP_OP_READ:
req->op = X_READ;
break;
case ARCHIP_OP_WRITE:
req->op = X_WRITE;
break;
case ARCHIP_OP_FLUSH:
req->op = X_FLUSH;
break;
}
reqdata->volname = s->volname;
reqdata->offset = offset;
reqdata->size = count;
reqdata->bufidx = bufidx;
reqdata->aio_cb = aio_cb;
reqdata->segreq = segreq;
reqdata->op = op;
xseg_set_req_data(s->xseg, req, reqdata);
if (op == ARCHIP_OP_WRITE) {
data = xseg_get_data(s->xseg, req);
if (!data) {
archipelagolog("Cannot get XSEG data\n");
goto err_exit;
}
qemu_iovec_to_buf(aio_cb->qiov, bufidx, data, count);
}
xport p = xseg_submit(s->xseg, req, s->srcport, X_ALLOC);
if (p == NoPort) {
archipelagolog("Could not submit XSEG request\n");
goto err_exit;
}
xseg_signal(s->xseg, p);
return 0;
err_exit:
g_free(reqdata);
xseg_put_request(s->xseg, req, s->srcport);
return -EIO;
err_exit2:
g_free(reqdata);
return -EIO;
}
static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
int64_t off,
QEMUIOVector *qiov,
int64_t size,
BlockCompletionFunc *cb,
void *opaque,
RBDAIOCmd cmd)
{
RBDAIOCB *acb;
RADOSCB *rcb = NULL;
rbd_completion_t c;
int r;
BDRVRBDState *s = bs->opaque;
acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
acb->cmd = cmd;
acb->qiov = qiov;
assert(!qiov || qiov->size == size);
rcb = g_new(RADOSCB, 1);
if (!LIBRBD_USE_IOVEC) {
if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) {
acb->bounce = NULL;
} else {
acb->bounce = qemu_try_blockalign(bs, qiov->size);
if (acb->bounce == NULL) {
goto failed;
}
}
if (cmd == RBD_AIO_WRITE) {
qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
}
rcb->buf = acb->bounce;
}
acb->ret = 0;
acb->error = 0;
acb->s = s;
rcb->acb = acb;
rcb->s = acb->s;
rcb->size = size;
r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
if (r < 0) {
goto failed;
}
switch (cmd) {
case RBD_AIO_WRITE:
#ifdef LIBRBD_SUPPORTS_IOVEC
r = rbd_aio_writev(s->image, qiov->iov, qiov->niov, off, c);
#else
r = rbd_aio_write(s->image, off, size, rcb->buf, c);
#endif
break;
case RBD_AIO_READ:
#ifdef LIBRBD_SUPPORTS_IOVEC
r = rbd_aio_readv(s->image, qiov->iov, qiov->niov, off, c);
#else
r = rbd_aio_read(s->image, off, size, rcb->buf, c);
#endif
break;
case RBD_AIO_DISCARD:
r = rbd_aio_discard_wrapper(s->image, off, size, c);
break;
case RBD_AIO_FLUSH:
r = rbd_aio_flush_wrapper(s->image, c);
break;
default:
r = -EINVAL;
}
if (r < 0) {
goto failed_completion;
}
return &acb->common;
failed_completion:
rbd_aio_release(c);
failed:
g_free(rcb);
if (!LIBRBD_USE_IOVEC) {
qemu_vfree(acb->bounce);
}
qemu_aio_unref(acb);
return NULL;
}
static BlockDriverAIOCB *
iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
IscsiLun *iscsilun = bs->opaque;
struct iscsi_context *iscsi = iscsilun->iscsi;
IscsiAIOCB *acb;
size_t size;
uint32_t num_sectors;
uint64_t lba;
struct iscsi_data data;
acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
trace_iscsi_aio_writev(iscsi, sector_num, nb_sectors, opaque, acb);
acb->iscsilun = iscsilun;
acb->qiov = qiov;
acb->canceled = 0;
acb->bh = NULL;
acb->status = -EINPROGRESS;
/* XXX we should pass the iovec to write16 to avoid the extra copy */
/* this will allow us to get rid of 'buf' completely */
size = nb_sectors * BDRV_SECTOR_SIZE;
data.size = MIN(size, acb->qiov->size);
/* if the iovec only contains one buffer we can pass it directly */
if (acb->qiov->niov == 1) {
acb->buf = NULL;
data.data = acb->qiov->iov[0].iov_base;
} else {
acb->buf = g_malloc(data.size);
qemu_iovec_to_buf(acb->qiov, 0, acb->buf, data.size);
data.data = acb->buf;
}
acb->task = malloc(sizeof(struct scsi_task));
if (acb->task == NULL) {
error_report("iSCSI: Failed to allocate task for scsi WRITE16 "
"command. %s", iscsi_get_error(iscsi));
qemu_aio_release(acb);
return NULL;
}
memset(acb->task, 0, sizeof(struct scsi_task));
acb->task->xfer_dir = SCSI_XFER_WRITE;
acb->task->cdb_size = 16;
acb->task->cdb[0] = 0x8a;
lba = sector_qemu2lun(sector_num, iscsilun);
*(uint32_t *)&acb->task->cdb[2] = htonl(lba >> 32);
*(uint32_t *)&acb->task->cdb[6] = htonl(lba & 0xffffffff);
num_sectors = size / iscsilun->block_size;
*(uint32_t *)&acb->task->cdb[10] = htonl(num_sectors);
acb->task->expxferlen = size;
if (iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
iscsi_aio_write16_cb,
&data,
acb) != 0) {
scsi_free_scsi_task(acb->task);
g_free(acb->buf);
qemu_aio_release(acb);
return NULL;
}
iscsi_set_events(iscsilun);
return &acb->common;
}
static coroutine_fn int
block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num,
int remaining_sectors, QEMUIOVector *qiov)
{
BlockCrypto *crypto = bs->opaque;
int cur_nr_sectors; /* number of sectors in current iteration */
uint64_t bytes_done = 0;
uint8_t *cipher_data = NULL;
QEMUIOVector hd_qiov;
int ret = 0;
size_t payload_offset =
qcrypto_block_get_payload_offset(crypto->block) / 512;
qemu_iovec_init(&hd_qiov, qiov->niov);
/* Bounce buffer so we have a linear mem region for
* entire sector. XXX optimize so we avoid bounce
* buffer in case that qiov->niov == 1
*/
cipher_data =
qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512,
qiov->size));
if (cipher_data == NULL) {
ret = -ENOMEM;
goto cleanup;
}
while (remaining_sectors) {
cur_nr_sectors = remaining_sectors;
if (cur_nr_sectors > BLOCK_CRYPTO_MAX_SECTORS) {
cur_nr_sectors = BLOCK_CRYPTO_MAX_SECTORS;
}
qemu_iovec_to_buf(qiov, bytes_done,
cipher_data, cur_nr_sectors * 512);
if (qcrypto_block_encrypt(crypto->block,
sector_num,
cipher_data, cur_nr_sectors * 512,
NULL) < 0) {
ret = -EIO;
goto cleanup;
}
qemu_iovec_reset(&hd_qiov);
qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512);
ret = bdrv_co_writev(bs->file,
payload_offset + sector_num,
cur_nr_sectors, &hd_qiov);
if (ret < 0) {
goto cleanup;
}
remaining_sectors -= cur_nr_sectors;
sector_num += cur_nr_sectors;
bytes_done += cur_nr_sectors * 512;
}
cleanup:
qemu_iovec_destroy(&hd_qiov);
qemu_vfree(cipher_data);
return ret;
}
