qemu/hw/block/virtio-blk.c

1334 lines
43 KiB
C
Raw Normal View History

/*
* Virtio Block Device
*
* Copyright IBM, Corp. 2007
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#include "qemu/osdep.h"
2016-03-14 11:01:28 +03:00
#include "qapi/error.h"
#include "qemu/iov.h"
#include "qemu/module.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "trace.h"
#include "hw/block/block.h"
#include "hw/qdev-properties.h"
#include "sysemu/blockdev.h"
#include "sysemu/block-ram-registrar.h"
#include "sysemu/sysemu.h"
#include "sysemu/runstate.h"
#include "hw/virtio/virtio-blk.h"
#include "dataplane/virtio-blk.h"
#include "scsi/constants.h"
#ifdef __linux__
# include <scsi/sg.h>
#endif
#include "hw/virtio/virtio-bus.h"
#include "migration/qemu-file-types.h"
#include "hw/virtio/virtio-access.h"
#include "hw/virtio/virtio-blk-common.h"
#include "qemu/coroutine.h"
static void virtio_blk_init_request(VirtIOBlock *s, VirtQueue *vq,
VirtIOBlockReq *req)
{
req->dev = s;
req->vq = vq;
req->qiov.size = 0;
req->in_len = 0;
req->next = NULL;
req->mr_next = NULL;
}
static void virtio_blk_free_request(VirtIOBlockReq *req)
{
g_free(req);
}
static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
{
VirtIOBlock *s = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
trace_virtio_blk_req_complete(vdev, req, status);
stb_p(&req->in->status, status);
iov_discard_undo(&req->inhdr_undo);
iov_discard_undo(&req->outhdr_undo);
virtqueue_push(req->vq, &req->elem, req->in_len);
if (s->dataplane_started && !s->dataplane_disabled) {
virtio_blk_data_plane_notify(s->dataplane, req->vq);
} else {
virtio_notify(vdev, req->vq);
}
}
static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
bool is_read, bool acct_failed)
{
VirtIOBlock *s = req->dev;
BlockErrorAction action = blk_get_error_action(s->blk, is_read, error);
if (action == BLOCK_ERROR_ACTION_STOP) {
/* Break the link as the next request is going to be parsed from the
* ring again. Otherwise we may end up doing a double completion! */
req->mr_next = NULL;
req->next = s->rq;
s->rq = req;
} else if (action == BLOCK_ERROR_ACTION_REPORT) {
virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
if (acct_failed) {
block_acct_failed(blk_get_stats(s->blk), &req->acct);
}
virtio_blk_free_request(req);
}
blk_error_action(s->blk, action, is_read, error);
return action != BLOCK_ERROR_ACTION_IGNORE;
}
static void virtio_blk_rw_complete(void *opaque, int ret)
{
VirtIOBlockReq *next = opaque;
VirtIOBlock *s = next->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
while (next) {
VirtIOBlockReq *req = next;
next = req->mr_next;
trace_virtio_blk_rw_complete(vdev, req, ret);
if (req->qiov.nalloc != -1) {
/* If nalloc is != -1 req->qiov is a local copy of the original
* external iovec. It was allocated in submit_requests to be
* able to merge requests. */
qemu_iovec_destroy(&req->qiov);
}
if (ret) {
int p = virtio_ldl_p(VIRTIO_DEVICE(s), &req->out.type);
bool is_read = !(p & VIRTIO_BLK_T_OUT);
/* Note that memory may be dirtied on read failure. If the
* virtio request is not completed here, as is the case for
* BLOCK_ERROR_ACTION_STOP, the memory may not be copied
* correctly during live migration. While this is ugly,
* it is acceptable because the device is free to write to
* the memory until the request is completed (which will
* happen on the other side of the migration).
*/
if (virtio_blk_handle_rw_error(req, -ret, is_read, true)) {
continue;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(s->blk), &req->acct);
virtio_blk_free_request(req);
}
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static void virtio_blk_flush_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
VirtIOBlock *s = req->dev;
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
if (ret) {
if (virtio_blk_handle_rw_error(req, -ret, 0, true)) {
goto out;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(s->blk), &req->acct);
virtio_blk_free_request(req);
out:
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static void virtio_blk_discard_write_zeroes_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
VirtIOBlock *s = req->dev;
bool is_write_zeroes = (virtio_ldl_p(VIRTIO_DEVICE(s), &req->out.type) &
~VIRTIO_BLK_T_BARRIER) == VIRTIO_BLK_T_WRITE_ZEROES;
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
if (ret) {
if (virtio_blk_handle_rw_error(req, -ret, false, is_write_zeroes)) {
goto out;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
if (is_write_zeroes) {
block_acct_done(blk_get_stats(s->blk), &req->acct);
}
virtio_blk_free_request(req);
out:
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
#ifdef __linux__
typedef struct {
VirtIOBlockReq *req;
struct sg_io_hdr hdr;
} VirtIOBlockIoctlReq;
static void virtio_blk_ioctl_complete(void *opaque, int status)
{
VirtIOBlockIoctlReq *ioctl_req = opaque;
VirtIOBlockReq *req = ioctl_req->req;
VirtIOBlock *s = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
struct virtio_scsi_inhdr *scsi;
struct sg_io_hdr *hdr;
scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;
if (status) {
status = VIRTIO_BLK_S_UNSUPP;
virtio_stl_p(vdev, &scsi->errors, 255);
goto out;
}
hdr = &ioctl_req->hdr;
/*
* From SCSI-Generic-HOWTO: "Some lower level drivers (e.g. ide-scsi)
* clear the masked_status field [hence status gets cleared too, see
* block/scsi_ioctl.c] even when a CHECK_CONDITION or COMMAND_TERMINATED
* status has occurred. However they do set DRIVER_SENSE in driver_status
* field. Also a (sb_len_wr > 0) indicates there is a sense buffer.
*/
if (hdr->status == 0 && hdr->sb_len_wr > 0) {
hdr->status = CHECK_CONDITION;
}
virtio_stl_p(vdev, &scsi->errors,
hdr->status | (hdr->msg_status << 8) |
(hdr->host_status << 16) | (hdr->driver_status << 24));
virtio_stl_p(vdev, &scsi->residual, hdr->resid);
virtio_stl_p(vdev, &scsi->sense_len, hdr->sb_len_wr);
virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len);
out:
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
virtio_blk_req_complete(req, status);
virtio_blk_free_request(req);
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
g_free(ioctl_req);
}
#endif
static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s, VirtQueue *vq)
{
VirtIOBlockReq *req = virtqueue_pop(vq, sizeof(VirtIOBlockReq));
if (req) {
virtio_blk_init_request(s, vq, req);
}
return req;
}
static int virtio_blk_handle_scsi_req(VirtIOBlockReq *req)
{
int status = VIRTIO_BLK_S_OK;
struct virtio_scsi_inhdr *scsi = NULL;
VirtIOBlock *blk = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(blk);
VirtQueueElement *elem = &req->elem;
#ifdef __linux__
int i;
VirtIOBlockIoctlReq *ioctl_req;
BlockAIOCB *acb;
#endif
/*
* We require at least one output segment each for the virtio_blk_outhdr
* and the SCSI command block.
*
* We also at least require the virtio_blk_inhdr, the virtio_scsi_inhdr
* and the sense buffer pointer in the input segments.
*/
if (elem->out_num < 2 || elem->in_num < 3) {
status = VIRTIO_BLK_S_IOERR;
goto fail;
}
/*
* The scsi inhdr is placed in the second-to-last input segment, just
* before the regular inhdr.
*/
scsi = (void *)elem->in_sg[elem->in_num - 2].iov_base;
if (!virtio_has_feature(blk->host_features, VIRTIO_BLK_F_SCSI)) {
status = VIRTIO_BLK_S_UNSUPP;
goto fail;
}
/*
* No support for bidirection commands yet.
*/
if (elem->out_num > 2 && elem->in_num > 3) {
status = VIRTIO_BLK_S_UNSUPP;
goto fail;
}
#ifdef __linux__
ioctl_req = g_new0(VirtIOBlockIoctlReq, 1);
ioctl_req->req = req;
ioctl_req->hdr.interface_id = 'S';
ioctl_req->hdr.cmd_len = elem->out_sg[1].iov_len;
ioctl_req->hdr.cmdp = elem->out_sg[1].iov_base;
ioctl_req->hdr.dxfer_len = 0;
if (elem->out_num > 2) {
/*
* If there are more than the minimally required 2 output segments
* there is write payload starting from the third iovec.
*/
ioctl_req->hdr.dxfer_direction = SG_DXFER_TO_DEV;
ioctl_req->hdr.iovec_count = elem->out_num - 2;
for (i = 0; i < ioctl_req->hdr.iovec_count; i++) {
ioctl_req->hdr.dxfer_len += elem->out_sg[i + 2].iov_len;
}
ioctl_req->hdr.dxferp = elem->out_sg + 2;
} else if (elem->in_num > 3) {
/*
* If we have more than 3 input segments the guest wants to actually
* read data.
*/
ioctl_req->hdr.dxfer_direction = SG_DXFER_FROM_DEV;
ioctl_req->hdr.iovec_count = elem->in_num - 3;
for (i = 0; i < ioctl_req->hdr.iovec_count; i++) {
ioctl_req->hdr.dxfer_len += elem->in_sg[i].iov_len;
}
ioctl_req->hdr.dxferp = elem->in_sg;
} else {
/*
* Some SCSI commands don't actually transfer any data.
*/
ioctl_req->hdr.dxfer_direction = SG_DXFER_NONE;
}
ioctl_req->hdr.sbp = elem->in_sg[elem->in_num - 3].iov_base;
ioctl_req->hdr.mx_sb_len = elem->in_sg[elem->in_num - 3].iov_len;
acb = blk_aio_ioctl(blk->blk, SG_IO, &ioctl_req->hdr,
virtio_blk_ioctl_complete, ioctl_req);
if (!acb) {
g_free(ioctl_req);
status = VIRTIO_BLK_S_UNSUPP;
goto fail;
}
return -EINPROGRESS;
#else
abort();
#endif
fail:
/* Just put anything nonzero so that the ioctl fails in the guest. */
if (scsi) {
virtio_stl_p(vdev, &scsi->errors, 255);
}
return status;
}
static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
{
int status;
status = virtio_blk_handle_scsi_req(req);
if (status != -EINPROGRESS) {
virtio_blk_req_complete(req, status);
virtio_blk_free_request(req);
}
}
static inline void submit_requests(VirtIOBlock *s, MultiReqBuffer *mrb,
int start, int num_reqs, int niov)
{
BlockBackend *blk = s->blk;
QEMUIOVector *qiov = &mrb->reqs[start]->qiov;
int64_t sector_num = mrb->reqs[start]->sector_num;
bool is_write = mrb->is_write;
BdrvRequestFlags flags = 0;
if (num_reqs > 1) {
int i;
struct iovec *tmp_iov = qiov->iov;
int tmp_niov = qiov->niov;
/* mrb->reqs[start]->qiov was initialized from external so we can't
* modify it here. We need to initialize it locally and then add the
* external iovecs. */
qemu_iovec_init(qiov, niov);
for (i = 0; i < tmp_niov; i++) {
qemu_iovec_add(qiov, tmp_iov[i].iov_base, tmp_iov[i].iov_len);
}
for (i = start + 1; i < start + num_reqs; i++) {
qemu_iovec_concat(qiov, &mrb->reqs[i]->qiov, 0,
mrb->reqs[i]->qiov.size);
mrb->reqs[i - 1]->mr_next = mrb->reqs[i];
}
trace_virtio_blk_submit_multireq(VIRTIO_DEVICE(mrb->reqs[start]->dev),
mrb, start, num_reqs,
sector_num << BDRV_SECTOR_BITS,
qiov->size, is_write);
block_acct_merge_done(blk_get_stats(blk),
is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ,
num_reqs - 1);
}
if (blk_ram_registrar_ok(&s->blk_ram_registrar)) {
flags |= BDRV_REQ_REGISTERED_BUF;
}
if (is_write) {
blk_aio_pwritev(blk, sector_num << BDRV_SECTOR_BITS, qiov,
flags, virtio_blk_rw_complete,
mrb->reqs[start]);
} else {
blk_aio_preadv(blk, sector_num << BDRV_SECTOR_BITS, qiov,
flags, virtio_blk_rw_complete,
mrb->reqs[start]);
}
}
static int multireq_compare(const void *a, const void *b)
{
const VirtIOBlockReq *req1 = *(VirtIOBlockReq **)a,
*req2 = *(VirtIOBlockReq **)b;
/*
* Note that we can't simply subtract sector_num1 from sector_num2
* here as that could overflow the return value.
*/
if (req1->sector_num > req2->sector_num) {
return 1;
} else if (req1->sector_num < req2->sector_num) {
return -1;
} else {
return 0;
}
}
static void virtio_blk_submit_multireq(VirtIOBlock *s, MultiReqBuffer *mrb)
{
int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0;
uint32_t max_transfer;
int64_t sector_num = 0;
if (mrb->num_reqs == 1) {
submit_requests(s, mrb, 0, 1, -1);
mrb->num_reqs = 0;
return;
}
max_transfer = blk_get_max_transfer(mrb->reqs[0]->dev->blk);
qsort(mrb->reqs, mrb->num_reqs, sizeof(*mrb->reqs),
&multireq_compare);
for (i = 0; i < mrb->num_reqs; i++) {
VirtIOBlockReq *req = mrb->reqs[i];
if (num_reqs > 0) {
/*
* NOTE: We cannot merge the requests in below situations:
* 1. requests are not sequential
* 2. merge would exceed maximum number of IOVs
* 3. merge would exceed maximum transfer length of backend device
*/
if (sector_num + nb_sectors != req->sector_num ||
niov > blk_get_max_iov(s->blk) - req->qiov.niov ||
req->qiov.size > max_transfer ||
nb_sectors > (max_transfer -
req->qiov.size) / BDRV_SECTOR_SIZE) {
submit_requests(s, mrb, start, num_reqs, niov);
num_reqs = 0;
}
}
if (num_reqs == 0) {
sector_num = req->sector_num;
nb_sectors = niov = 0;
start = i;
}
nb_sectors += req->qiov.size / BDRV_SECTOR_SIZE;
niov += req->qiov.niov;
num_reqs++;
}
submit_requests(s, mrb, start, num_reqs, niov);
mrb->num_reqs = 0;
}
static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
VirtIOBlock *s = req->dev;
block_acct_start(blk_get_stats(s->blk), &req->acct, 0,
BLOCK_ACCT_FLUSH);
/*
* Make sure all outstanding writes are posted to the backing device.
*/
if (mrb->is_write && mrb->num_reqs > 0) {
virtio_blk_submit_multireq(s, mrb);
}
blk_aio_flush(s->blk, virtio_blk_flush_complete, req);
}
static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
uint64_t sector, size_t size)
{
uint64_t nb_sectors = size >> BDRV_SECTOR_BITS;
uint64_t total_sectors;
if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
return false;
}
if (sector & dev->sector_mask) {
return false;
}
if (size % dev->conf.conf.logical_block_size) {
return false;
}
blk_get_geometry(dev->blk, &total_sectors);
if (sector > total_sectors || nb_sectors > total_sectors - sector) {
return false;
}
return true;
}
static uint8_t virtio_blk_handle_discard_write_zeroes(VirtIOBlockReq *req,
struct virtio_blk_discard_write_zeroes *dwz_hdr, bool is_write_zeroes)
{
VirtIOBlock *s = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
uint64_t sector;
uint32_t num_sectors, flags, max_sectors;
uint8_t err_status;
int bytes;
sector = virtio_ldq_p(vdev, &dwz_hdr->sector);
num_sectors = virtio_ldl_p(vdev, &dwz_hdr->num_sectors);
flags = virtio_ldl_p(vdev, &dwz_hdr->flags);
max_sectors = is_write_zeroes ? s->conf.max_write_zeroes_sectors :
s->conf.max_discard_sectors;
/*
* max_sectors is at most BDRV_REQUEST_MAX_SECTORS, this check
* make us sure that "num_sectors << BDRV_SECTOR_BITS" can fit in
* the integer variable.
*/
if (unlikely(num_sectors > max_sectors)) {
err_status = VIRTIO_BLK_S_IOERR;
goto err;
}
bytes = num_sectors << BDRV_SECTOR_BITS;
if (unlikely(!virtio_blk_sect_range_ok(s, sector, bytes))) {
err_status = VIRTIO_BLK_S_IOERR;
goto err;
}
/*
* The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for discard
* and write zeroes commands if any unknown flag is set.
*/
if (unlikely(flags & ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) {
err_status = VIRTIO_BLK_S_UNSUPP;
goto err;
}
if (is_write_zeroes) { /* VIRTIO_BLK_T_WRITE_ZEROES */
int blk_aio_flags = 0;
if (flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) {
blk_aio_flags |= BDRV_REQ_MAY_UNMAP;
}
block_acct_start(blk_get_stats(s->blk), &req->acct, bytes,
BLOCK_ACCT_WRITE);
blk_aio_pwrite_zeroes(s->blk, sector << BDRV_SECTOR_BITS,
bytes, blk_aio_flags,
virtio_blk_discard_write_zeroes_complete, req);
} else { /* VIRTIO_BLK_T_DISCARD */
/*
* The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for
* discard commands if the unmap flag is set.
*/
if (unlikely(flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) {
err_status = VIRTIO_BLK_S_UNSUPP;
goto err;
}
blk_aio_pdiscard(s->blk, sector << BDRV_SECTOR_BITS, bytes,
virtio_blk_discard_write_zeroes_complete, req);
}
return VIRTIO_BLK_S_OK;
err:
if (is_write_zeroes) {
block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_WRITE);
}
return err_status;
}
static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
uint32_t type;
struct iovec *in_iov = req->elem.in_sg;
struct iovec *out_iov = req->elem.out_sg;
unsigned in_num = req->elem.in_num;
unsigned out_num = req->elem.out_num;
VirtIOBlock *s = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
if (req->elem.out_num < 1 || req->elem.in_num < 1) {
virtio_error(vdev, "virtio-blk missing headers");
return -1;
}
if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out,
sizeof(req->out)) != sizeof(req->out))) {
virtio_error(vdev, "virtio-blk request outhdr too short");
return -1;
}
iov_discard_front_undoable(&out_iov, &out_num, sizeof(req->out),
&req->outhdr_undo);
if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
virtio_error(vdev, "virtio-blk request inhdr too short");
iov_discard_undo(&req->outhdr_undo);
return -1;
}
/* We always touch the last byte, so just see how big in_iov is. */
req->in_len = iov_size(in_iov, in_num);
req->in = (void *)in_iov[in_num - 1].iov_base
+ in_iov[in_num - 1].iov_len
- sizeof(struct virtio_blk_inhdr);
iov_discard_back_undoable(in_iov, &in_num, sizeof(struct virtio_blk_inhdr),
&req->inhdr_undo);
type = virtio_ldl_p(vdev, &req->out.type);
/* VIRTIO_BLK_T_OUT defines the command direction. VIRTIO_BLK_T_BARRIER
* is an optional flag. Although a guest should not send this flag if
* not negotiated we ignored it in the past. So keep ignoring it. */
switch (type & ~(VIRTIO_BLK_T_OUT | VIRTIO_BLK_T_BARRIER)) {
case VIRTIO_BLK_T_IN:
{
bool is_write = type & VIRTIO_BLK_T_OUT;
req->sector_num = virtio_ldq_p(vdev, &req->out.sector);
if (is_write) {
qemu_iovec_init_external(&req->qiov, out_iov, out_num);
trace_virtio_blk_handle_write(vdev, req, req->sector_num,
req->qiov.size / BDRV_SECTOR_SIZE);
} else {
qemu_iovec_init_external(&req->qiov, in_iov, in_num);
trace_virtio_blk_handle_read(vdev, req, req->sector_num,
req->qiov.size / BDRV_SECTOR_SIZE);
}
if (!virtio_blk_sect_range_ok(s, req->sector_num, req->qiov.size)) {
virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
block_acct_invalid(blk_get_stats(s->blk),
is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
virtio_blk_free_request(req);
return 0;
}
block_acct_start(blk_get_stats(s->blk), &req->acct, req->qiov.size,
is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
/* merge would exceed maximum number of requests or IO direction
* changes */
if (mrb->num_reqs > 0 && (mrb->num_reqs == VIRTIO_BLK_MAX_MERGE_REQS ||
is_write != mrb->is_write ||
!s->conf.request_merging)) {
virtio_blk_submit_multireq(s, mrb);
}
assert(mrb->num_reqs < VIRTIO_BLK_MAX_MERGE_REQS);
mrb->reqs[mrb->num_reqs++] = req;
mrb->is_write = is_write;
break;
}
case VIRTIO_BLK_T_FLUSH:
virtio_blk_handle_flush(req, mrb);
break;
case VIRTIO_BLK_T_SCSI_CMD:
virtio_blk_handle_scsi(req);
break;
case VIRTIO_BLK_T_GET_ID:
{
/*
* NB: per existing s/n string convention the string is
* terminated by '\0' only when shorter than buffer.
*/
const char *serial = s->conf.serial ? s->conf.serial : "";
size_t size = MIN(strlen(serial) + 1,
MIN(iov_size(in_iov, in_num),
VIRTIO_BLK_ID_BYTES));
iov_from_buf(in_iov, in_num, 0, serial, size);
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
virtio_blk_free_request(req);
break;
}
/*
* VIRTIO_BLK_T_DISCARD and VIRTIO_BLK_T_WRITE_ZEROES are defined with
* VIRTIO_BLK_T_OUT flag set. We masked this flag in the switch statement,
* so we must mask it for these requests, then we will check if it is set.
*/
case VIRTIO_BLK_T_DISCARD & ~VIRTIO_BLK_T_OUT:
case VIRTIO_BLK_T_WRITE_ZEROES & ~VIRTIO_BLK_T_OUT:
{
struct virtio_blk_discard_write_zeroes dwz_hdr;
size_t out_len = iov_size(out_iov, out_num);
bool is_write_zeroes = (type & ~VIRTIO_BLK_T_BARRIER) ==
VIRTIO_BLK_T_WRITE_ZEROES;
uint8_t err_status;
/*
* Unsupported if VIRTIO_BLK_T_OUT is not set or the request contains
* more than one segment.
*/
if (unlikely(!(type & VIRTIO_BLK_T_OUT) ||
out_len > sizeof(dwz_hdr))) {
virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
virtio_blk_free_request(req);
return 0;
}
if (unlikely(iov_to_buf(out_iov, out_num, 0, &dwz_hdr,
sizeof(dwz_hdr)) != sizeof(dwz_hdr))) {
iov_discard_undo(&req->inhdr_undo);
iov_discard_undo(&req->outhdr_undo);
virtio_error(vdev, "virtio-blk discard/write_zeroes header"
" too short");
return -1;
}
err_status = virtio_blk_handle_discard_write_zeroes(req, &dwz_hdr,
is_write_zeroes);
if (err_status != VIRTIO_BLK_S_OK) {
virtio_blk_req_complete(req, err_status);
virtio_blk_free_request(req);
}
break;
}
default:
virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
virtio_blk_free_request(req);
}
return 0;
}
void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq)
{
VirtIOBlockReq *req;
MultiReqBuffer mrb = {};
bool suppress_notifications = virtio_queue_get_notification(vq);
aio_context_acquire(blk_get_aio_context(s->blk));
blk_io_plug(s->blk);
do {
if (suppress_notifications) {
virtio_queue_set_notification(vq, 0);
}
while ((req = virtio_blk_get_request(s, vq))) {
if (virtio_blk_handle_request(req, &mrb)) {
virtqueue_detach_element(req->vq, &req->elem, 0);
virtio_blk_free_request(req);
break;
}
}
if (suppress_notifications) {
virtio_queue_set_notification(vq, 1);
}
} while (!virtio_queue_empty(vq));
if (mrb.num_reqs) {
virtio_blk_submit_multireq(s, &mrb);
}
blk_io_unplug(s->blk);
aio_context_release(blk_get_aio_context(s->blk));
}
static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBlock *s = (VirtIOBlock *)vdev;
if (s->dataplane && !s->dataplane_started) {
/* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
* dataplane here instead of waiting for .set_status().
*/
virtio_device_start_ioeventfd(vdev);
if (!s->dataplane_disabled) {
return;
}
}
virtio_blk_handle_vq(s, vq);
}
virtio-blk: simplify virtio_blk_dma_restart_cb() virtio_blk_dma_restart_cb() is tricky because the BH must deal with virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() being called. There are two issues with the code: 1. virtio_blk_realize() should use qdev_add_vm_change_state_handler() instead of qemu_add_vm_change_state_handler(). This ensures the ordering with virtio_init()'s vm change state handler that calls virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() is well-defined. Then blk's AioContext is guaranteed to be up-to-date in virtio_blk_dma_restart_cb() and it's no longer necessary to have a special case for virtio_blk_data_plane_start(). 2. Only blk_drain() waits for virtio_blk_dma_restart_cb()'s blk_inc_in_flight() to be decremented. The bdrv_drain() family of functions do not wait for BlockBackend's in_flight counter to reach zero. virtio_blk_data_plane_stop() relies on blk_set_aio_context()'s implicit drain, but that's a bdrv_drain() and not a blk_drain(). Note that virtio_blk_reset() already correctly relies on blk_drain(). If virtio_blk_data_plane_stop() switches to blk_drain() then we can properly wait for pending virtio_blk_dma_restart_bh() calls. Once these issues are taken care of the code becomes simpler. This change is in preparation for multiple IOThreads in virtio-blk where we need to clean up the multi-threading behavior. I ran the reproducer from commit 49b44549ace7 ("virtio-blk: On restart, process queued requests in the proper context") to check that there is no regression. Cc: Sergio Lopez <slp@redhat.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-id: 20221102182337.252202-1-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2022-11-02 21:23:37 +03:00
static void virtio_blk_dma_restart_bh(void *opaque)
{
virtio-blk: simplify virtio_blk_dma_restart_cb() virtio_blk_dma_restart_cb() is tricky because the BH must deal with virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() being called. There are two issues with the code: 1. virtio_blk_realize() should use qdev_add_vm_change_state_handler() instead of qemu_add_vm_change_state_handler(). This ensures the ordering with virtio_init()'s vm change state handler that calls virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() is well-defined. Then blk's AioContext is guaranteed to be up-to-date in virtio_blk_dma_restart_cb() and it's no longer necessary to have a special case for virtio_blk_data_plane_start(). 2. Only blk_drain() waits for virtio_blk_dma_restart_cb()'s blk_inc_in_flight() to be decremented. The bdrv_drain() family of functions do not wait for BlockBackend's in_flight counter to reach zero. virtio_blk_data_plane_stop() relies on blk_set_aio_context()'s implicit drain, but that's a bdrv_drain() and not a blk_drain(). Note that virtio_blk_reset() already correctly relies on blk_drain(). If virtio_blk_data_plane_stop() switches to blk_drain() then we can properly wait for pending virtio_blk_dma_restart_bh() calls. Once these issues are taken care of the code becomes simpler. This change is in preparation for multiple IOThreads in virtio-blk where we need to clean up the multi-threading behavior. I ran the reproducer from commit 49b44549ace7 ("virtio-blk: On restart, process queued requests in the proper context") to check that there is no regression. Cc: Sergio Lopez <slp@redhat.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-id: 20221102182337.252202-1-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2022-11-02 21:23:37 +03:00
VirtIOBlock *s = opaque;
VirtIOBlockReq *req = s->rq;
MultiReqBuffer mrb = {};
s->rq = NULL;
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
while (req) {
VirtIOBlockReq *next = req->next;
if (virtio_blk_handle_request(req, &mrb)) {
/* Device is now broken and won't do any processing until it gets
* reset. Already queued requests will be lost: let's purge them.
*/
while (req) {
next = req->next;
virtqueue_detach_element(req->vq, &req->elem, 0);
virtio_blk_free_request(req);
req = next;
}
break;
}
req = next;
}
if (mrb.num_reqs) {
virtio_blk_submit_multireq(s, &mrb);
}
virtio-blk: simplify virtio_blk_dma_restart_cb() virtio_blk_dma_restart_cb() is tricky because the BH must deal with virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() being called. There are two issues with the code: 1. virtio_blk_realize() should use qdev_add_vm_change_state_handler() instead of qemu_add_vm_change_state_handler(). This ensures the ordering with virtio_init()'s vm change state handler that calls virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() is well-defined. Then blk's AioContext is guaranteed to be up-to-date in virtio_blk_dma_restart_cb() and it's no longer necessary to have a special case for virtio_blk_data_plane_start(). 2. Only blk_drain() waits for virtio_blk_dma_restart_cb()'s blk_inc_in_flight() to be decremented. The bdrv_drain() family of functions do not wait for BlockBackend's in_flight counter to reach zero. virtio_blk_data_plane_stop() relies on blk_set_aio_context()'s implicit drain, but that's a bdrv_drain() and not a blk_drain(). Note that virtio_blk_reset() already correctly relies on blk_drain(). If virtio_blk_data_plane_stop() switches to blk_drain() then we can properly wait for pending virtio_blk_dma_restart_bh() calls. Once these issues are taken care of the code becomes simpler. This change is in preparation for multiple IOThreads in virtio-blk where we need to clean up the multi-threading behavior. I ran the reproducer from commit 49b44549ace7 ("virtio-blk: On restart, process queued requests in the proper context") to check that there is no regression. Cc: Sergio Lopez <slp@redhat.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-id: 20221102182337.252202-1-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2022-11-02 21:23:37 +03:00
/* Paired with inc in virtio_blk_dma_restart_cb() */
blk_dec_in_flight(s->conf.conf.blk);
virtio-blk: simplify virtio_blk_dma_restart_cb() virtio_blk_dma_restart_cb() is tricky because the BH must deal with virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() being called. There are two issues with the code: 1. virtio_blk_realize() should use qdev_add_vm_change_state_handler() instead of qemu_add_vm_change_state_handler(). This ensures the ordering with virtio_init()'s vm change state handler that calls virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() is well-defined. Then blk's AioContext is guaranteed to be up-to-date in virtio_blk_dma_restart_cb() and it's no longer necessary to have a special case for virtio_blk_data_plane_start(). 2. Only blk_drain() waits for virtio_blk_dma_restart_cb()'s blk_inc_in_flight() to be decremented. The bdrv_drain() family of functions do not wait for BlockBackend's in_flight counter to reach zero. virtio_blk_data_plane_stop() relies on blk_set_aio_context()'s implicit drain, but that's a bdrv_drain() and not a blk_drain(). Note that virtio_blk_reset() already correctly relies on blk_drain(). If virtio_blk_data_plane_stop() switches to blk_drain() then we can properly wait for pending virtio_blk_dma_restart_bh() calls. Once these issues are taken care of the code becomes simpler. This change is in preparation for multiple IOThreads in virtio-blk where we need to clean up the multi-threading behavior. I ran the reproducer from commit 49b44549ace7 ("virtio-blk: On restart, process queued requests in the proper context") to check that there is no regression. Cc: Sergio Lopez <slp@redhat.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-id: 20221102182337.252202-1-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2022-11-02 21:23:37 +03:00
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static void virtio_blk_dma_restart_cb(void *opaque, bool running,
RunState state)
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 22:33:41 +04:00
{
VirtIOBlock *s = opaque;
if (!running) {
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 22:33:41 +04:00
return;
}
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 22:33:41 +04:00
virtio-blk: simplify virtio_blk_dma_restart_cb() virtio_blk_dma_restart_cb() is tricky because the BH must deal with virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() being called. There are two issues with the code: 1. virtio_blk_realize() should use qdev_add_vm_change_state_handler() instead of qemu_add_vm_change_state_handler(). This ensures the ordering with virtio_init()'s vm change state handler that calls virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() is well-defined. Then blk's AioContext is guaranteed to be up-to-date in virtio_blk_dma_restart_cb() and it's no longer necessary to have a special case for virtio_blk_data_plane_start(). 2. Only blk_drain() waits for virtio_blk_dma_restart_cb()'s blk_inc_in_flight() to be decremented. The bdrv_drain() family of functions do not wait for BlockBackend's in_flight counter to reach zero. virtio_blk_data_plane_stop() relies on blk_set_aio_context()'s implicit drain, but that's a bdrv_drain() and not a blk_drain(). Note that virtio_blk_reset() already correctly relies on blk_drain(). If virtio_blk_data_plane_stop() switches to blk_drain() then we can properly wait for pending virtio_blk_dma_restart_bh() calls. Once these issues are taken care of the code becomes simpler. This change is in preparation for multiple IOThreads in virtio-blk where we need to clean up the multi-threading behavior. I ran the reproducer from commit 49b44549ace7 ("virtio-blk: On restart, process queued requests in the proper context") to check that there is no regression. Cc: Sergio Lopez <slp@redhat.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-id: 20221102182337.252202-1-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2022-11-02 21:23:37 +03:00
/* Paired with dec in virtio_blk_dma_restart_bh() */
blk_inc_in_flight(s->conf.conf.blk);
aio_bh_schedule_oneshot(blk_get_aio_context(s->conf.conf.blk),
virtio_blk_dma_restart_bh, s);
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 22:33:41 +04:00
}
static void virtio_blk_reset(VirtIODevice *vdev)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
AioContext *ctx;
VirtIOBlockReq *req;
ctx = blk_get_aio_context(s->blk);
aio_context_acquire(ctx);
blk_drain(s->blk);
/* We drop queued requests after blk_drain() because blk_drain() itself can
* produce them. */
while (s->rq) {
req = s->rq;
s->rq = req->next;
virtqueue_detach_element(req->vq, &req->elem, 0);
virtio_blk_free_request(req);
}
aio_context_release(ctx);
assert(!s->dataplane_started);
blk_set_enable_write_cache(s->blk, s->original_wce);
}
/* coalesce internal state, copy to pci i/o region 0
*/
static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
BlockConf *conf = &s->conf.conf;
struct virtio_blk_config blkcfg;
uint64_t capacity;
int64_t length;
int blk_size = conf->logical_block_size;
virtio-blk: add missing AioContext lock virtio_blk_update_config() calls blk_get_geometry and blk_getlength, and both functions eventually end up calling bdrv_poll_co when not running in a coroutine: - blk_getlength is a co_wrapper_mixed function - blk_get_geometry calls bdrv_get_geometry -> bdrv_nb_sectors, a co_wrapper_mixed function too Since we are not running in a coroutine, we need to take s->blk AioContext lock, otherwise bdrv_poll_co will inevitably call AIO_WAIT_WHILE and therefore try to un unlock() an AioContext lock that was never acquired. RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=2167838 Steps to reproduce the issue: simply boot a VM with -object '{"qom-type":"iothread","id":"iothread1"}' \ -blockdev '{"driver":"file","filename":"$QCOW2","aio":"native","node-name":"libvirt-1-storage","cache":{"direct":true,"no-flush":false},"auto-read-only":true,"discard":"unmap"}' \ -blockdev '{"node-name":"libvirt-1-format","read-only":false,"cache":{"direct":true,"no-flush":false},"driver":"qcow2","file":"libvirt-1-storage"}' \ -device virtio-blk-pci,iothread=iothread1,drive=libvirt-1-format,id=virtio-disk0,bootindex=1,write-cache=on and observe that it will fail not manage to boot with "qemu_mutex_unlock_impl: Operation not permitted" Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Tested-by: Lukáš Doktor <ldoktor@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20230208111148.1040083-1-eesposit@redhat.com>
2023-02-08 14:11:48 +03:00
AioContext *ctx;
ctx = blk_get_aio_context(s->blk);
aio_context_acquire(ctx);
blk_get_geometry(s->blk, &capacity);
memset(&blkcfg, 0, sizeof(blkcfg));
virtio_stq_p(vdev, &blkcfg.capacity, capacity);
virtio_stl_p(vdev, &blkcfg.seg_max,
s->conf.seg_max_adjust ? s->conf.queue_size - 2 : 128 - 2);
virtio_stw_p(vdev, &blkcfg.geometry.cylinders, conf->cyls);
virtio_stl_p(vdev, &blkcfg.blk_size, blk_size);
virtio_stw_p(vdev, &blkcfg.min_io_size, conf->min_io_size / blk_size);
virtio_stl_p(vdev, &blkcfg.opt_io_size, conf->opt_io_size / blk_size);
blkcfg.geometry.heads = conf->heads;
/*
* We must ensure that the block device capacity is a multiple of
* the logical block size. If that is not the case, let's use
* sector_mask to adopt the geometry to have a correct picture.
* For those devices where the capacity is ok for the given geometry
* we don't touch the sector value of the geometry, since some devices
* (like s390 dasd) need a specific value. Here the capacity is already
* cyls*heads*secs*blk_size and the sector value is not block size
* divided by 512 - instead it is the amount of blk_size blocks
* per track (cylinder).
*/
length = blk_getlength(s->blk);
virtio-blk: add missing AioContext lock virtio_blk_update_config() calls blk_get_geometry and blk_getlength, and both functions eventually end up calling bdrv_poll_co when not running in a coroutine: - blk_getlength is a co_wrapper_mixed function - blk_get_geometry calls bdrv_get_geometry -> bdrv_nb_sectors, a co_wrapper_mixed function too Since we are not running in a coroutine, we need to take s->blk AioContext lock, otherwise bdrv_poll_co will inevitably call AIO_WAIT_WHILE and therefore try to un unlock() an AioContext lock that was never acquired. RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=2167838 Steps to reproduce the issue: simply boot a VM with -object '{"qom-type":"iothread","id":"iothread1"}' \ -blockdev '{"driver":"file","filename":"$QCOW2","aio":"native","node-name":"libvirt-1-storage","cache":{"direct":true,"no-flush":false},"auto-read-only":true,"discard":"unmap"}' \ -blockdev '{"node-name":"libvirt-1-format","read-only":false,"cache":{"direct":true,"no-flush":false},"driver":"qcow2","file":"libvirt-1-storage"}' \ -device virtio-blk-pci,iothread=iothread1,drive=libvirt-1-format,id=virtio-disk0,bootindex=1,write-cache=on and observe that it will fail not manage to boot with "qemu_mutex_unlock_impl: Operation not permitted" Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Tested-by: Lukáš Doktor <ldoktor@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20230208111148.1040083-1-eesposit@redhat.com>
2023-02-08 14:11:48 +03:00
aio_context_release(ctx);
if (length > 0 && length / conf->heads / conf->secs % blk_size) {
blkcfg.geometry.sectors = conf->secs & ~s->sector_mask;
} else {
blkcfg.geometry.sectors = conf->secs;
}
blkcfg.size_max = 0;
blkcfg.physical_block_exp = get_physical_block_exp(conf);
blkcfg.alignment_offset = 0;
blkcfg.wce = blk_enable_write_cache(s->blk);
virtio_stw_p(vdev, &blkcfg.num_queues, s->conf.num_queues);
if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_DISCARD)) {
uint32_t discard_granularity = conf->discard_granularity;
if (discard_granularity == -1 || !s->conf.report_discard_granularity) {
discard_granularity = blk_size;
}
virtio_stl_p(vdev, &blkcfg.max_discard_sectors,
s->conf.max_discard_sectors);
virtio_stl_p(vdev, &blkcfg.discard_sector_alignment,
discard_granularity >> BDRV_SECTOR_BITS);
/*
* We support only one segment per request since multiple segments
* are not widely used and there are no userspace APIs that allow
* applications to submit multiple segments in a single call.
*/
virtio_stl_p(vdev, &blkcfg.max_discard_seg, 1);
}
if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_WRITE_ZEROES)) {
virtio_stl_p(vdev, &blkcfg.max_write_zeroes_sectors,
s->conf.max_write_zeroes_sectors);
blkcfg.write_zeroes_may_unmap = 1;
virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1);
}
memcpy(config, &blkcfg, s->config_size);
}
static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
struct virtio_blk_config blkcfg;
memcpy(&blkcfg, config, s->config_size);
aio_context_acquire(blk_get_aio_context(s->blk));
blk_set_enable_write_cache(s->blk, blkcfg.wce != 0);
aio_context_release(blk_get_aio_context(s->blk));
}
static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
Error **errp)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
/* Firstly sync all virtio-blk possible supported features */
features |= s->host_features;
virtio_add_feature(&features, VIRTIO_BLK_F_SEG_MAX);
virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
if (virtio_has_feature(features, VIRTIO_F_VERSION_1)) {
if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_SCSI)) {
error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0");
return 0;
}
} else {
virtio_clear_feature(&features, VIRTIO_F_ANY_LAYOUT);
virtio_add_feature(&features, VIRTIO_BLK_F_SCSI);
}
if (blk_enable_write_cache(s->blk) ||
(s->conf.x_enable_wce_if_config_wce &&
virtio_has_feature(features, VIRTIO_BLK_F_CONFIG_WCE))) {
virtio_add_feature(&features, VIRTIO_BLK_F_WCE);
}
if (!blk_is_writable(s->blk)) {
virtio_add_feature(&features, VIRTIO_BLK_F_RO);
}
if (s->conf.num_queues > 1) {
virtio_add_feature(&features, VIRTIO_BLK_F_MQ);
}
return features;
}
static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
if (!(status & (VIRTIO_CONFIG_S_DRIVER | VIRTIO_CONFIG_S_DRIVER_OK))) {
assert(!s->dataplane_started);
}
if (!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
return;
}
/* A guest that supports VIRTIO_BLK_F_CONFIG_WCE must be able to send
* cache flushes. Thus, the "auto writethrough" behavior is never
* necessary for guests that support the VIRTIO_BLK_F_CONFIG_WCE feature.
* Leaving it enabled would break the following sequence:
*
* Guest started with "-drive cache=writethrough"
* Guest sets status to 0
* Guest sets DRIVER bit in status field
* Guest reads host features (WCE=0, CONFIG_WCE=1)
* Guest writes guest features (WCE=0, CONFIG_WCE=1)
* Guest writes 1 to the WCE configuration field (writeback mode)
* Guest sets DRIVER_OK bit in status field
*
* s->blk would erroneously be placed in writethrough mode.
*/
if (!virtio_vdev_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE)) {
aio_context_acquire(blk_get_aio_context(s->blk));
blk_set_enable_write_cache(s->blk,
virtio_vdev_has_feature(vdev,
VIRTIO_BLK_F_WCE));
aio_context_release(blk_get_aio_context(s->blk));
}
}
static void virtio_blk_save_device(VirtIODevice *vdev, QEMUFile *f)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
VirtIOBlockReq *req = s->rq;
while (req) {
qemu_put_sbyte(f, 1);
if (s->conf.num_queues > 1) {
qemu_put_be32(f, virtio_get_queue_index(req->vq));
}
qemu_put_virtqueue_element(vdev, f, &req->elem);
req = req->next;
}
qemu_put_sbyte(f, 0);
}
static int virtio_blk_load_device(VirtIODevice *vdev, QEMUFile *f,
int version_id)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
while (qemu_get_sbyte(f)) {
unsigned nvqs = s->conf.num_queues;
unsigned vq_idx = 0;
VirtIOBlockReq *req;
if (nvqs > 1) {
vq_idx = qemu_get_be32(f);
if (vq_idx >= nvqs) {
error_report("Invalid virtqueue index in request list: %#x",
vq_idx);
return -EINVAL;
}
}
req = qemu_get_virtqueue_element(vdev, f, sizeof(VirtIOBlockReq));
virtio_blk_init_request(s, virtio_get_queue(vdev, vq_idx), req);
req->next = s->rq;
s->rq = req;
}
return 0;
}
static void virtio_resize_cb(void *opaque)
{
VirtIODevice *vdev = opaque;
assert(qemu_get_current_aio_context() == qemu_get_aio_context());
virtio_notify_config(vdev);
}
static void virtio_blk_resize(void *opaque)
{
VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
/*
* virtio_notify_config() needs to acquire the global mutex,
* so it can't be called from an iothread. Instead, schedule
* it to be run in the main context BH.
*/
aio_bh_schedule_oneshot(qemu_get_aio_context(), virtio_resize_cb, vdev);
}
static const BlockDevOps virtio_block_ops = {
.resize_cb = virtio_blk_resize,
};
static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOBlock *s = VIRTIO_BLK(dev);
VirtIOBlkConf *conf = &s->conf;
Error *err = NULL;
unsigned i;
if (!conf->conf.blk) {
error_setg(errp, "drive property not set");
return;
}
if (!blk_is_inserted(conf->conf.blk)) {
error_setg(errp, "Device needs media, but drive is empty");
return;
}
if (conf->num_queues == VIRTIO_BLK_AUTO_NUM_QUEUES) {
conf->num_queues = 1;
}
if (!conf->num_queues) {
error_setg(errp, "num-queues property must be larger than 0");
return;
}
if (conf->queue_size <= 2) {
error_setg(errp, "invalid queue-size property (%" PRIu16 "), "
"must be > 2", conf->queue_size);
return;
}
if (!is_power_of_2(conf->queue_size) ||
conf->queue_size > VIRTQUEUE_MAX_SIZE) {
error_setg(errp, "invalid queue-size property (%" PRIu16 "), "
"must be a power of 2 (max %d)",
conf->queue_size, VIRTQUEUE_MAX_SIZE);
return;
}
if (!blkconf_apply_backend_options(&conf->conf,
!blk_supports_write_perm(conf->conf.blk),
true, errp)) {
return;
}
s->original_wce = blk_enable_write_cache(conf->conf.blk);
if (!blkconf_geometry(&conf->conf, NULL, 65535, 255, 255, errp)) {
return;
}
if (!blkconf_blocksizes(&conf->conf, errp)) {
return;
}
if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_DISCARD) &&
(!conf->max_discard_sectors ||
conf->max_discard_sectors > BDRV_REQUEST_MAX_SECTORS)) {
error_setg(errp, "invalid max-discard-sectors property (%" PRIu32 ")"
", must be between 1 and %d",
conf->max_discard_sectors, (int)BDRV_REQUEST_MAX_SECTORS);
return;
}
if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_WRITE_ZEROES) &&
(!conf->max_write_zeroes_sectors ||
conf->max_write_zeroes_sectors > BDRV_REQUEST_MAX_SECTORS)) {
error_setg(errp, "invalid max-write-zeroes-sectors property (%" PRIu32
"), must be between 1 and %d",
conf->max_write_zeroes_sectors,
(int)BDRV_REQUEST_MAX_SECTORS);
return;
}
s->config_size = virtio_get_config_size(&virtio_blk_cfg_size_params,
virtio: introduce VirtIOConfigSizeParams & virtio_get_config_size This is the first step towards moving all device config size calculation logic into the virtio core code. In particular, this adds a struct that contains all the necessary information for common virtio code to be able to calculate the final config size for a device. This is expected to be used with the new virtio_get_config_size helper, which calculates the final length based on the provided host features. This builds on top of already existing code like VirtIOFeature and virtio_feature_get_config_size(), but adds additional fields, as well as sanity checking so that device-specifc code doesn't have to duplicate it. An example usage would be: static const VirtIOFeature dev_features[] = { {.flags = 1ULL << FEATURE_1_BIT, .end = endof(struct virtio_dev_config, feature_1)}, {.flags = 1ULL << FEATURE_2_BIT, .end = endof(struct virtio_dev_config, feature_2)}, {} }; static const VirtIOConfigSizeParams dev_cfg_size_params = { .min_size = DEV_BASE_CONFIG_SIZE, .max_size = sizeof(struct virtio_dev_config), .feature_sizes = dev_features }; // code inside my_dev_device_realize() size_t config_size = virtio_get_config_size(&dev_cfg_size_params, host_features); virtio_init(vdev, VIRTIO_ID_MYDEV, config_size); Currently every device is expected to write its own boilerplate from the example above in device_realize(), however, the next step of this transition is moving VirtIOConfigSizeParams into VirtioDeviceClass, so that it can be done automatically by the virtio initialization code. All of the users of virtio_feature_get_config_size have been converted to use virtio_get_config_size so it's no longer needed and is removed with this commit. Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru> Message-Id: <20220906073111.353245-2-d-tatianin@yandex-team.ru> Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2022-09-06 10:31:07 +03:00
s->host_features);
virtio_init(vdev, VIRTIO_ID_BLOCK, s->config_size);
s->blk = conf->conf.blk;
s->rq = NULL;
s->sector_mask = (s->conf.conf.logical_block_size / BDRV_SECTOR_SIZE) - 1;
for (i = 0; i < conf->num_queues; i++) {
virtio_add_queue(vdev, conf->queue_size, virtio_blk_handle_output);
}
qemu_coroutine_inc_pool_size(conf->num_queues * conf->queue_size / 2);
virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
if (err != NULL) {
error_propagate(errp, err);
for (i = 0; i < conf->num_queues; i++) {
virtio_del_queue(vdev, i);
}
virtio_cleanup(vdev);
return;
}
virtio-blk: simplify virtio_blk_dma_restart_cb() virtio_blk_dma_restart_cb() is tricky because the BH must deal with virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() being called. There are two issues with the code: 1. virtio_blk_realize() should use qdev_add_vm_change_state_handler() instead of qemu_add_vm_change_state_handler(). This ensures the ordering with virtio_init()'s vm change state handler that calls virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() is well-defined. Then blk's AioContext is guaranteed to be up-to-date in virtio_blk_dma_restart_cb() and it's no longer necessary to have a special case for virtio_blk_data_plane_start(). 2. Only blk_drain() waits for virtio_blk_dma_restart_cb()'s blk_inc_in_flight() to be decremented. The bdrv_drain() family of functions do not wait for BlockBackend's in_flight counter to reach zero. virtio_blk_data_plane_stop() relies on blk_set_aio_context()'s implicit drain, but that's a bdrv_drain() and not a blk_drain(). Note that virtio_blk_reset() already correctly relies on blk_drain(). If virtio_blk_data_plane_stop() switches to blk_drain() then we can properly wait for pending virtio_blk_dma_restart_bh() calls. Once these issues are taken care of the code becomes simpler. This change is in preparation for multiple IOThreads in virtio-blk where we need to clean up the multi-threading behavior. I ran the reproducer from commit 49b44549ace7 ("virtio-blk: On restart, process queued requests in the proper context") to check that there is no regression. Cc: Sergio Lopez <slp@redhat.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-id: 20221102182337.252202-1-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2022-11-02 21:23:37 +03:00
/*
* This must be after virtio_init() so virtio_blk_dma_restart_cb() gets
* called after ->start_ioeventfd() has already set blk's AioContext.
*/
s->change =
qdev_add_vm_change_state_handler(dev, virtio_blk_dma_restart_cb, s);
blk_ram_registrar_init(&s->blk_ram_registrar, s->blk);
blk_set_dev_ops(s->blk, &virtio_block_ops, s);
blk_iostatus_enable(s->blk);
add_boot_device_lchs(dev, "/disk@0,0",
conf->conf.lcyls,
conf->conf.lheads,
conf->conf.lsecs);
}
qdev: Unrealize must not fail Devices may have component devices and buses. Device realization may fail. Realization is recursive: a device's realize() method realizes its components, and device_set_realized() realizes its buses (which should in turn realize the devices on that bus, except bus_set_realized() doesn't implement that, yet). When realization of a component or bus fails, we need to roll back: unrealize everything we realized so far. If any of these unrealizes failed, the device would be left in an inconsistent state. Must not happen. device_set_realized() lets it happen: it ignores errors in the roll back code starting at label child_realize_fail. Since realization is recursive, unrealization must be recursive, too. But how could a partly failed unrealize be rolled back? We'd have to re-realize, which can fail. This design is fundamentally broken. device_set_realized() does not roll back at all. Instead, it keeps unrealizing, ignoring further errors. It can screw up even for a device with no buses: if the lone dc->unrealize() fails, it still unregisters vmstate, and calls listeners' unrealize() callback. bus_set_realized() does not roll back either. Instead, it stops unrealizing. Fortunately, no unrealize method can fail, as we'll see below. To fix the design error, drop parameter @errp from all the unrealize methods. Any unrealize method that uses @errp now needs an update. This leads us to unrealize() methods that can fail. Merely passing it to another unrealize method cannot cause failure, though. Here are the ones that do other things with @errp: * virtio_serial_device_unrealize() Fails when qbus_set_hotplug_handler() fails, but still does all the other work. On failure, the device would stay realized with its resources completely gone. Oops. Can't happen, because qbus_set_hotplug_handler() can't actually fail here. Pass &error_abort to qbus_set_hotplug_handler() instead. * hw/ppc/spapr_drc.c's unrealize() Fails when object_property_del() fails, but all the other work is already done. On failure, the device would stay realized with its vmstate registration gone. Oops. Can't happen, because object_property_del() can't actually fail here. Pass &error_abort to object_property_del() instead. * spapr_phb_unrealize() Fails and bails out when remove_drcs() fails, but other work is already done. On failure, the device would stay realized with some of its resources gone. Oops. remove_drcs() fails only when chassis_from_bus()'s object_property_get_uint() fails, and it can't here. Pass &error_abort to remove_drcs() instead. Therefore, no unrealize method can fail before this patch. device_set_realized()'s recursive unrealization via bus uses object_property_set_bool(). Can't drop @errp there, so pass &error_abort. We similarly unrealize with object_property_set_bool() elsewhere, always ignoring errors. Pass &error_abort instead. Several unrealize methods no longer handle errors from other unrealize methods: virtio_9p_device_unrealize(), virtio_input_device_unrealize(), scsi_qdev_unrealize(), ... Much of the deleted error handling looks wrong anyway. One unrealize methods no longer ignore such errors: usb_ehci_pci_exit(). Several realize methods no longer ignore errors when rolling back: v9fs_device_realize_common(), pci_qdev_unrealize(), spapr_phb_realize(), usb_qdev_realize(), vfio_ccw_realize(), virtio_device_realize(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20200505152926.18877-17-armbru@redhat.com>
2020-05-05 18:29:24 +03:00
static void virtio_blk_device_unrealize(DeviceState *dev)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOBlock *s = VIRTIO_BLK(dev);
VirtIOBlkConf *conf = &s->conf;
unsigned i;
blk_drain(s->blk);
del_boot_device_lchs(dev, "/disk@0,0");
virtio_blk_data_plane_destroy(s->dataplane);
s->dataplane = NULL;
for (i = 0; i < conf->num_queues; i++) {
virtio_del_queue(vdev, i);
}
qemu_coroutine_dec_pool_size(conf->num_queues * conf->queue_size / 2);
blk_ram_registrar_destroy(&s->blk_ram_registrar);
qemu_del_vm_change_state_handler(s->change);
blockdev_mark_auto_del(s->blk);
virtio_cleanup(vdev);
}
static void virtio_blk_instance_init(Object *obj)
{
VirtIOBlock *s = VIRTIO_BLK(obj);
device_add_bootindex_property(obj, &s->conf.conf.bootindex,
"bootindex", "/disk@0,0",
DEVICE(obj));
}
static const VMStateDescription vmstate_virtio_blk = {
.name = "virtio-blk",
.minimum_version_id = 2,
.version_id = 2,
.fields = (VMStateField[]) {
VMSTATE_VIRTIO_DEVICE,
VMSTATE_END_OF_LIST()
},
};
static Property virtio_blk_properties[] = {
DEFINE_BLOCK_PROPERTIES(VirtIOBlock, conf.conf),
DEFINE_BLOCK_ERROR_PROPERTIES(VirtIOBlock, conf.conf),
DEFINE_BLOCK_CHS_PROPERTIES(VirtIOBlock, conf.conf),
DEFINE_PROP_STRING("serial", VirtIOBlock, conf.serial),
DEFINE_PROP_BIT64("config-wce", VirtIOBlock, host_features,
VIRTIO_BLK_F_CONFIG_WCE, true),
#ifdef __linux__
DEFINE_PROP_BIT64("scsi", VirtIOBlock, host_features,
VIRTIO_BLK_F_SCSI, false),
#endif
DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0,
true),
DEFINE_PROP_UINT16("num-queues", VirtIOBlock, conf.num_queues,
VIRTIO_BLK_AUTO_NUM_QUEUES),
DEFINE_PROP_UINT16("queue-size", VirtIOBlock, conf.queue_size, 256),
DEFINE_PROP_BOOL("seg-max-adjust", VirtIOBlock, conf.seg_max_adjust, true),
DEFINE_PROP_LINK("iothread", VirtIOBlock, conf.iothread, TYPE_IOTHREAD,
IOThread *),
DEFINE_PROP_BIT64("discard", VirtIOBlock, host_features,
VIRTIO_BLK_F_DISCARD, true),
DEFINE_PROP_BOOL("report-discard-granularity", VirtIOBlock,
conf.report_discard_granularity, true),
DEFINE_PROP_BIT64("write-zeroes", VirtIOBlock, host_features,
VIRTIO_BLK_F_WRITE_ZEROES, true),
DEFINE_PROP_UINT32("max-discard-sectors", VirtIOBlock,
conf.max_discard_sectors, BDRV_REQUEST_MAX_SECTORS),
DEFINE_PROP_UINT32("max-write-zeroes-sectors", VirtIOBlock,
conf.max_write_zeroes_sectors, BDRV_REQUEST_MAX_SECTORS),
DEFINE_PROP_BOOL("x-enable-wce-if-config-wce", VirtIOBlock,
conf.x_enable_wce_if_config_wce, true),
DEFINE_PROP_END_OF_LIST(),
};
static void virtio_blk_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
device_class_set_props(dc, virtio_blk_properties);
dc->vmsd = &vmstate_virtio_blk;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
vdc->realize = virtio_blk_device_realize;
vdc->unrealize = virtio_blk_device_unrealize;
vdc->get_config = virtio_blk_update_config;
vdc->set_config = virtio_blk_set_config;
vdc->get_features = virtio_blk_get_features;
vdc->set_status = virtio_blk_set_status;
vdc->reset = virtio_blk_reset;
vdc->save = virtio_blk_save_device;
vdc->load = virtio_blk_load_device;
vdc->start_ioeventfd = virtio_blk_data_plane_start;
vdc->stop_ioeventfd = virtio_blk_data_plane_stop;
}
static const TypeInfo virtio_blk_info = {
.name = TYPE_VIRTIO_BLK,
.parent = TYPE_VIRTIO_DEVICE,
.instance_size = sizeof(VirtIOBlock),
.instance_init = virtio_blk_instance_init,
.class_init = virtio_blk_class_init,
};
static void virtio_register_types(void)
{
type_register_static(&virtio_blk_info);
}
type_init(virtio_register_types)