ShuriZma
/
xemu
mirror of https://github.com/xemu-project/xemu.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Block layer patches 

- Add vduse-blk export
 - Dirty bitmaps: Fix and improve bitmap merge
 - gluster: correctly set max_pdiscard
 - rbd: report a better error when namespace does not exist
 - aio_wait_kick: add missing memory barrier
 - Code cleanups
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCAAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAmK10yURHGt3b2xmQHJl
 ZGhhdC5jb20ACgkQfwmycsiPL9YnXg/+J9PKsGl7hbJUFVIb4RZ3pMQ0o4xC1TbS
 OjA63RRwdJWt1gGsgLNH6kdsgz04FXiXk7XNDTe8MYn21bvznCYGFsI2EFJiit+x
 HkOYXJwAGsrfKBViq8QznosBQbwf9fOrDUlOdbnixFH/dx6DXUZM2F9ud5shiuiC
 vrP76zjUgSlHhPwL+0xsJSNxxNISv845uN9SYNpiGbZDaYLBtNbEc8NA2GMOYW45
 sCbxJDxNSFNrTT5gaZyo4KGFH9393qJSmYHJ+q53elbhje5dpmcn2c/AkIG7/UM4
 HsEWd7Gj1YbLQV6kvkefJzF4BOuZmN/b8sG+LRDjrEMHLeOw5rh2ETmkQfIdy2H3
 2U52mHqw9bMGWtds0ocOJFKw3vPZuOCJaA+ql/A0aWGO9Fjivx1cQcOVXn3jKgj5
 7riSxigK9TCTd92Qhi3j4do86mJi9NpjgawbQ5oOvKqUiq29moOwcv1hit0WVzwB
 hJp2qsrM6w00wFseyp+10vHigW7ZMNEIh4TKYLfZ15Gvy6YIG/m/oyCYF4oVM5y5
 knbsnJBRpTjLnggag86Pk8Ji+Lxi0cbv7zrbn++/S9OLQ5VMV5OpxKXHmyX2HyXa
 RCV0rMaTC3s4hy8gElDSwSeor6NBaJ9TECcit67uJ/kw1eK+omoa4hKMCgKf6qYC
 GY+NRPELJGA=
 =OuiN
 -----END PGP SIGNATURE-----

Merge tag 'for-upstream' of git://repo.or.cz/qemu/kevin into staging

Block layer patches

- Add vduse-blk export
- Dirty bitmaps: Fix and improve bitmap merge
- gluster: correctly set max_pdiscard
- rbd: report a better error when namespace does not exist
- aio_wait_kick: add missing memory barrier
- Code cleanups

# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAmK10yURHGt3b2xmQHJl
# ZGhhdC5jb20ACgkQfwmycsiPL9YnXg/+J9PKsGl7hbJUFVIb4RZ3pMQ0o4xC1TbS
# OjA63RRwdJWt1gGsgLNH6kdsgz04FXiXk7XNDTe8MYn21bvznCYGFsI2EFJiit+x
# HkOYXJwAGsrfKBViq8QznosBQbwf9fOrDUlOdbnixFH/dx6DXUZM2F9ud5shiuiC
# vrP76zjUgSlHhPwL+0xsJSNxxNISv845uN9SYNpiGbZDaYLBtNbEc8NA2GMOYW45
# sCbxJDxNSFNrTT5gaZyo4KGFH9393qJSmYHJ+q53elbhje5dpmcn2c/AkIG7/UM4
# HsEWd7Gj1YbLQV6kvkefJzF4BOuZmN/b8sG+LRDjrEMHLeOw5rh2ETmkQfIdy2H3
# 2U52mHqw9bMGWtds0ocOJFKw3vPZuOCJaA+ql/A0aWGO9Fjivx1cQcOVXn3jKgj5
# 7riSxigK9TCTd92Qhi3j4do86mJi9NpjgawbQ5oOvKqUiq29moOwcv1hit0WVzwB
# hJp2qsrM6w00wFseyp+10vHigW7ZMNEIh4TKYLfZ15Gvy6YIG/m/oyCYF4oVM5y5
# knbsnJBRpTjLnggag86Pk8Ji+Lxi0cbv7zrbn++/S9OLQ5VMV5OpxKXHmyX2HyXa
# RCV0rMaTC3s4hy8gElDSwSeor6NBaJ9TECcit67uJ/kw1eK+omoa4hKMCgKf6qYC
# GY+NRPELJGA=
# =OuiN
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 24 Jun 2022 08:07:17 AM PDT
# gpg:                using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg:                issuer "kwolf@redhat.com"
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]

* tag 'for-upstream' of git://repo.or.cz/qemu/kevin:
  vduse-blk: Add name option
  vduse-blk: Add serial option
  nbd: Drop dead code spotted by Coverity
  aio_wait_kick: add missing memory barrier
  block/gluster: correctly set max_pdiscard
  block/rbd: report a better error when namespace does not exist
  qsd: document vduse-blk exports
  libvduse: Add support for reconnecting
  vduse-blk: Add vduse-blk resize support
  vduse-blk: Implement vduse-blk export
  libvduse: Add VDUSE (vDPA Device in Userspace) library
  linux-headers: Add vduse.h
  block/export: Abstract out the logic of virtio-blk I/O process
  block/export: Fix incorrect length passed to vu_queue_push()
  block: Support passing NULL ops to blk_set_dev_ops()
  block: simplify handling of try to merge different sized bitmaps
  block: improve block_dirty_bitmap_merge(): don't allocate extra bitmap
  block: block_dirty_bitmap_merge(): fix error path
  block: get rid of blk->guest_block_size
  block: drop unused bdrv_co_drain() API

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2022-06-24 10:52:46 -07:00
parent 8b5669e40f 779d82e1d3
commit 40d5224907
43 changed files with 2851 additions and 353 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
MAINTAINERS
View File

@ -3580,6 +3580,8 @@ M: Coiby Xu <Coiby.Xu@gmail.com>
S: Maintained
F: block/export/vhost-user-blk-server.c
F: block/export/vhost-user-blk-server.h
F: block/export/virtio-blk-handler.c
F: block/export/virtio-blk-handler.h
F: include/qemu/vhost-user-server.h
F: tests/qtest/libqos/vhost-user-blk.c
F: tests/qtest/libqos/vhost-user-blk.h
@ -3592,6 +3594,13 @@ L: qemu-block@nongnu.org
S: Supported
F: block/export/fuse.c
VDUSE library and block device exports
M: Xie Yongji <xieyongji@bytedance.com>
S: Maintained
F: subprojects/libvduse/
F: block/export/vduse-blk.c
F: block/export/vduse-blk.h
Replication
M: Wen Congyang <wencongyang2@huawei.com>
M: Xie Changlong <xiechanglong.d@gmail.com>

6
block/backup.c
View File

@ -228,15 +228,13 @@ out:
static void backup_init_bcs_bitmap(BackupBlockJob *job)
{
bool ret;
uint64_t estimate;
BdrvDirtyBitmap *bcs_bitmap = block_copy_dirty_bitmap(job->bcs);
if (job->sync_mode == MIRROR_SYNC_MODE_BITMAP) {
bdrv_clear_dirty_bitmap(bcs_bitmap, NULL);
ret = bdrv_dirty_bitmap_merge_internal(bcs_bitmap, job->sync_bitmap,
NULL, true);
assert(ret);
bdrv_dirty_bitmap_merge_internal(bcs_bitmap, job->sync_bitmap, NULL,
true);
} else if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
/*
* We can't hog the coroutine to initialize this thoroughly.

12
block/block-backend.c
View File

@ -56,9 +56,6 @@ struct BlockBackend {
const BlockDevOps *dev_ops;
void *dev_opaque;
/* the block size for which the guest device expects atomicity */
int guest_block_size;
/* If the BDS tree is removed, some of its options are stored here (which
* can be used to restore those options in the new BDS on insert) */
BlockBackendRootState root_state;
@ -998,7 +995,6 @@ void blk_detach_dev(BlockBackend *blk, DeviceState *dev)
blk->dev = NULL;
blk->dev_ops = NULL;
blk->dev_opaque = NULL;
blk->guest_block_size = 512;
blk_set_perm(blk, 0, BLK_PERM_ALL, &error_abort);
blk_unref(blk);
}
@ -1062,7 +1058,7 @@ void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
blk->dev_opaque = opaque;
/* Are we currently quiesced? Should we enforce this right now? */
if (blk->quiesce_counter && ops->drained_begin) {
if (blk->quiesce_counter && ops && ops->drained_begin) {
ops->drained_begin(opaque);
}
}
@ -2100,12 +2096,6 @@ int blk_get_max_iov(BlockBackend *blk)
return blk->root->bs->bl.max_iov;
}
void blk_set_guest_block_size(BlockBackend *blk, int align)
{
IO_CODE();
blk->guest_block_size = align;
}
void *blk_try_blockalign(BlockBackend *blk, size_t size)
{
IO_CODE();

26
block/dirty-bitmap.c
View File

@ -309,10 +309,7 @@ BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap_locked(BdrvDirtyBitmap *parent,
return NULL;
}
if (!hbitmap_merge(parent->bitmap, successor->bitmap, parent->bitmap)) {
error_setg(errp, "Merging of parent and successor bitmap failed");
return NULL;
}
hbitmap_merge(parent->bitmap, successor->bitmap, parent->bitmap);
parent->disabled = successor->disabled;
parent->busy = false;
@ -912,13 +909,15 @@ bool bdrv_merge_dirty_bitmap(BdrvDirtyBitmap *dest, const BdrvDirtyBitmap *src,
goto out;
}
if (!hbitmap_can_merge(dest->bitmap, src->bitmap)) {
error_setg(errp, "Bitmaps are incompatible and can't be merged");
if (bdrv_dirty_bitmap_size(src) != bdrv_dirty_bitmap_size(dest)) {
error_setg(errp, "Bitmaps are of different sizes (destination size is %"
PRId64 ", source size is %" PRId64 ") and can't be merged",
bdrv_dirty_bitmap_size(dest), bdrv_dirty_bitmap_size(src));
goto out;
}
ret = bdrv_dirty_bitmap_merge_internal(dest, src, backup, false);
assert(ret);
bdrv_dirty_bitmap_merge_internal(dest, src, backup, false);
ret = true;
out:
bdrv_dirty_bitmaps_unlock(dest->bs);
@ -932,17 +931,16 @@ out:
/**
* bdrv_dirty_bitmap_merge_internal: merge src into dest.
* Does NOT check bitmap permissions; not suitable for use as public API.
* @dest, @src and @backup (if not NULL) must have same size.
*
* @backup: If provided, make a copy of dest here prior to merge.
* @lock: If true, lock and unlock bitmaps on the way in/out.
* returns true if the merge succeeded; false if unattempted.
*/
bool bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest,
void bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest,
const BdrvDirtyBitmap *src,
HBitmap **backup,
bool lock)
{
bool ret;
IO_CODE();
assert(!bdrv_dirty_bitmap_readonly(dest));
@ -959,9 +957,9 @@ bool bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest,
if (backup) {
*backup = dest->bitmap;
dest->bitmap = hbitmap_alloc(dest->size, hbitmap_granularity(*backup));
ret = hbitmap_merge(*backup, src->bitmap, dest->bitmap);
hbitmap_merge(*backup, src->bitmap, dest->bitmap);
} else {
ret = hbitmap_merge(dest->bitmap, src->bitmap, dest->bitmap);
hbitmap_merge(dest->bitmap, src->bitmap, dest->bitmap);
}
if (lock) {
@ -970,6 +968,4 @@ bool bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest,
bdrv_dirty_bitmaps_unlock(src->bs);
}
}
return ret;
}

6
block/export/export.c
View File

@ -26,6 +26,9 @@
#ifdef CONFIG_VHOST_USER_BLK_SERVER
#include "vhost-user-blk-server.h"
#endif
#ifdef CONFIG_VDUSE_BLK_EXPORT
#include "vduse-blk.h"
#endif
static const BlockExportDriver *blk_exp_drivers[] = {
&blk_exp_nbd,
@ -35,6 +38,9 @@ static const BlockExportDriver *blk_exp_drivers[] = {
#ifdef CONFIG_FUSE
&blk_exp_fuse,
#endif
#ifdef CONFIG_VDUSE_BLK_EXPORT
&blk_exp_vduse_blk,
#endif
};
/* Only accessed from the main thread */

7
block/export/meson.build
View File

@ -1,7 +1,12 @@
blockdev_ss.add(files('export.c'))
if have_vhost_user_blk_server
blockdev_ss.add(files('vhost-user-blk-server.c'))
blockdev_ss.add(files('vhost-user-blk-server.c', 'virtio-blk-handler.c'))
endif
blockdev_ss.add(when: fuse, if_true: files('fuse.c'))
if have_vduse_blk_export
blockdev_ss.add(files('vduse-blk.c', 'virtio-blk-handler.c'))
blockdev_ss.add(libvduse)
endif

374
block/export/vduse-blk.c Normal file
View File

@ -0,0 +1,374 @@
/*
* Export QEMU block device via VDUSE
*
* Copyright (C) 2022 Bytedance Inc. and/or its affiliates. All rights reserved.
*
* Author:
* Xie Yongji <xieyongji@bytedance.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#include <sys/eventfd.h>
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "block/export.h"
#include "qemu/error-report.h"
#include "util/block-helpers.h"
#include "subprojects/libvduse/libvduse.h"
#include "virtio-blk-handler.h"
#include "standard-headers/linux/virtio_blk.h"
#define VDUSE_DEFAULT_NUM_QUEUE 1
#define VDUSE_DEFAULT_QUEUE_SIZE 256
typedef struct VduseBlkExport {
BlockExport export;
VirtioBlkHandler handler;
VduseDev *dev;
uint16_t num_queues;
char *recon_file;
unsigned int inflight;
} VduseBlkExport;
typedef struct VduseBlkReq {
VduseVirtqElement elem;
VduseVirtq *vq;
} VduseBlkReq;
static void vduse_blk_inflight_inc(VduseBlkExport *vblk_exp)
{
vblk_exp->inflight++;
}
static void vduse_blk_inflight_dec(VduseBlkExport *vblk_exp)
{
if (--vblk_exp->inflight == 0) {
aio_wait_kick();
}
}
static void vduse_blk_req_complete(VduseBlkReq *req, size_t in_len)
{
vduse_queue_push(req->vq, &req->elem, in_len);
vduse_queue_notify(req->vq);
free(req);
}
static void coroutine_fn vduse_blk_virtio_process_req(void *opaque)
{
VduseBlkReq *req = opaque;
VduseVirtq *vq = req->vq;
VduseDev *dev = vduse_queue_get_dev(vq);
VduseBlkExport *vblk_exp = vduse_dev_get_priv(dev);
VirtioBlkHandler *handler = &vblk_exp->handler;
VduseVirtqElement *elem = &req->elem;
struct iovec *in_iov = elem->in_sg;
struct iovec *out_iov = elem->out_sg;
unsigned in_num = elem->in_num;
unsigned out_num = elem->out_num;
int in_len;
in_len = virtio_blk_process_req(handler, in_iov,
out_iov, in_num, out_num);
if (in_len < 0) {
free(req);
return;
}
vduse_blk_req_complete(req, in_len);
vduse_blk_inflight_dec(vblk_exp);
}
static void vduse_blk_vq_handler(VduseDev *dev, VduseVirtq *vq)
{
VduseBlkExport *vblk_exp = vduse_dev_get_priv(dev);
while (1) {
VduseBlkReq *req;
req = vduse_queue_pop(vq, sizeof(VduseBlkReq));
if (!req) {
break;
}
req->vq = vq;
Coroutine *co =
qemu_coroutine_create(vduse_blk_virtio_process_req, req);
vduse_blk_inflight_inc(vblk_exp);
qemu_coroutine_enter(co);
}
}
static void on_vduse_vq_kick(void *opaque)
{
VduseVirtq *vq = opaque;
VduseDev *dev = vduse_queue_get_dev(vq);
int fd = vduse_queue_get_fd(vq);
eventfd_t kick_data;
if (eventfd_read(fd, &kick_data) == -1) {
error_report("failed to read data from eventfd");
return;
}
vduse_blk_vq_handler(dev, vq);
}
static void vduse_blk_enable_queue(VduseDev *dev, VduseVirtq *vq)
{
VduseBlkExport *vblk_exp = vduse_dev_get_priv(dev);
aio_set_fd_handler(vblk_exp->export.ctx, vduse_queue_get_fd(vq),
true, on_vduse_vq_kick, NULL, NULL, NULL, vq);
/* Make sure we don't miss any kick afer reconnecting */
eventfd_write(vduse_queue_get_fd(vq), 1);
}
static void vduse_blk_disable_queue(VduseDev *dev, VduseVirtq *vq)
{
VduseBlkExport *vblk_exp = vduse_dev_get_priv(dev);
aio_set_fd_handler(vblk_exp->export.ctx, vduse_queue_get_fd(vq),
true, NULL, NULL, NULL, NULL, NULL);
}
static const VduseOps vduse_blk_ops = {
.enable_queue = vduse_blk_enable_queue,
.disable_queue = vduse_blk_disable_queue,
};
static void on_vduse_dev_kick(void *opaque)
{
VduseDev *dev = opaque;
vduse_dev_handler(dev);
}
static void vduse_blk_attach_ctx(VduseBlkExport *vblk_exp, AioContext *ctx)
{
int i;
aio_set_fd_handler(vblk_exp->export.ctx, vduse_dev_get_fd(vblk_exp->dev),
true, on_vduse_dev_kick, NULL, NULL, NULL,
vblk_exp->dev);
for (i = 0; i < vblk_exp->num_queues; i++) {
VduseVirtq *vq = vduse_dev_get_queue(vblk_exp->dev, i);
int fd = vduse_queue_get_fd(vq);
if (fd < 0) {
continue;
}
aio_set_fd_handler(vblk_exp->export.ctx, fd, true,
on_vduse_vq_kick, NULL, NULL, NULL, vq);
}
}
static void vduse_blk_detach_ctx(VduseBlkExport *vblk_exp)
{
int i;
for (i = 0; i < vblk_exp->num_queues; i++) {
VduseVirtq *vq = vduse_dev_get_queue(vblk_exp->dev, i);
int fd = vduse_queue_get_fd(vq);
if (fd < 0) {
continue;
}
aio_set_fd_handler(vblk_exp->export.ctx, fd,
true, NULL, NULL, NULL, NULL, NULL);
}
aio_set_fd_handler(vblk_exp->export.ctx, vduse_dev_get_fd(vblk_exp->dev),
true, NULL, NULL, NULL, NULL, NULL);
AIO_WAIT_WHILE(vblk_exp->export.ctx, vblk_exp->inflight > 0);
}
static void blk_aio_attached(AioContext *ctx, void *opaque)
{
VduseBlkExport *vblk_exp = opaque;
vblk_exp->export.ctx = ctx;
vduse_blk_attach_ctx(vblk_exp, ctx);
}
static void blk_aio_detach(void *opaque)
{
VduseBlkExport *vblk_exp = opaque;
vduse_blk_detach_ctx(vblk_exp);
vblk_exp->export.ctx = NULL;
}
static void vduse_blk_resize(void *opaque)
{
BlockExport *exp = opaque;
VduseBlkExport *vblk_exp = container_of(exp, VduseBlkExport, export);
struct virtio_blk_config config;
config.capacity =
cpu_to_le64(blk_getlength(exp->blk) >> VIRTIO_BLK_SECTOR_BITS);
vduse_dev_update_config(vblk_exp->dev, sizeof(config.capacity),
offsetof(struct virtio_blk_config, capacity),
(char *)&config.capacity);
}
static const BlockDevOps vduse_block_ops = {
.resize_cb = vduse_blk_resize,
};
static int vduse_blk_exp_create(BlockExport *exp, BlockExportOptions *opts,
Error **errp)
{
VduseBlkExport *vblk_exp = container_of(exp, VduseBlkExport, export);
BlockExportOptionsVduseBlk *vblk_opts = &opts->u.vduse_blk;
uint64_t logical_block_size = VIRTIO_BLK_SECTOR_SIZE;
uint16_t num_queues = VDUSE_DEFAULT_NUM_QUEUE;
uint16_t queue_size = VDUSE_DEFAULT_QUEUE_SIZE;
Error *local_err = NULL;
struct virtio_blk_config config = { 0 };
uint64_t features;
int i, ret;
if (vblk_opts->has_num_queues) {
num_queues = vblk_opts->num_queues;
if (num_queues == 0) {
error_setg(errp, "num-queues must be greater than 0");
return -EINVAL;
}
}
if (vblk_opts->has_queue_size) {
queue_size = vblk_opts->queue_size;
if (queue_size <= 2 || !is_power_of_2(queue_size) ||
queue_size > VIRTQUEUE_MAX_SIZE) {
error_setg(errp, "queue-size is invalid");
return -EINVAL;
}
}
if (vblk_opts->has_logical_block_size) {
logical_block_size = vblk_opts->logical_block_size;
check_block_size(exp->id, "logical-block-size", logical_block_size,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EINVAL;
}
}
vblk_exp->num_queues = num_queues;
vblk_exp->handler.blk = exp->blk;
vblk_exp->handler.serial = g_strdup(vblk_opts->has_serial ?
vblk_opts->serial : "");
vblk_exp->handler.logical_block_size = logical_block_size;
vblk_exp->handler.writable = opts->writable;
config.capacity =
cpu_to_le64(blk_getlength(exp->blk) >> VIRTIO_BLK_SECTOR_BITS);
config.seg_max = cpu_to_le32(queue_size - 2);
config.min_io_size = cpu_to_le16(1);
config.opt_io_size = cpu_to_le32(1);
config.num_queues = cpu_to_le16(num_queues);
config.blk_size = cpu_to_le32(logical_block_size);
config.max_discard_sectors = cpu_to_le32(VIRTIO_BLK_MAX_DISCARD_SECTORS);
config.max_discard_seg = cpu_to_le32(1);
config.discard_sector_alignment =
cpu_to_le32(logical_block_size >> VIRTIO_BLK_SECTOR_BITS);
config.max_write_zeroes_sectors =
cpu_to_le32(VIRTIO_BLK_MAX_WRITE_ZEROES_SECTORS);
config.max_write_zeroes_seg = cpu_to_le32(1);
features = vduse_get_virtio_features() |
(1ULL << VIRTIO_BLK_F_SEG_MAX) |
(1ULL << VIRTIO_BLK_F_TOPOLOGY) |
(1ULL << VIRTIO_BLK_F_BLK_SIZE) |
(1ULL << VIRTIO_BLK_F_FLUSH) |
(1ULL << VIRTIO_BLK_F_DISCARD) |
(1ULL << VIRTIO_BLK_F_WRITE_ZEROES);
if (num_queues > 1) {
features |= 1ULL << VIRTIO_BLK_F_MQ;
}
if (!opts->writable) {
features |= 1ULL << VIRTIO_BLK_F_RO;
}
vblk_exp->dev = vduse_dev_create(vblk_opts->name, VIRTIO_ID_BLOCK, 0,
features, num_queues,
sizeof(struct virtio_blk_config),
(char *)&config, &vduse_blk_ops,
vblk_exp);
if (!vblk_exp->dev) {
error_setg(errp, "failed to create vduse device");
ret = -ENOMEM;
goto err_dev;
}
vblk_exp->recon_file = g_strdup_printf("%s/vduse-blk-%s",
g_get_tmp_dir(), vblk_opts->name);
if (vduse_set_reconnect_log_file(vblk_exp->dev, vblk_exp->recon_file)) {
error_setg(errp, "failed to set reconnect log file");
ret = -EINVAL;
goto err;
}
for (i = 0; i < num_queues; i++) {
vduse_dev_setup_queue(vblk_exp->dev, i, queue_size);
}
aio_set_fd_handler(exp->ctx, vduse_dev_get_fd(vblk_exp->dev), true,
on_vduse_dev_kick, NULL, NULL, NULL, vblk_exp->dev);
blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach,
vblk_exp);
blk_set_dev_ops(exp->blk, &vduse_block_ops, exp);
return 0;
err:
vduse_dev_destroy(vblk_exp->dev);
g_free(vblk_exp->recon_file);
err_dev:
g_free(vblk_exp->handler.serial);
return ret;
}
static void vduse_blk_exp_delete(BlockExport *exp)
{
VduseBlkExport *vblk_exp = container_of(exp, VduseBlkExport, export);
int ret;
blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach,
vblk_exp);
blk_set_dev_ops(exp->blk, NULL, NULL);
ret = vduse_dev_destroy(vblk_exp->dev);
if (ret != -EBUSY) {
unlink(vblk_exp->recon_file);
}
g_free(vblk_exp->recon_file);
g_free(vblk_exp->handler.serial);
}
static void vduse_blk_exp_request_shutdown(BlockExport *exp)
{
VduseBlkExport *vblk_exp = container_of(exp, VduseBlkExport, export);
aio_context_acquire(vblk_exp->export.ctx);
vduse_blk_detach_ctx(vblk_exp);
aio_context_acquire(vblk_exp->export.ctx);
}
const BlockExportDriver blk_exp_vduse_blk = {
.type = BLOCK_EXPORT_TYPE_VDUSE_BLK,
.instance_size = sizeof(VduseBlkExport),
.create = vduse_blk_exp_create,
.delete = vduse_blk_exp_delete,
.request_shutdown = vduse_blk_exp_request_shutdown,
};

20
block/export/vduse-blk.h Normal file
View File

@ -0,0 +1,20 @@
/*
* Export QEMU block device via VDUSE
*
* Copyright (C) 2022 Bytedance Inc. and/or its affiliates. All rights reserved.
*
* Author:
* Xie Yongji <xieyongji@bytedance.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#ifndef VDUSE_BLK_H
#define VDUSE_BLK_H
#include "block/export.h"
extern const BlockExportDriver blk_exp_vduse_blk;
#endif /* VDUSE_BLK_H */

261
block/export/vhost-user-blk-server.c
View File

@ -17,31 +17,15 @@
#include "vhost-user-blk-server.h"
#include "qapi/error.h"
#include "qom/object_interfaces.h"
#include "sysemu/block-backend.h"
#include "util/block-helpers.h"
/*
* Sector units are 512 bytes regardless of the
* virtio_blk_config->blk_size value.
*/
#define VIRTIO_BLK_SECTOR_BITS 9
#define VIRTIO_BLK_SECTOR_SIZE (1ull << VIRTIO_BLK_SECTOR_BITS)
#include "virtio-blk-handler.h"
enum {
VHOST_USER_BLK_NUM_QUEUES_DEFAULT = 1,
VHOST_USER_BLK_MAX_DISCARD_SECTORS = 32768,
VHOST_USER_BLK_MAX_WRITE_ZEROES_SECTORS = 32768,
};
struct virtio_blk_inhdr {
unsigned char status;
};
typedef struct VuBlkReq {
VuVirtqElement elem;
int64_t sector_num;
size_t size;
struct virtio_blk_inhdr *in;
struct virtio_blk_outhdr out;
VuServer *server;
struct VuVirtq *vq;
} VuBlkReq;
@ -50,248 +34,44 @@ typedef struct VuBlkReq {
typedef struct {
BlockExport export;
VuServer vu_server;
uint32_t blk_size;
VirtioBlkHandler handler;
QIOChannelSocket *sioc;
struct virtio_blk_config blkcfg;
bool writable;
} VuBlkExport;
static void vu_blk_req_complete(VuBlkReq *req)
static void vu_blk_req_complete(VuBlkReq *req, size_t in_len)
{
VuDev *vu_dev = &req->server->vu_dev;
/* IO size with 1 extra status byte */
vu_queue_push(vu_dev, req->vq, &req->elem, req->size + 1);
vu_queue_push(vu_dev, req->vq, &req->elem, in_len);
vu_queue_notify(vu_dev, req->vq);
free(req);
}
static bool vu_blk_sect_range_ok(VuBlkExport *vexp, uint64_t sector,
size_t size)
{
uint64_t nb_sectors;
uint64_t total_sectors;
if (size % VIRTIO_BLK_SECTOR_SIZE) {
return false;
}
nb_sectors = size >> VIRTIO_BLK_SECTOR_BITS;
QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != VIRTIO_BLK_SECTOR_SIZE);
if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
return false;
}
if ((sector << VIRTIO_BLK_SECTOR_BITS) % vexp->blk_size) {
return false;
}
blk_get_geometry(vexp->export.blk, &total_sectors);
if (sector > total_sectors || nb_sectors > total_sectors - sector) {
return false;
}
return true;
}
static int coroutine_fn
vu_blk_discard_write_zeroes(VuBlkExport *vexp, struct iovec *iov,
uint32_t iovcnt, uint32_t type)
{
BlockBackend *blk = vexp->export.blk;
struct virtio_blk_discard_write_zeroes desc;
ssize_t size;
uint64_t sector;
uint32_t num_sectors;
uint32_t max_sectors;
uint32_t flags;
int bytes;
/* Only one desc is currently supported */
if (unlikely(iov_size(iov, iovcnt) > sizeof(desc))) {
return VIRTIO_BLK_S_UNSUPP;
}
size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc));
if (unlikely(size != sizeof(desc))) {
error_report("Invalid size %zd, expected %zu", size, sizeof(desc));
return VIRTIO_BLK_S_IOERR;
}
sector = le64_to_cpu(desc.sector);
num_sectors = le32_to_cpu(desc.num_sectors);
flags = le32_to_cpu(desc.flags);
max_sectors = (type == VIRTIO_BLK_T_WRITE_ZEROES) ?
VHOST_USER_BLK_MAX_WRITE_ZEROES_SECTORS :
VHOST_USER_BLK_MAX_DISCARD_SECTORS;
/* This check ensures that 'bytes' fits in an int */
if (unlikely(num_sectors > max_sectors)) {
return VIRTIO_BLK_S_IOERR;
}
bytes = num_sectors << VIRTIO_BLK_SECTOR_BITS;
if (unlikely(!vu_blk_sect_range_ok(vexp, sector, bytes))) {
return VIRTIO_BLK_S_IOERR;
}
/*
* 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)) {
return VIRTIO_BLK_S_UNSUPP;
}
if (type == VIRTIO_BLK_T_WRITE_ZEROES) {
int blk_flags = 0;
if (flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) {
blk_flags |= BDRV_REQ_MAY_UNMAP;
}
if (blk_co_pwrite_zeroes(blk, sector << VIRTIO_BLK_SECTOR_BITS,
bytes, blk_flags) == 0) {
return VIRTIO_BLK_S_OK;
}
} else if (type == 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)) {
return VIRTIO_BLK_S_UNSUPP;
}
if (blk_co_pdiscard(blk, sector << VIRTIO_BLK_SECTOR_BITS,
bytes) == 0) {
return VIRTIO_BLK_S_OK;
}
}
return VIRTIO_BLK_S_IOERR;
}
/* Called with server refcount increased, must decrease before returning */
static void coroutine_fn vu_blk_virtio_process_req(void *opaque)
{
VuBlkReq *req = opaque;
VuServer *server = req->server;
VuVirtqElement *elem = &req->elem;
uint32_t type;
VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server);
BlockBackend *blk = vexp->export.blk;
VirtioBlkHandler *handler = &vexp->handler;
struct iovec *in_iov = elem->in_sg;
struct iovec *out_iov = elem->out_sg;
unsigned in_num = elem->in_num;
unsigned out_num = elem->out_num;
int in_len;
/* refer to hw/block/virtio_blk.c */
if (elem->out_num < 1 || elem->in_num < 1) {
error_report("virtio-blk request missing headers");
goto err;
in_len = virtio_blk_process_req(handler, in_iov, out_iov,
in_num, out_num);
if (in_len < 0) {
free(req);
vhost_user_server_unref(server);
return;
}
if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out,
sizeof(req->out)) != sizeof(req->out))) {
error_report("virtio-blk request outhdr too short");
goto err;
}
iov_discard_front(&out_iov, &out_num, sizeof(req->out));
if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
error_report("virtio-blk request inhdr too short");
goto err;
}
/* We always touch the last byte, so just see how big in_iov is. */
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(in_iov, &in_num, sizeof(struct virtio_blk_inhdr));
type = le32_to_cpu(req->out.type);
switch (type & ~VIRTIO_BLK_T_BARRIER) {
case VIRTIO_BLK_T_IN:
case VIRTIO_BLK_T_OUT: {
QEMUIOVector qiov;
int64_t offset;
ssize_t ret = 0;
bool is_write = type & VIRTIO_BLK_T_OUT;
req->sector_num = le64_to_cpu(req->out.sector);
if (is_write && !vexp->writable) {
req->in->status = VIRTIO_BLK_S_IOERR;
break;
}
if (is_write) {
qemu_iovec_init_external(&qiov, out_iov, out_num);
} else {
qemu_iovec_init_external(&qiov, in_iov, in_num);
}
if (unlikely(!vu_blk_sect_range_ok(vexp,
req->sector_num,
qiov.size))) {
req->in->status = VIRTIO_BLK_S_IOERR;
break;
}
offset = req->sector_num << VIRTIO_BLK_SECTOR_BITS;
if (is_write) {
ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0);
} else {
ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0);
}
if (ret >= 0) {
req->in->status = VIRTIO_BLK_S_OK;
} else {
req->in->status = VIRTIO_BLK_S_IOERR;
}
break;
}
case VIRTIO_BLK_T_FLUSH:
if (blk_co_flush(blk) == 0) {
req->in->status = VIRTIO_BLK_S_OK;
} else {
req->in->status = VIRTIO_BLK_S_IOERR;
}
break;
case VIRTIO_BLK_T_GET_ID: {
size_t size = MIN(iov_size(&elem->in_sg[0], in_num),
VIRTIO_BLK_ID_BYTES);
snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk");
req->in->status = VIRTIO_BLK_S_OK;
req->size = elem->in_sg[0].iov_len;
break;
}
case VIRTIO_BLK_T_DISCARD:
case VIRTIO_BLK_T_WRITE_ZEROES: {
if (!vexp->writable) {
req->in->status = VIRTIO_BLK_S_IOERR;
break;
}
req->in->status = vu_blk_discard_write_zeroes(vexp, out_iov, out_num,
type);
break;
}
default:
req->in->status = VIRTIO_BLK_S_UNSUPP;
break;
}
vu_blk_req_complete(req);
vhost_user_server_unref(server);
return;
err:
free(req);
vu_blk_req_complete(req, in_len);
vhost_user_server_unref(server);
}
@ -348,7 +128,7 @@ static uint64_t vu_blk_get_features(VuDev *dev)
1ull << VIRTIO_RING_F_EVENT_IDX |
1ull << VHOST_USER_F_PROTOCOL_FEATURES;
if (!vexp->writable) {
if (!vexp->handler.writable) {
features |= 1ull << VIRTIO_BLK_F_RO;
}
@ -455,12 +235,12 @@ vu_blk_initialize_config(BlockDriverState *bs,
config->opt_io_size = cpu_to_le32(1);
config->num_queues = cpu_to_le16(num_queues);
config->max_discard_sectors =
cpu_to_le32(VHOST_USER_BLK_MAX_DISCARD_SECTORS);
cpu_to_le32(VIRTIO_BLK_MAX_DISCARD_SECTORS);
config->max_discard_seg = cpu_to_le32(1);
config->discard_sector_alignment =
cpu_to_le32(blk_size >> VIRTIO_BLK_SECTOR_BITS);
config->max_write_zeroes_sectors
= cpu_to_le32(VHOST_USER_BLK_MAX_WRITE_ZEROES_SECTORS);
= cpu_to_le32(VIRTIO_BLK_MAX_WRITE_ZEROES_SECTORS);
config->max_write_zeroes_seg = cpu_to_le32(1);
}
@ -480,7 +260,6 @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts,
uint64_t logical_block_size;
uint16_t num_queues = VHOST_USER_BLK_NUM_QUEUES_DEFAULT;
vexp->writable = opts->writable;
vexp->blkcfg.wce = 0;
if (vu_opts->has_logical_block_size) {
@ -494,8 +273,6 @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts,
error_propagate(errp, local_err);
return -EINVAL;
}
vexp->blk_size = logical_block_size;
blk_set_guest_block_size(exp->blk, logical_block_size);
if (vu_opts->has_num_queues) {
num_queues = vu_opts->num_queues;
@ -504,6 +281,10 @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts,
error_setg(errp, "num-queues must be greater than 0");
return -EINVAL;
}
vexp->handler.blk = exp->blk;
vexp->handler.serial = g_strdup("vhost_user_blk");
vexp->handler.logical_block_size = logical_block_size;
vexp->handler.writable = opts->writable;
vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg,
logical_block_size, num_queues);
@ -515,6 +296,7 @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts,
num_queues, &vu_blk_iface, errp)) {
blk_remove_aio_context_notifier(exp->blk, blk_aio_attached,
blk_aio_detach, vexp);
g_free(vexp->handler.serial);
return -EADDRNOTAVAIL;
}
@ -527,6 +309,7 @@ static void vu_blk_exp_delete(BlockExport *exp)
blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach,
vexp);
g_free(vexp->handler.serial);
}
const BlockExportDriver blk_exp_vhost_user_blk = {

240
block/export/virtio-blk-handler.c Normal file
View File

@ -0,0 +1,240 @@
/*
* Handler for virtio-blk I/O
*
* Copyright (c) 2020 Red Hat, Inc.
* Copyright (C) 2022 Bytedance Inc. and/or its affiliates. All rights reserved.
*
* Author:
* Coiby Xu <coiby.xu@gmail.com>
* Xie Yongji <xieyongji@bytedance.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu/error-report.h"
#include "virtio-blk-handler.h"
#include "standard-headers/linux/virtio_blk.h"
struct virtio_blk_inhdr {
unsigned char status;
};
static bool virtio_blk_sect_range_ok(BlockBackend *blk, uint32_t block_size,
uint64_t sector, size_t size)
{
uint64_t nb_sectors;
uint64_t total_sectors;
if (size % VIRTIO_BLK_SECTOR_SIZE) {
return false;
}
nb_sectors = size >> VIRTIO_BLK_SECTOR_BITS;
QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != VIRTIO_BLK_SECTOR_SIZE);
if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
return false;
}
if ((sector << VIRTIO_BLK_SECTOR_BITS) % block_size) {
return false;
}
blk_get_geometry(blk, &total_sectors);
if (sector > total_sectors || nb_sectors > total_sectors - sector) {
return false;
}
return true;
}
static int coroutine_fn
virtio_blk_discard_write_zeroes(VirtioBlkHandler *handler, struct iovec *iov,
uint32_t iovcnt, uint32_t type)
{
BlockBackend *blk = handler->blk;
struct virtio_blk_discard_write_zeroes desc;
ssize_t size;
uint64_t sector;
uint32_t num_sectors;
uint32_t max_sectors;
uint32_t flags;
int bytes;
/* Only one desc is currently supported */
if (unlikely(iov_size(iov, iovcnt) > sizeof(desc))) {
return VIRTIO_BLK_S_UNSUPP;
}
size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc));
if (unlikely(size != sizeof(desc))) {
error_report("Invalid size %zd, expected %zu", size, sizeof(desc));
return VIRTIO_BLK_S_IOERR;
}
sector = le64_to_cpu(desc.sector);
num_sectors = le32_to_cpu(desc.num_sectors);
flags = le32_to_cpu(desc.flags);
max_sectors = (type == VIRTIO_BLK_T_WRITE_ZEROES) ?
VIRTIO_BLK_MAX_WRITE_ZEROES_SECTORS :
VIRTIO_BLK_MAX_DISCARD_SECTORS;
/* This check ensures that 'bytes' fits in an int */
if (unlikely(num_sectors > max_sectors)) {
return VIRTIO_BLK_S_IOERR;
}
bytes = num_sectors << VIRTIO_BLK_SECTOR_BITS;
if (unlikely(!virtio_blk_sect_range_ok(blk, handler->logical_block_size,
sector, bytes))) {
return VIRTIO_BLK_S_IOERR;
}
/*
* 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)) {
return VIRTIO_BLK_S_UNSUPP;
}
if (type == VIRTIO_BLK_T_WRITE_ZEROES) {
int blk_flags = 0;
if (flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) {
blk_flags |= BDRV_REQ_MAY_UNMAP;
}
if (blk_co_pwrite_zeroes(blk, sector << VIRTIO_BLK_SECTOR_BITS,
bytes, blk_flags) == 0) {
return VIRTIO_BLK_S_OK;
}
} else if (type == 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)) {
return VIRTIO_BLK_S_UNSUPP;
}
if (blk_co_pdiscard(blk, sector << VIRTIO_BLK_SECTOR_BITS,
bytes) == 0) {
return VIRTIO_BLK_S_OK;
}
}
return VIRTIO_BLK_S_IOERR;
}
int coroutine_fn virtio_blk_process_req(VirtioBlkHandler *handler,
struct iovec *in_iov,
struct iovec *out_iov,
unsigned int in_num,
unsigned int out_num)
{
BlockBackend *blk = handler->blk;
struct virtio_blk_inhdr *in;
struct virtio_blk_outhdr out;
uint32_t type;
int in_len;
if (out_num < 1 || in_num < 1) {
error_report("virtio-blk request missing headers");
return -EINVAL;
}
if (unlikely(iov_to_buf(out_iov, out_num, 0, &out,
sizeof(out)) != sizeof(out))) {
error_report("virtio-blk request outhdr too short");
return -EINVAL;
}
iov_discard_front(&out_iov, &out_num, sizeof(out));
if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
error_report("virtio-blk request inhdr too short");
return -EINVAL;
}
/* We always touch the last byte, so just see how big in_iov is. */
in_len = iov_size(in_iov, in_num);
in = (void *)in_iov[in_num - 1].iov_base
+ in_iov[in_num - 1].iov_len
- sizeof(struct virtio_blk_inhdr);
iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr));
type = le32_to_cpu(out.type);
switch (type & ~VIRTIO_BLK_T_BARRIER) {
case VIRTIO_BLK_T_IN:
case VIRTIO_BLK_T_OUT: {
QEMUIOVector qiov;
int64_t offset;
ssize_t ret = 0;
bool is_write = type & VIRTIO_BLK_T_OUT;
int64_t sector_num = le64_to_cpu(out.sector);
if (is_write && !handler->writable) {
in->status = VIRTIO_BLK_S_IOERR;
break;
}
if (is_write) {
qemu_iovec_init_external(&qiov, out_iov, out_num);
} else {
qemu_iovec_init_external(&qiov, in_iov, in_num);
}
if (unlikely(!virtio_blk_sect_range_ok(blk,
handler->logical_block_size,
sector_num, qiov.size))) {
in->status = VIRTIO_BLK_S_IOERR;
break;
}
offset = sector_num << VIRTIO_BLK_SECTOR_BITS;
if (is_write) {
ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0);
} else {
ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0);
}
if (ret >= 0) {
in->status = VIRTIO_BLK_S_OK;
} else {
in->status = VIRTIO_BLK_S_IOERR;
}
break;
}
case VIRTIO_BLK_T_FLUSH:
if (blk_co_flush(blk) == 0) {
in->status = VIRTIO_BLK_S_OK;
} else {
in->status = VIRTIO_BLK_S_IOERR;
}
break;
case VIRTIO_BLK_T_GET_ID: {
size_t size = MIN(strlen(handler->serial) + 1,
MIN(iov_size(in_iov, in_num),
VIRTIO_BLK_ID_BYTES));
iov_from_buf(in_iov, in_num, 0, handler->serial, size);
in->status = VIRTIO_BLK_S_OK;
break;
}
case VIRTIO_BLK_T_DISCARD:
case VIRTIO_BLK_T_WRITE_ZEROES:
if (!handler->writable) {
in->status = VIRTIO_BLK_S_IOERR;
break;
}
in->status = virtio_blk_discard_write_zeroes(handler, out_iov,
out_num, type);
break;
default:
in->status = VIRTIO_BLK_S_UNSUPP;
break;
}
return in_len;
}

37
block/export/virtio-blk-handler.h Normal file
View File

@ -0,0 +1,37 @@
/*
* Handler for virtio-blk I/O
*
* Copyright (C) 2022 Bytedance Inc. and/or its affiliates. All rights reserved.
*
* Author:
* Xie Yongji <xieyongji@bytedance.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#ifndef VIRTIO_BLK_HANDLER_H
#define VIRTIO_BLK_HANDLER_H
#include "sysemu/block-backend.h"
#define VIRTIO_BLK_SECTOR_BITS 9
#define VIRTIO_BLK_SECTOR_SIZE (1ULL << VIRTIO_BLK_SECTOR_BITS)
#define VIRTIO_BLK_MAX_DISCARD_SECTORS 32768
#define VIRTIO_BLK_MAX_WRITE_ZEROES_SECTORS 32768
typedef struct {
BlockBackend *blk;
char *serial;
uint32_t logical_block_size;
bool writable;
} VirtioBlkHandler;
int coroutine_fn virtio_blk_process_req(VirtioBlkHandler *handler,
struct iovec *in_iov,
struct iovec *out_iov,
unsigned int in_num,
unsigned int out_num);
#endif /* VIRTIO_BLK_HANDLER_H */

2
block/gluster.c
View File

@ -891,7 +891,7 @@ out:
static void qemu_gluster_refresh_limits(BlockDriverState *bs, Error **errp)
{
bs->bl.max_transfer = GLUSTER_MAX_TRANSFER;
bs->bl.max_pdiscard = SIZE_MAX;
bs->bl.max_pdiscard = MIN(SIZE_MAX, INT64_MAX);
}
static int qemu_gluster_reopen_prepare(BDRVReopenState *state,

15
block/io.c
View File

@ -588,21 +588,6 @@ void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
BDRV_POLL_WHILE(child->bs, qatomic_read(&drained_end_counter) > 0);
}
/*
* Wait for pending requests to complete on a single BlockDriverState subtree,
* and suspend block driver's internal I/O until next request arrives.
*
* Note that unlike bdrv_drain_all(), the caller must hold the BlockDriverState
* AioContext.
*/
void coroutine_fn bdrv_co_drain(BlockDriverState *bs)
{
IO_OR_GS_CODE();
assert(qemu_in_coroutine());
bdrv_drained_begin(bs);
bdrv_drained_end(bs);
}
void bdrv_drain(BlockDriverState *bs)
{
IO_OR_GS_CODE();

40
block/monitor/bitmap-qmp-cmds.c
View File

@ -261,8 +261,9 @@ BdrvDirtyBitmap *block_dirty_bitmap_merge(const char *node, const char *target,
HBitmap **backup, Error **errp)
{
BlockDriverState *bs;
BdrvDirtyBitmap *dst, *src, *anon;
BdrvDirtyBitmap *dst, *src;
BlockDirtyBitmapOrStrList *lst;
HBitmap *local_backup = NULL;
GLOBAL_STATE_CODE();
@ -271,12 +272,6 @@ BdrvDirtyBitmap *block_dirty_bitmap_merge(const char *node, const char *target,
return NULL;
}
anon = bdrv_create_dirty_bitmap(bs, bdrv_dirty_bitmap_granularity(dst),
NULL, errp);
if (!anon) {
return NULL;
}
for (lst = bms; lst; lst = lst->next) {
switch (lst->value->type) {
const char *name, *node;
@ -285,8 +280,7 @@ BdrvDirtyBitmap *block_dirty_bitmap_merge(const char *node, const char *target,
src = bdrv_find_dirty_bitmap(bs, name);
if (!src) {
error_setg(errp, "Dirty bitmap '%s' not found", name);
dst = NULL;
goto out;
goto fail;
}
break;
case QTYPE_QDICT:
@ -294,26 +288,36 @@ BdrvDirtyBitmap *block_dirty_bitmap_merge(const char *node, const char *target,
name = lst->value->u.external.name;
src = block_dirty_bitmap_lookup(node, name, NULL, errp);
if (!src) {
dst = NULL;
goto out;
goto fail;
}
break;
default:
abort();
}
if (!bdrv_merge_dirty_bitmap(anon, src, NULL, errp)) {
dst = NULL;
goto out;
/* We do backup only for first merge operation */
if (!bdrv_merge_dirty_bitmap(dst, src,
local_backup ? NULL : &local_backup,
errp))
{
goto fail;
}
}
/* Merge into dst; dst is unchanged on failure. */
bdrv_merge_dirty_bitmap(dst, anon, backup, errp);
if (backup) {
*backup = local_backup;
} else {
hbitmap_free(local_backup);
}
out:
bdrv_release_dirty_bitmap(anon);
return dst;
fail:
if (local_backup) {
bdrv_restore_dirty_bitmap(dst, local_backup);
}
return NULL;
}
void qmp_block_dirty_bitmap_merge(const char *node, const char *target,

8
block/nbd.c
View File

@ -521,12 +521,8 @@ static int coroutine_fn nbd_co_send_request(BlockDriverState *bs,
if (qiov) {
qio_channel_set_cork(s->ioc, true);
rc = nbd_send_request(s->ioc, request);
if (rc >= 0) {
if (qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov,
NULL) < 0) {
rc = -EIO;
}
} else if (rc >= 0) {
if (rc >= 0 && qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov,
NULL) < 0) {
rc = -EIO;
}
qio_channel_set_cork(s->ioc, false);

24
block/rbd.c
View File

@ -831,6 +831,26 @@ static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
error_setg_errno(errp, -r, "error opening pool %s", opts->pool);
goto failed_shutdown;
}
#ifdef HAVE_RBD_NAMESPACE_EXISTS
if (opts->has_q_namespace && strlen(opts->q_namespace) > 0) {
bool exists;
r = rbd_namespace_exists(*io_ctx, opts->q_namespace, &exists);
if (r < 0) {
error_setg_errno(errp, -r, "error checking namespace");
goto failed_ioctx_destroy;
}
if (!exists) {
error_setg(errp, "namespace '%s' does not exist",
opts->q_namespace);
r = -ENOENT;
goto failed_ioctx_destroy;
}
}
#endif
/*
* Set the namespace after opening the io context on the pool,
* if nspace == NULL or if nspace == "", it is just as we did nothing
@ -840,6 +860,10 @@ static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
r = 0;
goto out;
#ifdef HAVE_RBD_NAMESPACE_EXISTS
failed_ioctx_destroy:
rados_ioctx_destroy(*io_ctx);
#endif
failed_shutdown:
rados_shutdown(*cluster);
out:

22
docs/tools/qemu-storage-daemon.rst
View File

@ -77,6 +77,7 @@ Standard options:
--export [type=]vhost-user-blk,id=<id>,node-name=<node-name>,addr.type=unix,addr.path=<socket-path>[,writable=on|off][,logical-block-size=<block-size>][,num-queues=<num-queues>]
--export [type=]vhost-user-blk,id=<id>,node-name=<node-name>,addr.type=fd,addr.str=<fd>[,writable=on|off][,logical-block-size=<block-size>][,num-queues=<num-queues>]
--export [type=]fuse,id=<id>,node-name=<node-name>,mountpoint=<file>[,growable=on|off][,writable=on|off][,allow-other=on|off|auto]
--export [type=]vduse-blk,id=<id>,node-name=<node-name>,name=<vduse-name>[,writable=on|off][,num-queues=<num-queues>][,queue-size=<queue-size>][,logical-block-size=<block-size>][,serial=<serial-number>]
is a block export definition. ``node-name`` is the block node that should be
exported. ``writable`` determines whether or not the export allows write
@ -110,6 +111,27 @@ Standard options:
``allow-other`` to auto (the default) will try enabling this option, and on
error fall back to disabling it.
The ``vduse-blk`` export type takes a ``name`` (must be unique across the host)
to create the VDUSE device.
``num-queues`` sets the number of virtqueues (the default is 1).
``queue-size`` sets the virtqueue descriptor table size (the default is 256).
The instantiated VDUSE device must then be added to the vDPA bus using the
vdpa(8) command from the iproute2 project::
# vdpa dev add name <id> mgmtdev vduse
The device can be removed from the vDPA bus later as follows::
# vdpa dev del <id>
For more information about attaching vDPA devices to the host with
virtio_vdpa.ko or attaching them to guests with vhost_vdpa.ko, see
https://vdpa-dev.gitlab.io/.
For more information about VDUSE, see
https://docs.kernel.org/userspace-api/vduse.html.
.. option:: --monitor MONITORDEF
is a QMP monitor definition. See the :manpage:`qemu(1)` manual page for

1
hw/block/virtio-blk.c
View File

@ -1228,7 +1228,6 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
blk_set_dev_ops(s->blk, &virtio_block_ops, s);
blk_set_guest_block_size(s->blk, s->conf.conf.logical_block_size);
blk_iostatus_enable(s->blk);

1
hw/block/xen-block.c
View File

@ -243,7 +243,6 @@ static void xen_block_realize(XenDevice *xendev, Error **errp)
}
blk_set_dev_ops(blk, &xen_block_dev_ops, blockdev);
blk_set_guest_block_size(blk, conf->logical_block_size);
if (conf->discard_granularity == -1) {
conf->discard_granularity = conf->physical_block_size;

1
hw/ide/core.c
View File

@ -2548,7 +2548,6 @@ int ide_init_drive(IDEState *s, BlockBackend *blk, IDEDriveKind kind,
s->smart_selftest_count = 0;
if (kind == IDE_CD) {
blk_set_dev_ops(blk, &ide_cd_block_ops, s);
blk_set_guest_block_size(blk, 2048);
} else {
if (!blk_is_inserted(s->blk)) {
error_setg(errp, "Device needs media, but drive is empty");

1
hw/scsi/scsi-disk.c
View File

@ -2419,7 +2419,6 @@ static void scsi_realize(SCSIDevice *dev, Error **errp)
} else {
blk_set_dev_ops(s->qdev.conf.blk, &scsi_disk_block_ops, s);
}
blk_set_guest_block_size(s->qdev.conf.blk, s->qdev.blocksize);
blk_iostatus_enable(s->qdev.conf.blk);

1
hw/scsi/scsi-generic.c
View File

@ -321,7 +321,6 @@ static void scsi_read_complete(void * opaque, int ret)
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

2
include/block/aio-wait.h
View File

@ -81,6 +81,8 @@ extern AioWait global_aio_wait;
AioContext *ctx_ = (ctx); \
/* Increment wait_->num_waiters before evaluating cond. */ \
qatomic_inc(&wait_->num_waiters); \
/* Paired with smp_mb in aio_wait_kick(). */ \
smp_mb(); \
if (ctx_ && in_aio_context_home_thread(ctx_)) { \
while ((cond)) { \
aio_poll(ctx_, true); \

1
include/block/block-io.h
View File

@ -270,7 +270,6 @@ void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter);
cond); })
void bdrv_drain(BlockDriverState *bs);
void coroutine_fn bdrv_co_drain(BlockDriverState *bs);
int generated_co_wrapper
bdrv_truncate(BdrvChild *child, int64_t offset, bool exact,

2
include/block/block_int-io.h
View File

@ -102,7 +102,7 @@ bool blk_dev_is_tray_open(BlockBackend *blk);
void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes);
void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out);
bool bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest,
void bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest,
const BdrvDirtyBitmap *src,
HBitmap **backup, bool lock);

15
include/qemu/hbitmap.h
View File

@ -76,20 +76,9 @@ void hbitmap_truncate(HBitmap *hb, uint64_t size);
*
* Store result of merging @a and @b into @result.
* @result is allowed to be equal to @a or @b.
*
* Return true if the merge was successful,
* false if it was not attempted.
* All bitmaps must have same size.
*/
bool hbitmap_merge(const HBitmap *a, const HBitmap *b, HBitmap *result);
/**
* hbitmap_can_merge:
*
* hbitmap_can_merge(a, b) && hbitmap_can_merge(a, result) is sufficient and
* necessary for hbitmap_merge will not fail.
*
*/
bool hbitmap_can_merge(const HBitmap *a, const HBitmap *b);
void hbitmap_merge(const HBitmap *a, const HBitmap *b, HBitmap *result);
/**
* hbitmap_empty:

1
include/sysemu/block-backend-io.h
View File

@ -72,7 +72,6 @@ void blk_error_action(BlockBackend *blk, BlockErrorAction action,
void blk_iostatus_set_err(BlockBackend *blk, int error);
int blk_get_max_iov(BlockBackend *blk);
int blk_get_max_hw_iov(BlockBackend *blk);
void blk_set_guest_block_size(BlockBackend *blk, int align);
void blk_io_plug(BlockBackend *blk);
void blk_io_unplug(BlockBackend *blk);

306
linux-headers/linux/vduse.h Normal file
View File

@ -0,0 +1,306 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _VDUSE_H_
#define _VDUSE_H_
#include <linux/types.h>
#define VDUSE_BASE 0x81
/* The ioctls for control device (/dev/vduse/control) */
#define VDUSE_API_VERSION 0
/*
* Get the version of VDUSE API that kernel supported (VDUSE_API_VERSION).
* This is used for future extension.
*/
#define VDUSE_GET_API_VERSION _IOR(VDUSE_BASE, 0x00, __u64)
/* Set the version of VDUSE API that userspace supported. */
#define VDUSE_SET_API_VERSION _IOW(VDUSE_BASE, 0x01, __u64)
/**
* struct vduse_dev_config - basic configuration of a VDUSE device
* @name: VDUSE device name, needs to be NUL terminated
* @vendor_id: virtio vendor id
* @device_id: virtio device id
* @features: virtio features
* @vq_num: the number of virtqueues
* @vq_align: the allocation alignment of virtqueue's metadata
* @reserved: for future use, needs to be initialized to zero
* @config_size: the size of the configuration space
* @config: the buffer of the configuration space
*
* Structure used by VDUSE_CREATE_DEV ioctl to create VDUSE device.
*/
struct vduse_dev_config {
#define VDUSE_NAME_MAX 256
char name[VDUSE_NAME_MAX];
__u32 vendor_id;
__u32 device_id;
__u64 features;
__u32 vq_num;
__u32 vq_align;
__u32 reserved[13];
__u32 config_size;
__u8 config[];
};
/* Create a VDUSE device which is represented by a char device (/dev/vduse/$NAME) */
#define VDUSE_CREATE_DEV _IOW(VDUSE_BASE, 0x02, struct vduse_dev_config)
/*
* Destroy a VDUSE device. Make sure there are no more references
* to the char device (/dev/vduse/$NAME).
*/
#define VDUSE_DESTROY_DEV _IOW(VDUSE_BASE, 0x03, char[VDUSE_NAME_MAX])
/* The ioctls for VDUSE device (/dev/vduse/$NAME) */
/**
* struct vduse_iotlb_entry - entry of IOTLB to describe one IOVA region [start, last]
* @offset: the mmap offset on returned file descriptor
* @start: start of the IOVA region
* @last: last of the IOVA region
* @perm: access permission of the IOVA region
*
* Structure used by VDUSE_IOTLB_GET_FD ioctl to find an overlapped IOVA region.
*/
struct vduse_iotlb_entry {
__u64 offset;
__u64 start;
__u64 last;
#define VDUSE_ACCESS_RO 0x1
#define VDUSE_ACCESS_WO 0x2
#define VDUSE_ACCESS_RW 0x3
__u8 perm;
};
/*
* Find the first IOVA region that overlaps with the range [start, last]
* and return the corresponding file descriptor. Return -EINVAL means the
* IOVA region doesn't exist. Caller should set start and last fields.
*/
#define VDUSE_IOTLB_GET_FD _IOWR(VDUSE_BASE, 0x10, struct vduse_iotlb_entry)
/*
* Get the negotiated virtio features. It's a subset of the features in
* struct vduse_dev_config which can be accepted by virtio driver. It's
* only valid after FEATURES_OK status bit is set.
*/
#define VDUSE_DEV_GET_FEATURES _IOR(VDUSE_BASE, 0x11, __u64)
/**
* struct vduse_config_data - data used to update configuration space
* @offset: the offset from the beginning of configuration space
* @length: the length to write to configuration space
* @buffer: the buffer used to write from
*
* Structure used by VDUSE_DEV_SET_CONFIG ioctl to update device
* configuration space.
*/
struct vduse_config_data {
__u32 offset;
__u32 length;
__u8 buffer[];
};
/* Set device configuration space */
#define VDUSE_DEV_SET_CONFIG _IOW(VDUSE_BASE, 0x12, struct vduse_config_data)
/*
* Inject a config interrupt. It's usually used to notify virtio driver
* that device configuration space has changed.
*/
#define VDUSE_DEV_INJECT_CONFIG_IRQ _IO(VDUSE_BASE, 0x13)
/**
* struct vduse_vq_config - basic configuration of a virtqueue
* @index: virtqueue index
* @max_size: the max size of virtqueue
* @reserved: for future use, needs to be initialized to zero
*
* Structure used by VDUSE_VQ_SETUP ioctl to setup a virtqueue.
*/
struct vduse_vq_config {
__u32 index;
__u16 max_size;
__u16 reserved[13];
};
/*
* Setup the specified virtqueue. Make sure all virtqueues have been
* configured before the device is attached to vDPA bus.
*/
#define VDUSE_VQ_SETUP _IOW(VDUSE_BASE, 0x14, struct vduse_vq_config)
/**
* struct vduse_vq_state_split - split virtqueue state
* @avail_index: available index
*/
struct vduse_vq_state_split {
__u16 avail_index;
};
/**
* struct vduse_vq_state_packed - packed virtqueue state
* @last_avail_counter: last driver ring wrap counter observed by device
* @last_avail_idx: device available index
* @last_used_counter: device ring wrap counter
* @last_used_idx: used index
*/
struct vduse_vq_state_packed {
__u16 last_avail_counter;
__u16 last_avail_idx;
__u16 last_used_counter;
__u16 last_used_idx;
};
/**
* struct vduse_vq_info - information of a virtqueue
* @index: virtqueue index
* @num: the size of virtqueue
* @desc_addr: address of desc area
* @driver_addr: address of driver area
* @device_addr: address of device area
* @split: split virtqueue state
* @packed: packed virtqueue state
* @ready: ready status of virtqueue
*
* Structure used by VDUSE_VQ_GET_INFO ioctl to get virtqueue's information.
*/
struct vduse_vq_info {
__u32 index;
__u32 num;
__u64 desc_addr;
__u64 driver_addr;
__u64 device_addr;
union {
struct vduse_vq_state_split split;
struct vduse_vq_state_packed packed;
};
__u8 ready;
};
/* Get the specified virtqueue's information. Caller should set index field. */
#define VDUSE_VQ_GET_INFO _IOWR(VDUSE_BASE, 0x15, struct vduse_vq_info)
/**
* struct vduse_vq_eventfd - eventfd configuration for a virtqueue
* @index: virtqueue index
* @fd: eventfd, -1 means de-assigning the eventfd
*
* Structure used by VDUSE_VQ_SETUP_KICKFD ioctl to setup kick eventfd.
*/
struct vduse_vq_eventfd {
__u32 index;
#define VDUSE_EVENTFD_DEASSIGN -1
int fd;
};
/*
* Setup kick eventfd for specified virtqueue. The kick eventfd is used
* by VDUSE kernel module to notify userspace to consume the avail vring.
*/
#define VDUSE_VQ_SETUP_KICKFD _IOW(VDUSE_BASE, 0x16, struct vduse_vq_eventfd)
/*
* Inject an interrupt for specific virtqueue. It's used to notify virtio driver
* to consume the used vring.
*/
#define VDUSE_VQ_INJECT_IRQ _IOW(VDUSE_BASE, 0x17, __u32)
/* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */
/**
* enum vduse_req_type - request type
* @VDUSE_GET_VQ_STATE: get the state for specified virtqueue from userspace
* @VDUSE_SET_STATUS: set the device status
* @VDUSE_UPDATE_IOTLB: Notify userspace to update the memory mapping for
* specified IOVA range via VDUSE_IOTLB_GET_FD ioctl
*/
enum vduse_req_type {
VDUSE_GET_VQ_STATE,
VDUSE_SET_STATUS,
VDUSE_UPDATE_IOTLB,
};
/**
* struct vduse_vq_state - virtqueue state
* @index: virtqueue index
* @split: split virtqueue state
* @packed: packed virtqueue state
*/
struct vduse_vq_state {
__u32 index;
union {
struct vduse_vq_state_split split;
struct vduse_vq_state_packed packed;
};
};
/**
* struct vduse_dev_status - device status
* @status: device status
*/
struct vduse_dev_status {
__u8 status;
};
/**
* struct vduse_iova_range - IOVA range [start, last]
* @start: start of the IOVA range
* @last: last of the IOVA range
*/
struct vduse_iova_range {
__u64 start;
__u64 last;
};
/**
* struct vduse_dev_request - control request
* @type: request type
* @request_id: request id
* @reserved: for future use
* @vq_state: virtqueue state, only index field is available
* @s: device status
* @iova: IOVA range for updating
* @padding: padding
*
* Structure used by read(2) on /dev/vduse/$NAME.
*/
struct vduse_dev_request {
__u32 type;
__u32 request_id;
__u32 reserved[4];
union {
struct vduse_vq_state vq_state;
struct vduse_dev_status s;
struct vduse_iova_range iova;
__u32 padding[32];
};
};
/**
* struct vduse_dev_response - response to control request
* @request_id: corresponding request id
* @result: the result of request
* @reserved: for future use, needs to be initialized to zero
* @vq_state: virtqueue state
* @padding: padding
*
* Structure used by write(2) on /dev/vduse/$NAME.
*/
struct vduse_dev_response {
__u32 request_id;
#define VDUSE_REQ_RESULT_OK 0x00
#define VDUSE_REQ_RESULT_FAILED 0x01
__u32 result;
__u32 reserved[4];
union {
struct vduse_vq_state vq_state;
__u32 padding[32];
};
};
#endif /* _VDUSE_H_ */

34
meson.build
View File

@ -1541,6 +1541,26 @@ if get_option('fuse_lseek').allowed()
endif
endif
have_libvduse = (targetos == 'linux')
if get_option('libvduse').enabled()
if targetos != 'linux'
error('libvduse requires linux')
endif
elif get_option('libvduse').disabled()
have_libvduse = false
endif
have_vduse_blk_export = (have_libvduse and targetos == 'linux')
if get_option('vduse_blk_export').enabled()
if targetos != 'linux'
error('vduse_blk_export requires linux')
elif not have_libvduse
error('vduse_blk_export requires libvduse support')
endif
elif get_option('vduse_blk_export').disabled()
have_vduse_blk_export = false
endif
# libbpf
libbpf = dependency('libbpf', required: get_option('bpf'), method: 'pkg-config')
if libbpf.found() and not cc.links('''
@ -1783,6 +1803,7 @@ config_host_data.set('CONFIG_VHOST_CRYPTO', have_vhost_user_crypto)
config_host_data.set('CONFIG_VHOST_VDPA', have_vhost_vdpa)
config_host_data.set('CONFIG_VMNET', vmnet.found())
config_host_data.set('CONFIG_VHOST_USER_BLK_SERVER', have_vhost_user_blk_server)
config_host_data.set('CONFIG_VDUSE_BLK_EXPORT', have_vduse_blk_export)
config_host_data.set('CONFIG_PNG', png.found())
config_host_data.set('CONFIG_VNC', vnc.found())
config_host_data.set('CONFIG_VNC_JPEG', jpeg.found())
@ -1882,6 +1903,12 @@ config_host_data.set('HAVE_GETIFADDRS', cc.has_function('getifaddrs'))
config_host_data.set('HAVE_OPENPTY', cc.has_function('openpty', dependencies: util))
config_host_data.set('HAVE_STRCHRNUL', cc.has_function('strchrnul'))
config_host_data.set('HAVE_SYSTEM_FUNCTION', cc.has_function('system', prefix: '#include <stdlib.h>'))
if rbd.found()
config_host_data.set('HAVE_RBD_NAMESPACE_EXISTS',
cc.has_function('rbd_namespace_exists',
dependencies: rbd,
prefix: '#include <rbd/librbd.h>'))
endif
if rdma.found()
config_host_data.set('HAVE_IBV_ADVISE_MR',
cc.has_function('ibv_advise_mr',
@ -2986,6 +3013,12 @@ if targetos == 'linux' and have_vhost_user
vhost_user = libvhost_user.get_variable('vhost_user_dep')
endif
libvduse = not_found
if have_libvduse
libvduse_proj = subproject('libvduse')
libvduse = libvduse_proj.get_variable('libvduse_dep')
endif
# NOTE: the trace/ subdirectory needs the qapi_trace_events variable
# that is filled in by qapi/.
subdir('qapi')
@ -3842,6 +3875,7 @@ if have_block
summary_info += {'qed support': get_option('qed').allowed()}
summary_info += {'parallels support': get_option('parallels').allowed()}
summary_info += {'FUSE exports': fuse}
summary_info += {'VDUSE block exports': have_vduse_blk_export}
endif
summary(summary_info, bool_yn: true, section: 'Block layer support')

4
meson_options.txt
View File

@ -257,6 +257,10 @@ option('virtfs', type: 'feature', value: 'auto',
description: 'virtio-9p support')
option('virtiofsd', type: 'feature', value: 'auto',
description: 'build virtiofs daemon (virtiofsd)')
option('libvduse', type: 'feature', value: 'auto',
description: 'build VDUSE Library')
option('vduse_blk_export', type: 'feature', value: 'auto',
description: 'VDUSE block export support')
option('capstone', type: 'feature', value: 'auto',
description: 'Whether and how to find the capstone library')

29
qapi/block-export.json
View File

@ -178,6 +178,27 @@
'*allow-other': 'FuseExportAllowOther' },
'if': 'CONFIG_FUSE' }
##
# @BlockExportOptionsVduseBlk:
#
# A vduse-blk block export.
#
# @name: the name of VDUSE device (must be unique across the host).
# @num-queues: the number of virtqueues. Defaults to 1.
# @queue-size: the size of virtqueue. Defaults to 256.
# @logical-block-size: Logical block size in bytes. Range [512, PAGE_SIZE]
# and must be power of 2. Defaults to 512 bytes.
# @serial: the serial number of virtio block device. Defaults to empty string.
#
# Since: 7.1
##
{ 'struct': 'BlockExportOptionsVduseBlk',
'data': { 'name': 'str',
'*num-queues': 'uint16',
'*queue-size': 'uint16',
'*logical-block-size': 'size',
'*serial': 'str' } }
##
# @NbdServerAddOptions:
#
@ -284,6 +305,7 @@
# @nbd: NBD export
# @vhost-user-blk: vhost-user-blk export (since 5.2)
# @fuse: FUSE export (since: 6.0)
# @vduse-blk: vduse-blk export (since 7.1)
#
# Since: 4.2
##
@ -291,7 +313,8 @@
'data': [ 'nbd',
{ 'name': 'vhost-user-blk',
'if': 'CONFIG_VHOST_USER_BLK_SERVER' },
{ 'name': 'fuse', 'if': 'CONFIG_FUSE' } ] }
{ 'name': 'fuse', 'if': 'CONFIG_FUSE' },
{ 'name': 'vduse-blk', 'if': 'CONFIG_VDUSE_BLK_EXPORT' } ] }
##
# @BlockExportOptions:
@ -335,7 +358,9 @@
'vhost-user-blk': { 'type': 'BlockExportOptionsVhostUserBlk',
'if': 'CONFIG_VHOST_USER_BLK_SERVER' },
'fuse': { 'type': 'BlockExportOptionsFuse',
'if': 'CONFIG_FUSE' }
'if': 'CONFIG_FUSE' },
'vduse-blk': { 'type': 'BlockExportOptionsVduseBlk',
'if': 'CONFIG_VDUSE_BLK_EXPORT' }
} }
##

7
scripts/meson-buildoptions.sh
View File

@ -110,6 +110,7 @@ meson_options_help() {
printf "%s\n" ' libssh ssh block device support'
printf "%s\n" ' libudev Use libudev to enumerate host devices'
printf "%s\n" ' libusb libusb support for USB passthrough'
printf "%s\n" ' libvduse build VDUSE Library'
printf "%s\n" ' linux-aio Linux AIO support'
printf "%s\n" ' linux-io-uring Linux io_uring support'
printf "%s\n" ' live-block-migration'
@ -161,6 +162,8 @@ meson_options_help() {
printf "%s\n" ' vhost-user vhost-user backend support'
printf "%s\n" ' vhost-user-blk-server'
printf "%s\n" ' build vhost-user-blk server'
printf "%s\n" ' vduse-blk-export'
printf "%s\n" ' VDUSE block export support'
printf "%s\n" ' vhost-vdpa vhost-vdpa kernel backend support'
printf "%s\n" ' virglrenderer virgl rendering support'
printf "%s\n" ' virtfs virtio-9p support'
@ -307,6 +310,8 @@ _meson_option_parse() {
--disable-libudev) printf "%s" -Dlibudev=disabled ;;
--enable-libusb) printf "%s" -Dlibusb=enabled ;;
--disable-libusb) printf "%s" -Dlibusb=disabled ;;
--enable-libvduse) printf "%s" -Dlibvduse=enabled ;;
--disable-libvduse) printf "%s" -Dlibvduse=disabled ;;
--enable-linux-aio) printf "%s" -Dlinux_aio=enabled ;;
--disable-linux-aio) printf "%s" -Dlinux_aio=disabled ;;
--enable-linux-io-uring) printf "%s" -Dlinux_io_uring=enabled ;;
@ -429,6 +434,8 @@ _meson_option_parse() {
--disable-vhost-user) printf "%s" -Dvhost_user=disabled ;;
--enable-vhost-user-blk-server) printf "%s" -Dvhost_user_blk_server=enabled ;;
--disable-vhost-user-blk-server) printf "%s" -Dvhost_user_blk_server=disabled ;;
--enable-vduse-blk-export) printf "%s" -Dvduse_blk_export=enabled ;;
--disable-vduse-blk-export) printf "%s" -Dvduse_blk_export=disabled ;;
--enable-vhost-vdpa) printf "%s" -Dvhost_vdpa=enabled ;;
--disable-vhost-vdpa) printf "%s" -Dvhost_vdpa=disabled ;;
--enable-virglrenderer) printf "%s" -Dvirglrenderer=enabled ;;

2
scripts/update-linux-headers.sh
View File

@ -161,7 +161,7 @@ done
rm -rf "$output/linux-headers/linux"
mkdir -p "$output/linux-headers/linux"
for header in kvm.h vfio.h vfio_ccw.h vfio_zdev.h vhost.h \
psci.h psp-sev.h userfaultfd.h mman.h; do
psci.h psp-sev.h userfaultfd.h mman.h vduse.h; do
cp "$tmpdir/include/linux/$header" "$output/linux-headers/linux"
done

10
storage-daemon/qemu-storage-daemon.c
View File

@ -121,6 +121,16 @@ static void help(void)
" vhost-user-blk device over file descriptor\n"
"\n"
#endif /* CONFIG_VHOST_USER_BLK_SERVER */
#ifdef CONFIG_VDUSE_BLK_EXPORT
" --export [type=]vduse-blk,id=<id>,node-name=<node-name>\n"
" ,name=<vduse-name>[,writable=on|off]\n"
" [,num-queues=<num-queues>][,queue-size=<queue-size>]\n"
" [,logical-block-size=<logical-block-size>]\n"
" [,serial=<serial-number>]\n"
" export the specified block node as a\n"
" vduse-blk device\n"
"\n"
#endif /* CONFIG_VDUSE_BLK_EXPORT */
" --monitor [chardev=]name[,mode=control][,pretty[=on|off]]\n"
" configure a QMP monitor\n"
"\n"

1
subprojects/libvduse/include/atomic.h Symbolic link
View File

@ -0,0 +1 @@
../../../include/qemu/atomic.h

1
subprojects/libvduse/include/compiler.h Symbolic link
View File

@ -0,0 +1 @@
../../../include/qemu/compiler.h

1375
subprojects/libvduse/libvduse.c Normal file
View File

File diff suppressed because it is too large Load Diff

247
subprojects/libvduse/libvduse.h Normal file
View File

@ -0,0 +1,247 @@
/*
* VDUSE (vDPA Device in Userspace) library
*
* Copyright (C) 2022 Bytedance Inc. and/or its affiliates. All rights reserved.
*
* Author:
* Xie Yongji <xieyongji@bytedance.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#ifndef LIBVDUSE_H
#define LIBVDUSE_H
#include <stdint.h>
#include <sys/uio.h>
#define VIRTQUEUE_MAX_SIZE 1024
/* VDUSE device structure */
typedef struct VduseDev VduseDev;
/* Virtqueue structure */
typedef struct VduseVirtq VduseVirtq;
/* Some operation of VDUSE backend */
typedef struct VduseOps {
/* Called when virtqueue can be processed */
void (*enable_queue)(VduseDev *dev, VduseVirtq *vq);
/* Called when virtqueue processing should be stopped */
void (*disable_queue)(VduseDev *dev, VduseVirtq *vq);
} VduseOps;
/* Describing elements of the I/O buffer */
typedef struct VduseVirtqElement {
/* Descriptor table index */
unsigned int index;
/* Number of physically-contiguous device-readable descriptors */
unsigned int out_num;
/* Number of physically-contiguous device-writable descriptors */
unsigned int in_num;
/* Array to store physically-contiguous device-writable descriptors */
struct iovec *in_sg;
/* Array to store physically-contiguous device-readable descriptors */
struct iovec *out_sg;
} VduseVirtqElement;
/**
* vduse_get_virtio_features:
*
* Get supported virtio features
*
* Returns: supported feature bits
*/
uint64_t vduse_get_virtio_features(void);
/**
* vduse_queue_get_dev:
* @vq: specified virtqueue
*
* Get corresponding VDUSE device from the virtqueue.
*
* Returns: a pointer to VDUSE device on success, NULL on failure.
*/
VduseDev *vduse_queue_get_dev(VduseVirtq *vq);
/**
* vduse_queue_get_fd:
* @vq: specified virtqueue
*
* Get the kick fd for the virtqueue.
*
* Returns: file descriptor on success, -1 on failure.
*/
int vduse_queue_get_fd(VduseVirtq *vq);
/**
* vduse_queue_pop:
* @vq: specified virtqueue
* @sz: the size of struct to return (must be >= VduseVirtqElement)
*
* Pop an element from virtqueue available ring.
*
* Returns: a pointer to a structure containing VduseVirtqElement on success,
* NULL on failure.
*/
void *vduse_queue_pop(VduseVirtq *vq, size_t sz);
/**
* vduse_queue_push:
* @vq: specified virtqueue
* @elem: pointer to VduseVirtqElement returned by vduse_queue_pop()
* @len: length in bytes to write
*
* Push an element to virtqueue used ring.
*/
void vduse_queue_push(VduseVirtq *vq, const VduseVirtqElement *elem,
unsigned int len);
/**
* vduse_queue_notify:
* @vq: specified virtqueue
*
* Request to notify the queue.
*/
void vduse_queue_notify(VduseVirtq *vq);
/**
* vduse_dev_get_priv:
* @dev: VDUSE device
*
* Get the private pointer passed to vduse_dev_create().
*
* Returns: private pointer on success, NULL on failure.
*/
void *vduse_dev_get_priv(VduseDev *dev);
/**
* vduse_dev_get_queue:
* @dev: VDUSE device
* @index: virtqueue index
*
* Get the specified virtqueue.
*
* Returns: a pointer to the virtqueue on success, NULL on failure.
*/
VduseVirtq *vduse_dev_get_queue(VduseDev *dev, int index);
/**
* vduse_dev_get_fd:
* @dev: VDUSE device
*
* Get the control message fd for the VDUSE device.
*
* Returns: file descriptor on success, -1 on failure.
*/
int vduse_dev_get_fd(VduseDev *dev);
/**
* vduse_dev_handler:
* @dev: VDUSE device
*
* Used to process the control message.
*
* Returns: file descriptor on success, -errno on failure.
*/
int vduse_dev_handler(VduseDev *dev);
/**
* vduse_dev_update_config:
* @dev: VDUSE device
* @size: the size to write to configuration space
* @offset: the offset from the beginning of configuration space
* @buffer: the buffer used to write from
*
* Update device configuration space and inject a config interrupt.
*
* Returns: 0 on success, -errno on failure.
*/
int vduse_dev_update_config(VduseDev *dev, uint32_t size,
uint32_t offset, char *buffer);
/**
* vduse_dev_setup_queue:
* @dev: VDUSE device
* @index: virtqueue index
* @max_size: the max size of virtqueue
*
* Setup the specified virtqueue.
*
* Returns: 0 on success, -errno on failure.
*/
int vduse_dev_setup_queue(VduseDev *dev, int index, int max_size);
/**
* vduse_set_reconnect_log_file:
* @dev: VDUSE device
* @file: filename of reconnect log
*
* Specify the file to store log for reconnecting. It should
* be called before vduse_dev_setup_queue().
*
* Returns: 0 on success, -errno on failure.
*/
int vduse_set_reconnect_log_file(VduseDev *dev, const char *filename);
/**
* vduse_dev_create_by_fd:
* @fd: passed file descriptor
* @num_queues: the number of virtqueues
* @ops: the operation of VDUSE backend
* @priv: private pointer
*
* Create VDUSE device from a passed file descriptor.
*
* Returns: pointer to VDUSE device on success, NULL on failure.
*/
VduseDev *vduse_dev_create_by_fd(int fd, uint16_t num_queues,
const VduseOps *ops, void *priv);
/**
* vduse_dev_create_by_name:
* @name: VDUSE device name
* @num_queues: the number of virtqueues
* @ops: the operation of VDUSE backend
* @priv: private pointer
*
* Create VDUSE device on /dev/vduse/$NAME.
*
* Returns: pointer to VDUSE device on success, NULL on failure.
*/
VduseDev *vduse_dev_create_by_name(const char *name, uint16_t num_queues,
const VduseOps *ops, void *priv);
/**
* vduse_dev_create:
* @name: VDUSE device name
* @device_id: virtio device id
* @vendor_id: virtio vendor id
* @features: virtio features
* @num_queues: the number of virtqueues
* @config_size: the size of the configuration space
* @config: the buffer of the configuration space
* @ops: the operation of VDUSE backend
* @priv: private pointer
*
* Create VDUSE device.
*
* Returns: pointer to VDUSE device on success, NULL on failure.
*/
VduseDev *vduse_dev_create(const char *name, uint32_t device_id,
uint32_t vendor_id, uint64_t features,
uint16_t num_queues, uint32_t config_size,
char *config, const VduseOps *ops, void *priv);
/**
* vduse_dev_destroy:
* @dev: VDUSE device
*
* Destroy the VDUSE device.
*
* Returns: 0 on success, -errno on failure.
*/
int vduse_dev_destroy(VduseDev *dev);
#endif

1
subprojects/libvduse/linux-headers/linux Symbolic link
View File

@ -0,0 +1 @@
../../../linux-headers/linux/

10
subprojects/libvduse/meson.build Normal file
View File

@ -0,0 +1,10 @@
project('libvduse', 'c',
license: 'GPL-2.0-or-later',
default_options: ['c_std=gnu99'])
libvduse = static_library('vduse',
files('libvduse.c'),
c_args: '-D_GNU_SOURCE')
libvduse_dep = declare_dependency(link_with: libvduse,
include_directories: include_directories('.'))

1
subprojects/libvduse/standard-headers/linux Symbolic link
View File

@ -0,0 +1 @@
../../../include/standard-headers/linux/

16
util/aio-wait.c
View File

@ -35,7 +35,21 @@ static void dummy_bh_cb(void *opaque)
void aio_wait_kick(void)
{
/* The barrier (or an atomic op) is in the caller. */
/*
* Paired with smp_mb in AIO_WAIT_WHILE. Here we have:
* write(condition);
* aio_wait_kick() {
* smp_mb();
* read(num_waiters);
* }
*
* And in AIO_WAIT_WHILE:
* write(num_waiters);
* smp_mb();
* read(condition);
*/
smp_mb();
if (qatomic_read(&global_aio_wait.num_waiters)) {
aio_bh_schedule_oneshot(qemu_get_aio_context(), dummy_bh_cb, NULL);
}

25
util/hbitmap.c
View File

@ -873,11 +873,6 @@ void hbitmap_truncate(HBitmap *hb, uint64_t size)
}
}
bool hbitmap_can_merge(const HBitmap *a, const HBitmap *b)
{
return (a->orig_size == b->orig_size);
}
/**
* hbitmap_sparse_merge: performs dst = dst | src
* works with differing granularities.
@ -901,28 +896,24 @@ static void hbitmap_sparse_merge(HBitmap *dst, const HBitmap *src)
* Given HBitmaps A and B, let R := A (BITOR) B.
* Bitmaps A and B will not be modified,
* except when bitmap R is an alias of A or B.
*
* @return true if the merge was successful,
* false if it was not attempted.
* Bitmaps must have same size.
*/
bool hbitmap_merge(const HBitmap *a, const HBitmap *b, HBitmap *result)
void hbitmap_merge(const HBitmap *a, const HBitmap *b, HBitmap *result)
{
int i;
uint64_t j;
if (!hbitmap_can_merge(a, b) || !hbitmap_can_merge(a, result)) {
return false;
}
assert(hbitmap_can_merge(b, result));
assert(a->orig_size == result->orig_size);
assert(b->orig_size == result->orig_size);
if ((!hbitmap_count(a) && result == b) ||
(!hbitmap_count(b) && result == a)) {
return true;
return;
}
if (!hbitmap_count(a) && !hbitmap_count(b)) {
hbitmap_reset_all(result);
return true;
return;
}
if (a->granularity != b->granularity) {
@ -935,7 +926,7 @@ bool hbitmap_merge(const HBitmap *a, const HBitmap *b, HBitmap *result)
if (b != result) {
hbitmap_sparse_merge(result, b);
}
return true;
return;
}
/* This merge is O(size), as BITS_PER_LONG and HBITMAP_LEVELS are constant.
@ -951,8 +942,6 @@ bool hbitmap_merge(const HBitmap *a, const HBitmap *b, HBitmap *result)
/* Recompute the dirty count */
result->count = hb_count_between(result, 0, result->size - 1);
return true;
}
char *hbitmap_sha256(const HBitmap *bitmap, Error **errp)