The following changes since commit 028f2361d0c2d28d6f918fe618f389228ac22b60: Merge tag 'pull-target-arm-20220609' of https://git.linaro.org/people/pmaydell/qemu-arm into staging (2022-06-09 06:47:03 -0700) are available in the Git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to 7f9a8b3342ff00d3398fdc08264948762d748edb: nbd: Drop dead code spotted by Coverity (2022-06-09 18:07:17 +0200) ---------------------------------------------------------------- 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 ---------------------------------------------------------------- Emanuele Giuseppe Esposito (1): aio_wait_kick: add missing memory barrier Eric Blake (1): nbd: Drop dead code spotted by Coverity Fabian Ebner (1): block/gluster: correctly set max_pdiscard Stefan Hajnoczi (3): block: drop unused bdrv_co_drain() API block: get rid of blk->guest_block_size qsd: document vduse-blk exports Stefano Garzarella (1): block/rbd: report a better error when namespace does not exist Vladimir Sementsov-Ogievskiy (3): block: block_dirty_bitmap_merge(): fix error path block: improve block_dirty_bitmap_merge(): don't allocate extra bitmap block: simplify handling of try to merge different sized bitmaps Xie Yongji (8): block: Support passing NULL ops to blk_set_dev_ops() block/export: Fix incorrect length passed to vu_queue_push() block/export: Abstract out the logic of virtio-blk I/O process linux-headers: Add vduse.h libvduse: Add VDUSE (vDPA Device in Userspace) library vduse-blk: Implement vduse-blk export vduse-blk: Add vduse-blk resize support libvduse: Add support for reconnecting qapi/block-export.json | 28 +- docs/tools/qemu-storage-daemon.rst | 21 + meson_options.txt | 4 + block/export/vduse-blk.h | 20 + block/export/virtio-blk-handler.h | 37 + include/block/aio-wait.h | 2 + include/block/block-io.h | 1 - include/block/block_int-io.h | 2 +- include/qemu/hbitmap.h | 15 +- include/sysemu/block-backend-io.h | 1 - linux-headers/linux/vduse.h | 306 ++++++ subprojects/libvduse/include/atomic.h | 1 + subprojects/libvduse/include/compiler.h | 1 + subprojects/libvduse/libvduse.h | 247 +++++ block/backup.c | 6 +- block/block-backend.c | 12 +- block/dirty-bitmap.c | 26 +- block/export/export.c | 6 + block/export/vduse-blk.c | 341 +++++++ block/export/vhost-user-blk-server.c | 261 +---- block/export/virtio-blk-handler.c | 240 +++++ block/gluster.c | 2 +- block/io.c | 15 - block/monitor/bitmap-qmp-cmds.c | 40 +- block/nbd.c | 8 +- block/rbd.c | 24 + hw/block/virtio-blk.c | 1 - hw/block/xen-block.c | 1 - hw/ide/core.c | 1 - hw/scsi/scsi-disk.c | 1 - hw/scsi/scsi-generic.c | 1 - storage-daemon/qemu-storage-daemon.c | 9 + subprojects/libvduse/libvduse.c | 1392 +++++++++++++++++++++++++++ util/aio-wait.c | 16 +- util/hbitmap.c | 25 +- MAINTAINERS | 9 + block/export/meson.build | 7 +- meson.build | 34 + scripts/meson-buildoptions.sh | 7 + scripts/update-linux-headers.sh | 2 +- subprojects/libvduse/linux-headers/linux | 1 + subprojects/libvduse/meson.build | 10 + subprojects/libvduse/standard-headers/linux | 1 + 43 files changed, 2830 insertions(+), 355 deletions(-) create mode 100644 block/export/vduse-blk.h create mode 100644 block/export/virtio-blk-handler.h create mode 100644 linux-headers/linux/vduse.h create mode 120000 subprojects/libvduse/include/atomic.h create mode 120000 subprojects/libvduse/include/compiler.h create mode 100644 subprojects/libvduse/libvduse.h create mode 100644 block/export/vduse-blk.c create mode 100644 block/export/virtio-blk-handler.c create mode 100644 subprojects/libvduse/libvduse.c create mode 120000 subprojects/libvduse/linux-headers/linux create mode 100644 subprojects/libvduse/meson.build create mode 120000 subprojects/libvduse/standard-headers/linux From: Stefan Hajnoczi <stefanha@redhat.com> bdrv_co_drain() has not been used since commit 9a0cec664eef ("mirror: use bdrv_drained_begin/bdrv_drained_end") in 2016. Remove it so there are fewer drain scenarios to worry about. Use bdrv_drained_begin()/bdrv_drained_end() instead. They are "mixed" functions that can be called from coroutine context. Unlike bdrv_co_drain(), these functions provide control of the length of the drained section, which is usually the right thing. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220521122714.3837731-1-stefanha@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-io.h | 1 - block/io.c | 15 --------------- 2 files changed, 16 deletions(-) diff --git a/include/block/block-io.h b/include/block/block-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -XXX,XX +XXX,XX @@ 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, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ 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(); -- 2.35.3 From: Stefan Hajnoczi <stefanha@redhat.com> Commit 1b7fd729559c ("block: rename buffer_alignment to guest_block_size") noted: At this point, the field is set by the device emulation, but completely ignored by the block layer. The last time the value of buffer_alignment/guest_block_size was actually used was before commit 339064d50639 ("block: Don't use guest sector size for qemu_blockalign()"). This value has not been used since 2013. Get rid of it. Cc: Xie Yongji <xieyongji@bytedance.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220518130945.2657905-1-stefanha@redhat.com> Reviewed-by: Paul Durrant <paul@xen.org> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/sysemu/block-backend-io.h | 1 - block/block-backend.c | 10 ---------- block/export/vhost-user-blk-server.c | 1 - hw/block/virtio-blk.c | 1 - hw/block/xen-block.c | 1 - hw/ide/core.c | 1 - hw/scsi/scsi-disk.c | 1 - hw/scsi/scsi-generic.c | 1 - 8 files changed, 17 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ 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); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ 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; @@ -XXX,XX +XXX,XX @@ 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); } @@ -XXX,XX +XXX,XX @@ 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(); diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, 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; diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ 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); diff --git a/hw/block/xen-block.c b/hw/block/xen-block.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/xen-block.c +++ b/hw/block/xen-block.c @@ -XXX,XX +XXX,XX @@ 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; diff --git a/hw/ide/core.c b/hw/ide/core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ide/core.c +++ b/hw/ide/core.c @@ -XXX,XX +XXX,XX @@ 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"); diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -XXX,XX +XXX,XX @@ 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); diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/scsi-generic.c +++ b/hw/scsi/scsi-generic.c @@ -XXX,XX +XXX,XX @@ 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 -- 2.35.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@openvz.org> At the end we ignore failure of bdrv_merge_dirty_bitmap() and report success. And still set errp. That's wrong. Signed-off-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru> Reviewed-by: Nikita Lapshin <nikita.lapshin@virtuozzo.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220517111206.23585-2-v.sementsov-og@mail.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/monitor/bitmap-qmp-cmds.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/block/monitor/bitmap-qmp-cmds.c b/block/monitor/bitmap-qmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/block/monitor/bitmap-qmp-cmds.c +++ b/block/monitor/bitmap-qmp-cmds.c @@ -XXX,XX +XXX,XX @@ BdrvDirtyBitmap *block_dirty_bitmap_merge(const char *node, const char *target, } /* Merge into dst; dst is unchanged on failure. */ - bdrv_merge_dirty_bitmap(dst, anon, backup, errp); + if (!bdrv_merge_dirty_bitmap(dst, anon, backup, errp)) { + dst = NULL; + goto out; + } out: bdrv_release_dirty_bitmap(anon); -- 2.35.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@openvz.org> We don't need extra bitmap. All we need is to backup the original bitmap when we do first merge. So, drop extra temporary bitmap and work directly with target and backup. Still to keep old semantics, that on failure target is unchanged and user don't need to restore, we need a local_backup variable and do restore ourselves on failure path. Signed-off-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru> Message-Id: <20220517111206.23585-3-v.sementsov-og@mail.ru> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/monitor/bitmap-qmp-cmds.c | 41 +++++++++++++++++---------------- 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/block/monitor/bitmap-qmp-cmds.c b/block/monitor/bitmap-qmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/block/monitor/bitmap-qmp-cmds.c +++ b/block/monitor/bitmap-qmp-cmds.c @@ -XXX,XX +XXX,XX @@ 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(); @@ -XXX,XX +XXX,XX @@ 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; @@ -XXX,XX +XXX,XX @@ 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: @@ -XXX,XX +XXX,XX @@ 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. */ - if (!bdrv_merge_dirty_bitmap(dst, anon, backup, errp)) { - dst = NULL; - goto out; + 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, -- 2.35.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@openvz.org> We have too much logic to simply check that bitmaps are of the same size. Let's just define that hbitmap_merge() and bdrv_dirty_bitmap_merge_internal() require their argument bitmaps be of same size, this simplifies things. Let's look through the callers: For backup_init_bcs_bitmap() we already assert that merge can't fail. In bdrv_reclaim_dirty_bitmap_locked() we gracefully handle the error that can't happen: successor always has same size as its parent, drop this logic. In bdrv_merge_dirty_bitmap() we already has assertion and separate check. Make the check explicit and improve error message. Signed-off-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru> Reviewed-by: Nikita Lapshin <nikita.lapshin@virtuozzo.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220517111206.23585-4-v.sementsov-og@mail.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int-io.h | 2 +- include/qemu/hbitmap.h | 15 ++------------- block/backup.c | 6 ++---- block/dirty-bitmap.c | 26 +++++++++++--------------- util/hbitmap.c | 25 +++++++------------------ 5 files changed, 23 insertions(+), 51 deletions(-) diff --git a/include/block/block_int-io.h b/include/block/block_int-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-io.h +++ b/include/block/block_int-io.h @@ -XXX,XX +XXX,XX @@ 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); diff --git a/include/qemu/hbitmap.h b/include/qemu/hbitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/hbitmap.h +++ b/include/qemu/hbitmap.h @@ -XXX,XX +XXX,XX @@ 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. - */ -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. - * + * All bitmaps must have same size. */ -bool hbitmap_can_merge(const HBitmap *a, const HBitmap *b); +void hbitmap_merge(const HBitmap *a, const HBitmap *b, HBitmap *result); /** * hbitmap_empty: diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ 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. diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ 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; @@ -XXX,XX +XXX,XX @@ 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); @@ -XXX,XX +XXX,XX @@ 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)); @@ -XXX,XX +XXX,XX @@ 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) { @@ -XXX,XX +XXX,XX @@ bool bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest, bdrv_dirty_bitmaps_unlock(src->bs); } } - - return ret; } diff --git a/util/hbitmap.c b/util/hbitmap.c index XXXXXXX..XXXXXXX 100644 --- a/util/hbitmap.c +++ b/util/hbitmap.c @@ -XXX,XX +XXX,XX @@ 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. @@ -XXX,XX +XXX,XX @@ 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) { @@ -XXX,XX +XXX,XX @@ 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. @@ -XXX,XX +XXX,XX @@ 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) -- 2.35.3 From: Xie Yongji <xieyongji@bytedance.com> This supports passing NULL ops to blk_set_dev_ops() so that we can remove stale ops in some cases. Signed-off-by: Xie Yongji <xieyongji@bytedance.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220523084611.91-2-xieyongji@bytedance.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/block-backend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ 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); } } -- 2.35.3 From: Xie Yongji <xieyongji@bytedance.com> Now the req->size is set to the correct value only when handling VIRTIO_BLK_T_GET_ID request. This patch fixes it. Signed-off-by: Xie Yongji <xieyongji@bytedance.com> Message-Id: <20220523084611.91-3-xieyongji@bytedance.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/export/vhost-user-blk-server.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static void vu_blk_req_complete(VuBlkReq *req) { 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, req->size); vu_queue_notify(vu_dev, req->vq); free(req); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_blk_virtio_process_req(void *opaque) goto err; } + req->size = iov_size(in_iov, in_num); /* 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 @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_blk_virtio_process_req(void *opaque) 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: -- 2.35.3 From: Xie Yongji <xieyongji@bytedance.com> Abstract the common logic of virtio-blk I/O process to a function named virtio_blk_process_req(). It's needed for the following commit. Signed-off-by: Xie Yongji <xieyongji@bytedance.com> Message-Id: <20220523084611.91-4-xieyongji@bytedance.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/export/virtio-blk-handler.h | 37 ++++ block/export/vhost-user-blk-server.c | 259 +++------------------------ block/export/virtio-blk-handler.c | 240 +++++++++++++++++++++++++ MAINTAINERS | 2 + block/export/meson.build | 2 +- 5 files changed, 301 insertions(+), 239 deletions(-) create mode 100644 block/export/virtio-blk-handler.h create mode 100644 block/export/virtio-blk-handler.c diff --git a/block/export/virtio-blk-handler.h b/block/export/virtio-blk-handler.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/virtio-blk-handler.h @@ -XXX,XX +XXX,XX @@ +/* + * 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; + const 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 */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ #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; @@ -XXX,XX +XXX,XX @@ 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; - vu_queue_push(vu_dev, req->vq, &req->elem, req->size); + 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; - - /* 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; - } - - 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; - } - - req->size = iov_size(in_iov, in_num); - /* 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; - break; + int in_len; + + 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; } - 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); } @@ -XXX,XX +XXX,XX @@ 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; } @@ -XXX,XX +XXX,XX @@ 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); } @@ -XXX,XX +XXX,XX @@ 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) { @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, error_propagate(errp, local_err); return -EINVAL; } - vexp->blk_size = logical_block_size; if (vu_opts->has_num_queues) { num_queues = vu_opts->num_queues; @@ -XXX,XX +XXX,XX @@ 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 = "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); diff --git a/block/export/virtio-blk-handler.c b/block/export/virtio-blk-handler.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/virtio-blk-handler.c @@ -XXX,XX +XXX,XX @@ +/* + * 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; +} diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ 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 diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -XXX,XX +XXX,XX @@ 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')) -- 2.35.3 From: Xie Yongji <xieyongji@bytedance.com> This adds vduse header to linux headers so that the relevant VDUSE API can be used in subsequent patches. Signed-off-by: Xie Yongji <xieyongji@bytedance.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220523084611.91-5-xieyongji@bytedance.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- linux-headers/linux/vduse.h | 306 ++++++++++++++++++++++++++++++++ scripts/update-linux-headers.sh | 2 +- 2 files changed, 307 insertions(+), 1 deletion(-) create mode 100644 linux-headers/linux/vduse.h diff --git a/linux-headers/linux/vduse.h b/linux-headers/linux/vduse.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/linux-headers/linux/vduse.h @@ -XXX,XX +XXX,XX @@ +/* 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_ */ diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index XXXXXXX..XXXXXXX 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -XXX,XX +XXX,XX @@ 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 -- 2.35.3 From: Xie Yongji <xieyongji@bytedance.com> VDUSE [1] is a linux framework that makes it possible to implement software-emulated vDPA devices in userspace. This adds a library as a subproject to help implementing VDUSE backends in QEMU. [1] https://www.kernel.org/doc/html/latest/userspace-api/vduse.html Signed-off-by: Xie Yongji <xieyongji@bytedance.com> Message-Id: <20220523084611.91-6-xieyongji@bytedance.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- meson_options.txt | 2 + subprojects/libvduse/include/atomic.h | 1 + subprojects/libvduse/include/compiler.h | 1 + subprojects/libvduse/libvduse.h | 235 ++++ subprojects/libvduse/libvduse.c | 1167 +++++++++++++++++++ MAINTAINERS | 5 + meson.build | 15 + scripts/meson-buildoptions.sh | 3 + subprojects/libvduse/linux-headers/linux | 1 + subprojects/libvduse/meson.build | 10 + subprojects/libvduse/standard-headers/linux | 1 + 11 files changed, 1441 insertions(+) create mode 120000 subprojects/libvduse/include/atomic.h create mode 120000 subprojects/libvduse/include/compiler.h create mode 100644 subprojects/libvduse/libvduse.h create mode 100644 subprojects/libvduse/libvduse.c create mode 120000 subprojects/libvduse/linux-headers/linux create mode 100644 subprojects/libvduse/meson.build create mode 120000 subprojects/libvduse/standard-headers/linux diff --git a/meson_options.txt b/meson_options.txt index XXXXXXX..XXXXXXX 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -XXX,XX +XXX,XX @@ 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('capstone', type: 'feature', value: 'auto', description: 'Whether and how to find the capstone library') diff --git a/subprojects/libvduse/include/atomic.h b/subprojects/libvduse/include/atomic.h new file mode 120000 index XXXXXXX..XXXXXXX --- /dev/null +++ b/subprojects/libvduse/include/atomic.h @@ -0,0 +1 @@ +../../../include/qemu/atomic.h \ No newline at end of file diff --git a/subprojects/libvduse/include/compiler.h b/subprojects/libvduse/include/compiler.h new file mode 120000 index XXXXXXX..XXXXXXX --- /dev/null +++ b/subprojects/libvduse/include/compiler.h @@ -0,0 +1 @@ +../../../include/qemu/compiler.h \ No newline at end of file diff --git a/subprojects/libvduse/libvduse.h b/subprojects/libvduse/libvduse.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/subprojects/libvduse/libvduse.h @@ -XXX,XX +XXX,XX @@ +/* + * 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_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 diff --git a/subprojects/libvduse/libvduse.c b/subprojects/libvduse/libvduse.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/subprojects/libvduse/libvduse.c @@ -XXX,XX +XXX,XX @@ +/* + * VDUSE (vDPA Device in Userspace) library + * + * Copyright (C) 2022 Bytedance Inc. and/or its affiliates. All rights reserved. + * Portions of codes and concepts borrowed from libvhost-user.c, so: + * Copyright IBM, Corp. 2007 + * Copyright (c) 2016 Red Hat, Inc. + * + * Author: + * Xie Yongji <xieyongji@bytedance.com> + * Anthony Liguori <aliguori@us.ibm.com> + * Marc-André Lureau <mlureau@redhat.com> + * Victor Kaplansky <victork@redhat.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 <stdlib.h> +#include <stdio.h> +#include <stdbool.h> +#include <stddef.h> +#include <errno.h> +#include <string.h> +#include <assert.h> +#include <endian.h> +#include <unistd.h> +#include <limits.h> +#include <fcntl.h> + +#include <sys/ioctl.h> +#include <sys/eventfd.h> +#include <sys/mman.h> + +#include "include/atomic.h" +#include "linux-headers/linux/virtio_ring.h" +#include "linux-headers/linux/virtio_config.h" +#include "linux-headers/linux/vduse.h" +#include "libvduse.h" + +#define VDUSE_VQ_ALIGN 4096 +#define MAX_IOVA_REGIONS 256 + +/* Round number down to multiple */ +#define ALIGN_DOWN(n, m) ((n) / (m) * (m)) + +/* Round number up to multiple */ +#define ALIGN_UP(n, m) ALIGN_DOWN((n) + (m) - 1, (m)) + +#ifndef unlikely +#define unlikely(x) __builtin_expect(!!(x), 0) +#endif + +typedef struct VduseRing { + unsigned int num; + uint64_t desc_addr; + uint64_t avail_addr; + uint64_t used_addr; + struct vring_desc *desc; + struct vring_avail *avail; + struct vring_used *used; +} VduseRing; + +struct VduseVirtq { + VduseRing vring; + uint16_t last_avail_idx; + uint16_t shadow_avail_idx; + uint16_t used_idx; + uint16_t signalled_used; + bool signalled_used_valid; + int index; + int inuse; + bool ready; + int fd; + VduseDev *dev; +}; + +typedef struct VduseIovaRegion { + uint64_t iova; + uint64_t size; + uint64_t mmap_offset; + uint64_t mmap_addr; +} VduseIovaRegion; + +struct VduseDev { + VduseVirtq *vqs; + VduseIovaRegion regions[MAX_IOVA_REGIONS]; + int num_regions; + char *name; + uint32_t device_id; + uint32_t vendor_id; + uint16_t num_queues; + uint16_t queue_size; + uint64_t features; + const VduseOps *ops; + int fd; + int ctrl_fd; + void *priv; +}; + +static inline bool has_feature(uint64_t features, unsigned int fbit) +{ + assert(fbit < 64); + return !!(features & (1ULL << fbit)); +} + +static inline bool vduse_dev_has_feature(VduseDev *dev, unsigned int fbit) +{ + return has_feature(dev->features, fbit); +} + +uint64_t vduse_get_virtio_features(void) +{ + return (1ULL << VIRTIO_F_IOMMU_PLATFORM) | + (1ULL << VIRTIO_F_VERSION_1) | + (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) | + (1ULL << VIRTIO_RING_F_EVENT_IDX) | + (1ULL << VIRTIO_RING_F_INDIRECT_DESC); +} + +VduseDev *vduse_queue_get_dev(VduseVirtq *vq) +{ + return vq->dev; +} + +int vduse_queue_get_fd(VduseVirtq *vq) +{ + return vq->fd; +} + +void *vduse_dev_get_priv(VduseDev *dev) +{ + return dev->priv; +} + +VduseVirtq *vduse_dev_get_queue(VduseDev *dev, int index) +{ + return &dev->vqs[index]; +} + +int vduse_dev_get_fd(VduseDev *dev) +{ + return dev->fd; +} + +static int vduse_inject_irq(VduseDev *dev, int index) +{ + return ioctl(dev->fd, VDUSE_VQ_INJECT_IRQ, &index); +} + +static void vduse_iova_remove_region(VduseDev *dev, uint64_t start, + uint64_t last) +{ + int i; + + if (last == start) { + return; + } + + for (i = 0; i < MAX_IOVA_REGIONS; i++) { + if (!dev->regions[i].mmap_addr) { + continue; + } + + if (start <= dev->regions[i].iova && + last >= (dev->regions[i].iova + dev->regions[i].size - 1)) { + munmap((void *)dev->regions[i].mmap_addr, + dev->regions[i].mmap_offset + dev->regions[i].size); + dev->regions[i].mmap_addr = 0; + dev->num_regions--; + } + } +} + +static int vduse_iova_add_region(VduseDev *dev, int fd, + uint64_t offset, uint64_t start, + uint64_t last, int prot) +{ + int i; + uint64_t size = last - start + 1; + void *mmap_addr = mmap(0, size + offset, prot, MAP_SHARED, fd, 0); + + if (mmap_addr == MAP_FAILED) { + close(fd); + return -EINVAL; + } + + for (i = 0; i < MAX_IOVA_REGIONS; i++) { + if (!dev->regions[i].mmap_addr) { + dev->regions[i].mmap_addr = (uint64_t)(uintptr_t)mmap_addr; + dev->regions[i].mmap_offset = offset; + dev->regions[i].iova = start; + dev->regions[i].size = size; + dev->num_regions++; + break; + } + } + assert(i < MAX_IOVA_REGIONS); + close(fd); + + return 0; +} + +static int perm_to_prot(uint8_t perm) +{ + int prot = 0; + + switch (perm) { + case VDUSE_ACCESS_WO: + prot |= PROT_WRITE; + break; + case VDUSE_ACCESS_RO: + prot |= PROT_READ; + break; + case VDUSE_ACCESS_RW: + prot |= PROT_READ | PROT_WRITE; + break; + default: + break; + } + + return prot; +} + +static inline void *iova_to_va(VduseDev *dev, uint64_t *plen, uint64_t iova) +{ + int i, ret; + struct vduse_iotlb_entry entry; + + for (i = 0; i < MAX_IOVA_REGIONS; i++) { + VduseIovaRegion *r = &dev->regions[i]; + + if (!r->mmap_addr) { + continue; + } + + if ((iova >= r->iova) && (iova < (r->iova + r->size))) { + if ((iova + *plen) > (r->iova + r->size)) { + *plen = r->iova + r->size - iova; + } + return (void *)(uintptr_t)(iova - r->iova + + r->mmap_addr + r->mmap_offset); + } + } + + entry.start = iova; + entry.last = iova + 1; + ret = ioctl(dev->fd, VDUSE_IOTLB_GET_FD, &entry); + if (ret < 0) { + return NULL; + } + + if (!vduse_iova_add_region(dev, ret, entry.offset, entry.start, + entry.last, perm_to_prot(entry.perm))) { + return iova_to_va(dev, plen, iova); + } + + return NULL; +} + +static inline uint16_t vring_avail_flags(VduseVirtq *vq) +{ + return le16toh(vq->vring.avail->flags); +} + +static inline uint16_t vring_avail_idx(VduseVirtq *vq) +{ + vq->shadow_avail_idx = le16toh(vq->vring.avail->idx); + + return vq->shadow_avail_idx; +} + +static inline uint16_t vring_avail_ring(VduseVirtq *vq, int i) +{ + return le16toh(vq->vring.avail->ring[i]); +} + +static inline uint16_t vring_get_used_event(VduseVirtq *vq) +{ + return vring_avail_ring(vq, vq->vring.num); +} + +static bool vduse_queue_get_head(VduseVirtq *vq, unsigned int idx, + unsigned int *head) +{ + /* + * Grab the next descriptor number they're advertising, and increment + * the index we've seen. + */ + *head = vring_avail_ring(vq, idx % vq->vring.num); + + /* If their number is silly, that's a fatal mistake. */ + if (*head >= vq->vring.num) { + fprintf(stderr, "Guest says index %u is available\n", *head); + return false; + } + + return true; +} + +static int +vduse_queue_read_indirect_desc(VduseDev *dev, struct vring_desc *desc, + uint64_t addr, size_t len) +{ + struct vring_desc *ori_desc; + uint64_t read_len; + + if (len > (VIRTQUEUE_MAX_SIZE * sizeof(struct vring_desc))) { + return -1; + } + + if (len == 0) { + return -1; + } + + while (len) { + read_len = len; + ori_desc = iova_to_va(dev, &read_len, addr); + if (!ori_desc) { + return -1; + } + + memcpy(desc, ori_desc, read_len); + len -= read_len; + addr += read_len; + desc += read_len; + } + + return 0; +} + +enum { + VIRTQUEUE_READ_DESC_ERROR = -1, + VIRTQUEUE_READ_DESC_DONE = 0, /* end of chain */ + VIRTQUEUE_READ_DESC_MORE = 1, /* more buffers in chain */ +}; + +static int vduse_queue_read_next_desc(struct vring_desc *desc, int i, + unsigned int max, unsigned int *next) +{ + /* If this descriptor says it doesn't chain, we're done. */ + if (!(le16toh(desc[i].flags) & VRING_DESC_F_NEXT)) { + return VIRTQUEUE_READ_DESC_DONE; + } + + /* Check they're not leading us off end of descriptors. */ + *next = desc[i].next; + /* Make sure compiler knows to grab that: we don't want it changing! */ + smp_wmb(); + + if (*next >= max) { + fprintf(stderr, "Desc next is %u\n", *next); + return VIRTQUEUE_READ_DESC_ERROR; + } + + return VIRTQUEUE_READ_DESC_MORE; +} + +/* + * Fetch avail_idx from VQ memory only when we really need to know if + * guest has added some buffers. + */ +static bool vduse_queue_empty(VduseVirtq *vq) +{ + if (unlikely(!vq->vring.avail)) { + return true; + } + + if (vq->shadow_avail_idx != vq->last_avail_idx) { + return false; + } + + return vring_avail_idx(vq) == vq->last_avail_idx; +} + +static bool vduse_queue_should_notify(VduseVirtq *vq) +{ + VduseDev *dev = vq->dev; + uint16_t old, new; + bool v; + + /* We need to expose used array entries before checking used event. */ + smp_mb(); + + /* Always notify when queue is empty (when feature acknowledge) */ + if (vduse_dev_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY) && + !vq->inuse && vduse_queue_empty(vq)) { + return true; + } + + if (!vduse_dev_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) { + return !(vring_avail_flags(vq) & VRING_AVAIL_F_NO_INTERRUPT); + } + + v = vq->signalled_used_valid; + vq->signalled_used_valid = true; + old = vq->signalled_used; + new = vq->signalled_used = vq->used_idx; + return !v || vring_need_event(vring_get_used_event(vq), new, old); +} + +void vduse_queue_notify(VduseVirtq *vq) +{ + VduseDev *dev = vq->dev; + + if (unlikely(!vq->vring.avail)) { + return; + } + + if (!vduse_queue_should_notify(vq)) { + return; + } + + if (vduse_inject_irq(dev, vq->index) < 0) { + fprintf(stderr, "Error inject irq for vq %d: %s\n", + vq->index, strerror(errno)); + } +} + +static inline void vring_used_flags_set_bit(VduseVirtq *vq, int mask) +{ + uint16_t *flags; + + flags = (uint16_t *)((char*)vq->vring.used + + offsetof(struct vring_used, flags)); + *flags = htole16(le16toh(*flags) | mask); +} + +static inline void vring_used_flags_unset_bit(VduseVirtq *vq, int mask) +{ + uint16_t *flags; + + flags = (uint16_t *)((char*)vq->vring.used + + offsetof(struct vring_used, flags)); + *flags = htole16(le16toh(*flags) & ~mask); +} + +static inline void vring_set_avail_event(VduseVirtq *vq, uint16_t val) +{ + *((uint16_t *)&vq->vring.used->ring[vq->vring.num]) = htole16(val); +} + +static bool vduse_queue_map_single_desc(VduseVirtq *vq, unsigned int *p_num_sg, + struct iovec *iov, unsigned int max_num_sg, + bool is_write, uint64_t pa, size_t sz) +{ + unsigned num_sg = *p_num_sg; + VduseDev *dev = vq->dev; + + assert(num_sg <= max_num_sg); + + if (!sz) { + fprintf(stderr, "virtio: zero sized buffers are not allowed\n"); + return false; + } + + while (sz) { + uint64_t len = sz; + + if (num_sg == max_num_sg) { + fprintf(stderr, + "virtio: too many descriptors in indirect table\n"); + return false; + } + + iov[num_sg].iov_base = iova_to_va(dev, &len, pa); + if (iov[num_sg].iov_base == NULL) { + fprintf(stderr, "virtio: invalid address for buffers\n"); + return false; + } + iov[num_sg++].iov_len = len; + sz -= len; + pa += len; + } + + *p_num_sg = num_sg; + return true; +} + +static void *vduse_queue_alloc_element(size_t sz, unsigned out_num, + unsigned in_num) +{ + VduseVirtqElement *elem; + size_t in_sg_ofs = ALIGN_UP(sz, __alignof__(elem->in_sg[0])); + size_t out_sg_ofs = in_sg_ofs + in_num * sizeof(elem->in_sg[0]); + size_t out_sg_end = out_sg_ofs + out_num * sizeof(elem->out_sg[0]); + + assert(sz >= sizeof(VduseVirtqElement)); + elem = malloc(out_sg_end); + if (!elem) { + return NULL; + } + elem->out_num = out_num; + elem->in_num = in_num; + elem->in_sg = (void *)elem + in_sg_ofs; + elem->out_sg = (void *)elem + out_sg_ofs; + return elem; +} + +static void *vduse_queue_map_desc(VduseVirtq *vq, unsigned int idx, size_t sz) +{ + struct vring_desc *desc = vq->vring.desc; + VduseDev *dev = vq->dev; + uint64_t desc_addr, read_len; + unsigned int desc_len; + unsigned int max = vq->vring.num; + unsigned int i = idx; + VduseVirtqElement *elem; + struct iovec iov[VIRTQUEUE_MAX_SIZE]; + struct vring_desc desc_buf[VIRTQUEUE_MAX_SIZE]; + unsigned int out_num = 0, in_num = 0; + int rc; + + if (le16toh(desc[i].flags) & VRING_DESC_F_INDIRECT) { + if (le32toh(desc[i].len) % sizeof(struct vring_desc)) { + fprintf(stderr, "Invalid size for indirect buffer table\n"); + return NULL; + } + + /* loop over the indirect descriptor table */ + desc_addr = le64toh(desc[i].addr); + desc_len = le32toh(desc[i].len); + max = desc_len / sizeof(struct vring_desc); + read_len = desc_len; + desc = iova_to_va(dev, &read_len, desc_addr); + if (unlikely(desc && read_len != desc_len)) { + /* Failed to use zero copy */ + desc = NULL; + if (!vduse_queue_read_indirect_desc(dev, desc_buf, + desc_addr, + desc_len)) { + desc = desc_buf; + } + } + if (!desc) { + fprintf(stderr, "Invalid indirect buffer table\n"); + return NULL; + } + i = 0; + } + + /* Collect all the descriptors */ + do { + if (le16toh(desc[i].flags) & VRING_DESC_F_WRITE) { + if (!vduse_queue_map_single_desc(vq, &in_num, iov + out_num, + VIRTQUEUE_MAX_SIZE - out_num, + true, le64toh(desc[i].addr), + le32toh(desc[i].len))) { + return NULL; + } + } else { + if (in_num) { + fprintf(stderr, "Incorrect order for descriptors\n"); + return NULL; + } + if (!vduse_queue_map_single_desc(vq, &out_num, iov, + VIRTQUEUE_MAX_SIZE, false, + le64toh(desc[i].addr), + le32toh(desc[i].len))) { + return NULL; + } + } + + /* If we've got too many, that implies a descriptor loop. */ + if ((in_num + out_num) > max) { + fprintf(stderr, "Looped descriptor\n"); + return NULL; + } + rc = vduse_queue_read_next_desc(desc, i, max, &i); + } while (rc == VIRTQUEUE_READ_DESC_MORE); + + if (rc == VIRTQUEUE_READ_DESC_ERROR) { + fprintf(stderr, "read descriptor error\n"); + return NULL; + } + + /* Now copy what we have collected and mapped */ + elem = vduse_queue_alloc_element(sz, out_num, in_num); + if (!elem) { + fprintf(stderr, "read descriptor error\n"); + return NULL; + } + elem->index = idx; + for (i = 0; i < out_num; i++) { + elem->out_sg[i] = iov[i]; + } + for (i = 0; i < in_num; i++) { + elem->in_sg[i] = iov[out_num + i]; + } + + return elem; +} + +void *vduse_queue_pop(VduseVirtq *vq, size_t sz) +{ + unsigned int head; + VduseVirtqElement *elem; + VduseDev *dev = vq->dev; + + if (unlikely(!vq->vring.avail)) { + return NULL; + } + + if (vduse_queue_empty(vq)) { + return NULL; + } + /* Needed after virtio_queue_empty() */ + smp_rmb(); + + if (vq->inuse >= vq->vring.num) { + fprintf(stderr, "Virtqueue size exceeded: %d\n", vq->inuse); + return NULL; + } + + if (!vduse_queue_get_head(vq, vq->last_avail_idx++, &head)) { + return NULL; + } + + if (vduse_dev_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) { + vring_set_avail_event(vq, vq->last_avail_idx); + } + + elem = vduse_queue_map_desc(vq, head, sz); + + if (!elem) { + return NULL; + } + + vq->inuse++; + + return elem; +} + +static inline void vring_used_write(VduseVirtq *vq, + struct vring_used_elem *uelem, int i) +{ + struct vring_used *used = vq->vring.used; + + used->ring[i] = *uelem; +} + +static void vduse_queue_fill(VduseVirtq *vq, const VduseVirtqElement *elem, + unsigned int len, unsigned int idx) +{ + struct vring_used_elem uelem; + + if (unlikely(!vq->vring.used)) { + return; + } + + idx = (idx + vq->used_idx) % vq->vring.num; + + uelem.id = htole32(elem->index); + uelem.len = htole32(len); + vring_used_write(vq, &uelem, idx); +} + +static inline void vring_used_idx_set(VduseVirtq *vq, uint16_t val) +{ + vq->vring.used->idx = htole16(val); + vq->used_idx = val; +} + +static void vduse_queue_flush(VduseVirtq *vq, unsigned int count) +{ + uint16_t old, new; + + if (unlikely(!vq->vring.used)) { + return; + } + + /* Make sure buffer is written before we update index. */ + smp_wmb(); + + old = vq->used_idx; + new = old + count; + vring_used_idx_set(vq, new); + vq->inuse -= count; + if (unlikely((int16_t)(new - vq->signalled_used) < (uint16_t)(new - old))) { + vq->signalled_used_valid = false; + } +} + +void vduse_queue_push(VduseVirtq *vq, const VduseVirtqElement *elem, + unsigned int len) +{ + vduse_queue_fill(vq, elem, len, 0); + vduse_queue_flush(vq, 1); +} + +static int vduse_queue_update_vring(VduseVirtq *vq, uint64_t desc_addr, + uint64_t avail_addr, uint64_t used_addr) +{ + struct VduseDev *dev = vq->dev; + uint64_t len; + + len = sizeof(struct vring_desc); + vq->vring.desc = iova_to_va(dev, &len, desc_addr); + if (len != sizeof(struct vring_desc)) { + return -EINVAL; + } + + len = sizeof(struct vring_avail); + vq->vring.avail = iova_to_va(dev, &len, avail_addr); + if (len != sizeof(struct vring_avail)) { + return -EINVAL; + } + + len = sizeof(struct vring_used); + vq->vring.used = iova_to_va(dev, &len, used_addr); + if (len != sizeof(struct vring_used)) { + return -EINVAL; + } + + if (!vq->vring.desc || !vq->vring.avail || !vq->vring.used) { + fprintf(stderr, "Failed to get vq[%d] iova mapping\n", vq->index); + return -EINVAL; + } + + return 0; +} + +static void vduse_queue_enable(VduseVirtq *vq) +{ + struct VduseDev *dev = vq->dev; + struct vduse_vq_info vq_info; + struct vduse_vq_eventfd vq_eventfd; + int fd; + + vq_info.index = vq->index; + if (ioctl(dev->fd, VDUSE_VQ_GET_INFO, &vq_info)) { + fprintf(stderr, "Failed to get vq[%d] info: %s\n", + vq->index, strerror(errno)); + return; + } + + if (!vq_info.ready) { + return; + } + + vq->vring.num = vq_info.num; + vq->vring.desc_addr = vq_info.desc_addr; + vq->vring.avail_addr = vq_info.driver_addr; + vq->vring.used_addr = vq_info.device_addr; + + if (vduse_queue_update_vring(vq, vq_info.desc_addr, + vq_info.driver_addr, vq_info.device_addr)) { + fprintf(stderr, "Failed to update vring for vq[%d]\n", vq->index); + return; + } + + fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC); + if (fd < 0) { + fprintf(stderr, "Failed to init eventfd for vq[%d]\n", vq->index); + return; + } + + vq_eventfd.index = vq->index; + vq_eventfd.fd = fd; + if (ioctl(dev->fd, VDUSE_VQ_SETUP_KICKFD, &vq_eventfd)) { + fprintf(stderr, "Failed to setup kick fd for vq[%d]\n", vq->index); + close(fd); + return; + } + + vq->fd = fd; + vq->shadow_avail_idx = vq->last_avail_idx = vq_info.split.avail_index; + vq->inuse = 0; + vq->used_idx = 0; + vq->signalled_used_valid = false; + vq->ready = true; + + dev->ops->enable_queue(dev, vq); +} + +static void vduse_queue_disable(VduseVirtq *vq) +{ + struct VduseDev *dev = vq->dev; + struct vduse_vq_eventfd eventfd; + + if (!vq->ready) { + return; + } + + dev->ops->disable_queue(dev, vq); + + eventfd.index = vq->index; + eventfd.fd = VDUSE_EVENTFD_DEASSIGN; + ioctl(dev->fd, VDUSE_VQ_SETUP_KICKFD, &eventfd); + close(vq->fd); + + assert(vq->inuse == 0); + + vq->vring.num = 0; + vq->vring.desc_addr = 0; + vq->vring.avail_addr = 0; + vq->vring.used_addr = 0; + vq->vring.desc = 0; + vq->vring.avail = 0; + vq->vring.used = 0; + vq->ready = false; + vq->fd = -1; +} + +static void vduse_dev_start_dataplane(VduseDev *dev) +{ + int i; + + if (ioctl(dev->fd, VDUSE_DEV_GET_FEATURES, &dev->features)) { + fprintf(stderr, "Failed to get features: %s\n", strerror(errno)); + return; + } + assert(vduse_dev_has_feature(dev, VIRTIO_F_VERSION_1)); + + for (i = 0; i < dev->num_queues; i++) { + vduse_queue_enable(&dev->vqs[i]); + } +} + +static void vduse_dev_stop_dataplane(VduseDev *dev) +{ + int i; + + for (i = 0; i < dev->num_queues; i++) { + vduse_queue_disable(&dev->vqs[i]); + } + dev->features = 0; + vduse_iova_remove_region(dev, 0, ULONG_MAX); +} + +int vduse_dev_handler(VduseDev *dev) +{ + struct vduse_dev_request req; + struct vduse_dev_response resp = { 0 }; + VduseVirtq *vq; + int i, ret; + + ret = read(dev->fd, &req, sizeof(req)); + if (ret != sizeof(req)) { + fprintf(stderr, "Read request error [%d]: %s\n", + ret, strerror(errno)); + return -errno; + } + resp.request_id = req.request_id; + + switch (req.type) { + case VDUSE_GET_VQ_STATE: + vq = &dev->vqs[req.vq_state.index]; + resp.vq_state.split.avail_index = vq->last_avail_idx; + resp.result = VDUSE_REQ_RESULT_OK; + break; + case VDUSE_SET_STATUS: + if (req.s.status & VIRTIO_CONFIG_S_DRIVER_OK) { + vduse_dev_start_dataplane(dev); + } else if (req.s.status == 0) { + vduse_dev_stop_dataplane(dev); + } + resp.result = VDUSE_REQ_RESULT_OK; + break; + case VDUSE_UPDATE_IOTLB: + /* The iova will be updated by iova_to_va() later, so just remove it */ + vduse_iova_remove_region(dev, req.iova.start, req.iova.last); + for (i = 0; i < dev->num_queues; i++) { + VduseVirtq *vq = &dev->vqs[i]; + if (vq->ready) { + if (vduse_queue_update_vring(vq, vq->vring.desc_addr, + vq->vring.avail_addr, + vq->vring.used_addr)) { + fprintf(stderr, "Failed to update vring for vq[%d]\n", + vq->index); + } + } + } + resp.result = VDUSE_REQ_RESULT_OK; + break; + default: + resp.result = VDUSE_REQ_RESULT_FAILED; + break; + } + + ret = write(dev->fd, &resp, sizeof(resp)); + if (ret != sizeof(resp)) { + fprintf(stderr, "Write request %d error [%d]: %s\n", + req.type, ret, strerror(errno)); + return -errno; + } + return 0; +} + +int vduse_dev_update_config(VduseDev *dev, uint32_t size, + uint32_t offset, char *buffer) +{ + int ret; + struct vduse_config_data *data; + + data = malloc(offsetof(struct vduse_config_data, buffer) + size); + if (!data) { + return -ENOMEM; + } + + data->offset = offset; + data->length = size; + memcpy(data->buffer, buffer, size); + + ret = ioctl(dev->fd, VDUSE_DEV_SET_CONFIG, data); + free(data); + + if (ret) { + return -errno; + } + + if (ioctl(dev->fd, VDUSE_DEV_INJECT_CONFIG_IRQ)) { + return -errno; + } + + return 0; +} + +int vduse_dev_setup_queue(VduseDev *dev, int index, int max_size) +{ + VduseVirtq *vq = &dev->vqs[index]; + struct vduse_vq_config vq_config = { 0 }; + + if (max_size > VIRTQUEUE_MAX_SIZE) { + return -EINVAL; + } + + vq_config.index = vq->index; + vq_config.max_size = max_size; + + if (ioctl(dev->fd, VDUSE_VQ_SETUP, &vq_config)) { + return -errno; + } + + return 0; +} + +static int vduse_dev_init_vqs(VduseDev *dev, uint16_t num_queues) +{ + VduseVirtq *vqs; + int i; + + vqs = calloc(sizeof(VduseVirtq), num_queues); + if (!vqs) { + return -ENOMEM; + } + + for (i = 0; i < num_queues; i++) { + vqs[i].index = i; + vqs[i].dev = dev; + vqs[i].fd = -1; + } + dev->vqs = vqs; + + return 0; +} + +static int vduse_dev_init(VduseDev *dev, const char *name, + uint16_t num_queues, const VduseOps *ops, + void *priv) +{ + char *dev_path, *dev_name; + int ret, fd; + + dev_path = malloc(strlen(name) + strlen("/dev/vduse/") + 1); + if (!dev_path) { + return -ENOMEM; + } + sprintf(dev_path, "/dev/vduse/%s", name); + + fd = open(dev_path, O_RDWR); + free(dev_path); + if (fd < 0) { + fprintf(stderr, "Failed to open vduse dev %s: %s\n", + name, strerror(errno)); + return -errno; + } + + dev_name = strdup(name); + if (!dev_name) { + close(fd); + return -ENOMEM; + } + + ret = vduse_dev_init_vqs(dev, num_queues); + if (ret) { + free(dev_name); + close(fd); + return ret; + } + + dev->name = dev_name; + dev->num_queues = num_queues; + dev->fd = fd; + dev->ops = ops; + dev->priv = priv; + + return 0; +} + +static inline bool vduse_name_is_valid(const char *name) +{ + return strlen(name) >= VDUSE_NAME_MAX || strstr(name, ".."); +} + +VduseDev *vduse_dev_create_by_fd(int fd, uint16_t num_queues, + const VduseOps *ops, void *priv) +{ + VduseDev *dev; + int ret; + + if (!ops || !ops->enable_queue || !ops->disable_queue) { + fprintf(stderr, "Invalid parameter for vduse\n"); + return NULL; + } + + dev = calloc(sizeof(VduseDev), 1); + if (!dev) { + fprintf(stderr, "Failed to allocate vduse device\n"); + return NULL; + } + + ret = vduse_dev_init_vqs(dev, num_queues); + if (ret) { + fprintf(stderr, "Failed to init vqs\n"); + free(dev); + return NULL; + } + + dev->num_queues = num_queues; + dev->fd = fd; + dev->ops = ops; + dev->priv = priv; + + return dev; +} + +VduseDev *vduse_dev_create_by_name(const char *name, uint16_t num_queues, + const VduseOps *ops, void *priv) +{ + VduseDev *dev; + int ret; + + if (!name || vduse_name_is_valid(name) || !ops || + !ops->enable_queue || !ops->disable_queue) { + fprintf(stderr, "Invalid parameter for vduse\n"); + return NULL; + } + + dev = calloc(sizeof(VduseDev), 1); + if (!dev) { + fprintf(stderr, "Failed to allocate vduse device\n"); + return NULL; + } + + ret = vduse_dev_init(dev, name, num_queues, ops, priv); + if (ret < 0) { + fprintf(stderr, "Failed to init vduse device %s: %s\n", + name, strerror(ret)); + free(dev); + return NULL; + } + + return dev; +} + +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) +{ + VduseDev *dev; + int ret, ctrl_fd; + uint64_t version; + struct vduse_dev_config *dev_config; + size_t size = offsetof(struct vduse_dev_config, config); + + if (!name || vduse_name_is_valid(name) || + !has_feature(features, VIRTIO_F_VERSION_1) || !config || + !config_size || !ops || !ops->enable_queue || !ops->disable_queue) { + fprintf(stderr, "Invalid parameter for vduse\n"); + return NULL; + } + + dev = calloc(sizeof(VduseDev), 1); + if (!dev) { + fprintf(stderr, "Failed to allocate vduse device\n"); + return NULL; + } + + ctrl_fd = open("/dev/vduse/control", O_RDWR); + if (ctrl_fd < 0) { + fprintf(stderr, "Failed to open /dev/vduse/control: %s\n", + strerror(errno)); + goto err_ctrl; + } + + version = VDUSE_API_VERSION; + if (ioctl(ctrl_fd, VDUSE_SET_API_VERSION, &version)) { + fprintf(stderr, "Failed to set api version %lu: %s\n", + version, strerror(errno)); + goto err_dev; + } + + dev_config = calloc(size + config_size, 1); + if (!dev_config) { + fprintf(stderr, "Failed to allocate config space\n"); + goto err_dev; + } + + strcpy(dev_config->name, name); + dev_config->device_id = device_id; + dev_config->vendor_id = vendor_id; + dev_config->features = features; + dev_config->vq_num = num_queues; + dev_config->vq_align = VDUSE_VQ_ALIGN; + dev_config->config_size = config_size; + memcpy(dev_config->config, config, config_size); + + ret = ioctl(ctrl_fd, VDUSE_CREATE_DEV, dev_config); + free(dev_config); + if (ret < 0) { + fprintf(stderr, "Failed to create vduse device %s: %s\n", + name, strerror(errno)); + goto err_dev; + } + dev->ctrl_fd = ctrl_fd; + + ret = vduse_dev_init(dev, name, num_queues, ops, priv); + if (ret < 0) { + fprintf(stderr, "Failed to init vduse device %s: %s\n", + name, strerror(ret)); + goto err; + } + + return dev; +err: + ioctl(ctrl_fd, VDUSE_DESTROY_DEV, name); +err_dev: + close(ctrl_fd); +err_ctrl: + free(dev); + + return NULL; +} + +int vduse_dev_destroy(VduseDev *dev) +{ + int ret = 0; + + free(dev->vqs); + if (dev->fd > 0) { + close(dev->fd); + dev->fd = -1; + } + if (dev->ctrl_fd > 0) { + if (ioctl(dev->ctrl_fd, VDUSE_DESTROY_DEV, dev->name)) { + ret = -errno; + } + close(dev->ctrl_fd); + dev->ctrl_fd = -1; + } + free(dev->name); + free(dev); + + return ret; +} diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-block@nongnu.org S: Supported F: block/export/fuse.c +VDUSE library +M: Xie Yongji <xieyongji@bytedance.com> +S: Maintained +F: subprojects/libvduse/ + Replication M: Wen Congyang <wencongyang2@huawei.com> M: Xie Changlong <xiechanglong.d@gmail.com> diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ 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 + +libvduse = not_found +if have_libvduse + libvduse_proj = subproject('libvduse') + libvduse = libvduse_proj.get_variable('libvduse_dep') +endif + # libbpf libbpf = dependency('libbpf', required: get_option('bpf'), method: 'pkg-config') if libbpf.found() and not cc.links(''' diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh index XXXXXXX..XXXXXXX 100644 --- a/scripts/meson-buildoptions.sh +++ b/scripts/meson-buildoptions.sh @@ -XXX,XX +XXX,XX @@ 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' @@ -XXX,XX +XXX,XX @@ _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 ;; diff --git a/subprojects/libvduse/linux-headers/linux b/subprojects/libvduse/linux-headers/linux new file mode 120000 index XXXXXXX..XXXXXXX --- /dev/null +++ b/subprojects/libvduse/linux-headers/linux @@ -0,0 +1 @@ +../../../linux-headers/linux/ \ No newline at end of file diff --git a/subprojects/libvduse/meson.build b/subprojects/libvduse/meson.build new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/subprojects/libvduse/meson.build @@ -XXX,XX +XXX,XX @@ +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('.')) diff --git a/subprojects/libvduse/standard-headers/linux b/subprojects/libvduse/standard-headers/linux new file mode 120000 index XXXXXXX..XXXXXXX --- /dev/null +++ b/subprojects/libvduse/standard-headers/linux @@ -0,0 +1 @@ +../../../include/standard-headers/linux/ \ No newline at end of file -- 2.35.3 From: Xie Yongji <xieyongji@bytedance.com> This implements a VDUSE block backends based on the libvduse library. We can use it to export the BDSs for both VM and container (host) usage. The new command-line syntax is: $ qemu-storage-daemon \ --blockdev file,node-name=drive0,filename=test.img \ --export vduse-blk,node-name=drive0,id=vduse-export0,writable=on After the qemu-storage-daemon started, we need to use the "vdpa" command to attach the device to vDPA bus: $ vdpa dev add name vduse-export0 mgmtdev vduse Also the device must be removed via the "vdpa" command before we stop the qemu-storage-daemon. Signed-off-by: Xie Yongji <xieyongji@bytedance.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220523084611.91-7-xieyongji@bytedance.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-export.json | 28 +++- meson_options.txt | 2 + block/export/vduse-blk.h | 20 +++ block/export/export.c | 6 + block/export/vduse-blk.c | 307 ++++++++++++++++++++++++++++++++++ MAINTAINERS | 4 +- block/export/meson.build | 5 + meson.build | 13 ++ scripts/meson-buildoptions.sh | 4 + 9 files changed, 385 insertions(+), 4 deletions(-) create mode 100644 block/export/vduse-blk.h create mode 100644 block/export/vduse-blk.c diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ '*allow-other': 'FuseExportAllowOther' }, 'if': 'CONFIG_FUSE' } +## +# @BlockExportOptionsVduseBlk: +# +# A vduse-blk block export. +# +# @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. +# +# Since: 7.1 +## +{ 'struct': 'BlockExportOptionsVduseBlk', + 'data': { '*num-queues': 'uint16', + '*queue-size': 'uint16', + '*logical-block-size': 'size'} } + ## # @NbdServerAddOptions: # @@ -XXX,XX +XXX,XX @@ # @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 ## @@ -XXX,XX +XXX,XX @@ '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: @@ -XXX,XX +XXX,XX @@ # Describes a block export, i.e. how single node should be exported on an # external interface. # -# @id: A unique identifier for the block export (across all export types) +# @id: A unique identifier for the block export (across the host for vduse-blk +# export type or across all export types for other types) # # @node-name: The node name of the block node to be exported (since: 5.2) # @@ -XXX,XX +XXX,XX @@ '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' } } } ## diff --git a/meson_options.txt b/meson_options.txt index XXXXXXX..XXXXXXX 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -XXX,XX +XXX,XX @@ 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') diff --git a/block/export/vduse-blk.h b/block/export/vduse-blk.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/vduse-blk.h @@ -XXX,XX +XXX,XX @@ +/* + * 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 */ diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #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, @@ -XXX,XX +XXX,XX @@ 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 */ diff --git a/block/export/vduse-blk.c b/block/export/vduse-blk.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/vduse-blk.c @@ -XXX,XX +XXX,XX @@ +/* + * 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; +} VduseBlkExport; + +typedef struct VduseBlkReq { + VduseVirtqElement elem; + VduseVirtq *vq; +} VduseBlkReq; + +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); +} + +static void vduse_blk_vq_handler(VduseDev *dev, VduseVirtq *vq) +{ + 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); + 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); +} + +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); +} + + +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 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; + + 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 = exp->id; + 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(exp->id, 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"); + return -ENOMEM; + } + + 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); + + return 0; +} + +static void vduse_blk_exp_delete(BlockExport *exp) +{ + VduseBlkExport *vblk_exp = container_of(exp, VduseBlkExport, export); + + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vblk_exp); + vduse_dev_destroy(vblk_exp->dev); +} + +static void vduse_blk_exp_request_shutdown(BlockExport *exp) +{ + VduseBlkExport *vblk_exp = container_of(exp, VduseBlkExport, export); + + vduse_blk_detach_ctx(vblk_exp); +} + +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, +}; diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-block@nongnu.org S: Supported F: block/export/fuse.c -VDUSE library +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> diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -XXX,XX +XXX,XX @@ if have_vhost_user_blk_server 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 diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ if have_libvduse libvduse = libvduse_proj.get_variable('libvduse_dep') 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(''' @@ -XXX,XX +XXX,XX @@ 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()) @@ -XXX,XX +XXX,XX @@ 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') diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh index XXXXXXX..XXXXXXX 100644 --- a/scripts/meson-buildoptions.sh +++ b/scripts/meson-buildoptions.sh @@ -XXX,XX +XXX,XX @@ 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' @@ -XXX,XX +XXX,XX @@ _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 ;; -- 2.35.3 From: Xie Yongji <xieyongji@bytedance.com> To support block resize, this uses vduse_dev_update_config() to update the capacity field in configuration space and inject config interrupt on the block resize callback. Signed-off-by: Xie Yongji <xieyongji@bytedance.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220523084611.91-8-xieyongji@bytedance.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/export/vduse-blk.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/block/export/vduse-blk.c b/block/export/vduse-blk.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vduse-blk.c +++ b/block/export/vduse-blk.c @@ -XXX,XX +XXX,XX @@ static void blk_aio_detach(void *opaque) 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) { @@ -XXX,XX +XXX,XX @@ static int vduse_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, 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; } @@ -XXX,XX +XXX,XX @@ static void vduse_blk_exp_delete(BlockExport *exp) blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vblk_exp); + blk_set_dev_ops(exp->blk, NULL, NULL); vduse_dev_destroy(vblk_exp->dev); } -- 2.35.3 From: Xie Yongji <xieyongji@bytedance.com> To support reconnecting after restart or crash, VDUSE backend might need to resubmit inflight I/Os. This stores the metadata such as the index of inflight I/O's descriptors to a shm file so that VDUSE backend can restore them during reconnecting. Signed-off-by: Xie Yongji <xieyongji@bytedance.com> Message-Id: <20220523084611.91-9-xieyongji@bytedance.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- subprojects/libvduse/libvduse.h | 12 ++ block/export/vduse-blk.c | 14 ++ subprojects/libvduse/libvduse.c | 235 +++++++++++++++++++++++++++++++- 3 files changed, 256 insertions(+), 5 deletions(-) diff --git a/subprojects/libvduse/libvduse.h b/subprojects/libvduse/libvduse.h index XXXXXXX..XXXXXXX 100644 --- a/subprojects/libvduse/libvduse.h +++ b/subprojects/libvduse/libvduse.h @@ -XXX,XX +XXX,XX @@ int vduse_dev_update_config(VduseDev *dev, uint32_t size, */ 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 diff --git a/block/export/vduse-blk.c b/block/export/vduse-blk.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vduse-blk.c +++ b/block/export/vduse-blk.c @@ -XXX,XX +XXX,XX @@ typedef struct VduseBlkExport { VirtioBlkHandler handler; VduseDev *dev; uint16_t num_queues; + char *recon_file; } VduseBlkExport; typedef struct VduseBlkReq { @@ -XXX,XX +XXX,XX @@ static void vduse_blk_enable_queue(VduseDev *dev, VduseVirtq *vq) 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) @@ -XXX,XX +XXX,XX @@ static int vduse_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, return -ENOMEM; } + vblk_exp->recon_file = g_strdup_printf("%s/vduse-blk-%s", + g_get_tmp_dir(), exp->id); + if (vduse_set_reconnect_log_file(vblk_exp->dev, vblk_exp->recon_file)) { + error_setg(errp, "failed to set reconnect log file"); + vduse_dev_destroy(vblk_exp->dev); + g_free(vblk_exp->recon_file); + return -EINVAL; + } + for (i = 0; i < num_queues; i++) { vduse_dev_setup_queue(vblk_exp->dev, i, queue_size); } @@ -XXX,XX +XXX,XX @@ static void vduse_blk_exp_delete(BlockExport *exp) vblk_exp); blk_set_dev_ops(exp->blk, NULL, NULL); vduse_dev_destroy(vblk_exp->dev); + unlink(vblk_exp->recon_file); + g_free(vblk_exp->recon_file); } static void vduse_blk_exp_request_shutdown(BlockExport *exp) diff --git a/subprojects/libvduse/libvduse.c b/subprojects/libvduse/libvduse.c index XXXXXXX..XXXXXXX 100644 --- a/subprojects/libvduse/libvduse.c +++ b/subprojects/libvduse/libvduse.c @@ -XXX,XX +XXX,XX @@ #define VDUSE_VQ_ALIGN 4096 #define MAX_IOVA_REGIONS 256 +#define LOG_ALIGNMENT 64 + /* Round number down to multiple */ #define ALIGN_DOWN(n, m) ((n) / (m) * (m)) @@ -XXX,XX +XXX,XX @@ #define unlikely(x) __builtin_expect(!!(x), 0) #endif +typedef struct VduseDescStateSplit { + uint8_t inflight; + uint8_t padding[5]; + uint16_t next; + uint64_t counter; +} VduseDescStateSplit; + +typedef struct VduseVirtqLogInflight { + uint64_t features; + uint16_t version; + uint16_t desc_num; + uint16_t last_batch_head; + uint16_t used_idx; + VduseDescStateSplit desc[]; +} VduseVirtqLogInflight; + +typedef struct VduseVirtqLog { + VduseVirtqLogInflight inflight; +} VduseVirtqLog; + +typedef struct VduseVirtqInflightDesc { + uint16_t index; + uint64_t counter; +} VduseVirtqInflightDesc; + typedef struct VduseRing { unsigned int num; uint64_t desc_addr; @@ -XXX,XX +XXX,XX @@ struct VduseVirtq { bool ready; int fd; VduseDev *dev; + VduseVirtqInflightDesc *resubmit_list; + uint16_t resubmit_num; + uint64_t counter; + VduseVirtqLog *log; }; typedef struct VduseIovaRegion { @@ -XXX,XX +XXX,XX @@ struct VduseDev { int fd; int ctrl_fd; void *priv; + void *log; }; +static inline size_t vduse_vq_log_size(uint16_t queue_size) +{ + return ALIGN_UP(sizeof(VduseDescStateSplit) * queue_size + + sizeof(VduseVirtqLogInflight), LOG_ALIGNMENT); +} + +static void *vduse_log_get(const char *filename, size_t size) +{ + void *ptr = MAP_FAILED; + int fd; + + fd = open(filename, O_RDWR | O_CREAT, 0600); + if (fd == -1) { + return MAP_FAILED; + } + + if (ftruncate(fd, size) == -1) { + goto out; + } + + ptr = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + +out: + close(fd); + return ptr; +} + static inline bool has_feature(uint64_t features, unsigned int fbit) { assert(fbit < 64); @@ -XXX,XX +XXX,XX @@ static int vduse_inject_irq(VduseDev *dev, int index) return ioctl(dev->fd, VDUSE_VQ_INJECT_IRQ, &index); } +static int inflight_desc_compare(const void *a, const void *b) +{ + VduseVirtqInflightDesc *desc0 = (VduseVirtqInflightDesc *)a, + *desc1 = (VduseVirtqInflightDesc *)b; + + if (desc1->counter > desc0->counter && + (desc1->counter - desc0->counter) < VIRTQUEUE_MAX_SIZE * 2) { + return 1; + } + + return -1; +} + +static int vduse_queue_check_inflights(VduseVirtq *vq) +{ + int i = 0; + VduseDev *dev = vq->dev; + + vq->used_idx = le16toh(vq->vring.used->idx); + vq->resubmit_num = 0; + vq->resubmit_list = NULL; + vq->counter = 0; + + if (unlikely(vq->log->inflight.used_idx != vq->used_idx)) { + if (vq->log->inflight.last_batch_head > VIRTQUEUE_MAX_SIZE) { + return -1; + } + + vq->log->inflight.desc[vq->log->inflight.last_batch_head].inflight = 0; + + barrier(); + + vq->log->inflight.used_idx = vq->used_idx; + } + + for (i = 0; i < vq->log->inflight.desc_num; i++) { + if (vq->log->inflight.desc[i].inflight == 1) { + vq->inuse++; + } + } + + vq->shadow_avail_idx = vq->last_avail_idx = vq->inuse + vq->used_idx; + + if (vq->inuse) { + vq->resubmit_list = calloc(vq->inuse, sizeof(VduseVirtqInflightDesc)); + if (!vq->resubmit_list) { + return -1; + } + + for (i = 0; i < vq->log->inflight.desc_num; i++) { + if (vq->log->inflight.desc[i].inflight) { + vq->resubmit_list[vq->resubmit_num].index = i; + vq->resubmit_list[vq->resubmit_num].counter = + vq->log->inflight.desc[i].counter; + vq->resubmit_num++; + } + } + + if (vq->resubmit_num > 1) { + qsort(vq->resubmit_list, vq->resubmit_num, + sizeof(VduseVirtqInflightDesc), inflight_desc_compare); + } + vq->counter = vq->resubmit_list[0].counter + 1; + } + + vduse_inject_irq(dev, vq->index); + + return 0; +} + +static int vduse_queue_inflight_get(VduseVirtq *vq, int desc_idx) +{ + vq->log->inflight.desc[desc_idx].counter = vq->counter++; + + barrier(); + + vq->log->inflight.desc[desc_idx].inflight = 1; + + return 0; +} + +static int vduse_queue_inflight_pre_put(VduseVirtq *vq, int desc_idx) +{ + vq->log->inflight.last_batch_head = desc_idx; + + return 0; +} + +static int vduse_queue_inflight_post_put(VduseVirtq *vq, int desc_idx) +{ + vq->log->inflight.desc[desc_idx].inflight = 0; + + barrier(); + + vq->log->inflight.used_idx = vq->used_idx; + + return 0; +} + static void vduse_iova_remove_region(VduseDev *dev, uint64_t start, uint64_t last) { @@ -XXX,XX +XXX,XX @@ void *vduse_queue_pop(VduseVirtq *vq, size_t sz) unsigned int head; VduseVirtqElement *elem; VduseDev *dev = vq->dev; + int i; if (unlikely(!vq->vring.avail)) { return NULL; } + if (unlikely(vq->resubmit_list && vq->resubmit_num > 0)) { + i = (--vq->resubmit_num); + elem = vduse_queue_map_desc(vq, vq->resubmit_list[i].index, sz); + + if (!vq->resubmit_num) { + free(vq->resubmit_list); + vq->resubmit_list = NULL; + } + + return elem; + } + if (vduse_queue_empty(vq)) { return NULL; } @@ -XXX,XX +XXX,XX @@ void *vduse_queue_pop(VduseVirtq *vq, size_t sz) vq->inuse++; + vduse_queue_inflight_get(vq, head); + return elem; } @@ -XXX,XX +XXX,XX @@ void vduse_queue_push(VduseVirtq *vq, const VduseVirtqElement *elem, unsigned int len) { vduse_queue_fill(vq, elem, len, 0); + vduse_queue_inflight_pre_put(vq, elem->index); vduse_queue_flush(vq, 1); + vduse_queue_inflight_post_put(vq, elem->index); } static int vduse_queue_update_vring(VduseVirtq *vq, uint64_t desc_addr, @@ -XXX,XX +XXX,XX @@ static void vduse_queue_enable(VduseVirtq *vq) } vq->fd = fd; - vq->shadow_avail_idx = vq->last_avail_idx = vq_info.split.avail_index; - vq->inuse = 0; - vq->used_idx = 0; vq->signalled_used_valid = false; vq->ready = true; + if (vduse_queue_check_inflights(vq)) { + fprintf(stderr, "Failed to check inflights for vq[%d]\n", vq->index); + close(fd); + return; + } + dev->ops->enable_queue(dev, vq); } @@ -XXX,XX +XXX,XX @@ static void vduse_dev_start_dataplane(VduseDev *dev) static void vduse_dev_stop_dataplane(VduseDev *dev) { + size_t log_size = dev->num_queues * vduse_vq_log_size(VIRTQUEUE_MAX_SIZE); int i; for (i = 0; i < dev->num_queues; i++) { vduse_queue_disable(&dev->vqs[i]); } + if (dev->log) { + memset(dev->log, 0, log_size); + } dev->features = 0; vduse_iova_remove_region(dev, 0, ULONG_MAX); } @@ -XXX,XX +XXX,XX @@ int vduse_dev_setup_queue(VduseDev *dev, int index, int max_size) return -errno; } + vduse_queue_enable(vq); + + return 0; +} + +int vduse_set_reconnect_log_file(VduseDev *dev, const char *filename) +{ + + size_t log_size = dev->num_queues * vduse_vq_log_size(VIRTQUEUE_MAX_SIZE); + void *log; + int i; + + dev->log = log = vduse_log_get(filename, log_size); + if (log == MAP_FAILED) { + fprintf(stderr, "Failed to get vduse log\n"); + return -EINVAL; + } + + for (i = 0; i < dev->num_queues; i++) { + dev->vqs[i].log = log; + dev->vqs[i].log->inflight.desc_num = VIRTQUEUE_MAX_SIZE; + log = (void *)((char *)log + vduse_vq_log_size(VIRTQUEUE_MAX_SIZE)); + } + return 0; } @@ -XXX,XX +XXX,XX @@ static int vduse_dev_init(VduseDev *dev, const char *name, return -errno; } + if (ioctl(fd, VDUSE_DEV_GET_FEATURES, &dev->features)) { + fprintf(stderr, "Failed to get features: %s\n", strerror(errno)); + close(fd); + return -errno; + } + dev_name = strdup(name); if (!dev_name) { close(fd); @@ -XXX,XX +XXX,XX @@ VduseDev *vduse_dev_create_by_fd(int fd, uint16_t num_queues, return NULL; } + if (ioctl(fd, VDUSE_DEV_GET_FEATURES, &dev->features)) { + fprintf(stderr, "Failed to get features: %s\n", strerror(errno)); + free(dev); + return NULL; + } + ret = vduse_dev_init_vqs(dev, num_queues); if (ret) { fprintf(stderr, "Failed to init vqs\n"); @@ -XXX,XX +XXX,XX @@ VduseDev *vduse_dev_create(const char *name, uint32_t device_id, ret = ioctl(ctrl_fd, VDUSE_CREATE_DEV, dev_config); free(dev_config); - if (ret < 0) { + if (ret && errno != EEXIST) { fprintf(stderr, "Failed to create vduse device %s: %s\n", name, strerror(errno)); goto err_dev; @@ -XXX,XX +XXX,XX @@ err_ctrl: int vduse_dev_destroy(VduseDev *dev) { - int ret = 0; + size_t log_size = dev->num_queues * vduse_vq_log_size(VIRTQUEUE_MAX_SIZE); + int i, ret = 0; + if (dev->log) { + munmap(dev->log, log_size); + } + for (i = 0; i < dev->num_queues; i++) { + free(dev->vqs[i].resubmit_list); + } free(dev->vqs); if (dev->fd > 0) { close(dev->fd); -- 2.35.3 From: Stefan Hajnoczi <stefanha@redhat.com> Document vduse-blk exports in qemu-storage-daemon --help and the qemu-storage-daemon(1) man page. Based-on: <20220523084611.91-1-xieyongji@bytedance.com> Cc: Xie Yongji <xieyongji@bytedance.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220525121947.859820-1-stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- docs/tools/qemu-storage-daemon.rst | 21 +++++++++++++++++++++ storage-daemon/qemu-storage-daemon.c | 9 +++++++++ 2 files changed, 30 insertions(+) diff --git a/docs/tools/qemu-storage-daemon.rst b/docs/tools/qemu-storage-daemon.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/tools/qemu-storage-daemon.rst +++ b/docs/tools/qemu-storage-daemon.rst @@ -XXX,XX +XXX,XX @@ 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>[,writable=on|off][,num-queues=<num-queues>][,queue-size=<queue-size>][,logical-block-size=<block-size>] is a block export definition. ``node-name`` is the block node that should be exported. ``writable`` determines whether or not the export allows write @@ -XXX,XX +XXX,XX @@ 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 uses the ``id`` as the VDUSE device name. + ``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 diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c index XXXXXXX..XXXXXXX 100644 --- a/storage-daemon/qemu-storage-daemon.c +++ b/storage-daemon/qemu-storage-daemon.c @@ -XXX,XX +XXX,XX @@ 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" +" [,writable=on|off][,num-queues=<num-queues>]\n" +" [,queue-size=<queue-size>]\n" +" [,logical-block-size=<logical-block-size>]\n" +" export the specified block node as a vduse-blk\n" +" device using the id as the VDUSE device name\n" +"\n" +#endif /* CONFIG_VDUSE_BLK_EXPORT */ " --monitor [chardev=]name[,mode=control][,pretty[=on|off]]\n" " configure a QMP monitor\n" "\n" -- 2.35.3 From: Stefano Garzarella <sgarzare@redhat.com> If the namespace does not exist, rbd_create() fails with -ENOENT and QEMU reports a generic "error rbd create: No such file or directory": $ qemu-img create rbd:rbd/namespace/image 1M Formatting 'rbd:rbd/namespace/image', fmt=raw size=1048576 qemu-img: rbd:rbd/namespace/image: error rbd create: No such file or directory Unfortunately rados_ioctx_set_namespace() does not fail if the namespace does not exist, so let's use rbd_namespace_exists() in qemu_rbd_connect() to check if the namespace exists, reporting a more understandable error: $ qemu-img create rbd:rbd/namespace/image 1M Formatting 'rbd:rbd/namespace/image', fmt=raw size=1048576 qemu-img: rbd:rbd/namespace/image: namespace 'namespace' does not exist Reported-by: Tingting Mao <timao@redhat.com> Reviewed-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-Id: <20220517071012.6120-1-sgarzare@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/rbd.c | 24 ++++++++++++++++++++++++ meson.build | 6 ++++++ 2 files changed, 30 insertions(+) diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ 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 @@ -XXX,XX +XXX,XX @@ 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: diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ 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', -- 2.35.3 From: Fabian Ebner <f.ebner@proxmox.com> On 64-bit platforms, assigning SIZE_MAX to the int64_t max_pdiscard results in a negative value, and the following assertion would trigger down the line (it's not the same max_pdiscard, but computed from the other one): qemu-system-x86_64: ../block/io.c:3166: bdrv_co_pdiscard: Assertion `max_pdiscard >= bs->bl.request_alignment' failed. On 32-bit platforms, it's fine to keep using SIZE_MAX. The assertion in qemu_gluster_co_pdiscard() is checking that the value of 'bytes' can safely be passed to glfs_discard_async(), which takes a size_t for the argument in question, so it is kept as is. And since max_pdiscard is still <= SIZE_MAX, relying on max_pdiscard is still fine. Fixes: 0c8022876f ("block: use int64_t instead of int in driver discard handlers") Cc: qemu-stable@nongnu.org Signed-off-by: Fabian Ebner <f.ebner@proxmox.com> Message-Id: <20220520075922.43972-1-f.ebner@proxmox.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/gluster.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ 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, -- 2.35.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> It seems that aio_wait_kick always required a memory barrier or atomic operation in the caller, but nobody actually took care of doing it. Let's put the barrier in the function instead, and pair it with another one in AIO_WAIT_WHILE. Read aio_wait_kick() comment for further explanation. Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-Id: <20220524173054.12651-1-eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/aio-wait.h | 2 ++ util/aio-wait.c | 16 +++++++++++++++- 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio-wait.h +++ b/include/block/aio-wait.h @@ -XXX,XX +XXX,XX @@ 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); \ diff --git a/util/aio-wait.c b/util/aio-wait.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-wait.c +++ b/util/aio-wait.c @@ -XXX,XX +XXX,XX @@ 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); } -- 2.35.3 From: Eric Blake <eblake@redhat.com> CID 1488362 points out that the second 'rc >= 0' check is now dead code. Reported-by: Peter Maydell <peter.maydell@linaro.org> Fixes: 172f5f1a40(nbd: remove peppering of nbd_client_connected) Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <20220516210519.76135-1-eblake@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/nbd.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/block/nbd.c b/block/nbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -XXX,XX +XXX,XX @@ 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); -- 2.35.3 The following changes since commit 13356edb87506c148b163b8c7eb0695647d00c2a: Merge tag 'block-pull-request' of https://gitlab.com/stefanha/qemu into staging (2023-01-24 09:45:33 +0000) are available in the Git repository at: https://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to d570177b50c389f379f93183155a27d44856ab46: qemu-img: Change info key names for protocol nodes (2023-02-01 16:52:33 +0100) v4: - Fixed the 'qemu-img-close-errors' test case to run only on Linux and only with the file protocol, use qemu-io instead of truncate v3: - Make the compiler happier on BSD and CentOS Stream 8 v2: - Rebased to resolve merge conflicts in coroutine.h ---------------------------------------------------------------- Block layer patches - qemu-img info: Show protocol-level information - Move more functions to coroutines - Make coroutine annotations ready for static analysis - qemu-img: Fix exit code for errors closing the image - qcow2 bitmaps: Fix theoretical corruption in error path - pflash: Only load non-zero parts of backend image to save memory - Code cleanup and test case improvements ---------------------------------------------------------------- Alberto Faria (2): coroutine: annotate coroutine_fn for libclang block: Add no_coroutine_fn and coroutine_mixed_fn marker Emanuele Giuseppe Esposito (14): block-coroutine-wrapper: support void functions block: Convert bdrv_io_plug() to co_wrapper block: Convert bdrv_io_unplug() to co_wrapper block: Convert bdrv_is_inserted() to co_wrapper block: Rename refresh_total_sectors to bdrv_refresh_total_sectors block: Convert bdrv_refresh_total_sectors() to co_wrapper_mixed block-backend: use bdrv_getlength instead of blk_getlength block: use bdrv_co_refresh_total_sectors when possible block: Convert bdrv_get_allocated_file_size() to co_wrapper block: Convert bdrv_get_info() to co_wrapper_mixed block: Convert bdrv_eject() to co_wrapper block: Convert bdrv_lock_medium() to co_wrapper block: Convert bdrv_debug_event() to co_wrapper_mixed block: Rename bdrv_load/save_vmstate() to bdrv_co_load/save_vmstate() Hanna Reitz (12): block: Improve empty format-specific info dump block/file: Add file-specific image info block/vmdk: Change extent info type block: Split BlockNodeInfo off of ImageInfo qemu-img: Use BlockNodeInfo block/qapi: Let bdrv_query_image_info() recurse block/qapi: Introduce BlockGraphInfo block/qapi: Add indentation to bdrv_node_info_dump() iotests: Filter child node information iotests/106, 214, 308: Read only one size line qemu-img: Let info print block graph qemu-img: Change info key names for protocol nodes Kevin Wolf (4): qcow2: Fix theoretical corruption in store_bitmap() error path qemu-img commit: Report errors while closing the image qemu-img bitmap: Report errors while closing the image qemu-iotests: Test qemu-img bitmap/commit exit code on error Paolo Bonzini (2): qemu-io: do not reinvent the blk_pwrite_zeroes wheel block: remove bdrv_coroutine_enter Philippe Mathieu-Daudé (1): block/nbd: Add missing <qemu/bswap.h> include Thomas Huth (2): tests/qemu-iotests/312: Mark "quorum" as required driver tests/qemu-iotests/262: Check for availability of "blkverify" first Xiang Zheng (1): pflash: Only read non-zero parts of backend image qapi/block-core.json | 123 +++++++- include/block/block-common.h | 11 +- include/block/block-io.h | 41 ++- include/block/block_int-common.h | 26 +- include/block/block_int-io.h | 5 +- include/block/nbd.h | 1 + include/block/qapi.h | 14 +- include/qemu/osdep.h | 44 +++ include/sysemu/block-backend-io.h | 31 +- block.c | 88 +++--- block/blkdebug.c | 11 +- block/blkio.c | 15 +- block/blklogwrites.c | 6 +- block/blkreplay.c | 6 +- block/blkverify.c | 6 +- block/block-backend.c | 38 +-- block/commit.c | 4 +- block/copy-on-read.c | 18 +- block/crypto.c | 14 +- block/curl.c | 10 +- block/file-posix.c | 137 +++++---- block/file-win32.c | 18 +- block/filter-compress.c | 20 +- block/gluster.c | 23 +- block/io.c | 76 ++--- block/iscsi.c | 17 +- block/mirror.c | 6 +- block/monitor/block-hmp-cmds.c | 2 +- block/nbd.c | 8 +- block/nfs.c | 4 +- block/null.c | 13 +- block/nvme.c | 14 +- block/preallocate.c | 16 +- block/qapi.c | 317 ++++++++++++++++----- block/qcow.c | 5 +- block/qcow2-bitmap.c | 5 +- block/qcow2-refcount.c | 2 +- block/qcow2.c | 17 +- block/qed.c | 11 +- block/quorum.c | 8 +- block/raw-format.c | 25 +- block/rbd.c | 9 +- block/replication.c | 6 +- block/ssh.c | 4 +- block/throttle.c | 6 +- block/vdi.c | 7 +- block/vhdx.c | 5 +- block/vmdk.c | 22 +- block/vpc.c | 5 +- blockdev.c | 8 +- hw/block/block.c | 36 ++- hw/scsi/scsi-disk.c | 5 + qemu-img.c | 100 +++++-- qemu-io-cmds.c | 62 +--- tests/unit/test-block-iothread.c | 3 + scripts/block-coroutine-wrapper.py | 20 +- tests/qemu-iotests/iotests.py | 18 +- block/meson.build | 1 + tests/qemu-iotests/065 | 2 +- tests/qemu-iotests/106 | 4 +- tests/qemu-iotests/214 | 6 +- tests/qemu-iotests/262 | 3 +- tests/qemu-iotests/302.out | 5 + tests/qemu-iotests/308 | 4 +- tests/qemu-iotests/312 | 1 + tests/qemu-iotests/common.filter | 22 +- tests/qemu-iotests/common.rc | 22 +- tests/qemu-iotests/tests/qemu-img-close-errors | 96 +++++++ tests/qemu-iotests/tests/qemu-img-close-errors.out | 23 ++ 69 files changed, 1209 insertions(+), 552 deletions(-) create mode 100755 tests/qemu-iotests/tests/qemu-img-close-errors create mode 100644 tests/qemu-iotests/tests/qemu-img-close-errors.out