Re: [RFC v5 08/11] virtio-blk: add zoned storage APIs for zoned devices
On Sun, 31 Jul 2022 at 21:43, Sam Li wrote:
>
> This patch extends virtio-blk emulation to handle zoned device commands
> by calling the new block layer APIs to perform zoned device I/O on
> behalf of the guest. It supports Report Zone, and four zone oparations (open,
> close, finish, reset). The virtio-blk zoned device command specifications
> is currently in the reviewing process.
>
> VIRTIO_BLK_F_ZONED will only be set if the host does support zoned block
> devices. The regular block device will not be set. The guest os having
> zoned device support can use blkzone(8) to test those commands.
>
> Signed-off-by: Sam Li
> ---
> block/block-backend.c | 92
> hw/block/virtio-blk.c | 172 +-
> include/sysemu/block-backend-io.h | 6 ++
> 3 files changed, 268 insertions(+), 2 deletions(-)
>
> diff --git a/block/block-backend.c b/block/block-backend.c
> index ef6a1f33d5..8f2cfcbd9d 100644
> --- a/block/block-backend.c
> +++ b/block/block-backend.c
> @@ -1431,6 +1431,15 @@ typedef struct BlkRwCo {
> void *iobuf;
> int ret;
> BdrvRequestFlags flags;
> +union {
> +struct {
> +unsigned int *nr_zones;
> +BlockZoneDescriptor *zones;
> +} zone_report;
> +struct {
> +BlockZoneOp op;
> +} zone_mgmt;
> +};
> } BlkRwCo;
>
> int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags)
> @@ -1775,6 +1784,89 @@ int coroutine_fn blk_co_flush(BlockBackend *blk)
> return ret;
> }
>
> +static void blk_aio_zone_report_entry(void *opaque) {
> +BlkAioEmAIOCB *acb = opaque;
> +BlkRwCo *rwco = &acb->rwco;
> +
> +rwco->ret = blk_co_zone_report(rwco->blk, rwco->offset,
> + rwco->zone_report.nr_zones,
> + rwco->zone_report.zones);
> +blk_aio_complete(acb);
> +}
> +
> +BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset,
> +unsigned int *nr_zones,
> +BlockZoneDescriptor *zones,
> +BlockCompletionFunc *cb, void *opaque)
> +{
> +BlkAioEmAIOCB *acb;
> +Coroutine *co;
> +
> +blk_inc_in_flight(blk);
> +acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
> +acb->rwco = (BlkRwCo) {
> +.blk= blk,
> +.offset = offset,
> +.ret= NOT_DONE,
> +.zone_report = {
> +.zones = zones,
> +.nr_zones = nr_zones,
> +},
> +};
> +acb->has_returned = false;
> +
> +co = qemu_coroutine_create(blk_aio_zone_report_entry, acb);
> +bdrv_coroutine_enter(blk_bs(blk), co);
> +
> +acb->has_returned = true;
> +if (acb->rwco.ret != NOT_DONE) {
> +replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
> + blk_aio_complete_bh, acb);
> +}
> +
> +return &acb->common;
> +}
> +
> +static void blk_aio_zone_mgmt_entry(void *opaque) {
> +BlkAioEmAIOCB *acb = opaque;
> +BlkRwCo *rwco = &acb->rwco;
> +
> +rwco->ret = blk_co_zone_mgmt(rwco->blk, rwco->zone_mgmt.op,
> + rwco->offset, acb->bytes);
> +blk_aio_complete(acb);
> +}
> +
> +BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
> + int64_t offset, int64_t len,
> + BlockCompletionFunc *cb, void *opaque) {
> +BlkAioEmAIOCB *acb;
> +Coroutine *co;
> +
> +blk_inc_in_flight(blk);
> +acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
> +acb->rwco = (BlkRwCo) {
> +.blk= blk,
> +.offset = offset,
> +.ret= NOT_DONE,
> +.zone_mgmt = {
> +.op = op,
> +},
> +};
> +acb->bytes = len;
> +acb->has_returned = false;
> +
> +co = qemu_coroutine_create(blk_aio_zone_mgmt_entry, acb);
> +bdrv_coroutine_enter(blk_bs(blk), co);
> +
> +acb->has_returned = true;
> +if (acb->rwco.ret != NOT_DONE) {
> +replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
> + blk_aio_complete_bh, acb);
> +}
> +
> +return &acb->common;
> +}
> +
> /*
> * Send a zone_report command.
> * offset is a byte offset from the start of the device. No alignment
> diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
> index e9ba752f6b..9722f447a2 100644
> --- a/hw/block/virtio-blk.c
> +++ b/hw/block/virtio-blk.c
> @@ -37,6 +37,7 @@
> /* Config size before the discard support (hide associated config fields) */
> #define VIRTIO_BLK_CFG_SIZE offsetof(struct virtio_blk_config, \
> max_discard_sectors)
> +
> /*
> * Starting from the discard feature, we can use this array to properly
> * set the config size depending on the features enabled.
>
[RFC v5 08/11] virtio-blk: add zoned storage APIs for zoned devices
This patch extends virtio-blk emulation to handle zoned device commands
by calling the new block layer APIs to perform zoned device I/O on
behalf of the guest. It supports Report Zone, and four zone oparations (open,
close, finish, reset). The virtio-blk zoned device command specifications
is currently in the reviewing process.
VIRTIO_BLK_F_ZONED will only be set if the host does support zoned block
devices. The regular block device will not be set. The guest os having
zoned device support can use blkzone(8) to test those commands.
Signed-off-by: Sam Li
---
block/block-backend.c | 92
hw/block/virtio-blk.c | 172 +-
include/sysemu/block-backend-io.h | 6 ++
3 files changed, 268 insertions(+), 2 deletions(-)
diff --git a/block/block-backend.c b/block/block-backend.c
index ef6a1f33d5..8f2cfcbd9d 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1431,6 +1431,15 @@ typedef struct BlkRwCo {
void *iobuf;
int ret;
BdrvRequestFlags flags;
+union {
+struct {
+unsigned int *nr_zones;
+BlockZoneDescriptor *zones;
+} zone_report;
+struct {
+BlockZoneOp op;
+} zone_mgmt;
+};
} BlkRwCo;
int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags)
@@ -1775,6 +1784,89 @@ int coroutine_fn blk_co_flush(BlockBackend *blk)
return ret;
}
+static void blk_aio_zone_report_entry(void *opaque) {
+BlkAioEmAIOCB *acb = opaque;
+BlkRwCo *rwco = &acb->rwco;
+
+rwco->ret = blk_co_zone_report(rwco->blk, rwco->offset,
+ rwco->zone_report.nr_zones,
+ rwco->zone_report.zones);
+blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset,
+unsigned int *nr_zones,
+BlockZoneDescriptor *zones,
+BlockCompletionFunc *cb, void *opaque)
+{
+BlkAioEmAIOCB *acb;
+Coroutine *co;
+
+blk_inc_in_flight(blk);
+acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
+acb->rwco = (BlkRwCo) {
+.blk= blk,
+.offset = offset,
+.ret= NOT_DONE,
+.zone_report = {
+.zones = zones,
+.nr_zones = nr_zones,
+},
+};
+acb->has_returned = false;
+
+co = qemu_coroutine_create(blk_aio_zone_report_entry, acb);
+bdrv_coroutine_enter(blk_bs(blk), co);
+
+acb->has_returned = true;
+if (acb->rwco.ret != NOT_DONE) {
+replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+ blk_aio_complete_bh, acb);
+}
+
+return &acb->common;
+}
+
+static void blk_aio_zone_mgmt_entry(void *opaque) {
+BlkAioEmAIOCB *acb = opaque;
+BlkRwCo *rwco = &acb->rwco;
+
+rwco->ret = blk_co_zone_mgmt(rwco->blk, rwco->zone_mgmt.op,
+ rwco->offset, acb->bytes);
+blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+ int64_t offset, int64_t len,
+ BlockCompletionFunc *cb, void *opaque) {
+BlkAioEmAIOCB *acb;
+Coroutine *co;
+
+blk_inc_in_flight(blk);
+acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
+acb->rwco = (BlkRwCo) {
+.blk= blk,
+.offset = offset,
+.ret= NOT_DONE,
+.zone_mgmt = {
+.op = op,
+},
+};
+acb->bytes = len;
+acb->has_returned = false;
+
+co = qemu_coroutine_create(blk_aio_zone_mgmt_entry, acb);
+bdrv_coroutine_enter(blk_bs(blk), co);
+
+acb->has_returned = true;
+if (acb->rwco.ret != NOT_DONE) {
+replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+ blk_aio_complete_bh, acb);
+}
+
+return &acb->common;
+}
+
/*
* Send a zone_report command.
* offset is a byte offset from the start of the device. No alignment
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index e9ba752f6b..9722f447a2 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -37,6 +37,7 @@
/* Config size before the discard support (hide associated config fields) */
#define VIRTIO_BLK_CFG_SIZE offsetof(struct virtio_blk_config, \
max_discard_sectors)
+
/*
* Starting from the discard feature, we can use this array to properly
* set the config size depending on the features enabled.
@@ -46,6 +47,8 @@ static const VirtIOFeature feature_sizes[] = {
.end = endof(struct virtio_blk_config, discard_sector_alignment)},
{.flags = 1ULL << VIRTIO_BLK_F_WRITE_ZEROES,
.end = endof(struct virtio_blk_config, write_zeroes_may_unmap)},
+{.flags = 1ULL << VIRTIO_BLK_F_ZONED,
+ .end = endo
