* [RFC v6 1/4] include: update virtio_blk headers
2023-01-29 10:39 [RFC v6 0/4] Add zoned storage emulation to virtio-blk driver Sam Li
@ 2023-01-29 10:39 ` Sam Li
2023-01-29 10:39 ` [RFC v6 2/4] virtio-blk: add zoned storage emulation for zoned devices Sam Li
` (2 subsequent siblings)
3 siblings, 0 replies; 9+ messages in thread
From: Sam Li @ 2023-01-29 10:39 UTC (permalink / raw)
To: qemu-devel
Cc: dmitry.fomichev, Raphael Norwitz, stefanha, Michael S. Tsirkin,
Kevin Wolf, damien.lemoal, hare, Markus Armbruster, qemu-block,
Eric Blake, Hanna Reitz, Sam Li
Use scripts/update-linux-headers.sh to update virtio-blk headers
from Dmitry's "virtio-blk:add support for zoned block devices"
Linux patches.
Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
---
include/standard-headers/linux/virtio_blk.h | 158 ++++++++++++++++++--
1 file changed, 142 insertions(+), 16 deletions(-)
diff --git a/include/standard-headers/linux/virtio_blk.h b/include/standard-headers/linux/virtio_blk.h
index 2dcc90826a..3744e4da1b 100644
--- a/include/standard-headers/linux/virtio_blk.h
+++ b/include/standard-headers/linux/virtio_blk.h
@@ -25,10 +25,10 @@
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE. */
-#include "standard-headers/linux/types.h"
-#include "standard-headers/linux/virtio_ids.h"
-#include "standard-headers/linux/virtio_config.h"
-#include "standard-headers/linux/virtio_types.h"
+#include <linux/types.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_types.h>
/* Feature bits */
#define VIRTIO_BLK_F_SIZE_MAX 1 /* Indicates maximum segment size */
@@ -40,6 +40,8 @@
#define VIRTIO_BLK_F_MQ 12 /* support more than one vq */
#define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */
#define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */
+#define VIRTIO_BLK_F_SECURE_ERASE 16 /* Secure Erase is supported */
+#define VIRTIO_BLK_F_ZONED 17 /* Zoned block device */
/* Legacy feature bits */
#ifndef VIRTIO_BLK_NO_LEGACY
@@ -47,8 +49,10 @@
#define VIRTIO_BLK_F_SCSI 7 /* Supports scsi command passthru */
#define VIRTIO_BLK_F_FLUSH 9 /* Flush command supported */
#define VIRTIO_BLK_F_CONFIG_WCE 11 /* Writeback mode available in config */
+#ifndef __KERNEL__
/* Old (deprecated) name for VIRTIO_BLK_F_FLUSH. */
#define VIRTIO_BLK_F_WCE VIRTIO_BLK_F_FLUSH
+#endif
#endif /* !VIRTIO_BLK_NO_LEGACY */
#define VIRTIO_BLK_ID_BYTES 20 /* ID string length */
@@ -63,8 +67,8 @@ struct virtio_blk_config {
/* geometry of the device (if VIRTIO_BLK_F_GEOMETRY) */
struct virtio_blk_geometry {
__virtio16 cylinders;
- uint8_t heads;
- uint8_t sectors;
+ __u8 heads;
+ __u8 sectors;
} geometry;
/* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */
@@ -72,17 +76,17 @@ struct virtio_blk_config {
/* the next 4 entries are guarded by VIRTIO_BLK_F_TOPOLOGY */
/* exponent for physical block per logical block. */
- uint8_t physical_block_exp;
+ __u8 physical_block_exp;
/* alignment offset in logical blocks. */
- uint8_t alignment_offset;
+ __u8 alignment_offset;
/* minimum I/O size without performance penalty in logical blocks. */
__virtio16 min_io_size;
/* optimal sustained I/O size in logical blocks. */
__virtio32 opt_io_size;
/* writeback mode (if VIRTIO_BLK_F_CONFIG_WCE) */
- uint8_t wce;
- uint8_t unused;
+ __u8 wce;
+ __u8 unused;
/* number of vqs, only available when VIRTIO_BLK_F_MQ is set */
__virtio16 num_queues;
@@ -116,10 +120,35 @@ struct virtio_blk_config {
* Set if a VIRTIO_BLK_T_WRITE_ZEROES request may result in the
* deallocation of one or more of the sectors.
*/
- uint8_t write_zeroes_may_unmap;
+ __u8 write_zeroes_may_unmap;
- uint8_t unused1[3];
-} QEMU_PACKED;
+ __u8 unused1[3];
+
+ /* the next 3 entries are guarded by VIRTIO_BLK_F_SECURE_ERASE */
+ /*
+ * The maximum secure erase sectors (in 512-byte sectors) for
+ * one segment.
+ */
+ __virtio32 max_secure_erase_sectors;
+ /*
+ * The maximum number of secure erase segments in a
+ * secure erase command.
+ */
+ __virtio32 max_secure_erase_seg;
+ /* Secure erase commands must be aligned to this number of sectors. */
+ __virtio32 secure_erase_sector_alignment;
+
+ /* Zoned block device characteristics (if VIRTIO_BLK_F_ZONED) */
+ struct virtio_blk_zoned_characteristics {
+ __virtio32 zone_sectors;
+ __virtio32 max_open_zones;
+ __virtio32 max_active_zones;
+ __virtio32 max_append_sectors;
+ __virtio32 write_granularity;
+ __u8 model;
+ __u8 unused2[3];
+ } zoned;
+} __attribute__((packed));
/*
* Command types
@@ -153,6 +182,30 @@ struct virtio_blk_config {
/* Write zeroes command */
#define VIRTIO_BLK_T_WRITE_ZEROES 13
+/* Secure erase command */
+#define VIRTIO_BLK_T_SECURE_ERASE 14
+
+/* Zone append command */
+#define VIRTIO_BLK_T_ZONE_APPEND 15
+
+/* Report zones command */
+#define VIRTIO_BLK_T_ZONE_REPORT 16
+
+/* Open zone command */
+#define VIRTIO_BLK_T_ZONE_OPEN 18
+
+/* Close zone command */
+#define VIRTIO_BLK_T_ZONE_CLOSE 20
+
+/* Finish zone command */
+#define VIRTIO_BLK_T_ZONE_FINISH 22
+
+/* Reset zone command */
+#define VIRTIO_BLK_T_ZONE_RESET 24
+
+/* Reset All zones command */
+#define VIRTIO_BLK_T_ZONE_RESET_ALL 26
+
#ifndef VIRTIO_BLK_NO_LEGACY
/* Barrier before this op. */
#define VIRTIO_BLK_T_BARRIER 0x80000000
@@ -172,17 +225,83 @@ struct virtio_blk_outhdr {
__virtio64 sector;
};
+/*
+ * Supported zoned device models.
+ */
+
+/* Regular block device */
+#define VIRTIO_BLK_Z_NONE 0
+/* Host-managed zoned device */
+#define VIRTIO_BLK_Z_HM 1
+/* Host-aware zoned device */
+#define VIRTIO_BLK_Z_HA 2
+
+/*
+ * Zone descriptor. A part of VIRTIO_BLK_T_ZONE_REPORT command reply.
+ */
+struct virtio_blk_zone_descriptor {
+ /* Zone capacity */
+ __virtio64 z_cap;
+ /* The starting sector of the zone */
+ __virtio64 z_start;
+ /* Zone write pointer position in sectors */
+ __virtio64 z_wp;
+ /* Zone type */
+ __u8 z_type;
+ /* Zone state */
+ __u8 z_state;
+ __u8 reserved[38];
+};
+
+struct virtio_blk_zone_report {
+ __virtio64 nr_zones;
+ __u8 reserved[56];
+ struct virtio_blk_zone_descriptor zones[];
+};
+
+/*
+ * Supported zone types.
+ */
+
+/* Conventional zone */
+#define VIRTIO_BLK_ZT_CONV 1
+/* Sequential Write Required zone */
+#define VIRTIO_BLK_ZT_SWR 2
+/* Sequential Write Preferred zone */
+#define VIRTIO_BLK_ZT_SWP 3
+
+/*
+ * Zone states that are available for zones of all types.
+ */
+
+/* Not a write pointer (conventional zones only) */
+#define VIRTIO_BLK_ZS_NOT_WP 0
+/* Empty */
+#define VIRTIO_BLK_ZS_EMPTY 1
+/* Implicitly Open */
+#define VIRTIO_BLK_ZS_IOPEN 2
+/* Explicitly Open */
+#define VIRTIO_BLK_ZS_EOPEN 3
+/* Closed */
+#define VIRTIO_BLK_ZS_CLOSED 4
+/* Read-Only */
+#define VIRTIO_BLK_ZS_RDONLY 13
+/* Full */
+#define VIRTIO_BLK_ZS_FULL 14
+/* Offline */
+#define VIRTIO_BLK_ZS_OFFLINE 15
+
/* Unmap this range (only valid for write zeroes command) */
#define VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP 0x00000001
/* Discard/write zeroes range for each request. */
struct virtio_blk_discard_write_zeroes {
/* discard/write zeroes start sector */
- uint64_t sector;
+ __le64 sector;
/* number of discard/write zeroes sectors */
- uint32_t num_sectors;
+ __le32 num_sectors;
/* flags for this range */
- uint32_t flags;
+ __le32 flags;
};
#ifndef VIRTIO_BLK_NO_LEGACY
@@ -198,4 +317,11 @@ struct virtio_scsi_inhdr {
#define VIRTIO_BLK_S_OK 0
#define VIRTIO_BLK_S_IOERR 1
#define VIRTIO_BLK_S_UNSUPP 2
+
+/* Error codes that are specific to zoned block devices */
+#define VIRTIO_BLK_S_ZONE_INVALID_CMD 3
+#define VIRTIO_BLK_S_ZONE_UNALIGNED_WP 4
+#define VIRTIO_BLK_S_ZONE_OPEN_RESOURCE 5
+#define VIRTIO_BLK_S_ZONE_ACTIVE_RESOURCE 6
+
#endif /* _LINUX_VIRTIO_BLK_H */
--
2.38.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [RFC v6 2/4] virtio-blk: add zoned storage emulation for zoned devices
2023-01-29 10:39 [RFC v6 0/4] Add zoned storage emulation to virtio-blk driver Sam Li
2023-01-29 10:39 ` [RFC v6 1/4] include: update virtio_blk headers Sam Li
@ 2023-01-29 10:39 ` Sam Li
2023-01-30 12:32 ` Daniel P. Berrangé
2023-01-29 10:39 ` [RFC v6 3/4] block: add accounting for zone append operation Sam Li
2023-01-29 10:39 ` [RFC v6 4/4] virtio-blk: add some trace events for zoned emulation Sam Li
3 siblings, 1 reply; 9+ messages in thread
From: Sam Li @ 2023-01-29 10:39 UTC (permalink / raw)
To: qemu-devel
Cc: dmitry.fomichev, Raphael Norwitz, stefanha, Michael S. Tsirkin,
Kevin Wolf, damien.lemoal, hare, Markus Armbruster, qemu-block,
Eric Blake, Hanna Reitz, Sam Li
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, four zone oparations (open,
close, finish, reset), and Append Zone.
The VIRTIO_BLK_F_ZONED feature bit will only be set if the host does
support zoned block devices. Regular block devices(conventional zones)
will not be set.
The guest os can use blktests, fio to test those commands on zoned devices.
Furthermore, using zonefs to test zone append write is also supported.
Signed-off-by: Sam Li <faithilikerun@gmail.com>
---
hw/block/virtio-blk-common.c | 2 +
hw/block/virtio-blk.c | 394 +++++++++++++++++++++++++++++++++++
2 files changed, 396 insertions(+)
diff --git a/hw/block/virtio-blk-common.c b/hw/block/virtio-blk-common.c
index ac52d7c176..e2f8e2f6da 100644
--- a/hw/block/virtio-blk-common.c
+++ b/hw/block/virtio-blk-common.c
@@ -29,6 +29,8 @@ 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 = endof(struct virtio_blk_config, zoned)},
{}
};
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 1762517878..09220f400d 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -17,6 +17,7 @@
#include "qemu/module.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
+#include "block/block_int.h"
#include "trace.h"
#include "hw/block/block.h"
#include "hw/qdev-properties.h"
@@ -601,6 +602,341 @@ err:
return err_status;
}
+typedef struct ZoneCmdData {
+ VirtIOBlockReq *req;
+ struct iovec *in_iov;
+ unsigned in_num;
+ union {
+ struct {
+ unsigned int nr_zones;
+ BlockZoneDescriptor *zones;
+ } zone_report_data;
+ struct {
+ int64_t offset;
+ } zone_append_data;
+ };
+} ZoneCmdData;
+
+/*
+ * check zoned_request: error checking before issuing requests. If all checks
+ * passed, return true.
+ * append: true if only zone append requests issued.
+ */
+static bool check_zoned_request(VirtIOBlock *s, int64_t offset, int64_t len,
+ bool append, uint8_t *status) {
+ BlockDriverState *bs = blk_bs(s->blk);
+ int index;
+
+ if (!virtio_has_feature(s->host_features, VIRTIO_BLK_F_ZONED)) {
+ *status = VIRTIO_BLK_S_UNSUPP;
+ return false;
+ }
+
+ if (offset < 0 || len < 0 || len > (bs->total_sectors << BDRV_SECTOR_BITS)
+ || offset > (bs->total_sectors << BDRV_SECTOR_BITS) - len) {
+ *status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ return false;
+ }
+
+ if (append) {
+ if (bs->bl.write_granularity) {
+ if ((offset % bs->bl.write_granularity) != 0) {
+ *status = VIRTIO_BLK_S_ZONE_UNALIGNED_WP;
+ return false;
+ }
+ }
+
+ index = offset / bs->bl.zone_size;
+ if (BDRV_ZT_IS_CONV(bs->bl.wps->wp[index])) {
+ *status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ return false;
+ }
+
+ if (len / 512 > bs->bl.max_append_sectors) {
+ if (bs->bl.max_append_sectors == 0) {
+ *status = VIRTIO_BLK_S_UNSUPP;
+ } else {
+ *status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ }
+ return false;
+ }
+ }
+ return true;
+}
+
+static void virtio_blk_zone_report_complete(void *opaque, int ret)
+{
+ ZoneCmdData *data = opaque;
+ VirtIOBlockReq *req = data->req;
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(req->dev);
+ struct iovec *in_iov = data->in_iov;
+ unsigned in_num = data->in_num;
+ int64_t zrp_size, n, j = 0;
+ int64_t nz = data->zone_report_data.nr_zones;
+ int8_t err_status = VIRTIO_BLK_S_OK;
+
+ if (ret) {
+ err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ goto out;
+ }
+
+ struct virtio_blk_zone_report zrp_hdr = (struct virtio_blk_zone_report) {
+ .nr_zones = cpu_to_le64(nz),
+ };
+ zrp_size = sizeof(struct virtio_blk_zone_report)
+ + sizeof(struct virtio_blk_zone_descriptor) * nz;
+ n = iov_from_buf(in_iov, in_num, 0, &zrp_hdr, sizeof(zrp_hdr));
+ if (n != sizeof(zrp_hdr)) {
+ virtio_error(vdev, "Driver provided input buffer that is too small!");
+ err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ goto out;
+ }
+
+ for (size_t i = sizeof(zrp_hdr); i < zrp_size;
+ i += sizeof(struct virtio_blk_zone_descriptor), ++j) {
+ struct virtio_blk_zone_descriptor desc =
+ (struct virtio_blk_zone_descriptor) {
+ .z_start = cpu_to_le64(data->zone_report_data.zones[j].start
+ >> BDRV_SECTOR_BITS),
+ .z_cap = cpu_to_le64(data->zone_report_data.zones[j].cap
+ >> BDRV_SECTOR_BITS),
+ .z_wp = cpu_to_le64(data->zone_report_data.zones[j].wp
+ >> BDRV_SECTOR_BITS),
+ };
+
+ switch (data->zone_report_data.zones[j].type) {
+ case BLK_ZT_CONV:
+ desc.z_type = VIRTIO_BLK_ZT_CONV;
+ break;
+ case BLK_ZT_SWR:
+ desc.z_type = VIRTIO_BLK_ZT_SWR;
+ break;
+ case BLK_ZT_SWP:
+ desc.z_type = VIRTIO_BLK_ZT_SWP;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ switch (data->zone_report_data.zones[j].state) {
+ case BLK_ZS_RDONLY:
+ desc.z_state = VIRTIO_BLK_ZS_RDONLY;
+ break;
+ case BLK_ZS_OFFLINE:
+ desc.z_state = VIRTIO_BLK_ZS_OFFLINE;
+ break;
+ case BLK_ZS_EMPTY:
+ desc.z_state = VIRTIO_BLK_ZS_EMPTY;
+ break;
+ case BLK_ZS_CLOSED:
+ desc.z_state = VIRTIO_BLK_ZS_CLOSED;
+ break;
+ case BLK_ZS_FULL:
+ desc.z_state = VIRTIO_BLK_ZS_FULL;
+ break;
+ case BLK_ZS_EOPEN:
+ desc.z_state = VIRTIO_BLK_ZS_EOPEN;
+ break;
+ case BLK_ZS_IOPEN:
+ desc.z_state = VIRTIO_BLK_ZS_IOPEN;
+ break;
+ case BLK_ZS_NOT_WP:
+ desc.z_state = VIRTIO_BLK_ZS_NOT_WP;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ /* TODO: it takes O(n^2) time complexity. Optimizations required. */
+ n = iov_from_buf(in_iov, in_num, i, &desc, sizeof(desc));
+ if (n != sizeof(desc)) {
+ virtio_error(vdev, "Driver provided input buffer "
+ "for descriptors that is too small!");
+ err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ }
+ }
+
+out:
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ virtio_blk_req_complete(req, err_status);
+ virtio_blk_free_request(req);
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+ g_free(data->zone_report_data.zones);
+ g_free(data);
+}
+
+static int virtio_blk_handle_zone_report(VirtIOBlockReq *req,
+ struct iovec *in_iov,
+ unsigned in_num)
+{
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+ unsigned int nr_zones;
+ ZoneCmdData *data;
+ int64_t zone_size, offset;
+ uint8_t err_status;
+
+ if (req->in_len < sizeof(struct virtio_blk_inhdr) +
+ sizeof(struct virtio_blk_zone_report) +
+ sizeof(struct virtio_blk_zone_descriptor)) {
+ virtio_error(vdev, "in buffer too small for zone report");
+ return -1;
+ }
+
+ /* start byte offset of the zone report */
+ offset = virtio_ldq_p(vdev, &req->out.sector) << BDRV_SECTOR_BITS;
+ if (!check_zoned_request(s, offset, 0, false, &err_status)) {
+ goto out;
+ }
+ nr_zones = (req->in_len - sizeof(struct virtio_blk_inhdr) -
+ sizeof(struct virtio_blk_zone_report)) /
+ sizeof(struct virtio_blk_zone_descriptor);
+
+ zone_size = sizeof(BlockZoneDescriptor) * nr_zones;
+ data = g_malloc(sizeof(ZoneCmdData));
+ data->req = req;
+ data->in_iov = in_iov;
+ data->in_num = in_num;
+ data->zone_report_data.nr_zones = nr_zones;
+ data->zone_report_data.zones = g_malloc(zone_size),
+
+ blk_aio_zone_report(s->blk, offset, &data->zone_report_data.nr_zones,
+ data->zone_report_data.zones,
+ virtio_blk_zone_report_complete, data);
+ return 0;
+
+out:
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ virtio_blk_req_complete(req, err_status);
+ virtio_blk_free_request(req);
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+ return err_status;
+}
+
+static void virtio_blk_zone_mgmt_complete(void *opaque, int ret)
+{
+ VirtIOBlockReq *req = opaque;
+ VirtIOBlock *s = req->dev;
+ int8_t err_status = VIRTIO_BLK_S_OK;
+
+ if (ret) {
+ err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ }
+
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ virtio_blk_req_complete(req, err_status);
+ virtio_blk_free_request(req);
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+}
+
+static int virtio_blk_handle_zone_mgmt(VirtIOBlockReq *req, BlockZoneOp op)
+{
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+ BlockDriverState *bs = blk_bs(s->blk);
+ int64_t offset = virtio_ldq_p(vdev, &req->out.sector) << BDRV_SECTOR_BITS;
+ uint64_t len;
+ uint64_t capacity = bs->total_sectors << BDRV_SECTOR_BITS;
+ uint8_t err_status = VIRTIO_BLK_S_OK;
+
+ uint32_t type = virtio_ldl_p(vdev, &req->out.type);
+ if (type == VIRTIO_BLK_T_ZONE_RESET_ALL) {
+ /* Entire drive capacity */
+ offset = 0;
+ len = capacity;
+ } else {
+ if (bs->bl.zone_size > capacity - offset) {
+ /* The zoned device allows the last smaller zone. */
+ len = capacity - bs->bl.zone_size * (bs->bl.nr_zones - 1);
+ } else {
+ len = bs->bl.zone_size;
+ }
+ }
+
+ if (!check_zoned_request(s, offset, len, false, &err_status)) {
+ goto out;
+ }
+
+ blk_aio_zone_mgmt(s->blk, op, offset, len,
+ virtio_blk_zone_mgmt_complete, req);
+
+ return 0;
+out:
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ virtio_blk_req_complete(req, err_status);
+ virtio_blk_free_request(req);
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+ return err_status;
+}
+
+static void virtio_blk_zone_append_complete(void *opaque, int ret)
+{
+ ZoneCmdData *data = opaque;
+ VirtIOBlockReq *req = data->req;
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(req->dev);
+ int64_t append_sector, n;
+ uint8_t err_status = VIRTIO_BLK_S_OK;
+
+ if (ret) {
+ err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ goto out;
+ }
+
+ virtio_stq_p(vdev, &append_sector,
+ data->zone_append_data.offset >> BDRV_SECTOR_BITS);
+ n = iov_from_buf(data->in_iov, data->in_num, 0, &append_sector,
+ sizeof(append_sector));
+ if (n != sizeof(append_sector)) {
+ virtio_error(vdev, "Driver provided input buffer less than size of "
+ "append_sector");
+ err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
+ goto out;
+ }
+
+out:
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ virtio_blk_req_complete(req, err_status);
+ virtio_blk_free_request(req);
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+ g_free(data);
+}
+
+static int virtio_blk_handle_zone_append(VirtIOBlockReq *req,
+ struct iovec *out_iov,
+ struct iovec *in_iov,
+ uint64_t out_num,
+ unsigned in_num) {
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+ uint8_t err_status = VIRTIO_BLK_S_OK;
+
+ int64_t offset = virtio_ldq_p(vdev, &req->out.sector) << BDRV_SECTOR_BITS;
+ int64_t len = iov_size(out_iov, out_num);
+
+ if (!check_zoned_request(s, offset, len, true, &err_status)) {
+ goto out;
+ }
+
+ ZoneCmdData *data = g_malloc(sizeof(ZoneCmdData));
+ data->req = req;
+ data->in_iov = in_iov;
+ data->in_num = in_num;
+ data->zone_append_data.offset = offset;
+ qemu_iovec_init_external(&req->qiov, out_iov, out_num);
+ blk_aio_zone_append(s->blk, &data->zone_append_data.offset, &req->qiov, 0,
+ virtio_blk_zone_append_complete, data);
+ return 0;
+
+out:
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ virtio_blk_req_complete(req, err_status);
+ virtio_blk_free_request(req);
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+ return err_status;
+}
+
static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
uint32_t type;
@@ -687,6 +1023,24 @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
case VIRTIO_BLK_T_FLUSH:
virtio_blk_handle_flush(req, mrb);
break;
+ case VIRTIO_BLK_T_ZONE_REPORT:
+ virtio_blk_handle_zone_report(req, in_iov, in_num);
+ break;
+ case VIRTIO_BLK_T_ZONE_OPEN:
+ virtio_blk_handle_zone_mgmt(req, BLK_ZO_OPEN);
+ break;
+ case VIRTIO_BLK_T_ZONE_CLOSE:
+ virtio_blk_handle_zone_mgmt(req, BLK_ZO_CLOSE);
+ break;
+ case VIRTIO_BLK_T_ZONE_FINISH:
+ virtio_blk_handle_zone_mgmt(req, BLK_ZO_FINISH);
+ break;
+ case VIRTIO_BLK_T_ZONE_RESET:
+ virtio_blk_handle_zone_mgmt(req, BLK_ZO_RESET);
+ break;
+ case VIRTIO_BLK_T_ZONE_RESET_ALL:
+ virtio_blk_handle_zone_mgmt(req, BLK_ZO_RESET);
+ break;
case VIRTIO_BLK_T_SCSI_CMD:
virtio_blk_handle_scsi(req);
break;
@@ -705,6 +1059,13 @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
virtio_blk_free_request(req);
break;
}
+ case VIRTIO_BLK_T_ZONE_APPEND & ~VIRTIO_BLK_T_OUT:
+ /*
+ * It is not safe to access req->elem.out_sg directly because it
+ * may be modified by virtio_blk_handle_request().
+ */
+ virtio_blk_handle_zone_append(req, out_iov, in_iov, out_num, in_num);
+ break;
/*
* VIRTIO_BLK_T_DISCARD and VIRTIO_BLK_T_WRITE_ZEROES are defined with
* VIRTIO_BLK_T_OUT flag set. We masked this flag in the switch statement,
@@ -890,6 +1251,7 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
BlockConf *conf = &s->conf.conf;
+ BlockDriverState *bs = blk_bs(s->blk);
struct virtio_blk_config blkcfg;
uint64_t capacity;
int64_t length;
@@ -949,6 +1311,30 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
blkcfg.write_zeroes_may_unmap = 1;
virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1);
}
+ if (bs->bl.zoned != BLK_Z_NONE) {
+ switch (bs->bl.zoned) {
+ case BLK_Z_HM:
+ blkcfg.zoned.model = VIRTIO_BLK_Z_HM;
+ break;
+ case BLK_Z_HA:
+ blkcfg.zoned.model = VIRTIO_BLK_Z_HA;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ virtio_stl_p(vdev, &blkcfg.zoned.zone_sectors,
+ bs->bl.zone_size / 512);
+ virtio_stl_p(vdev, &blkcfg.zoned.max_active_zones,
+ bs->bl.max_active_zones);
+ virtio_stl_p(vdev, &blkcfg.zoned.max_open_zones,
+ bs->bl.max_open_zones);
+ virtio_stl_p(vdev, &blkcfg.zoned.write_granularity, blk_size);
+ virtio_stl_p(vdev, &blkcfg.zoned.max_append_sectors,
+ bs->bl.max_append_sectors);
+ } else {
+ blkcfg.zoned.model = VIRTIO_BLK_Z_NONE;
+ }
memcpy(config, &blkcfg, s->config_size);
}
@@ -1113,6 +1499,7 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOBlock *s = VIRTIO_BLK(dev);
VirtIOBlkConf *conf = &s->conf;
+ BlockDriverState *bs = blk_bs(conf->conf.blk);
Error *err = NULL;
unsigned i;
@@ -1158,6 +1545,13 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
return;
}
+ if (bs->bl.zoned != BLK_Z_NONE) {
+ virtio_add_feature(&s->host_features, VIRTIO_BLK_F_ZONED);
+ if (bs->bl.zoned == BLK_Z_HM) {
+ virtio_clear_feature(&s->host_features, VIRTIO_BLK_F_DISCARD);
+ }
+ }
+
if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_DISCARD) &&
(!conf->max_discard_sectors ||
conf->max_discard_sectors > BDRV_REQUEST_MAX_SECTORS)) {
--
2.38.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* Re: [RFC v6 2/4] virtio-blk: add zoned storage emulation for zoned devices
2023-01-29 10:39 ` [RFC v6 2/4] virtio-blk: add zoned storage emulation for zoned devices Sam Li
@ 2023-01-30 12:32 ` Daniel P. Berrangé
2023-01-30 15:17 ` Stefan Hajnoczi
0 siblings, 1 reply; 9+ messages in thread
From: Daniel P. Berrangé @ 2023-01-30 12:32 UTC (permalink / raw)
To: Sam Li
Cc: qemu-devel, dmitry.fomichev, Raphael Norwitz, stefanha,
Michael S. Tsirkin, Kevin Wolf, damien.lemoal, hare,
Markus Armbruster, qemu-block, Eric Blake, Hanna Reitz
On Sun, Jan 29, 2023 at 06:39:49PM +0800, 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, four zone oparations (open,
> close, finish, reset), and Append Zone.
>
> The VIRTIO_BLK_F_ZONED feature bit will only be set if the host does
> support zoned block devices. Regular block devices(conventional zones)
> will not be set.
>
> The guest os can use blktests, fio to test those commands on zoned devices.
> Furthermore, using zonefs to test zone append write is also supported.
>
> Signed-off-by: Sam Li <faithilikerun@gmail.com>
> ---
> hw/block/virtio-blk-common.c | 2 +
> hw/block/virtio-blk.c | 394 +++++++++++++++++++++++++++++++++++
> 2 files changed, 396 insertions(+)
>
> @@ -949,6 +1311,30 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
> blkcfg.write_zeroes_may_unmap = 1;
> virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1);
> }
> + if (bs->bl.zoned != BLK_Z_NONE) {
> + switch (bs->bl.zoned) {
> + case BLK_Z_HM:
> + blkcfg.zoned.model = VIRTIO_BLK_Z_HM;
> + break;
> + case BLK_Z_HA:
> + blkcfg.zoned.model = VIRTIO_BLK_Z_HA;
> + break;
> + default:
> + g_assert_not_reached();
> + }
> +
> + virtio_stl_p(vdev, &blkcfg.zoned.zone_sectors,
> + bs->bl.zone_size / 512);
> + virtio_stl_p(vdev, &blkcfg.zoned.max_active_zones,
> + bs->bl.max_active_zones);
> + virtio_stl_p(vdev, &blkcfg.zoned.max_open_zones,
> + bs->bl.max_open_zones);
> + virtio_stl_p(vdev, &blkcfg.zoned.write_granularity, blk_size);
> + virtio_stl_p(vdev, &blkcfg.zoned.max_append_sectors,
> + bs->bl.max_append_sectors);
So these are all ABI sensitive frontend device settings, but they are
not exposed as tunables on the virtio-blk device, instead they are
implicitly set from the backend.
We have done this kind of thing before in QEMU, but several times it
has bitten QEMU maintainers/users, as having a backend affect the
frontend ABI is not to typical. It wouldn't be immediately obvious
when starting QEMU on a target host that the live migration would
be breaking ABI if the target host wasn't using a zoned device with
exact same settings.
This also limits mgmt flexibility across live migration, if the
mgmt app wants/needs to change the storage backend. eg maybe they
need to evacuate the host for an emergency, but don't have spare
hosts with same kind of storage. It might be desirable to migrate
and switch to a plain block device or raw/qcow2 file, rather than
let the VM die.
Can we make these virtio setting be explicitly controlled on the
virtio-blk device. If not specified explicitly they could be
auto-populated from the backend for ease of use, but if specified
then simply validate the backend is a match. libvirt would then
make sure these are always explicitly set on the frontend.
With regards,
Daniel
--
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org -o- https://fstop138.berrange.com :|
|: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [RFC v6 2/4] virtio-blk: add zoned storage emulation for zoned devices
2023-01-30 12:32 ` Daniel P. Berrangé
@ 2023-01-30 15:17 ` Stefan Hajnoczi
2023-01-30 18:30 ` Daniel P. Berrangé
0 siblings, 1 reply; 9+ messages in thread
From: Stefan Hajnoczi @ 2023-01-30 15:17 UTC (permalink / raw)
To: Daniel P. Berrangé
Cc: Sam Li, qemu-devel, dmitry.fomichev, Raphael Norwitz, stefanha,
Michael S. Tsirkin, Kevin Wolf, damien.lemoal, hare,
Markus Armbruster, qemu-block, Eric Blake, Hanna Reitz
On Mon, 30 Jan 2023 at 07:33, Daniel P. Berrangé <berrange@redhat.com> wrote:
>
> On Sun, Jan 29, 2023 at 06:39:49PM +0800, 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, four zone oparations (open,
> > close, finish, reset), and Append Zone.
> >
> > The VIRTIO_BLK_F_ZONED feature bit will only be set if the host does
> > support zoned block devices. Regular block devices(conventional zones)
> > will not be set.
> >
> > The guest os can use blktests, fio to test those commands on zoned devices.
> > Furthermore, using zonefs to test zone append write is also supported.
> >
> > Signed-off-by: Sam Li <faithilikerun@gmail.com>
> > ---
> > hw/block/virtio-blk-common.c | 2 +
> > hw/block/virtio-blk.c | 394 +++++++++++++++++++++++++++++++++++
> > 2 files changed, 396 insertions(+)
> >
>
> > @@ -949,6 +1311,30 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
> > blkcfg.write_zeroes_may_unmap = 1;
> > virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1);
> > }
> > + if (bs->bl.zoned != BLK_Z_NONE) {
> > + switch (bs->bl.zoned) {
> > + case BLK_Z_HM:
> > + blkcfg.zoned.model = VIRTIO_BLK_Z_HM;
> > + break;
> > + case BLK_Z_HA:
> > + blkcfg.zoned.model = VIRTIO_BLK_Z_HA;
> > + break;
> > + default:
> > + g_assert_not_reached();
> > + }
> > +
> > + virtio_stl_p(vdev, &blkcfg.zoned.zone_sectors,
> > + bs->bl.zone_size / 512);
> > + virtio_stl_p(vdev, &blkcfg.zoned.max_active_zones,
> > + bs->bl.max_active_zones);
> > + virtio_stl_p(vdev, &blkcfg.zoned.max_open_zones,
> > + bs->bl.max_open_zones);
> > + virtio_stl_p(vdev, &blkcfg.zoned.write_granularity, blk_size);
> > + virtio_stl_p(vdev, &blkcfg.zoned.max_append_sectors,
> > + bs->bl.max_append_sectors);
>
> So these are all ABI sensitive frontend device settings, but they are
> not exposed as tunables on the virtio-blk device, instead they are
> implicitly set from the backend.
>
> We have done this kind of thing before in QEMU, but several times it
> has bitten QEMU maintainers/users, as having a backend affect the
> frontend ABI is not to typical. It wouldn't be immediately obvious
> when starting QEMU on a target host that the live migration would
> be breaking ABI if the target host wasn't using a zoned device with
> exact same settings.
>
> This also limits mgmt flexibility across live migration, if the
> mgmt app wants/needs to change the storage backend. eg maybe they
> need to evacuate the host for an emergency, but don't have spare
> hosts with same kind of storage. It might be desirable to migrate
> and switch to a plain block device or raw/qcow2 file, rather than
> let the VM die.
>
> Can we make these virtio setting be explicitly controlled on the
> virtio-blk device. If not specified explicitly they could be
> auto-populated from the backend for ease of use, but if specified
> then simply validate the backend is a match. libvirt would then
> make sure these are always explicitly set on the frontend.
I think this is a good idea, especially if we streamline the
file-posix.c driver by merging --blockdev zoned_host_device into
--blockdev host_device. It won't be obvious from the command-line
whether this is a zoned or non-zoned device. There should be a
--device virtio-blk-pci,drive=drive0,zoned=on option that fails when
drive0 isn't zoned. It should probably be on/off/auto where auto is
the default and doesn't check anything, on requires a zoned device,
and off requires a non-zoned device. That will prevent accidental
migration between zoned/non-zoned devices.
I want to point out that virtio-blk doesn't have checks for the disk
size or other details, so what you're suggesting for zone_sectors, etc
is stricter than what QEMU does today. Since the virtio-blk parameters
you're proposing are optional, I think it doesn't hurt though.
Stefan
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [RFC v6 2/4] virtio-blk: add zoned storage emulation for zoned devices
2023-01-30 15:17 ` Stefan Hajnoczi
@ 2023-01-30 18:30 ` Daniel P. Berrangé
2023-01-31 14:10 ` Stefan Hajnoczi
0 siblings, 1 reply; 9+ messages in thread
From: Daniel P. Berrangé @ 2023-01-30 18:30 UTC (permalink / raw)
To: Stefan Hajnoczi
Cc: Sam Li, qemu-devel, dmitry.fomichev, Raphael Norwitz, stefanha,
Michael S. Tsirkin, Kevin Wolf, damien.lemoal, hare,
Markus Armbruster, qemu-block, Eric Blake, Hanna Reitz
On Mon, Jan 30, 2023 at 10:17:48AM -0500, Stefan Hajnoczi wrote:
> On Mon, 30 Jan 2023 at 07:33, Daniel P. Berrangé <berrange@redhat.com> wrote:
> >
> > On Sun, Jan 29, 2023 at 06:39:49PM +0800, 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, four zone oparations (open,
> > > close, finish, reset), and Append Zone.
> > >
> > > The VIRTIO_BLK_F_ZONED feature bit will only be set if the host does
> > > support zoned block devices. Regular block devices(conventional zones)
> > > will not be set.
> > >
> > > The guest os can use blktests, fio to test those commands on zoned devices.
> > > Furthermore, using zonefs to test zone append write is also supported.
> > >
> > > Signed-off-by: Sam Li <faithilikerun@gmail.com>
> > > ---
> > > hw/block/virtio-blk-common.c | 2 +
> > > hw/block/virtio-blk.c | 394 +++++++++++++++++++++++++++++++++++
> > > 2 files changed, 396 insertions(+)
> > >
> >
> > > @@ -949,6 +1311,30 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
> > > blkcfg.write_zeroes_may_unmap = 1;
> > > virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1);
> > > }
> > > + if (bs->bl.zoned != BLK_Z_NONE) {
> > > + switch (bs->bl.zoned) {
> > > + case BLK_Z_HM:
> > > + blkcfg.zoned.model = VIRTIO_BLK_Z_HM;
> > > + break;
> > > + case BLK_Z_HA:
> > > + blkcfg.zoned.model = VIRTIO_BLK_Z_HA;
> > > + break;
> > > + default:
> > > + g_assert_not_reached();
> > > + }
> > > +
> > > + virtio_stl_p(vdev, &blkcfg.zoned.zone_sectors,
> > > + bs->bl.zone_size / 512);
> > > + virtio_stl_p(vdev, &blkcfg.zoned.max_active_zones,
> > > + bs->bl.max_active_zones);
> > > + virtio_stl_p(vdev, &blkcfg.zoned.max_open_zones,
> > > + bs->bl.max_open_zones);
> > > + virtio_stl_p(vdev, &blkcfg.zoned.write_granularity, blk_size);
> > > + virtio_stl_p(vdev, &blkcfg.zoned.max_append_sectors,
> > > + bs->bl.max_append_sectors);
> >
> > So these are all ABI sensitive frontend device settings, but they are
> > not exposed as tunables on the virtio-blk device, instead they are
> > implicitly set from the backend.
> >
> > We have done this kind of thing before in QEMU, but several times it
> > has bitten QEMU maintainers/users, as having a backend affect the
> > frontend ABI is not to typical. It wouldn't be immediately obvious
> > when starting QEMU on a target host that the live migration would
> > be breaking ABI if the target host wasn't using a zoned device with
> > exact same settings.
> >
> > This also limits mgmt flexibility across live migration, if the
> > mgmt app wants/needs to change the storage backend. eg maybe they
> > need to evacuate the host for an emergency, but don't have spare
> > hosts with same kind of storage. It might be desirable to migrate
> > and switch to a plain block device or raw/qcow2 file, rather than
> > let the VM die.
> >
> > Can we make these virtio setting be explicitly controlled on the
> > virtio-blk device. If not specified explicitly they could be
> > auto-populated from the backend for ease of use, but if specified
> > then simply validate the backend is a match. libvirt would then
> > make sure these are always explicitly set on the frontend.
>
> I think this is a good idea, especially if we streamline the
> file-posix.c driver by merging --blockdev zoned_host_device into
> --blockdev host_device. It won't be obvious from the command-line
> whether this is a zoned or non-zoned device. There should be a
> --device virtio-blk-pci,drive=drive0,zoned=on option that fails when
> drive0 isn't zoned. It should probably be on/off/auto where auto is
> the default and doesn't check anything, on requires a zoned device,
> and off requires a non-zoned device. That will prevent accidental
> migration between zoned/non-zoned devices.
>
> I want to point out that virtio-blk doesn't have checks for the disk
> size or other details, so what you're suggesting for zone_sectors, etc
> is stricter than what QEMU does today. Since the virtio-blk parameters
> you're proposing are optional, I think it doesn't hurt though.
Yeah, it is slightly different than some of the parameters handling.
I guess you could say that with disk capacity, matching size is a
fairly obvious constraint/expectation to manage, and also long standing.
With disk capacity, you can add the 'raw' driver on top of any block
driver stack, to apply an arbitrary offset+size, to make the storage
smaller than it otherwise is on disk. Conceptually than could have
been done on the frontend device(s) too, but I guess it made more
sense to do it in the block layer to give consistent enforcement
of the limits across frontends. It is fuzzy whether such a use of
the 'raw' driver is really considered backend config, as opposed to
frontend config but to me it feels likle frontend config.
You could possibly come up with the concept of a 'zoned' format that
can be layered on top of a block driver stack to add zoned I/O constraints
for sake of compatibility, where none otherwise exists in the physical
storage. Possibly useful if multiple frontends all support zoned storage,
to avoid duplicating the constraints across all ?
With regards,
Daniel
--
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org -o- https://fstop138.berrange.com :|
|: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [RFC v6 2/4] virtio-blk: add zoned storage emulation for zoned devices
2023-01-30 18:30 ` Daniel P. Berrangé
@ 2023-01-31 14:10 ` Stefan Hajnoczi
0 siblings, 0 replies; 9+ messages in thread
From: Stefan Hajnoczi @ 2023-01-31 14:10 UTC (permalink / raw)
To: Daniel P. Berrangé
Cc: Stefan Hajnoczi, Sam Li, qemu-devel, dmitry.fomichev,
Raphael Norwitz, Michael S. Tsirkin, Kevin Wolf, damien.lemoal,
hare, Markus Armbruster, qemu-block, Eric Blake, Hanna Reitz
[-- Attachment #1: Type: text/plain, Size: 6740 bytes --]
On Mon, Jan 30, 2023 at 06:30:16PM +0000, Daniel P. Berrangé wrote:
> On Mon, Jan 30, 2023 at 10:17:48AM -0500, Stefan Hajnoczi wrote:
> > On Mon, 30 Jan 2023 at 07:33, Daniel P. Berrangé <berrange@redhat.com> wrote:
> > >
> > > On Sun, Jan 29, 2023 at 06:39:49PM +0800, 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, four zone oparations (open,
> > > > close, finish, reset), and Append Zone.
> > > >
> > > > The VIRTIO_BLK_F_ZONED feature bit will only be set if the host does
> > > > support zoned block devices. Regular block devices(conventional zones)
> > > > will not be set.
> > > >
> > > > The guest os can use blktests, fio to test those commands on zoned devices.
> > > > Furthermore, using zonefs to test zone append write is also supported.
> > > >
> > > > Signed-off-by: Sam Li <faithilikerun@gmail.com>
> > > > ---
> > > > hw/block/virtio-blk-common.c | 2 +
> > > > hw/block/virtio-blk.c | 394 +++++++++++++++++++++++++++++++++++
> > > > 2 files changed, 396 insertions(+)
> > > >
> > >
> > > > @@ -949,6 +1311,30 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
> > > > blkcfg.write_zeroes_may_unmap = 1;
> > > > virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1);
> > > > }
> > > > + if (bs->bl.zoned != BLK_Z_NONE) {
> > > > + switch (bs->bl.zoned) {
> > > > + case BLK_Z_HM:
> > > > + blkcfg.zoned.model = VIRTIO_BLK_Z_HM;
> > > > + break;
> > > > + case BLK_Z_HA:
> > > > + blkcfg.zoned.model = VIRTIO_BLK_Z_HA;
> > > > + break;
> > > > + default:
> > > > + g_assert_not_reached();
> > > > + }
> > > > +
> > > > + virtio_stl_p(vdev, &blkcfg.zoned.zone_sectors,
> > > > + bs->bl.zone_size / 512);
> > > > + virtio_stl_p(vdev, &blkcfg.zoned.max_active_zones,
> > > > + bs->bl.max_active_zones);
> > > > + virtio_stl_p(vdev, &blkcfg.zoned.max_open_zones,
> > > > + bs->bl.max_open_zones);
> > > > + virtio_stl_p(vdev, &blkcfg.zoned.write_granularity, blk_size);
> > > > + virtio_stl_p(vdev, &blkcfg.zoned.max_append_sectors,
> > > > + bs->bl.max_append_sectors);
> > >
> > > So these are all ABI sensitive frontend device settings, but they are
> > > not exposed as tunables on the virtio-blk device, instead they are
> > > implicitly set from the backend.
> > >
> > > We have done this kind of thing before in QEMU, but several times it
> > > has bitten QEMU maintainers/users, as having a backend affect the
> > > frontend ABI is not to typical. It wouldn't be immediately obvious
> > > when starting QEMU on a target host that the live migration would
> > > be breaking ABI if the target host wasn't using a zoned device with
> > > exact same settings.
> > >
> > > This also limits mgmt flexibility across live migration, if the
> > > mgmt app wants/needs to change the storage backend. eg maybe they
> > > need to evacuate the host for an emergency, but don't have spare
> > > hosts with same kind of storage. It might be desirable to migrate
> > > and switch to a plain block device or raw/qcow2 file, rather than
> > > let the VM die.
> > >
> > > Can we make these virtio setting be explicitly controlled on the
> > > virtio-blk device. If not specified explicitly they could be
> > > auto-populated from the backend for ease of use, but if specified
> > > then simply validate the backend is a match. libvirt would then
> > > make sure these are always explicitly set on the frontend.
> >
> > I think this is a good idea, especially if we streamline the
> > file-posix.c driver by merging --blockdev zoned_host_device into
> > --blockdev host_device. It won't be obvious from the command-line
> > whether this is a zoned or non-zoned device. There should be a
> > --device virtio-blk-pci,drive=drive0,zoned=on option that fails when
> > drive0 isn't zoned. It should probably be on/off/auto where auto is
> > the default and doesn't check anything, on requires a zoned device,
> > and off requires a non-zoned device. That will prevent accidental
> > migration between zoned/non-zoned devices.
> >
> > I want to point out that virtio-blk doesn't have checks for the disk
> > size or other details, so what you're suggesting for zone_sectors, etc
> > is stricter than what QEMU does today. Since the virtio-blk parameters
> > you're proposing are optional, I think it doesn't hurt though.
>
> Yeah, it is slightly different than some of the parameters handling.
> I guess you could say that with disk capacity, matching size is a
> fairly obvious constraint/expectation to manage, and also long standing.
>
> With disk capacity, you can add the 'raw' driver on top of any block
> driver stack, to apply an arbitrary offset+size, to make the storage
> smaller than it otherwise is on disk. Conceptually than could have
> been done on the frontend device(s) too, but I guess it made more
> sense to do it in the block layer to give consistent enforcement
> of the limits across frontends. It is fuzzy whether such a use of
> the 'raw' driver is really considered backend config, as opposed to
> frontend config but to me it feels likle frontend config.
>
> You could possibly come up with the concept of a 'zoned' format that
> can be layered on top of a block driver stack to add zoned I/O constraints
> for sake of compatibility, where none otherwise exists in the physical
> storage. Possibly useful if multiple frontends all support zoned storage,
> to avoid duplicating the constraints across all ?
Maybe:
DEFINE_BLOCK_ZONED_PROPERTIES(VirtIOBlock, conf.conf),
and then:
bool blkconf_check_zoned_properties(BlockBackend *blk, BlockZonedConf *conf, Error **errp);
That macro and helper function can be shared by all emulated storage
controllers that implement zoned storage.
However, there's one problem: some storage interfaces extend the zoned
storage model (e.g. NVMe ZNS seems to have functionality that's not
available elsewhere). It would be necessary to check whether there is a
common subset of parameters with matching property names (because
terminology could be different) across emulated storage controllers.
But I think it's likely that this will work. I think the macro and
helper function approach is nice because it's internal to QEMU and users
don't need to set up a --blockdev enforce-zoned.
Stefan
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 9+ messages in thread
* [RFC v6 3/4] block: add accounting for zone append operation
2023-01-29 10:39 [RFC v6 0/4] Add zoned storage emulation to virtio-blk driver Sam Li
2023-01-29 10:39 ` [RFC v6 1/4] include: update virtio_blk headers Sam Li
2023-01-29 10:39 ` [RFC v6 2/4] virtio-blk: add zoned storage emulation for zoned devices Sam Li
@ 2023-01-29 10:39 ` Sam Li
2023-01-29 10:39 ` [RFC v6 4/4] virtio-blk: add some trace events for zoned emulation Sam Li
3 siblings, 0 replies; 9+ messages in thread
From: Sam Li @ 2023-01-29 10:39 UTC (permalink / raw)
To: qemu-devel
Cc: dmitry.fomichev, Raphael Norwitz, stefanha, Michael S. Tsirkin,
Kevin Wolf, damien.lemoal, hare, Markus Armbruster, qemu-block,
Eric Blake, Hanna Reitz, Sam Li
Taking account of the new zone append write operation for zoned devices,
BLOCK_ACCT_APPEND enum is introduced as other I/O request type (read,
write, flush).
Signed-off-by: Sam Li <faithilikerun@gmail.com>
---
block/qapi-sysemu.c | 11 ++++++++
block/qapi.c | 15 ++++++++++
hw/block/virtio-blk.c | 4 +++
include/block/accounting.h | 1 +
qapi/block-core.json | 56 ++++++++++++++++++++++++++++++--------
qapi/block.json | 4 +++
6 files changed, 80 insertions(+), 11 deletions(-)
diff --git a/block/qapi-sysemu.c b/block/qapi-sysemu.c
index 7bd7554150..f7e56dfeb2 100644
--- a/block/qapi-sysemu.c
+++ b/block/qapi-sysemu.c
@@ -517,6 +517,7 @@ void qmp_block_latency_histogram_set(
bool has_boundaries, uint64List *boundaries,
bool has_boundaries_read, uint64List *boundaries_read,
bool has_boundaries_write, uint64List *boundaries_write,
+ bool has_boundaries_append, uint64List *boundaries_append,
bool has_boundaries_flush, uint64List *boundaries_flush,
Error **errp)
{
@@ -557,6 +558,16 @@ void qmp_block_latency_histogram_set(
}
}
+ if (has_boundaries || has_boundaries_append) {
+ ret = block_latency_histogram_set(
+ stats, BLOCK_ACCT_APPEND,
+ has_boundaries_append ? boundaries_append : boundaries);
+ if (ret) {
+ error_setg(errp, "Device '%s' set append write boundaries fail", id);
+ return;
+ }
+ }
+
if (has_boundaries || has_boundaries_flush) {
ret = block_latency_histogram_set(
stats, BLOCK_ACCT_FLUSH,
diff --git a/block/qapi.c b/block/qapi.c
index 9b4da12966..0b37a21af7 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -424,27 +424,33 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
ds->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
ds->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
+ ds->zap_bytes = stats->nr_bytes[BLOCK_ACCT_APPEND];
ds->unmap_bytes = stats->nr_bytes[BLOCK_ACCT_UNMAP];
ds->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
ds->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
+ ds->zap_operations = stats->nr_ops[BLOCK_ACCT_APPEND];
ds->unmap_operations = stats->nr_ops[BLOCK_ACCT_UNMAP];
ds->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
ds->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
+ ds->failed_zap_operations = stats->failed_ops[BLOCK_ACCT_APPEND];
ds->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
ds->failed_unmap_operations = stats->failed_ops[BLOCK_ACCT_UNMAP];
ds->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
ds->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
+ ds->invalid_zap_operations = stats->invalid_ops[BLOCK_ACCT_APPEND];
ds->invalid_flush_operations =
stats->invalid_ops[BLOCK_ACCT_FLUSH];
ds->invalid_unmap_operations = stats->invalid_ops[BLOCK_ACCT_UNMAP];
ds->rd_merged = stats->merged[BLOCK_ACCT_READ];
ds->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
+ ds->zap_merged = stats->merged[BLOCK_ACCT_APPEND];
ds->unmap_merged = stats->merged[BLOCK_ACCT_UNMAP];
ds->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
ds->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
+ ds->zap_total_time_ns = stats->total_time_ns[BLOCK_ACCT_APPEND];
ds->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
ds->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
ds->unmap_total_time_ns = stats->total_time_ns[BLOCK_ACCT_UNMAP];
@@ -462,6 +468,7 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
+ TimedAverage *zap = &ts->latency[BLOCK_ACCT_APPEND];
TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
dev_stats->interval_length = ts->interval_length;
@@ -474,6 +481,10 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
dev_stats->max_wr_latency_ns = timed_average_max(wr);
dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
+ dev_stats->min_zap_latency_ns = timed_average_min(zap);
+ dev_stats->max_zap_latency_ns = timed_average_max(zap);
+ dev_stats->avg_zap_latency_ns = timed_average_avg(zap);
+
dev_stats->min_flush_latency_ns = timed_average_min(fl);
dev_stats->max_flush_latency_ns = timed_average_max(fl);
dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
@@ -482,6 +493,8 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
block_acct_queue_depth(ts, BLOCK_ACCT_READ);
dev_stats->avg_wr_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
+ dev_stats->avg_zap_queue_depth =
+ block_acct_queue_depth(ts, BLOCK_ACCT_APPEND);
QAPI_LIST_PREPEND(ds->timed_stats, dev_stats);
}
@@ -491,6 +504,8 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
= bdrv_latency_histogram_stats(&hgram[BLOCK_ACCT_READ]);
ds->wr_latency_histogram
= bdrv_latency_histogram_stats(&hgram[BLOCK_ACCT_WRITE]);
+ ds->zap_latency_histogram
+ = bdrv_latency_histogram_stats(&hgram[BLOCK_ACCT_APPEND]);
ds->flush_latency_histogram
= bdrv_latency_histogram_stats(&hgram[BLOCK_ACCT_FLUSH]);
}
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 09220f400d..5c9dc4eec1 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -925,6 +925,10 @@ static int virtio_blk_handle_zone_append(VirtIOBlockReq *req,
data->in_num = in_num;
data->zone_append_data.offset = offset;
qemu_iovec_init_external(&req->qiov, out_iov, out_num);
+
+ block_acct_start(blk_get_stats(s->blk), &req->acct, len,
+ BLOCK_ACCT_APPEND);
+
blk_aio_zone_append(s->blk, &data->zone_append_data.offset, &req->qiov, 0,
virtio_blk_zone_append_complete, data);
return 0;
diff --git a/include/block/accounting.h b/include/block/accounting.h
index b9caad60d5..61cc868666 100644
--- a/include/block/accounting.h
+++ b/include/block/accounting.h
@@ -37,6 +37,7 @@ enum BlockAcctType {
BLOCK_ACCT_READ,
BLOCK_ACCT_WRITE,
BLOCK_ACCT_FLUSH,
+ BLOCK_ACCT_APPEND,
BLOCK_ACCT_UNMAP,
BLOCK_MAX_IOTYPE,
};
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 95ac4fa634..7f83982614 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -754,6 +754,9 @@
# @min_wr_latency_ns: Minimum latency of write operations in the
# defined interval, in nanoseconds.
#
+# @min_zap_latency_ns: Minimum latency of zone append operations in the
+# defined interval, in nanoseconds.
+#
# @min_flush_latency_ns: Minimum latency of flush operations in the
# defined interval, in nanoseconds.
#
@@ -763,6 +766,9 @@
# @max_wr_latency_ns: Maximum latency of write operations in the
# defined interval, in nanoseconds.
#
+# @max_zap_latency_ns: Maximum latency of zone append operations in the
+# defined interval, in nanoseconds.
+#
# @max_flush_latency_ns: Maximum latency of flush operations in the
# defined interval, in nanoseconds.
#
@@ -772,6 +778,9 @@
# @avg_wr_latency_ns: Average latency of write operations in the
# defined interval, in nanoseconds.
#
+# @avg_zap_latency_ns: Average latency of zone append operations in the
+# defined interval, in nanoseconds.
+#
# @avg_flush_latency_ns: Average latency of flush operations in the
# defined interval, in nanoseconds.
#
@@ -781,15 +790,20 @@
# @avg_wr_queue_depth: Average number of pending write operations
# in the defined interval.
#
+# @avg_zap_queue_depth: Average number of pending zone append operations
+# in the defined interval.
+#
# Since: 2.5
##
{ 'struct': 'BlockDeviceTimedStats',
'data': { 'interval_length': 'int', 'min_rd_latency_ns': 'int',
'max_rd_latency_ns': 'int', 'avg_rd_latency_ns': 'int',
'min_wr_latency_ns': 'int', 'max_wr_latency_ns': 'int',
- 'avg_wr_latency_ns': 'int', 'min_flush_latency_ns': 'int',
- 'max_flush_latency_ns': 'int', 'avg_flush_latency_ns': 'int',
- 'avg_rd_queue_depth': 'number', 'avg_wr_queue_depth': 'number' } }
+ 'avg_wr_latency_ns': 'int', 'min_zap_latency_ns': 'int',
+ 'max_zap_latency_ns': 'int', 'avg_zap_latency_ns': 'int',
+ 'min_flush_latency_ns': 'int', 'max_flush_latency_ns': 'int',
+ 'avg_flush_latency_ns': 'int', 'avg_rd_queue_depth': 'number',
+ 'avg_wr_queue_depth': 'number', 'avg_zap_queue_depth': 'number' } }
##
# @BlockDeviceStats:
@@ -800,12 +814,16 @@
#
# @wr_bytes: The number of bytes written by the device.
#
+# @zap_bytes: The number of bytes appended by the zoned devices.
+#
# @unmap_bytes: The number of bytes unmapped by the device (Since 4.2)
#
# @rd_operations: The number of read operations performed by the device.
#
# @wr_operations: The number of write operations performed by the device.
#
+# @zap_operations: The number of zone append operations performed by the zoned devices.
+#
# @flush_operations: The number of cache flush operations performed by the
# device (since 0.15)
#
@@ -816,6 +834,8 @@
#
# @wr_total_time_ns: Total time spent on writes in nanoseconds (since 0.15).
#
+# @zap_total_time_ns: Total time spent on zone append writes in nanoseconds.
+#
# @flush_total_time_ns: Total time spent on cache flushes in nanoseconds
# (since 0.15).
#
@@ -833,6 +853,9 @@
# @wr_merged: Number of write requests that have been merged into another
# request (Since 2.3).
#
+# @zap_merged: Number of zone append requests that have been merged into
+# another request.
+#
# @unmap_merged: Number of unmap requests that have been merged into another
# request (Since 4.2)
#
@@ -846,6 +869,9 @@
# @failed_wr_operations: The number of failed write operations
# performed by the device (Since 2.5)
#
+# @failed_zap_operations: The number of failed zone append write
+# operations performed by the zoned devices
+#
# @failed_flush_operations: The number of failed flush operations
# performed by the device (Since 2.5)
#
@@ -858,6 +884,9 @@
# @invalid_wr_operations: The number of invalid write operations
# performed by the device (Since 2.5)
#
+# @invalid_zap_operations: The number of invalid zone append operations
+# performed by the zoned device
+#
# @invalid_flush_operations: The number of invalid flush operations
# performed by the device (Since 2.5)
#
@@ -877,27 +906,32 @@
#
# @wr_latency_histogram: @BlockLatencyHistogramInfo. (Since 4.0)
#
+# @zap_latency_histogram: @BlockLatencyHistogramInfo.
+#
# @flush_latency_histogram: @BlockLatencyHistogramInfo. (Since 4.0)
#
# Since: 0.14
##
{ 'struct': 'BlockDeviceStats',
- 'data': {'rd_bytes': 'int', 'wr_bytes': 'int', 'unmap_bytes' : 'int',
- 'rd_operations': 'int', 'wr_operations': 'int',
+ 'data': {'rd_bytes': 'int', 'wr_bytes': 'int', 'zap_bytes': 'int',
+ 'unmap_bytes' : 'int', 'rd_operations': 'int',
+ 'wr_operations': 'int', 'zap_operations': 'int',
'flush_operations': 'int', 'unmap_operations': 'int',
'rd_total_time_ns': 'int', 'wr_total_time_ns': 'int',
- 'flush_total_time_ns': 'int', 'unmap_total_time_ns': 'int',
- 'wr_highest_offset': 'int',
- 'rd_merged': 'int', 'wr_merged': 'int', 'unmap_merged': 'int',
- '*idle_time_ns': 'int',
+ 'zap_total_time_ns': 'int', 'flush_total_time_ns': 'int',
+ 'unmap_total_time_ns': 'int', 'wr_highest_offset': 'int',
+ 'rd_merged': 'int', 'wr_merged': 'int', 'zap_merged': 'int',
+ 'unmap_merged': 'int', '*idle_time_ns': 'int',
'failed_rd_operations': 'int', 'failed_wr_operations': 'int',
- 'failed_flush_operations': 'int', 'failed_unmap_operations': 'int',
- 'invalid_rd_operations': 'int', 'invalid_wr_operations': 'int',
+ 'failed_zap_operations': 'int', 'failed_flush_operations': 'int',
+ 'failed_unmap_operations': 'int', 'invalid_rd_operations': 'int',
+ 'invalid_wr_operations': 'int', 'invalid_zap_operations': 'int',
'invalid_flush_operations': 'int', 'invalid_unmap_operations': 'int',
'account_invalid': 'bool', 'account_failed': 'bool',
'timed_stats': ['BlockDeviceTimedStats'],
'*rd_latency_histogram': 'BlockLatencyHistogramInfo',
'*wr_latency_histogram': 'BlockLatencyHistogramInfo',
+ '*zap_latency_histogram': 'BlockLatencyHistogramInfo',
'*flush_latency_histogram': 'BlockLatencyHistogramInfo' } }
##
diff --git a/qapi/block.json b/qapi/block.json
index 5fe068f903..5a57ef4a9f 100644
--- a/qapi/block.json
+++ b/qapi/block.json
@@ -525,6 +525,9 @@
# @boundaries-write: list of interval boundary values for write latency
# histogram.
#
+# @boundaries-zap: list of interval boundary values for zone append write
+# latency histogram.
+#
# @boundaries-flush: list of interval boundary values for flush latency
# histogram.
#
@@ -573,5 +576,6 @@
'*boundaries': ['uint64'],
'*boundaries-read': ['uint64'],
'*boundaries-write': ['uint64'],
+ '*boundaries-zap': ['uint64'],
'*boundaries-flush': ['uint64'] },
'allow-preconfig': true }
--
2.38.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [RFC v6 4/4] virtio-blk: add some trace events for zoned emulation
2023-01-29 10:39 [RFC v6 0/4] Add zoned storage emulation to virtio-blk driver Sam Li
` (2 preceding siblings ...)
2023-01-29 10:39 ` [RFC v6 3/4] block: add accounting for zone append operation Sam Li
@ 2023-01-29 10:39 ` Sam Li
3 siblings, 0 replies; 9+ messages in thread
From: Sam Li @ 2023-01-29 10:39 UTC (permalink / raw)
To: qemu-devel
Cc: dmitry.fomichev, Raphael Norwitz, stefanha, Michael S. Tsirkin,
Kevin Wolf, damien.lemoal, hare, Markus Armbruster, qemu-block,
Eric Blake, Hanna Reitz, Sam Li
Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
hw/block/trace-events | 7 +++++++
hw/block/virtio-blk.c | 12 ++++++++++++
2 files changed, 19 insertions(+)
diff --git a/hw/block/trace-events b/hw/block/trace-events
index 2c45a62bd5..34be8b9135 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -44,9 +44,16 @@ pflash_write_unknown(const char *name, uint8_t cmd) "%s: unknown command 0x%02x"
# virtio-blk.c
virtio_blk_req_complete(void *vdev, void *req, int status) "vdev %p req %p status %d"
virtio_blk_rw_complete(void *vdev, void *req, int ret) "vdev %p req %p ret %d"
+virtio_blk_zone_report_complete(void *vdev, void *req, unsigned int nr_zones, int ret) "vdev %p req %p nr_zones %u ret %d"
+virtio_blk_zone_mgmt_complete(void *vdev, void *req, int ret) "vdev %p req %p ret %d"
+virtio_blk_zone_append_complete(void *vdev, void *req, int64_t sector, int ret) "vdev %p req %p, append sector 0x%" PRIx64 " ret %d"
virtio_blk_handle_write(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu"
virtio_blk_handle_read(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu"
virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint64_t offset, size_t size, bool is_write) "vdev %p mrb %p start %d num_reqs %d offset %"PRIu64" size %zu is_write %d"
+virtio_blk_handle_zone_report(void *vdev, void *req, int64_t sector, unsigned int nr_zones) "vdev %p req %p sector 0x%" PRIx64 " nr_zones %u"
+virtio_blk_handle_zone_mgmt(void *vdev, void *req, uint8_t op, int64_t sector, int64_t len) "vdev %p req %p op 0x%x sector 0x%" PRIx64 " len 0x%" PRIx64 ""
+virtio_blk_handle_zone_reset_all(void *vdev, void *req, int64_t sector, int64_t len) "vdev %p req %p sector 0x%" PRIx64 " cap 0x%" PRIx64 ""
+virtio_blk_handle_zone_append(void *vdev, void *req, int64_t sector) "vdev %p req %p, append sector 0x%" PRIx64 ""
# hd-geometry.c
hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d"
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 5c9dc4eec1..1776a89c4c 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -676,6 +676,7 @@ static void virtio_blk_zone_report_complete(void *opaque, int ret)
int64_t nz = data->zone_report_data.nr_zones;
int8_t err_status = VIRTIO_BLK_S_OK;
+ trace_virtio_blk_zone_report_complete(vdev, req, nz, ret);
if (ret) {
err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
goto out;
@@ -792,6 +793,8 @@ static int virtio_blk_handle_zone_report(VirtIOBlockReq *req,
nr_zones = (req->in_len - sizeof(struct virtio_blk_inhdr) -
sizeof(struct virtio_blk_zone_report)) /
sizeof(struct virtio_blk_zone_descriptor);
+ trace_virtio_blk_handle_zone_report(vdev, req,
+ offset >> BDRV_SECTOR_BITS, nr_zones);
zone_size = sizeof(BlockZoneDescriptor) * nr_zones;
data = g_malloc(sizeof(ZoneCmdData));
@@ -818,7 +821,9 @@ static void virtio_blk_zone_mgmt_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
int8_t err_status = VIRTIO_BLK_S_OK;
+ trace_virtio_blk_zone_mgmt_complete(vdev, req,ret);
if (ret) {
err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
@@ -845,6 +850,8 @@ static int virtio_blk_handle_zone_mgmt(VirtIOBlockReq *req, BlockZoneOp op)
/* Entire drive capacity */
offset = 0;
len = capacity;
+ trace_virtio_blk_handle_zone_reset_all(vdev, req, 0,
+ bs->total_sectors);
} else {
if (bs->bl.zone_size > capacity - offset) {
/* The zoned device allows the last smaller zone. */
@@ -852,6 +859,9 @@ static int virtio_blk_handle_zone_mgmt(VirtIOBlockReq *req, BlockZoneOp op)
} else {
len = bs->bl.zone_size;
}
+ trace_virtio_blk_handle_zone_mgmt(vdev, req, op,
+ offset >> BDRV_SECTOR_BITS,
+ len >> BDRV_SECTOR_BITS);
}
if (!check_zoned_request(s, offset, len, false, &err_status)) {
@@ -894,6 +904,7 @@ static void virtio_blk_zone_append_complete(void *opaque, int ret)
err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
goto out;
}
+ trace_virtio_blk_zone_append_complete(vdev, req, append_sector, ret);
out:
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
@@ -915,6 +926,7 @@ static int virtio_blk_handle_zone_append(VirtIOBlockReq *req,
int64_t offset = virtio_ldq_p(vdev, &req->out.sector) << BDRV_SECTOR_BITS;
int64_t len = iov_size(out_iov, out_num);
+ trace_virtio_blk_handle_zone_append(vdev, req, offset >> BDRV_SECTOR_BITS);
if (!check_zoned_request(s, offset, len, true, &err_status)) {
goto out;
}
--
2.38.1
^ permalink raw reply related [flat|nested] 9+ messages in thread