@@ -1966,6 +1966,7 @@ config_host_data.set('CONFIG_REPLICATION', get_option('replication').allowed())
# has_header
config_host_data.set('CONFIG_EPOLL', cc.has_header('sys/epoll.h'))
config_host_data.set('CONFIG_LINUX_MAGIC_H', cc.has_header('linux/magic.h'))
+config_host_data.set('CONFIG_BLKZONED', cc.has_header('linux/blkzoned.h'))
config_host_data.set('CONFIG_VALGRIND_H', cc.has_header('valgrind/valgrind.h'))
config_host_data.set('HAVE_BTRFS_H', cc.has_header('linux/btrfs.h'))
config_host_data.set('HAVE_DRM_H', cc.has_header('libdrm/drm.h'))
@@ -2052,6 +2053,9 @@ config_host_data.set('HAVE_SIGEV_NOTIFY_THREAD_ID',
config_host_data.set('HAVE_STRUCT_STAT_ST_ATIM',
cc.has_member('struct stat', 'st_atim',
prefix: '#include <sys/stat.h>'))
+config_host_data.set('HAVE_BLK_ZONE_REP_CAPACITY',
+ cc.has_member('struct blk_zone', 'capacity',
+ prefix: '#include <linux/blkzoned.h>'))
# has_type
config_host_data.set('CONFIG_IOVEC',
@@ -111,6 +111,15 @@ int coroutine_fn GRAPH_RDLOCK bdrv_co_flush(BlockDriverState *bs);
int coroutine_fn GRAPH_RDLOCK bdrv_co_pdiscard(BdrvChild *child, int64_t offset,
int64_t bytes);
+/* Report zone information of zone block device. */
+int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_report(BlockDriverState *bs,
+ int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones);
+int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_mgmt(BlockDriverState *bs,
+ BlockZoneOp op,
+ int64_t offset, int64_t len);
+
bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs);
int bdrv_block_status(BlockDriverState *bs, int64_t offset,
int64_t bytes, int64_t *pnum, int64_t *map,
@@ -712,6 +712,12 @@ struct BlockDriver {
int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_load_vmstate)(
BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
+ int coroutine_fn (*bdrv_co_zone_report)(BlockDriverState *bs,
+ int64_t offset, unsigned int *nr_zones,
+ BlockZoneDescriptor *zones);
+ int coroutine_fn (*bdrv_co_zone_mgmt)(BlockDriverState *bs, BlockZoneOp op,
+ int64_t offset, int64_t len);
+
/* removable device specific */
bool coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_is_inserted)(
BlockDriverState *bs);
@@ -864,6 +870,21 @@ typedef struct BlockLimits {
/* device zone model */
BlockZoneModel zoned;
+
+ /* zone size expressed in bytes */
+ uint32_t zone_size;
+
+ /* total number of zones */
+ uint32_t nr_zones;
+
+ /* maximum sectors of a zone append write operation */
+ int64_t max_append_sectors;
+
+ /* maximum number of open zones */
+ int64_t max_open_zones;
+
+ /* maximum number of active zones */
+ int64_t max_active_zones;
} BlockLimits;
typedef struct BdrvOpBlocker BdrvOpBlocker;
@@ -28,6 +28,8 @@
#define QEMU_AIO_WRITE_ZEROES 0x0020
#define QEMU_AIO_COPY_RANGE 0x0040
#define QEMU_AIO_TRUNCATE 0x0080
+#define QEMU_AIO_ZONE_REPORT 0x0100
+#define QEMU_AIO_ZONE_MGMT 0x0200
#define QEMU_AIO_TYPE_MASK \
(QEMU_AIO_READ | \
QEMU_AIO_WRITE | \
@@ -36,7 +38,9 @@
QEMU_AIO_DISCARD | \
QEMU_AIO_WRITE_ZEROES | \
QEMU_AIO_COPY_RANGE | \
- QEMU_AIO_TRUNCATE)
+ QEMU_AIO_TRUNCATE | \
+ QEMU_AIO_ZONE_REPORT | \
+ QEMU_AIO_ZONE_MGMT)
/* AIO flags */
#define QEMU_AIO_MISALIGNED 0x1000
@@ -46,6 +46,13 @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *blk_aio_flush(BlockBackend *blk,
BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones,
+ BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+ int64_t offset, int64_t len,
+ BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes,
BlockCompletionFunc *cb, void *opaque);
void blk_aio_cancel_async(BlockAIOCB *acb);
@@ -191,6 +198,17 @@ int co_wrapper_mixed blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset,
int64_t bytes, BdrvRequestFlags flags);
+int coroutine_fn blk_co_zone_report(BlockBackend *blk, int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones);
+int co_wrapper_mixed blk_zone_report(BlockBackend *blk, int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones);
+int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+ int64_t offset, int64_t len);
+int co_wrapper_mixed blk_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+ int64_t offset, int64_t len);
+
int co_wrapper_mixed blk_pdiscard(BlockBackend *blk, int64_t offset,
int64_t bytes);
int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset,
@@ -1845,6 +1845,143 @@ int coroutine_fn blk_co_flush(BlockBackend *blk)
return ret;
}
+static void coroutine_fn blk_aio_zone_report_entry(void *opaque)
+{
+ BlkAioEmAIOCB *acb = opaque;
+ BlkRwCo *rwco = &acb->rwco;
+
+ rwco->ret = blk_co_zone_report(rwco->blk, rwco->offset,
+ (unsigned int*)(uintptr_t)acb->bytes,
+ rwco->iobuf);
+ 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;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
+ acb->rwco = (BlkRwCo) {
+ .blk = blk,
+ .offset = offset,
+ .iobuf = zones,
+ .ret = NOT_DONE,
+ };
+ acb->bytes = (int64_t)(uintptr_t)nr_zones,
+ acb->has_returned = false;
+
+ co = qemu_coroutine_create(blk_aio_zone_report_entry, acb);
+ aio_co_enter(blk_get_aio_context(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 coroutine_fn blk_aio_zone_mgmt_entry(void *opaque)
+{
+ BlkAioEmAIOCB *acb = opaque;
+ BlkRwCo *rwco = &acb->rwco;
+
+ rwco->ret = blk_co_zone_mgmt(rwco->blk,
+ (BlockZoneOp)(uintptr_t)rwco->iobuf,
+ 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;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
+ acb->rwco = (BlkRwCo) {
+ .blk = blk,
+ .offset = offset,
+ .iobuf = (void *)(uintptr_t)op,
+ .ret = NOT_DONE,
+ };
+ acb->bytes = len;
+ acb->has_returned = false;
+
+ co = qemu_coroutine_create(blk_aio_zone_mgmt_entry, acb);
+ aio_co_enter(blk_get_aio_context(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
+ * required for offset.
+ * nr_zones represents IN maximum and OUT actual.
+ */
+int coroutine_fn blk_co_zone_report(BlockBackend *blk, int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones)
+{
+ int ret;
+ IO_CODE();
+
+ blk_inc_in_flight(blk); /* increase before waiting */
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+ if (!blk_is_available(blk)) {
+ blk_dec_in_flight(blk);
+ return -ENOMEDIUM;
+ }
+ ret = bdrv_co_zone_report(blk_bs(blk), offset, nr_zones, zones);
+ blk_dec_in_flight(blk);
+ return ret;
+}
+
+/*
+ * Send a zone_management command.
+ * op is the zone operation;
+ * offset is the byte offset from the start of the zoned device;
+ * len is the maximum number of bytes the command should operate on. It
+ * should be aligned with the device zone size.
+ */
+int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+ int64_t offset, int64_t len)
+{
+ int ret;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ ret = blk_check_byte_request(blk, offset, len);
+ if (ret < 0) {
+ blk_dec_in_flight(blk);
+ return ret;
+ }
+
+ ret = bdrv_co_zone_mgmt(blk_bs(blk), op, offset, len);
+ blk_dec_in_flight(blk);
+ return ret;
+}
+
void blk_drain(BlockBackend *blk)
{
BlockDriverState *bs = blk_bs(blk);
@@ -68,6 +68,9 @@
#include <sys/param.h>
#include <sys/syscall.h>
#include <sys/vfs.h>
+#if defined(CONFIG_BLKZONED)
+#include <linux/blkzoned.h>
+#endif
#include <linux/cdrom.h>
#include <linux/fd.h>
#include <linux/fs.h>
@@ -216,6 +219,13 @@ typedef struct RawPosixAIOData {
PreallocMode prealloc;
Error **errp;
} truncate;
+ struct {
+ unsigned int *nr_zones;
+ BlockZoneDescriptor *zones;
+ } zone_report;
+ struct {
+ unsigned long op;
+ } zone_mgmt;
};
} RawPosixAIOData;
@@ -1236,6 +1246,7 @@ static int get_sysfs_str_val(struct stat *st, const char *attribute,
#endif
}
+#if defined(CONFIG_BLKZONED)
static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned)
{
g_autofree char *val = NULL;
@@ -1257,6 +1268,7 @@ static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned)
}
return 0;
}
+#endif /* defined(CONFIG_BLKZONED) */
/*
* Get a sysfs attribute value as a long integer.
@@ -1302,6 +1314,7 @@ static int hdev_get_max_segments(int fd, struct stat *st)
#endif
}
+#if defined(CONFIG_BLKZONED)
static void raw_refresh_zoned_limits(BlockDriverState *bs, struct stat *st,
Error **errp)
{
@@ -1315,7 +1328,54 @@ static void raw_refresh_zoned_limits(BlockDriverState *bs, struct stat *st,
return;
}
bs->bl.zoned = zoned;
+
+ ret = get_sysfs_long_val(st, "max_open_zones");
+ if (ret >= 0) {
+ bs->bl.max_open_zones = ret;
+ }
+
+ ret = get_sysfs_long_val(st, "max_active_zones");
+ if (ret >= 0) {
+ bs->bl.max_active_zones = ret;
+ }
+
+ /*
+ * The zoned device must at least have zone size and nr_zones fields.
+ */
+ ret = get_sysfs_long_val(st, "chunk_sectors");
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Unable to read chunk_sectors "
+ "sysfs attribute");
+ return;
+ } else if (!ret) {
+ error_setg(errp, "Read 0 from chunk_sectors sysfs attribute");
+ return;
+ }
+ bs->bl.zone_size = ret << BDRV_SECTOR_BITS;
+
+ ret = get_sysfs_long_val(st, "nr_zones");
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Unable to read nr_zones "
+ "sysfs attribute");
+ return;
+ } else if (!ret) {
+ error_setg(errp, "Read 0 from nr_zones sysfs attribute");
+ return;
+ }
+ bs->bl.nr_zones = ret;
+
+ ret = get_sysfs_long_val(st, "zone_append_max_bytes");
+ if (ret > 0) {
+ bs->bl.max_append_sectors = ret >> BDRV_SECTOR_BITS;
+ }
}
+#else /* !defined(CONFIG_BLKZONED) */
+static void raw_refresh_zoned_limits(BlockDriverState *bs, struct stat *st,
+ Error **errp)
+{
+ bs->bl.zoned = BLK_Z_NONE;
+}
+#endif /* !defined(CONFIG_BLKZONED) */
static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
{
@@ -1383,9 +1443,12 @@ static int hdev_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
BDRVRawState *s = bs->opaque;
int ret;
- /* If DASD, get blocksizes */
+ /* If DASD or zoned devices, get blocksizes */
if (check_for_dasd(s->fd) < 0) {
- return -ENOTSUP;
+ /* zoned devices are not DASD */
+ if (bs->bl.zoned == BLK_Z_NONE) {
+ return -ENOTSUP;
+ }
}
ret = probe_logical_blocksize(s->fd, &bsz->log);
if (ret < 0) {
@@ -1853,6 +1916,147 @@ static off_t copy_file_range(int in_fd, off_t *in_off, int out_fd,
}
#endif
+/*
+ * parse_zone - Fill a zone descriptor
+ */
+#if defined(CONFIG_BLKZONED)
+static inline int parse_zone(struct BlockZoneDescriptor *zone,
+ const struct blk_zone *blkz) {
+ zone->start = blkz->start << BDRV_SECTOR_BITS;
+ zone->length = blkz->len << BDRV_SECTOR_BITS;
+ zone->wp = blkz->wp << BDRV_SECTOR_BITS;
+
+#ifdef HAVE_BLK_ZONE_REP_CAPACITY
+ zone->cap = blkz->capacity << BDRV_SECTOR_BITS;
+#else
+ zone->cap = blkz->len << BDRV_SECTOR_BITS;
+#endif
+
+ switch (blkz->type) {
+ case BLK_ZONE_TYPE_SEQWRITE_REQ:
+ zone->type = BLK_ZT_SWR;
+ break;
+ case BLK_ZONE_TYPE_SEQWRITE_PREF:
+ zone->type = BLK_ZT_SWP;
+ break;
+ case BLK_ZONE_TYPE_CONVENTIONAL:
+ zone->type = BLK_ZT_CONV;
+ break;
+ default:
+ error_report("Unsupported zone type: 0x%x", blkz->type);
+ return -ENOTSUP;
+ }
+
+ switch (blkz->cond) {
+ case BLK_ZONE_COND_NOT_WP:
+ zone->state = BLK_ZS_NOT_WP;
+ break;
+ case BLK_ZONE_COND_EMPTY:
+ zone->state = BLK_ZS_EMPTY;
+ break;
+ case BLK_ZONE_COND_IMP_OPEN:
+ zone->state = BLK_ZS_IOPEN;
+ break;
+ case BLK_ZONE_COND_EXP_OPEN:
+ zone->state = BLK_ZS_EOPEN;
+ break;
+ case BLK_ZONE_COND_CLOSED:
+ zone->state = BLK_ZS_CLOSED;
+ break;
+ case BLK_ZONE_COND_READONLY:
+ zone->state = BLK_ZS_RDONLY;
+ break;
+ case BLK_ZONE_COND_FULL:
+ zone->state = BLK_ZS_FULL;
+ break;
+ case BLK_ZONE_COND_OFFLINE:
+ zone->state = BLK_ZS_OFFLINE;
+ break;
+ default:
+ error_report("Unsupported zone state: 0x%x", blkz->cond);
+ return -ENOTSUP;
+ }
+ return 0;
+}
+#endif
+
+#if defined(CONFIG_BLKZONED)
+static int handle_aiocb_zone_report(void *opaque)
+{
+ RawPosixAIOData *aiocb = opaque;
+ int fd = aiocb->aio_fildes;
+ unsigned int *nr_zones = aiocb->zone_report.nr_zones;
+ BlockZoneDescriptor *zones = aiocb->zone_report.zones;
+ /* zoned block devices use 512-byte sectors */
+ uint64_t sector = aiocb->aio_offset / 512;
+
+ struct blk_zone *blkz;
+ size_t rep_size;
+ unsigned int nrz;
+ int ret;
+ unsigned int n = 0, i = 0;
+
+ nrz = *nr_zones;
+ rep_size = sizeof(struct blk_zone_report) + nrz * sizeof(struct blk_zone);
+ g_autofree struct blk_zone_report *rep = NULL;
+ rep = g_malloc(rep_size);
+
+ blkz = (struct blk_zone *)(rep + 1);
+ while (n < nrz) {
+ memset(rep, 0, rep_size);
+ rep->sector = sector;
+ rep->nr_zones = nrz - n;
+
+ do {
+ ret = ioctl(fd, BLKREPORTZONE, rep);
+ } while (ret != 0 && errno == EINTR);
+ if (ret != 0) {
+ error_report("%d: ioctl BLKREPORTZONE at %" PRId64 " failed %d",
+ fd, sector, errno);
+ return -errno;
+ }
+
+ if (!rep->nr_zones) {
+ break;
+ }
+
+ for (i = 0; i < rep->nr_zones; i++, n++) {
+ ret = parse_zone(&zones[n], &blkz[i]);
+ if (ret != 0) {
+ return ret;
+ }
+
+ /* The next report should start after the last zone reported */
+ sector = blkz[i].start + blkz[i].len;
+ }
+ }
+
+ *nr_zones = n;
+ return 0;
+}
+#endif
+
+#if defined(CONFIG_BLKZONED)
+static int handle_aiocb_zone_mgmt(void *opaque)
+{
+ RawPosixAIOData *aiocb = opaque;
+ int fd = aiocb->aio_fildes;
+ uint64_t sector = aiocb->aio_offset / 512;
+ int64_t nr_sectors = aiocb->aio_nbytes / 512;
+ struct blk_zone_range range;
+ int ret;
+
+ /* Execute the operation */
+ range.sector = sector;
+ range.nr_sectors = nr_sectors;
+ do {
+ ret = ioctl(fd, aiocb->zone_mgmt.op, &range);
+ } while (ret != 0 && errno == EINTR);
+
+ return ret;
+}
+#endif
+
static int handle_aiocb_copy_range(void *opaque)
{
RawPosixAIOData *aiocb = opaque;
@@ -3032,6 +3236,104 @@ static void raw_account_discard(BDRVRawState *s, uint64_t nbytes, int ret)
}
}
+/*
+ * zone report - Get a zone block device's information in the form
+ * of an array of zone descriptors.
+ * zones is an array of zone descriptors to hold zone information on reply;
+ * offset can be any byte within the entire size of the device;
+ * nr_zones is the maxium number of sectors the command should operate on.
+ */
+#if defined(CONFIG_BLKZONED)
+static int coroutine_fn raw_co_zone_report(BlockDriverState *bs, int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones) {
+ BDRVRawState *s = bs->opaque;
+ RawPosixAIOData acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_fildes = s->fd,
+ .aio_type = QEMU_AIO_ZONE_REPORT,
+ .aio_offset = offset,
+ .zone_report = {
+ .nr_zones = nr_zones,
+ .zones = zones,
+ },
+ };
+
+ return raw_thread_pool_submit(handle_aiocb_zone_report, &acb);
+}
+#endif
+
+/*
+ * zone management operations - Execute an operation on a zone
+ */
+#if defined(CONFIG_BLKZONED)
+static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
+ int64_t offset, int64_t len) {
+ BDRVRawState *s = bs->opaque;
+ RawPosixAIOData acb;
+ int64_t zone_size, zone_size_mask;
+ const char *op_name;
+ unsigned long zo;
+ int ret;
+ int64_t capacity = bs->total_sectors << BDRV_SECTOR_BITS;
+
+ zone_size = bs->bl.zone_size;
+ zone_size_mask = zone_size - 1;
+ if (offset & zone_size_mask) {
+ error_report("sector offset %" PRId64 " is not aligned to zone size "
+ "%" PRId64 "", offset / 512, zone_size / 512);
+ return -EINVAL;
+ }
+
+ if (((offset + len) < capacity && len & zone_size_mask) ||
+ offset + len > capacity) {
+ error_report("number of sectors %" PRId64 " is not aligned to zone size"
+ " %" PRId64 "", len / 512, zone_size / 512);
+ return -EINVAL;
+ }
+
+ switch (op) {
+ case BLK_ZO_OPEN:
+ op_name = "BLKOPENZONE";
+ zo = BLKOPENZONE;
+ break;
+ case BLK_ZO_CLOSE:
+ op_name = "BLKCLOSEZONE";
+ zo = BLKCLOSEZONE;
+ break;
+ case BLK_ZO_FINISH:
+ op_name = "BLKFINISHZONE";
+ zo = BLKFINISHZONE;
+ break;
+ case BLK_ZO_RESET:
+ op_name = "BLKRESETZONE";
+ zo = BLKRESETZONE;
+ break;
+ default:
+ error_report("Unsupported zone op: 0x%x", op);
+ return -ENOTSUP;
+ }
+
+ acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_fildes = s->fd,
+ .aio_type = QEMU_AIO_ZONE_MGMT,
+ .aio_offset = offset,
+ .aio_nbytes = len,
+ .zone_mgmt = {
+ .op = zo,
+ },
+ };
+
+ ret = raw_thread_pool_submit(handle_aiocb_zone_mgmt, &acb);
+ if (ret != 0) {
+ error_report("ioctl %s failed %d", op_name, ret);
+ }
+
+ return ret;
+}
+#endif
+
static coroutine_fn int
raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes,
bool blkdev)
@@ -3787,6 +4089,13 @@ static BlockDriver bdrv_host_device = {
#ifdef __linux__
.bdrv_co_ioctl = hdev_co_ioctl,
#endif
+
+ /* zoned device */
+#if defined(CONFIG_BLKZONED)
+ /* zone management operations */
+ .bdrv_co_zone_report = raw_co_zone_report,
+ .bdrv_co_zone_mgmt = raw_co_zone_mgmt,
+#endif
};
#if defined(__linux__) || defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
@@ -3115,6 +3115,47 @@ out:
return co.ret;
}
+int coroutine_fn bdrv_co_zone_report(BlockDriverState *bs, int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+ IO_CODE();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_zone_report || bs->bl.zoned == BLK_Z_NONE) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+ co.ret = drv->bdrv_co_zone_report(bs, offset, nr_zones, zones);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
+int coroutine_fn bdrv_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
+ int64_t offset, int64_t len)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+ IO_CODE();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_zone_mgmt || bs->bl.zoned == BLK_Z_NONE) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+ co.ret = drv->bdrv_co_zone_mgmt(bs, op, offset, len);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
void *qemu_blockalign(BlockDriverState *bs, size_t size)
{
IO_CODE();
@@ -1730,6 +1730,150 @@ static const cmdinfo_t flush_cmd = {
.oneline = "flush all in-core file state to disk",
};
+static inline int64_t tosector(int64_t bytes)
+{
+ return bytes >> BDRV_SECTOR_BITS;
+}
+
+static int zone_report_f(BlockBackend *blk, int argc, char **argv)
+{
+ int ret;
+ int64_t offset;
+ unsigned int nr_zones;
+
+ ++optind;
+ offset = cvtnum(argv[optind]);
+ ++optind;
+ nr_zones = cvtnum(argv[optind]);
+
+ g_autofree BlockZoneDescriptor *zones = NULL;
+ zones = g_new(BlockZoneDescriptor, nr_zones);
+ ret = blk_zone_report(blk, offset, &nr_zones, zones);
+ if (ret < 0) {
+ printf("zone report failed: %s\n", strerror(-ret));
+ } else {
+ for (int i = 0; i < nr_zones; ++i) {
+ printf("start: 0x%" PRIx64 ", len 0x%" PRIx64 ", "
+ "cap"" 0x%" PRIx64 ", wptr 0x%" PRIx64 ", "
+ "zcond:%u, [type: %u]\n",
+ tosector(zones[i].start), tosector(zones[i].length),
+ tosector(zones[i].cap), tosector(zones[i].wp),
+ zones[i].state, zones[i].type);
+ }
+ }
+ return ret;
+}
+
+static const cmdinfo_t zone_report_cmd = {
+ .name = "zone_report",
+ .altname = "zrp",
+ .cfunc = zone_report_f,
+ .argmin = 2,
+ .argmax = 2,
+ .args = "offset number",
+ .oneline = "report zone information",
+};
+
+static int zone_open_f(BlockBackend *blk, int argc, char **argv)
+{
+ int ret;
+ int64_t offset, len;
+ ++optind;
+ offset = cvtnum(argv[optind]);
+ ++optind;
+ len = cvtnum(argv[optind]);
+ ret = blk_zone_mgmt(blk, BLK_ZO_OPEN, offset, len);
+ if (ret < 0) {
+ printf("zone open failed: %s\n", strerror(-ret));
+ }
+ return ret;
+}
+
+static const cmdinfo_t zone_open_cmd = {
+ .name = "zone_open",
+ .altname = "zo",
+ .cfunc = zone_open_f,
+ .argmin = 2,
+ .argmax = 2,
+ .args = "offset len",
+ .oneline = "explicit open a range of zones in zone block device",
+};
+
+static int zone_close_f(BlockBackend *blk, int argc, char **argv)
+{
+ int ret;
+ int64_t offset, len;
+ ++optind;
+ offset = cvtnum(argv[optind]);
+ ++optind;
+ len = cvtnum(argv[optind]);
+ ret = blk_zone_mgmt(blk, BLK_ZO_CLOSE, offset, len);
+ if (ret < 0) {
+ printf("zone close failed: %s\n", strerror(-ret));
+ }
+ return ret;
+}
+
+static const cmdinfo_t zone_close_cmd = {
+ .name = "zone_close",
+ .altname = "zc",
+ .cfunc = zone_close_f,
+ .argmin = 2,
+ .argmax = 2,
+ .args = "offset len",
+ .oneline = "close a range of zones in zone block device",
+};
+
+static int zone_finish_f(BlockBackend *blk, int argc, char **argv)
+{
+ int ret;
+ int64_t offset, len;
+ ++optind;
+ offset = cvtnum(argv[optind]);
+ ++optind;
+ len = cvtnum(argv[optind]);
+ ret = blk_zone_mgmt(blk, BLK_ZO_FINISH, offset, len);
+ if (ret < 0) {
+ printf("zone finish failed: %s\n", strerror(-ret));
+ }
+ return ret;
+}
+
+static const cmdinfo_t zone_finish_cmd = {
+ .name = "zone_finish",
+ .altname = "zf",
+ .cfunc = zone_finish_f,
+ .argmin = 2,
+ .argmax = 2,
+ .args = "offset len",
+ .oneline = "finish a range of zones in zone block device",
+};
+
+static int zone_reset_f(BlockBackend *blk, int argc, char **argv)
+{
+ int ret;
+ int64_t offset, len;
+ ++optind;
+ offset = cvtnum(argv[optind]);
+ ++optind;
+ len = cvtnum(argv[optind]);
+ ret = blk_zone_mgmt(blk, BLK_ZO_RESET, offset, len);
+ if (ret < 0) {
+ printf("zone reset failed: %s\n", strerror(-ret));
+ }
+ return ret;
+}
+
+static const cmdinfo_t zone_reset_cmd = {
+ .name = "zone_reset",
+ .altname = "zrs",
+ .cfunc = zone_reset_f,
+ .argmin = 2,
+ .argmax = 2,
+ .args = "offset len",
+ .oneline = "reset a zone write pointer in zone block device",
+};
+
static int truncate_f(BlockBackend *blk, int argc, char **argv);
static const cmdinfo_t truncate_cmd = {
.name = "truncate",
@@ -2523,6 +2667,11 @@ static void __attribute((constructor)) init_qemuio_commands(void)
qemuio_add_command(&aio_write_cmd);
qemuio_add_command(&aio_flush_cmd);
qemuio_add_command(&flush_cmd);
+ qemuio_add_command(&zone_report_cmd);
+ qemuio_add_command(&zone_open_cmd);
+ qemuio_add_command(&zone_close_cmd);
+ qemuio_add_command(&zone_finish_cmd);
+ qemuio_add_command(&zone_reset_cmd);
qemuio_add_command(&truncate_cmd);
qemuio_add_command(&length_cmd);
qemuio_add_command(&info_cmd);