| Message ID | 20220805075751.77499-5-faithilikerun@gmail.com |
|---|---|
| State | New |
| Headers | show |
| Series | Add support for zoned device | expand |
On Fri, Aug 05, 2022 at 03:57:47PM +0800, Sam Li wrote: > By adding zone management operations in BlockDriver, storage controller > emulation can use the new block layer APIs including Report Zone and > four zone management operations (open, close, finish, reset). > > Add zoned storage commands of the device: zone_report(zrp), zone_open(zo), > zone_close(zc), zone_reset(zrs), zone_finish(zf). > > For example, to test zone_report, use following command: > $ ./build/qemu-io --image-opts driver=zoned_host_device, filename=/dev/nullb0 > -c "zrp offset nr_zones" > > Signed-off-by: Sam Li <faithilikerun@gmail.com> > Reviewed-by: Hannes Reinecke <hare@suse.de> > --- > block/block-backend.c | 50 +++++ > block/coroutines.h | 6 + > block/file-posix.c | 315 ++++++++++++++++++++++++++++++- > block/io.c | 41 ++++ > include/block/block-common.h | 1 - > include/block/block-io.h | 13 ++ > include/block/block_int-common.h | 22 ++- > include/block/raw-aio.h | 6 +- > meson.build | 1 + > qapi/block-core.json | 8 +- > qemu-io-cmds.c | 144 ++++++++++++++ > 11 files changed, 601 insertions(+), 6 deletions(-) > > diff --git a/block/block-backend.c b/block/block-backend.c > index d4a5df2ac2..fc639b0cd7 100644 > --- a/block/block-backend.c > +++ b/block/block-backend.c > @@ -1775,6 +1775,56 @@ int coroutine_fn blk_co_flush(BlockBackend *blk) > return ret; > } > > +/* > + * 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); > + 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. > + * offset is the starting zone specified as a sector offset. > + * len is the maximum number of sectors the command should operate on. > + */ > +int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op, > + int64_t offset, int64_t len) > +{ > + int ret; > + IO_CODE(); > + > + ret = blk_check_byte_request(blk, offset, len); > + if (ret < 0) { > + return ret; > + } > + blk_inc_in_flight(blk); > + blk_wait_while_drained(blk); > + if (!blk_is_available(blk)) { > + blk_dec_in_flight(blk); > + return -ENOMEDIUM; > + } > + 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); > diff --git a/block/coroutines.h b/block/coroutines.h > index 3a2bad564f..e3f62d94e5 100644 > --- a/block/coroutines.h > +++ b/block/coroutines.h > @@ -63,6 +63,12 @@ nbd_co_do_establish_connection(BlockDriverState *bs, bool blocking, > Error **errp); > > > +int coroutine_fn blk_co_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); > + > /* > * "I/O or GS" API functions. These functions can run without > * the BQL, but only in one specific iothread/main loop. > diff --git a/block/file-posix.c b/block/file-posix.c > index 4785203eea..2627431581 100644 > --- a/block/file-posix.c > +++ b/block/file-posix.c > @@ -67,6 +67,9 @@ > #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 { > + BlockZoneOp op; > + } zone_mgmt; > }; > } RawPosixAIOData; > > @@ -1369,7 +1379,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) > #endif > > if (bs->sg || S_ISBLK(st.st_mode)) { > - int ret = hdev_get_max_hw_transfer(s->fd, &st); > + ret = hdev_get_max_hw_transfer(s->fd, &st); > > if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) { > bs->bl.max_hw_transfer = ret; > @@ -1386,6 +1396,27 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) > zoned = BLK_Z_NONE; > } > bs->bl.zoned = zoned; > + if (zoned != BLK_Z_NONE) { > + ret = get_sysfs_long_val(s->fd, &st, "chunk_sectors"); > + if (ret > 0) { > + bs->bl.zone_sectors = ret; > + } > + > + ret = get_sysfs_long_val(s->fd, &st, "zone_append_max_bytes"); > + if (ret > 0) { > + bs->bl.zone_append_max_bytes = ret; > + } > + > + ret = get_sysfs_long_val(s->fd, &st, "max_open_zones"); > + if (ret > 0) { > + bs->bl.max_open_zones = ret; > + } > + > + ret = get_sysfs_long_val(s->fd, &st, "max_active_zones"); > + if (ret > 0) { > + bs->bl.max_active_zones = ret; > + } > + } > } > > static int check_for_dasd(int fd) > @@ -1880,6 +1911,167 @@ 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 void parse_zone(struct BlockZoneDescriptor *zone, > + struct blk_zone *blkz) { > + zone->start = blkz->start; > + zone->length = blkz->len; > + zone->cap = blkz->capacity; > + zone->wp = blkz->wp; > + zone->type = blkz->type; > + > + switch (blkz->cond) { > + case BLK_ZONE_COND_NOT_WP: > + blkz->cond = BLK_ZS_NOT_WP; > + break; > + case BLK_ZONE_COND_EMPTY: > + blkz->cond = BLK_ZS_EMPTY; > + break; > + case BLK_ZONE_COND_IMP_OPEN: > + blkz->cond =BLK_ZS_IOPEN; > + break; > + case BLK_ZONE_COND_EXP_OPEN: > + blkz->cond = BLK_ZS_EOPEN; > + break; > + case BLK_ZONE_COND_CLOSED: > + blkz->cond = BLK_ZS_CLOSED; > + break; > + case BLK_ZONE_COND_READONLY: > + blkz->cond = BLK_ZS_RDONLY; > + break; > + case BLK_ZONE_COND_FULL: > + blkz->cond = BLK_ZS_FULL; > + break; > + case BLK_ZONE_COND_OFFLINE: > + blkz->cond = BLK_ZS_OFFLINE; > + break; > + default: > + error_report("Invalid zone condition 0x%x", blkz->cond); > + } > +} > +#endif > + > +static int handle_aiocb_zone_report(void *opaque) { When implementing thread pool functions it's preferrable to perform input validation and error checking outside the thread pool function. The reason is that the threads run without the Big QEMU Lock and don't have access to the full QEMU API environment. For example, the error_report() functions called in the thread pool function will not print to the current monitor, they always print to stderr and the error message may not be associated with the current monitor command. I would try to move all the preparation and input validation into raw_co_zone_report(). > +#if defined(CONFIG_BLKZONED) > + RawPosixAIOData *aiocb = opaque; > + int fd = aiocb->aio_fildes; > + unsigned int *nr_zones = aiocb->zone_report.nr_zones; > + BlockZoneDescriptor *zones = aiocb->zone_report.zones; > + int64_t sector = aiocb->aio_offset / 512; /* ZBDs use 512B sectors */ > + > + struct blk_zone *blkz; > + int64_t rep_size; > + unsigned int nrz; > + int ret, 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; > + > + ret = ioctl(fd, BLKREPORTZONE, rep); > + 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++) { > + parse_zone(&zones[n], &blkz[i]); > + /* The next report should start after the last zone reported */ > + sector = blkz[i].start + blkz[i].len; > + } > + } > + > + *nr_zones = n; > + return 0; > +#else > + return -ENOTSUP; > +#endif > +} > + > +static int handle_aiocb_zone_mgmt(void *opaque) { > +#if defined(CONFIG_BLKZONED) > + RawPosixAIOData *aiocb = opaque; > + BlockDriverState *bs = aiocb->bs; > + int fd = aiocb->aio_fildes; > + int64_t sector = aiocb->aio_offset; > + int64_t nr_sectors = aiocb->aio_nbytes; > + BlockZoneOp op = aiocb->zone_mgmt.op; > + struct blk_zone_range range; > + const char *ioctl_name; > + unsigned long ioctl_op; > + int64_t zone_sector, zone_sector_mask; > + int ret; > + > + zone_sector = bs->bl.zone_sectors; > + zone_sector_mask = zone_sector - 1; > + if (sector & zone_sector_mask) { > + error_report("offset %" PRId64 " is not aligned to zone size " > + "%" PRId64 "", sector, zone_sector); > + return -EINVAL; > + } > + > + if (nr_sectors & zone_sector_mask) { > + error_report("number of sectors %" PRId64 " is not aligned to zone size" > + " %" PRId64 "", nr_sectors, zone_sector); > + return -EINVAL; > + } > + > + switch (op) { > + case BLK_ZO_OPEN: > + ioctl_name = "BLKOPENZONE"; > + ioctl_op = BLKOPENZONE; > + break; > + case BLK_ZO_CLOSE: > + ioctl_name = "BLKCLOSEZONE"; > + ioctl_op = BLKCLOSEZONE; > + break; > + case BLK_ZO_FINISH: > + ioctl_name = "BLKFINISHZONE"; > + ioctl_op = BLKFINISHZONE; > + break; > + case BLK_ZO_RESET: > + ioctl_name = "BLKRESETZONE"; > + ioctl_op = BLKRESETZONE; > + break; > + default: > + error_report("Invalid zone operation 0x%x", op); > + return -EINVAL; > + } > + Everything above here can go in raw_co_zone_mgmt(). > + /* Execute the operation */ > + range.sector = sector; > + range.nr_sectors = nr_sectors; > + do { > + ret = ioctl(fd, ioctl_op, &range); > + } while (ret != 0 && errno == EINTR); Everything below here can go in raw_co_zone_mgmt(). > + > + if (ret != 0) { > + error_report("ioctl %s failed %d", > + ioctl_name, errno); > + return -errno; > + } > + > + return 0; > +#else > + return -ENOTSUP; > +#endif > +} > + > static int handle_aiocb_copy_range(void *opaque) > { > RawPosixAIOData *aiocb = opaque; > @@ -3052,6 +3244,67 @@ 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. > + * > + * @param bs: passing zone block device file descriptor > + * @param zones: an array of zone descriptors to hold zone > + * information on reply > + * @param offset: offset can be any byte within the zone size. > + * @param len: (not sure yet. > + * @return 0 on success, -1 on failure > + */ > +static int coroutine_fn raw_co_zone_report(BlockDriverState *bs, int64_t offset, > + unsigned int *nr_zones, > + BlockZoneDescriptor *zones) { > +#if defined(CONFIG_BLKZONED) > + BDRVRawState *s = bs->opaque; > + RawPosixAIOData acb; > + > + 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(bs, handle_aiocb_zone_report, &acb); > +#else > + return -ENOTSUP; > +#endif > +} > + > +/* > + * zone management operations - Execute an operation on a zone > + */ > +static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, > + int64_t offset, int64_t len) { > +#if defined(CONFIG_BLKZONED) > + BDRVRawState *s = bs->opaque; > + RawPosixAIOData acb; > + > + acb = (RawPosixAIOData) { > + .bs = bs, > + .aio_fildes = s->fd, > + .aio_type = QEMU_AIO_ZONE_MGMT, > + .aio_offset = offset, > + .aio_nbytes = len, > + .zone_mgmt = { > + .op = op, > + }, > + }; > + > + return raw_thread_pool_submit(bs, handle_aiocb_zone_mgmt, &acb); > +#else > + return -ENOTSUP; > +#endif > +} > + > static coroutine_fn int > raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes, > bool blkdev) > @@ -3552,6 +3805,14 @@ static void hdev_parse_filename(const char *filename, QDict *options, > bdrv_parse_filename_strip_prefix(filename, "host_device:", options); > } > > +#if defined(CONFIG_BLKZONED) > +static void zoned_host_device_parse_filename(const char *filename, QDict *options, > + Error **errp) > +{ > + bdrv_parse_filename_strip_prefix(filename, "zoned_host_device:", options); > +} > +#endif > + > static bool hdev_is_sg(BlockDriverState *bs) > { > > @@ -3782,6 +4043,55 @@ static BlockDriver bdrv_host_device = { > #endif > }; > > +#if defined(CONFIG_BLKZONED) > +static BlockDriver bdrv_zoned_host_device = { > + .format_name = "zoned_host_device", > + .protocol_name = "zoned_host_device", > + .instance_size = sizeof(BDRVRawState), > + .bdrv_needs_filename = true, > + .bdrv_probe_device = hdev_probe_device, > + .bdrv_parse_filename = zoned_host_device_parse_filename, > + .bdrv_file_open = hdev_open, > + .bdrv_close = raw_close, > + .bdrv_reopen_prepare = raw_reopen_prepare, > + .bdrv_reopen_commit = raw_reopen_commit, > + .bdrv_reopen_abort = raw_reopen_abort, > + .bdrv_co_create_opts = bdrv_co_create_opts_simple, > + .create_opts = &bdrv_create_opts_simple, > + .mutable_opts = mutable_opts, > + .bdrv_co_invalidate_cache = raw_co_invalidate_cache, > + .bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes, > + > + .bdrv_co_preadv = raw_co_preadv, > + .bdrv_co_pwritev = raw_co_pwritev, > + .bdrv_co_flush_to_disk = raw_co_flush_to_disk, > + .bdrv_co_pdiscard = hdev_co_pdiscard, > + .bdrv_co_copy_range_from = raw_co_copy_range_from, > + .bdrv_co_copy_range_to = raw_co_copy_range_to, > + .bdrv_refresh_limits = raw_refresh_limits, > + .bdrv_io_plug = raw_aio_plug, > + .bdrv_io_unplug = raw_aio_unplug, > + .bdrv_attach_aio_context = raw_aio_attach_aio_context, > + > + .bdrv_co_truncate = raw_co_truncate, > + .bdrv_getlength = raw_getlength, > + .bdrv_get_info = raw_get_info, > + .bdrv_get_allocated_file_size > + = raw_get_allocated_file_size, > + .bdrv_get_specific_stats = hdev_get_specific_stats, > + .bdrv_check_perm = raw_check_perm, > + .bdrv_set_perm = raw_set_perm, > + .bdrv_abort_perm_update = raw_abort_perm_update, > + .bdrv_probe_blocksizes = hdev_probe_blocksizes, > + .bdrv_probe_geometry = hdev_probe_geometry, > + .bdrv_co_ioctl = hdev_co_ioctl, > + > + /* 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__) > static void cdrom_parse_filename(const char *filename, QDict *options, > Error **errp) > @@ -4042,6 +4352,9 @@ static void bdrv_file_init(void) > bdrv_register(&bdrv_file); > #if defined(HAVE_HOST_BLOCK_DEVICE) > bdrv_register(&bdrv_host_device); > +#if defined(CONFIG_BLKZONED) > + bdrv_register(&bdrv_zoned_host_device); > +#endif > #ifdef __linux__ > bdrv_register(&bdrv_host_cdrom); > #endif > diff --git a/block/io.c b/block/io.c > index 0a8cbefe86..de9ec1d740 100644 > --- a/block/io.c > +++ b/block/io.c > @@ -3198,6 +3198,47 @@ out: > return co.ret; > } > > +int 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) { > + 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 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) { > + 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(); > diff --git a/include/block/block-common.h b/include/block/block-common.h > index 36bd0e480e..5102fa6858 100644 > --- a/include/block/block-common.h > +++ b/include/block/block-common.h > @@ -23,7 +23,6 @@ > */ > #ifndef BLOCK_COMMON_H > #define BLOCK_COMMON_H > - > #include "block/aio.h" > #include "block/aio-wait.h" > #include "qemu/iov.h" > diff --git a/include/block/block-io.h b/include/block/block-io.h > index fd25ffa9be..55ad261e16 100644 > --- a/include/block/block-io.h > +++ b/include/block/block-io.h > @@ -88,6 +88,13 @@ int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf); > /* Ensure contents are flushed to disk. */ > int coroutine_fn bdrv_co_flush(BlockDriverState *bs); > > +/* Report zone information of zone block device. */ > +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); > + > int bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes); > bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); > int bdrv_block_status(BlockDriverState *bs, int64_t offset, > @@ -297,6 +304,12 @@ bdrv_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); > int generated_co_wrapper > bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); > > +int generated_co_wrapper > +blk_zone_report(BlockBackend *blk, int64_t offset, unsigned int *nr_zones, > + BlockZoneDescriptor *zones); > +int generated_co_wrapper > +blk_zone_mgmt(BlockBackend *blk, BlockZoneOp op, int64_t offset, int64_t len); > + > /** > * bdrv_parent_drained_begin_single: > * > diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h > index 7f7863cc9e..de44c7b6f4 100644 > --- a/include/block/block_int-common.h > +++ b/include/block/block_int-common.h > @@ -94,7 +94,6 @@ typedef struct BdrvTrackedRequest { > struct BdrvTrackedRequest *waiting_for; > } BdrvTrackedRequest; > > - > struct BlockDriver { > /* > * These fields are initialized when this object is created, > @@ -691,6 +690,12 @@ struct BlockDriver { > 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 (*bdrv_is_inserted)(BlockDriverState *bs); > void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag); > @@ -828,6 +833,21 @@ typedef struct BlockLimits { > > /* device zone model */ > BlockZoneModel zoned; > + > + /* zone size expressed in 512-byte sectors */ > + uint32_t zone_sectors; > + > + /* total number of zones */ > + unsigned int nr_zones; > + > + /* maximum size in bytes of a zone append write operation */ > + int64_t zone_append_max_bytes; > + > + /* 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; > diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h > index 21fc10c4c9..3d26929cdd 100644 > --- a/include/block/raw-aio.h > +++ b/include/block/raw-aio.h > @@ -29,6 +29,8 @@ > #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 | \ > @@ -37,7 +39,9 @@ > 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 > diff --git a/meson.build b/meson.build > index 75aaca8462..8c34516443 100644 > --- a/meson.build > +++ b/meson.build > @@ -1883,6 +1883,7 @@ config_host_data.set('CONFIG_REPLICATION', get_option('live_block_migration').al > # 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')) > diff --git a/qapi/block-core.json b/qapi/block-core.json > index 2173e7734a..c6bbb7a037 100644 > --- a/qapi/block-core.json > +++ b/qapi/block-core.json > @@ -2942,6 +2942,7 @@ > # @compress: Since 5.0 > # @copy-before-write: Since 6.2 > # @snapshot-access: Since 7.0 > +# @zoned_host_device: Since 7.2 > # > # Since: 2.9 > ## > @@ -2955,7 +2956,8 @@ > 'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', > 'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd', > { 'name': 'replication', 'if': 'CONFIG_REPLICATION' }, > - 'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] } > + 'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', > + { 'name': 'zoned_host_device', 'if': 'CONFIG_BLKZONED' } ] } > > ## > # @BlockdevOptionsFile: > @@ -4329,7 +4331,9 @@ > 'vhdx': 'BlockdevOptionsGenericFormat', > 'vmdk': 'BlockdevOptionsGenericCOWFormat', > 'vpc': 'BlockdevOptionsGenericFormat', > - 'vvfat': 'BlockdevOptionsVVFAT' > + 'vvfat': 'BlockdevOptionsVVFAT', > + 'zoned_host_device': { 'type': 'BlockdevOptionsFile', > + 'if': 'CONFIG_BLKZONED' } > } } > > ## > diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c > index 952dc940f1..5a215277c7 100644 > --- a/qemu-io-cmds.c > +++ b/qemu-io-cmds.c > @@ -1712,6 +1712,145 @@ static const cmdinfo_t flush_cmd = { > .oneline = "flush all in-core file state to disk", > }; > > +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", > + zones[i].start, zones[i].length, zones[i].cap, zones[i].wp, > + zones[i].cond, 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", > @@ -2504,6 +2643,11 @@ 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); > -- > 2.37.1 >
Sam Li <faithilikerun@gmail.com> 于2022年8月5日周五 15:58写道： > > By adding zone management operations in BlockDriver, storage controller > emulation can use the new block layer APIs including Report Zone and > four zone management operations (open, close, finish, reset). > > Add zoned storage commands of the device: zone_report(zrp), zone_open(zo), > zone_close(zc), zone_reset(zrs), zone_finish(zf). > > For example, to test zone_report, use following command: > $ ./build/qemu-io --image-opts driver=zoned_host_device, filename=/dev/nullb0 > -c "zrp offset nr_zones" > > Signed-off-by: Sam Li <faithilikerun@gmail.com> > Reviewed-by: Hannes Reinecke <hare@suse.de> > --- > block/block-backend.c | 50 +++++ > block/coroutines.h | 6 + > block/file-posix.c | 315 ++++++++++++++++++++++++++++++- > block/io.c | 41 ++++ > include/block/block-common.h | 1 - > include/block/block-io.h | 13 ++ > include/block/block_int-common.h | 22 ++- > include/block/raw-aio.h | 6 +- > meson.build | 1 + > qapi/block-core.json | 8 +- > qemu-io-cmds.c | 144 ++++++++++++++ > 11 files changed, 601 insertions(+), 6 deletions(-) > > diff --git a/block/block-backend.c b/block/block-backend.c > index d4a5df2ac2..fc639b0cd7 100644 > --- a/block/block-backend.c > +++ b/block/block-backend.c > @@ -1775,6 +1775,56 @@ int coroutine_fn blk_co_flush(BlockBackend *blk) > return ret; > } > > +/* > + * 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); > + 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. > + * offset is the starting zone specified as a sector offset. > + * len is the maximum number of sectors the command should operate on. > + */ > +int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op, > + int64_t offset, int64_t len) > +{ > + int ret; > + IO_CODE(); > + > + ret = blk_check_byte_request(blk, offset, len); > + if (ret < 0) { > + return ret; > + } > + blk_inc_in_flight(blk); > + blk_wait_while_drained(blk); > + if (!blk_is_available(blk)) { > + blk_dec_in_flight(blk); > + return -ENOMEDIUM; > + } > + 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); > diff --git a/block/coroutines.h b/block/coroutines.h > index 3a2bad564f..e3f62d94e5 100644 > --- a/block/coroutines.h > +++ b/block/coroutines.h > @@ -63,6 +63,12 @@ nbd_co_do_establish_connection(BlockDriverState *bs, bool blocking, > Error **errp); > > > +int coroutine_fn blk_co_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); > + > /* > * "I/O or GS" API functions. These functions can run without > * the BQL, but only in one specific iothread/main loop. > diff --git a/block/file-posix.c b/block/file-posix.c > index 4785203eea..2627431581 100644 > --- a/block/file-posix.c > +++ b/block/file-posix.c > @@ -67,6 +67,9 @@ > #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 { > + BlockZoneOp op; > + } zone_mgmt; > }; > } RawPosixAIOData; > > @@ -1369,7 +1379,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) > #endif > > if (bs->sg || S_ISBLK(st.st_mode)) { > - int ret = hdev_get_max_hw_transfer(s->fd, &st); > + ret = hdev_get_max_hw_transfer(s->fd, &st); > > if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) { > bs->bl.max_hw_transfer = ret; > @@ -1386,6 +1396,27 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) > zoned = BLK_Z_NONE; > } > bs->bl.zoned = zoned; > + if (zoned != BLK_Z_NONE) { > + ret = get_sysfs_long_val(s->fd, &st, "chunk_sectors"); > + if (ret > 0) { > + bs->bl.zone_sectors = ret; > + } > + > + ret = get_sysfs_long_val(s->fd, &st, "zone_append_max_bytes"); > + if (ret > 0) { > + bs->bl.zone_append_max_bytes = ret; > + } > + > + ret = get_sysfs_long_val(s->fd, &st, "max_open_zones"); > + if (ret > 0) { > + bs->bl.max_open_zones = ret; > + } > + > + ret = get_sysfs_long_val(s->fd, &st, "max_active_zones"); > + if (ret > 0) { > + bs->bl.max_active_zones = ret; > + } > + } > } > > static int check_for_dasd(int fd) > @@ -1880,6 +1911,167 @@ 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 void parse_zone(struct BlockZoneDescriptor *zone, > + struct blk_zone *blkz) { > + zone->start = blkz->start; > + zone->length = blkz->len; > + zone->cap = blkz->capacity; > + zone->wp = blkz->wp; > + zone->type = blkz->type; > + > + switch (blkz->cond) { > + case BLK_ZONE_COND_NOT_WP: > + blkz->cond = BLK_ZS_NOT_WP; Typo: it should be zone->cond. Same for the other zone states as below. > + break; > + case BLK_ZONE_COND_EMPTY: > + blkz->cond = BLK_ZS_EMPTY; > + break; > + case BLK_ZONE_COND_IMP_OPEN: > + blkz->cond =BLK_ZS_IOPEN; > + break; > + case BLK_ZONE_COND_EXP_OPEN: > + blkz->cond = BLK_ZS_EOPEN; > + break; > + case BLK_ZONE_COND_CLOSED: > + blkz->cond = BLK_ZS_CLOSED; > + break; > + case BLK_ZONE_COND_READONLY: > + blkz->cond = BLK_ZS_RDONLY; > + break; > + case BLK_ZONE_COND_FULL: > + blkz->cond = BLK_ZS_FULL; > + break; > + case BLK_ZONE_COND_OFFLINE: > + blkz->cond = BLK_ZS_OFFLINE; > + break; > + default: > + error_report("Invalid zone condition 0x%x", blkz->cond); > + } > +} > +#endif > + > +static int handle_aiocb_zone_report(void *opaque) { > +#if defined(CONFIG_BLKZONED) > + RawPosixAIOData *aiocb = opaque; > + int fd = aiocb->aio_fildes; > + unsigned int *nr_zones = aiocb->zone_report.nr_zones; > + BlockZoneDescriptor *zones = aiocb->zone_report.zones; > + int64_t sector = aiocb->aio_offset / 512; /* ZBDs use 512B sectors */ > + > + struct blk_zone *blkz; > + int64_t rep_size; > + unsigned int nrz; > + int ret, 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; > + > + ret = ioctl(fd, BLKREPORTZONE, rep); > + 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++) { > + parse_zone(&zones[n], &blkz[i]); > + /* The next report should start after the last zone reported */ > + sector = blkz[i].start + blkz[i].len; > + } > + } > + > + *nr_zones = n; > + return 0; > +#else > + return -ENOTSUP; > +#endif > +} > + > +static int handle_aiocb_zone_mgmt(void *opaque) { > +#if defined(CONFIG_BLKZONED) > + RawPosixAIOData *aiocb = opaque; > + BlockDriverState *bs = aiocb->bs; > + int fd = aiocb->aio_fildes; > + int64_t sector = aiocb->aio_offset; > + int64_t nr_sectors = aiocb->aio_nbytes; > + BlockZoneOp op = aiocb->zone_mgmt.op; > + struct blk_zone_range range; > + const char *ioctl_name; > + unsigned long ioctl_op; > + int64_t zone_sector, zone_sector_mask; > + int ret; > + > + zone_sector = bs->bl.zone_sectors; > + zone_sector_mask = zone_sector - 1; > + if (sector & zone_sector_mask) { > + error_report("offset %" PRId64 " is not aligned to zone size " > + "%" PRId64 "", sector, zone_sector); > + return -EINVAL; > + } > + > + if (nr_sectors & zone_sector_mask) { > + error_report("number of sectors %" PRId64 " is not aligned to zone size" > + " %" PRId64 "", nr_sectors, zone_sector); > + return -EINVAL; > + } > + > + switch (op) { > + case BLK_ZO_OPEN: > + ioctl_name = "BLKOPENZONE"; > + ioctl_op = BLKOPENZONE; > + break; > + case BLK_ZO_CLOSE: > + ioctl_name = "BLKCLOSEZONE"; > + ioctl_op = BLKCLOSEZONE; > + break; > + case BLK_ZO_FINISH: > + ioctl_name = "BLKFINISHZONE"; > + ioctl_op = BLKFINISHZONE; > + break; > + case BLK_ZO_RESET: > + ioctl_name = "BLKRESETZONE"; > + ioctl_op = BLKRESETZONE; > + break; > + default: > + error_report("Invalid zone operation 0x%x", op); > + return -EINVAL; > + } > + > + /* Execute the operation */ > + range.sector = sector; > + range.nr_sectors = nr_sectors; > + do { > + ret = ioctl(fd, ioctl_op, &range); > + } while (ret != 0 && errno == EINTR); > + > + if (ret != 0) { > + error_report("ioctl %s failed %d", > + ioctl_name, errno); > + return -errno; > + } > + > + return 0; > +#else > + return -ENOTSUP; > +#endif > +} > + > static int handle_aiocb_copy_range(void *opaque) > { > RawPosixAIOData *aiocb = opaque; > @@ -3052,6 +3244,67 @@ 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. > + * > + * @param bs: passing zone block device file descriptor > + * @param zones: an array of zone descriptors to hold zone > + * information on reply > + * @param offset: offset can be any byte within the zone size. > + * @param len: (not sure yet. > + * @return 0 on success, -1 on failure > + */ > +static int coroutine_fn raw_co_zone_report(BlockDriverState *bs, int64_t offset, > + unsigned int *nr_zones, > + BlockZoneDescriptor *zones) { > +#if defined(CONFIG_BLKZONED) > + BDRVRawState *s = bs->opaque; > + RawPosixAIOData acb; > + > + 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(bs, handle_aiocb_zone_report, &acb); > +#else > + return -ENOTSUP; > +#endif > +} > + > +/* > + * zone management operations - Execute an operation on a zone > + */ > +static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, > + int64_t offset, int64_t len) { > +#if defined(CONFIG_BLKZONED) > + BDRVRawState *s = bs->opaque; > + RawPosixAIOData acb; > + > + acb = (RawPosixAIOData) { > + .bs = bs, > + .aio_fildes = s->fd, > + .aio_type = QEMU_AIO_ZONE_MGMT, > + .aio_offset = offset, > + .aio_nbytes = len, > + .zone_mgmt = { > + .op = op, > + }, > + }; > + > + return raw_thread_pool_submit(bs, handle_aiocb_zone_mgmt, &acb); > +#else > + return -ENOTSUP; > +#endif > +} > + > static coroutine_fn int > raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes, > bool blkdev) > @@ -3552,6 +3805,14 @@ static void hdev_parse_filename(const char *filename, QDict *options, > bdrv_parse_filename_strip_prefix(filename, "host_device:", options); > } > > +#if defined(CONFIG_BLKZONED) > +static void zoned_host_device_parse_filename(const char *filename, QDict *options, > + Error **errp) > +{ > + bdrv_parse_filename_strip_prefix(filename, "zoned_host_device:", options); > +} > +#endif > + > static bool hdev_is_sg(BlockDriverState *bs) > { > > @@ -3782,6 +4043,55 @@ static BlockDriver bdrv_host_device = { > #endif > }; > > +#if defined(CONFIG_BLKZONED) > +static BlockDriver bdrv_zoned_host_device = { > + .format_name = "zoned_host_device", > + .protocol_name = "zoned_host_device", > + .instance_size = sizeof(BDRVRawState), > + .bdrv_needs_filename = true, > + .bdrv_probe_device = hdev_probe_device, > + .bdrv_parse_filename = zoned_host_device_parse_filename, > + .bdrv_file_open = hdev_open, > + .bdrv_close = raw_close, > + .bdrv_reopen_prepare = raw_reopen_prepare, > + .bdrv_reopen_commit = raw_reopen_commit, > + .bdrv_reopen_abort = raw_reopen_abort, > + .bdrv_co_create_opts = bdrv_co_create_opts_simple, > + .create_opts = &bdrv_create_opts_simple, > + .mutable_opts = mutable_opts, > + .bdrv_co_invalidate_cache = raw_co_invalidate_cache, > + .bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes, > + > + .bdrv_co_preadv = raw_co_preadv, > + .bdrv_co_pwritev = raw_co_pwritev, > + .bdrv_co_flush_to_disk = raw_co_flush_to_disk, > + .bdrv_co_pdiscard = hdev_co_pdiscard, > + .bdrv_co_copy_range_from = raw_co_copy_range_from, > + .bdrv_co_copy_range_to = raw_co_copy_range_to, > + .bdrv_refresh_limits = raw_refresh_limits, > + .bdrv_io_plug = raw_aio_plug, > + .bdrv_io_unplug = raw_aio_unplug, > + .bdrv_attach_aio_context = raw_aio_attach_aio_context, > + > + .bdrv_co_truncate = raw_co_truncate, > + .bdrv_getlength = raw_getlength, > + .bdrv_get_info = raw_get_info, > + .bdrv_get_allocated_file_size > + = raw_get_allocated_file_size, > + .bdrv_get_specific_stats = hdev_get_specific_stats, > + .bdrv_check_perm = raw_check_perm, > + .bdrv_set_perm = raw_set_perm, > + .bdrv_abort_perm_update = raw_abort_perm_update, > + .bdrv_probe_blocksizes = hdev_probe_blocksizes, > + .bdrv_probe_geometry = hdev_probe_geometry, > + .bdrv_co_ioctl = hdev_co_ioctl, > + > + /* 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__) > static void cdrom_parse_filename(const char *filename, QDict *options, > Error **errp) > @@ -4042,6 +4352,9 @@ static void bdrv_file_init(void) > bdrv_register(&bdrv_file); > #if defined(HAVE_HOST_BLOCK_DEVICE) > bdrv_register(&bdrv_host_device); > +#if defined(CONFIG_BLKZONED) > + bdrv_register(&bdrv_zoned_host_device); > +#endif > #ifdef __linux__ > bdrv_register(&bdrv_host_cdrom); > #endif > diff --git a/block/io.c b/block/io.c > index 0a8cbefe86..de9ec1d740 100644 > --- a/block/io.c > +++ b/block/io.c > @@ -3198,6 +3198,47 @@ out: > return co.ret; > } > > +int 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) { > + 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 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) { > + 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(); > diff --git a/include/block/block-common.h b/include/block/block-common.h > index 36bd0e480e..5102fa6858 100644 > --- a/include/block/block-common.h > +++ b/include/block/block-common.h > @@ -23,7 +23,6 @@ > */ > #ifndef BLOCK_COMMON_H > #define BLOCK_COMMON_H > - > #include "block/aio.h" > #include "block/aio-wait.h" > #include "qemu/iov.h" > diff --git a/include/block/block-io.h b/include/block/block-io.h > index fd25ffa9be..55ad261e16 100644 > --- a/include/block/block-io.h > +++ b/include/block/block-io.h > @@ -88,6 +88,13 @@ int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf); > /* Ensure contents are flushed to disk. */ > int coroutine_fn bdrv_co_flush(BlockDriverState *bs); > > +/* Report zone information of zone block device. */ > +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); > + > int bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes); > bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); > int bdrv_block_status(BlockDriverState *bs, int64_t offset, > @@ -297,6 +304,12 @@ bdrv_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); > int generated_co_wrapper > bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); > > +int generated_co_wrapper > +blk_zone_report(BlockBackend *blk, int64_t offset, unsigned int *nr_zones, > + BlockZoneDescriptor *zones); > +int generated_co_wrapper > +blk_zone_mgmt(BlockBackend *blk, BlockZoneOp op, int64_t offset, int64_t len); > + > /** > * bdrv_parent_drained_begin_single: > * > diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h > index 7f7863cc9e..de44c7b6f4 100644 > --- a/include/block/block_int-common.h > +++ b/include/block/block_int-common.h > @@ -94,7 +94,6 @@ typedef struct BdrvTrackedRequest { > struct BdrvTrackedRequest *waiting_for; > } BdrvTrackedRequest; > > - > struct BlockDriver { > /* > * These fields are initialized when this object is created, > @@ -691,6 +690,12 @@ struct BlockDriver { > 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 (*bdrv_is_inserted)(BlockDriverState *bs); > void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag); > @@ -828,6 +833,21 @@ typedef struct BlockLimits { > > /* device zone model */ > BlockZoneModel zoned; > + > + /* zone size expressed in 512-byte sectors */ > + uint32_t zone_sectors; > + > + /* total number of zones */ > + unsigned int nr_zones; > + > + /* maximum size in bytes of a zone append write operation */ > + int64_t zone_append_max_bytes; > + > + /* 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; > diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h > index 21fc10c4c9..3d26929cdd 100644 > --- a/include/block/raw-aio.h > +++ b/include/block/raw-aio.h > @@ -29,6 +29,8 @@ > #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 | \ > @@ -37,7 +39,9 @@ > 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 > diff --git a/meson.build b/meson.build > index 75aaca8462..8c34516443 100644 > --- a/meson.build > +++ b/meson.build > @@ -1883,6 +1883,7 @@ config_host_data.set('CONFIG_REPLICATION', get_option('live_block_migration').al > # 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')) > diff --git a/qapi/block-core.json b/qapi/block-core.json > index 2173e7734a..c6bbb7a037 100644 > --- a/qapi/block-core.json > +++ b/qapi/block-core.json > @@ -2942,6 +2942,7 @@ > # @compress: Since 5.0 > # @copy-before-write: Since 6.2 > # @snapshot-access: Since 7.0 > +# @zoned_host_device: Since 7.2 > # > # Since: 2.9 > ## > @@ -2955,7 +2956,8 @@ > 'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', > 'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd', > { 'name': 'replication', 'if': 'CONFIG_REPLICATION' }, > - 'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] } > + 'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', > + { 'name': 'zoned_host_device', 'if': 'CONFIG_BLKZONED' } ] } > > ## > # @BlockdevOptionsFile: > @@ -4329,7 +4331,9 @@ > 'vhdx': 'BlockdevOptionsGenericFormat', > 'vmdk': 'BlockdevOptionsGenericCOWFormat', > 'vpc': 'BlockdevOptionsGenericFormat', > - 'vvfat': 'BlockdevOptionsVVFAT' > + 'vvfat': 'BlockdevOptionsVVFAT', > + 'zoned_host_device': { 'type': 'BlockdevOptionsFile', > + 'if': 'CONFIG_BLKZONED' } > } } > > ## > diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c > index 952dc940f1..5a215277c7 100644 > --- a/qemu-io-cmds.c > +++ b/qemu-io-cmds.c > @@ -1712,6 +1712,145 @@ static const cmdinfo_t flush_cmd = { > .oneline = "flush all in-core file state to disk", > }; > > +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", > + zones[i].start, zones[i].length, zones[i].cap, zones[i].wp, > + zones[i].cond, 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", > +}; > + > + An extra blank line should be removed. > static int truncate_f(BlockBackend *blk, int argc, char **argv); > static const cmdinfo_t truncate_cmd = { > .name = "truncate", > @@ -2504,6 +2643,11 @@ 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); > -- > 2.37.1 >
diff --git a/block/block-backend.c b/block/block-backend.c index d4a5df2ac2..fc639b0cd7 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -1775,6 +1775,56 @@ int coroutine_fn blk_co_flush(BlockBackend *blk) return ret; } +/* + * 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); + 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. + * offset is the starting zone specified as a sector offset. + * len is the maximum number of sectors the command should operate on. + */ +int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op, + int64_t offset, int64_t len) +{ + int ret; + IO_CODE(); + + ret = blk_check_byte_request(blk, offset, len); + if (ret < 0) { + return ret; + } + blk_inc_in_flight(blk); + blk_wait_while_drained(blk); + if (!blk_is_available(blk)) { + blk_dec_in_flight(blk); + return -ENOMEDIUM; + } + 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); diff --git a/block/coroutines.h b/block/coroutines.h index 3a2bad564f..e3f62d94e5 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -63,6 +63,12 @@ nbd_co_do_establish_connection(BlockDriverState *bs, bool blocking, Error **errp); +int coroutine_fn blk_co_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); + /* * "I/O or GS" API functions. These functions can run without * the BQL, but only in one specific iothread/main loop. diff --git a/block/file-posix.c b/block/file-posix.c index 4785203eea..2627431581 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -67,6 +67,9 @@ #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 { + BlockZoneOp op; + } zone_mgmt; }; } RawPosixAIOData; @@ -1369,7 +1379,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) #endif if (bs->sg || S_ISBLK(st.st_mode)) { - int ret = hdev_get_max_hw_transfer(s->fd, &st); + ret = hdev_get_max_hw_transfer(s->fd, &st); if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) { bs->bl.max_hw_transfer = ret; @@ -1386,6 +1396,27 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) zoned = BLK_Z_NONE; } bs->bl.zoned = zoned; + if (zoned != BLK_Z_NONE) { + ret = get_sysfs_long_val(s->fd, &st, "chunk_sectors"); + if (ret > 0) { + bs->bl.zone_sectors = ret; + } + + ret = get_sysfs_long_val(s->fd, &st, "zone_append_max_bytes"); + if (ret > 0) { + bs->bl.zone_append_max_bytes = ret; + } + + ret = get_sysfs_long_val(s->fd, &st, "max_open_zones"); + if (ret > 0) { + bs->bl.max_open_zones = ret; + } + + ret = get_sysfs_long_val(s->fd, &st, "max_active_zones"); + if (ret > 0) { + bs->bl.max_active_zones = ret; + } + } } static int check_for_dasd(int fd) @@ -1880,6 +1911,167 @@ 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 void parse_zone(struct BlockZoneDescriptor *zone, + struct blk_zone *blkz) { + zone->start = blkz->start; + zone->length = blkz->len; + zone->cap = blkz->capacity; + zone->wp = blkz->wp; + zone->type = blkz->type; + + switch (blkz->cond) { + case BLK_ZONE_COND_NOT_WP: + blkz->cond = BLK_ZS_NOT_WP; + break; + case BLK_ZONE_COND_EMPTY: + blkz->cond = BLK_ZS_EMPTY; + break; + case BLK_ZONE_COND_IMP_OPEN: + blkz->cond =BLK_ZS_IOPEN; + break; + case BLK_ZONE_COND_EXP_OPEN: + blkz->cond = BLK_ZS_EOPEN; + break; + case BLK_ZONE_COND_CLOSED: + blkz->cond = BLK_ZS_CLOSED; + break; + case BLK_ZONE_COND_READONLY: + blkz->cond = BLK_ZS_RDONLY; + break; + case BLK_ZONE_COND_FULL: + blkz->cond = BLK_ZS_FULL; + break; + case BLK_ZONE_COND_OFFLINE: + blkz->cond = BLK_ZS_OFFLINE; + break; + default: + error_report("Invalid zone condition 0x%x", blkz->cond); + } +} +#endif + +static int handle_aiocb_zone_report(void *opaque) { +#if defined(CONFIG_BLKZONED) + RawPosixAIOData *aiocb = opaque; + int fd = aiocb->aio_fildes; + unsigned int *nr_zones = aiocb->zone_report.nr_zones; + BlockZoneDescriptor *zones = aiocb->zone_report.zones; + int64_t sector = aiocb->aio_offset / 512; /* ZBDs use 512B sectors */ + + struct blk_zone *blkz; + int64_t rep_size; + unsigned int nrz; + int ret, 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; + + ret = ioctl(fd, BLKREPORTZONE, rep); + 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++) { + parse_zone(&zones[n], &blkz[i]); + /* The next report should start after the last zone reported */ + sector = blkz[i].start + blkz[i].len; + } + } + + *nr_zones = n; + return 0; +#else + return -ENOTSUP; +#endif +} + +static int handle_aiocb_zone_mgmt(void *opaque) { +#if defined(CONFIG_BLKZONED) + RawPosixAIOData *aiocb = opaque; + BlockDriverState *bs = aiocb->bs; + int fd = aiocb->aio_fildes; + int64_t sector = aiocb->aio_offset; + int64_t nr_sectors = aiocb->aio_nbytes; + BlockZoneOp op = aiocb->zone_mgmt.op; + struct blk_zone_range range; + const char *ioctl_name; + unsigned long ioctl_op; + int64_t zone_sector, zone_sector_mask; + int ret; + + zone_sector = bs->bl.zone_sectors; + zone_sector_mask = zone_sector - 1; + if (sector & zone_sector_mask) { + error_report("offset %" PRId64 " is not aligned to zone size " + "%" PRId64 "", sector, zone_sector); + return -EINVAL; + } + + if (nr_sectors & zone_sector_mask) { + error_report("number of sectors %" PRId64 " is not aligned to zone size" + " %" PRId64 "", nr_sectors, zone_sector); + return -EINVAL; + } + + switch (op) { + case BLK_ZO_OPEN: + ioctl_name = "BLKOPENZONE"; + ioctl_op = BLKOPENZONE; + break; + case BLK_ZO_CLOSE: + ioctl_name = "BLKCLOSEZONE"; + ioctl_op = BLKCLOSEZONE; + break; + case BLK_ZO_FINISH: + ioctl_name = "BLKFINISHZONE"; + ioctl_op = BLKFINISHZONE; + break; + case BLK_ZO_RESET: + ioctl_name = "BLKRESETZONE"; + ioctl_op = BLKRESETZONE; + break; + default: + error_report("Invalid zone operation 0x%x", op); + return -EINVAL; + } + + /* Execute the operation */ + range.sector = sector; + range.nr_sectors = nr_sectors; + do { + ret = ioctl(fd, ioctl_op, &range); + } while (ret != 0 && errno == EINTR); + + if (ret != 0) { + error_report("ioctl %s failed %d", + ioctl_name, errno); + return -errno; + } + + return 0; +#else + return -ENOTSUP; +#endif +} + static int handle_aiocb_copy_range(void *opaque) { RawPosixAIOData *aiocb = opaque; @@ -3052,6 +3244,67 @@ 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. + * + * @param bs: passing zone block device file descriptor + * @param zones: an array of zone descriptors to hold zone + * information on reply + * @param offset: offset can be any byte within the zone size. + * @param len: (not sure yet. + * @return 0 on success, -1 on failure + */ +static int coroutine_fn raw_co_zone_report(BlockDriverState *bs, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones) { +#if defined(CONFIG_BLKZONED) + BDRVRawState *s = bs->opaque; + RawPosixAIOData acb; + + 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(bs, handle_aiocb_zone_report, &acb); +#else + return -ENOTSUP; +#endif +} + +/* + * zone management operations - Execute an operation on a zone + */ +static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, + int64_t offset, int64_t len) { +#if defined(CONFIG_BLKZONED) + BDRVRawState *s = bs->opaque; + RawPosixAIOData acb; + + acb = (RawPosixAIOData) { + .bs = bs, + .aio_fildes = s->fd, + .aio_type = QEMU_AIO_ZONE_MGMT, + .aio_offset = offset, + .aio_nbytes = len, + .zone_mgmt = { + .op = op, + }, + }; + + return raw_thread_pool_submit(bs, handle_aiocb_zone_mgmt, &acb); +#else + return -ENOTSUP; +#endif +} + static coroutine_fn int raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes, bool blkdev) @@ -3552,6 +3805,14 @@ static void hdev_parse_filename(const char *filename, QDict *options, bdrv_parse_filename_strip_prefix(filename, "host_device:", options); } +#if defined(CONFIG_BLKZONED) +static void zoned_host_device_parse_filename(const char *filename, QDict *options, + Error **errp) +{ + bdrv_parse_filename_strip_prefix(filename, "zoned_host_device:", options); +} +#endif + static bool hdev_is_sg(BlockDriverState *bs) { @@ -3782,6 +4043,55 @@ static BlockDriver bdrv_host_device = { #endif }; +#if defined(CONFIG_BLKZONED) +static BlockDriver bdrv_zoned_host_device = { + .format_name = "zoned_host_device", + .protocol_name = "zoned_host_device", + .instance_size = sizeof(BDRVRawState), + .bdrv_needs_filename = true, + .bdrv_probe_device = hdev_probe_device, + .bdrv_parse_filename = zoned_host_device_parse_filename, + .bdrv_file_open = hdev_open, + .bdrv_close = raw_close, + .bdrv_reopen_prepare = raw_reopen_prepare, + .bdrv_reopen_commit = raw_reopen_commit, + .bdrv_reopen_abort = raw_reopen_abort, + .bdrv_co_create_opts = bdrv_co_create_opts_simple, + .create_opts = &bdrv_create_opts_simple, + .mutable_opts = mutable_opts, + .bdrv_co_invalidate_cache = raw_co_invalidate_cache, + .bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes, + + .bdrv_co_preadv = raw_co_preadv, + .bdrv_co_pwritev = raw_co_pwritev, + .bdrv_co_flush_to_disk = raw_co_flush_to_disk, + .bdrv_co_pdiscard = hdev_co_pdiscard, + .bdrv_co_copy_range_from = raw_co_copy_range_from, + .bdrv_co_copy_range_to = raw_co_copy_range_to, + .bdrv_refresh_limits = raw_refresh_limits, + .bdrv_io_plug = raw_aio_plug, + .bdrv_io_unplug = raw_aio_unplug, + .bdrv_attach_aio_context = raw_aio_attach_aio_context, + + .bdrv_co_truncate = raw_co_truncate, + .bdrv_getlength = raw_getlength, + .bdrv_get_info = raw_get_info, + .bdrv_get_allocated_file_size + = raw_get_allocated_file_size, + .bdrv_get_specific_stats = hdev_get_specific_stats, + .bdrv_check_perm = raw_check_perm, + .bdrv_set_perm = raw_set_perm, + .bdrv_abort_perm_update = raw_abort_perm_update, + .bdrv_probe_blocksizes = hdev_probe_blocksizes, + .bdrv_probe_geometry = hdev_probe_geometry, + .bdrv_co_ioctl = hdev_co_ioctl, + + /* 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__) static void cdrom_parse_filename(const char *filename, QDict *options, Error **errp) @@ -4042,6 +4352,9 @@ static void bdrv_file_init(void) bdrv_register(&bdrv_file); #if defined(HAVE_HOST_BLOCK_DEVICE) bdrv_register(&bdrv_host_device); +#if defined(CONFIG_BLKZONED) + bdrv_register(&bdrv_zoned_host_device); +#endif #ifdef __linux__ bdrv_register(&bdrv_host_cdrom); #endif diff --git a/block/io.c b/block/io.c index 0a8cbefe86..de9ec1d740 100644 --- a/block/io.c +++ b/block/io.c @@ -3198,6 +3198,47 @@ out: return co.ret; } +int 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) { + 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 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) { + 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(); diff --git a/include/block/block-common.h b/include/block/block-common.h index 36bd0e480e..5102fa6858 100644 --- a/include/block/block-common.h +++ b/include/block/block-common.h @@ -23,7 +23,6 @@ */ #ifndef BLOCK_COMMON_H #define BLOCK_COMMON_H - #include "block/aio.h" #include "block/aio-wait.h" #include "qemu/iov.h" diff --git a/include/block/block-io.h b/include/block/block-io.h index fd25ffa9be..55ad261e16 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -88,6 +88,13 @@ int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf); /* Ensure contents are flushed to disk. */ int coroutine_fn bdrv_co_flush(BlockDriverState *bs); +/* Report zone information of zone block device. */ +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); + int bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes); bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); int bdrv_block_status(BlockDriverState *bs, int64_t offset, @@ -297,6 +304,12 @@ bdrv_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); int generated_co_wrapper bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); +int generated_co_wrapper +blk_zone_report(BlockBackend *blk, int64_t offset, unsigned int *nr_zones, + BlockZoneDescriptor *zones); +int generated_co_wrapper +blk_zone_mgmt(BlockBackend *blk, BlockZoneOp op, int64_t offset, int64_t len); + /** * bdrv_parent_drained_begin_single: * diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index 7f7863cc9e..de44c7b6f4 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -94,7 +94,6 @@ typedef struct BdrvTrackedRequest { struct BdrvTrackedRequest *waiting_for; } BdrvTrackedRequest; - struct BlockDriver { /* * These fields are initialized when this object is created, @@ -691,6 +690,12 @@ struct BlockDriver { 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 (*bdrv_is_inserted)(BlockDriverState *bs); void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag); @@ -828,6 +833,21 @@ typedef struct BlockLimits { /* device zone model */ BlockZoneModel zoned; + + /* zone size expressed in 512-byte sectors */ + uint32_t zone_sectors; + + /* total number of zones */ + unsigned int nr_zones; + + /* maximum size in bytes of a zone append write operation */ + int64_t zone_append_max_bytes; + + /* 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; diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h index 21fc10c4c9..3d26929cdd 100644 --- a/include/block/raw-aio.h +++ b/include/block/raw-aio.h @@ -29,6 +29,8 @@ #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 | \ @@ -37,7 +39,9 @@ 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 diff --git a/meson.build b/meson.build index 75aaca8462..8c34516443 100644 --- a/meson.build +++ b/meson.build @@ -1883,6 +1883,7 @@ config_host_data.set('CONFIG_REPLICATION', get_option('live_block_migration').al # 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')) diff --git a/qapi/block-core.json b/qapi/block-core.json index 2173e7734a..c6bbb7a037 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -2942,6 +2942,7 @@ # @compress: Since 5.0 # @copy-before-write: Since 6.2 # @snapshot-access: Since 7.0 +# @zoned_host_device: Since 7.2 # # Since: 2.9 ## @@ -2955,7 +2956,8 @@ 'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', 'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd', { 'name': 'replication', 'if': 'CONFIG_REPLICATION' }, - 'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] } + 'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', + { 'name': 'zoned_host_device', 'if': 'CONFIG_BLKZONED' } ] } ## # @BlockdevOptionsFile: @@ -4329,7 +4331,9 @@ 'vhdx': 'BlockdevOptionsGenericFormat', 'vmdk': 'BlockdevOptionsGenericCOWFormat', 'vpc': 'BlockdevOptionsGenericFormat', - 'vvfat': 'BlockdevOptionsVVFAT' + 'vvfat': 'BlockdevOptionsVVFAT', + 'zoned_host_device': { 'type': 'BlockdevOptionsFile', + 'if': 'CONFIG_BLKZONED' } } } ## diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index 952dc940f1..5a215277c7 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -1712,6 +1712,145 @@ static const cmdinfo_t flush_cmd = { .oneline = "flush all in-core file state to disk", }; +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", + zones[i].start, zones[i].length, zones[i].cap, zones[i].wp, + zones[i].cond, 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", @@ -2504,6 +2643,11 @@ 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);