@@ -1770,6 +1770,396 @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
return blk_aio_prwv(blk, req, 0, buf, blk_aio_ioctl_entry, 0, cb, opaque);
}
+typedef struct BlkPrInCo {
+ BlockBackend *blk;
+ uint32_t *generation;
+ uint32_t num_keys;
+ BlockPrType *type;
+ uint64_t *keys;
+ int ret;
+} BlkPrInCo;
+
+typedef struct BlkPrInCB {
+ BlockAIOCB common;
+ BlkPrInCo prco;
+ bool has_returned;
+} BlkPrInCB;
+
+static const AIOCBInfo blk_pr_in_aiocb_info = {
+ .aiocb_size = sizeof(BlkPrInCB),
+};
+
+static void blk_pr_in_complete(BlkPrInCB *acb)
+{
+ if (acb->has_returned) {
+ acb->common.cb(acb->common.opaque, acb->prco.ret);
+ blk_dec_in_flight(acb->prco.blk);
+ qemu_aio_unref(acb);
+ }
+}
+
+static void blk_pr_in_complete_bh(void *opaque)
+{
+ BlkPrInCB *acb = opaque;
+ assert(acb->has_returned);
+ blk_pr_in_complete(acb);
+}
+
+static BlockAIOCB *blk_aio_pr_in(BlockBackend *blk, uint32_t *generation,
+ uint32_t num_keys, BlockPrType *type,
+ uint64_t *keys, CoroutineEntry co_entry,
+ BlockCompletionFunc *cb, void *opaque)
+{
+ BlkPrInCB *acb;
+ Coroutine *co;
+
+ blk_inc_in_flight(blk);
+ acb = blk_aio_get(&blk_pr_in_aiocb_info, blk, cb, opaque);
+ acb->prco = (BlkPrInCo) {
+ .blk = blk,
+ .generation = generation,
+ .num_keys = num_keys,
+ .type = type,
+ .ret = NOT_DONE,
+ .keys = keys,
+ };
+ acb->has_returned = false;
+
+ co = qemu_coroutine_create(co_entry, acb);
+ aio_co_enter(qemu_get_current_aio_context(), co);
+
+ acb->has_returned = true;
+ if (acb->prco.ret != NOT_DONE) {
+ replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+ blk_pr_in_complete_bh, acb);
+ }
+
+ return &acb->common;
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_aio_pr_do_read_keys(BlockBackend *blk, uint32_t *generation,
+ uint32_t num_keys, uint64_t *keys)
+{
+ IO_CODE();
+
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ if (!blk_co_is_available(blk)) {
+ return -ENOMEDIUM;
+ }
+
+ return bdrv_co_pr_read_keys(blk_bs(blk), generation, num_keys, keys);
+}
+
+static void coroutine_fn blk_aio_pr_read_keys_entry(void *opaque)
+{
+ BlkPrInCB *acb = opaque;
+ BlkPrInCo *prco = &acb->prco;
+
+ prco->ret = blk_aio_pr_do_read_keys(prco->blk, prco->generation,
+ prco->num_keys, prco->keys);
+ blk_pr_in_complete(acb);
+}
+
+BlockAIOCB *blk_aio_pr_read_keys(BlockBackend *blk, uint32_t *generation,
+ uint32_t num_keys, uint64_t *keys,
+ BlockCompletionFunc *cb, void *opaque)
+{
+ IO_CODE();
+ return blk_aio_pr_in(blk, generation, num_keys, NULL, keys,
+ blk_aio_pr_read_keys_entry, cb, opaque);
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_aio_pr_do_read_reservation(BlockBackend *blk, uint32_t *generation,
+ uint64_t *key, BlockPrType *type)
+{
+ IO_CODE();
+
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ if (!blk_co_is_available(blk)) {
+ return -ENOMEDIUM;
+ }
+
+ return bdrv_co_pr_read_reservation(blk_bs(blk), generation, key, type);
+}
+
+static void coroutine_fn blk_aio_pr_read_reservation_entry(void *opaque)
+{
+ BlkPrInCB *acb = opaque;
+ BlkPrInCo *prco = &acb->prco;
+
+ prco->ret = blk_aio_pr_do_read_reservation(prco->blk, prco->generation,
+ prco->keys, prco->type);
+ blk_pr_in_complete(acb);
+}
+
+BlockAIOCB *blk_aio_pr_read_reservation(BlockBackend *blk, uint32_t *generation,
+ uint64_t *key, BlockPrType *type,
+ BlockCompletionFunc *cb, void *opaque)
+{
+ IO_CODE();
+ return blk_aio_pr_in(blk, generation, 0, type, key,
+ blk_aio_pr_read_reservation_entry, cb, opaque);
+}
+
+typedef struct BlkPrOutCo {
+ BlockBackend *blk;
+ uint64_t old_key;
+ uint64_t new_key;
+ BlockPrType type;
+ bool ignore_key;
+ bool abort;
+ int ret;
+} BlkPrOutCo;
+
+typedef struct BlkPrOutCB {
+ BlockAIOCB common;
+ BlkPrOutCo prco;
+ bool has_returned;
+} BlkPrOutCB;
+
+static const AIOCBInfo blk_pr_out_aiocb_info = {
+ .aiocb_size = sizeof(BlkPrOutCB),
+};
+
+static void blk_pr_out_complete(BlkPrOutCB *acb)
+{
+ if (acb->has_returned) {
+ acb->common.cb(acb->common.opaque, acb->prco.ret);
+ blk_dec_in_flight(acb->prco.blk);
+ qemu_aio_unref(acb);
+ }
+}
+
+static void blk_pr_out_complete_bh(void *opaque)
+{
+ BlkPrOutCB *acb = opaque;
+ assert(acb->has_returned);
+ blk_pr_out_complete(acb);
+}
+
+static BlockAIOCB *blk_aio_pr_out(BlockBackend *blk, uint64_t old_key,
+ uint64_t new_key, BlockPrType type,
+ bool ignore_key, bool abort,
+ CoroutineEntry co_entry,
+ BlockCompletionFunc *cb, void *opaque)
+{
+ BlkPrOutCB *acb;
+ Coroutine *co;
+
+ blk_inc_in_flight(blk);
+ acb = blk_aio_get(&blk_pr_out_aiocb_info, blk, cb, opaque);
+ acb->prco = (BlkPrOutCo) {
+ .blk = blk,
+ .old_key = old_key,
+ .new_key = new_key,
+ .type = type,
+ .ignore_key = ignore_key,
+ .abort = abort,
+ .ret = NOT_DONE,
+ };
+ acb->has_returned = false;
+
+ co = qemu_coroutine_create(co_entry, acb);
+ aio_co_enter(qemu_get_current_aio_context(), co);
+
+ acb->has_returned = true;
+ if (acb->prco.ret != NOT_DONE) {
+ replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+ blk_pr_out_complete_bh, acb);
+ }
+
+ return &acb->common;
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_aio_pr_do_register(BlockBackend *blk, uint64_t old_key,
+ uint64_t new_key, BlockPrType type,
+ bool ignore_key)
+{
+ IO_CODE();
+
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ if (!blk_co_is_available(blk)) {
+ return -ENOMEDIUM;
+ }
+
+ return bdrv_co_pr_register(blk_bs(blk), old_key, new_key, type, ignore_key);
+}
+
+static void coroutine_fn blk_aio_pr_register_entry(void *opaque)
+{
+ BlkPrOutCB *acb = opaque;
+ BlkPrOutCo *prco = &acb->prco;
+
+ prco->ret = blk_aio_pr_do_register(prco->blk, prco->old_key, prco->new_key,
+ prco->type, prco->ignore_key);
+ blk_pr_out_complete(acb);
+}
+
+BlockAIOCB *blk_aio_pr_register(BlockBackend *blk, uint64_t old_key,
+ uint64_t new_key, BlockPrType type,
+ bool ignore_key, BlockCompletionFunc *cb,
+ void *opaque)
+{
+ IO_CODE();
+ return blk_aio_pr_out(blk, old_key, new_key, type, ignore_key, false,
+ blk_aio_pr_register_entry, cb, opaque);
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_aio_pr_do_reserve(BlockBackend *blk, uint64_t key, BlockPrType type)
+{
+ IO_CODE();
+
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ if (!blk_co_is_available(blk)) {
+ return -ENOMEDIUM;
+ }
+
+ return bdrv_co_pr_reserve(blk_bs(blk), key, type);
+}
+
+static void coroutine_fn blk_aio_pr_reserve_entry(void *opaque)
+{
+ BlkPrOutCB *acb = opaque;
+ BlkPrOutCo *prco = &acb->prco;
+
+ prco->ret = blk_aio_pr_do_reserve(prco->blk, prco->old_key, prco->type);
+ blk_pr_out_complete(acb);
+}
+
+
+BlockAIOCB *blk_aio_pr_reserve(BlockBackend *blk, uint64_t key,
+ BlockPrType type, BlockCompletionFunc *cb,
+ void *opaque)
+{
+ IO_CODE();
+ return blk_aio_pr_out(blk, key, 0, type, false, false,
+ blk_aio_pr_reserve_entry, cb, opaque);
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_aio_pr_do_release(BlockBackend *blk, uint64_t key, BlockPrType type)
+{
+ IO_CODE();
+
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ if (!blk_co_is_available(blk)) {
+ return -ENOMEDIUM;
+ }
+
+ return bdrv_co_pr_release(blk_bs(blk), key, type);
+}
+
+static void coroutine_fn blk_aio_pr_release_entry(void *opaque)
+{
+ BlkPrOutCB *acb = opaque;
+ BlkPrOutCo *prco = &acb->prco;
+
+ prco->ret = blk_aio_pr_do_release(prco->blk, prco->old_key, prco->type);
+ blk_pr_out_complete(acb);
+}
+
+
+BlockAIOCB *blk_aio_pr_release(BlockBackend *blk, uint64_t key,
+ BlockPrType type, BlockCompletionFunc *cb,
+ void *opaque)
+{
+ IO_CODE();
+ return blk_aio_pr_out(blk, key, 0, type, false, false,
+ blk_aio_pr_release_entry, cb, opaque);
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_aio_pr_do_clear(BlockBackend *blk, uint64_t key)
+{
+ IO_CODE();
+
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ if (!blk_co_is_available(blk)) {
+ return -ENOMEDIUM;
+ }
+
+ return bdrv_co_pr_clear(blk_bs(blk), key);
+}
+
+static void coroutine_fn blk_aio_pr_clear_entry(void *opaque)
+{
+ BlkPrOutCB *acb = opaque;
+ BlkPrOutCo *prco = &acb->prco;
+
+ prco->ret = blk_aio_pr_do_clear(prco->blk, prco->old_key);
+ blk_pr_out_complete(acb);
+}
+
+
+BlockAIOCB *blk_aio_pr_clear(BlockBackend *blk, uint64_t key,
+ BlockCompletionFunc *cb, void *opaque)
+{
+ IO_CODE();
+ return blk_aio_pr_out(blk, key, 0, 0, false, false,
+ blk_aio_pr_clear_entry, cb, opaque);
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_aio_pr_do_preempt(BlockBackend *blk, uint64_t cr_key,
+ uint64_t pr_key, BlockPrType type, bool abort)
+{
+ IO_CODE();
+
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ if (!blk_co_is_available(blk)) {
+ return -ENOMEDIUM;
+ }
+
+ return bdrv_co_pr_preempt(blk_bs(blk), cr_key, pr_key, type, abort);
+}
+
+static void coroutine_fn blk_aio_pr_preempt_entry(void *opaque)
+{
+ BlkPrOutCB *acb = opaque;
+ BlkPrOutCo *prco = &acb->prco;
+
+ prco->ret = blk_aio_pr_do_preempt(prco->blk, prco->old_key,
+ prco->new_key, prco->type,
+ prco->abort);
+ blk_pr_out_complete(acb);
+}
+
+
+BlockAIOCB *blk_aio_pr_preempt(BlockBackend *blk, uint64_t cr_key,
+ uint64_t pr_key, BlockPrType type,
+ bool abort, BlockCompletionFunc *cb,
+ void *opaque)
+{
+ IO_CODE();
+ return blk_aio_pr_out(blk, cr_key, pr_key, type, false, abort,
+ blk_aio_pr_preempt_entry, cb, opaque);
+}
+
/* To be called between exactly one pair of blk_inc/dec_in_flight() */
static int coroutine_fn
blk_co_do_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes)
@@ -3220,6 +3220,167 @@ out:
return co.ret;
}
+int coroutine_fn bdrv_co_pr_read_keys(BlockDriverState *bs,
+ uint32_t *generation, uint32_t num_keys,
+ uint64_t *keys)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ IO_CODE();
+ assert_bdrv_graph_readable();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_pr_read_keys) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+
+ co.ret = drv->bdrv_co_pr_read_keys(bs, generation, num_keys, keys);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
+int coroutine_fn bdrv_co_pr_read_reservation(BlockDriverState *bs,
+ uint32_t *generation, uint64_t *key, BlockPrType *type)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ IO_CODE();
+ assert_bdrv_graph_readable();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_pr_read_reservation) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+
+ co.ret = drv->bdrv_co_pr_read_reservation(bs, generation, key, type);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
+int coroutine_fn bdrv_co_pr_register(BlockDriverState *bs, uint64_t old_key,
+ uint64_t new_key, BlockPrType type, bool ignore_key)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ IO_CODE();
+ assert_bdrv_graph_readable();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_pr_register) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+
+ co.ret = drv->bdrv_co_pr_register(bs, old_key, new_key, type, ignore_key);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
+int coroutine_fn bdrv_co_pr_reserve(BlockDriverState *bs, uint64_t key,
+ BlockPrType type)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ IO_CODE();
+ assert_bdrv_graph_readable();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_pr_reserve) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+
+ co.ret = drv->bdrv_co_pr_reserve(bs, key, type);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
+int coroutine_fn bdrv_co_pr_release(BlockDriverState *bs, uint64_t key,
+ BlockPrType type)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ IO_CODE();
+ assert_bdrv_graph_readable();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_pr_release) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+
+ co.ret = drv->bdrv_co_pr_release(bs, key, type);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
+int coroutine_fn bdrv_co_pr_clear(BlockDriverState *bs, uint64_t key)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ IO_CODE();
+ assert_bdrv_graph_readable();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_pr_clear) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+
+ co.ret = drv->bdrv_co_pr_clear(bs, key);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
+int coroutine_fn bdrv_co_pr_preempt(BlockDriverState *bs, uint64_t cr_key,
+ uint64_t pr_key, BlockPrType type, bool abort)
+{
+ BlockDriver *drv = bs->drv;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ IO_CODE();
+ assert_bdrv_graph_readable();
+
+ bdrv_inc_in_flight(bs);
+ if (!drv || !drv->bdrv_co_pr_preempt) {
+ co.ret = -ENOTSUP;
+ goto out;
+ }
+
+ co.ret = drv->bdrv_co_pr_preempt(bs, cr_key, pr_key, type, abort);
+out:
+ bdrv_dec_in_flight(bs);
+ return co.ret;
+}
+
int coroutine_fn bdrv_co_zone_report(BlockDriverState *bs, int64_t offset,
unsigned int *nr_zones,
BlockZoneDescriptor *zones)
@@ -524,6 +524,46 @@ typedef enum {
BDRV_FIX_ERRORS = 2,
} BdrvCheckMode;
+/**
+ * According SCSI protocol(chapter 5.9 of SCSI Primary Commands - 4)
+ * and NVMe protocol(chapter 7.2 of NVMe Base Specification 2.0),
+ * the persistent reservation types and persistent capabilities of
+ * the public layer block are abstracted.
+ */
+typedef enum {
+ BLK_PR_WRITE_EXCLUSIVE = 0x1,
+ BLK_PR_EXCLUSIVE_ACCESS = 0x2,
+ BLK_PR_WRITE_EXCLUSIVE_REGS_ONLY = 0x3,
+ BLK_PR_EXCLUSIVE_ACCESS_REGS_ONLY = 0x4,
+ BLK_PR_WRITE_EXCLUSIVE_ALL_REGS = 0x5,
+ BLK_PR_EXCLUSIVE_ACCESS_ALL_REGS = 0x6,
+} BlockPrType;
+
+typedef enum BLKPrCap {
+ /* Persist Through Power Loss */
+ BLK_PR_CAP_PTPL = 1 << 0,
+ /* Write Exclusive reservation type */
+ BLK_PR_CAP_WR_EX = 1 << 1,
+ /* Exclusive Access reservation type */
+ BLK_PR_CAP_EX_AC = 1 << 2,
+ /* Write Exclusive Registrants Only reservation type */
+ BLK_PR_CAP_WR_EX_RO = 1 << 3,
+ /* Exclusive Access Registrants Only reservation type */
+ BLK_PR_CAP_EX_AC_RO = 1 << 4,
+ /* Write Exclusive All Registrants reservation type */
+ BLK_PR_CAP_WR_EX_AR = 1 << 5,
+ /* Exclusive Access All Registrants reservation type */
+ BLK_PR_CAP_EX_AC_AR = 1 << 6,
+
+ BLK_PR_CAP_ALL = (BLK_PR_CAP_PTPL |
+ BLK_PR_CAP_WR_EX |
+ BLK_PR_CAP_EX_AC |
+ BLK_PR_CAP_WR_EX_RO |
+ BLK_PR_CAP_EX_AC_RO |
+ BLK_PR_CAP_WR_EX_AR |
+ BLK_PR_CAP_EX_AC_AR),
+} BLKPrCap;
+
typedef struct BlockSizes {
uint32_t phys;
uint32_t log;
@@ -106,6 +106,25 @@ void bdrv_aio_cancel_async(BlockAIOCB *acb);
int coroutine_fn GRAPH_RDLOCK
bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf);
+int coroutine_fn GRAPH_RDLOCK
+bdrv_co_pr_read_keys(BlockDriverState *bs, uint32_t *generation,
+ uint32_t num_keys, uint64_t *keys);
+int coroutine_fn GRAPH_RDLOCK
+bdrv_co_pr_read_reservation(BlockDriverState *bs, uint32_t *generation,
+ uint64_t *key, BlockPrType *type);
+int coroutine_fn GRAPH_RDLOCK
+bdrv_co_pr_register(BlockDriverState *bs, uint64_t old_key,
+ uint64_t new_key, BlockPrType type, bool ignore_key);
+int coroutine_fn GRAPH_RDLOCK
+bdrv_co_pr_reserve(BlockDriverState *bs, uint64_t key, BlockPrType type);
+int coroutine_fn GRAPH_RDLOCK
+bdrv_co_pr_release(BlockDriverState *bs, uint64_t key, BlockPrType type);
+int coroutine_fn GRAPH_RDLOCK
+bdrv_co_pr_clear(BlockDriverState *bs, uint64_t key);
+int coroutine_fn GRAPH_RDLOCK
+bdrv_co_pr_preempt(BlockDriverState *bs, uint64_t cr_key, uint64_t pr_key,
+ BlockPrType type, bool abort);
+
/* Ensure contents are flushed to disk. */
int coroutine_fn GRAPH_RDLOCK bdrv_co_flush(BlockDriverState *bs);
@@ -766,6 +766,88 @@ struct BlockDriver {
int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_ioctl)(
BlockDriverState *bs, unsigned long int req, void *buf);
+ /*
+ * Persistent reservation series api.
+ * Please refer to chapter 5.9 of SCSI Primary Commands - 4 or
+ * chapter 7 of NVMe Base Specification 2.0.
+ *
+ * The block layer driver should implement all the following APIs
+ * or none at all, including: bdrv_co_pr_read_keys,
+ * bdrv_co_pr_read_reservation, bdrv_co_pr_register,
+ * bdrv_co_pr_reserve, bdrv_co_pr_release,
+ * bdrv_co_pr_clear and bdrv_co_pr_preempt.
+ *
+ * Read the registered keys and return them in the @keys.
+ * @generation: The generation of the reservation key.
+ * @num_keys: The maximum number of keys that can be transmitted.
+ * @keys: Registered keys array.
+ *
+ * On success, store generation in @generation and store keys @keys
+ * and return the number of @keys.
+ * On failure return -errno.
+ */
+ int coroutine_fn GRAPH_RDLOCK_PTR(*bdrv_co_pr_read_keys)(
+ BlockDriverState *bs, uint32_t *generation,
+ uint32_t num_keys, uint64_t *keys);
+ /*
+ * Read the reservation key and store it in the @key.
+ * @generation: The generation of the reservation key.
+ * @key: The reservation key.
+ * @type: Type of the reservation key.
+ *
+ * On success, store generation in @generation, store the
+ * reservation key in @key and return the number of @key
+ * which used to determine whether the reservation key exists.
+ * On failure return -errno.
+ */
+ int coroutine_fn GRAPH_RDLOCK_PTR(*bdrv_co_pr_read_reservation)(
+ BlockDriverState *bs, uint32_t *generation,
+ uint64_t *key, BlockPrType *type);
+ /*
+ * Register, unregister, or replace a reservation key.
+ * @old_key: The current reservation key associated with the host.
+ * @new_key: The new reservation Key.
+ * @type: Type of the reservation key.
+ * @ignore_key: Ignore or not @old_key.
+ *
+ * Persist Through Power Loss(PTPL) is considered as required in QEMU
+ * block layer, the block driver need always enable PTPL.
+ */
+ int coroutine_fn GRAPH_RDLOCK_PTR(*bdrv_co_pr_register)(
+ BlockDriverState *bs, uint64_t old_key,
+ uint64_t new_key, BlockPrType type, bool ignore_key);
+ /*
+ * Acquire a reservation on a host.
+ * @key: The current reservation key associated with the host.
+ * @type: Type of the reservation key.
+ */
+ int coroutine_fn GRAPH_RDLOCK_PTR(*bdrv_co_pr_reserve)(
+ BlockDriverState *bs, uint64_t key, BlockPrType type);
+ /*
+ * Release a reservation on a host.
+ * @key: The current reservation key associated with the host.
+ * @type: Type of the reservation key.
+ */
+ int coroutine_fn GRAPH_RDLOCK_PTR(*bdrv_co_pr_release)(
+ BlockDriverState *bs, uint64_t key, BlockPrType type);
+ /**
+ * Clear reservations on a host.
+ * @key: The current reservation key associated with the host.
+ */
+ int coroutine_fn GRAPH_RDLOCK_PTR(*bdrv_co_pr_clear)(
+ BlockDriverState *bs, uint64_t key);
+ /*
+ * Preempt a reservation held on a host.
+ * @cr_key: The current reservation key associated with the host.
+ * @pr_key: The preempt reservation Key which to be
+ * unregistered from the namespace.
+ * @type: Type of the reservation key.
+ * @abort: Whether to abort a reservation held on a host.
+ */
+ int coroutine_fn GRAPH_RDLOCK_PTR(*bdrv_co_pr_preempt)(
+ BlockDriverState *bs, uint64_t cr_key,
+ uint64_t pr_key, BlockPrType type, bool abort);
+
/*
* Returns 0 for completed check, -errno for internal errors.
* The check results are stored in result.
@@ -899,6 +981,9 @@ typedef struct BlockLimits {
uint32_t max_active_zones;
uint32_t write_granularity;
+
+ /* Persistent reservation capacities. */
+ uint8_t pr_cap;
} BlockLimits;
typedef struct BdrvOpBlocker BdrvOpBlocker;
@@ -62,6 +62,28 @@ void blk_aio_cancel_async(BlockAIOCB *acb);
BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_pr_read_keys(BlockBackend *blk, uint32_t *generation,
+ uint32_t num_keys, uint64_t *keys,
+ BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_pr_read_reservation(BlockBackend *blk, uint32_t *generation,
+ uint64_t *key, BlockPrType *type,
+ BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_pr_register(BlockBackend *blk, uint64_t old_key,
+ uint64_t new_key, BlockPrType type,
+ bool ignore_key, BlockCompletionFunc *cb,
+ void *opaque);
+BlockAIOCB *blk_aio_pr_reserve(BlockBackend *blk, uint64_t key,
+ BlockPrType type, BlockCompletionFunc *cb,
+ void *opaque);
+BlockAIOCB *blk_aio_pr_release(BlockBackend *blk, uint64_t key,
+ BlockPrType type, BlockCompletionFunc *cb,
+ void *opaque);
+BlockAIOCB *blk_aio_pr_clear(BlockBackend *blk, uint64_t key,
+ BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_pr_preempt(BlockBackend *blk, uint64_t cr_key,
+ uint64_t pr_key, BlockPrType type, bool abort,
+ BlockCompletionFunc *cb, void *opaque);
+
void blk_inc_in_flight(BlockBackend *blk);
void blk_dec_in_flight(BlockBackend *blk);