#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
-static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb);
-
typedef struct BlockBackendAioNotifier {
void (*attached_aio_context)(AioContext *new_context, void *opaque);
void (*detach_aio_context)(void *opaque);
} BlockBackendAIOCB;
static const AIOCBInfo block_backend_aiocb_info = {
- .get_aio_context = blk_aiocb_get_aio_context,
.aiocb_size = sizeof(BlockBackendAIOCB),
};
static QTAILQ_HEAD(, BlockBackend) monitor_block_backends =
QTAILQ_HEAD_INITIALIZER(monitor_block_backends);
+static int coroutine_mixed_fn GRAPH_RDLOCK
+blk_set_perm_locked(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+ Error **errp);
+
static void blk_root_inherit_options(BdrvChildRole role, bool parent_is_format,
int *child_flags, QDict *child_options,
int parent_flags, QDict *parent_options)
*
* If an error is returned, the VM cannot be allowed to be resumed.
*/
-static void blk_root_activate(BdrvChild *child, Error **errp)
+static void GRAPH_RDLOCK blk_root_activate(BdrvChild *child, Error **errp)
{
BlockBackend *blk = child->opaque;
Error *local_err = NULL;
*/
saved_shared_perm = blk->shared_perm;
- blk_set_perm(blk, blk->perm, BLK_PERM_ALL, &local_err);
+ blk_set_perm_locked(blk, blk->perm, BLK_PERM_ALL, &local_err);
if (local_err) {
error_propagate(errp, local_err);
blk->disable_perm = true;
return;
}
- blk_set_perm(blk, blk->perm, blk->shared_perm, &local_err);
+ blk_set_perm_locked(blk, blk->perm, blk->shared_perm, &local_err);
if (local_err) {
error_propagate(errp, local_err);
blk->disable_perm = true;
return blk->force_allow_inactivate;
}
-static int blk_root_inactivate(BdrvChild *child)
+static int GRAPH_RDLOCK blk_root_inactivate(BdrvChild *child)
{
BlockBackend *blk = child->opaque;
/*
* Creates a new BlockBackend, opens a new BlockDriverState, and connects both.
- * The new BlockBackend is in the main AioContext.
+ * By default, the new BlockBackend is in the main AioContext, but if the
+ * parameters connect it with any existing node in a different AioContext, it
+ * may end up there instead.
*
* Just as with bdrv_open(), after having called this function the reference to
* @options belongs to the block layer (even on failure).
shared = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED;
}
- blk = blk_new(qemu_get_aio_context(), perm, shared);
bs = bdrv_open(filename, reference, options, flags, errp);
if (!bs) {
- blk_unref(blk);
return NULL;
}
- blk->root = bdrv_root_attach_child(bs, "root", &child_root,
- BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
- perm, shared, blk, errp);
+ /* bdrv_open() could have moved bs to a different AioContext */
+ blk = blk_new(bdrv_get_aio_context(bs), perm, shared);
+ blk->perm = perm;
+ blk->shared_perm = shared;
+
+ blk_insert_bs(blk, bs, errp);
+ bdrv_unref(bs);
+
if (!blk->root) {
blk_unref(blk);
return NULL;
GLOBAL_STATE_CODE();
while ((blk = blk_all_next(blk)) != NULL) {
- AioContext *ctx = blk_get_aio_context(blk);
-
- aio_context_acquire(ctx);
if (blk->root) {
blk_remove_bs(blk);
}
- aio_context_release(ctx);
}
}
return blk->root ? blk->root->bs : NULL;
}
-static BlockBackend *bdrv_first_blk(BlockDriverState *bs)
+static BlockBackend * GRAPH_RDLOCK bdrv_first_blk(BlockDriverState *bs)
{
BdrvChild *child;
GLOBAL_STATE_CODE();
+ assert_bdrv_graph_readable();
QLIST_FOREACH(child, &bs->parents, next_parent) {
if (child->klass == &child_root) {
BdrvChild *c;
GLOBAL_STATE_CODE();
+ assert_bdrv_graph_readable();
+
QLIST_FOREACH(c, &bs->parents, next_parent) {
if (c->klass != &child_root) {
return false;
blk_drain(blk);
root = blk->root;
blk->root = NULL;
+
+ bdrv_graph_wrlock();
bdrv_root_unref_child(root);
+ bdrv_graph_wrunlock();
}
/*
int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
{
ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
+
GLOBAL_STATE_CODE();
bdrv_ref(bs);
+ bdrv_graph_wrlock();
blk->root = bdrv_root_attach_child(bs, "root", &child_root,
BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
blk->perm, blk->shared_perm,
blk, errp);
+ bdrv_graph_wrunlock();
if (blk->root == NULL) {
return -EPERM;
}
/*
* Sets the permission bitmasks that the user of the BlockBackend needs.
*/
-int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
- Error **errp)
+static int coroutine_mixed_fn GRAPH_RDLOCK
+blk_set_perm_locked(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+ Error **errp)
{
int ret;
GLOBAL_STATE_CODE();
return 0;
}
+int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+ Error **errp)
+{
+ GLOBAL_STATE_CODE();
+ GRAPH_RDLOCK_GUARD_MAINLOOP();
+
+ return blk_set_perm_locked(blk, perm, shared_perm, errp);
+}
+
void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
{
GLOBAL_STATE_CODE();
return 0;
}
+/* Are we currently in a drained section? */
+bool blk_in_drain(BlockBackend *blk)
+{
+ GLOBAL_STATE_CODE(); /* change to IO_OR_GS_CODE(), if necessary */
+ return qatomic_read(&blk->quiesce_counter);
+}
+
/* To be called between exactly one pair of blk_inc/dec_in_flight() */
static void coroutine_fn blk_wait_while_drained(BlockBackend *blk)
{
/* throttling disk I/O */
if (blk->public.throttle_group_member.throttle_state) {
throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
- bytes, false);
+ bytes, THROTTLE_READ);
}
ret = bdrv_co_preadv_part(blk->root, offset, bytes, qiov, qiov_offset,
/* throttling disk I/O */
if (blk->public.throttle_group_member.throttle_state) {
throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
- bytes, true);
+ bytes, THROTTLE_WRITE);
}
if (!blk->enable_write_cache) {
acb->blk = blk;
acb->ret = ret;
- replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+ replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
error_callback_bh, acb);
return &acb->common;
}
bool has_returned;
} BlkAioEmAIOCB;
-static AioContext *blk_aio_em_aiocb_get_aio_context(BlockAIOCB *acb_)
-{
- BlkAioEmAIOCB *acb = container_of(acb_, BlkAioEmAIOCB, common);
-
- return blk_get_aio_context(acb->rwco.blk);
-}
-
static const AIOCBInfo blk_aio_em_aiocb_info = {
.aiocb_size = sizeof(BlkAioEmAIOCB),
- .get_aio_context = blk_aio_em_aiocb_get_aio_context,
};
static void blk_aio_complete(BlkAioEmAIOCB *acb)
acb->has_returned = false;
co = qemu_coroutine_create(co_entry, acb);
- aio_co_enter(blk_get_aio_context(blk), co);
+ aio_co_enter(qemu_get_current_aio_context(), co);
acb->has_returned = true;
if (acb->rwco.ret != NOT_DONE) {
- replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+ replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
blk_aio_complete_bh, acb);
}
return ret;
}
+static void coroutine_fn blk_aio_zone_report_entry(void *opaque)
+{
+ BlkAioEmAIOCB *acb = opaque;
+ BlkRwCo *rwco = &acb->rwco;
+
+ rwco->ret = blk_co_zone_report(rwco->blk, rwco->offset,
+ (unsigned int*)(uintptr_t)acb->bytes,
+ rwco->iobuf);
+ blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones,
+ BlockCompletionFunc *cb, void *opaque)
+{
+ BlkAioEmAIOCB *acb;
+ Coroutine *co;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
+ acb->rwco = (BlkRwCo) {
+ .blk = blk,
+ .offset = offset,
+ .iobuf = zones,
+ .ret = NOT_DONE,
+ };
+ acb->bytes = (int64_t)(uintptr_t)nr_zones,
+ acb->has_returned = false;
+
+ co = qemu_coroutine_create(blk_aio_zone_report_entry, acb);
+ aio_co_enter(qemu_get_current_aio_context(), co);
+
+ acb->has_returned = true;
+ if (acb->rwco.ret != NOT_DONE) {
+ replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+ blk_aio_complete_bh, acb);
+ }
+
+ return &acb->common;
+}
+
+static void coroutine_fn blk_aio_zone_mgmt_entry(void *opaque)
+{
+ BlkAioEmAIOCB *acb = opaque;
+ BlkRwCo *rwco = &acb->rwco;
+
+ rwco->ret = blk_co_zone_mgmt(rwco->blk,
+ (BlockZoneOp)(uintptr_t)rwco->iobuf,
+ rwco->offset, acb->bytes);
+ blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+ int64_t offset, int64_t len,
+ BlockCompletionFunc *cb, void *opaque) {
+ BlkAioEmAIOCB *acb;
+ Coroutine *co;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
+ acb->rwco = (BlkRwCo) {
+ .blk = blk,
+ .offset = offset,
+ .iobuf = (void *)(uintptr_t)op,
+ .ret = NOT_DONE,
+ };
+ acb->bytes = len;
+ acb->has_returned = false;
+
+ co = qemu_coroutine_create(blk_aio_zone_mgmt_entry, acb);
+ aio_co_enter(qemu_get_current_aio_context(), co);
+
+ acb->has_returned = true;
+ if (acb->rwco.ret != NOT_DONE) {
+ replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+ blk_aio_complete_bh, acb);
+ }
+
+ return &acb->common;
+}
+
+static void coroutine_fn blk_aio_zone_append_entry(void *opaque)
+{
+ BlkAioEmAIOCB *acb = opaque;
+ BlkRwCo *rwco = &acb->rwco;
+
+ rwco->ret = blk_co_zone_append(rwco->blk, (int64_t *)(uintptr_t)acb->bytes,
+ rwco->iobuf, rwco->flags);
+ blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_zone_append(BlockBackend *blk, int64_t *offset,
+ QEMUIOVector *qiov, BdrvRequestFlags flags,
+ BlockCompletionFunc *cb, void *opaque) {
+ BlkAioEmAIOCB *acb;
+ Coroutine *co;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
+ acb->rwco = (BlkRwCo) {
+ .blk = blk,
+ .ret = NOT_DONE,
+ .flags = flags,
+ .iobuf = qiov,
+ };
+ acb->bytes = (int64_t)(uintptr_t)offset;
+ acb->has_returned = false;
+
+ co = qemu_coroutine_create(blk_aio_zone_append_entry, acb);
+ aio_co_enter(qemu_get_current_aio_context(), co);
+ acb->has_returned = true;
+ if (acb->rwco.ret != NOT_DONE) {
+ replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+ blk_aio_complete_bh, acb);
+ }
+
+ return &acb->common;
+}
+
+/*
+ * Send a zone_report command.
+ * offset is a byte offset from the start of the device. No alignment
+ * required for offset.
+ * nr_zones represents IN maximum and OUT actual.
+ */
+int coroutine_fn blk_co_zone_report(BlockBackend *blk, int64_t offset,
+ unsigned int *nr_zones,
+ BlockZoneDescriptor *zones)
+{
+ int ret;
+ IO_CODE();
+
+ blk_inc_in_flight(blk); /* increase before waiting */
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+ if (!blk_is_available(blk)) {
+ blk_dec_in_flight(blk);
+ return -ENOMEDIUM;
+ }
+ ret = bdrv_co_zone_report(blk_bs(blk), offset, nr_zones, zones);
+ blk_dec_in_flight(blk);
+ return ret;
+}
+
+/*
+ * Send a zone_management command.
+ * op is the zone operation;
+ * offset is the byte offset from the start of the zoned device;
+ * len is the maximum number of bytes the command should operate on. It
+ * should be aligned with the device zone size.
+ */
+int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
+ int64_t offset, int64_t len)
+{
+ int ret;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+
+ ret = blk_check_byte_request(blk, offset, len);
+ if (ret < 0) {
+ blk_dec_in_flight(blk);
+ return ret;
+ }
+
+ ret = bdrv_co_zone_mgmt(blk_bs(blk), op, offset, len);
+ blk_dec_in_flight(blk);
+ return ret;
+}
+
+/*
+ * Send a zone_append command.
+ */
+int coroutine_fn blk_co_zone_append(BlockBackend *blk, int64_t *offset,
+ QEMUIOVector *qiov, BdrvRequestFlags flags)
+{
+ int ret;
+ IO_CODE();
+
+ blk_inc_in_flight(blk);
+ blk_wait_while_drained(blk);
+ GRAPH_RDLOCK_GUARD();
+ if (!blk_is_available(blk)) {
+ blk_dec_in_flight(blk);
+ return -ENOMEDIUM;
+ }
+
+ ret = bdrv_co_zone_append(blk_bs(blk), offset, qiov, flags);
+ blk_dec_in_flight(blk);
+ return ret;
+}
+
void blk_drain(BlockBackend *blk)
{
BlockDriverState *bs = blk_bs(blk);
return;
}
- bdrv_activate(bs, errp);
+ /*
+ * Migration code can call this function in coroutine context, so leave
+ * coroutine context if necessary.
+ */
+ if (qemu_in_coroutine()) {
+ bdrv_co_activate(bs, errp);
+ } else {
+ GRAPH_RDLOCK_GUARD_MAINLOOP();
+ bdrv_activate(bs, errp);
+ }
}
bool coroutine_fn blk_co_is_inserted(BlockBackend *blk)
{
BlockDriverState *bs = blk_bs(blk);
GLOBAL_STATE_CODE();
+ GRAPH_RDLOCK_GUARD_MAINLOOP();
if (!bs) {
return false;
AioContext *blk_get_aio_context(BlockBackend *blk)
{
- BlockDriverState *bs = blk_bs(blk);
+ BlockDriverState *bs;
IO_CODE();
+ if (!blk) {
+ return qemu_get_aio_context();
+ }
+
+ bs = blk_bs(blk);
if (bs) {
AioContext *ctx = bdrv_get_aio_context(blk_bs(blk));
assert(ctx == blk->ctx);
return blk->ctx;
}
-static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb)
-{
- BlockBackendAIOCB *blk_acb = DO_UPCAST(BlockBackendAIOCB, common, acb);
- return blk_get_aio_context(blk_acb->blk);
-}
-
-static int blk_do_set_aio_context(BlockBackend *blk, AioContext *new_context,
- bool update_root_node, Error **errp)
+int blk_set_aio_context(BlockBackend *blk, AioContext *new_context,
+ Error **errp)
{
+ bool old_allow_change;
BlockDriverState *bs = blk_bs(blk);
- ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
int ret;
- if (bs) {
- bdrv_ref(bs);
-
- if (update_root_node) {
- /*
- * update_root_node MUST be false for blk_root_set_aio_ctx_commit(),
- * as we are already in the commit function of a transaction.
- */
- ret = bdrv_try_change_aio_context(bs, new_context, blk->root, errp);
- if (ret < 0) {
- bdrv_unref(bs);
- return ret;
- }
- }
- /*
- * Make blk->ctx consistent with the root node before we invoke any
- * other operations like drain that might inquire blk->ctx
- */
- blk->ctx = new_context;
- if (tgm->throttle_state) {
- bdrv_drained_begin(bs);
- throttle_group_detach_aio_context(tgm);
- throttle_group_attach_aio_context(tgm, new_context);
- bdrv_drained_end(bs);
- }
+ GLOBAL_STATE_CODE();
- bdrv_unref(bs);
- } else {
+ if (!bs) {
blk->ctx = new_context;
+ return 0;
}
- return 0;
-}
+ bdrv_ref(bs);
-int blk_set_aio_context(BlockBackend *blk, AioContext *new_context,
- Error **errp)
-{
- GLOBAL_STATE_CODE();
- return blk_do_set_aio_context(blk, new_context, true, errp);
+ old_allow_change = blk->allow_aio_context_change;
+ blk->allow_aio_context_change = true;
+
+ ret = bdrv_try_change_aio_context(bs, new_context, NULL, errp);
+
+ blk->allow_aio_context_change = old_allow_change;
+
+ bdrv_unref(bs);
+ return ret;
}
typedef struct BdrvStateBlkRootContext {
{
BdrvStateBlkRootContext *s = opaque;
BlockBackend *blk = s->blk;
+ AioContext *new_context = s->new_ctx;
+ ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
- blk_do_set_aio_context(blk, s->new_ctx, false, &error_abort);
+ blk->ctx = new_context;
+ if (tgm->throttle_state) {
+ throttle_group_detach_aio_context(tgm);
+ throttle_group_attach_aio_context(tgm, new_context);
+ }
}
static TransactionActionDrv set_blk_root_context = {
notifier_list_add(&blk->insert_bs_notifiers, notify);
}
-void coroutine_fn blk_co_io_plug(BlockBackend *blk)
-{
- BlockDriverState *bs = blk_bs(blk);
- IO_CODE();
- GRAPH_RDLOCK_GUARD();
-
- if (bs) {
- bdrv_co_io_plug(bs);
- }
-}
-
-void coroutine_fn blk_co_io_unplug(BlockBackend *blk)
-{
- BlockDriverState *bs = blk_bs(blk);
- IO_CODE();
- GRAPH_RDLOCK_GUARD();
-
- if (bs) {
- bdrv_co_io_unplug(bs);
- }
-}
-
BlockAcctStats *blk_get_stats(BlockBackend *blk)
{
IO_CODE();
int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz)
{
GLOBAL_STATE_CODE();
+ GRAPH_RDLOCK_GUARD_MAINLOOP();
+
if (!blk_is_available(blk)) {
return -ENOMEDIUM;
}
{
BlockBackend *blk = NULL;
GLOBAL_STATE_CODE();
+ GRAPH_RDLOCK_GUARD_MAINLOOP();
while ((blk = blk_all_next(blk)) != NULL) {
- AioContext *aio_context = blk_get_aio_context(blk);
BlockDriverState *unfiltered_bs = bdrv_skip_filters(blk_bs(blk));
- aio_context_acquire(aio_context);
if (blk_is_inserted(blk) && bdrv_cow_child(unfiltered_bs)) {
int ret;
ret = bdrv_commit(unfiltered_bs);
if (ret < 0) {
- aio_context_release(aio_context);
return ret;
}
}
- aio_context_release(aio_context);
}
return 0;
}
int blk_make_empty(BlockBackend *blk, Error **errp)
{
GLOBAL_STATE_CODE();
+ GRAPH_RDLOCK_GUARD_MAINLOOP();
+
if (!blk_is_available(blk)) {
error_setg(errp, "No medium inserted");
return -ENOMEDIUM;
projects / mirror_qemu.git / blobdiff