Merge tag 'for-upstream' of https://repo.or.cz/qemu/kevin into staging
Block layer patches
- virtio-blk: Multiqueue support (configurable iothread per queue)
- Made NBD export and hw/scsi thread-safe without AioContext lock
- Fix crash when loading snapshot on inactive node
# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAmWEw/8RHGt3b2xmQHJl
# ZGhhdC5jb20ACgkQfwmycsiPL9bX0Q/9G+Qx8mQGmbxJzvtW7/1eaeJ5CPCYT8w3
# 033S5hCil43mvX2aQKTFrh1Nz4aYlqMDyURvNu7nigyADY+kBpzzJ1MFr6WQrzYv
# QEk4jf/FOllfKn8+/A0z2NJDhtpVgqKKHBsFZl8FBUcxd79daTaoPPM3BNNsOHQD
# o7Z7hR/iEdG9dkAh/fpwctsgMO/CoN0BRRyN2OByj03zeu1TlDJ6lX0hxlcJl9Jw
# vLo81rWTCqKRu+SbjBsb0HfYE2hP54A4hvxn4I9vYGYDz8ElucluYyeqUEK+mdrX
# /DQBdb+Osl1FD6MuIaFR+Rgp9Mu5h6ZOdvUyCY0zuByti851hV8qjW9BtrTfqaMh
# LMOKoL6c5B8XJYWVGAGrJexIw1hHq5WKdXN9zp4FZA4tOyHUMRjHuR1+zScU6gnU
# WRSIQR46w75A13clWyJs9Hf/q5Fp/1KT4nfuZ/hmiXvxdsYY5x1w/W3s9tRNjYKL
# d6FVk17cFc6Ksb7lWvDCgg61BNZtGm4Clmw0kJ6V1reiQz7AvDLmduLUQbmrVt7G
# gWAY4b2L9YXJpEx5en0kE50KLAUw/E9ozbOq6ZT9nFUKeNAPC8PS5lK7vYVwebCk
# VA0t8pFzKhdB1bJaG5fMSRPBuqkvhsaDEEDABlSro8dyyjoQBaEdk5P9Kxe66hBc
# xhTmDPdv/JM=
# =E3Zh
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 21 Dec 2023 18:02:23 EST
# gpg: using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg: issuer "kwolf@redhat.com"
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74 56FE 7F09 B272 C88F 2FD6
* tag 'for-upstream' of https://repo.or.cz/qemu/kevin: (33 commits)
virtio-blk: add iothread-vq-mapping parameter
qdev: add IOThreadVirtQueueMappingList property type
qdev-properties: alias all object class properties
string-output-visitor: show structs as "<omitted>"
block-coroutine-wrapper: use qemu_get_current_aio_context()
block: remove outdated AioContext locking comments
job: remove outdated AioContext locking comments
scsi: remove outdated AioContext lock comment
docs: remove AioContext lock from IOThread docs
aio: remove aio_context_acquire()/aio_context_release() API
aio-wait: draw equivalence between AIO_WAIT_WHILE() and AIO_WAIT_WHILE_UNLOCKED()
scsi: remove AioContext locking
block: remove bdrv_co_lock()
block: remove AioContext locking
graph-lock: remove AioContext locking
aio: make aio_context_acquire()/aio_context_release() a no-op
tests: remove aio_context_acquire() tests
scsi: assert that callbacks run in the correct AioContext
virtio-scsi: replace AioContext lock with tmf_bh_lock
dma-helpers: don't lock AioContext in dma_blk_cb()
...
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
diff --git a/block.c b/block.c
index bfb0861..a097772 100644
--- a/block.c
+++ b/block.c
@@ -1616,16 +1616,10 @@
g_free(gen_node_name);
}
-/*
- * The caller must always hold @bs AioContext lock, because this function calls
- * bdrv_refresh_total_sectors() which polls when called from non-coroutine
- * context.
- */
static int no_coroutine_fn GRAPH_UNLOCKED
bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv, const char *node_name,
QDict *options, int open_flags, Error **errp)
{
- AioContext *ctx;
Error *local_err = NULL;
int i, ret;
GLOBAL_STATE_CODE();
@@ -1673,21 +1667,15 @@
bs->supported_read_flags |= BDRV_REQ_REGISTERED_BUF;
bs->supported_write_flags |= BDRV_REQ_REGISTERED_BUF;
- /* Get the context after .bdrv_open, it can change the context */
- ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
-
ret = bdrv_refresh_total_sectors(bs, bs->total_sectors);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not refresh total sector count");
- aio_context_release(ctx);
return ret;
}
bdrv_graph_rdlock_main_loop();
bdrv_refresh_limits(bs, NULL, &local_err);
bdrv_graph_rdunlock_main_loop();
- aio_context_release(ctx);
if (local_err) {
error_propagate(errp, local_err);
@@ -1708,12 +1696,12 @@
open_failed:
bs->drv = NULL;
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
if (bs->file != NULL) {
bdrv_unref_child(bs, bs->file);
assert(!bs->file);
}
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
g_free(bs->opaque);
bs->opaque = NULL;
@@ -2908,7 +2896,7 @@
* Replaces the node that a BdrvChild points to without updating permissions.
*
* If @new_bs is non-NULL, the parent of @child must already be drained through
- * @child and the caller must hold the AioContext lock for @new_bs.
+ * @child.
*/
static void GRAPH_WRLOCK
bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs)
@@ -3048,9 +3036,8 @@
*
* Returns new created child.
*
- * The caller must hold the AioContext lock for @child_bs. Both @parent_bs and
- * @child_bs can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * Both @parent_bs and @child_bs can move to a different AioContext in this
+ * function.
*/
static BdrvChild * GRAPH_WRLOCK
bdrv_attach_child_common(BlockDriverState *child_bs,
@@ -3062,7 +3049,7 @@
Transaction *tran, Error **errp)
{
BdrvChild *new_child;
- AioContext *parent_ctx, *new_child_ctx;
+ AioContext *parent_ctx;
AioContext *child_ctx = bdrv_get_aio_context(child_bs);
assert(child_class->get_parent_desc);
@@ -3114,12 +3101,6 @@
}
}
- new_child_ctx = bdrv_get_aio_context(child_bs);
- if (new_child_ctx != child_ctx) {
- aio_context_release(child_ctx);
- aio_context_acquire(new_child_ctx);
- }
-
bdrv_ref(child_bs);
/*
* Let every new BdrvChild start with a drained parent. Inserting the child
@@ -3149,20 +3130,14 @@
};
tran_add(tran, &bdrv_attach_child_common_drv, s);
- if (new_child_ctx != child_ctx) {
- aio_context_release(new_child_ctx);
- aio_context_acquire(child_ctx);
- }
-
return new_child;
}
/*
* Function doesn't update permissions, caller is responsible for this.
*
- * The caller must hold the AioContext lock for @child_bs. Both @parent_bs and
- * @child_bs can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * Both @parent_bs and @child_bs can move to a different AioContext in this
+ * function.
*
* After calling this function, the transaction @tran may only be completed
* while holding a writer lock for the graph.
@@ -3202,9 +3177,6 @@
*
* On failure NULL is returned, errp is set and the reference to
* child_bs is also dropped.
- *
- * The caller must hold the AioContext lock @child_bs, but not that of @ctx
- * (unless @child_bs is already in @ctx).
*/
BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
const char *child_name,
@@ -3244,9 +3216,6 @@
*
* On failure NULL is returned, errp is set and the reference to
* child_bs is also dropped.
- *
- * If @parent_bs and @child_bs are in different AioContexts, the caller must
- * hold the AioContext lock for @child_bs, but not for @parent_bs.
*/
BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
BlockDriverState *child_bs,
@@ -3436,9 +3405,8 @@
*
* Function doesn't update permissions, caller is responsible for this.
*
- * The caller must hold the AioContext lock for @child_bs. Both @parent_bs and
- * @child_bs can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * Both @parent_bs and @child_bs can move to a different AioContext in this
+ * function.
*
* After calling this function, the transaction @tran may only be completed
* while holding a writer lock for the graph.
@@ -3531,9 +3499,8 @@
}
/*
- * The caller must hold the AioContext lock for @backing_hd. Both @bs and
- * @backing_hd can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * Both @bs and @backing_hd can move to a different AioContext in this
+ * function.
*
* If a backing child is already present (i.e. we're detaching a node), that
* child node must be drained.
@@ -3575,9 +3542,9 @@
bdrv_ref(drain_bs);
bdrv_drained_begin(drain_bs);
- bdrv_graph_wrlock(backing_hd);
+ bdrv_graph_wrlock();
ret = bdrv_set_backing_hd_drained(bs, backing_hd, errp);
- bdrv_graph_wrunlock(backing_hd);
+ bdrv_graph_wrunlock();
bdrv_drained_end(drain_bs);
bdrv_unref(drain_bs);
@@ -3592,8 +3559,6 @@
* itself, all options starting with "${bdref_key}." are considered part of the
* BlockdevRef.
*
- * The caller must hold the main AioContext lock.
- *
* TODO Can this be unified with bdrv_open_image()?
*/
int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
@@ -3605,7 +3570,6 @@
int ret = 0;
bool implicit_backing = false;
BlockDriverState *backing_hd;
- AioContext *backing_hd_ctx;
QDict *options;
QDict *tmp_parent_options = NULL;
Error *local_err = NULL;
@@ -3691,11 +3655,8 @@
/* Hook up the backing file link; drop our reference, bs owns the
* backing_hd reference now */
- backing_hd_ctx = bdrv_get_aio_context(backing_hd);
- aio_context_acquire(backing_hd_ctx);
ret = bdrv_set_backing_hd(bs, backing_hd, errp);
bdrv_unref(backing_hd);
- aio_context_release(backing_hd_ctx);
if (ret < 0) {
goto free_exit;
@@ -3767,9 +3728,7 @@
*
* The BlockdevRef will be removed from the options QDict.
*
- * The caller must hold the lock of the main AioContext and no other AioContext.
- * @parent can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * @parent can move to a different AioContext in this function.
*/
BdrvChild *bdrv_open_child(const char *filename,
QDict *options, const char *bdref_key,
@@ -3780,7 +3739,6 @@
{
BlockDriverState *bs;
BdrvChild *child;
- AioContext *ctx;
GLOBAL_STATE_CODE();
@@ -3790,13 +3748,10 @@
return NULL;
}
- bdrv_graph_wrlock(NULL);
- ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
+ bdrv_graph_wrlock();
child = bdrv_attach_child(parent, bs, bdref_key, child_class, child_role,
errp);
- aio_context_release(ctx);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
return child;
}
@@ -3804,9 +3759,7 @@
/*
* Wrapper on bdrv_open_child() for most popular case: open primary child of bs.
*
- * The caller must hold the lock of the main AioContext and no other AioContext.
- * @parent can move to a different AioContext in this function. Callers must
- * make sure that their AioContext locking is still correct after this.
+ * @parent can move to a different AioContext in this function.
*/
int bdrv_open_file_child(const char *filename,
QDict *options, const char *bdref_key,
@@ -3881,7 +3834,6 @@
int64_t total_size;
QemuOpts *opts = NULL;
BlockDriverState *bs_snapshot = NULL;
- AioContext *ctx = bdrv_get_aio_context(bs);
int ret;
GLOBAL_STATE_CODE();
@@ -3890,9 +3842,7 @@
instead of opening 'filename' directly */
/* Get the required size from the image */
- aio_context_acquire(ctx);
total_size = bdrv_getlength(bs);
- aio_context_release(ctx);
if (total_size < 0) {
error_setg_errno(errp, -total_size, "Could not get image size");
@@ -3927,10 +3877,7 @@
goto out;
}
- aio_context_acquire(ctx);
ret = bdrv_append(bs_snapshot, bs, errp);
- aio_context_release(ctx);
-
if (ret < 0) {
bs_snapshot = NULL;
goto out;
@@ -3955,8 +3902,6 @@
* The reference parameter may be used to specify an existing block device which
* should be opened. If specified, neither options nor a filename may be given,
* nor can an existing BDS be reused (that is, *pbs has to be NULL).
- *
- * The caller must always hold the main AioContext lock.
*/
static BlockDriverState * no_coroutine_fn
bdrv_open_inherit(const char *filename, const char *reference, QDict *options,
@@ -3974,7 +3919,6 @@
Error *local_err = NULL;
QDict *snapshot_options = NULL;
int snapshot_flags = 0;
- AioContext *ctx = qemu_get_aio_context();
assert(!child_class || !flags);
assert(!child_class == !parent);
@@ -4115,12 +4059,10 @@
/* Not requesting BLK_PERM_CONSISTENT_READ because we're only
* looking at the header to guess the image format. This works even
* in cases where a guest would not see a consistent state. */
- ctx = bdrv_get_aio_context(file_bs);
- aio_context_acquire(ctx);
+ AioContext *ctx = bdrv_get_aio_context(file_bs);
file = blk_new(ctx, 0, BLK_PERM_ALL);
blk_insert_bs(file, file_bs, &local_err);
bdrv_unref(file_bs);
- aio_context_release(ctx);
if (local_err) {
goto fail;
@@ -4167,13 +4109,8 @@
goto fail;
}
- /* The AioContext could have changed during bdrv_open_common() */
- ctx = bdrv_get_aio_context(bs);
-
if (file) {
- aio_context_acquire(ctx);
blk_unref(file);
- aio_context_release(ctx);
file = NULL;
}
@@ -4231,16 +4168,13 @@
* (snapshot_bs); thus, we have to drop the strong reference to bs
* (which we obtained by calling bdrv_new()). bs will not be deleted,
* though, because the overlay still has a reference to it. */
- aio_context_acquire(ctx);
bdrv_unref(bs);
- aio_context_release(ctx);
bs = snapshot_bs;
}
return bs;
fail:
- aio_context_acquire(ctx);
blk_unref(file);
qobject_unref(snapshot_options);
qobject_unref(bs->explicit_options);
@@ -4249,21 +4183,17 @@
bs->options = NULL;
bs->explicit_options = NULL;
bdrv_unref(bs);
- aio_context_release(ctx);
error_propagate(errp, local_err);
return NULL;
close_and_fail:
- aio_context_acquire(ctx);
bdrv_unref(bs);
- aio_context_release(ctx);
qobject_unref(snapshot_options);
qobject_unref(options);
error_propagate(errp, local_err);
return NULL;
}
-/* The caller must always hold the main AioContext lock. */
BlockDriverState *bdrv_open(const char *filename, const char *reference,
QDict *options, int flags, Error **errp)
{
@@ -4540,12 +4470,7 @@
if (bs_queue) {
BlockReopenQueueEntry *bs_entry, *next;
QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
- AioContext *ctx = bdrv_get_aio_context(bs_entry->state.bs);
-
- aio_context_acquire(ctx);
bdrv_drained_end(bs_entry->state.bs);
- aio_context_release(ctx);
-
qobject_unref(bs_entry->state.explicit_options);
qobject_unref(bs_entry->state.options);
g_free(bs_entry);
@@ -4577,7 +4502,6 @@
{
int ret = -1;
BlockReopenQueueEntry *bs_entry, *next;
- AioContext *ctx;
Transaction *tran = tran_new();
g_autoptr(GSList) refresh_list = NULL;
@@ -4586,10 +4510,7 @@
GLOBAL_STATE_CODE();
QTAILQ_FOREACH(bs_entry, bs_queue, entry) {
- ctx = bdrv_get_aio_context(bs_entry->state.bs);
- aio_context_acquire(ctx);
ret = bdrv_flush(bs_entry->state.bs);
- aio_context_release(ctx);
if (ret < 0) {
error_setg_errno(errp, -ret, "Error flushing drive");
goto abort;
@@ -4598,10 +4519,7 @@
QTAILQ_FOREACH(bs_entry, bs_queue, entry) {
assert(bs_entry->state.bs->quiesce_counter > 0);
- ctx = bdrv_get_aio_context(bs_entry->state.bs);
- aio_context_acquire(ctx);
ret = bdrv_reopen_prepare(&bs_entry->state, bs_queue, tran, errp);
- aio_context_release(ctx);
if (ret < 0) {
goto abort;
}
@@ -4644,24 +4562,18 @@
* to first element.
*/
QTAILQ_FOREACH_REVERSE(bs_entry, bs_queue, entry) {
- ctx = bdrv_get_aio_context(bs_entry->state.bs);
- aio_context_acquire(ctx);
bdrv_reopen_commit(&bs_entry->state);
- aio_context_release(ctx);
}
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
tran_commit(tran);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
QTAILQ_FOREACH_REVERSE(bs_entry, bs_queue, entry) {
BlockDriverState *bs = bs_entry->state.bs;
if (bs->drv->bdrv_reopen_commit_post) {
- ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
bs->drv->bdrv_reopen_commit_post(&bs_entry->state);
- aio_context_release(ctx);
}
}
@@ -4669,16 +4581,13 @@
goto cleanup;
abort:
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
tran_abort(tran);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
if (bs_entry->prepared) {
- ctx = bdrv_get_aio_context(bs_entry->state.bs);
- aio_context_acquire(ctx);
bdrv_reopen_abort(&bs_entry->state);
- aio_context_release(ctx);
}
}
@@ -4691,24 +4600,13 @@
int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
Error **errp)
{
- AioContext *ctx = bdrv_get_aio_context(bs);
BlockReopenQueue *queue;
- int ret;
GLOBAL_STATE_CODE();
queue = bdrv_reopen_queue(NULL, bs, opts, keep_old_opts);
- if (ctx != qemu_get_aio_context()) {
- aio_context_release(ctx);
- }
- ret = bdrv_reopen_multiple(queue, errp);
-
- if (ctx != qemu_get_aio_context()) {
- aio_context_acquire(ctx);
- }
-
- return ret;
+ return bdrv_reopen_multiple(queue, errp);
}
int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only,
@@ -4743,10 +4641,7 @@
*
* Return 0 on success, otherwise return < 0 and set @errp.
*
- * The caller must hold the AioContext lock of @reopen_state->bs.
* @reopen_state->bs can move to a different AioContext in this function.
- * Callers must make sure that their AioContext locking is still correct after
- * this.
*/
static int GRAPH_UNLOCKED
bdrv_reopen_parse_file_or_backing(BDRVReopenState *reopen_state,
@@ -4760,7 +4655,6 @@
const char *child_name = is_backing ? "backing" : "file";
QObject *value;
const char *str;
- AioContext *ctx, *old_ctx;
bool has_child;
int ret;
@@ -4844,25 +4738,13 @@
bdrv_drained_begin(old_child_bs);
}
- old_ctx = bdrv_get_aio_context(bs);
- ctx = bdrv_get_aio_context(new_child_bs);
- if (old_ctx != ctx) {
- aio_context_release(old_ctx);
- aio_context_acquire(ctx);
- }
-
bdrv_graph_rdunlock_main_loop();
- bdrv_graph_wrlock(new_child_bs);
+ bdrv_graph_wrlock();
ret = bdrv_set_file_or_backing_noperm(bs, new_child_bs, is_backing,
tran, errp);
- bdrv_graph_wrunlock_ctx(ctx);
-
- if (old_ctx != ctx) {
- aio_context_release(ctx);
- aio_context_acquire(old_ctx);
- }
+ bdrv_graph_wrunlock();
if (old_child_bs) {
bdrv_drained_end(old_child_bs);
@@ -4892,8 +4774,6 @@
* It is the responsibility of the caller to then call the abort() or
* commit() for any other BDS that have been left in a prepare() state
*
- * The caller must hold the AioContext lock of @reopen_state->bs.
- *
* After calling this function, the transaction @change_child_tran may only be
* completed while holding a writer lock for the graph.
*/
@@ -5209,14 +5089,14 @@
bs->drv = NULL;
}
- bdrv_graph_wrlock(bs);
+ bdrv_graph_wrlock();
QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
bdrv_unref_child(bs, child);
}
assert(!bs->backing);
assert(!bs->file);
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
g_free(bs->opaque);
bs->opaque = NULL;
@@ -5509,9 +5389,9 @@
bdrv_graph_rdunlock_main_loop();
bdrv_drained_begin(child_bs);
- bdrv_graph_wrlock(bs);
+ bdrv_graph_wrlock();
ret = bdrv_replace_node_common(bs, child_bs, true, true, errp);
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
bdrv_drained_end(child_bs);
return ret;
@@ -5528,8 +5408,6 @@
* child.
*
* This function does not create any image files.
- *
- * The caller must hold the AioContext lock for @bs_top.
*/
int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
Error **errp)
@@ -5537,7 +5415,6 @@
int ret;
BdrvChild *child;
Transaction *tran = tran_new();
- AioContext *old_context, *new_context = NULL;
GLOBAL_STATE_CODE();
@@ -5545,23 +5422,10 @@
assert(!bs_new->backing);
bdrv_graph_rdunlock_main_loop();
- old_context = bdrv_get_aio_context(bs_top);
bdrv_drained_begin(bs_top);
-
- /*
- * bdrv_drained_begin() requires that only the AioContext of the drained
- * node is locked, and at this point it can still differ from the AioContext
- * of bs_top.
- */
- new_context = bdrv_get_aio_context(bs_new);
- aio_context_release(old_context);
- aio_context_acquire(new_context);
bdrv_drained_begin(bs_new);
- aio_context_release(new_context);
- aio_context_acquire(old_context);
- new_context = NULL;
- bdrv_graph_wrlock(bs_top);
+ bdrv_graph_wrlock();
child = bdrv_attach_child_noperm(bs_new, bs_top, "backing",
&child_of_bds, bdrv_backing_role(bs_new),
@@ -5571,18 +5435,6 @@
goto out;
}
- /*
- * bdrv_attach_child_noperm could change the AioContext of bs_top and
- * bs_new, but at least they are in the same AioContext now. This is the
- * AioContext that we need to lock for the rest of the function.
- */
- new_context = bdrv_get_aio_context(bs_top);
-
- if (old_context != new_context) {
- aio_context_release(old_context);
- aio_context_acquire(new_context);
- }
-
ret = bdrv_replace_node_noperm(bs_top, bs_new, true, tran, errp);
if (ret < 0) {
goto out;
@@ -5593,16 +5445,11 @@
tran_finalize(tran, ret);
bdrv_refresh_limits(bs_top, NULL, NULL);
- bdrv_graph_wrunlock(bs_top);
+ bdrv_graph_wrunlock();
bdrv_drained_end(bs_top);
bdrv_drained_end(bs_new);
- if (new_context && old_context != new_context) {
- aio_context_release(new_context);
- aio_context_acquire(old_context);
- }
-
return ret;
}
@@ -5620,7 +5467,7 @@
bdrv_ref(old_bs);
bdrv_drained_begin(old_bs);
bdrv_drained_begin(new_bs);
- bdrv_graph_wrlock(new_bs);
+ bdrv_graph_wrlock();
bdrv_replace_child_tran(child, new_bs, tran);
@@ -5631,7 +5478,7 @@
tran_finalize(tran, ret);
- bdrv_graph_wrunlock(new_bs);
+ bdrv_graph_wrunlock();
bdrv_drained_end(old_bs);
bdrv_drained_end(new_bs);
bdrv_unref(old_bs);
@@ -5667,9 +5514,8 @@
* after the call (even on failure), so if the caller intends to reuse the
* dictionary, it needs to use qobject_ref() before calling bdrv_open.
*
- * The caller holds the AioContext lock for @bs. It must make sure that @bs
- * stays in the same AioContext, i.e. @options must not refer to nodes in a
- * different AioContext.
+ * The caller must make sure that @bs stays in the same AioContext, i.e.
+ * @options must not refer to nodes in a different AioContext.
*/
BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *options,
int flags, Error **errp)
@@ -5697,12 +5543,8 @@
GLOBAL_STATE_CODE();
- aio_context_release(ctx);
- aio_context_acquire(qemu_get_aio_context());
new_node_bs = bdrv_new_open_driver_opts(drv, node_name, options, flags,
errp);
- aio_context_release(qemu_get_aio_context());
- aio_context_acquire(ctx);
assert(bdrv_get_aio_context(bs) == ctx);
options = NULL; /* bdrv_new_open_driver() eats options */
@@ -5718,9 +5560,9 @@
bdrv_ref(bs);
bdrv_drained_begin(bs);
bdrv_drained_begin(new_node_bs);
- bdrv_graph_wrlock(new_node_bs);
+ bdrv_graph_wrlock();
ret = bdrv_replace_node(bs, new_node_bs, errp);
- bdrv_graph_wrunlock(new_node_bs);
+ bdrv_graph_wrunlock();
bdrv_drained_end(new_node_bs);
bdrv_drained_end(bs);
bdrv_unref(bs);
@@ -5975,7 +5817,7 @@
bdrv_ref(top);
bdrv_drained_begin(base);
- bdrv_graph_wrlock(base);
+ bdrv_graph_wrlock();
if (!top->drv || !base->drv) {
goto exit_wrlock;
@@ -6015,7 +5857,7 @@
* That's a FIXME.
*/
bdrv_replace_node_common(top, base, false, false, &local_err);
- bdrv_graph_wrunlock(base);
+ bdrv_graph_wrunlock();
if (local_err) {
error_report_err(local_err);
@@ -6052,7 +5894,7 @@
goto exit;
exit_wrlock:
- bdrv_graph_wrunlock(base);
+ bdrv_graph_wrunlock();
exit:
bdrv_drained_end(base);
bdrv_unref(top);
@@ -7037,12 +6879,9 @@
GRAPH_RDLOCK_GUARD_MAINLOOP();
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
int ret;
- aio_context_acquire(aio_context);
ret = bdrv_activate(bs, errp);
- aio_context_release(aio_context);
if (ret < 0) {
bdrv_next_cleanup(&it);
return;
@@ -7137,21 +6976,11 @@
BlockDriverState *bs = NULL;
BdrvNextIterator it;
int ret = 0;
- GSList *aio_ctxs = NULL, *ctx;
GLOBAL_STATE_CODE();
GRAPH_RDLOCK_GUARD_MAINLOOP();
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
-
- if (!g_slist_find(aio_ctxs, aio_context)) {
- aio_ctxs = g_slist_prepend(aio_ctxs, aio_context);
- aio_context_acquire(aio_context);
- }
- }
-
- for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
/* Nodes with BDS parents are covered by recursion from the last
* parent that gets inactivated. Don't inactivate them a second
* time if that has already happened. */
@@ -7161,17 +6990,10 @@
ret = bdrv_inactivate_recurse(bs);
if (ret < 0) {
bdrv_next_cleanup(&it);
- goto out;
+ break;
}
}
-out:
- for (ctx = aio_ctxs; ctx != NULL; ctx = ctx->next) {
- AioContext *aio_context = ctx->data;
- aio_context_release(aio_context);
- }
- g_slist_free(aio_ctxs);
-
return ret;
}
@@ -7257,11 +7079,8 @@
static void bdrv_schedule_unref_bh(void *opaque)
{
BlockDriverState *bs = opaque;
- AioContext *ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
bdrv_unref(bs);
- aio_context_release(ctx);
}
/*
@@ -7398,8 +7217,6 @@
return;
}
- aio_context_acquire(qemu_get_aio_context());
-
/* Create parameter list */
create_opts = qemu_opts_append(create_opts, drv->create_opts);
create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);
@@ -7549,7 +7366,6 @@
qemu_opts_del(opts);
qemu_opts_free(create_opts);
error_propagate(errp, local_err);
- aio_context_release(qemu_get_aio_context());
}
AioContext *bdrv_get_aio_context(BlockDriverState *bs)
@@ -7583,33 +7399,6 @@
bdrv_dec_in_flight(bs);
}
-void coroutine_fn bdrv_co_lock(BlockDriverState *bs)
-{
- AioContext *ctx = bdrv_get_aio_context(bs);
-
- /* In the main thread, bs->aio_context won't change concurrently */
- assert(qemu_get_current_aio_context() == qemu_get_aio_context());
-
- /*
- * We're in coroutine context, so we already hold the lock of the main
- * loop AioContext. Don't lock it twice to avoid deadlocks.
- */
- assert(qemu_in_coroutine());
- if (ctx != qemu_get_aio_context()) {
- aio_context_acquire(ctx);
- }
-}
-
-void coroutine_fn bdrv_co_unlock(BlockDriverState *bs)
-{
- AioContext *ctx = bdrv_get_aio_context(bs);
-
- assert(qemu_in_coroutine());
- if (ctx != qemu_get_aio_context()) {
- aio_context_release(ctx);
- }
-}
-
static void bdrv_do_remove_aio_context_notifier(BdrvAioNotifier *ban)
{
GLOBAL_STATE_CODE();
@@ -7728,21 +7517,8 @@
BdrvStateSetAioContext *state = (BdrvStateSetAioContext *) opaque;
BlockDriverState *bs = (BlockDriverState *) state->bs;
AioContext *new_context = state->new_ctx;
- AioContext *old_context = bdrv_get_aio_context(bs);
- /*
- * Take the old AioContex when detaching it from bs.
- * At this point, new_context lock is already acquired, and we are now
- * also taking old_context. This is safe as long as bdrv_detach_aio_context
- * does not call AIO_POLL_WHILE().
- */
- if (old_context != qemu_get_aio_context()) {
- aio_context_acquire(old_context);
- }
bdrv_detach_aio_context(bs);
- if (old_context != qemu_get_aio_context()) {
- aio_context_release(old_context);
- }
bdrv_attach_aio_context(bs, new_context);
}
@@ -7757,10 +7533,6 @@
*
* Must be called from the main AioContext.
*
- * The caller must own the AioContext lock for the old AioContext of bs, but it
- * must not own the AioContext lock for new_context (unless new_context is the
- * same as the current context of bs).
- *
* @visited will accumulate all visited BdrvChild objects. The caller is
* responsible for freeing the list afterwards.
*/
@@ -7813,13 +7585,6 @@
*
* If ignore_child is not NULL, that child (and its subgraph) will not
* be touched.
- *
- * This function still requires the caller to take the bs current
- * AioContext lock, otherwise draining will fail since AIO_WAIT_WHILE
- * assumes the lock is always held if bs is in another AioContext.
- * For the same reason, it temporarily also holds the new AioContext, since
- * bdrv_drained_end calls BDRV_POLL_WHILE that assumes the lock is taken too.
- * Therefore the new AioContext lock must not be taken by the caller.
*/
int bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx,
BdrvChild *ignore_child, Error **errp)
@@ -7827,7 +7592,6 @@
Transaction *tran;
GHashTable *visited;
int ret;
- AioContext *old_context = bdrv_get_aio_context(bs);
GLOBAL_STATE_CODE();
/*
@@ -7846,8 +7610,8 @@
/*
* Linear phase: go through all callbacks collected in the transaction.
- * Run all callbacks collected in the recursion to switch all nodes
- * AioContext lock (transaction commit), or undo all changes done in the
+ * Run all callbacks collected in the recursion to switch every node's
+ * AioContext (transaction commit), or undo all changes done in the
* recursion (transaction abort).
*/
@@ -7857,34 +7621,7 @@
return -EPERM;
}
- /*
- * Release old AioContext, it won't be needed anymore, as all
- * bdrv_drained_begin() have been called already.
- */
- if (qemu_get_aio_context() != old_context) {
- aio_context_release(old_context);
- }
-
- /*
- * Acquire new AioContext since bdrv_drained_end() is going to be called
- * after we switched all nodes in the new AioContext, and the function
- * assumes that the lock of the bs is always taken.
- */
- if (qemu_get_aio_context() != ctx) {
- aio_context_acquire(ctx);
- }
-
tran_commit(tran);
-
- if (qemu_get_aio_context() != ctx) {
- aio_context_release(ctx);
- }
-
- /* Re-acquire the old AioContext, since the caller takes and releases it. */
- if (qemu_get_aio_context() != old_context) {
- aio_context_acquire(old_context);
- }
-
return 0;
}
@@ -8006,7 +7743,6 @@
const char *node_name, Error **errp)
{
BlockDriverState *to_replace_bs = bdrv_find_node(node_name);
- AioContext *aio_context;
GLOBAL_STATE_CODE();
@@ -8015,12 +7751,8 @@
return NULL;
}
- aio_context = bdrv_get_aio_context(to_replace_bs);
- aio_context_acquire(aio_context);
-
if (bdrv_op_is_blocked(to_replace_bs, BLOCK_OP_TYPE_REPLACE, errp)) {
- to_replace_bs = NULL;
- goto out;
+ return NULL;
}
/* We don't want arbitrary node of the BDS chain to be replaced only the top
@@ -8033,12 +7765,9 @@
"because it cannot be guaranteed that doing so would not "
"lead to an abrupt change of visible data",
node_name, parent_bs->node_name);
- to_replace_bs = NULL;
- goto out;
+ return NULL;
}
-out:
- aio_context_release(aio_context);
return to_replace_bs;
}
diff --git a/block/backup.c b/block/backup.c
index 8aae583..ec29d6b 100644
--- a/block/backup.c
+++ b/block/backup.c
@@ -496,10 +496,10 @@
block_copy_set_speed(bcs, speed);
/* Required permissions are taken by copy-before-write filter target */
- bdrv_graph_wrlock(target);
+ bdrv_graph_wrlock();
block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
&error_abort);
- bdrv_graph_wrunlock(target);
+ bdrv_graph_wrunlock();
return &job->common;
diff --git a/block/blklogwrites.c b/block/blklogwrites.c
index 3678f6c..7207b2e 100644
--- a/block/blklogwrites.c
+++ b/block/blklogwrites.c
@@ -251,9 +251,9 @@
ret = 0;
fail_log:
if (ret < 0) {
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, s->log_file);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
s->log_file = NULL;
}
fail:
@@ -265,10 +265,10 @@
{
BDRVBlkLogWritesState *s = bs->opaque;
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, s->log_file);
s->log_file = NULL;
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
}
static int64_t coroutine_fn GRAPH_RDLOCK
diff --git a/block/blkverify.c b/block/blkverify.c
index 9b17c46..ec45d83 100644
--- a/block/blkverify.c
+++ b/block/blkverify.c
@@ -151,10 +151,10 @@
{
BDRVBlkverifyState *s = bs->opaque;
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, s->test_file);
s->test_file = NULL;
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
}
static int64_t coroutine_fn GRAPH_RDLOCK
diff --git a/block/block-backend.c b/block/block-backend.c
index ec21148..209eb07 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -390,8 +390,6 @@
* Both sets of permissions can be changed later using blk_set_perm().
*
* Return the new BlockBackend on success, null on failure.
- *
- * Callers must hold the AioContext lock of @bs.
*/
BlockBackend *blk_new_with_bs(BlockDriverState *bs, uint64_t perm,
uint64_t shared_perm, Error **errp)
@@ -416,8 +414,6 @@
* Just as with bdrv_open(), after having called this function the reference to
* @options belongs to the block layer (even on failure).
*
- * Called without holding an AioContext lock.
- *
* TODO: Remove @filename and @flags; it should be possible to specify a whole
* BDS tree just by specifying the @options QDict (or @reference,
* alternatively). At the time of adding this function, this is not possible,
@@ -429,7 +425,6 @@
{
BlockBackend *blk;
BlockDriverState *bs;
- AioContext *ctx;
uint64_t perm = 0;
uint64_t shared = BLK_PERM_ALL;
@@ -459,23 +454,18 @@
shared = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED;
}
- aio_context_acquire(qemu_get_aio_context());
bs = bdrv_open(filename, reference, options, flags, errp);
- aio_context_release(qemu_get_aio_context());
if (!bs) {
return NULL;
}
/* bdrv_open() could have moved bs to a different AioContext */
- ctx = bdrv_get_aio_context(bs);
blk = blk_new(bdrv_get_aio_context(bs), perm, shared);
blk->perm = perm;
blk->shared_perm = shared;
- aio_context_acquire(ctx);
blk_insert_bs(blk, bs, errp);
bdrv_unref(bs);
- aio_context_release(ctx);
if (!blk->root) {
blk_unref(blk);
@@ -577,13 +567,9 @@
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);
}
}
@@ -882,14 +868,11 @@
/*
* Disassociates the currently associated BlockDriverState from @blk.
- *
- * The caller must hold the AioContext lock for the BlockBackend.
*/
void blk_remove_bs(BlockBackend *blk)
{
ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
BdrvChild *root;
- AioContext *ctx;
GLOBAL_STATE_CODE();
@@ -919,30 +902,26 @@
root = blk->root;
blk->root = NULL;
- ctx = bdrv_get_aio_context(root->bs);
- bdrv_graph_wrlock(root->bs);
+ bdrv_graph_wrlock();
bdrv_root_unref_child(root);
- bdrv_graph_wrunlock_ctx(ctx);
+ bdrv_graph_wrunlock();
}
/*
* Associates a new BlockDriverState with @blk.
- *
- * Callers must hold the AioContext lock of @bs.
*/
int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
{
ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
- AioContext *ctx = bdrv_get_aio_context(bs);
GLOBAL_STATE_CODE();
bdrv_ref(bs);
- bdrv_graph_wrlock(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_ctx(ctx);
+ bdrv_graph_wrunlock();
if (blk->root == NULL) {
return -EPERM;
}
@@ -2739,20 +2718,16 @@
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;
}
diff --git a/block/commit.c b/block/commit.c
index 69cc75b..1dd7a65 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -100,9 +100,9 @@
bdrv_graph_rdunlock_main_loop();
bdrv_drained_begin(commit_top_backing_bs);
- bdrv_graph_wrlock(commit_top_backing_bs);
+ bdrv_graph_wrlock();
bdrv_replace_node(s->commit_top_bs, commit_top_backing_bs, &error_abort);
- bdrv_graph_wrunlock(commit_top_backing_bs);
+ bdrv_graph_wrunlock();
bdrv_drained_end(commit_top_backing_bs);
bdrv_unref(s->commit_top_bs);
@@ -339,7 +339,7 @@
* this is the responsibility of the interface (i.e. whoever calls
* commit_start()).
*/
- bdrv_graph_wrlock(top);
+ bdrv_graph_wrlock();
s->base_overlay = bdrv_find_overlay(top, base);
assert(s->base_overlay);
@@ -370,19 +370,19 @@
ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
iter_shared_perms, errp);
if (ret < 0) {
- bdrv_graph_wrunlock(top);
+ bdrv_graph_wrunlock();
goto fail;
}
}
if (bdrv_freeze_backing_chain(commit_top_bs, base, errp) < 0) {
- bdrv_graph_wrunlock(top);
+ bdrv_graph_wrunlock();
goto fail;
}
s->chain_frozen = true;
ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
- bdrv_graph_wrunlock(top);
+ bdrv_graph_wrunlock();
if (ret < 0) {
goto fail;
@@ -434,9 +434,9 @@
* otherwise this would fail because of lack of permissions. */
if (commit_top_bs) {
bdrv_drained_begin(top);
- bdrv_graph_wrlock(top);
+ bdrv_graph_wrlock();
bdrv_replace_node(commit_top_bs, top, &error_abort);
- bdrv_graph_wrunlock(top);
+ bdrv_graph_wrunlock();
bdrv_drained_end(top);
}
}
diff --git a/block/copy-before-write.c b/block/copy-before-write.c
index 1397287..0842a1a 100644
--- a/block/copy-before-write.c
+++ b/block/copy-before-write.c
@@ -412,7 +412,6 @@
int64_t cluster_size;
g_autoptr(BlockdevOptions) full_opts = NULL;
BlockdevOptionsCbw *opts;
- AioContext *ctx;
int ret;
full_opts = cbw_parse_options(options, errp);
@@ -435,15 +434,11 @@
GRAPH_RDLOCK_GUARD_MAINLOOP();
- ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
-
if (opts->bitmap) {
bitmap = block_dirty_bitmap_lookup(opts->bitmap->node,
opts->bitmap->name, NULL, errp);
if (!bitmap) {
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
}
s->on_cbw_error = opts->has_on_cbw_error ? opts->on_cbw_error :
@@ -461,24 +456,21 @@
s->bcs = block_copy_state_new(bs->file, s->target, bitmap, errp);
if (!s->bcs) {
error_prepend(errp, "Cannot create block-copy-state: ");
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
cluster_size = block_copy_cluster_size(s->bcs);
s->done_bitmap = bdrv_create_dirty_bitmap(bs, cluster_size, NULL, errp);
if (!s->done_bitmap) {
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
bdrv_disable_dirty_bitmap(s->done_bitmap);
/* s->access_bitmap starts equal to bcs bitmap */
s->access_bitmap = bdrv_create_dirty_bitmap(bs, cluster_size, NULL, errp);
if (!s->access_bitmap) {
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
bdrv_disable_dirty_bitmap(s->access_bitmap);
bdrv_dirty_bitmap_merge_internal(s->access_bitmap,
@@ -487,11 +479,7 @@
qemu_co_mutex_init(&s->lock);
QLIST_INIT(&s->frozen_read_reqs);
-
- ret = 0;
-out:
- aio_context_release(ctx);
- return ret;
+ return 0;
}
static void cbw_close(BlockDriverState *bs)
diff --git a/block/export/export.c b/block/export/export.c
index a8f274e..6d51ae8 100644
--- a/block/export/export.c
+++ b/block/export/export.c
@@ -114,7 +114,6 @@
}
ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
if (export->iothread) {
IOThread *iothread;
@@ -133,8 +132,6 @@
set_context_errp = fixed_iothread ? errp : NULL;
ret = bdrv_try_change_aio_context(bs, new_ctx, NULL, set_context_errp);
if (ret == 0) {
- aio_context_release(ctx);
- aio_context_acquire(new_ctx);
ctx = new_ctx;
} else if (fixed_iothread) {
goto fail;
@@ -191,8 +188,6 @@
assert(exp->blk != NULL);
QLIST_INSERT_HEAD(&block_exports, exp, next);
-
- aio_context_release(ctx);
return exp;
fail:
@@ -200,7 +195,6 @@
blk_set_dev_ops(blk, NULL, NULL);
blk_unref(blk);
}
- aio_context_release(ctx);
if (exp) {
g_free(exp->id);
g_free(exp);
@@ -218,9 +212,6 @@
static void blk_exp_delete_bh(void *opaque)
{
BlockExport *exp = opaque;
- AioContext *aio_context = exp->ctx;
-
- aio_context_acquire(aio_context);
assert(exp->refcount == 0);
QLIST_REMOVE(exp, next);
@@ -230,8 +221,6 @@
qapi_event_send_block_export_deleted(exp->id);
g_free(exp->id);
g_free(exp);
-
- aio_context_release(aio_context);
}
void blk_exp_unref(BlockExport *exp)
@@ -249,22 +238,16 @@
* connections and other internally held references start to shut down. When
* the function returns, there may still be active references while the export
* is in the process of shutting down.
- *
- * Acquires exp->ctx internally. Callers must *not* hold the lock.
*/
void blk_exp_request_shutdown(BlockExport *exp)
{
- AioContext *aio_context = exp->ctx;
-
- aio_context_acquire(aio_context);
-
/*
* If the user doesn't own the export any more, it is already shutting
* down. We must not call .request_shutdown and decrease the refcount a
* second time.
*/
if (!exp->user_owned) {
- goto out;
+ return;
}
exp->drv->request_shutdown(exp);
@@ -272,9 +255,6 @@
assert(exp->user_owned);
exp->user_owned = false;
blk_exp_unref(exp);
-
-out:
- aio_context_release(aio_context);
}
/*
diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c
index 16f4838..50c358e 100644
--- a/block/export/vhost-user-blk-server.c
+++ b/block/export/vhost-user-blk-server.c
@@ -278,7 +278,6 @@
vu_config_change_msg(&vexp->vu_server.vu_dev);
}
-/* Called with vexp->export.ctx acquired */
static void vu_blk_drained_begin(void *opaque)
{
VuBlkExport *vexp = opaque;
@@ -287,7 +286,6 @@
vhost_user_server_detach_aio_context(&vexp->vu_server);
}
-/* Called with vexp->export.blk AioContext acquired */
static void vu_blk_drained_end(void *opaque)
{
VuBlkExport *vexp = opaque;
@@ -300,8 +298,6 @@
* Ensures that bdrv_drained_begin() waits until in-flight requests complete
* and the server->co_trip coroutine has terminated. It will be restarted in
* vhost_user_server_attach_aio_context().
- *
- * Called with vexp->export.ctx acquired.
*/
static bool vu_blk_drained_poll(void *opaque)
{
diff --git a/block/file-posix.c b/block/file-posix.c
index b862406..35684f7 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -712,17 +712,11 @@
#ifdef CONFIG_LINUX_AIO
/* Currently Linux does AIO only for files opened with O_DIRECT */
- if (s->use_linux_aio) {
- if (!(s->open_flags & O_DIRECT)) {
- error_setg(errp, "aio=native was specified, but it requires "
- "cache.direct=on, which was not specified.");
- ret = -EINVAL;
- goto fail;
- }
- if (!aio_setup_linux_aio(bdrv_get_aio_context(bs), errp)) {
- error_prepend(errp, "Unable to use native AIO: ");
- goto fail;
- }
+ if (s->use_linux_aio && !(s->open_flags & O_DIRECT)) {
+ error_setg(errp, "aio=native was specified, but it requires "
+ "cache.direct=on, which was not specified.");
+ ret = -EINVAL;
+ goto fail;
}
#else
if (s->use_linux_aio) {
@@ -733,14 +727,7 @@
}
#endif /* !defined(CONFIG_LINUX_AIO) */
-#ifdef CONFIG_LINUX_IO_URING
- if (s->use_linux_io_uring) {
- if (!aio_setup_linux_io_uring(bdrv_get_aio_context(bs), errp)) {
- error_prepend(errp, "Unable to use io_uring: ");
- goto fail;
- }
- }
-#else
+#ifndef CONFIG_LINUX_IO_URING
if (s->use_linux_io_uring) {
error_setg(errp, "aio=io_uring was specified, but is not supported "
"in this build.");
@@ -2444,6 +2431,48 @@
return true;
}
+#ifdef CONFIG_LINUX_IO_URING
+static inline bool raw_check_linux_io_uring(BDRVRawState *s)
+{
+ Error *local_err = NULL;
+ AioContext *ctx;
+
+ if (!s->use_linux_io_uring) {
+ return false;
+ }
+
+ ctx = qemu_get_current_aio_context();
+ if (unlikely(!aio_setup_linux_io_uring(ctx, &local_err))) {
+ error_reportf_err(local_err, "Unable to use linux io_uring, "
+ "falling back to thread pool: ");
+ s->use_linux_io_uring = false;
+ return false;
+ }
+ return true;
+}
+#endif
+
+#ifdef CONFIG_LINUX_AIO
+static inline bool raw_check_linux_aio(BDRVRawState *s)
+{
+ Error *local_err = NULL;
+ AioContext *ctx;
+
+ if (!s->use_linux_aio) {
+ return false;
+ }
+
+ ctx = qemu_get_current_aio_context();
+ if (unlikely(!aio_setup_linux_aio(ctx, &local_err))) {
+ error_reportf_err(local_err, "Unable to use Linux AIO, "
+ "falling back to thread pool: ");
+ s->use_linux_aio = false;
+ return false;
+ }
+ return true;
+}
+#endif
+
static int coroutine_fn raw_co_prw(BlockDriverState *bs, int64_t *offset_ptr,
uint64_t bytes, QEMUIOVector *qiov, int type)
{
@@ -2474,13 +2503,13 @@
if (s->needs_alignment && !bdrv_qiov_is_aligned(bs, qiov)) {
type |= QEMU_AIO_MISALIGNED;
#ifdef CONFIG_LINUX_IO_URING
- } else if (s->use_linux_io_uring) {
+ } else if (raw_check_linux_io_uring(s)) {
assert(qiov->size == bytes);
ret = luring_co_submit(bs, s->fd, offset, qiov, type);
goto out;
#endif
#ifdef CONFIG_LINUX_AIO
- } else if (s->use_linux_aio) {
+ } else if (raw_check_linux_aio(s)) {
assert(qiov->size == bytes);
ret = laio_co_submit(s->fd, offset, qiov, type,
s->aio_max_batch);
@@ -2567,39 +2596,13 @@
};
#ifdef CONFIG_LINUX_IO_URING
- if (s->use_linux_io_uring) {
+ if (raw_check_linux_io_uring(s)) {
return luring_co_submit(bs, s->fd, 0, NULL, QEMU_AIO_FLUSH);
}
#endif
return raw_thread_pool_submit(handle_aiocb_flush, &acb);
}
-static void raw_aio_attach_aio_context(BlockDriverState *bs,
- AioContext *new_context)
-{
- BDRVRawState __attribute__((unused)) *s = bs->opaque;
-#ifdef CONFIG_LINUX_AIO
- if (s->use_linux_aio) {
- Error *local_err = NULL;
- if (!aio_setup_linux_aio(new_context, &local_err)) {
- error_reportf_err(local_err, "Unable to use native AIO, "
- "falling back to thread pool: ");
- s->use_linux_aio = false;
- }
- }
-#endif
-#ifdef CONFIG_LINUX_IO_URING
- if (s->use_linux_io_uring) {
- Error *local_err = NULL;
- if (!aio_setup_linux_io_uring(new_context, &local_err)) {
- error_reportf_err(local_err, "Unable to use linux io_uring, "
- "falling back to thread pool: ");
- s->use_linux_io_uring = false;
- }
- }
-#endif
-}
-
static void raw_close(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
@@ -3896,7 +3899,6 @@
.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_attach_aio_context = raw_aio_attach_aio_context,
.bdrv_co_truncate = raw_co_truncate,
.bdrv_co_getlength = raw_co_getlength,
@@ -4266,7 +4268,6 @@
.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_attach_aio_context = raw_aio_attach_aio_context,
.bdrv_co_truncate = raw_co_truncate,
.bdrv_co_getlength = raw_co_getlength,
@@ -4402,7 +4403,6 @@
.bdrv_co_pwritev = raw_co_pwritev,
.bdrv_co_flush_to_disk = raw_co_flush_to_disk,
.bdrv_refresh_limits = cdrom_refresh_limits,
- .bdrv_attach_aio_context = raw_aio_attach_aio_context,
.bdrv_co_truncate = raw_co_truncate,
.bdrv_co_getlength = raw_co_getlength,
@@ -4528,7 +4528,6 @@
.bdrv_co_pwritev = raw_co_pwritev,
.bdrv_co_flush_to_disk = raw_co_flush_to_disk,
.bdrv_refresh_limits = cdrom_refresh_limits,
- .bdrv_attach_aio_context = raw_aio_attach_aio_context,
.bdrv_co_truncate = raw_co_truncate,
.bdrv_co_getlength = raw_co_getlength,
diff --git a/block/graph-lock.c b/block/graph-lock.c
index 079e878..c81162b 100644
--- a/block/graph-lock.c
+++ b/block/graph-lock.c
@@ -106,27 +106,12 @@
return rd;
}
-void no_coroutine_fn bdrv_graph_wrlock(BlockDriverState *bs)
+void no_coroutine_fn bdrv_graph_wrlock(void)
{
- AioContext *ctx = NULL;
-
GLOBAL_STATE_CODE();
assert(!qatomic_read(&has_writer));
assert(!qemu_in_coroutine());
- /*
- * Release only non-mainloop AioContext. The mainloop often relies on the
- * BQL and doesn't lock the main AioContext before doing things.
- */
- if (bs) {
- ctx = bdrv_get_aio_context(bs);
- if (ctx != qemu_get_aio_context()) {
- aio_context_release(ctx);
- } else {
- ctx = NULL;
- }
- }
-
/* Make sure that constantly arriving new I/O doesn't cause starvation */
bdrv_drain_all_begin_nopoll();
@@ -155,27 +140,13 @@
} while (reader_count() >= 1);
bdrv_drain_all_end();
-
- if (ctx) {
- aio_context_acquire(bdrv_get_aio_context(bs));
- }
}
-void no_coroutine_fn bdrv_graph_wrunlock_ctx(AioContext *ctx)
+void no_coroutine_fn bdrv_graph_wrunlock(void)
{
GLOBAL_STATE_CODE();
assert(qatomic_read(&has_writer));
- /*
- * Release only non-mainloop AioContext. The mainloop often relies on the
- * BQL and doesn't lock the main AioContext before doing things.
- */
- if (ctx && ctx != qemu_get_aio_context()) {
- aio_context_release(ctx);
- } else {
- ctx = NULL;
- }
-
WITH_QEMU_LOCK_GUARD(&aio_context_list_lock) {
/*
* No need for memory barriers, this works in pair with
@@ -197,17 +168,6 @@
* progress.
*/
aio_bh_poll(qemu_get_aio_context());
-
- if (ctx) {
- aio_context_acquire(ctx);
- }
-}
-
-void no_coroutine_fn bdrv_graph_wrunlock(BlockDriverState *bs)
-{
- AioContext *ctx = bs ? bdrv_get_aio_context(bs) : NULL;
-
- bdrv_graph_wrunlock_ctx(ctx);
}
void coroutine_fn bdrv_graph_co_rdlock(void)
diff --git a/block/io.c b/block/io.c
index 7e62fab..8fa7670 100644
--- a/block/io.c
+++ b/block/io.c
@@ -294,8 +294,6 @@
BlockDriverState *bs = data->bs;
if (bs) {
- AioContext *ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
bdrv_dec_in_flight(bs);
if (data->begin) {
bdrv_do_drained_begin(bs, data->parent, data->poll);
@@ -303,7 +301,6 @@
assert(!data->poll);
bdrv_do_drained_end(bs, data->parent);
}
- aio_context_release(ctx);
} else {
assert(data->begin);
bdrv_drain_all_begin();
@@ -320,8 +317,6 @@
{
BdrvCoDrainData data;
Coroutine *self = qemu_coroutine_self();
- AioContext *ctx = bdrv_get_aio_context(bs);
- AioContext *co_ctx = qemu_coroutine_get_aio_context(self);
/* Calling bdrv_drain() from a BH ensures the current coroutine yields and
* other coroutines run if they were queued by aio_co_enter(). */
@@ -340,17 +335,6 @@
bdrv_inc_in_flight(bs);
}
- /*
- * Temporarily drop the lock across yield or we would get deadlocks.
- * bdrv_co_drain_bh_cb() reaquires the lock as needed.
- *
- * When we yield below, the lock for the current context will be
- * released, so if this is actually the lock that protects bs, don't drop
- * it a second time.
- */
- if (ctx != co_ctx) {
- aio_context_release(ctx);
- }
replay_bh_schedule_oneshot_event(qemu_get_aio_context(),
bdrv_co_drain_bh_cb, &data);
@@ -358,11 +342,6 @@
/* If we are resumed from some other event (such as an aio completion or a
* timer callback), it is a bug in the caller that should be fixed. */
assert(data.done);
-
- /* Reacquire the AioContext of bs if we dropped it */
- if (ctx != co_ctx) {
- aio_context_acquire(ctx);
- }
}
static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
@@ -478,13 +457,12 @@
GLOBAL_STATE_CODE();
GRAPH_RDLOCK_GUARD_MAINLOOP();
- /* bdrv_drain_poll() can't make changes to the graph and we are holding the
- * main AioContext lock, so iterating bdrv_next_all_states() is safe. */
+ /*
+ * bdrv_drain_poll() can't make changes to the graph and we hold the BQL,
+ * so iterating bdrv_next_all_states() is safe.
+ */
while ((bs = bdrv_next_all_states(bs))) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
result |= bdrv_drain_poll(bs, NULL, true);
- aio_context_release(aio_context);
}
return result;
@@ -525,11 +503,7 @@
/* Quiesce all nodes, without polling in-flight requests yet. The graph
* cannot change during this loop. */
while ((bs = bdrv_next_all_states(bs))) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
-
- aio_context_acquire(aio_context);
bdrv_do_drained_begin(bs, NULL, false);
- aio_context_release(aio_context);
}
}
@@ -588,11 +562,7 @@
}
while ((bs = bdrv_next_all_states(bs))) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
-
- aio_context_acquire(aio_context);
bdrv_do_drained_end(bs, NULL);
- aio_context_release(aio_context);
}
assert(qemu_get_current_aio_context() == qemu_get_aio_context());
@@ -2368,15 +2338,10 @@
}
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
- int ret;
-
- aio_context_acquire(aio_context);
- ret = bdrv_flush(bs);
+ int ret = bdrv_flush(bs);
if (ret < 0 && !result) {
result = ret;
}
- aio_context_release(aio_context);
}
return result;
diff --git a/block/mirror.c b/block/mirror.c
index cd9d3ad..5145eb5 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -662,7 +662,6 @@
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common.job);
BlockJob *bjob = &s->common;
MirrorBDSOpaque *bs_opaque;
- AioContext *replace_aio_context = NULL;
BlockDriverState *src;
BlockDriverState *target_bs;
BlockDriverState *mirror_top_bs;
@@ -677,7 +676,6 @@
}
s->prepared = true;
- aio_context_acquire(qemu_get_aio_context());
bdrv_graph_rdlock_main_loop();
mirror_top_bs = s->mirror_top_bs;
@@ -742,11 +740,6 @@
}
bdrv_graph_rdunlock_main_loop();
- if (s->to_replace) {
- replace_aio_context = bdrv_get_aio_context(s->to_replace);
- aio_context_acquire(replace_aio_context);
- }
-
if (s->should_complete && !abort) {
BlockDriverState *to_replace = s->to_replace ?: src;
bool ro = bdrv_is_read_only(to_replace);
@@ -764,7 +757,7 @@
* check for an op blocker on @to_replace, and we have our own
* there.
*/
- bdrv_graph_wrlock(target_bs);
+ bdrv_graph_wrlock();
if (bdrv_recurse_can_replace(src, to_replace)) {
bdrv_replace_node(to_replace, target_bs, &local_err);
} else {
@@ -773,7 +766,7 @@
"would not lead to an abrupt change of visible data",
to_replace->node_name, target_bs->node_name);
}
- bdrv_graph_wrunlock(target_bs);
+ bdrv_graph_wrunlock();
bdrv_drained_end(to_replace);
if (local_err) {
error_report_err(local_err);
@@ -785,9 +778,6 @@
error_free(s->replace_blocker);
bdrv_unref(s->to_replace);
}
- if (replace_aio_context) {
- aio_context_release(replace_aio_context);
- }
g_free(s->replaces);
/*
@@ -796,9 +786,9 @@
* valid.
*/
block_job_remove_all_bdrv(bjob);
- bdrv_graph_wrlock(mirror_top_bs);
+ bdrv_graph_wrlock();
bdrv_replace_node(mirror_top_bs, mirror_top_bs->backing->bs, &error_abort);
- bdrv_graph_wrunlock(mirror_top_bs);
+ bdrv_graph_wrunlock();
bdrv_drained_end(target_bs);
bdrv_unref(target_bs);
@@ -811,8 +801,6 @@
bdrv_unref(mirror_top_bs);
bdrv_unref(src);
- aio_context_release(qemu_get_aio_context());
-
return ret;
}
@@ -1191,24 +1179,17 @@
/* block all operations on to_replace bs */
if (s->replaces) {
- AioContext *replace_aio_context;
-
s->to_replace = bdrv_find_node(s->replaces);
if (!s->to_replace) {
error_setg(errp, "Node name '%s' not found", s->replaces);
return;
}
- replace_aio_context = bdrv_get_aio_context(s->to_replace);
- aio_context_acquire(replace_aio_context);
-
/* TODO Translate this into child freeze system. */
error_setg(&s->replace_blocker,
"block device is in use by block-job-complete");
bdrv_op_block_all(s->to_replace, s->replace_blocker);
bdrv_ref(s->to_replace);
-
- aio_context_release(replace_aio_context);
}
s->should_complete = true;
@@ -1914,13 +1895,13 @@
*/
bdrv_disable_dirty_bitmap(s->dirty_bitmap);
- bdrv_graph_wrlock(bs);
+ bdrv_graph_wrlock();
ret = block_job_add_bdrv(&s->common, "source", bs, 0,
BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE |
BLK_PERM_CONSISTENT_READ,
errp);
if (ret < 0) {
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
goto fail;
}
@@ -1965,17 +1946,17 @@
ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
iter_shared_perms, errp);
if (ret < 0) {
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
goto fail;
}
}
if (bdrv_freeze_backing_chain(mirror_top_bs, target, errp) < 0) {
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
goto fail;
}
}
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
QTAILQ_INIT(&s->ops_in_flight);
@@ -2001,12 +1982,12 @@
bs_opaque->stop = true;
bdrv_drained_begin(bs);
- bdrv_graph_wrlock(bs);
+ bdrv_graph_wrlock();
assert(mirror_top_bs->backing->bs == bs);
bdrv_child_refresh_perms(mirror_top_bs, mirror_top_bs->backing,
&error_abort);
bdrv_replace_node(mirror_top_bs, bs, &error_abort);
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
bdrv_drained_end(bs);
bdrv_unref(mirror_top_bs);
diff --git a/block/monitor/bitmap-qmp-cmds.c b/block/monitor/bitmap-qmp-cmds.c
index 70d01a3..a738e7b 100644
--- a/block/monitor/bitmap-qmp-cmds.c
+++ b/block/monitor/bitmap-qmp-cmds.c
@@ -95,7 +95,6 @@
{
BlockDriverState *bs;
BdrvDirtyBitmap *bitmap;
- AioContext *aio_context;
if (!name || name[0] == '\0') {
error_setg(errp, "Bitmap name cannot be empty");
@@ -107,14 +106,11 @@
return;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
-
if (has_granularity) {
if (granularity < 512 || !is_power_of_2(granularity)) {
error_setg(errp, "Granularity must be power of 2 "
"and at least 512");
- goto out;
+ return;
}
} else {
/* Default to cluster size, if available: */
@@ -132,12 +128,12 @@
if (persistent &&
!bdrv_can_store_new_dirty_bitmap(bs, name, granularity, errp))
{
- goto out;
+ return;
}
bitmap = bdrv_create_dirty_bitmap(bs, granularity, name, errp);
if (bitmap == NULL) {
- goto out;
+ return;
}
if (disabled) {
@@ -145,9 +141,6 @@
}
bdrv_dirty_bitmap_set_persistence(bitmap, persistent);
-
-out:
- aio_context_release(aio_context);
}
BdrvDirtyBitmap *block_dirty_bitmap_remove(const char *node, const char *name,
@@ -157,7 +150,6 @@
{
BlockDriverState *bs;
BdrvDirtyBitmap *bitmap;
- AioContext *aio_context;
GLOBAL_STATE_CODE();
@@ -166,19 +158,14 @@
return NULL;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
-
if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_BUSY | BDRV_BITMAP_RO,
errp)) {
- aio_context_release(aio_context);
return NULL;
}
if (bdrv_dirty_bitmap_get_persistence(bitmap) &&
bdrv_remove_persistent_dirty_bitmap(bs, name, errp) < 0)
{
- aio_context_release(aio_context);
return NULL;
}
@@ -190,7 +177,6 @@
*bitmap_bs = bs;
}
- aio_context_release(aio_context);
return release ? NULL : bitmap;
}
diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
index c729cbf..bdbb5cb 100644
--- a/block/monitor/block-hmp-cmds.c
+++ b/block/monitor/block-hmp-cmds.c
@@ -141,7 +141,6 @@
const char *id = qdict_get_str(qdict, "id");
BlockBackend *blk;
BlockDriverState *bs;
- AioContext *aio_context;
Error *local_err = NULL;
GLOBAL_STATE_CODE();
@@ -168,14 +167,10 @@
return;
}
- aio_context = blk_get_aio_context(blk);
- aio_context_acquire(aio_context);
-
bs = blk_bs(blk);
if (bs) {
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_DRIVE_DEL, &local_err)) {
error_report_err(local_err);
- aio_context_release(aio_context);
return;
}
@@ -196,8 +191,6 @@
} else {
blk_unref(blk);
}
-
- aio_context_release(aio_context);
}
void hmp_commit(Monitor *mon, const QDict *qdict)
@@ -213,7 +206,6 @@
ret = blk_commit_all();
} else {
BlockDriverState *bs;
- AioContext *aio_context;
blk = blk_by_name(device);
if (!blk) {
@@ -222,18 +214,13 @@
}
bs = bdrv_skip_implicit_filters(blk_bs(blk));
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
if (!blk_is_available(blk)) {
error_report("Device '%s' has no medium", device);
- aio_context_release(aio_context);
return;
}
ret = bdrv_commit(bs);
-
- aio_context_release(aio_context);
}
if (ret < 0) {
error_report("'commit' error for '%s': %s", device, strerror(-ret));
@@ -560,7 +547,6 @@
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
BlockBackend *local_blk = NULL;
- AioContext *ctx = NULL;
bool qdev = qdict_get_try_bool(qdict, "qdev", false);
const char *device = qdict_get_str(qdict, "device");
const char *command = qdict_get_str(qdict, "command");
@@ -582,9 +568,6 @@
}
}
- ctx = blk ? blk_get_aio_context(blk) : bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
-
if (bs) {
blk = local_blk = blk_new(bdrv_get_aio_context(bs), 0, BLK_PERM_ALL);
ret = blk_insert_bs(blk, bs, &err);
@@ -622,11 +605,6 @@
fail:
blk_unref(local_blk);
-
- if (ctx) {
- aio_context_release(ctx);
- }
-
hmp_handle_error(mon, err);
}
@@ -882,7 +860,6 @@
int nb_sns, i;
int total;
int *global_snapshots;
- AioContext *aio_context;
typedef struct SnapshotEntry {
QEMUSnapshotInfo sn;
@@ -909,11 +886,8 @@
error_report_err(err);
return;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
nb_sns = bdrv_snapshot_list(bs, &sn_tab);
- aio_context_release(aio_context);
if (nb_sns < 0) {
monitor_printf(mon, "bdrv_snapshot_list: error %d\n", nb_sns);
@@ -924,9 +898,7 @@
int bs1_nb_sns = 0;
ImageEntry *ie;
SnapshotEntry *se;
- AioContext *ctx = bdrv_get_aio_context(bs1);
- aio_context_acquire(ctx);
if (bdrv_can_snapshot(bs1)) {
sn = NULL;
bs1_nb_sns = bdrv_snapshot_list(bs1, &sn);
@@ -944,7 +916,6 @@
}
g_free(sn);
}
- aio_context_release(ctx);
}
if (no_snapshot) {
diff --git a/block/qapi-sysemu.c b/block/qapi-sysemu.c
index 1618cd2..e428263 100644
--- a/block/qapi-sysemu.c
+++ b/block/qapi-sysemu.c
@@ -174,7 +174,6 @@
{
BlockBackend *blk;
BlockDriverState *bs;
- AioContext *aio_context;
bool has_attached_device;
GLOBAL_STATE_CODE();
@@ -204,13 +203,10 @@
return;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
-
bdrv_graph_rdlock_main_loop();
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_EJECT, errp)) {
bdrv_graph_rdunlock_main_loop();
- goto out;
+ return;
}
bdrv_graph_rdunlock_main_loop();
@@ -223,9 +219,6 @@
* value passed here (i.e. false). */
blk_dev_change_media_cb(blk, false, &error_abort);
}
-
-out:
- aio_context_release(aio_context);
}
void qmp_blockdev_remove_medium(const char *id, Error **errp)
@@ -237,7 +230,6 @@
BlockDriverState *bs, Error **errp)
{
Error *local_err = NULL;
- AioContext *ctx;
bool has_device;
int ret;
@@ -259,11 +251,7 @@
return;
}
- ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
ret = blk_insert_bs(blk, bs, errp);
- aio_context_release(ctx);
-
if (ret < 0) {
return;
}
@@ -374,9 +362,7 @@
qdict_put_str(options, "driver", format);
}
- aio_context_acquire(qemu_get_aio_context());
medium_bs = bdrv_open(filename, NULL, options, bdrv_flags, errp);
- aio_context_release(qemu_get_aio_context());
if (!medium_bs) {
goto fail;
@@ -437,20 +423,16 @@
ThrottleConfig cfg;
BlockDriverState *bs;
BlockBackend *blk;
- AioContext *aio_context;
blk = qmp_get_blk(arg->device, arg->id, errp);
if (!blk) {
return;
}
- aio_context = blk_get_aio_context(blk);
- aio_context_acquire(aio_context);
-
bs = blk_bs(blk);
if (!bs) {
error_setg(errp, "Device has no medium");
- goto out;
+ return;
}
throttle_config_init(&cfg);
@@ -505,7 +487,7 @@
}
if (!throttle_is_valid(&cfg, errp)) {
- goto out;
+ return;
}
if (throttle_enabled(&cfg)) {
@@ -522,9 +504,6 @@
/* If all throttling settings are set to 0, disable I/O limits */
blk_io_limits_disable(blk);
}
-
-out:
- aio_context_release(aio_context);
}
void qmp_block_latency_histogram_set(
diff --git a/block/qapi.c b/block/qapi.c
index 82a30b3..9e806fa 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -234,13 +234,11 @@
int ret;
Error *err = NULL;
- aio_context_acquire(bdrv_get_aio_context(bs));
-
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "Can't get image size '%s'",
bs->exact_filename);
- goto out;
+ return;
}
bdrv_refresh_filename(bs);
@@ -265,7 +263,7 @@
info->format_specific = bdrv_get_specific_info(bs, &err);
if (err) {
error_propagate(errp, err);
- goto out;
+ return;
}
backing_filename = bs->backing_file;
if (backing_filename[0] != '\0') {
@@ -300,11 +298,8 @@
break;
default:
error_propagate(errp, err);
- goto out;
+ return;
}
-
-out:
- aio_context_release(bdrv_get_aio_context(bs));
}
/**
@@ -709,15 +704,10 @@
/* Just to be safe if query_nodes is not always initialized */
if (has_query_nodes && query_nodes) {
for (bs = bdrv_next_node(NULL); bs; bs = bdrv_next_node(bs)) {
- AioContext *ctx = bdrv_get_aio_context(bs);
-
- aio_context_acquire(ctx);
QAPI_LIST_APPEND(tail, bdrv_query_bds_stats(bs, false));
- aio_context_release(ctx);
}
} else {
for (blk = blk_all_next(NULL); blk; blk = blk_all_next(blk)) {
- AioContext *ctx = blk_get_aio_context(blk);
BlockStats *s;
char *qdev;
@@ -725,7 +715,6 @@
continue;
}
- aio_context_acquire(ctx);
s = bdrv_query_bds_stats(blk_bs(blk), true);
s->device = g_strdup(blk_name(blk));
@@ -737,7 +726,6 @@
}
bdrv_query_blk_stats(s->stats, blk);
- aio_context_release(ctx);
QAPI_LIST_APPEND(tail, s);
}
diff --git a/block/qcow2.c b/block/qcow2.c
index 13e032b..9bee66f 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -2807,9 +2807,9 @@
if (close_data_file && has_data_file(bs)) {
GLOBAL_STATE_CODE();
bdrv_graph_rdunlock_main_loop();
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, s->data_file);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
s->data_file = NULL;
bdrv_graph_rdlock_main_loop();
}
diff --git a/block/quorum.c b/block/quorum.c
index 505b8b3..db8fe89 100644
--- a/block/quorum.c
+++ b/block/quorum.c
@@ -1037,14 +1037,14 @@
close_exit:
/* cleanup on error */
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
for (i = 0; i < s->num_children; i++) {
if (!opened[i]) {
continue;
}
bdrv_unref_child(bs, s->children[i]);
}
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
g_free(s->children);
g_free(opened);
exit:
@@ -1057,11 +1057,11 @@
BDRVQuorumState *s = bs->opaque;
int i;
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
for (i = 0; i < s->num_children; i++) {
bdrv_unref_child(bs, s->children[i]);
}
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
g_free(s->children);
}
diff --git a/block/raw-format.c b/block/raw-format.c
index 1111dff..ac7e849 100644
--- a/block/raw-format.c
+++ b/block/raw-format.c
@@ -470,7 +470,6 @@
Error **errp)
{
BDRVRawState *s = bs->opaque;
- AioContext *ctx;
bool has_size;
uint64_t offset, size;
BdrvChildRole file_role;
@@ -522,11 +521,7 @@
bs->file->bs->filename);
}
- ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
ret = raw_apply_options(bs, s, offset, has_size, size, errp);
- aio_context_release(ctx);
-
if (ret < 0) {
return ret;
}
diff --git a/block/replication.c b/block/replication.c
index 5ded5f1..ca6bd0a 100644
--- a/block/replication.c
+++ b/block/replication.c
@@ -394,14 +394,7 @@
}
if (reopen_queue) {
- AioContext *ctx = bdrv_get_aio_context(bs);
- if (ctx != qemu_get_aio_context()) {
- aio_context_release(ctx);
- }
bdrv_reopen_multiple(reopen_queue, errp);
- if (ctx != qemu_get_aio_context()) {
- aio_context_acquire(ctx);
- }
}
}
@@ -462,14 +455,11 @@
BlockDriverState *top_bs;
BdrvChild *active_disk, *hidden_disk, *secondary_disk;
int64_t active_length, hidden_length, disk_length;
- AioContext *aio_context;
Error *local_err = NULL;
BackupPerf perf = { .use_copy_range = true, .max_workers = 1 };
GLOBAL_STATE_CODE();
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
s = bs->opaque;
if (s->stage == BLOCK_REPLICATION_DONE ||
@@ -479,20 +469,17 @@
* Ignore the request because the secondary side of replication
* doesn't have to do anything anymore.
*/
- aio_context_release(aio_context);
return;
}
if (s->stage != BLOCK_REPLICATION_NONE) {
error_setg(errp, "Block replication is running or done");
- aio_context_release(aio_context);
return;
}
if (s->mode != mode) {
error_setg(errp, "The parameter mode's value is invalid, needs %d,"
" but got %d", s->mode, mode);
- aio_context_release(aio_context);
return;
}
@@ -505,7 +492,6 @@
if (!active_disk || !active_disk->bs || !active_disk->bs->backing) {
error_setg(errp, "Active disk doesn't have backing file");
bdrv_graph_rdunlock_main_loop();
- aio_context_release(aio_context);
return;
}
@@ -513,7 +499,6 @@
if (!hidden_disk->bs || !hidden_disk->bs->backing) {
error_setg(errp, "Hidden disk doesn't have backing file");
bdrv_graph_rdunlock_main_loop();
- aio_context_release(aio_context);
return;
}
@@ -521,7 +506,6 @@
if (!secondary_disk->bs || !bdrv_has_blk(secondary_disk->bs)) {
error_setg(errp, "The secondary disk doesn't have block backend");
bdrv_graph_rdunlock_main_loop();
- aio_context_release(aio_context);
return;
}
bdrv_graph_rdunlock_main_loop();
@@ -534,7 +518,6 @@
active_length != hidden_length || hidden_length != disk_length) {
error_setg(errp, "Active disk, hidden disk, secondary disk's length"
" are not the same");
- aio_context_release(aio_context);
return;
}
@@ -546,7 +529,6 @@
!hidden_disk->bs->drv->bdrv_make_empty) {
error_setg(errp,
"Active disk or hidden disk doesn't support make_empty");
- aio_context_release(aio_context);
bdrv_graph_rdunlock_main_loop();
return;
}
@@ -556,11 +538,10 @@
reopen_backing_file(bs, true, &local_err);
if (local_err) {
error_propagate(errp, local_err);
- aio_context_release(aio_context);
return;
}
- bdrv_graph_wrlock(bs);
+ bdrv_graph_wrlock();
bdrv_ref(hidden_disk->bs);
s->hidden_disk = bdrv_attach_child(bs, hidden_disk->bs, "hidden disk",
@@ -568,8 +549,7 @@
&local_err);
if (local_err) {
error_propagate(errp, local_err);
- bdrv_graph_wrunlock(bs);
- aio_context_release(aio_context);
+ bdrv_graph_wrunlock();
return;
}
@@ -579,8 +559,7 @@
BDRV_CHILD_DATA, &local_err);
if (local_err) {
error_propagate(errp, local_err);
- bdrv_graph_wrunlock(bs);
- aio_context_release(aio_context);
+ bdrv_graph_wrunlock();
return;
}
@@ -592,15 +571,14 @@
if (!top_bs || !bdrv_is_root_node(top_bs) ||
!check_top_bs(top_bs, bs)) {
error_setg(errp, "No top_bs or it is invalid");
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
reopen_backing_file(bs, false, NULL);
- aio_context_release(aio_context);
return;
}
bdrv_op_block_all(top_bs, s->blocker);
bdrv_op_unblock(top_bs, BLOCK_OP_TYPE_DATAPLANE, s->blocker);
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
s->backup_job = backup_job_create(
NULL, s->secondary_disk->bs, s->hidden_disk->bs,
@@ -612,13 +590,11 @@
if (local_err) {
error_propagate(errp, local_err);
backup_job_cleanup(bs);
- aio_context_release(aio_context);
return;
}
job_start(&s->backup_job->job);
break;
default:
- aio_context_release(aio_context);
abort();
}
@@ -629,18 +605,12 @@
}
s->error = 0;
- aio_context_release(aio_context);
}
static void replication_do_checkpoint(ReplicationState *rs, Error **errp)
{
BlockDriverState *bs = rs->opaque;
- BDRVReplicationState *s;
- AioContext *aio_context;
-
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
- s = bs->opaque;
+ BDRVReplicationState *s = bs->opaque;
if (s->stage == BLOCK_REPLICATION_DONE ||
s->stage == BLOCK_REPLICATION_FAILOVER) {
@@ -649,38 +619,28 @@
* Ignore the request because the secondary side of replication
* doesn't have to do anything anymore.
*/
- aio_context_release(aio_context);
return;
}
if (s->mode == REPLICATION_MODE_SECONDARY) {
secondary_do_checkpoint(bs, errp);
}
- aio_context_release(aio_context);
}
static void replication_get_error(ReplicationState *rs, Error **errp)
{
BlockDriverState *bs = rs->opaque;
- BDRVReplicationState *s;
- AioContext *aio_context;
-
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
- s = bs->opaque;
+ BDRVReplicationState *s = bs->opaque;
if (s->stage == BLOCK_REPLICATION_NONE) {
error_setg(errp, "Block replication is not running");
- aio_context_release(aio_context);
return;
}
if (s->error) {
error_setg(errp, "I/O error occurred");
- aio_context_release(aio_context);
return;
}
- aio_context_release(aio_context);
}
static void replication_done(void *opaque, int ret)
@@ -691,12 +651,12 @@
if (ret == 0) {
s->stage = BLOCK_REPLICATION_DONE;
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, s->secondary_disk);
s->secondary_disk = NULL;
bdrv_unref_child(bs, s->hidden_disk);
s->hidden_disk = NULL;
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
s->error = 0;
} else {
@@ -708,12 +668,7 @@
static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
{
BlockDriverState *bs = rs->opaque;
- BDRVReplicationState *s;
- AioContext *aio_context;
-
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
- s = bs->opaque;
+ BDRVReplicationState *s = bs->opaque;
if (s->stage == BLOCK_REPLICATION_DONE ||
s->stage == BLOCK_REPLICATION_FAILOVER) {
@@ -722,13 +677,11 @@
* Ignore the request because the secondary side of replication
* doesn't have to do anything anymore.
*/
- aio_context_release(aio_context);
return;
}
if (s->stage != BLOCK_REPLICATION_RUNNING) {
error_setg(errp, "Block replication is not running");
- aio_context_release(aio_context);
return;
}
@@ -744,15 +697,12 @@
* disk, secondary disk in backup_job_completed().
*/
if (s->backup_job) {
- aio_context_release(aio_context);
job_cancel_sync(&s->backup_job->job, true);
- aio_context_acquire(aio_context);
}
if (!failover) {
secondary_do_checkpoint(bs, errp);
s->stage = BLOCK_REPLICATION_DONE;
- aio_context_release(aio_context);
return;
}
@@ -765,10 +715,8 @@
bdrv_graph_rdunlock_main_loop();
break;
default:
- aio_context_release(aio_context);
abort();
}
- aio_context_release(aio_context);
}
static const char *const replication_strong_runtime_opts[] = {
diff --git a/block/snapshot.c b/block/snapshot.c
index ec8cf48..8694fc0 100644
--- a/block/snapshot.c
+++ b/block/snapshot.c
@@ -196,8 +196,10 @@
int bdrv_can_snapshot(BlockDriverState *bs)
{
BlockDriver *drv = bs->drv;
+
GLOBAL_STATE_CODE();
- if (!drv || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
+
+ if (!drv || !bdrv_is_inserted(bs) || !bdrv_is_writable(bs)) {
return 0;
}
@@ -290,9 +292,9 @@
}
/* .bdrv_open() will re-attach it */
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, fallback);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
ret = bdrv_snapshot_goto(fallback_bs, snapshot_id, errp);
open_ret = drv->bdrv_open(bs, options, bs->open_flags, &local_err);
@@ -525,9 +527,7 @@
return bdrv_has_blk(bs) || QLIST_EMPTY(&bs->parents);
}
-/* Group operations. All block drivers are involved.
- * These functions will properly handle dataplane (take aio_context_acquire
- * when appropriate for appropriate block drivers) */
+/* Group operations. All block drivers are involved. */
bool bdrv_all_can_snapshot(bool has_devices, strList *devices,
Error **errp)
@@ -545,14 +545,11 @@
iterbdrvs = bdrvs;
while (iterbdrvs) {
BlockDriverState *bs = iterbdrvs->data;
- AioContext *ctx = bdrv_get_aio_context(bs);
bool ok = true;
- aio_context_acquire(ctx);
if (devices || bdrv_all_snapshots_includes_bs(bs)) {
ok = bdrv_can_snapshot(bs);
}
- aio_context_release(ctx);
if (!ok) {
error_setg(errp, "Device '%s' is writable but does not support "
"snapshots", bdrv_get_device_or_node_name(bs));
@@ -582,18 +579,15 @@
iterbdrvs = bdrvs;
while (iterbdrvs) {
BlockDriverState *bs = iterbdrvs->data;
- AioContext *ctx = bdrv_get_aio_context(bs);
QEMUSnapshotInfo sn1, *snapshot = &sn1;
int ret = 0;
- aio_context_acquire(ctx);
if ((devices || bdrv_all_snapshots_includes_bs(bs)) &&
bdrv_snapshot_find(bs, snapshot, name) >= 0)
{
ret = bdrv_snapshot_delete(bs, snapshot->id_str,
snapshot->name, errp);
}
- aio_context_release(ctx);
if (ret < 0) {
error_prepend(errp, "Could not delete snapshot '%s' on '%s': ",
name, bdrv_get_device_or_node_name(bs));
@@ -628,17 +622,14 @@
iterbdrvs = bdrvs;
while (iterbdrvs) {
BlockDriverState *bs = iterbdrvs->data;
- AioContext *ctx = bdrv_get_aio_context(bs);
bool all_snapshots_includes_bs;
- aio_context_acquire(ctx);
bdrv_graph_rdlock_main_loop();
all_snapshots_includes_bs = bdrv_all_snapshots_includes_bs(bs);
bdrv_graph_rdunlock_main_loop();
ret = (devices || all_snapshots_includes_bs) ?
bdrv_snapshot_goto(bs, name, errp) : 0;
- aio_context_release(ctx);
if (ret < 0) {
bdrv_graph_rdlock_main_loop();
error_prepend(errp, "Could not load snapshot '%s' on '%s': ",
@@ -670,15 +661,12 @@
iterbdrvs = bdrvs;
while (iterbdrvs) {
BlockDriverState *bs = iterbdrvs->data;
- AioContext *ctx = bdrv_get_aio_context(bs);
QEMUSnapshotInfo sn;
int ret = 0;
- aio_context_acquire(ctx);
if (devices || bdrv_all_snapshots_includes_bs(bs)) {
ret = bdrv_snapshot_find(bs, &sn, name);
}
- aio_context_release(ctx);
if (ret < 0) {
if (ret == -ENOENT) {
return 0;
@@ -715,10 +703,8 @@
iterbdrvs = bdrvs;
while (iterbdrvs) {
BlockDriverState *bs = iterbdrvs->data;
- AioContext *ctx = bdrv_get_aio_context(bs);
int ret = 0;
- aio_context_acquire(ctx);
if (bs == vm_state_bs) {
sn->vm_state_size = vm_state_size;
ret = bdrv_snapshot_create(bs, sn);
@@ -726,7 +712,6 @@
sn->vm_state_size = 0;
ret = bdrv_snapshot_create(bs, sn);
}
- aio_context_release(ctx);
if (ret < 0) {
error_setg(errp, "Could not create snapshot '%s' on '%s'",
sn->name, bdrv_get_device_or_node_name(bs));
@@ -757,13 +742,10 @@
iterbdrvs = bdrvs;
while (iterbdrvs) {
BlockDriverState *bs = iterbdrvs->data;
- AioContext *ctx = bdrv_get_aio_context(bs);
bool found = false;
- aio_context_acquire(ctx);
found = (devices || bdrv_all_snapshots_includes_bs(bs)) &&
bdrv_can_snapshot(bs);
- aio_context_release(ctx);
if (vmstate_bs) {
if (g_str_equal(vmstate_bs,
diff --git a/block/stream.c b/block/stream.c
index 01fe7c0..048c2d2 100644
--- a/block/stream.c
+++ b/block/stream.c
@@ -99,9 +99,9 @@
}
}
- bdrv_graph_wrlock(s->target_bs);
+ bdrv_graph_wrlock();
bdrv_set_backing_hd_drained(unfiltered_bs, base, &local_err);
- bdrv_graph_wrunlock(s->target_bs);
+ bdrv_graph_wrunlock();
/*
* This call will do I/O, so the graph can change again from here on.
@@ -366,10 +366,10 @@
* already have our own plans. Also don't allow resize as the image size is
* queried only at the job start and then cached.
*/
- bdrv_graph_wrlock(bs);
+ bdrv_graph_wrlock();
if (block_job_add_bdrv(&s->common, "active node", bs, 0,
basic_flags | BLK_PERM_WRITE, errp)) {
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
goto fail;
}
@@ -389,11 +389,11 @@
ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
basic_flags, errp);
if (ret < 0) {
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
goto fail;
}
}
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
s->base_overlay = base_overlay;
s->above_base = above_base;
diff --git a/block/vmdk.c b/block/vmdk.c
index d6971c7..bf78e12 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -272,7 +272,7 @@
BDRVVmdkState *s = bs->opaque;
VmdkExtent *e;
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
for (i = 0; i < s->num_extents; i++) {
e = &s->extents[i];
g_free(e->l1_table);
@@ -283,7 +283,7 @@
bdrv_unref_child(bs, e->file);
}
}
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
g_free(s->extents);
}
@@ -1247,9 +1247,9 @@
0, 0, 0, 0, 0, &extent, errp);
if (ret < 0) {
bdrv_graph_rdunlock_main_loop();
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, extent_file);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
bdrv_graph_rdlock_main_loop();
goto out;
}
@@ -1266,9 +1266,9 @@
g_free(buf);
if (ret) {
bdrv_graph_rdunlock_main_loop();
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, extent_file);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
bdrv_graph_rdlock_main_loop();
goto out;
}
@@ -1277,9 +1277,9 @@
ret = vmdk_open_se_sparse(bs, extent_file, bs->open_flags, errp);
if (ret) {
bdrv_graph_rdunlock_main_loop();
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, extent_file);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
bdrv_graph_rdlock_main_loop();
goto out;
}
@@ -1287,9 +1287,9 @@
} else {
error_setg(errp, "Unsupported extent type '%s'", type);
bdrv_graph_rdunlock_main_loop();
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(bs, extent_file);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
bdrv_graph_rdlock_main_loop();
ret = -ENOTSUP;
goto out;
diff --git a/block/write-threshold.c b/block/write-threshold.c
index 76d8885..56fe88d 100644
--- a/block/write-threshold.c
+++ b/block/write-threshold.c
@@ -33,7 +33,6 @@
Error **errp)
{
BlockDriverState *bs;
- AioContext *aio_context;
bs = bdrv_find_node(node_name);
if (!bs) {
@@ -41,12 +40,7 @@
return;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
-
bdrv_write_threshold_set(bs, threshold_bytes);
-
- aio_context_release(aio_context);
}
void bdrv_write_threshold_check_write(BlockDriverState *bs, int64_t offset,
diff --git a/blockdev.c b/blockdev.c
index c91f49e..3a5e722 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -662,7 +662,6 @@
/* Takes the ownership of bs_opts */
BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp)
{
- BlockDriverState *bs;
int bdrv_flags = 0;
GLOBAL_STATE_CODE();
@@ -677,11 +676,7 @@
bdrv_flags |= BDRV_O_INACTIVE;
}
- aio_context_acquire(qemu_get_aio_context());
- bs = bdrv_open(NULL, NULL, bs_opts, bdrv_flags, errp);
- aio_context_release(qemu_get_aio_context());
-
- return bs;
+ return bdrv_open(NULL, NULL, bs_opts, bdrv_flags, errp);
}
void blockdev_close_all_bdrv_states(void)
@@ -690,11 +685,7 @@
GLOBAL_STATE_CODE();
QTAILQ_FOREACH_SAFE(bs, &monitor_bdrv_states, monitor_list, next_bs) {
- AioContext *ctx = bdrv_get_aio_context(bs);
-
- aio_context_acquire(ctx);
bdrv_unref(bs);
- aio_context_release(ctx);
}
}
@@ -1048,7 +1039,6 @@
static BlockDriverState *qmp_get_root_bs(const char *name, Error **errp)
{
BlockDriverState *bs;
- AioContext *aio_context;
GRAPH_RDLOCK_GUARD_MAINLOOP();
@@ -1062,16 +1052,11 @@
return NULL;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
-
if (!bdrv_is_inserted(bs)) {
error_setg(errp, "Device has no medium");
bs = NULL;
}
- aio_context_release(aio_context);
-
return bs;
}
@@ -1141,7 +1126,6 @@
Error **errp)
{
BlockDriverState *bs;
- AioContext *aio_context;
QEMUSnapshotInfo sn;
Error *local_err = NULL;
SnapshotInfo *info = NULL;
@@ -1154,39 +1138,35 @@
if (!bs) {
return NULL;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
if (!id && !name) {
error_setg(errp, "Name or id must be provided");
- goto out_aio_context;
+ return NULL;
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_INTERNAL_SNAPSHOT_DELETE, errp)) {
- goto out_aio_context;
+ return NULL;
}
ret = bdrv_snapshot_find_by_id_and_name(bs, id, name, &sn, &local_err);
if (local_err) {
error_propagate(errp, local_err);
- goto out_aio_context;
+ return NULL;
}
if (!ret) {
error_setg(errp,
"Snapshot with id '%s' and name '%s' does not exist on "
"device '%s'",
STR_OR_NULL(id), STR_OR_NULL(name), device);
- goto out_aio_context;
+ return NULL;
}
bdrv_snapshot_delete(bs, id, name, &local_err);
if (local_err) {
error_propagate(errp, local_err);
- goto out_aio_context;
+ return NULL;
}
- aio_context_release(aio_context);
-
info = g_new0(SnapshotInfo, 1);
info->id = g_strdup(sn.id_str);
info->name = g_strdup(sn.name);
@@ -1201,10 +1181,6 @@
}
return info;
-
-out_aio_context:
- aio_context_release(aio_context);
- return NULL;
}
/* internal snapshot private data */
@@ -1232,7 +1208,6 @@
bool ret;
int64_t rt;
InternalSnapshotState *state = g_new0(InternalSnapshotState, 1);
- AioContext *aio_context;
int ret1;
GLOBAL_STATE_CODE();
@@ -1248,33 +1223,30 @@
return;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
-
state->bs = bs;
/* Paired with .clean() */
bdrv_drained_begin(bs);
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_INTERNAL_SNAPSHOT, errp)) {
- goto out;
+ return;
}
if (bdrv_is_read_only(bs)) {
error_setg(errp, "Device '%s' is read only", device);
- goto out;
+ return;
}
if (!bdrv_can_snapshot(bs)) {
error_setg(errp, "Block format '%s' used by device '%s' "
"does not support internal snapshots",
bs->drv->format_name, device);
- goto out;
+ return;
}
if (!strlen(name)) {
error_setg(errp, "Name is empty");
- goto out;
+ return;
}
/* check whether a snapshot with name exist */
@@ -1282,12 +1254,12 @@
&local_err);
if (local_err) {
error_propagate(errp, local_err);
- goto out;
+ return;
} else if (ret) {
error_setg(errp,
"Snapshot with name '%s' already exists on device '%s'",
name, device);
- goto out;
+ return;
}
/* 3. take the snapshot */
@@ -1308,14 +1280,11 @@
error_setg_errno(errp, -ret1,
"Failed to create snapshot '%s' on device '%s'",
name, device);
- goto out;
+ return;
}
/* 4. succeed, mark a snapshot is created */
state->created = true;
-
-out:
- aio_context_release(aio_context);
}
static void internal_snapshot_abort(void *opaque)
@@ -1323,7 +1292,6 @@
InternalSnapshotState *state = opaque;
BlockDriverState *bs = state->bs;
QEMUSnapshotInfo *sn = &state->sn;
- AioContext *aio_context;
Error *local_error = NULL;
GLOBAL_STATE_CODE();
@@ -1333,9 +1301,6 @@
return;
}
- aio_context = bdrv_get_aio_context(state->bs);
- aio_context_acquire(aio_context);
-
if (bdrv_snapshot_delete(bs, sn->id_str, sn->name, &local_error) < 0) {
error_reportf_err(local_error,
"Failed to delete snapshot with id '%s' and "
@@ -1343,25 +1308,17 @@
sn->id_str, sn->name,
bdrv_get_device_name(bs));
}
-
- aio_context_release(aio_context);
}
static void internal_snapshot_clean(void *opaque)
{
g_autofree InternalSnapshotState *state = opaque;
- AioContext *aio_context;
if (!state->bs) {
return;
}
- aio_context = bdrv_get_aio_context(state->bs);
- aio_context_acquire(aio_context);
-
bdrv_drained_end(state->bs);
-
- aio_context_release(aio_context);
}
/* external snapshot private data */
@@ -1395,7 +1352,6 @@
/* File name of the new image (for 'blockdev-snapshot-sync') */
const char *new_image_file;
ExternalSnapshotState *state = g_new0(ExternalSnapshotState, 1);
- AioContext *aio_context;
uint64_t perm, shared;
/* TODO We'll eventually have to take a writer lock in this function */
@@ -1435,26 +1391,23 @@
return;
}
- aio_context = bdrv_get_aio_context(state->old_bs);
- aio_context_acquire(aio_context);
-
/* Paired with .clean() */
bdrv_drained_begin(state->old_bs);
if (!bdrv_is_inserted(state->old_bs)) {
error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
- goto out;
+ return;
}
if (bdrv_op_is_blocked(state->old_bs,
BLOCK_OP_TYPE_EXTERNAL_SNAPSHOT, errp)) {
- goto out;
+ return;
}
if (!bdrv_is_read_only(state->old_bs)) {
if (bdrv_flush(state->old_bs)) {
error_setg(errp, QERR_IO_ERROR);
- goto out;
+ return;
}
}
@@ -1466,13 +1419,13 @@
if (node_name && !snapshot_node_name) {
error_setg(errp, "New overlay node-name missing");
- goto out;
+ return;
}
if (snapshot_node_name &&
bdrv_lookup_bs(snapshot_node_name, snapshot_node_name, NULL)) {
error_setg(errp, "New overlay node-name already in use");
- goto out;
+ return;
}
flags = state->old_bs->open_flags;
@@ -1485,20 +1438,18 @@
int64_t size = bdrv_getlength(state->old_bs);
if (size < 0) {
error_setg_errno(errp, -size, "bdrv_getlength failed");
- goto out;
+ return;
}
bdrv_refresh_filename(state->old_bs);
- aio_context_release(aio_context);
bdrv_img_create(new_image_file, format,
state->old_bs->filename,
state->old_bs->drv->format_name,
NULL, size, flags, false, &local_err);
- aio_context_acquire(aio_context);
if (local_err) {
error_propagate(errp, local_err);
- goto out;
+ return;
}
}
@@ -1508,20 +1459,15 @@
}
qdict_put_str(options, "driver", format);
}
- aio_context_release(aio_context);
- aio_context_acquire(qemu_get_aio_context());
state->new_bs = bdrv_open(new_image_file, snapshot_ref, options, flags,
errp);
- aio_context_release(qemu_get_aio_context());
/* We will manually add the backing_hd field to the bs later */
if (!state->new_bs) {
return;
}
- aio_context_acquire(aio_context);
-
/*
* Allow attaching a backing file to an overlay that's already in use only
* if the parents don't assume that they are already seeing a valid image.
@@ -1530,41 +1476,34 @@
bdrv_get_cumulative_perm(state->new_bs, &perm, &shared);
if (perm & BLK_PERM_CONSISTENT_READ) {
error_setg(errp, "The overlay is already in use");
- goto out;
+ return;
}
if (state->new_bs->drv->is_filter) {
error_setg(errp, "Filters cannot be used as overlays");
- goto out;
+ return;
}
if (bdrv_cow_child(state->new_bs)) {
error_setg(errp, "The overlay already has a backing image");
- goto out;
+ return;
}
if (!state->new_bs->drv->supports_backing) {
error_setg(errp, "The overlay does not support backing images");
- goto out;
+ return;
}
ret = bdrv_append(state->new_bs, state->old_bs, errp);
if (ret < 0) {
- goto out;
+ return;
}
state->overlay_appended = true;
-
-out:
- aio_context_release(aio_context);
}
static void external_snapshot_commit(void *opaque)
{
ExternalSnapshotState *state = opaque;
- AioContext *aio_context;
-
- aio_context = bdrv_get_aio_context(state->old_bs);
- aio_context_acquire(aio_context);
/* We don't need (or want) to use the transactional
* bdrv_reopen_multiple() across all the entries at once, because we
@@ -1572,8 +1511,6 @@
if (!qatomic_read(&state->old_bs->copy_on_read)) {
bdrv_reopen_set_read_only(state->old_bs, true, NULL);
}
-
- aio_context_release(aio_context);
}
static void external_snapshot_abort(void *opaque)
@@ -1586,7 +1523,6 @@
int ret;
aio_context = bdrv_get_aio_context(state->old_bs);
- aio_context_acquire(aio_context);
bdrv_ref(state->old_bs); /* we can't let bdrv_set_backind_hd()
close state->old_bs; we need it */
@@ -1599,26 +1535,18 @@
*/
tmp_context = bdrv_get_aio_context(state->old_bs);
if (aio_context != tmp_context) {
- aio_context_release(aio_context);
- aio_context_acquire(tmp_context);
-
ret = bdrv_try_change_aio_context(state->old_bs,
aio_context, NULL, NULL);
assert(ret == 0);
-
- aio_context_release(tmp_context);
- aio_context_acquire(aio_context);
}
bdrv_drained_begin(state->new_bs);
- bdrv_graph_wrlock(state->old_bs);
+ bdrv_graph_wrlock();
bdrv_replace_node(state->new_bs, state->old_bs, &error_abort);
- bdrv_graph_wrunlock(state->old_bs);
+ bdrv_graph_wrunlock();
bdrv_drained_end(state->new_bs);
bdrv_unref(state->old_bs); /* bdrv_replace_node() ref'ed old_bs */
-
- aio_context_release(aio_context);
}
}
}
@@ -1626,19 +1554,13 @@
static void external_snapshot_clean(void *opaque)
{
g_autofree ExternalSnapshotState *state = opaque;
- AioContext *aio_context;
if (!state->old_bs) {
return;
}
- aio_context = bdrv_get_aio_context(state->old_bs);
- aio_context_acquire(aio_context);
-
bdrv_drained_end(state->old_bs);
bdrv_unref(state->new_bs);
-
- aio_context_release(aio_context);
}
typedef struct DriveBackupState {
@@ -1670,7 +1592,6 @@
BlockDriverState *target_bs;
BlockDriverState *source = NULL;
AioContext *aio_context;
- AioContext *old_context;
const char *format;
QDict *options;
Error *local_err = NULL;
@@ -1698,7 +1619,6 @@
}
aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
state->bs = bs;
/* Paired with .clean() */
@@ -1713,7 +1633,7 @@
bdrv_graph_rdlock_main_loop();
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
bdrv_graph_rdunlock_main_loop();
- goto out;
+ return;
}
flags = bs->open_flags | BDRV_O_RDWR;
@@ -1744,7 +1664,7 @@
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "bdrv_getlength failed");
- goto out;
+ return;
}
if (backup->mode != NEW_IMAGE_MODE_EXISTING) {
@@ -1770,7 +1690,7 @@
if (local_err) {
error_propagate(errp, local_err);
- goto out;
+ return;
}
options = qdict_new();
@@ -1779,30 +1699,18 @@
if (format) {
qdict_put_str(options, "driver", format);
}
- aio_context_release(aio_context);
- aio_context_acquire(qemu_get_aio_context());
target_bs = bdrv_open(backup->target, NULL, options, flags, errp);
- aio_context_release(qemu_get_aio_context());
-
if (!target_bs) {
return;
}
- /* Honor bdrv_try_change_aio_context() context acquisition requirements. */
- old_context = bdrv_get_aio_context(target_bs);
- aio_context_acquire(old_context);
-
ret = bdrv_try_change_aio_context(target_bs, aio_context, NULL, errp);
if (ret < 0) {
bdrv_unref(target_bs);
- aio_context_release(old_context);
return;
}
- aio_context_release(old_context);
- aio_context_acquire(aio_context);
-
if (set_backing_hd) {
if (bdrv_set_backing_hd(target_bs, source, errp) < 0) {
goto unref;
@@ -1815,22 +1723,14 @@
unref:
bdrv_unref(target_bs);
-out:
- aio_context_release(aio_context);
}
static void drive_backup_commit(void *opaque)
{
DriveBackupState *state = opaque;
- AioContext *aio_context;
-
- aio_context = bdrv_get_aio_context(state->bs);
- aio_context_acquire(aio_context);
assert(state->job);
job_start(&state->job->job);
-
- aio_context_release(aio_context);
}
static void drive_backup_abort(void *opaque)
@@ -1845,18 +1745,12 @@
static void drive_backup_clean(void *opaque)
{
g_autofree DriveBackupState *state = opaque;
- AioContext *aio_context;
if (!state->bs) {
return;
}
- aio_context = bdrv_get_aio_context(state->bs);
- aio_context_acquire(aio_context);
-
bdrv_drained_end(state->bs);
-
- aio_context_release(aio_context);
}
typedef struct BlockdevBackupState {
@@ -1881,7 +1775,6 @@
BlockDriverState *bs;
BlockDriverState *target_bs;
AioContext *aio_context;
- AioContext *old_context;
int ret;
tran_add(tran, &blockdev_backup_drv, state);
@@ -1898,17 +1791,12 @@
/* Honor bdrv_try_change_aio_context() context acquisition requirements. */
aio_context = bdrv_get_aio_context(bs);
- old_context = bdrv_get_aio_context(target_bs);
- aio_context_acquire(old_context);
ret = bdrv_try_change_aio_context(target_bs, aio_context, NULL, errp);
if (ret < 0) {
- aio_context_release(old_context);
return;
}
- aio_context_release(old_context);
- aio_context_acquire(aio_context);
state->bs = bs;
/* Paired with .clean() */
@@ -1917,22 +1805,14 @@
state->job = do_backup_common(qapi_BlockdevBackup_base(backup),
bs, target_bs, aio_context,
block_job_txn, errp);
-
- aio_context_release(aio_context);
}
static void blockdev_backup_commit(void *opaque)
{
BlockdevBackupState *state = opaque;
- AioContext *aio_context;
-
- aio_context = bdrv_get_aio_context(state->bs);
- aio_context_acquire(aio_context);
assert(state->job);
job_start(&state->job->job);
-
- aio_context_release(aio_context);
}
static void blockdev_backup_abort(void *opaque)
@@ -1947,18 +1827,12 @@
static void blockdev_backup_clean(void *opaque)
{
g_autofree BlockdevBackupState *state = opaque;
- AioContext *aio_context;
if (!state->bs) {
return;
}
- aio_context = bdrv_get_aio_context(state->bs);
- aio_context_acquire(aio_context);
-
bdrv_drained_end(state->bs);
-
- aio_context_release(aio_context);
}
typedef struct BlockDirtyBitmapState {
@@ -2390,18 +2264,13 @@
return;
}
- bdrv_co_lock(bs);
bdrv_drained_begin(bs);
- bdrv_co_unlock(bs);
old_ctx = bdrv_co_enter(bs);
blk_co_truncate(blk, size, false, PREALLOC_MODE_OFF, 0, errp);
bdrv_co_leave(bs, old_ctx);
- bdrv_co_lock(bs);
bdrv_drained_end(bs);
- bdrv_co_unlock(bs);
-
blk_co_unref(blk);
}
@@ -2454,7 +2323,6 @@
}
aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
bdrv_graph_rdlock_main_loop();
if (base) {
@@ -2521,7 +2389,7 @@
if (!base_bs && backing_file) {
error_setg(errp, "backing file specified, but streaming the "
"entire chain");
- goto out;
+ return;
}
if (has_auto_finalize && !auto_finalize) {
@@ -2536,18 +2404,14 @@
filter_node_name, &local_err);
if (local_err) {
error_propagate(errp, local_err);
- goto out;
+ return;
}
trace_qmp_block_stream(bs);
-
-out:
- aio_context_release(aio_context);
return;
out_rdlock:
bdrv_graph_rdunlock_main_loop();
- aio_context_release(aio_context);
}
void qmp_block_commit(const char *job_id, const char *device,
@@ -2606,10 +2470,9 @@
}
aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, errp)) {
- goto out;
+ return;
}
/* default top_bs is the active layer */
@@ -2617,16 +2480,16 @@
if (top_node && top) {
error_setg(errp, "'top-node' and 'top' are mutually exclusive");
- goto out;
+ return;
} else if (top_node) {
top_bs = bdrv_lookup_bs(NULL, top_node, errp);
if (top_bs == NULL) {
- goto out;
+ return;
}
if (!bdrv_chain_contains(bs, top_bs)) {
error_setg(errp, "'%s' is not in this backing file chain",
top_node);
- goto out;
+ return;
}
} else if (top) {
/* This strcmp() is just a shortcut, there is no need to
@@ -2640,35 +2503,35 @@
if (top_bs == NULL) {
error_setg(errp, "Top image file %s not found", top ? top : "NULL");
- goto out;
+ return;
}
assert(bdrv_get_aio_context(top_bs) == aio_context);
if (base_node && base) {
error_setg(errp, "'base-node' and 'base' are mutually exclusive");
- goto out;
+ return;
} else if (base_node) {
base_bs = bdrv_lookup_bs(NULL, base_node, errp);
if (base_bs == NULL) {
- goto out;
+ return;
}
if (!bdrv_chain_contains(top_bs, base_bs)) {
error_setg(errp, "'%s' is not in this backing file chain",
base_node);
- goto out;
+ return;
}
} else if (base) {
base_bs = bdrv_find_backing_image(top_bs, base);
if (base_bs == NULL) {
error_setg(errp, "Can't find '%s' in the backing chain", base);
- goto out;
+ return;
}
} else {
base_bs = bdrv_find_base(top_bs);
if (base_bs == NULL) {
error_setg(errp, "There is no backimg image");
- goto out;
+ return;
}
}
@@ -2678,14 +2541,14 @@
iter = bdrv_filter_or_cow_bs(iter))
{
if (bdrv_op_is_blocked(iter, BLOCK_OP_TYPE_COMMIT_TARGET, errp)) {
- goto out;
+ return;
}
}
/* Do not allow attempts to commit an image into itself */
if (top_bs == base_bs) {
error_setg(errp, "cannot commit an image into itself");
- goto out;
+ return;
}
/*
@@ -2708,7 +2571,7 @@
error_setg(errp, "'backing-file' specified, but 'top' has a "
"writer on it");
}
- goto out;
+ return;
}
if (!job_id) {
/*
@@ -2724,7 +2587,7 @@
} else {
BlockDriverState *overlay_bs = bdrv_find_overlay(bs, top_bs);
if (bdrv_op_is_blocked(overlay_bs, BLOCK_OP_TYPE_COMMIT_TARGET, errp)) {
- goto out;
+ return;
}
commit_start(job_id, bs, base_bs, top_bs, job_flags,
speed, on_error, backing_file,
@@ -2732,11 +2595,8 @@
}
if (local_err != NULL) {
error_propagate(errp, local_err);
- goto out;
+ return;
}
-
-out:
- aio_context_release(aio_context);
}
/* Common QMP interface for drive-backup and blockdev-backup */
@@ -2985,8 +2845,6 @@
if (replaces) {
BlockDriverState *to_replace_bs;
- AioContext *aio_context;
- AioContext *replace_aio_context;
int64_t bs_size, replace_size;
bs_size = bdrv_getlength(bs);
@@ -3000,19 +2858,7 @@
return;
}
- aio_context = bdrv_get_aio_context(bs);
- replace_aio_context = bdrv_get_aio_context(to_replace_bs);
- /*
- * bdrv_getlength() is a co-wrapper and uses AIO_WAIT_WHILE. Be sure not
- * to acquire the same AioContext twice.
- */
- if (replace_aio_context != aio_context) {
- aio_context_acquire(replace_aio_context);
- }
replace_size = bdrv_getlength(to_replace_bs);
- if (replace_aio_context != aio_context) {
- aio_context_release(replace_aio_context);
- }
if (replace_size < 0) {
error_setg_errno(errp, -replace_size,
@@ -3041,7 +2887,6 @@
BlockDriverState *bs;
BlockDriverState *target_backing_bs, *target_bs;
AioContext *aio_context;
- AioContext *old_context;
BlockMirrorBackingMode backing_mode;
Error *local_err = NULL;
QDict *options = NULL;
@@ -3064,7 +2909,6 @@
}
aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
if (!arg->has_mode) {
arg->mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;
@@ -3088,14 +2932,14 @@
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "bdrv_getlength failed");
- goto out;
+ return;
}
if (arg->replaces) {
if (!arg->node_name) {
error_setg(errp, "a node-name must be provided when replacing a"
" named node of the graph");
- goto out;
+ return;
}
}
@@ -3143,7 +2987,7 @@
if (local_err) {
error_propagate(errp, local_err);
- goto out;
+ return;
}
options = qdict_new();
@@ -3153,15 +2997,11 @@
if (format) {
qdict_put_str(options, "driver", format);
}
- aio_context_release(aio_context);
/* Mirroring takes care of copy-on-write using the source's backing
* file.
*/
- aio_context_acquire(qemu_get_aio_context());
target_bs = bdrv_open(arg->target, NULL, options, flags, errp);
- aio_context_release(qemu_get_aio_context());
-
if (!target_bs) {
return;
}
@@ -3173,20 +3013,12 @@
bdrv_graph_rdunlock_main_loop();
- /* Honor bdrv_try_change_aio_context() context acquisition requirements. */
- old_context = bdrv_get_aio_context(target_bs);
- aio_context_acquire(old_context);
-
ret = bdrv_try_change_aio_context(target_bs, aio_context, NULL, errp);
if (ret < 0) {
bdrv_unref(target_bs);
- aio_context_release(old_context);
return;
}
- aio_context_release(old_context);
- aio_context_acquire(aio_context);
-
blockdev_mirror_common(arg->job_id, bs, target_bs,
arg->replaces, arg->sync,
backing_mode, zero_target,
@@ -3202,8 +3034,6 @@
arg->has_auto_dismiss, arg->auto_dismiss,
errp);
bdrv_unref(target_bs);
-out:
- aio_context_release(aio_context);
}
void qmp_blockdev_mirror(const char *job_id,
@@ -3226,7 +3056,6 @@
BlockDriverState *bs;
BlockDriverState *target_bs;
AioContext *aio_context;
- AioContext *old_context;
BlockMirrorBackingMode backing_mode = MIRROR_LEAVE_BACKING_CHAIN;
bool zero_target;
int ret;
@@ -3243,18 +3072,11 @@
zero_target = (sync == MIRROR_SYNC_MODE_FULL);
- /* Honor bdrv_try_change_aio_context() context acquisition requirements. */
- old_context = bdrv_get_aio_context(target_bs);
aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(old_context);
ret = bdrv_try_change_aio_context(target_bs, aio_context, NULL, errp);
-
- aio_context_release(old_context);
- aio_context_acquire(aio_context);
-
if (ret < 0) {
- goto out;
+ return;
}
blockdev_mirror_common(job_id, bs, target_bs,
@@ -3269,8 +3091,6 @@
has_auto_finalize, auto_finalize,
has_auto_dismiss, auto_dismiss,
errp);
-out:
- aio_context_release(aio_context);
}
/*
@@ -3433,7 +3253,6 @@
Error **errp)
{
BlockDriverState *bs = NULL;
- AioContext *aio_context;
BlockDriverState *image_bs = NULL;
Error *local_err = NULL;
bool ro;
@@ -3444,9 +3263,6 @@
return;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
-
bdrv_graph_rdlock_main_loop();
image_bs = bdrv_lookup_bs(NULL, image_node_name, &local_err);
@@ -3485,7 +3301,7 @@
if (ro) {
if (bdrv_reopen_set_read_only(image_bs, false, errp) != 0) {
- goto out;
+ return;
}
}
@@ -3503,14 +3319,10 @@
if (ro) {
bdrv_reopen_set_read_only(image_bs, true, errp);
}
-
-out:
- aio_context_release(aio_context);
return;
out_rdlock:
bdrv_graph_rdunlock_main_loop();
- aio_context_release(aio_context);
}
void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
@@ -3550,7 +3362,6 @@
for (; reopen_list != NULL; reopen_list = reopen_list->next) {
BlockdevOptions *options = reopen_list->value;
BlockDriverState *bs;
- AioContext *ctx;
QObject *obj;
Visitor *v;
QDict *qdict;
@@ -3578,12 +3389,7 @@
qdict_flatten(qdict);
- ctx = bdrv_get_aio_context(bs);
- aio_context_acquire(ctx);
-
queue = bdrv_reopen_queue(queue, bs, qdict, false);
-
- aio_context_release(ctx);
}
/* Perform the reopen operation */
@@ -3596,7 +3402,6 @@
void qmp_blockdev_del(const char *node_name, Error **errp)
{
- AioContext *aio_context;
BlockDriverState *bs;
GLOBAL_STATE_CODE();
@@ -3611,30 +3416,25 @@
error_setg(errp, "Node %s is in use", node_name);
return;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_DRIVE_DEL, errp)) {
- goto out;
+ return;
}
if (!QTAILQ_IN_USE(bs, monitor_list)) {
error_setg(errp, "Node %s is not owned by the monitor",
bs->node_name);
- goto out;
+ return;
}
if (bs->refcnt > 1) {
error_setg(errp, "Block device %s is in use",
bdrv_get_device_or_node_name(bs));
- goto out;
+ return;
}
QTAILQ_REMOVE(&monitor_bdrv_states, bs, monitor_list);
bdrv_unref(bs);
-
-out:
- aio_context_release(aio_context);
}
static BdrvChild * GRAPH_RDLOCK
@@ -3657,7 +3457,7 @@
BlockDriverState *parent_bs, *new_bs = NULL;
BdrvChild *p_child;
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
parent_bs = bdrv_lookup_bs(parent, parent, errp);
if (!parent_bs) {
@@ -3693,7 +3493,7 @@
}
out:
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
}
BlockJobInfoList *qmp_query_block_jobs(Error **errp)
@@ -3724,7 +3524,6 @@
void qmp_x_blockdev_set_iothread(const char *node_name, StrOrNull *iothread,
bool has_force, bool force, Error **errp)
{
- AioContext *old_context;
AioContext *new_context;
BlockDriverState *bs;
@@ -3756,12 +3555,7 @@
new_context = qemu_get_aio_context();
}
- old_context = bdrv_get_aio_context(bs);
- aio_context_acquire(old_context);
-
bdrv_try_change_aio_context(bs, new_context, NULL, errp);
-
- aio_context_release(old_context);
}
QemuOptsList qemu_common_drive_opts = {
diff --git a/blockjob.c b/blockjob.c
index b7a2905..d5f29e1 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -198,9 +198,7 @@
* one to make sure that such a concurrent access does not attempt
* to process an already freed BdrvChild.
*/
- aio_context_release(job->job.aio_context);
- bdrv_graph_wrlock(NULL);
- aio_context_acquire(job->job.aio_context);
+ bdrv_graph_wrlock();
while (job->nodes) {
GSList *l = job->nodes;
BdrvChild *c = l->data;
@@ -212,7 +210,7 @@
g_slist_free_1(l);
}
- bdrv_graph_wrunlock_ctx(job->job.aio_context);
+ bdrv_graph_wrunlock();
}
bool block_job_has_bdrv(BlockJob *job, BlockDriverState *bs)
@@ -234,28 +232,12 @@
uint64_t perm, uint64_t shared_perm, Error **errp)
{
BdrvChild *c;
- AioContext *ctx = bdrv_get_aio_context(bs);
- bool need_context_ops;
GLOBAL_STATE_CODE();
bdrv_ref(bs);
- need_context_ops = ctx != job->job.aio_context;
-
- if (need_context_ops) {
- if (job->job.aio_context != qemu_get_aio_context()) {
- aio_context_release(job->job.aio_context);
- }
- aio_context_acquire(ctx);
- }
c = bdrv_root_attach_child(bs, name, &child_job, 0, perm, shared_perm, job,
errp);
- if (need_context_ops) {
- aio_context_release(ctx);
- if (job->job.aio_context != qemu_get_aio_context()) {
- aio_context_acquire(job->job.aio_context);
- }
- }
if (c == NULL) {
return -EPERM;
}
@@ -514,7 +496,7 @@
int ret;
GLOBAL_STATE_CODE();
- bdrv_graph_wrlock(bs);
+ bdrv_graph_wrlock();
if (job_id == NULL && !(flags & JOB_INTERNAL)) {
job_id = bdrv_get_device_name(bs);
@@ -523,7 +505,7 @@
job = job_create(job_id, &driver->job_driver, txn, bdrv_get_aio_context(bs),
flags, cb, opaque, errp);
if (job == NULL) {
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
return NULL;
}
@@ -563,11 +545,11 @@
goto fail;
}
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
return job;
fail:
- bdrv_graph_wrunlock(bs);
+ bdrv_graph_wrunlock();
job_early_fail(&job->job);
return NULL;
}
diff --git a/docs/devel/multiple-iothreads.txt b/docs/devel/multiple-iothreads.txt
index a3e949f..4865196 100644
--- a/docs/devel/multiple-iothreads.txt
+++ b/docs/devel/multiple-iothreads.txt
@@ -88,27 +88,18 @@
How to synchronize with an IOThread
-----------------------------------
-AioContext is not thread-safe so some rules must be followed when using file
-descriptors, event notifiers, timers, or BHs across threads:
+Variables that can be accessed by multiple threads require some form of
+synchronization such as qemu_mutex_lock(), rcu_read_lock(), etc.
-1. AioContext functions can always be called safely. They handle their
-own locking internally.
-
-2. Other threads wishing to access the AioContext must use
-aio_context_acquire()/aio_context_release() for mutual exclusion. Once the
-context is acquired no other thread can access it or run event loop iterations
-in this AioContext.
-
-Legacy code sometimes nests aio_context_acquire()/aio_context_release() calls.
-Do not use nesting anymore, it is incompatible with the BDRV_POLL_WHILE() macro
-used in the block layer and can lead to hangs.
-
-There is currently no lock ordering rule if a thread needs to acquire multiple
-AioContexts simultaneously. Therefore, it is only safe for code holding the
-QEMU global mutex to acquire other AioContexts.
+AioContext functions like aio_set_fd_handler(), aio_set_event_notifier(),
+aio_bh_new(), and aio_timer_new() are thread-safe. They can be used to trigger
+activity in an IOThread.
Side note: the best way to schedule a function call across threads is to call
-aio_bh_schedule_oneshot(). No acquire/release or locking is needed.
+aio_bh_schedule_oneshot().
+
+The main loop thread can wait synchronously for a condition using
+AIO_WAIT_WHILE().
AioContext and the block layer
------------------------------
@@ -124,22 +115,16 @@
old APIs that implicitly use the main loop. See the "How to program for
IOThreads" above for information on how to do that.
-If main loop code such as a QMP function wishes to access a BlockDriverState
-it must first call aio_context_acquire(bdrv_get_aio_context(bs)) to ensure
-that callbacks in the IOThread do not run in parallel.
-
Code running in the monitor typically needs to ensure that past
requests from the guest are completed. When a block device is running
in an IOThread, the IOThread can also process requests from the guest
(via ioeventfd). To achieve both objects, wrap the code between
bdrv_drained_begin() and bdrv_drained_end(), thus creating a "drained
-section". The functions must be called between aio_context_acquire()
-and aio_context_release(). You can freely release and re-acquire the
-AioContext within a drained section.
+section".
-Long-running jobs (usually in the form of coroutines) are best scheduled in
-the BlockDriverState's AioContext to avoid the need to acquire/release around
-each bdrv_*() call. The functions bdrv_add/remove_aio_context_notifier,
-or alternatively blk_add/remove_aio_context_notifier if you use BlockBackends,
-can be used to get a notification whenever bdrv_try_change_aio_context() moves a
+Long-running jobs (usually in the form of coroutines) are often scheduled in
+the BlockDriverState's AioContext. The functions
+bdrv_add/remove_aio_context_notifier, or alternatively
+blk_add/remove_aio_context_notifier if you use BlockBackends, can be used to
+get a notification whenever bdrv_try_change_aio_context() moves a
BlockDriverState to a different AioContext.
diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index f83bb0f..6debd44 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -32,13 +32,11 @@
VirtIOBlkConf *conf;
VirtIODevice *vdev;
- /* Note that these EventNotifiers are assigned by value. This is
- * fine as long as you do not call event_notifier_cleanup on them
- * (because you don't own the file descriptor or handle; you just
- * use it).
+ /*
+ * The AioContext for each virtqueue. The BlockDriverState will use the
+ * first element as its AioContext.
*/
- IOThread *iothread;
- AioContext *ctx;
+ AioContext **vq_aio_context;
};
/* Raise an interrupt to signal guest, if necessary */
@@ -47,6 +45,45 @@
virtio_notify_irqfd(s->vdev, vq);
}
+/* Generate vq:AioContext mappings from a validated iothread-vq-mapping list */
+static void
+apply_vq_mapping(IOThreadVirtQueueMappingList *iothread_vq_mapping_list,
+ AioContext **vq_aio_context, uint16_t num_queues)
+{
+ IOThreadVirtQueueMappingList *node;
+ size_t num_iothreads = 0;
+ size_t cur_iothread = 0;
+
+ for (node = iothread_vq_mapping_list; node; node = node->next) {
+ num_iothreads++;
+ }
+
+ for (node = iothread_vq_mapping_list; node; node = node->next) {
+ IOThread *iothread = iothread_by_id(node->value->iothread);
+ AioContext *ctx = iothread_get_aio_context(iothread);
+
+ /* Released in virtio_blk_data_plane_destroy() */
+ object_ref(OBJECT(iothread));
+
+ if (node->value->vqs) {
+ uint16List *vq;
+
+ /* Explicit vq:IOThread assignment */
+ for (vq = node->value->vqs; vq; vq = vq->next) {
+ vq_aio_context[vq->value] = ctx;
+ }
+ } else {
+ /* Round-robin vq:IOThread assignment */
+ for (unsigned i = cur_iothread; i < num_queues;
+ i += num_iothreads) {
+ vq_aio_context[i] = ctx;
+ }
+ }
+
+ cur_iothread++;
+ }
+}
+
/* Context: QEMU global mutex held */
bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
VirtIOBlockDataPlane **dataplane,
@@ -58,7 +95,7 @@
*dataplane = NULL;
- if (conf->iothread) {
+ if (conf->iothread || conf->iothread_vq_mapping_list) {
if (!k->set_guest_notifiers || !k->ioeventfd_assign) {
error_setg(errp,
"device is incompatible with iothread "
@@ -86,13 +123,24 @@
s = g_new0(VirtIOBlockDataPlane, 1);
s->vdev = vdev;
s->conf = conf;
+ s->vq_aio_context = g_new(AioContext *, conf->num_queues);
- if (conf->iothread) {
- s->iothread = conf->iothread;
- object_ref(OBJECT(s->iothread));
- s->ctx = iothread_get_aio_context(s->iothread);
+ if (conf->iothread_vq_mapping_list) {
+ apply_vq_mapping(conf->iothread_vq_mapping_list, s->vq_aio_context,
+ conf->num_queues);
+ } else if (conf->iothread) {
+ AioContext *ctx = iothread_get_aio_context(conf->iothread);
+ for (unsigned i = 0; i < conf->num_queues; i++) {
+ s->vq_aio_context[i] = ctx;
+ }
+
+ /* Released in virtio_blk_data_plane_destroy() */
+ object_ref(OBJECT(conf->iothread));
} else {
- s->ctx = qemu_get_aio_context();
+ AioContext *ctx = qemu_get_aio_context();
+ for (unsigned i = 0; i < conf->num_queues; i++) {
+ s->vq_aio_context[i] = ctx;
+ }
}
*dataplane = s;
@@ -104,6 +152,7 @@
void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
{
VirtIOBlock *vblk;
+ VirtIOBlkConf *conf = s->conf;
if (!s) {
return;
@@ -111,9 +160,21 @@
vblk = VIRTIO_BLK(s->vdev);
assert(!vblk->dataplane_started);
- if (s->iothread) {
- object_unref(OBJECT(s->iothread));
+
+ if (conf->iothread_vq_mapping_list) {
+ IOThreadVirtQueueMappingList *node;
+
+ for (node = conf->iothread_vq_mapping_list; node; node = node->next) {
+ IOThread *iothread = iothread_by_id(node->value->iothread);
+ object_unref(OBJECT(iothread));
+ }
}
+
+ if (conf->iothread) {
+ object_unref(OBJECT(conf->iothread));
+ }
+
+ g_free(s->vq_aio_context);
g_free(s);
}
@@ -124,7 +185,6 @@
VirtIOBlockDataPlane *s = vblk->dataplane;
BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vblk)));
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
- AioContext *old_context;
unsigned i;
unsigned nvqs = s->conf->num_queues;
Error *local_err = NULL;
@@ -178,22 +238,13 @@
trace_virtio_blk_data_plane_start(s);
- old_context = blk_get_aio_context(s->conf->conf.blk);
- aio_context_acquire(old_context);
- r = blk_set_aio_context(s->conf->conf.blk, s->ctx, &local_err);
- aio_context_release(old_context);
+ r = blk_set_aio_context(s->conf->conf.blk, s->vq_aio_context[0],
+ &local_err);
if (r < 0) {
error_report_err(local_err);
goto fail_aio_context;
}
- /* Kick right away to begin processing requests already in vring */
- for (i = 0; i < nvqs; i++) {
- VirtQueue *vq = virtio_get_queue(s->vdev, i);
-
- event_notifier_set(virtio_queue_get_host_notifier(vq));
- }
-
/*
* These fields must be visible to the IOThread when it processes the
* virtqueue, otherwise it will think dataplane has not started yet.
@@ -208,13 +259,15 @@
/* Get this show started by hooking up our callbacks */
if (!blk_in_drain(s->conf->conf.blk)) {
- aio_context_acquire(s->ctx);
for (i = 0; i < nvqs; i++) {
VirtQueue *vq = virtio_get_queue(s->vdev, i);
+ AioContext *ctx = s->vq_aio_context[i];
- virtio_queue_aio_attach_host_notifier(vq, s->ctx);
+ /* Kick right away to begin processing requests already in vring */
+ event_notifier_set(virtio_queue_get_host_notifier(vq));
+
+ virtio_queue_aio_attach_host_notifier(vq, ctx);
}
- aio_context_release(s->ctx);
}
return 0;
@@ -242,23 +295,18 @@
*
* Context: BH in IOThread
*/
-static void virtio_blk_data_plane_stop_bh(void *opaque)
+static void virtio_blk_data_plane_stop_vq_bh(void *opaque)
{
- VirtIOBlockDataPlane *s = opaque;
- unsigned i;
+ VirtQueue *vq = opaque;
+ EventNotifier *host_notifier = virtio_queue_get_host_notifier(vq);
- for (i = 0; i < s->conf->num_queues; i++) {
- VirtQueue *vq = virtio_get_queue(s->vdev, i);
- EventNotifier *host_notifier = virtio_queue_get_host_notifier(vq);
+ virtio_queue_aio_detach_host_notifier(vq, qemu_get_current_aio_context());
- virtio_queue_aio_detach_host_notifier(vq, s->ctx);
-
- /*
- * Test and clear notifier after disabling event, in case poll callback
- * didn't have time to run.
- */
- virtio_queue_host_notifier_read(host_notifier);
- }
+ /*
+ * Test and clear notifier after disabling event, in case poll callback
+ * didn't have time to run.
+ */
+ virtio_queue_host_notifier_read(host_notifier);
}
/* Context: QEMU global mutex held */
@@ -285,7 +333,12 @@
trace_virtio_blk_data_plane_stop(s);
if (!blk_in_drain(s->conf->conf.blk)) {
- aio_wait_bh_oneshot(s->ctx, virtio_blk_data_plane_stop_bh, s);
+ for (i = 0; i < nvqs; i++) {
+ VirtQueue *vq = virtio_get_queue(s->vdev, i);
+ AioContext *ctx = s->vq_aio_context[i];
+
+ aio_wait_bh_oneshot(ctx, virtio_blk_data_plane_stop_vq_bh, vq);
+ }
}
/*
@@ -314,8 +367,6 @@
*/
vblk->dataplane_started = false;
- aio_context_acquire(s->ctx);
-
/* Wait for virtio_blk_dma_restart_bh() and in flight I/O to complete */
blk_drain(s->conf->conf.blk);
@@ -325,10 +376,28 @@
*/
blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context(), NULL);
- aio_context_release(s->ctx);
-
/* Clean up guest notifier (irq) */
k->set_guest_notifiers(qbus->parent, nvqs, false);
s->stopping = false;
}
+
+void virtio_blk_data_plane_detach(VirtIOBlockDataPlane *s)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(s->vdev);
+
+ for (uint16_t i = 0; i < s->conf->num_queues; i++) {
+ VirtQueue *vq = virtio_get_queue(vdev, i);
+ virtio_queue_aio_detach_host_notifier(vq, s->vq_aio_context[i]);
+ }
+}
+
+void virtio_blk_data_plane_attach(VirtIOBlockDataPlane *s)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(s->vdev);
+
+ for (uint16_t i = 0; i < s->conf->num_queues; i++) {
+ VirtQueue *vq = virtio_get_queue(vdev, i);
+ virtio_queue_aio_attach_host_notifier(vq, s->vq_aio_context[i]);
+ }
+}
diff --git a/hw/block/dataplane/virtio-blk.h b/hw/block/dataplane/virtio-blk.h
index 5e18bb9..1a806fe 100644
--- a/hw/block/dataplane/virtio-blk.h
+++ b/hw/block/dataplane/virtio-blk.h
@@ -28,4 +28,7 @@
int virtio_blk_data_plane_start(VirtIODevice *vdev);
void virtio_blk_data_plane_stop(VirtIODevice *vdev);
+void virtio_blk_data_plane_detach(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_attach(VirtIOBlockDataPlane *s);
+
#endif /* HW_DATAPLANE_VIRTIO_BLK_H */
diff --git a/hw/block/dataplane/xen-block.c b/hw/block/dataplane/xen-block.c
index c4bb28c..98501e6 100644
--- a/hw/block/dataplane/xen-block.c
+++ b/hw/block/dataplane/xen-block.c
@@ -260,8 +260,6 @@
XenBlockRequest *request = opaque;
XenBlockDataPlane *dataplane = request->dataplane;
- aio_context_acquire(dataplane->ctx);
-
if (ret != 0) {
error_report("%s I/O error",
request->req.operation == BLKIF_OP_READ ?
@@ -273,10 +271,10 @@
if (request->presync) {
request->presync = 0;
xen_block_do_aio(request);
- goto done;
+ return;
}
if (request->aio_inflight > 0) {
- goto done;
+ return;
}
switch (request->req.operation) {
@@ -318,9 +316,6 @@
if (dataplane->more_work) {
qemu_bh_schedule(dataplane->bh);
}
-
-done:
- aio_context_release(dataplane->ctx);
}
static bool xen_block_split_discard(XenBlockRequest *request,
@@ -601,9 +596,7 @@
{
XenBlockDataPlane *dataplane = opaque;
- aio_context_acquire(dataplane->ctx);
xen_block_handle_requests(dataplane);
- aio_context_release(dataplane->ctx);
}
static bool xen_block_dataplane_event(void *opaque)
@@ -703,10 +696,8 @@
xen_block_dataplane_detach(dataplane);
}
- aio_context_acquire(dataplane->ctx);
/* Xen doesn't have multiple users for nodes, so this can't fail */
blk_set_aio_context(dataplane->blk, qemu_get_aio_context(), &error_abort);
- aio_context_release(dataplane->ctx);
/*
* Now that the context has been moved onto the main thread, cancel
@@ -752,7 +743,6 @@
{
ERRP_GUARD();
XenDevice *xendev = dataplane->xendev;
- AioContext *old_context;
unsigned int ring_size;
unsigned int i;
@@ -836,11 +826,8 @@
goto stop;
}
- old_context = blk_get_aio_context(dataplane->blk);
- aio_context_acquire(old_context);
/* If other users keep the BlockBackend in the iothread, that's ok */
blk_set_aio_context(dataplane->blk, dataplane->ctx, NULL);
- aio_context_release(old_context);
if (!blk_in_drain(dataplane->blk)) {
xen_block_dataplane_attach(dataplane);
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index a1f8e15..46e73b2 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -82,8 +82,11 @@
/* Break the link as the next request is going to be parsed from the
* ring again. Otherwise we may end up doing a double completion! */
req->mr_next = NULL;
- req->next = s->rq;
- s->rq = req;
+
+ WITH_QEMU_LOCK_GUARD(&s->rq_lock) {
+ req->next = s->rq;
+ s->rq = req;
+ }
} else if (action == BLOCK_ERROR_ACTION_REPORT) {
virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
if (acct_failed) {
@@ -102,7 +105,6 @@
VirtIOBlock *s = next->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
while (next) {
VirtIOBlockReq *req = next;
next = req->mr_next;
@@ -135,7 +137,6 @@
block_acct_done(blk_get_stats(s->blk), &req->acct);
virtio_blk_free_request(req);
}
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static void virtio_blk_flush_complete(void *opaque, int ret)
@@ -143,19 +144,13 @@
VirtIOBlockReq *req = opaque;
VirtIOBlock *s = req->dev;
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
- if (ret) {
- if (virtio_blk_handle_rw_error(req, -ret, 0, true)) {
- goto out;
- }
+ if (ret && virtio_blk_handle_rw_error(req, -ret, 0, true)) {
+ return;
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(s->blk), &req->acct);
virtio_blk_free_request(req);
-
-out:
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static void virtio_blk_discard_write_zeroes_complete(void *opaque, int ret)
@@ -165,11 +160,8 @@
bool is_write_zeroes = (virtio_ldl_p(VIRTIO_DEVICE(s), &req->out.type) &
~VIRTIO_BLK_T_BARRIER) == VIRTIO_BLK_T_WRITE_ZEROES;
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
- if (ret) {
- if (virtio_blk_handle_rw_error(req, -ret, false, is_write_zeroes)) {
- goto out;
- }
+ if (ret && virtio_blk_handle_rw_error(req, -ret, false, is_write_zeroes)) {
+ return;
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
@@ -177,9 +169,6 @@
block_acct_done(blk_get_stats(s->blk), &req->acct);
}
virtio_blk_free_request(req);
-
-out:
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
#ifdef __linux__
@@ -226,10 +215,8 @@
virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len);
out:
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
virtio_blk_req_complete(req, status);
virtio_blk_free_request(req);
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
g_free(ioctl_req);
}
@@ -669,7 +656,6 @@
{
ZoneCmdData *data = opaque;
VirtIOBlockReq *req = data->req;
- VirtIOBlock *s = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(req->dev);
struct iovec *in_iov = data->in_iov;
unsigned in_num = data->in_num;
@@ -760,10 +746,8 @@
}
out:
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
virtio_blk_req_complete(req, err_status);
virtio_blk_free_request(req);
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
g_free(data->zone_report_data.zones);
g_free(data);
}
@@ -826,10 +810,8 @@
err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD;
}
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
virtio_blk_req_complete(req, err_status);
virtio_blk_free_request(req);
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static int virtio_blk_handle_zone_mgmt(VirtIOBlockReq *req, BlockZoneOp op)
@@ -879,7 +861,6 @@
{
ZoneCmdData *data = opaque;
VirtIOBlockReq *req = data->req;
- VirtIOBlock *s = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(req->dev);
int64_t append_sector, n;
uint8_t err_status = VIRTIO_BLK_S_OK;
@@ -902,10 +883,8 @@
trace_virtio_blk_zone_append_complete(vdev, req, append_sector, ret);
out:
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
virtio_blk_req_complete(req, err_status);
virtio_blk_free_request(req);
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
g_free(data);
}
@@ -941,10 +920,8 @@
return 0;
out:
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
virtio_blk_req_complete(req, err_status);
virtio_blk_free_request(req);
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
return err_status;
}
@@ -1134,7 +1111,6 @@
MultiReqBuffer mrb = {};
bool suppress_notifications = virtio_queue_get_notification(vq);
- aio_context_acquire(blk_get_aio_context(s->blk));
defer_call_begin();
do {
@@ -1160,7 +1136,6 @@
}
defer_call_end();
- aio_context_release(blk_get_aio_context(s->blk));
}
static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
@@ -1176,6 +1151,7 @@
return;
}
}
+
virtio_blk_handle_vq(s, vq);
}
@@ -1183,12 +1159,14 @@
{
VirtIOBlock *s = opaque;
- VirtIOBlockReq *req = s->rq;
+ VirtIOBlockReq *req;
MultiReqBuffer mrb = {};
- s->rq = NULL;
+ WITH_QEMU_LOCK_GUARD(&s->rq_lock) {
+ req = s->rq;
+ s->rq = NULL;
+ }
- aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
while (req) {
VirtIOBlockReq *next = req->next;
if (virtio_blk_handle_request(req, &mrb)) {
@@ -1212,8 +1190,6 @@
/* Paired with inc in virtio_blk_dma_restart_cb() */
blk_dec_in_flight(s->conf.conf.blk);
-
- aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static void virtio_blk_dma_restart_cb(void *opaque, bool running,
@@ -1235,25 +1211,28 @@
static void virtio_blk_reset(VirtIODevice *vdev)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
- AioContext *ctx;
VirtIOBlockReq *req;
- ctx = blk_get_aio_context(s->blk);
- aio_context_acquire(ctx);
+ /* Dataplane has stopped... */
+ assert(!s->dataplane_started);
+
+ /* ...but requests may still be in flight. */
blk_drain(s->blk);
/* We drop queued requests after blk_drain() because blk_drain() itself can
* produce them. */
- while (s->rq) {
- req = s->rq;
- s->rq = req->next;
- virtqueue_detach_element(req->vq, &req->elem, 0);
- virtio_blk_free_request(req);
+ WITH_QEMU_LOCK_GUARD(&s->rq_lock) {
+ while (s->rq) {
+ req = s->rq;
+ s->rq = req->next;
+
+ /* No other threads can access req->vq here */
+ virtqueue_detach_element(req->vq, &req->elem, 0);
+
+ virtio_blk_free_request(req);
+ }
}
- aio_context_release(ctx);
-
- assert(!s->dataplane_started);
blk_set_enable_write_cache(s->blk, s->original_wce);
}
@@ -1268,10 +1247,6 @@
uint64_t capacity;
int64_t length;
int blk_size = conf->logical_block_size;
- AioContext *ctx;
-
- ctx = blk_get_aio_context(s->blk);
- aio_context_acquire(ctx);
blk_get_geometry(s->blk, &capacity);
memset(&blkcfg, 0, sizeof(blkcfg));
@@ -1295,7 +1270,6 @@
* per track (cylinder).
*/
length = blk_getlength(s->blk);
- aio_context_release(ctx);
if (length > 0 && length / conf->heads / conf->secs % blk_size) {
blkcfg.geometry.sectors = conf->secs & ~s->sector_mask;
} else {
@@ -1362,9 +1336,7 @@
memcpy(&blkcfg, config, s->config_size);
- aio_context_acquire(blk_get_aio_context(s->blk));
blk_set_enable_write_cache(s->blk, blkcfg.wce != 0);
- aio_context_release(blk_get_aio_context(s->blk));
}
static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
@@ -1432,29 +1404,31 @@
* s->blk would erroneously be placed in writethrough mode.
*/
if (!virtio_vdev_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE)) {
- aio_context_acquire(blk_get_aio_context(s->blk));
blk_set_enable_write_cache(s->blk,
virtio_vdev_has_feature(vdev,
VIRTIO_BLK_F_WCE));
- aio_context_release(blk_get_aio_context(s->blk));
}
}
static void virtio_blk_save_device(VirtIODevice *vdev, QEMUFile *f)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
- VirtIOBlockReq *req = s->rq;
- while (req) {
- qemu_put_sbyte(f, 1);
+ WITH_QEMU_LOCK_GUARD(&s->rq_lock) {
+ VirtIOBlockReq *req = s->rq;
- if (s->conf.num_queues > 1) {
- qemu_put_be32(f, virtio_get_queue_index(req->vq));
+ while (req) {
+ qemu_put_sbyte(f, 1);
+
+ if (s->conf.num_queues > 1) {
+ qemu_put_be32(f, virtio_get_queue_index(req->vq));
+ }
+
+ qemu_put_virtqueue_element(vdev, f, &req->elem);
+ req = req->next;
}
-
- qemu_put_virtqueue_element(vdev, f, &req->elem);
- req = req->next;
}
+
qemu_put_sbyte(f, 0);
}
@@ -1480,13 +1454,78 @@
req = qemu_get_virtqueue_element(vdev, f, sizeof(VirtIOBlockReq));
virtio_blk_init_request(s, virtio_get_queue(vdev, vq_idx), req);
- req->next = s->rq;
- s->rq = req;
+
+ WITH_QEMU_LOCK_GUARD(&s->rq_lock) {
+ req->next = s->rq;
+ s->rq = req;
+ }
}
return 0;
}
+static bool
+validate_iothread_vq_mapping_list(IOThreadVirtQueueMappingList *list,
+ uint16_t num_queues, Error **errp)
+{
+ g_autofree unsigned long *vqs = bitmap_new(num_queues);
+ g_autoptr(GHashTable) iothreads =
+ g_hash_table_new(g_str_hash, g_str_equal);
+
+ for (IOThreadVirtQueueMappingList *node = list; node; node = node->next) {
+ const char *name = node->value->iothread;
+ uint16List *vq;
+
+ if (!iothread_by_id(name)) {
+ error_setg(errp, "IOThread \"%s\" object does not exist", name);
+ return false;
+ }
+
+ if (!g_hash_table_add(iothreads, (gpointer)name)) {
+ error_setg(errp,
+ "duplicate IOThread name \"%s\" in iothread-vq-mapping",
+ name);
+ return false;
+ }
+
+ if (node != list) {
+ if (!!node->value->vqs != !!list->value->vqs) {
+ error_setg(errp, "either all items in iothread-vq-mapping "
+ "must have vqs or none of them must have it");
+ return false;
+ }
+ }
+
+ for (vq = node->value->vqs; vq; vq = vq->next) {
+ if (vq->value >= num_queues) {
+ error_setg(errp, "vq index %u for IOThread \"%s\" must be "
+ "less than num_queues %u in iothread-vq-mapping",
+ vq->value, name, num_queues);
+ return false;
+ }
+
+ if (test_and_set_bit(vq->value, vqs)) {
+ error_setg(errp, "cannot assign vq %u to IOThread \"%s\" "
+ "because it is already assigned", vq->value, name);
+ return false;
+ }
+ }
+ }
+
+ if (list->value->vqs) {
+ for (uint16_t i = 0; i < num_queues; i++) {
+ if (!test_bit(i, vqs)) {
+ error_setg(errp,
+ "missing vq %u IOThread assignment in iothread-vq-mapping",
+ i);
+ return false;
+ }
+ }
+ }
+
+ return true;
+}
+
static void virtio_resize_cb(void *opaque)
{
VirtIODevice *vdev = opaque;
@@ -1511,34 +1550,24 @@
static void virtio_blk_drained_begin(void *opaque)
{
VirtIOBlock *s = opaque;
- VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
- AioContext *ctx = blk_get_aio_context(s->conf.conf.blk);
if (!s->dataplane || !s->dataplane_started) {
return;
}
- for (uint16_t i = 0; i < s->conf.num_queues; i++) {
- VirtQueue *vq = virtio_get_queue(vdev, i);
- virtio_queue_aio_detach_host_notifier(vq, ctx);
- }
+ virtio_blk_data_plane_detach(s->dataplane);
}
/* Resume virtqueue ioeventfd processing after drain */
static void virtio_blk_drained_end(void *opaque)
{
VirtIOBlock *s = opaque;
- VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
- AioContext *ctx = blk_get_aio_context(s->conf.conf.blk);
if (!s->dataplane || !s->dataplane_started) {
return;
}
- for (uint16_t i = 0; i < s->conf.num_queues; i++) {
- VirtQueue *vq = virtio_get_queue(vdev, i);
- virtio_queue_aio_attach_host_notifier(vq, ctx);
- }
+ virtio_blk_data_plane_attach(s->dataplane);
}
static const BlockDevOps virtio_block_ops = {
@@ -1624,10 +1653,25 @@
return;
}
+ if (conf->iothread_vq_mapping_list) {
+ if (conf->iothread) {
+ error_setg(errp, "iothread and iothread-vq-mapping properties "
+ "cannot be set at the same time");
+ return;
+ }
+
+ if (!validate_iothread_vq_mapping_list(conf->iothread_vq_mapping_list,
+ conf->num_queues, errp)) {
+ return;
+ }
+ }
+
s->config_size = virtio_get_config_size(&virtio_blk_cfg_size_params,
s->host_features);
virtio_init(vdev, VIRTIO_ID_BLOCK, s->config_size);
+ qemu_mutex_init(&s->rq_lock);
+
s->blk = conf->conf.blk;
s->rq = NULL;
s->sector_mask = (s->conf.conf.logical_block_size / BDRV_SECTOR_SIZE) - 1;
@@ -1679,6 +1723,7 @@
virtio_del_queue(vdev, i);
}
qemu_coroutine_dec_pool_size(conf->num_queues * conf->queue_size / 2);
+ qemu_mutex_destroy(&s->rq_lock);
blk_ram_registrar_destroy(&s->blk_ram_registrar);
qemu_del_vm_change_state_handler(s->change);
blockdev_mark_auto_del(s->blk);
@@ -1723,6 +1768,8 @@
DEFINE_PROP_BOOL("seg-max-adjust", VirtIOBlock, conf.seg_max_adjust, true),
DEFINE_PROP_LINK("iothread", VirtIOBlock, conf.iothread, TYPE_IOTHREAD,
IOThread *),
+ DEFINE_PROP_IOTHREAD_VQ_MAPPING_LIST("iothread-vq-mapping", VirtIOBlock,
+ conf.iothread_vq_mapping_list),
DEFINE_PROP_BIT64("discard", VirtIOBlock, host_features,
VIRTIO_BLK_F_DISCARD, true),
DEFINE_PROP_BOOL("report-discard-granularity", VirtIOBlock,
diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c
index 1473ab3..1a39652 100644
--- a/hw/core/qdev-properties-system.c
+++ b/hw/core/qdev-properties-system.c
@@ -18,6 +18,7 @@
#include "qapi/qapi-types-block.h"
#include "qapi/qapi-types-machine.h"
#include "qapi/qapi-types-migration.h"
+#include "qapi/qapi-visit-virtio.h"
#include "qapi/qmp/qerror.h"
#include "qemu/ctype.h"
#include "qemu/cutils.h"
@@ -120,9 +121,7 @@
"node");
}
- aio_context_acquire(ctx);
blk_replace_bs(blk, bs, errp);
- aio_context_release(ctx);
return;
}
@@ -148,10 +147,7 @@
0, BLK_PERM_ALL);
blk_created = true;
- aio_context_acquire(ctx);
ret = blk_insert_bs(blk, bs, errp);
- aio_context_release(ctx);
-
if (ret < 0) {
goto fail;
}
@@ -207,12 +203,8 @@
BlockBackend **ptr = object_field_prop_ptr(obj, prop);
if (*ptr) {
- AioContext *ctx = blk_get_aio_context(*ptr);
-
- aio_context_acquire(ctx);
blockdev_auto_del(*ptr);
blk_detach_dev(*ptr, dev);
- aio_context_release(ctx);
}
}
@@ -1169,3 +1161,48 @@
.set = qdev_propinfo_set_enum,
.set_default_value = qdev_propinfo_set_default_value_enum,
};
+
+/* --- IOThreadVirtQueueMappingList --- */
+
+static void get_iothread_vq_mapping_list(Object *obj, Visitor *v,
+ const char *name, void *opaque, Error **errp)
+{
+ IOThreadVirtQueueMappingList **prop_ptr =
+ object_field_prop_ptr(obj, opaque);
+
+ visit_type_IOThreadVirtQueueMappingList(v, name, prop_ptr, errp);
+}
+
+static void set_iothread_vq_mapping_list(Object *obj, Visitor *v,
+ const char *name, void *opaque, Error **errp)
+{
+ IOThreadVirtQueueMappingList **prop_ptr =
+ object_field_prop_ptr(obj, opaque);
+ IOThreadVirtQueueMappingList *list;
+
+ if (!visit_type_IOThreadVirtQueueMappingList(v, name, &list, errp)) {
+ return;
+ }
+
+ qapi_free_IOThreadVirtQueueMappingList(*prop_ptr);
+ *prop_ptr = list;
+}
+
+static void release_iothread_vq_mapping_list(Object *obj,
+ const char *name, void *opaque)
+{
+ IOThreadVirtQueueMappingList **prop_ptr =
+ object_field_prop_ptr(obj, opaque);
+
+ qapi_free_IOThreadVirtQueueMappingList(*prop_ptr);
+ *prop_ptr = NULL;
+}
+
+const PropertyInfo qdev_prop_iothread_vq_mapping_list = {
+ .name = "IOThreadVirtQueueMappingList",
+ .description = "IOThread virtqueue mapping list [{\"iothread\":\"<id>\", "
+ "\"vqs\":[1,2,3,...]},...]",
+ .get = get_iothread_vq_mapping_list,
+ .set = set_iothread_vq_mapping_list,
+ .release = release_iothread_vq_mapping_list,
+};
diff --git a/hw/core/qdev-properties.c b/hw/core/qdev-properties.c
index 840006e..7d6fa72 100644
--- a/hw/core/qdev-properties.c
+++ b/hw/core/qdev-properties.c
@@ -1076,16 +1076,18 @@
void qdev_alias_all_properties(DeviceState *target, Object *source)
{
ObjectClass *class;
- Property *prop;
+ ObjectPropertyIterator iter;
+ ObjectProperty *prop;
class = object_get_class(OBJECT(target));
- do {
- DeviceClass *dc = DEVICE_CLASS(class);
- for (prop = dc->props_; prop && prop->name; prop++) {
- object_property_add_alias(source, prop->name,
- OBJECT(target), prop->name);
+ object_class_property_iter_init(&iter, class);
+ while ((prop = object_property_iter_next(&iter))) {
+ if (object_property_find(source, prop->name)) {
+ continue; /* skip duplicate properties */
}
- class = object_class_get_parent(class);
- } while (class != object_class_by_name(TYPE_DEVICE));
+
+ object_property_add_alias(source, prop->name,
+ OBJECT(target), prop->name);
+ }
}
diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
index fc4b77f..5b08cbf 100644
--- a/hw/scsi/scsi-bus.c
+++ b/hw/scsi/scsi-bus.c
@@ -85,6 +85,89 @@
return d;
}
+/*
+ * Invoke @fn() for each enqueued request in device @s. Must be called from the
+ * main loop thread while the guest is stopped. This is only suitable for
+ * vmstate ->put(), use scsi_device_for_each_req_async() for other cases.
+ */
+static void scsi_device_for_each_req_sync(SCSIDevice *s,
+ void (*fn)(SCSIRequest *, void *),
+ void *opaque)
+{
+ SCSIRequest *req;
+ SCSIRequest *next_req;
+
+ assert(!runstate_is_running());
+ assert(qemu_in_main_thread());
+
+ QTAILQ_FOREACH_SAFE(req, &s->requests, next, next_req) {
+ fn(req, opaque);
+ }
+}
+
+typedef struct {
+ SCSIDevice *s;
+ void (*fn)(SCSIRequest *, void *);
+ void *fn_opaque;
+} SCSIDeviceForEachReqAsyncData;
+
+static void scsi_device_for_each_req_async_bh(void *opaque)
+{
+ g_autofree SCSIDeviceForEachReqAsyncData *data = opaque;
+ SCSIDevice *s = data->s;
+ AioContext *ctx;
+ SCSIRequest *req;
+ SCSIRequest *next;
+
+ /*
+ * If the AioContext changed before this BH was called then reschedule into
+ * the new AioContext before accessing ->requests. This can happen when
+ * scsi_device_for_each_req_async() is called and then the AioContext is
+ * changed before BHs are run.
+ */
+ ctx = blk_get_aio_context(s->conf.blk);
+ if (ctx != qemu_get_current_aio_context()) {
+ aio_bh_schedule_oneshot(ctx, scsi_device_for_each_req_async_bh,
+ g_steal_pointer(&data));
+ return;
+ }
+
+ QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) {
+ data->fn(req, data->fn_opaque);
+ }
+
+ /* Drop the reference taken by scsi_device_for_each_req_async() */
+ object_unref(OBJECT(s));
+}
+
+/*
+ * Schedule @fn() to be invoked for each enqueued request in device @s. @fn()
+ * runs in the AioContext that is executing the request.
+ */
+static void scsi_device_for_each_req_async(SCSIDevice *s,
+ void (*fn)(SCSIRequest *, void *),
+ void *opaque)
+{
+ assert(qemu_in_main_thread());
+
+ SCSIDeviceForEachReqAsyncData *data =
+ g_new(SCSIDeviceForEachReqAsyncData, 1);
+
+ data->s = s;
+ data->fn = fn;
+ data->fn_opaque = opaque;
+
+ /*
+ * Hold a reference to the SCSIDevice until
+ * scsi_device_for_each_req_async_bh() finishes.
+ */
+ object_ref(OBJECT(s));
+
+ aio_bh_schedule_oneshot(blk_get_aio_context(s->conf.blk),
+ scsi_device_for_each_req_async_bh,
+ data);
+}
+
static void scsi_device_realize(SCSIDevice *s, Error **errp)
{
SCSIDeviceClass *sc = SCSI_DEVICE_GET_CLASS(s);
@@ -144,20 +227,18 @@
qbus_set_bus_hotplug_handler(BUS(bus));
}
-static void scsi_dma_restart_bh(void *opaque)
+void scsi_req_retry(SCSIRequest *req)
{
- SCSIDevice *s = opaque;
- SCSIRequest *req, *next;
+ req->retry = true;
+}
- qemu_bh_delete(s->bh);
- s->bh = NULL;
-
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
- QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) {
- scsi_req_ref(req);
- if (req->retry) {
- req->retry = false;
- switch (req->cmd.mode) {
+/* Called in the AioContext that is executing the request */
+static void scsi_dma_restart_req(SCSIRequest *req, void *opaque)
+{
+ scsi_req_ref(req);
+ if (req->retry) {
+ req->retry = false;
+ switch (req->cmd.mode) {
case SCSI_XFER_FROM_DEV:
case SCSI_XFER_TO_DEV:
scsi_req_continue(req);
@@ -166,37 +247,22 @@
scsi_req_dequeue(req);
scsi_req_enqueue(req);
break;
- }
}
- scsi_req_unref(req);
}
- aio_context_release(blk_get_aio_context(s->conf.blk));
- /* Drop the reference that was acquired in scsi_dma_restart_cb */
- object_unref(OBJECT(s));
-}
-
-void scsi_req_retry(SCSIRequest *req)
-{
- /* No need to save a reference, because scsi_dma_restart_bh just
- * looks at the request list. */
- req->retry = true;
+ scsi_req_unref(req);
}
static void scsi_dma_restart_cb(void *opaque, bool running, RunState state)
{
SCSIDevice *s = opaque;
+ assert(qemu_in_main_thread());
+
if (!running) {
return;
}
- if (!s->bh) {
- AioContext *ctx = blk_get_aio_context(s->conf.blk);
- /* The reference is dropped in scsi_dma_restart_bh.*/
- object_ref(OBJECT(s));
- s->bh = aio_bh_new_guarded(ctx, scsi_dma_restart_bh, s,
- &DEVICE(s)->mem_reentrancy_guard);
- qemu_bh_schedule(s->bh);
- }
+
+ scsi_device_for_each_req_async(s, scsi_dma_restart_req, NULL);
}
static bool scsi_bus_is_address_free(SCSIBus *bus,
@@ -1657,17 +1723,16 @@
}
}
+static void scsi_device_purge_one_req(SCSIRequest *req, void *opaque)
+{
+ scsi_req_cancel_async(req, NULL);
+}
+
void scsi_device_purge_requests(SCSIDevice *sdev, SCSISense sense)
{
- SCSIRequest *req;
+ scsi_device_for_each_req_async(sdev, scsi_device_purge_one_req, NULL);
- aio_context_acquire(blk_get_aio_context(sdev->conf.blk));
- while (!QTAILQ_EMPTY(&sdev->requests)) {
- req = QTAILQ_FIRST(&sdev->requests);
- scsi_req_cancel_async(req, NULL);
- }
blk_drain(sdev->conf.blk);
- aio_context_release(blk_get_aio_context(sdev->conf.blk));
scsi_device_set_ua(sdev, sense);
}
@@ -1737,31 +1802,33 @@
/* SCSI request list. For simplicity, pv points to the whole device */
+static void put_scsi_req(SCSIRequest *req, void *opaque)
+{
+ QEMUFile *f = opaque;
+
+ assert(!req->io_canceled);
+ assert(req->status == -1 && req->host_status == -1);
+ assert(req->enqueued);
+
+ qemu_put_sbyte(f, req->retry ? 1 : 2);
+ qemu_put_buffer(f, req->cmd.buf, sizeof(req->cmd.buf));
+ qemu_put_be32s(f, &req->tag);
+ qemu_put_be32s(f, &req->lun);
+ if (req->bus->info->save_request) {
+ req->bus->info->save_request(f, req);
+ }
+ if (req->ops->save_request) {
+ req->ops->save_request(f, req);
+ }
+}
+
static int put_scsi_requests(QEMUFile *f, void *pv, size_t size,
const VMStateField *field, JSONWriter *vmdesc)
{
SCSIDevice *s = pv;
- SCSIBus *bus = DO_UPCAST(SCSIBus, qbus, s->qdev.parent_bus);
- SCSIRequest *req;
- QTAILQ_FOREACH(req, &s->requests, next) {
- assert(!req->io_canceled);
- assert(req->status == -1 && req->host_status == -1);
- assert(req->enqueued);
-
- qemu_put_sbyte(f, req->retry ? 1 : 2);
- qemu_put_buffer(f, req->cmd.buf, sizeof(req->cmd.buf));
- qemu_put_be32s(f, &req->tag);
- qemu_put_be32s(f, &req->lun);
- if (bus->info->save_request) {
- bus->info->save_request(f, req);
- }
- if (req->ops->save_request) {
- req->ops->save_request(f, req);
- }
- }
+ scsi_device_for_each_req_sync(s, put_scsi_req, f);
qemu_put_sbyte(f, 0);
-
return 0;
}
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 6691f5e..2e7e1e9 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -273,7 +273,9 @@
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
+ /* The request must only run in the BlockBackend's AioContext */
+ assert(blk_get_aio_context(s->qdev.conf.blk) ==
+ qemu_get_current_aio_context());
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -286,7 +288,6 @@
scsi_req_complete(&r->req, GOOD);
done:
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
scsi_req_unref(&r->req);
}
@@ -354,7 +355,6 @@
scsi_req_unref(&r->req);
}
-/* Called with AioContext lock held */
static void scsi_dma_complete(void *opaque, int ret)
{
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
@@ -373,8 +373,13 @@
static void scsi_read_complete_noio(SCSIDiskReq *r, int ret)
{
+ SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
uint32_t n;
+ /* The request must only run in the BlockBackend's AioContext */
+ assert(blk_get_aio_context(s->qdev.conf.blk) ==
+ qemu_get_current_aio_context());
+
assert(r->req.aiocb == NULL);
if (scsi_disk_req_check_error(r, ret, false)) {
goto done;
@@ -394,8 +399,6 @@
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -406,7 +409,6 @@
trace_scsi_disk_read_complete(r->req.tag, r->qiov.size);
}
scsi_read_complete_noio(r, ret);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
/* Actually issue a read to the block device. */
@@ -448,8 +450,6 @@
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert (r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -459,7 +459,6 @@
block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
}
scsi_do_read(opaque, ret);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
/* Read more data from scsi device into buffer. */
@@ -505,8 +504,13 @@
static void scsi_write_complete_noio(SCSIDiskReq *r, int ret)
{
+ SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
uint32_t n;
+ /* The request must only run in the BlockBackend's AioContext */
+ assert(blk_get_aio_context(s->qdev.conf.blk) ==
+ qemu_get_current_aio_context());
+
assert (r->req.aiocb == NULL);
if (scsi_disk_req_check_error(r, ret, false)) {
goto done;
@@ -533,8 +537,6 @@
SCSIDiskReq *r = (SCSIDiskReq *)opaque;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert (r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -544,7 +546,6 @@
block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
}
scsi_write_complete_noio(r, ret);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
static void scsi_write_data(SCSIRequest *req)
@@ -1742,8 +1743,6 @@
SCSIDiskReq *r = data->r;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -1754,7 +1753,6 @@
block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
scsi_unmap_complete_noio(data, ret);
}
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
static void scsi_disk_emulate_unmap(SCSIDiskReq *r, uint8_t *inbuf)
@@ -1822,8 +1820,6 @@
SCSIDiskReq *r = data->r;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
- aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
@@ -1847,7 +1843,6 @@
data->sector << BDRV_SECTOR_BITS,
&data->qiov, 0,
scsi_write_same_complete, data);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
return;
}
@@ -1857,7 +1852,6 @@
scsi_req_unref(&r->req);
qemu_vfree(data->iov.iov_base);
g_free(data);
- aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
}
static void scsi_disk_emulate_write_same(SCSIDiskReq *r, uint8_t *inbuf)
@@ -2344,14 +2338,10 @@
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev.qdev, dev);
uint64_t nb_sectors;
- AioContext *ctx;
scsi_device_purge_requests(&s->qdev, SENSE_CODE(RESET));
- ctx = blk_get_aio_context(s->qdev.conf.blk);
- aio_context_acquire(ctx);
blk_get_geometry(s->qdev.conf.blk, &nb_sectors);
- aio_context_release(ctx);
nb_sectors /= s->qdev.blocksize / BDRV_SECTOR_SIZE;
if (nb_sectors) {
@@ -2550,15 +2540,13 @@
static void scsi_hd_realize(SCSIDevice *dev, Error **errp)
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
- AioContext *ctx = NULL;
+
/* can happen for devices without drive. The error message for missing
* backend will be issued in scsi_realize
*/
if (s->qdev.conf.blk) {
- ctx = blk_get_aio_context(s->qdev.conf.blk);
- aio_context_acquire(ctx);
if (!blkconf_blocksizes(&s->qdev.conf, errp)) {
- goto out;
+ return;
}
}
s->qdev.blocksize = s->qdev.conf.logical_block_size;
@@ -2567,16 +2555,11 @@
s->product = g_strdup("QEMU HARDDISK");
}
scsi_realize(&s->qdev, errp);
-out:
- if (ctx) {
- aio_context_release(ctx);
- }
}
static void scsi_cd_realize(SCSIDevice *dev, Error **errp)
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
- AioContext *ctx;
int ret;
uint32_t blocksize = 2048;
@@ -2592,8 +2575,6 @@
blocksize = dev->conf.physical_block_size;
}
- ctx = blk_get_aio_context(dev->conf.blk);
- aio_context_acquire(ctx);
s->qdev.blocksize = blocksize;
s->qdev.type = TYPE_ROM;
s->features |= 1 << SCSI_DISK_F_REMOVABLE;
@@ -2601,7 +2582,6 @@
s->product = g_strdup("QEMU CD-ROM");
}
scsi_realize(&s->qdev, errp);
- aio_context_release(ctx);
}
@@ -2732,7 +2712,6 @@
static void scsi_block_realize(SCSIDevice *dev, Error **errp)
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
- AioContext *ctx;
int sg_version;
int rc;
@@ -2747,9 +2726,6 @@
"be removed in a future version");
}
- ctx = blk_get_aio_context(s->qdev.conf.blk);
- aio_context_acquire(ctx);
-
/* check we are using a driver managing SG_IO (version 3 and after) */
rc = blk_ioctl(s->qdev.conf.blk, SG_GET_VERSION_NUM, &sg_version);
if (rc < 0) {
@@ -2757,18 +2733,18 @@
if (rc != -EPERM) {
error_append_hint(errp, "Is this a SCSI device?\n");
}
- goto out;
+ return;
}
if (sg_version < 30000) {
error_setg(errp, "scsi generic interface too old");
- goto out;
+ return;
}
/* get device type from INQUIRY data */
rc = get_device_type(s);
if (rc < 0) {
error_setg(errp, "INQUIRY failed");
- goto out;
+ return;
}
/* Make a guess for the block size, we'll fix it when the guest sends.
@@ -2788,9 +2764,6 @@
scsi_realize(&s->qdev, errp);
scsi_generic_read_device_inquiry(&s->qdev);
-
-out:
- aio_context_release(ctx);
}
typedef struct SCSIBlockReq {
@@ -2810,7 +2783,6 @@
{
SCSIBlockReq *req = (SCSIBlockReq *)opaque;
SCSIDiskReq *r = &req->req;
- SCSIDevice *s = r->req.dev;
sg_io_hdr_t *io_hdr = &req->io_header;
if (ret == 0) {
@@ -2827,13 +2799,10 @@
}
if (ret > 0) {
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
if (scsi_handle_rw_error(r, ret, true)) {
- aio_context_release(blk_get_aio_context(s->conf.blk));
scsi_req_unref(&r->req);
return;
}
- aio_context_release(blk_get_aio_context(s->conf.blk));
/* Ignore error. */
ret = 0;
diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
index 2417f0a..b7b04e1 100644
--- a/hw/scsi/scsi-generic.c
+++ b/hw/scsi/scsi-generic.c
@@ -109,15 +109,11 @@
static void scsi_command_complete(void *opaque, int ret)
{
SCSIGenericReq *r = (SCSIGenericReq *)opaque;
- SCSIDevice *s = r->req.dev;
-
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
scsi_command_complete_noio(r, ret);
- aio_context_release(blk_get_aio_context(s->conf.blk));
}
static int execute_command(BlockBackend *blk,
@@ -274,14 +270,12 @@
SCSIDevice *s = r->req.dev;
int len;
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
if (ret || r->req.io_canceled) {
scsi_command_complete_noio(r, ret);
- goto done;
+ return;
}
len = r->io_header.dxfer_len - r->io_header.resid;
@@ -320,7 +314,7 @@
r->io_header.status != GOOD ||
len == 0) {
scsi_command_complete_noio(r, 0);
- goto done;
+ return;
}
/* Snoop READ CAPACITY output to set the blocksize. */
@@ -356,9 +350,6 @@
req_complete:
scsi_req_data(&r->req, len);
scsi_req_unref(&r->req);
-
-done:
- aio_context_release(blk_get_aio_context(s->conf.blk));
}
/* Read more data from scsi device into buffer. */
@@ -391,14 +382,12 @@
trace_scsi_generic_write_complete(ret);
- aio_context_acquire(blk_get_aio_context(s->conf.blk));
-
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
if (ret || r->req.io_canceled) {
scsi_command_complete_noio(r, ret);
- goto done;
+ return;
}
if (r->req.cmd.buf[0] == MODE_SELECT && r->req.cmd.buf[4] == 12 &&
@@ -408,9 +397,6 @@
}
scsi_command_complete_noio(r, ret);
-
-done:
- aio_context_release(blk_get_aio_context(s->conf.blk));
}
/* Write data to a scsi device. Returns nonzero on failure.
diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c
index 1e684be..135e23f 100644
--- a/hw/scsi/virtio-scsi-dataplane.c
+++ b/hw/scsi/virtio-scsi-dataplane.c
@@ -149,23 +149,17 @@
memory_region_transaction_commit();
- /*
- * These fields are visible to the IOThread so we rely on implicit barriers
- * in aio_context_acquire() on the write side and aio_notify_accept() on
- * the read side.
- */
s->dataplane_starting = false;
s->dataplane_started = true;
+ smp_wmb(); /* paired with aio_notify_accept() */
if (s->bus.drain_count == 0) {
- aio_context_acquire(s->ctx);
virtio_queue_aio_attach_host_notifier(vs->ctrl_vq, s->ctx);
virtio_queue_aio_attach_host_notifier_no_poll(vs->event_vq, s->ctx);
for (i = 0; i < vs->conf.num_queues; i++) {
virtio_queue_aio_attach_host_notifier(vs->cmd_vqs[i], s->ctx);
}
- aio_context_release(s->ctx);
}
return 0;
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 9c751bf..ca365a7 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -123,6 +123,30 @@
virtio_scsi_free_req(req);
}
+static void virtio_scsi_complete_req_bh(void *opaque)
+{
+ VirtIOSCSIReq *req = opaque;
+
+ virtio_scsi_complete_req(req);
+}
+
+/*
+ * Called from virtio_scsi_do_one_tmf_bh() in main loop thread. The main loop
+ * thread cannot touch the virtqueue since that could race with an IOThread.
+ */
+static void virtio_scsi_complete_req_from_main_loop(VirtIOSCSIReq *req)
+{
+ VirtIOSCSI *s = req->dev;
+
+ if (!s->ctx || s->ctx == qemu_get_aio_context()) {
+ /* No need to schedule a BH when there is no IOThread */
+ virtio_scsi_complete_req(req);
+ } else {
+ /* Run request completion in the IOThread */
+ aio_wait_bh_oneshot(s->ctx, virtio_scsi_complete_req_bh, req);
+ }
+}
+
static void virtio_scsi_bad_req(VirtIOSCSIReq *req)
{
virtio_error(VIRTIO_DEVICE(req->dev), "wrong size for virtio-scsi headers");
@@ -338,10 +362,7 @@
out:
object_unref(OBJECT(d));
-
- virtio_scsi_acquire(s);
- virtio_scsi_complete_req(req);
- virtio_scsi_release(s);
+ virtio_scsi_complete_req_from_main_loop(req);
}
/* Some TMFs must be processed from the main loop thread */
@@ -354,18 +375,16 @@
GLOBAL_STATE_CODE();
- virtio_scsi_acquire(s);
+ WITH_QEMU_LOCK_GUARD(&s->tmf_bh_lock) {
+ QTAILQ_FOREACH_SAFE(req, &s->tmf_bh_list, next, tmp) {
+ QTAILQ_REMOVE(&s->tmf_bh_list, req, next);
+ QTAILQ_INSERT_TAIL(&reqs, req, next);
+ }
- QTAILQ_FOREACH_SAFE(req, &s->tmf_bh_list, next, tmp) {
- QTAILQ_REMOVE(&s->tmf_bh_list, req, next);
- QTAILQ_INSERT_TAIL(&reqs, req, next);
+ qemu_bh_delete(s->tmf_bh);
+ s->tmf_bh = NULL;
}
- qemu_bh_delete(s->tmf_bh);
- s->tmf_bh = NULL;
-
- virtio_scsi_release(s);
-
QTAILQ_FOREACH_SAFE(req, &reqs, next, tmp) {
QTAILQ_REMOVE(&reqs, req, next);
virtio_scsi_do_one_tmf_bh(req);
@@ -379,8 +398,7 @@
GLOBAL_STATE_CODE();
- virtio_scsi_acquire(s);
-
+ /* Called after ioeventfd has been stopped, so tmf_bh_lock is not needed */
if (s->tmf_bh) {
qemu_bh_delete(s->tmf_bh);
s->tmf_bh = NULL;
@@ -393,19 +411,19 @@
req->resp.tmf.response = VIRTIO_SCSI_S_TARGET_FAILURE;
virtio_scsi_complete_req(req);
}
-
- virtio_scsi_release(s);
}
static void virtio_scsi_defer_tmf_to_bh(VirtIOSCSIReq *req)
{
VirtIOSCSI *s = req->dev;
- QTAILQ_INSERT_TAIL(&s->tmf_bh_list, req, next);
+ WITH_QEMU_LOCK_GUARD(&s->tmf_bh_lock) {
+ QTAILQ_INSERT_TAIL(&s->tmf_bh_list, req, next);
- if (!s->tmf_bh) {
- s->tmf_bh = qemu_bh_new(virtio_scsi_do_tmf_bh, s);
- qemu_bh_schedule(s->tmf_bh);
+ if (!s->tmf_bh) {
+ s->tmf_bh = qemu_bh_new(virtio_scsi_do_tmf_bh, s);
+ qemu_bh_schedule(s->tmf_bh);
+ }
}
}
@@ -624,9 +642,7 @@
return;
}
- virtio_scsi_acquire(s);
virtio_scsi_handle_ctrl_vq(s, vq);
- virtio_scsi_release(s);
}
static void virtio_scsi_complete_cmd_req(VirtIOSCSIReq *req)
@@ -864,9 +880,7 @@
return;
}
- virtio_scsi_acquire(s);
virtio_scsi_handle_cmd_vq(s, vq);
- virtio_scsi_release(s);
}
static void virtio_scsi_get_config(VirtIODevice *vdev,
@@ -1013,9 +1027,7 @@
return;
}
- virtio_scsi_acquire(s);
virtio_scsi_handle_event_vq(s, vq);
- virtio_scsi_release(s);
}
static void virtio_scsi_change(SCSIBus *bus, SCSIDevice *dev, SCSISense sense)
@@ -1034,9 +1046,7 @@
},
};
- virtio_scsi_acquire(s);
virtio_scsi_push_event(s, &info);
- virtio_scsi_release(s);
}
}
@@ -1053,17 +1063,13 @@
VirtIODevice *vdev = VIRTIO_DEVICE(hotplug_dev);
VirtIOSCSI *s = VIRTIO_SCSI(vdev);
SCSIDevice *sd = SCSI_DEVICE(dev);
- AioContext *old_context;
int ret;
if (s->ctx && !s->dataplane_fenced) {
if (blk_op_is_blocked(sd->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
return;
}
- old_context = blk_get_aio_context(sd->conf.blk);
- aio_context_acquire(old_context);
ret = blk_set_aio_context(sd->conf.blk, s->ctx, errp);
- aio_context_release(old_context);
if (ret < 0) {
return;
}
@@ -1079,10 +1085,8 @@
},
};
- virtio_scsi_acquire(s);
virtio_scsi_push_event(s, &info);
scsi_bus_set_ua(&s->bus, SENSE_CODE(REPORTED_LUNS_CHANGED));
- virtio_scsi_release(s);
}
}
@@ -1104,17 +1108,13 @@
qdev_simple_device_unplug_cb(hotplug_dev, dev, errp);
if (s->ctx) {
- virtio_scsi_acquire(s);
/* If other users keep the BlockBackend in the iothread, that's ok */
blk_set_aio_context(sd->conf.blk, qemu_get_aio_context(), NULL);
- virtio_scsi_release(s);
}
if (virtio_vdev_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG)) {
- virtio_scsi_acquire(s);
virtio_scsi_push_event(s, &info);
scsi_bus_set_ua(&s->bus, SENSE_CODE(REPORTED_LUNS_CHANGED));
- virtio_scsi_release(s);
}
}
@@ -1235,6 +1235,7 @@
Error *err = NULL;
QTAILQ_INIT(&s->tmf_bh_list);
+ qemu_mutex_init(&s->tmf_bh_lock);
virtio_scsi_common_realize(dev,
virtio_scsi_handle_ctrl,
@@ -1277,6 +1278,7 @@
qbus_set_hotplug_handler(BUS(&s->bus), NULL);
virtio_scsi_common_unrealize(dev);
+ qemu_mutex_destroy(&s->tmf_bh_lock);
}
static Property virtio_scsi_properties[] = {
diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index 5449b6d..157f105 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -63,9 +63,6 @@
* @ctx: the aio context, or NULL if multiple aio contexts (for which the
* caller does not hold a lock) are involved in the polling condition.
* @cond: wait while this conditional expression is true
- * @unlock: whether to unlock and then lock again @ctx. This applies
- * only when waiting for another AioContext from the main loop.
- * Otherwise it's ignored.
*
* Wait while a condition is true. Use this to implement synchronous
* operations that require event loop activity.
@@ -78,7 +75,7 @@
* wait on conditions between two IOThreads since that could lead to deadlock,
* go via the main loop instead.
*/
-#define AIO_WAIT_WHILE_INTERNAL(ctx, cond, unlock) ({ \
+#define AIO_WAIT_WHILE_INTERNAL(ctx, cond) ({ \
bool waited_ = false; \
AioWait *wait_ = &global_aio_wait; \
AioContext *ctx_ = (ctx); \
@@ -95,13 +92,7 @@
assert(qemu_get_current_aio_context() == \
qemu_get_aio_context()); \
while ((cond)) { \
- if (unlock && ctx_) { \
- aio_context_release(ctx_); \
- } \
aio_poll(qemu_get_aio_context(), true); \
- if (unlock && ctx_) { \
- aio_context_acquire(ctx_); \
- } \
waited_ = true; \
} \
} \
@@ -109,10 +100,11 @@
waited_; })
#define AIO_WAIT_WHILE(ctx, cond) \
- AIO_WAIT_WHILE_INTERNAL(ctx, cond, true)
+ AIO_WAIT_WHILE_INTERNAL(ctx, cond)
+/* TODO replace this with AIO_WAIT_WHILE() in a future patch */
#define AIO_WAIT_WHILE_UNLOCKED(ctx, cond) \
- AIO_WAIT_WHILE_INTERNAL(ctx, cond, false)
+ AIO_WAIT_WHILE_INTERNAL(ctx, cond)
/**
* aio_wait_kick:
diff --git a/include/block/aio.h b/include/block/aio.h
index f08b358..af05512 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -278,23 +278,6 @@
*/
void aio_context_unref(AioContext *ctx);
-/* Take ownership of the AioContext. If the AioContext will be shared between
- * threads, and a thread does not want to be interrupted, it will have to
- * take ownership around calls to aio_poll(). Otherwise, aio_poll()
- * automatically takes care of calling aio_context_acquire and
- * aio_context_release.
- *
- * Note that this is separate from bdrv_drained_begin/bdrv_drained_end. A
- * thread still has to call those to avoid being interrupted by the guest.
- *
- * Bottom halves, timers and callbacks can be created or removed without
- * acquiring the AioContext.
- */
-void aio_context_acquire(AioContext *ctx);
-
-/* Relinquish ownership of the AioContext. */
-void aio_context_release(AioContext *ctx);
-
/**
* aio_bh_schedule_oneshot_full: Allocate a new bottom half structure that will
* run only once and as soon as possible.
diff --git a/include/block/block-common.h b/include/block/block-common.h
index d759956..a846023 100644
--- a/include/block/block-common.h
+++ b/include/block/block-common.h
@@ -70,9 +70,6 @@
* automatically takes the graph rdlock when calling the wrapped function. In
* the same way, no_co_wrapper_bdrv_wrlock functions automatically take the
* graph wrlock.
- *
- * If the first parameter of the function is a BlockDriverState, BdrvChild or
- * BlockBackend pointer, the AioContext lock for it is taken in the wrapper.
*/
#define no_co_wrapper
#define no_co_wrapper_bdrv_rdlock
diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h
index 6b21fbc..4ec0b21 100644
--- a/include/block/block-global-state.h
+++ b/include/block/block-global-state.h
@@ -31,11 +31,10 @@
/*
* Global state (GS) API. These functions run under the BQL.
*
- * If a function modifies the graph, it also uses drain and/or
- * aio_context_acquire/release to be sure it has unique access.
- * aio_context locking is needed together with BQL because of
- * the thread-safe I/O API that concurrently runs and accesses
- * the graph without the BQL.
+ * If a function modifies the graph, it also uses the graph lock to be sure it
+ * has unique access. The graph lock is needed together with BQL because of the
+ * thread-safe I/O API that concurrently runs and accesses the graph without
+ * the BQL.
*
* It is important to note that not all of these functions are
* necessarily limited to running under the BQL, but they would
@@ -268,20 +267,6 @@
int bdrv_debug_resume(BlockDriverState *bs, const char *tag);
bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
-/**
- * Locks the AioContext of @bs if it's not the current AioContext. This avoids
- * double locking which could lead to deadlocks: This is a coroutine_fn, so we
- * know we already own the lock of the current AioContext.
- *
- * May only be called in the main thread.
- */
-void coroutine_fn bdrv_co_lock(BlockDriverState *bs);
-
-/**
- * Unlocks the AioContext of @bs if it's not the current AioContext.
- */
-void coroutine_fn bdrv_co_unlock(BlockDriverState *bs);
-
bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx,
GHashTable *visited, Transaction *tran,
Error **errp);
diff --git a/include/block/block-io.h b/include/block/block-io.h
index f8729cc..b49e053 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -31,8 +31,7 @@
/*
* I/O API functions. These functions are thread-safe, and therefore
- * can run in any thread as long as the thread has called
- * aio_context_acquire/release().
+ * can run in any thread.
*
* These functions can only call functions from I/O and Common categories,
* but can be invoked by GS, "I/O or GS" and I/O APIs.
@@ -333,11 +332,10 @@
* "I/O or GS" API functions. These functions can run without
* the BQL, but only in one specific iothread/main loop.
*
- * More specifically, these functions use BDRV_POLL_WHILE(bs), which
- * requires the caller to be either in the main thread and hold
- * the BlockdriverState (bs) AioContext lock, or directly in the
- * home thread that runs the bs AioContext. Calling them from
- * another thread in another AioContext would cause deadlocks.
+ * More specifically, these functions use BDRV_POLL_WHILE(bs), which requires
+ * the caller to be either in the main thread or directly in the home thread
+ * that runs the bs AioContext. Calling them from another thread in another
+ * AioContext would cause deadlocks.
*
* Therefore, these functions are not proper I/O, because they
* can't run in *any* iothreads, but only in a specific one.
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 4e31d16..151279d 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -1192,8 +1192,6 @@
/* The error object in use for blocking operations on backing_hd */
Error *backing_blocker;
- /* Protected by AioContext lock */
-
/*
* If we are reading a disk image, give its size in sectors.
* Generally read-only; it is written to by load_snapshot and
diff --git a/include/block/graph-lock.h b/include/block/graph-lock.h
index 22b5db1..d7545e8 100644
--- a/include/block/graph-lock.h
+++ b/include/block/graph-lock.h
@@ -110,34 +110,17 @@
*
* The wrlock can only be taken from the main loop, with BQL held, as only the
* main loop is allowed to modify the graph.
- *
- * If @bs is non-NULL, its AioContext is temporarily released.
- *
- * This function polls. Callers must not hold the lock of any AioContext other
- * than the current one and the one of @bs.
*/
void no_coroutine_fn TSA_ACQUIRE(graph_lock) TSA_NO_TSA
-bdrv_graph_wrlock(BlockDriverState *bs);
+bdrv_graph_wrlock(void);
/*
* bdrv_graph_wrunlock:
* Write finished, reset global has_writer to 0 and restart
* all readers that are waiting.
- *
- * If @bs is non-NULL, its AioContext is temporarily released.
*/
void no_coroutine_fn TSA_RELEASE(graph_lock) TSA_NO_TSA
-bdrv_graph_wrunlock(BlockDriverState *bs);
-
-/*
- * bdrv_graph_wrunlock_ctx:
- * Write finished, reset global has_writer to 0 and restart
- * all readers that are waiting.
- *
- * If @ctx is non-NULL, its lock is temporarily released.
- */
-void no_coroutine_fn TSA_RELEASE(graph_lock) TSA_NO_TSA
-bdrv_graph_wrunlock_ctx(AioContext *ctx);
+bdrv_graph_wrunlock(void);
/*
* bdrv_graph_co_rdlock:
diff --git a/include/block/snapshot.h b/include/block/snapshot.h
index d49c559..304cc6e 100644
--- a/include/block/snapshot.h
+++ b/include/block/snapshot.h
@@ -86,8 +86,6 @@
/*
* Group operations. All block drivers are involved.
- * These functions will properly handle dataplane (take aio_context_acquire
- * when appropriate for appropriate block drivers
*/
bool bdrv_all_can_snapshot(bool has_devices, strList *devices,
diff --git a/include/hw/qdev-properties-system.h b/include/hw/qdev-properties-system.h
index 91f7a24..06c359c 100644
--- a/include/hw/qdev-properties-system.h
+++ b/include/hw/qdev-properties-system.h
@@ -24,6 +24,7 @@
extern const PropertyInfo qdev_prop_pcie_link_speed;
extern const PropertyInfo qdev_prop_pcie_link_width;
extern const PropertyInfo qdev_prop_cpus390entitlement;
+extern const PropertyInfo qdev_prop_iothread_vq_mapping_list;
#define DEFINE_PROP_PCI_DEVFN(_n, _s, _f, _d) \
DEFINE_PROP_SIGNED(_n, _s, _f, _d, qdev_prop_pci_devfn, int32_t)
@@ -82,4 +83,8 @@
DEFINE_PROP_SIGNED(_n, _s, _f, _d, qdev_prop_cpus390entitlement, \
CpuS390Entitlement)
+#define DEFINE_PROP_IOTHREAD_VQ_MAPPING_LIST(_name, _state, _field) \
+ DEFINE_PROP(_name, _state, _field, qdev_prop_iothread_vq_mapping_list, \
+ IOThreadVirtQueueMappingList *)
+
#endif
diff --git a/include/hw/qdev-properties.h b/include/hw/qdev-properties.h
index 25743a2..09aa04c 100644
--- a/include/hw/qdev-properties.h
+++ b/include/hw/qdev-properties.h
@@ -230,8 +230,8 @@
* @target: Device which has properties to be aliased
* @source: Object to add alias properties to
*
- * Add alias properties to the @source object for all qdev properties on
- * the @target DeviceState.
+ * Add alias properties to the @source object for all properties on the @target
+ * DeviceState.
*
* This is useful when @target is an internal implementation object
* owned by @source, and you want to expose all the properties of that
diff --git a/include/hw/scsi/scsi.h b/include/hw/scsi/scsi.h
index 3692ca8..10c4e82 100644
--- a/include/hw/scsi/scsi.h
+++ b/include/hw/scsi/scsi.h
@@ -69,14 +69,19 @@
{
DeviceState qdev;
VMChangeStateEntry *vmsentry;
- QEMUBH *bh;
uint32_t id;
BlockConf conf;
SCSISense unit_attention;
bool sense_is_ua;
uint8_t sense[SCSI_SENSE_BUF_SIZE];
uint32_t sense_len;
+
+ /*
+ * The requests list is only accessed from the AioContext that executes
+ * requests or from the main loop when IOThread processing is stopped.
+ */
QTAILQ_HEAD(, SCSIRequest) requests;
+
uint32_t channel;
uint32_t lun;
int blocksize;
diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h
index dafec43..5e4091e 100644
--- a/include/hw/virtio/virtio-blk.h
+++ b/include/hw/virtio/virtio-blk.h
@@ -21,6 +21,7 @@
#include "sysemu/block-backend.h"
#include "sysemu/block-ram-registrar.h"
#include "qom/object.h"
+#include "qapi/qapi-types-virtio.h"
#define TYPE_VIRTIO_BLK "virtio-blk-device"
OBJECT_DECLARE_SIMPLE_TYPE(VirtIOBlock, VIRTIO_BLK)
@@ -37,6 +38,7 @@
{
BlockConf conf;
IOThread *iothread;
+ IOThreadVirtQueueMappingList *iothread_vq_mapping_list;
char *serial;
uint32_t request_merging;
uint16_t num_queues;
@@ -54,7 +56,8 @@
struct VirtIOBlock {
VirtIODevice parent_obj;
BlockBackend *blk;
- void *rq;
+ QemuMutex rq_lock;
+ void *rq; /* protected by rq_lock */
VirtIOBlkConf conf;
unsigned short sector_mask;
bool original_wce;
diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h
index 779568a..7f0573b 100644
--- a/include/hw/virtio/virtio-scsi.h
+++ b/include/hw/virtio/virtio-scsi.h
@@ -85,8 +85,9 @@
/*
* TMFs deferred to main loop BH. These fields are protected by
- * virtio_scsi_acquire().
+ * tmf_bh_lock.
*/
+ QemuMutex tmf_bh_lock;
QEMUBH *tmf_bh;
QTAILQ_HEAD(, VirtIOSCSIReq) tmf_bh_list;
@@ -100,20 +101,6 @@
uint32_t host_features;
};
-static inline void virtio_scsi_acquire(VirtIOSCSI *s)
-{
- if (s->ctx) {
- aio_context_acquire(s->ctx);
- }
-}
-
-static inline void virtio_scsi_release(VirtIOSCSI *s)
-{
- if (s->ctx) {
- aio_context_release(s->ctx);
- }
-}
-
void virtio_scsi_common_realize(DeviceState *dev,
VirtIOHandleOutput ctrl,
VirtIOHandleOutput evt,
diff --git a/include/qapi/string-output-visitor.h b/include/qapi/string-output-visitor.h
index 268dfe9..b1ee473 100644
--- a/include/qapi/string-output-visitor.h
+++ b/include/qapi/string-output-visitor.h
@@ -26,9 +26,9 @@
* If everything else succeeds, pass @result to visit_complete() to
* collect the result of the visit.
*
- * The string output visitor does not implement support for visiting
- * QAPI structs, alternates, null, or arbitrary QTypes. It also
- * requires a non-null list argument to visit_start_list().
+ * The string output visitor does not implement support for alternates, null,
+ * or arbitrary QTypes. Struct fields are not shown. It also requires a
+ * non-null list argument to visit_start_list().
*/
Visitor *string_output_visitor_new(bool human, char **result);
diff --git a/include/qemu/job.h b/include/qemu/job.h
index e502787..9ea98b5 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -67,8 +67,6 @@
/**
* The completion function that will be called when the job completes.
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
BlockCompletionFunc *cb;
@@ -264,9 +262,6 @@
*
* This callback will not be invoked if the job has already failed.
* If it fails, abort and then clean will be called.
- *
- * Called with AioContext lock held, since many callbacs implementations
- * use bdrv_* functions that require to hold the lock.
*/
int (*prepare)(Job *job);
@@ -277,9 +272,6 @@
*
* All jobs will complete with a call to either .commit() or .abort() but
* never both.
- *
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
void (*commit)(Job *job);
@@ -290,9 +282,6 @@
*
* All jobs will complete with a call to either .commit() or .abort() but
* never both.
- *
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
void (*abort)(Job *job);
@@ -301,9 +290,6 @@
* .commit() or .abort(). Regardless of which callback is invoked after
* completion, .clean() will always be called, even if the job does not
* belong to a transaction group.
- *
- * Called with AioContext lock held, since many callbacs implementations
- * use bdrv_* functions that require to hold the lock.
*/
void (*clean)(Job *job);
@@ -318,17 +304,12 @@
* READY).
* (If the callback is NULL, the job is assumed to terminate
* without I/O.)
- *
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
bool (*cancel)(Job *job, bool force);
/**
* Called when the job is freed.
- * Called with AioContext lock held, since many callback implementations
- * use bdrv_* functions that require to hold the lock.
*/
void (*free)(Job *job);
};
@@ -424,7 +405,6 @@
* Release a reference that was previously acquired with job_ref_locked() or
* job_create(). If it's the last reference to the object, it will be freed.
*
- * Takes AioContext lock internally to invoke a job->driver callback.
* Called with job lock held.
*/
void job_unref_locked(Job *job);
diff --git a/job.c b/job.c
index 99a2e54..660ce22 100644
--- a/job.c
+++ b/job.c
@@ -464,12 +464,8 @@
assert(!job->txn);
if (job->driver->free) {
- AioContext *aio_context = job->aio_context;
job_unlock();
- /* FIXME: aiocontext lock is required because cb calls blk_unref */
- aio_context_acquire(aio_context);
job->driver->free(job);
- aio_context_release(aio_context);
job_lock();
}
@@ -840,12 +836,10 @@
/*
* Called with job_mutex held, but releases it temporarily.
- * Takes AioContext lock internally to invoke a job->driver callback.
*/
static int job_finalize_single_locked(Job *job)
{
int job_ret;
- AioContext *ctx = job->aio_context;
assert(job_is_completed_locked(job));
@@ -854,7 +848,6 @@
job_ret = job->ret;
job_unlock();
- aio_context_acquire(ctx);
if (!job_ret) {
job_commit(job);
@@ -867,7 +860,6 @@
job->cb(job->opaque, job_ret);
}
- aio_context_release(ctx);
job_lock();
/* Emit events only if we actually started */
@@ -886,17 +878,13 @@
/*
* Called with job_mutex held, but releases it temporarily.
- * Takes AioContext lock internally to invoke a job->driver callback.
*/
static void job_cancel_async_locked(Job *job, bool force)
{
- AioContext *ctx = job->aio_context;
GLOBAL_STATE_CODE();
if (job->driver->cancel) {
job_unlock();
- aio_context_acquire(ctx);
force = job->driver->cancel(job, force);
- aio_context_release(ctx);
job_lock();
} else {
/* No .cancel() means the job will behave as if force-cancelled */
@@ -931,7 +919,6 @@
/*
* Called with job_mutex held, but releases it temporarily.
- * Takes AioContext lock internally to invoke a job->driver callback.
*/
static void job_completed_txn_abort_locked(Job *job)
{
@@ -979,15 +966,12 @@
static int job_prepare_locked(Job *job)
{
int ret;
- AioContext *ctx = job->aio_context;
GLOBAL_STATE_CODE();
if (job->ret == 0 && job->driver->prepare) {
job_unlock();
- aio_context_acquire(ctx);
ret = job->driver->prepare(job);
- aio_context_release(ctx);
job_lock();
job->ret = ret;
job_update_rc_locked(job);
diff --git a/migration/block.c b/migration/block.c
index a15f9bd..6ec6a1d 100644
--- a/migration/block.c
+++ b/migration/block.c
@@ -66,7 +66,7 @@
/* Protected by block migration lock. */
int64_t completed_sectors;
- /* During migration this is protected by iothread lock / AioContext.
+ /* During migration this is protected by bdrv_dirty_bitmap_lock().
* Allocation and free happen during setup and cleanup respectively.
*/
BdrvDirtyBitmap *dirty_bitmap;
@@ -101,7 +101,7 @@
int prev_progress;
int bulk_completed;
- /* Lock must be taken _inside_ the iothread lock and any AioContexts. */
+ /* Lock must be taken _inside_ the iothread lock. */
QemuMutex lock;
} BlkMigState;
@@ -270,7 +270,6 @@
if (bmds->shared_base) {
qemu_mutex_lock_iothread();
- aio_context_acquire(blk_get_aio_context(bb));
/* Skip unallocated sectors; intentionally treats failure or
* partial sector as an allocated sector */
while (cur_sector < total_sectors &&
@@ -281,7 +280,6 @@
}
cur_sector += count >> BDRV_SECTOR_BITS;
}
- aio_context_release(blk_get_aio_context(bb));
qemu_mutex_unlock_iothread();
}
@@ -313,21 +311,16 @@
block_mig_state.submitted++;
blk_mig_unlock();
- /* We do not know if bs is under the main thread (and thus does
- * not acquire the AioContext when doing AIO) or rather under
- * dataplane. Thus acquire both the iothread mutex and the
- * AioContext.
- *
- * This is ugly and will disappear when we make bdrv_* thread-safe,
- * without the need to acquire the AioContext.
+ /*
+ * The migration thread does not have an AioContext. Lock the BQL so that
+ * I/O runs in the main loop AioContext (see
+ * qemu_get_current_aio_context()).
*/
qemu_mutex_lock_iothread();
- aio_context_acquire(blk_get_aio_context(bmds->blk));
bdrv_reset_dirty_bitmap(bmds->dirty_bitmap, cur_sector * BDRV_SECTOR_SIZE,
nr_sectors * BDRV_SECTOR_SIZE);
blk->aiocb = blk_aio_preadv(bb, cur_sector * BDRV_SECTOR_SIZE, &blk->qiov,
0, blk_mig_read_cb, blk);
- aio_context_release(blk_get_aio_context(bmds->blk));
qemu_mutex_unlock_iothread();
bmds->cur_sector = cur_sector + nr_sectors;
@@ -512,7 +505,7 @@
}
}
-/* Called with iothread lock and AioContext taken. */
+/* Called with iothread lock taken. */
static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
int is_async)
@@ -606,9 +599,7 @@
int ret = 1;
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
- aio_context_acquire(blk_get_aio_context(bmds->blk));
ret = mig_save_device_dirty(f, bmds, is_async);
- aio_context_release(blk_get_aio_context(bmds->blk));
if (ret <= 0) {
break;
}
@@ -666,9 +657,9 @@
int64_t dirty = 0;
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
- aio_context_acquire(blk_get_aio_context(bmds->blk));
+ bdrv_dirty_bitmap_lock(bmds->dirty_bitmap);
dirty += bdrv_get_dirty_count(bmds->dirty_bitmap);
- aio_context_release(blk_get_aio_context(bmds->blk));
+ bdrv_dirty_bitmap_unlock(bmds->dirty_bitmap);
}
return dirty;
@@ -681,7 +672,6 @@
{
BlkMigDevState *bmds;
BlockDriverState *bs;
- AioContext *ctx;
unset_dirty_tracking();
@@ -693,13 +683,7 @@
bdrv_op_unblock_all(bs, bmds->blocker);
}
error_free(bmds->blocker);
-
- /* Save ctx, because bmds->blk can disappear during blk_unref. */
- ctx = blk_get_aio_context(bmds->blk);
- aio_context_acquire(ctx);
blk_unref(bmds->blk);
- aio_context_release(ctx);
-
g_free(bmds->blk_name);
g_free(bmds->aio_bitmap);
g_free(bmds);
diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c
index 86ae832..99710c8 100644
--- a/migration/migration-hmp-cmds.c
+++ b/migration/migration-hmp-cmds.c
@@ -852,14 +852,11 @@
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
SnapshotInfoList *snapshots, *snapshot;
- AioContext *ctx = bdrv_get_aio_context(bs);
bool ok = false;
- aio_context_acquire(ctx);
if (bdrv_can_snapshot(bs)) {
ok = bdrv_query_snapshot_info_list(bs, &snapshots, NULL) == 0;
}
- aio_context_release(ctx);
if (!ok) {
continue;
}
diff --git a/migration/savevm.c b/migration/savevm.c
index eec5503..1b9ab7b 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -3049,7 +3049,6 @@
int saved_vm_running;
uint64_t vm_state_size;
g_autoptr(GDateTime) now = g_date_time_new_now_local();
- AioContext *aio_context;
GLOBAL_STATE_CODE();
@@ -3092,7 +3091,6 @@
if (bs == NULL) {
return false;
}
- aio_context = bdrv_get_aio_context(bs);
saved_vm_running = runstate_is_running();
@@ -3101,8 +3099,6 @@
bdrv_drain_all_begin();
- aio_context_acquire(aio_context);
-
memset(sn, 0, sizeof(*sn));
/* fill auxiliary fields */
@@ -3139,14 +3135,6 @@
goto the_end;
}
- /* The bdrv_all_create_snapshot() call that follows acquires the AioContext
- * for itself. BDRV_POLL_WHILE() does not support nested locking because
- * it only releases the lock once. Therefore synchronous I/O will deadlock
- * unless we release the AioContext before bdrv_all_create_snapshot().
- */
- aio_context_release(aio_context);
- aio_context = NULL;
-
ret = bdrv_all_create_snapshot(sn, bs, vm_state_size,
has_devices, devices, errp);
if (ret < 0) {
@@ -3157,10 +3145,6 @@
ret = 0;
the_end:
- if (aio_context) {
- aio_context_release(aio_context);
- }
-
bdrv_drain_all_end();
if (saved_vm_running) {
@@ -3258,7 +3242,6 @@
QEMUSnapshotInfo sn;
QEMUFile *f;
int ret;
- AioContext *aio_context;
MigrationIncomingState *mis = migration_incoming_get_current();
if (!bdrv_all_can_snapshot(has_devices, devices, errp)) {
@@ -3278,12 +3261,9 @@
if (!bs_vm_state) {
return false;
}
- aio_context = bdrv_get_aio_context(bs_vm_state);
/* Don't even try to load empty VM states */
- aio_context_acquire(aio_context);
ret = bdrv_snapshot_find(bs_vm_state, &sn, name);
- aio_context_release(aio_context);
if (ret < 0) {
return false;
} else if (sn.vm_state_size == 0) {
@@ -3320,10 +3300,8 @@
ret = -EINVAL;
goto err_drain;
}
- aio_context_acquire(aio_context);
ret = qemu_loadvm_state(f);
migration_incoming_state_destroy();
- aio_context_release(aio_context);
bdrv_drain_all_end();
diff --git a/nbd/server.c b/nbd/server.c
index 895cf0a..941832f 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -122,26 +122,28 @@
};
struct NBDClient {
- int refcount;
+ int refcount; /* atomic */
void (*close_fn)(NBDClient *client, bool negotiated);
+ QemuMutex lock;
+
NBDExport *exp;
QCryptoTLSCreds *tlscreds;
char *tlsauthz;
QIOChannelSocket *sioc; /* The underlying data channel */
QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
- Coroutine *recv_coroutine;
+ Coroutine *recv_coroutine; /* protected by lock */
CoMutex send_lock;
Coroutine *send_coroutine;
- bool read_yielding;
- bool quiescing;
+ bool read_yielding; /* protected by lock */
+ bool quiescing; /* protected by lock */
QTAILQ_ENTRY(NBDClient) next;
- int nb_requests;
- bool closing;
+ int nb_requests; /* protected by lock */
+ bool closing; /* protected by lock */
uint32_t check_align; /* If non-zero, check for aligned client requests */
@@ -1415,11 +1417,18 @@
len = qio_channel_readv(client->ioc, &iov, 1, errp);
if (len == QIO_CHANNEL_ERR_BLOCK) {
- client->read_yielding = true;
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ client->read_yielding = true;
+
+ /* Prompt main loop thread to re-run nbd_drained_poll() */
+ aio_wait_kick();
+ }
qio_channel_yield(client->ioc, G_IO_IN);
- client->read_yielding = false;
- if (client->quiescing) {
- return -EAGAIN;
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ client->read_yielding = false;
+ if (client->quiescing) {
+ return -EAGAIN;
+ }
}
continue;
} else if (len < 0) {
@@ -1501,14 +1510,17 @@
#define MAX_NBD_REQUESTS 16
+/* Runs in export AioContext and main loop thread */
void nbd_client_get(NBDClient *client)
{
- client->refcount++;
+ qatomic_inc(&client->refcount);
}
void nbd_client_put(NBDClient *client)
{
- if (--client->refcount == 0) {
+ assert(qemu_in_main_thread());
+
+ if (qatomic_fetch_dec(&client->refcount) == 1) {
/* The last reference should be dropped by client->close,
* which is called by client_close.
*/
@@ -1525,17 +1537,47 @@
blk_exp_unref(&client->exp->common);
}
g_free(client->contexts.bitmaps);
+ qemu_mutex_destroy(&client->lock);
g_free(client);
}
}
+/*
+ * Tries to release the reference to @client, but only if other references
+ * remain. This is an optimization for the common case where we want to avoid
+ * the expense of scheduling nbd_client_put() in the main loop thread.
+ *
+ * Returns true upon success or false if the reference was not released because
+ * it is the last reference.
+ */
+static bool nbd_client_put_nonzero(NBDClient *client)
+{
+ int old = qatomic_read(&client->refcount);
+ int expected;
+
+ do {
+ if (old == 1) {
+ return false;
+ }
+
+ expected = old;
+ old = qatomic_cmpxchg(&client->refcount, expected, expected - 1);
+ } while (old != expected);
+
+ return true;
+}
+
static void client_close(NBDClient *client, bool negotiated)
{
- if (client->closing) {
- return;
- }
+ assert(qemu_in_main_thread());
- client->closing = true;
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ if (client->closing) {
+ return;
+ }
+
+ client->closing = true;
+ }
/* Force requests to finish. They will drop their own references,
* then we'll close the socket and free the NBDClient.
@@ -1549,6 +1591,7 @@
}
}
+/* Runs in export AioContext with client->lock held */
static NBDRequestData *nbd_request_get(NBDClient *client)
{
NBDRequestData *req;
@@ -1557,11 +1600,11 @@
client->nb_requests++;
req = g_new0(NBDRequestData, 1);
- nbd_client_get(client);
req->client = client;
return req;
}
+/* Runs in export AioContext with client->lock held */
static void nbd_request_put(NBDRequestData *req)
{
NBDClient *client = req->client;
@@ -1578,8 +1621,6 @@
}
nbd_client_receive_next_request(client);
-
- nbd_client_put(client);
}
static void blk_aio_attached(AioContext *ctx, void *opaque)
@@ -1587,14 +1628,18 @@
NBDExport *exp = opaque;
NBDClient *client;
+ assert(qemu_in_main_thread());
+
trace_nbd_blk_aio_attached(exp->name, ctx);
exp->common.ctx = ctx;
QTAILQ_FOREACH(client, &exp->clients, next) {
- assert(client->nb_requests == 0);
- assert(client->recv_coroutine == NULL);
- assert(client->send_coroutine == NULL);
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ assert(client->nb_requests == 0);
+ assert(client->recv_coroutine == NULL);
+ assert(client->send_coroutine == NULL);
+ }
}
}
@@ -1602,6 +1647,8 @@
{
NBDExport *exp = opaque;
+ assert(qemu_in_main_thread());
+
trace_nbd_blk_aio_detach(exp->name, exp->common.ctx);
exp->common.ctx = NULL;
@@ -1612,8 +1659,12 @@
NBDExport *exp = opaque;
NBDClient *client;
+ assert(qemu_in_main_thread());
+
QTAILQ_FOREACH(client, &exp->clients, next) {
- client->quiescing = true;
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ client->quiescing = true;
+ }
}
}
@@ -1622,28 +1673,48 @@
NBDExport *exp = opaque;
NBDClient *client;
+ assert(qemu_in_main_thread());
+
QTAILQ_FOREACH(client, &exp->clients, next) {
- client->quiescing = false;
- nbd_client_receive_next_request(client);
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ client->quiescing = false;
+ nbd_client_receive_next_request(client);
+ }
}
}
+/* Runs in export AioContext */
+static void nbd_wake_read_bh(void *opaque)
+{
+ NBDClient *client = opaque;
+ qio_channel_wake_read(client->ioc);
+}
+
static bool nbd_drained_poll(void *opaque)
{
NBDExport *exp = opaque;
NBDClient *client;
- QTAILQ_FOREACH(client, &exp->clients, next) {
- if (client->nb_requests != 0) {
- /*
- * If there's a coroutine waiting for a request on nbd_read_eof()
- * enter it here so we don't depend on the client to wake it up.
- */
- if (client->recv_coroutine != NULL && client->read_yielding) {
- qio_channel_wake_read(client->ioc);
- }
+ assert(qemu_in_main_thread());
- return true;
+ QTAILQ_FOREACH(client, &exp->clients, next) {
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ if (client->nb_requests != 0) {
+ /*
+ * If there's a coroutine waiting for a request on nbd_read_eof()
+ * enter it here so we don't depend on the client to wake it up.
+ *
+ * Schedule a BH in the export AioContext to avoid missing the
+ * wake up due to the race between qio_channel_wake_read() and
+ * qio_channel_yield().
+ */
+ if (client->recv_coroutine != NULL && client->read_yielding) {
+ aio_bh_schedule_oneshot(nbd_export_aio_context(client->exp),
+ nbd_wake_read_bh, client);
+ }
+
+ return true;
+ }
}
}
@@ -1654,6 +1725,8 @@
{
NBDExport *exp = container_of(n, NBDExport, eject_notifier);
+ assert(qemu_in_main_thread());
+
blk_exp_request_shutdown(&exp->common);
}
@@ -2539,7 +2612,6 @@
int ret;
g_assert(qemu_in_coroutine());
- assert(client->recv_coroutine == qemu_coroutine_self());
ret = nbd_receive_request(client, request, errp);
if (ret < 0) {
return ret;
@@ -2936,15 +3008,23 @@
static coroutine_fn void nbd_trip(void *opaque)
{
NBDClient *client = opaque;
- NBDRequestData *req;
+ NBDRequestData *req = NULL;
NBDRequest request = { 0 }; /* GCC thinks it can be used uninitialized */
int ret;
Error *local_err = NULL;
+ /*
+ * Note that nbd_client_put() and client_close() must be called from the
+ * main loop thread. Use aio_co_reschedule_self() to switch AioContext
+ * before calling these functions.
+ */
+
trace_nbd_trip();
+
+ qemu_mutex_lock(&client->lock);
+
if (client->closing) {
- nbd_client_put(client);
- return;
+ goto done;
}
if (client->quiescing) {
@@ -2952,14 +3032,27 @@
* We're switching between AIO contexts. Don't attempt to receive a new
* request and kick the main context which may be waiting for us.
*/
- nbd_client_put(client);
client->recv_coroutine = NULL;
aio_wait_kick();
- return;
+ goto done;
}
req = nbd_request_get(client);
- ret = nbd_co_receive_request(req, &request, &local_err);
+
+ /*
+ * nbd_co_receive_request() returns -EAGAIN when nbd_drained_begin() has
+ * set client->quiescing but by the time we get back nbd_drained_end() may
+ * have already cleared client->quiescing. In that case we try again
+ * because nothing else will spawn an nbd_trip() coroutine until we set
+ * client->recv_coroutine = NULL further down.
+ */
+ do {
+ assert(client->recv_coroutine == qemu_coroutine_self());
+ qemu_mutex_unlock(&client->lock);
+ ret = nbd_co_receive_request(req, &request, &local_err);
+ qemu_mutex_lock(&client->lock);
+ } while (ret == -EAGAIN && !client->quiescing);
+
client->recv_coroutine = NULL;
if (client->closing) {
@@ -2971,15 +3064,16 @@
}
if (ret == -EAGAIN) {
- assert(client->quiescing);
goto done;
}
nbd_client_receive_next_request(client);
+
if (ret == -EIO) {
goto disconnect;
}
+ qemu_mutex_unlock(&client->lock);
qio_channel_set_cork(client->ioc, true);
if (ret < 0) {
@@ -2999,6 +3093,10 @@
g_free(request.contexts->bitmaps);
g_free(request.contexts);
}
+
+ qio_channel_set_cork(client->ioc, false);
+ qemu_mutex_lock(&client->lock);
+
if (ret < 0) {
error_prepend(&local_err, "Failed to send reply: ");
goto disconnect;
@@ -3013,21 +3111,36 @@
goto disconnect;
}
- qio_channel_set_cork(client->ioc, false);
done:
- nbd_request_put(req);
- nbd_client_put(client);
+ if (req) {
+ nbd_request_put(req);
+ }
+
+ qemu_mutex_unlock(&client->lock);
+
+ if (!nbd_client_put_nonzero(client)) {
+ aio_co_reschedule_self(qemu_get_aio_context());
+ nbd_client_put(client);
+ }
return;
disconnect:
if (local_err) {
error_reportf_err(local_err, "Disconnect client, due to: ");
}
+
nbd_request_put(req);
+ qemu_mutex_unlock(&client->lock);
+
+ aio_co_reschedule_self(qemu_get_aio_context());
client_close(client, true);
nbd_client_put(client);
}
+/*
+ * Runs in export AioContext and main loop thread. Caller must hold
+ * client->lock.
+ */
static void nbd_client_receive_next_request(NBDClient *client)
{
if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS &&
@@ -3053,7 +3166,9 @@
return;
}
- nbd_client_receive_next_request(client);
+ WITH_QEMU_LOCK_GUARD(&client->lock) {
+ nbd_client_receive_next_request(client);
+ }
}
/*
@@ -3070,6 +3185,7 @@
Coroutine *co;
client = g_new0(NBDClient, 1);
+ qemu_mutex_init(&client->lock);
client->refcount = 1;
client->tlscreds = tlscreds;
if (tlscreds) {
diff --git a/net/colo-compare.c b/net/colo-compare.c
index 7f9e6f8..f2dfc0e 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -1439,12 +1439,10 @@
qemu_bh_delete(s->event_bh);
AioContext *ctx = iothread_get_aio_context(s->iothread);
- aio_context_acquire(ctx);
AIO_WAIT_WHILE(ctx, !s->out_sendco.done);
if (s->notify_dev) {
AIO_WAIT_WHILE(ctx, !s->notify_sendco.done);
}
- aio_context_release(ctx);
/* Release all unhandled packets after compare thead exited */
g_queue_foreach(&s->conn_list, colo_flush_packets, s);
diff --git a/qapi/string-output-visitor.c b/qapi/string-output-visitor.c
index c0cb72d..f0c1dea 100644
--- a/qapi/string-output-visitor.c
+++ b/qapi/string-output-visitor.c
@@ -292,6 +292,20 @@
return true;
}
+static bool start_struct(Visitor *v, const char *name, void **obj,
+ size_t size, Error **errp)
+{
+ return true;
+}
+
+static void end_struct(Visitor *v, void **obj)
+{
+ StringOutputVisitor *sov = to_sov(v);
+
+ /* TODO actually print struct fields */
+ string_output_set(sov, g_strdup("<omitted>"));
+}
+
static bool
start_list(Visitor *v, const char *name, GenericList **list, size_t size,
Error **errp)
@@ -379,6 +393,8 @@
v->visitor.type_str = print_type_str;
v->visitor.type_number = print_type_number;
v->visitor.type_null = print_type_null;
+ v->visitor.start_struct = start_struct;
+ v->visitor.end_struct = end_struct;
v->visitor.start_list = start_list;
v->visitor.next_list = next_list;
v->visitor.end_list = end_list;
diff --git a/qapi/virtio.json b/qapi/virtio.json
index e6dcee7..19c7c36 100644
--- a/qapi/virtio.json
+++ b/qapi/virtio.json
@@ -928,3 +928,32 @@
'data': { 'path': 'str', 'queue': 'uint16', '*index': 'uint16' },
'returns': 'VirtioQueueElement',
'features': [ 'unstable' ] }
+
+##
+# @IOThreadVirtQueueMapping:
+#
+# Describes the subset of virtqueues assigned to an IOThread.
+#
+# @iothread: the id of IOThread object
+#
+# @vqs: an optional array of virtqueue indices that will be handled by this
+# IOThread. When absent, virtqueues are assigned round-robin across all
+# IOThreadVirtQueueMappings provided. Either all IOThreadVirtQueueMappings
+# must have @vqs or none of them must have it.
+#
+# Since: 9.0
+##
+
+{ 'struct': 'IOThreadVirtQueueMapping',
+ 'data': { 'iothread': 'str', '*vqs': ['uint16'] } }
+
+##
+# @DummyVirtioForceArrays:
+#
+# Not used by QMP; hack to let us use IOThreadVirtQueueMappingList internally
+#
+# Since: 9.0
+##
+
+{ 'struct': 'DummyVirtioForceArrays',
+ 'data': { 'unused-iothread-vq-mapping': ['IOThreadVirtQueueMapping'] } }
diff --git a/qemu-img.c b/qemu-img.c
index 5a77f67..7668f86 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -960,7 +960,6 @@
Error *local_err = NULL;
CommonBlockJobCBInfo cbi;
bool image_opts = false;
- AioContext *aio_context;
int64_t rate_limit = 0;
fmt = NULL;
@@ -1078,12 +1077,9 @@
.bs = bs,
};
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
commit_active_start("commit", bs, base_bs, JOB_DEFAULT, rate_limit,
BLOCKDEV_ON_ERROR_REPORT, NULL, common_block_job_cb,
&cbi, false, &local_err);
- aio_context_release(aio_context);
if (local_err) {
goto done;
}
diff --git a/qemu-io.c b/qemu-io.c
index 050c708..6cb1e00 100644
--- a/qemu-io.c
+++ b/qemu-io.c
@@ -414,15 +414,7 @@
static int do_qemuio_command(const char *cmd)
{
- int ret;
- AioContext *ctx =
- qemuio_blk ? blk_get_aio_context(qemuio_blk) : qemu_get_aio_context();
-
- aio_context_acquire(ctx);
- ret = qemuio_command(qemuio_blk, cmd);
- aio_context_release(ctx);
-
- return ret;
+ return qemuio_command(qemuio_blk, cmd);
}
static int command_loop(void)
diff --git a/qemu-nbd.c b/qemu-nbd.c
index 186e646..bac0b5e 100644
--- a/qemu-nbd.c
+++ b/qemu-nbd.c
@@ -1123,9 +1123,7 @@
qdict_put_str(raw_opts, "file", bs->node_name);
qdict_put_int(raw_opts, "offset", dev_offset);
- aio_context_acquire(qemu_get_aio_context());
bs = bdrv_open(NULL, NULL, raw_opts, flags, &error_fatal);
- aio_context_release(qemu_get_aio_context());
blk_remove_bs(blk);
blk_insert_bs(blk, bs, &error_fatal);
diff --git a/replay/replay-debugging.c b/replay/replay-debugging.c
index 3e60549..82c66ff 100644
--- a/replay/replay-debugging.c
+++ b/replay/replay-debugging.c
@@ -144,7 +144,6 @@
char *ret = NULL;
int rv;
int nb_sns, i;
- AioContext *aio_context;
*snapshot_icount = -1;
@@ -152,11 +151,8 @@
if (!bs) {
goto fail;
}
- aio_context = bdrv_get_aio_context(bs);
- aio_context_acquire(aio_context);
nb_sns = bdrv_snapshot_list(bs, &sn_tab);
- aio_context_release(aio_context);
for (i = 0; i < nb_sns; i++) {
rv = bdrv_all_has_snapshot(sn_tab[i].name, false, NULL, NULL);
diff --git a/scripts/block-coroutine-wrapper.py b/scripts/block-coroutine-wrapper.py
index a38e583..dbbde99 100644
--- a/scripts/block-coroutine-wrapper.py
+++ b/scripts/block-coroutine-wrapper.py
@@ -92,8 +92,6 @@ def __init__(self, wrapper_type: str, return_type: str, name: str,
f"{self.name}")
self.target_name = f'{subsystem}_{subname}'
- self.ctx = self.gen_ctx()
-
self.get_result = 's->ret = '
self.ret = 'return s.ret;'
self.co_ret = 'return '
@@ -167,7 +165,7 @@ def create_mixed_wrapper(func: FuncDecl) -> str:
{func.co_ret}{name}({ func.gen_list('{name}') });
}} else {{
{struct_name} s = {{
- .poll_state.ctx = {func.ctx},
+ .poll_state.ctx = qemu_get_current_aio_context(),
.poll_state.in_progress = true,
{ func.gen_block(' .{name} = {name},') }
@@ -191,7 +189,7 @@ def create_co_wrapper(func: FuncDecl) -> str:
{func.return_type} {func.name}({ func.gen_list('{decl}') })
{{
{struct_name} s = {{
- .poll_state.ctx = {func.ctx},
+ .poll_state.ctx = qemu_get_current_aio_context(),
.poll_state.in_progress = true,
{ func.gen_block(' .{name} = {name},') }
@@ -261,8 +259,8 @@ def gen_no_co_wrapper(func: FuncDecl) -> str:
graph_lock=' bdrv_graph_rdlock_main_loop();'
graph_unlock=' bdrv_graph_rdunlock_main_loop();'
elif func.graph_wrlock:
- graph_lock=' bdrv_graph_wrlock(NULL);'
- graph_unlock=' bdrv_graph_wrunlock(NULL);'
+ graph_lock=' bdrv_graph_wrlock();'
+ graph_unlock=' bdrv_graph_wrunlock();'
return f"""\
/*
@@ -278,12 +276,9 @@ def gen_no_co_wrapper(func: FuncDecl) -> str:
static void {name}_bh(void *opaque)
{{
{struct_name} *s = opaque;
- AioContext *ctx = {func.gen_ctx('s->')};
{graph_lock}
- aio_context_acquire(ctx);
{func.get_result}{name}({ func.gen_list('s->{name}') });
- aio_context_release(ctx);
{graph_unlock}
aio_co_wake(s->co);
diff --git a/system/dma-helpers.c b/system/dma-helpers.c
index 36211ac..9b221cf 100644
--- a/system/dma-helpers.c
+++ b/system/dma-helpers.c
@@ -119,13 +119,15 @@
trace_dma_blk_cb(dbs, ret);
- aio_context_acquire(ctx);
+ /* DMAAIOCB is not thread-safe and must be accessed only from dbs->ctx */
+ assert(ctx == qemu_get_current_aio_context());
+
dbs->acb = NULL;
dbs->offset += dbs->iov.size;
if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) {
dma_complete(dbs, ret);
- goto out;
+ return;
}
dma_blk_unmap(dbs);
@@ -168,7 +170,7 @@
trace_dma_map_wait(dbs);
dbs->bh = aio_bh_new(ctx, reschedule_dma, dbs);
cpu_register_map_client(dbs->bh);
- goto out;
+ return;
}
if (!QEMU_IS_ALIGNED(dbs->iov.size, dbs->align)) {
@@ -179,8 +181,6 @@
dbs->acb = dbs->io_func(dbs->offset, &dbs->iov,
dma_blk_cb, dbs, dbs->io_func_opaque);
assert(dbs->acb);
-out:
- aio_context_release(ctx);
}
static void dma_aio_cancel(BlockAIOCB *acb)
diff --git a/system/vl.c b/system/vl.c
index 2bcd9ef..6b87bfa 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -2426,6 +2426,10 @@
}
}
+ if (loadvm && incoming) {
+ error_report("'incoming' and 'loadvm' options are mutually exclusive");
+ exit(EXIT_FAILURE);
+ }
if (loadvm && preconfig_requested) {
error_report("'preconfig' and 'loadvm' options are "
"mutually exclusive");
diff --git a/tests/qemu-iotests/202 b/tests/qemu-iotests/202
index b784dcd..1330424 100755
--- a/tests/qemu-iotests/202
+++ b/tests/qemu-iotests/202
@@ -21,7 +21,7 @@
# Check that QMP 'transaction' blockdev-snapshot-sync with multiple drives on a
# single IOThread completes successfully. This particular command triggered a
# hang due to recursive AioContext locking and BDRV_POLL_WHILE(). Protect
-# against regressions.
+# against regressions even though the AioContext lock no longer exists.
import iotests
diff --git a/tests/qemu-iotests/203 b/tests/qemu-iotests/203
index ab80fd0..1ba8785 100755
--- a/tests/qemu-iotests/203
+++ b/tests/qemu-iotests/203
@@ -21,7 +21,8 @@
# Check that QMP 'migrate' with multiple drives on a single IOThread completes
# successfully. This particular command triggered a hang in the source QEMU
# process due to recursive AioContext locking in bdrv_invalidate_all() and
-# BDRV_POLL_WHILE().
+# BDRV_POLL_WHILE(). Protect against regressions even though the AioContext
+# lock no longer exists.
import iotests
diff --git a/tests/qemu-iotests/tests/qcow2-internal-snapshots b/tests/qemu-iotests/tests/qcow2-internal-snapshots
new file mode 100755
index 0000000..36523ab
--- /dev/null
+++ b/tests/qemu-iotests/tests/qcow2-internal-snapshots
@@ -0,0 +1,170 @@
+#!/usr/bin/env bash
+# group: rw quick
+#
+# Test case for internal snapshots in qcow2
+#
+# Copyright (C) 2023 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=kwolf@redhat.com
+
+seq="$(basename $0)"
+echo "QA output created by $seq"
+
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ../common.rc
+. ../common.filter
+
+# This tests qcow2-specific low-level functionality
+_supported_fmt qcow2
+_supported_proto generic
+# Internal snapshots are (currently) impossible with refcount_bits=1,
+# and generally impossible with external data files
+_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' data_file
+
+IMG_SIZE=64M
+
+_qemu()
+{
+ $QEMU -no-shutdown -nographic -monitor stdio -serial none \
+ -blockdev file,filename="$TEST_IMG",node-name=disk0-file \
+ -blockdev "$IMGFMT",file=disk0-file,node-name=disk0 \
+ -object iothread,id=iothread0 \
+ -device virtio-scsi,iothread=iothread0 \
+ -device scsi-hd,drive=disk0,share-rw=on \
+ "$@" 2>&1 |\
+ _filter_qemu | _filter_hmp | _filter_qemu_io
+}
+
+_make_test_img $IMG_SIZE
+
+echo
+echo "=== Write some data, take a snapshot and overwrite part of it ==="
+echo
+
+{
+ echo 'qemu-io disk0 "write -P0x11 0 1M"'
+ # Give qemu some time to boot before saving the VM state
+ sleep 0.5
+ echo "savevm snap0"
+ echo 'qemu-io disk0 "write -P0x22 0 512k"'
+ echo "quit"
+} | _qemu
+
+echo
+$QEMU_IMG snapshot -l "$TEST_IMG" | _filter_date | _filter_vmstate_size
+_check_test_img
+
+echo
+echo "=== Verify that loading the snapshot reverts to the old content ==="
+echo
+
+{
+ # -loadvm reverted the write from the previous QEMU instance
+ echo 'qemu-io disk0 "read -P0x11 0 1M"'
+
+ # Verify that it works without restarting QEMU, too
+ echo 'qemu-io disk0 "write -P0x33 512k 512k"'
+ echo "loadvm snap0"
+ echo 'qemu-io disk0 "read -P0x11 0 1M"'
+
+ # Verify COW by writing a partial cluster
+ echo 'qemu-io disk0 "write -P0x33 63k 2k"'
+ echo 'qemu-io disk0 "read -P0x11 0 63k"'
+ echo 'qemu-io disk0 "read -P0x33 63k 2k"'
+ echo 'qemu-io disk0 "read -P0x11 65k 63k"'
+
+ # Take a second snapshot
+ echo "savevm snap1"
+
+ echo "quit"
+} | _qemu -loadvm snap0
+
+echo
+$QEMU_IMG snapshot -l "$TEST_IMG" | _filter_date | _filter_vmstate_size
+_check_test_img
+
+echo
+echo "=== qemu-img snapshot can revert to snapshots ==="
+echo
+
+$QEMU_IMG snapshot -a snap0 "$TEST_IMG"
+$QEMU_IO -c "read -P0x11 0 1M" "$TEST_IMG" | _filter_qemu_io
+$QEMU_IMG snapshot -a snap1 "$TEST_IMG"
+$QEMU_IO \
+ -c "read -P0x11 0 63k" \
+ -c "read -P0x33 63k 2k" \
+ -c "read -P0x11 65k 63k" \
+ "$TEST_IMG" | _filter_qemu_io
+
+echo
+echo "=== Deleting snapshots ==="
+echo
+{
+ # The active layer stays unaffected by deleting the snapshot
+ echo "delvm snap1"
+ echo 'qemu-io disk0 "read -P0x11 0 63k"'
+ echo 'qemu-io disk0 "read -P0x33 63k 2k"'
+ echo 'qemu-io disk0 "read -P0x11 65k 63k"'
+
+ echo "quit"
+} | _qemu
+
+
+echo
+$QEMU_IMG snapshot -l "$TEST_IMG" | _filter_date | _filter_vmstate_size
+_check_test_img
+
+echo
+echo "=== Error cases ==="
+echo
+
+# snap1 should not exist any more
+_qemu -loadvm snap1
+
+echo
+{
+ echo "loadvm snap1"
+ echo "quit"
+} | _qemu
+
+# Snapshot operations and inactive images are incompatible
+echo
+_qemu -loadvm snap0 -incoming defer
+{
+ echo "loadvm snap0"
+ echo "delvm snap0"
+ echo "savevm snap1"
+ echo "quit"
+} | _qemu -incoming defer
+
+# -loadvm and -preconfig are incompatible
+echo
+_qemu -loadvm snap0 -preconfig
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/tests/qcow2-internal-snapshots.out b/tests/qemu-iotests/tests/qcow2-internal-snapshots.out
new file mode 100644
index 0000000..438f535
--- /dev/null
+++ b/tests/qemu-iotests/tests/qcow2-internal-snapshots.out
@@ -0,0 +1,107 @@
+QA output created by qcow2-internal-snapshots
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
+
+=== Write some data, take a snapshot and overwrite part of it ===
+
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) qemu-io disk0 "write -P0x11 0 1M"
+wrote 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) savevm snap0
+(qemu) qemu-io disk0 "write -P0x22 0 512k"
+wrote 524288/524288 bytes at offset 0
+512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) quit
+
+Snapshot list:
+ID TAG VM SIZE DATE VM CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+No errors were found on the image.
+
+=== Verify that loading the snapshot reverts to the old content ===
+
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) qemu-io disk0 "read -P0x11 0 1M"
+read 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) qemu-io disk0 "write -P0x33 512k 512k"
+wrote 524288/524288 bytes at offset 524288
+512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) loadvm snap0
+(qemu) qemu-io disk0 "read -P0x11 0 1M"
+read 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) qemu-io disk0 "write -P0x33 63k 2k"
+wrote 2048/2048 bytes at offset 64512
+2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) qemu-io disk0 "read -P0x11 0 63k"
+read 64512/64512 bytes at offset 0
+63 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) qemu-io disk0 "read -P0x33 63k 2k"
+read 2048/2048 bytes at offset 64512
+2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) qemu-io disk0 "read -P0x11 65k 63k"
+read 64512/64512 bytes at offset 66560
+63 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) savevm snap1
+(qemu) quit
+
+Snapshot list:
+ID TAG VM SIZE DATE VM CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+2 snap1 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+No errors were found on the image.
+
+=== qemu-img snapshot can revert to snapshots ===
+
+read 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 64512/64512 bytes at offset 0
+63 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 2048/2048 bytes at offset 64512
+2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 64512/64512 bytes at offset 66560
+63 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+=== Deleting snapshots ===
+
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) delvm snap1
+(qemu) qemu-io disk0 "read -P0x11 0 63k"
+read 64512/64512 bytes at offset 0
+63 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) qemu-io disk0 "read -P0x33 63k 2k"
+read 2048/2048 bytes at offset 64512
+2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) qemu-io disk0 "read -P0x11 65k 63k"
+read 64512/64512 bytes at offset 66560
+63 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+(qemu) quit
+
+Snapshot list:
+ID TAG VM SIZE DATE VM CLOCK ICOUNT
+1 snap0 SIZE yyyy-mm-dd hh:mm:ss 00:00:00.000
+No errors were found on the image.
+
+=== Error cases ===
+
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) QEMU_PROG: Snapshot 'snap1' does not exist in one or more devices
+
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) loadvm snap1
+Error: Snapshot 'snap1' does not exist in one or more devices
+(qemu) quit
+
+QEMU_PROG: 'incoming' and 'loadvm' options are mutually exclusive
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) loadvm snap0
+Error: Device 'disk0' is writable but does not support snapshots
+(qemu) delvm snap0
+Error: Device 'disk0' is writable but does not support snapshots
+(qemu) savevm snap1
+Error: Device 'disk0' is writable but does not support snapshots
+(qemu) quit
+
+QEMU_PROG: 'preconfig' and 'loadvm' options are mutually exclusive
+*** done
diff --git a/tests/tsan/suppressions.tsan b/tests/tsan/suppressions.tsan
index d9a002a..b3ef59c 100644
--- a/tests/tsan/suppressions.tsan
+++ b/tests/tsan/suppressions.tsan
@@ -4,7 +4,6 @@
# TSan reports a double lock on RECURSIVE mutexes.
# Since the recursive lock is intentional, we choose to ignore it.
-mutex:aio_context_acquire
mutex:pthread_mutex_lock
# TSan reports a race between pthread_mutex_init() and
diff --git a/tests/unit/test-aio.c b/tests/unit/test-aio.c
index 337b6e4..e77d86b 100644
--- a/tests/unit/test-aio.c
+++ b/tests/unit/test-aio.c
@@ -100,76 +100,12 @@
/* Tests using aio_*. */
-typedef struct {
- QemuMutex start_lock;
- EventNotifier notifier;
- bool thread_acquired;
-} AcquireTestData;
-
-static void *test_acquire_thread(void *opaque)
-{
- AcquireTestData *data = opaque;
-
- /* Wait for other thread to let us start */
- qemu_mutex_lock(&data->start_lock);
- qemu_mutex_unlock(&data->start_lock);
-
- /* event_notifier_set might be called either before or after
- * the main thread's call to poll(). The test case's outcome
- * should be the same in either case.
- */
- event_notifier_set(&data->notifier);
- aio_context_acquire(ctx);
- aio_context_release(ctx);
-
- data->thread_acquired = true; /* success, we got here */
-
- return NULL;
-}
-
static void set_event_notifier(AioContext *nctx, EventNotifier *notifier,
EventNotifierHandler *handler)
{
aio_set_event_notifier(nctx, notifier, handler, NULL, NULL);
}
-static void dummy_notifier_read(EventNotifier *n)
-{
- event_notifier_test_and_clear(n);
-}
-
-static void test_acquire(void)
-{
- QemuThread thread;
- AcquireTestData data;
-
- /* Dummy event notifier ensures aio_poll() will block */
- event_notifier_init(&data.notifier, false);
- set_event_notifier(ctx, &data.notifier, dummy_notifier_read);
- g_assert(!aio_poll(ctx, false)); /* consume aio_notify() */
-
- qemu_mutex_init(&data.start_lock);
- qemu_mutex_lock(&data.start_lock);
- data.thread_acquired = false;
-
- qemu_thread_create(&thread, "test_acquire_thread",
- test_acquire_thread,
- &data, QEMU_THREAD_JOINABLE);
-
- /* Block in aio_poll(), let other thread kick us and acquire context */
- aio_context_acquire(ctx);
- qemu_mutex_unlock(&data.start_lock); /* let the thread run */
- g_assert(aio_poll(ctx, true));
- g_assert(!data.thread_acquired);
- aio_context_release(ctx);
-
- qemu_thread_join(&thread);
- set_event_notifier(ctx, &data.notifier, NULL);
- event_notifier_cleanup(&data.notifier);
-
- g_assert(data.thread_acquired);
-}
-
static void test_bh_schedule(void)
{
BHTestData data = { .n = 0 };
@@ -879,7 +815,7 @@
qemu_thread_get_self(&this_thread);
co = qemu_coroutine_create(co_check_current_thread, &this_thread);
- qemu_thread_create(&worker_thread, "test_acquire_thread",
+ qemu_thread_create(&worker_thread, "test_aio_co_enter",
test_aio_co_enter,
co, QEMU_THREAD_JOINABLE);
@@ -899,7 +835,6 @@
while (g_main_context_iteration(NULL, false));
g_test_init(&argc, &argv, NULL);
- g_test_add_func("/aio/acquire", test_acquire);
g_test_add_func("/aio/bh/schedule", test_bh_schedule);
g_test_add_func("/aio/bh/schedule10", test_bh_schedule10);
g_test_add_func("/aio/bh/cancel", test_bh_cancel);
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index 704d1a3..17830a6 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -179,13 +179,7 @@
static void do_drain_begin_unlocked(enum drain_type drain_type, BlockDriverState *bs)
{
- if (drain_type != BDRV_DRAIN_ALL) {
- aio_context_acquire(bdrv_get_aio_context(bs));
- }
do_drain_begin(drain_type, bs);
- if (drain_type != BDRV_DRAIN_ALL) {
- aio_context_release(bdrv_get_aio_context(bs));
- }
}
static BlockBackend * no_coroutine_fn test_setup(void)
@@ -209,13 +203,7 @@
static void do_drain_end_unlocked(enum drain_type drain_type, BlockDriverState *bs)
{
- if (drain_type != BDRV_DRAIN_ALL) {
- aio_context_acquire(bdrv_get_aio_context(bs));
- }
do_drain_end(drain_type, bs);
- if (drain_type != BDRV_DRAIN_ALL) {
- aio_context_release(bdrv_get_aio_context(bs));
- }
}
/*
@@ -520,12 +508,8 @@
{
struct test_iothread_data *data = opaque;
- /* Test that the AioContext is not yet locked in a random BH that is
- * executed during drain, otherwise this would deadlock. */
- aio_context_acquire(bdrv_get_aio_context(data->bs));
bdrv_flush(data->bs);
bdrv_dec_in_flight(data->bs); /* incremented by test_iothread_common() */
- aio_context_release(bdrv_get_aio_context(data->bs));
}
/*
@@ -567,7 +551,6 @@
blk_set_disable_request_queuing(blk, true);
blk_set_aio_context(blk, ctx_a, &error_abort);
- aio_context_acquire(ctx_a);
s->bh_indirection_ctx = ctx_b;
@@ -582,8 +565,6 @@
g_assert(acb != NULL);
g_assert_cmpint(aio_ret, ==, -EINPROGRESS);
- aio_context_release(ctx_a);
-
data = (struct test_iothread_data) {
.bs = bs,
.drain_type = drain_type,
@@ -592,10 +573,6 @@
switch (drain_thread) {
case 0:
- if (drain_type != BDRV_DRAIN_ALL) {
- aio_context_acquire(ctx_a);
- }
-
/*
* Increment in_flight so that do_drain_begin() waits for
* test_iothread_main_thread_bh(). This prevents the race between
@@ -613,20 +590,10 @@
do_drain_begin(drain_type, bs);
g_assert_cmpint(bs->in_flight, ==, 0);
- if (drain_type != BDRV_DRAIN_ALL) {
- aio_context_release(ctx_a);
- }
qemu_event_wait(&done_event);
- if (drain_type != BDRV_DRAIN_ALL) {
- aio_context_acquire(ctx_a);
- }
g_assert_cmpint(aio_ret, ==, 0);
do_drain_end(drain_type, bs);
-
- if (drain_type != BDRV_DRAIN_ALL) {
- aio_context_release(ctx_a);
- }
break;
case 1:
co = qemu_coroutine_create(test_iothread_drain_co_entry, &data);
@@ -637,9 +604,7 @@
g_assert_not_reached();
}
- aio_context_acquire(ctx_a);
blk_set_aio_context(blk, qemu_get_aio_context(), &error_abort);
- aio_context_release(ctx_a);
bdrv_unref(bs);
blk_unref(blk);
@@ -757,7 +722,6 @@
BlockJob *job;
TestBlockJob *tjob;
IOThread *iothread = NULL;
- AioContext *ctx;
int ret;
src = bdrv_new_open_driver(&bdrv_test, "source", BDRV_O_RDWR,
@@ -787,11 +751,11 @@
}
if (use_iothread) {
+ AioContext *ctx;
+
iothread = iothread_new();
ctx = iothread_get_aio_context(iothread);
blk_set_aio_context(blk_src, ctx, &error_abort);
- } else {
- ctx = qemu_get_aio_context();
}
target = bdrv_new_open_driver(&bdrv_test, "target", BDRV_O_RDWR,
@@ -800,16 +764,15 @@
blk_insert_bs(blk_target, target, &error_abort);
blk_set_allow_aio_context_change(blk_target, true);
- aio_context_acquire(ctx);
tjob = block_job_create("job0", &test_job_driver, NULL, src,
0, BLK_PERM_ALL,
0, 0, NULL, NULL, &error_abort);
tjob->bs = src;
job = &tjob->common;
- bdrv_graph_wrlock(target);
+ bdrv_graph_wrlock();
block_job_add_bdrv(job, "target", target, 0, BLK_PERM_ALL, &error_abort);
- bdrv_graph_wrunlock(target);
+ bdrv_graph_wrunlock();
switch (result) {
case TEST_JOB_SUCCESS:
@@ -821,7 +784,6 @@
tjob->prepare_ret = -EIO;
break;
}
- aio_context_release(ctx);
job_start(&job->job);
@@ -912,12 +874,10 @@
}
g_assert_cmpint(ret, ==, (result == TEST_JOB_SUCCESS ? 0 : -EIO));
- aio_context_acquire(ctx);
if (use_iothread) {
blk_set_aio_context(blk_src, qemu_get_aio_context(), &error_abort);
assert(blk_get_aio_context(blk_target) == qemu_get_aio_context());
}
- aio_context_release(ctx);
blk_unref(blk_src);
blk_unref(blk_target);
@@ -991,11 +951,11 @@
{
BdrvChild *c, *next_c;
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
QLIST_FOREACH_SAFE(c, &bs->children, next, next_c) {
bdrv_unref_child(bs, c);
}
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
}
static int coroutine_fn GRAPH_RDLOCK
@@ -1085,10 +1045,10 @@
null_bs = bdrv_open("null-co://", NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
&error_abort);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_attach_child(bs, null_bs, "null-child", &child_of_bds,
BDRV_CHILD_DATA, &error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
/* This child will be the one to pass to requests through to, and
* it will stall until a drain occurs */
@@ -1096,21 +1056,21 @@
&error_abort);
child_bs->total_sectors = 65536 >> BDRV_SECTOR_BITS;
/* Takes our reference to child_bs */
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
tts->wait_child = bdrv_attach_child(bs, child_bs, "wait-child",
&child_of_bds,
BDRV_CHILD_DATA | BDRV_CHILD_PRIMARY,
&error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
/* This child is just there to be deleted
* (for detach_instead_of_delete == true) */
null_bs = bdrv_open("null-co://", NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
&error_abort);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_attach_child(bs, null_bs, "null-child", &child_of_bds, BDRV_CHILD_DATA,
&error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
blk = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
blk_insert_bs(blk, bs, &error_abort);
@@ -1193,14 +1153,14 @@
bdrv_dec_in_flight(data->child_b->bs);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_unref_child(data->parent_b, data->child_b);
bdrv_ref(data->c);
data->child_c = bdrv_attach_child(data->parent_b, data->c, "PB-C",
&child_of_bds, BDRV_CHILD_DATA,
&error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
}
static void coroutine_mixed_fn detach_by_parent_aio_cb(void *opaque, int ret)
@@ -1298,7 +1258,7 @@
/* Set child relationships */
bdrv_ref(b);
bdrv_ref(a);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
child_b = bdrv_attach_child(parent_b, b, "PB-B", &child_of_bds,
BDRV_CHILD_DATA, &error_abort);
child_a = bdrv_attach_child(parent_b, a, "PB-A", &child_of_bds,
@@ -1308,7 +1268,7 @@
bdrv_attach_child(parent_a, a, "PA-A",
by_parent_cb ? &child_of_bds : &detach_by_driver_cb_class,
BDRV_CHILD_DATA, &error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
g_assert_cmpint(parent_a->refcnt, ==, 1);
g_assert_cmpint(parent_b->refcnt, ==, 1);
@@ -1401,9 +1361,7 @@
g_assert_cmpint(base_s->drain_count, ==, 1);
g_assert_cmpint(base->in_flight, ==, 0);
- aio_context_acquire(qemu_get_aio_context());
bdrv_append(overlay, base, &error_abort);
- aio_context_release(qemu_get_aio_context());
g_assert_cmpint(base->in_flight, ==, 0);
g_assert_cmpint(overlay->in_flight, ==, 0);
@@ -1438,16 +1396,11 @@
bdrv_drained_begin(bs);
bdrv_try_change_aio_context(bs, ctx_a, NULL, &error_abort);
-
- aio_context_acquire(ctx_a);
bdrv_drained_end(bs);
bdrv_drained_begin(bs);
bdrv_try_change_aio_context(bs, ctx_b, NULL, &error_abort);
- aio_context_release(ctx_a);
- aio_context_acquire(ctx_b);
bdrv_try_change_aio_context(bs, qemu_get_aio_context(), NULL, &error_abort);
- aio_context_release(ctx_b);
bdrv_drained_end(bs);
bdrv_unref(bs);
@@ -1727,7 +1680,7 @@
* Establish the chain last, so the chain links are the first
* elements in the BDS.parents lists
*/
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
for (i = 0; i < 3; i++) {
if (i) {
/* Takes the reference to chain[i - 1] */
@@ -1735,7 +1688,7 @@
&chain_child_class, BDRV_CHILD_COW, &error_abort);
}
}
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
job = block_job_create("job", &test_simple_job_driver, NULL, job_node,
0, BLK_PERM_ALL, 0, 0, NULL, NULL, &error_abort);
@@ -1982,10 +1935,10 @@
new_child_bs->total_sectors = 1;
bdrv_ref(old_child_bs);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_attach_child(parent_bs, old_child_bs, "child", &child_of_bds,
BDRV_CHILD_COW, &error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
parent_s->setup_completed = true;
for (i = 0; i < old_drain_count; i++) {
@@ -2016,9 +1969,9 @@
g_assert(parent_bs->quiesce_counter == old_drain_count);
bdrv_drained_begin(old_child_bs);
bdrv_drained_begin(new_child_bs);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_replace_node(old_child_bs, new_child_bs, &error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
bdrv_drained_end(new_child_bs);
bdrv_drained_end(old_child_bs);
g_assert(parent_bs->quiesce_counter == new_drain_count);
diff --git a/tests/unit/test-bdrv-graph-mod.c b/tests/unit/test-bdrv-graph-mod.c
index 074adcb..cafc023 100644
--- a/tests/unit/test-bdrv-graph-mod.c
+++ b/tests/unit/test-bdrv-graph-mod.c
@@ -137,15 +137,13 @@
blk_insert_bs(root, bs, &error_abort);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_attach_child(filter, bs, "child", &child_of_bds,
BDRV_CHILD_DATA, &error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
- aio_context_acquire(qemu_get_aio_context());
ret = bdrv_append(filter, bs, NULL);
g_assert_cmpint(ret, <, 0);
- aio_context_release(qemu_get_aio_context());
bdrv_unref(filter);
blk_unref(root);
@@ -206,14 +204,12 @@
bdrv_set_backing_hd(target, bs, &error_abort);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
g_assert(target->backing->bs == bs);
bdrv_attach_child(filter, target, "target", &child_of_bds,
BDRV_CHILD_DATA, &error_abort);
- bdrv_graph_wrunlock(NULL);
- aio_context_acquire(qemu_get_aio_context());
+ bdrv_graph_wrunlock();
bdrv_append(filter, bs, &error_abort);
- aio_context_release(qemu_get_aio_context());
bdrv_graph_rdlock_main_loop();
g_assert(target->backing->bs == bs);
@@ -248,7 +244,7 @@
bdrv_ref(base);
bdrv_ref(fl1);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_attach_child(top, fl1, "backing", &child_of_bds,
BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
&error_abort);
@@ -260,7 +256,7 @@
&error_abort);
bdrv_replace_node(fl1, fl2, &error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
bdrv_drained_end(fl2);
bdrv_drained_end(fl1);
@@ -367,7 +363,7 @@
*/
bdrv_ref(base);
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_attach_child(top, ws, "file", &child_of_bds, BDRV_CHILD_DATA,
&error_abort);
c_fl1 = bdrv_attach_child(ws, fl1, "first", &child_of_bds,
@@ -380,7 +376,7 @@
bdrv_attach_child(fl2, base, "backing", &child_of_bds,
BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
&error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
/* Select fl1 as first child to be active */
s->selected = c_fl1;
@@ -434,15 +430,13 @@
BlockDriverState *base = no_perm_node("base");
BlockDriverState *fl = exclusive_writer_node("fl1");
- bdrv_graph_wrlock(NULL);
+ bdrv_graph_wrlock();
bdrv_attach_child(top, base, "backing", &child_of_bds,
BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
&error_abort);
- bdrv_graph_wrunlock(NULL);
+ bdrv_graph_wrunlock();
- aio_context_acquire(qemu_get_aio_context());
bdrv_append(fl, base, &error_abort);
- aio_context_release(qemu_get_aio_context());
bdrv_unref(fl);
bdrv_unref(top);
}
diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c
index 9b15d27..3766d5d 100644
--- a/tests/unit/test-block-iothread.c
+++ b/tests/unit/test-block-iothread.c
@@ -483,7 +483,6 @@
bdrv_graph_rdunlock_main_loop();
blk_set_aio_context(blk, ctx, &error_abort);
- aio_context_acquire(ctx);
if (t->fn) {
t->fn(c);
}
@@ -491,7 +490,6 @@
t->blkfn(blk);
}
blk_set_aio_context(blk, qemu_get_aio_context(), &error_abort);
- aio_context_release(ctx);
bdrv_unref(bs);
blk_unref(blk);
@@ -576,9 +574,7 @@
aio_poll(qemu_get_aio_context(), false);
}
- aio_context_acquire(ctx);
blk_set_aio_context(blk, qemu_get_aio_context(), &error_abort);
- aio_context_release(ctx);
tjob->n = 0;
while (tjob->n == 0) {
@@ -595,9 +591,7 @@
WITH_JOB_LOCK_GUARD() {
job_complete_sync_locked(&tjob->common.job, &error_abort);
}
- aio_context_acquire(ctx);
blk_set_aio_context(blk, qemu_get_aio_context(), &error_abort);
- aio_context_release(ctx);
bdrv_unref(bs);
blk_unref(blk);
@@ -654,9 +648,7 @@
/* Switch the AioContext back */
main_ctx = qemu_get_aio_context();
- aio_context_acquire(ctx);
blk_set_aio_context(blk, main_ctx, &error_abort);
- aio_context_release(ctx);
g_assert(blk_get_aio_context(blk) == main_ctx);
g_assert(bdrv_get_aio_context(bs_a) == main_ctx);
g_assert(bdrv_get_aio_context(bs_verify) == main_ctx);
@@ -732,9 +724,7 @@
/* Switch the AioContext back */
main_ctx = qemu_get_aio_context();
- aio_context_acquire(ctx);
blk_set_aio_context(blk, main_ctx, &error_abort);
- aio_context_release(ctx);
g_assert(blk_get_aio_context(blk) == main_ctx);
g_assert(bdrv_get_aio_context(bs_verify) == main_ctx);
g_assert(bdrv_get_aio_context(bs_a) == main_ctx);
@@ -764,13 +754,11 @@
&error_abort);
/* Start a mirror job */
- aio_context_acquire(main_ctx);
mirror_start("job0", src, target, NULL, JOB_DEFAULT, 0, 0, 0,
MIRROR_SYNC_MODE_NONE, MIRROR_OPEN_BACKING_CHAIN, false,
BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT,
false, "filter_node", MIRROR_COPY_MODE_BACKGROUND,
&error_abort);
- aio_context_release(main_ctx);
WITH_JOB_LOCK_GUARD() {
job = job_get_locked("job0");
@@ -785,9 +773,7 @@
g_assert(job->aio_context == ctx);
/* Change the AioContext of target */
- aio_context_acquire(ctx);
bdrv_try_change_aio_context(target, main_ctx, NULL, &error_abort);
- aio_context_release(ctx);
g_assert(bdrv_get_aio_context(src) == main_ctx);
g_assert(bdrv_get_aio_context(target) == main_ctx);
g_assert(bdrv_get_aio_context(filter) == main_ctx);
@@ -805,10 +791,8 @@
g_assert(bdrv_get_aio_context(filter) == main_ctx);
/* ...unless we explicitly allow it */
- aio_context_acquire(ctx);
blk_set_allow_aio_context_change(blk, true);
bdrv_try_change_aio_context(target, ctx, NULL, &error_abort);
- aio_context_release(ctx);
g_assert(blk_get_aio_context(blk) == ctx);
g_assert(bdrv_get_aio_context(src) == ctx);
@@ -817,10 +801,8 @@
job_cancel_sync_all();
- aio_context_acquire(ctx);
blk_set_aio_context(blk, main_ctx, &error_abort);
bdrv_try_change_aio_context(target, main_ctx, NULL, &error_abort);
- aio_context_release(ctx);
blk_unref(blk);
bdrv_unref(src);
@@ -836,7 +818,6 @@
BlockDriverState *bs, *filter;
QDict *options;
- aio_context_acquire(main_ctx);
blk = blk_new(ctx, BLK_PERM_ALL, BLK_PERM_ALL);
bs = bdrv_new_open_driver(&bdrv_test, "base", BDRV_O_RDWR, &error_abort);
blk_insert_bs(blk, bs, &error_abort);
@@ -846,15 +827,12 @@
qdict_put_str(options, "file", "base");
filter = bdrv_open(NULL, NULL, options, BDRV_O_RDWR, &error_abort);
- aio_context_release(main_ctx);
g_assert(blk_get_aio_context(blk) == ctx);
g_assert(bdrv_get_aio_context(bs) == ctx);
g_assert(bdrv_get_aio_context(filter) == ctx);
- aio_context_acquire(ctx);
blk_set_aio_context(blk, main_ctx, &error_abort);
- aio_context_release(ctx);
g_assert(blk_get_aio_context(blk) == main_ctx);
g_assert(bdrv_get_aio_context(bs) == main_ctx);
g_assert(bdrv_get_aio_context(filter) == main_ctx);
@@ -868,11 +846,9 @@
{
IOThread *iothread = iothread_new();
AioContext *ctx = iothread_get_aio_context(iothread);
- AioContext *main_ctx = qemu_get_aio_context();
BlockBackend *blk;
BlockDriverState *bs;
- aio_context_acquire(main_ctx);
blk = blk_new(ctx, BLK_PERM_ALL, BLK_PERM_ALL);
bs = bdrv_new_open_driver(&bdrv_test, "base", BDRV_O_RDWR, &error_abort);
bs->total_sectors = 65536 / BDRV_SECTOR_SIZE;
@@ -881,25 +857,18 @@
blk_insert_bs(blk, bs, &error_abort);
g_assert(blk_get_aio_context(blk) == ctx);
g_assert(bdrv_get_aio_context(bs) == ctx);
- aio_context_release(main_ctx);
/* Remove the node again */
- aio_context_acquire(ctx);
blk_remove_bs(blk);
- aio_context_release(ctx);
g_assert(blk_get_aio_context(blk) == ctx);
g_assert(bdrv_get_aio_context(bs) == qemu_get_aio_context());
/* Re-attach the node */
- aio_context_acquire(main_ctx);
blk_insert_bs(blk, bs, &error_abort);
- aio_context_release(main_ctx);
g_assert(blk_get_aio_context(blk) == ctx);
g_assert(bdrv_get_aio_context(bs) == ctx);
- aio_context_acquire(ctx);
blk_set_aio_context(blk, qemu_get_aio_context(), &error_abort);
- aio_context_release(ctx);
bdrv_unref(bs);
blk_unref(blk);
}
diff --git a/tests/unit/test-blockjob.c b/tests/unit/test-blockjob.c
index a130f6f..fe3e0d2 100644
--- a/tests/unit/test-blockjob.c
+++ b/tests/unit/test-blockjob.c
@@ -228,7 +228,6 @@
BlockJob *job = &s->common;
BlockBackend *blk = s->blk;
JobStatus sts = job->job.status;
- AioContext *ctx = job->job.aio_context;
job_cancel_sync(&job->job, true);
WITH_JOB_LOCK_GUARD() {
@@ -240,9 +239,7 @@
job_unref_locked(&job->job);
}
- aio_context_acquire(ctx);
destroy_blk(blk);
- aio_context_release(ctx);
}
@@ -391,132 +388,6 @@
cancel_common(s);
}
-/* (See test_yielding_driver for the job description) */
-typedef struct YieldingJob {
- BlockJob common;
- bool should_complete;
-} YieldingJob;
-
-static void yielding_job_complete(Job *job, Error **errp)
-{
- YieldingJob *s = container_of(job, YieldingJob, common.job);
- s->should_complete = true;
- job_enter(job);
-}
-
-static int coroutine_fn yielding_job_run(Job *job, Error **errp)
-{
- YieldingJob *s = container_of(job, YieldingJob, common.job);
-
- job_transition_to_ready(job);
-
- while (!s->should_complete) {
- job_yield(job);
- }
-
- return 0;
-}
-
-/*
- * This job transitions immediately to the READY state, and then
- * yields until it is to complete.
- */
-static const BlockJobDriver test_yielding_driver = {
- .job_driver = {
- .instance_size = sizeof(YieldingJob),
- .free = block_job_free,
- .user_resume = block_job_user_resume,
- .run = yielding_job_run,
- .complete = yielding_job_complete,
- },
-};
-
-/*
- * Test that job_complete_locked() works even on jobs that are in a paused
- * state (i.e., STANDBY).
- *
- * To do this, run YieldingJob in an IO thread, get it into the READY
- * state, then have a drained section. Before ending the section,
- * acquire the context so the job will not be entered and will thus
- * remain on STANDBY.
- *
- * job_complete_locked() should still work without error.
- *
- * Note that on the QMP interface, it is impossible to lock an IO
- * thread before a drained section ends. In practice, the
- * bdrv_drain_all_end() and the aio_context_acquire() will be
- * reversed. However, that makes for worse reproducibility here:
- * Sometimes, the job would no longer be in STANDBY then but already
- * be started. We cannot prevent that, because the IO thread runs
- * concurrently. We can only prevent it by taking the lock before
- * ending the drained section, so we do that.
- *
- * (You can reverse the order of operations and most of the time the
- * test will pass, but sometimes the assert(status == STANDBY) will
- * fail.)
- */
-static void test_complete_in_standby(void)
-{
- BlockBackend *blk;
- IOThread *iothread;
- AioContext *ctx;
- Job *job;
- BlockJob *bjob;
-
- /* Create a test drive, move it to an IO thread */
- blk = create_blk(NULL);
- iothread = iothread_new();
-
- ctx = iothread_get_aio_context(iothread);
- blk_set_aio_context(blk, ctx, &error_abort);
-
- /* Create our test job */
- bjob = mk_job(blk, "job", &test_yielding_driver, true,
- JOB_MANUAL_FINALIZE | JOB_MANUAL_DISMISS);
- job = &bjob->job;
- assert_job_status_is(job, JOB_STATUS_CREATED);
-
- /* Wait for the job to become READY */
- job_start(job);
- /*
- * Here we are waiting for the status to change, so don't bother
- * protecting the read every time.
- */
- AIO_WAIT_WHILE_UNLOCKED(ctx, job->status != JOB_STATUS_READY);
-
- /* Begin the drained section, pausing the job */
- bdrv_drain_all_begin();
- assert_job_status_is(job, JOB_STATUS_STANDBY);
-
- /* Lock the IO thread to prevent the job from being run */
- aio_context_acquire(ctx);
- /* This will schedule the job to resume it */
- bdrv_drain_all_end();
- aio_context_release(ctx);
-
- WITH_JOB_LOCK_GUARD() {
- /* But the job cannot run, so it will remain on standby */
- assert(job->status == JOB_STATUS_STANDBY);
-
- /* Even though the job is on standby, this should work */
- job_complete_locked(job, &error_abort);
-
- /* The test is done now, clean up. */
- job_finish_sync_locked(job, NULL, &error_abort);
- assert(job->status == JOB_STATUS_PENDING);
-
- job_finalize_locked(job, &error_abort);
- assert(job->status == JOB_STATUS_CONCLUDED);
-
- job_dismiss_locked(&job, &error_abort);
- }
-
- aio_context_acquire(ctx);
- destroy_blk(blk);
- aio_context_release(ctx);
- iothread_join(iothread);
-}
-
int main(int argc, char **argv)
{
qemu_init_main_loop(&error_abort);
@@ -531,13 +402,5 @@
g_test_add_func("/blockjob/cancel/standby", test_cancel_standby);
g_test_add_func("/blockjob/cancel/pending", test_cancel_pending);
g_test_add_func("/blockjob/cancel/concluded", test_cancel_concluded);
-
- /*
- * This test is flaky and sometimes fails in CI and otherwise:
- * don't run unless user opts in via environment variable.
- */
- if (getenv("QEMU_TEST_FLAKY_TESTS")) {
- g_test_add_func("/blockjob/complete_in_standby", test_complete_in_standby);
- }
return g_test_run();
}
diff --git a/tests/unit/test-replication.c b/tests/unit/test-replication.c
index afff908..5d2003b 100644
--- a/tests/unit/test-replication.c
+++ b/tests/unit/test-replication.c
@@ -199,17 +199,13 @@
static void teardown_primary(void)
{
BlockBackend *blk;
- AioContext *ctx;
/* remove P_ID */
blk = blk_by_name(P_ID);
assert(blk);
- ctx = blk_get_aio_context(blk);
- aio_context_acquire(ctx);
monitor_remove_blk(blk);
blk_unref(blk);
- aio_context_release(ctx);
}
static void test_primary_read(void)
@@ -345,27 +341,20 @@
{
/* only need to destroy two BBs */
BlockBackend *blk;
- AioContext *ctx;
/* remove S_LOCAL_DISK_ID */
blk = blk_by_name(S_LOCAL_DISK_ID);
assert(blk);
- ctx = blk_get_aio_context(blk);
- aio_context_acquire(ctx);
monitor_remove_blk(blk);
blk_unref(blk);
- aio_context_release(ctx);
/* remove S_ID */
blk = blk_by_name(S_ID);
assert(blk);
- ctx = blk_get_aio_context(blk);
- aio_context_acquire(ctx);
monitor_remove_blk(blk);
blk_unref(blk);
- aio_context_release(ctx);
}
static void test_secondary_read(void)
diff --git a/util/async.c b/util/async.c
index 8f90ddc..4605290 100644
--- a/util/async.c
+++ b/util/async.c
@@ -562,12 +562,10 @@
Coroutine *co = QSLIST_FIRST(&straight);
QSLIST_REMOVE_HEAD(&straight, co_scheduled_next);
trace_aio_co_schedule_bh_cb(ctx, co);
- aio_context_acquire(ctx);
/* Protected by write barrier in qemu_aio_coroutine_enter */
qatomic_set(&co->scheduled, NULL);
qemu_aio_coroutine_enter(ctx, co);
- aio_context_release(ctx);
}
}
@@ -707,9 +705,7 @@
assert(self != co);
QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, co, co_queue_next);
} else {
- aio_context_acquire(ctx);
qemu_aio_coroutine_enter(ctx, co);
- aio_context_release(ctx);
}
}
@@ -723,16 +719,6 @@
g_source_unref(&ctx->source);
}
-void aio_context_acquire(AioContext *ctx)
-{
- qemu_rec_mutex_lock(&ctx->lock);
-}
-
-void aio_context_release(AioContext *ctx)
-{
- qemu_rec_mutex_unlock(&ctx->lock);
-}
-
QEMU_DEFINE_STATIC_CO_TLS(AioContext *, my_aiocontext)
AioContext *qemu_get_current_aio_context(void)
diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c
index a9a48ff..3bfb1ad 100644
--- a/util/vhost-user-server.c
+++ b/util/vhost-user-server.c
@@ -360,10 +360,7 @@
qio_channel_set_follow_coroutine_ctx(server->ioc, true);
- /* Attaching the AioContext starts the vu_client_trip coroutine */
- aio_context_acquire(server->ctx);
vhost_user_server_attach_aio_context(server, server->ctx);
- aio_context_release(server->ctx);
}
/* server->ctx acquired by caller */
