Merge tag 'for-upstream' of https://repo.or.cz/qemu/kevin into staging

Block layer patches

- Fix blockdev-create with iothreads
- Remove aio_disable_external() API

# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAmR2JIARHGt3b2xmQHJl
# ZGhhdC5jb20ACgkQfwmycsiPL9brtA/9HVdAdtJxW78J60TE2lTqE9XlqMOEHBZl
# 8GN72trjP2geY/9mVsv/XoFie4ecqFsYjwAWWUuXZwLgAo53jh7oFN7gBH5iGyyD
# +EukYEfjqoykX5BkoK0gbMZZUe5Y4Dr2CNXYw4bNg8kDzj2RLifGA1XhdL3HoiVt
# PHZrhwBR7ddww6gVOnyJrfGL8fMkW/ZNeKRhrTZuSP+63oDOeGTsTumD+YKJzfPs
# p5WlwkuPjcqbO+w32FeVOHVhNI4swkN5svz3fkr8NuflfA7kH6nBQ5wymObbaTLc
# Erx03lrtP1+6nw43V11UnYt6iDMg4EBUQwtzNaKFnk3rMIdjoQYxIM5FTBWL2rYD
# Dg6PhkncXQ1WNWhUaFqpTFLB52XAYsSa4/y2QAGP6nWbqAUAUknQ3exaMvWiq7Z0
# nZeyyhIWvpJIHGCArWRdqqh+zsBdsmUVuPGyZnZgL/cXoJboYiHMyMJSUWE0XxML
# NGrncwxdsBXkVGGwTdHpBT64dcu3ENRgwtraqRLQm+tp5MKNTJB/+Ug2/p1vonHT
# UOoHz//UPskn8sHIyevoHXeu2Ns0uIHzrAXr+7Ay+9UYyIH6a07F4b2BGqkfyi/i
# 8wQsDmJ/idx5C4q1+jS+GuIbpnjIx6nxXwXMqpscUXZmM4Am8OMkiKxQAa1wExGF
# paId+HHwyks=
# =yuER
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 30 May 2023 09:29:52 AM PDT
# gpg:                using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg:                issuer "kwolf@redhat.com"
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]

* tag 'for-upstream' of https://repo.or.cz/qemu/kevin: (32 commits)
  aio: remove aio_disable_external() API
  virtio: do not set is_external=true on host notifiers
  virtio-scsi: implement BlockDevOps->drained_begin()
  virtio-blk: implement BlockDevOps->drained_begin()
  virtio: make it possible to detach host notifier from any thread
  block/fuse: do not set is_external=true on FUSE fd
  block/export: don't require AioContext lock around blk_exp_ref/unref()
  block/export: rewrite vduse-blk drain code
  hw/xen: do not set is_external=true on evtchn fds
  xen-block: implement BlockDevOps->drained_begin()
  block: drain from main loop thread in bdrv_co_yield_to_drain()
  block: add blk_in_drain() API
  hw/xen: do not use aio_set_fd_handler(is_external=true) in xen_xenstore
  block/export: stop using is_external in vhost-user-blk server
  block/export: wait for vhost-user-blk requests when draining
  util/vhost-user-server: rename refcount to in_flight counter
  virtio-scsi: stop using aio_disable_external() during unplug
  virtio-scsi: avoid race between unplug and transport event
  hw/qdev: introduce qdev_is_realized() helper
  block-backend: split blk_do_set_aio_context()
  ...

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

9 files changed, 88 insertions, 111 deletions

diff --git a/include/block/aio.h b/include/block/aio.h
index 89bbc536f9..32042e8905 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -225,8 +225,6 @@ struct AioContext {
      */
     QEMUTimerListGroup tlg;
 
-    int external_disable_cnt;
-
     /* Number of AioHandlers without .io_poll() */
     int poll_disable_cnt;
 
@@ -481,7 +479,6 @@ bool aio_poll(AioContext *ctx, bool blocking);
  */
 void aio_set_fd_handler(AioContext *ctx,
                         int fd,
-                        bool is_external,
                         IOHandler *io_read,
                         IOHandler *io_write,
                         AioPollFn *io_poll,
@@ -497,7 +494,6 @@ void aio_set_fd_handler(AioContext *ctx,
  */
 void aio_set_event_notifier(AioContext *ctx,
                             EventNotifier *notifier,
-                            bool is_external,
                             EventNotifierHandler *io_read,
                             AioPollFn *io_poll,
                             EventNotifierHandler *io_poll_ready);
@@ -627,59 +623,6 @@ static inline void aio_timer_init(AioContext *ctx,
 int64_t aio_compute_timeout(AioContext *ctx);
 
 /**
- * aio_disable_external:
- * @ctx: the aio context
- *
- * Disable the further processing of external clients.
- */
-static inline void aio_disable_external(AioContext *ctx)
-{
-    qatomic_inc(&ctx->external_disable_cnt);
-}
-
-/**
- * aio_enable_external:
- * @ctx: the aio context
- *
- * Enable the processing of external clients.
- */
-static inline void aio_enable_external(AioContext *ctx)
-{
-    int old;
-
-    old = qatomic_fetch_dec(&ctx->external_disable_cnt);
-    assert(old > 0);
-    if (old == 1) {
-        /* Kick event loop so it re-arms file descriptors */
-        aio_notify(ctx);
-    }
-}
-
-/**
- * aio_external_disabled:
- * @ctx: the aio context
- *
- * Return true if the external clients are disabled.
- */
-static inline bool aio_external_disabled(AioContext *ctx)
-{
-    return qatomic_read(&ctx->external_disable_cnt);
-}
-
-/**
- * aio_node_check:
- * @ctx: the aio context
- * @is_external: Whether or not the checked node is an external event source.
- *
- * Check if the node's is_external flag is okay to be polled by the ctx at this
- * moment. True means green light.
- */
-static inline bool aio_node_check(AioContext *ctx, bool is_external)
-{
-    return !is_external || !qatomic_read(&ctx->external_disable_cnt);
-}
-
-/**
  * aio_co_schedule:
  * @ctx: the aio context
  * @co: the coroutine
diff --git a/include/block/block-common.h b/include/block/block-common.h
index 93196229ac..e15395f2cb 100644
--- a/include/block/block-common.h
+++ b/include/block/block-common.h
@@ -65,6 +65,9 @@
  * scheduling a BH in the bottom half that runs the respective non-coroutine
  * function. The coroutine yields after scheduling the BH and is reentered when
  * the wrapped function returns.
+ *
+ * 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
 
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 6492a1e538..b1cbc1e00c 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -364,6 +364,21 @@ struct BlockDriver {
                                     AioContext *new_context);
 
     /**
+     * bdrv_drain_begin is called if implemented in the beginning of a
+     * drain operation to drain and stop any internal sources of requests in
+     * the driver.
+     * bdrv_drain_end is called if implemented at the end of the drain.
+     *
+     * They should be used by the driver to e.g. manage scheduled I/O
+     * requests, or toggle an internal state. After the end of the drain new
+     * requests will continue normally.
+     *
+     * Implementations of both functions must not call aio_poll().
+     */
+    void (*bdrv_drain_begin)(BlockDriverState *bs);
+    void (*bdrv_drain_end)(BlockDriverState *bs);
+
+    /**
      * Try to get @bs's logical and physical block size.
      * On success, store them in @bsz and return zero.
      * On failure, return negative errno.
@@ -758,21 +773,6 @@ struct BlockDriver {
     void coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_io_unplug)(
         BlockDriverState *bs);
 
-    /**
-     * bdrv_drain_begin is called if implemented in the beginning of a
-     * drain operation to drain and stop any internal sources of requests in
-     * the driver.
-     * bdrv_drain_end is called if implemented at the end of the drain.
-     *
-     * They should be used by the driver to e.g. manage scheduled I/O
-     * requests, or toggle an internal state. After the end of the drain new
-     * requests will continue normally.
-     *
-     * Implementations of both functions must not call aio_poll().
-     */
-    void (*bdrv_drain_begin)(BlockDriverState *bs);
-    void (*bdrv_drain_end)(BlockDriverState *bs);
-
     bool (*bdrv_supports_persistent_dirty_bitmap)(BlockDriverState *bs);
 
     bool coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_can_store_new_dirty_bitmap)(
@@ -956,6 +956,27 @@ struct BdrvChildClass {
     void GRAPH_WRLOCK_PTR (*detach)(BdrvChild *child);
 
     /*
+     * If this pair of functions is implemented, the parent doesn't issue new
+     * requests after returning from .drained_begin() until .drained_end() is
+     * called.
+     *
+     * These functions must not change the graph (and therefore also must not
+     * call aio_poll(), which could change the graph indirectly).
+     *
+     * Note that this can be nested. If drained_begin() was called twice, new
+     * I/O is allowed only after drained_end() was called twice, too.
+     */
+    void (*drained_begin)(BdrvChild *child);
+    void (*drained_end)(BdrvChild *child);
+
+    /*
+     * Returns whether the parent has pending requests for the child. This
+     * callback is polled after .drained_begin() has been called until all
+     * activity on the child has stopped.
+     */
+    bool (*drained_poll)(BdrvChild *child);
+
+    /*
      * Notifies the parent that the filename of its child has changed (e.g.
      * because the direct child was removed from the backing chain), so that it
      * can update its reference.
@@ -984,27 +1005,6 @@ struct BdrvChildClass {
     const char *(*get_name)(BdrvChild *child);
 
     AioContext *(*get_parent_aio_context)(BdrvChild *child);
-
-    /*
-     * If this pair of functions is implemented, the parent doesn't issue new
-     * requests after returning from .drained_begin() until .drained_end() is
-     * called.
-     *
-     * These functions must not change the graph (and therefore also must not
-     * call aio_poll(), which could change the graph indirectly).
-     *
-     * Note that this can be nested. If drained_begin() was called twice, new
-     * I/O is allowed only after drained_end() was called twice, too.
-     */
-    void (*drained_begin)(BdrvChild *child);
-    void (*drained_end)(BdrvChild *child);
-
-    /*
-     * Returns whether the parent has pending requests for the child. This
-     * callback is polled after .drained_begin() has been called until all
-     * activity on the child has stopped.
-     */
-    bool (*drained_poll)(BdrvChild *child);
 };
 
 extern const BdrvChildClass child_of_bds;
diff --git a/include/block/export.h b/include/block/export.h
index 7feb02e10d..f2fe0f8078 100644
--- a/include/block/export.h
+++ b/include/block/export.h
@@ -57,6 +57,8 @@ struct BlockExport {
      * Reference count for this block export. This includes strong references
      * both from the owner (qemu-nbd or the monitor) and clients connected to
      * the export.
+     *
+     * Use atomics to access this field.
      */
     int refcount;
 
diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index 7623703943..f1070d6dc7 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -1,6 +1,7 @@
 #ifndef QDEV_CORE_H
 #define QDEV_CORE_H
 
+#include "qemu/atomic.h"
 #include "qemu/queue.h"
 #include "qemu/bitmap.h"
 #include "qemu/rcu.h"
@@ -168,9 +169,6 @@ typedef struct {
 
 /**
  * DeviceState:
- * @realized: Indicates whether the device has been fully constructed.
- *            When accessed outside big qemu lock, must be accessed with
- *            qatomic_load_acquire()
  * @reset: ResettableState for the device; handled by Resettable interface.
  *
  * This structure should not be accessed directly.  We declare it here
@@ -340,6 +338,19 @@ DeviceState *qdev_new(const char *name);
 DeviceState *qdev_try_new(const char *name);
 
 /**
+ * qdev_is_realized:
+ * @dev: The device to check.
+ *
+ * May be called outside big qemu lock.
+ *
+ * Returns: %true% if the device has been fully constructed, %false% otherwise.
+ */
+static inline bool qdev_is_realized(DeviceState *dev)
+{
+    return qatomic_load_acquire(&dev->realized);
+}
+
+/**
  * qdev_realize: Realize @dev.
  * @dev: device to realize
  * @bus: bus to plug it into (may be NULL)
diff --git a/include/hw/scsi/scsi.h b/include/hw/scsi/scsi.h
index 6f23a7a73e..e2bb1a2fbf 100644
--- a/include/hw/scsi/scsi.h
+++ b/include/hw/scsi/scsi.h
@@ -133,6 +133,16 @@ struct SCSIBusInfo {
     void (*save_request)(QEMUFile *f, SCSIRequest *req);
     void *(*load_request)(QEMUFile *f, SCSIRequest *req);
     void (*free_request)(SCSIBus *bus, void *priv);
+
+    /*
+     * Temporarily stop submitting new requests between drained_begin() and
+     * drained_end(). Called from the main loop thread with the BQL held.
+     *
+     * Implement these callbacks if request processing is triggered by a file
+     * descriptor like an EventNotifier. Otherwise set them to NULL.
+     */
+    void (*drained_begin)(SCSIBus *bus);
+    void (*drained_end)(SCSIBus *bus);
 };
 
 #define TYPE_SCSI_BUS "SCSI"
@@ -144,6 +154,8 @@ struct SCSIBus {
 
     SCSISense unit_attention;
     const SCSIBusInfo *info;
+
+    int drain_count; /* protected by BQL */
 };
 
 /**
@@ -213,6 +225,8 @@ void scsi_req_cancel_complete(SCSIRequest *req);
 void scsi_req_cancel(SCSIRequest *req);
 void scsi_req_cancel_async(SCSIRequest *req, Notifier *notifier);
 void scsi_req_retry(SCSIRequest *req);
+void scsi_device_drained_begin(SCSIDevice *sdev);
+void scsi_device_drained_end(SCSIDevice *sdev);
 void scsi_device_purge_requests(SCSIDevice *sdev, SCSISense sense);
 void scsi_device_set_ua(SCSIDevice *sdev, SCSISense sense);
 void scsi_device_report_change(SCSIDevice *dev, SCSISense sense);
diff --git a/include/qemu/vhost-user-server.h b/include/qemu/vhost-user-server.h
index 25c72433ca..b1c1cda886 100644
--- a/include/qemu/vhost-user-server.h
+++ b/include/qemu/vhost-user-server.h
@@ -40,8 +40,9 @@ typedef struct {
     int max_queues;
     const VuDevIface *vu_iface;
 
+    unsigned int in_flight; /* atomic */
+
     /* Protected by ctx lock */
-    unsigned int refcount;
     bool wait_idle;
     VuDev vu_dev;
     QIOChannel *ioc; /* The I/O channel with the client */
@@ -60,8 +61,9 @@ bool vhost_user_server_start(VuServer *server,
 
 void vhost_user_server_stop(VuServer *server);
 
-void vhost_user_server_ref(VuServer *server);
-void vhost_user_server_unref(VuServer *server);
+void vhost_user_server_inc_in_flight(VuServer *server);
+void vhost_user_server_dec_in_flight(VuServer *server);
+bool vhost_user_server_has_in_flight(VuServer *server);
 
 void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx);
 void vhost_user_server_detach_aio_context(VuServer *server);
diff --git a/include/sysemu/block-backend-common.h b/include/sysemu/block-backend-common.h
index 2391679c56..780cea7305 100644
--- a/include/sysemu/block-backend-common.h
+++ b/include/sysemu/block-backend-common.h
@@ -60,6 +60,19 @@ typedef struct BlockDevOps {
     bool (*is_medium_locked)(void *opaque);
 
     /*
+     * Runs when the backend receives a drain request.
+     */
+    void (*drained_begin)(void *opaque);
+    /*
+     * Runs when the backend's last drain request ends.
+     */
+    void (*drained_end)(void *opaque);
+    /*
+     * Is the device still busy?
+     */
+    bool (*drained_poll)(void *opaque);
+
+    /*
      * I/O API functions. These functions are thread-safe.
      *
      * See include/block/block-io.h for more information about
@@ -76,18 +89,6 @@ typedef struct BlockDevOps {
      * Runs when the size changed (e.g. monitor command block_resize)
      */
     void (*resize_cb)(void *opaque);
-    /*
-     * Runs when the backend receives a drain request.
-     */
-    void (*drained_begin)(void *opaque);
-    /*
-     * Runs when the backend's last drain request ends.
-     */
-    void (*drained_end)(void *opaque);
-    /*
-     * Is the device still busy?
-     */
-    bool (*drained_poll)(void *opaque);
 } BlockDevOps;
 
 /*
diff --git a/include/sysemu/block-backend-global-state.h b/include/sysemu/block-backend-global-state.h
index fa83f9389c..184e667ebd 100644
--- a/include/sysemu/block-backend-global-state.h
+++ b/include/sysemu/block-backend-global-state.h
@@ -81,6 +81,7 @@ void blk_activate(BlockBackend *blk, Error **errp);
 int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags);
 void blk_aio_cancel(BlockAIOCB *acb);
 int blk_commit_all(void);
+bool blk_in_drain(BlockBackend *blk);
 void blk_drain(BlockBackend *blk);
 void blk_drain_all(void);
 void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error,