Merge remote-tracking branch 'remotes/xanclic/tags/pull-block-2018-09-25' into staging

Block layer patches:
- Drain fixes
- node-name parameters for block-commit
- Refactor block jobs to use transactional callbacks for exiting

# gpg: Signature made Tue 25 Sep 2018 16:12:44 BST
# gpg:                using RSA key F407DB0061D5CF40
# gpg: Good signature from "Max Reitz <mreitz@redhat.com>"
# Primary key fingerprint: 91BE B60A 30DB 3E88 57D1  1829 F407 DB00 61D5 CF40

* remotes/xanclic/tags/pull-block-2018-09-25: (42 commits)
  test-bdrv-drain: Test draining job source child and parent
  block: Use a single global AioWait
  test-bdrv-drain: Fix outdated comments
  test-bdrv-drain: AIO_WAIT_WHILE() in job .commit/.abort
  job: Avoid deadlocks in job_completed_txn_abort()
  test-bdrv-drain: Test nested poll in bdrv_drain_poll_top_level()
  block: Remove aio_poll() in bdrv_drain_poll variants
  blockjob: Lie better in child_job_drained_poll()
  block-backend: Decrease in_flight only after callback
  block-backend: Fix potential double blk_delete()
  block-backend: Add .drained_poll callback
  block: Add missing locking in bdrv_co_drain_bh_cb()
  test-bdrv-drain: Test AIO_WAIT_WHILE() in completion callback
  job: Use AIO_WAIT_WHILE() in job_finish_sync()
  test-blockjob: Acquire AioContext around job_cancel_sync()
  test-bdrv-drain: Drain with block jobs in an I/O thread
  aio-wait: Increase num_waiters even in home thread
  blockjob: Wake up BDS when job becomes idle
  job: Fix missing locking due to mismerge
  job: Fix nested aio_poll() hanging in job_txn_apply
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

6 files changed, 47 insertions, 36 deletions

diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index c85a62f798..afd0ff7eb8 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -30,14 +30,15 @@
 /**
  * AioWait:
  *
- * An object that facilitates synchronous waiting on a condition.  The main
- * loop can wait on an operation running in an IOThread as follows:
+ * An object that facilitates synchronous waiting on a condition. A single
+ * global AioWait object (global_aio_wait) is used internally.
+ *
+ * The main loop can wait on an operation running in an IOThread as follows:
  *
- *   AioWait *wait = ...;
  *   AioContext *ctx = ...;
  *   MyWork work = { .done = false };
  *   schedule_my_work_in_iothread(ctx, &work);
- *   AIO_WAIT_WHILE(wait, ctx, !work.done);
+ *   AIO_WAIT_WHILE(ctx, !work.done);
  *
  * The IOThread must call aio_wait_kick() to notify the main loop when
  * work.done changes:
@@ -46,7 +47,7 @@
  *   {
  *       ...
  *       work.done = true;
- *       aio_wait_kick(wait);
+ *       aio_wait_kick();
  *   }
  */
 typedef struct {
@@ -54,9 +55,10 @@ typedef struct {
     unsigned num_waiters;
 } AioWait;
 
+extern AioWait global_aio_wait;
+
 /**
  * AIO_WAIT_WHILE:
- * @wait: the aio wait object
  * @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
@@ -72,10 +74,12 @@ typedef struct {
  * wait on conditions between two IOThreads since that could lead to deadlock,
  * go via the main loop instead.
  */
-#define AIO_WAIT_WHILE(wait, ctx, cond) ({                         \
+#define AIO_WAIT_WHILE(ctx, cond) ({                               \
     bool waited_ = false;                                          \
-    AioWait *wait_ = (wait);                                       \
+    AioWait *wait_ = &global_aio_wait;                             \
     AioContext *ctx_ = (ctx);                                      \
+    /* Increment wait_->num_waiters before evaluating cond. */     \
+    atomic_inc(&wait_->num_waiters);                               \
     if (ctx_ && in_aio_context_home_thread(ctx_)) {                \
         while ((cond)) {                                           \
             aio_poll(ctx_, true);                                  \
@@ -84,8 +88,6 @@ typedef struct {
     } else {                                                       \
         assert(qemu_get_current_aio_context() ==                   \
                qemu_get_aio_context());                            \
-        /* Increment wait_->num_waiters before evaluating cond. */ \
-        atomic_inc(&wait_->num_waiters);                           \
         while ((cond)) {                                           \
             if (ctx_) {                                            \
                 aio_context_release(ctx_);                         \
@@ -96,20 +98,18 @@ typedef struct {
             }                                                      \
             waited_ = true;                                        \
         }                                                          \
-        atomic_dec(&wait_->num_waiters);                           \
     }                                                              \
+    atomic_dec(&wait_->num_waiters);                               \
     waited_; })
 
 /**
  * aio_wait_kick:
- * @wait: the aio wait object that should re-evaluate its condition
- *
  * Wake up the main thread if it is waiting on AIO_WAIT_WHILE().  During
  * synchronous operations performed in an IOThread, the main thread lets the
  * IOThread's event loop run, waiting for the operation to complete.  A
  * aio_wait_kick() call will wake up the main thread.
  */
-void aio_wait_kick(AioWait *wait);
+void aio_wait_kick(void);
 
 /**
  * aio_wait_bh_oneshot:
diff --git a/include/block/block.h b/include/block/block.h
index 4e0871aaf9..4edc1e8afa 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -410,13 +410,9 @@ void bdrv_drain_all_begin(void);
 void bdrv_drain_all_end(void);
 void bdrv_drain_all(void);
 
-/* Returns NULL when bs == NULL */
-AioWait *bdrv_get_aio_wait(BlockDriverState *bs);
-
 #define BDRV_POLL_WHILE(bs, cond) ({                       \
     BlockDriverState *bs_ = (bs);                          \
-    AIO_WAIT_WHILE(bdrv_get_aio_wait(bs_),                 \
-                   bdrv_get_aio_context(bs_),              \
+    AIO_WAIT_WHILE(bdrv_get_aio_context(bs_),              \
                    cond); })
 
 int bdrv_pdiscard(BdrvChild *child, int64_t offset, int bytes);
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 903b9c1034..92ecbd866e 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -794,9 +794,6 @@ struct BlockDriverState {
     unsigned int in_flight;
     unsigned int serialising_in_flight;
 
-    /* Kicked to signal main loop when a request completes. */
-    AioWait wait;
-
     /* counter for nested bdrv_io_plug.
      * Accessed with atomic ops.
     */
@@ -958,6 +955,8 @@ int is_windows_drive(const char *filename);
  * flatten the whole backing file chain onto @bs.
  * @backing_file_str: The file name that will be written to @bs as the
  * the new backing file if the job completes. Ignored if @base is %NULL.
+ * @creation_flags: Flags that control the behavior of the Job lifetime.
+ *                  See @BlockJobCreateFlags
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @on_error: The action to take upon error.
  * @errp: Error object.
@@ -971,7 +970,8 @@ int is_windows_drive(const char *filename);
  */
 void stream_start(const char *job_id, BlockDriverState *bs,
                   BlockDriverState *base, const char *backing_file_str,
-                  int64_t speed, BlockdevOnError on_error, Error **errp);
+                  int creation_flags, int64_t speed,
+                  BlockdevOnError on_error, Error **errp);
 
 /**
  * commit_start:
@@ -980,6 +980,8 @@ void stream_start(const char *job_id, BlockDriverState *bs,
  * @bs: Active block device.
  * @top: Top block device to be committed.
  * @base: Block device that will be written into, and become the new top.
+ * @creation_flags: Flags that control the behavior of the Job lifetime.
+ *                  See @BlockJobCreateFlags
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @on_error: The action to take upon error.
  * @backing_file_str: String to use as the backing file in @top's overlay
@@ -990,7 +992,8 @@ void stream_start(const char *job_id, BlockDriverState *bs,
  *
  */
 void commit_start(const char *job_id, BlockDriverState *bs,
-                  BlockDriverState *base, BlockDriverState *top, int64_t speed,
+                  BlockDriverState *base, BlockDriverState *top,
+                  int creation_flags, int64_t speed,
                   BlockdevOnError on_error, const char *backing_file_str,
                   const char *filter_node_name, Error **errp);
 /**
@@ -1026,6 +1029,8 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
  * @target: Block device to write to.
  * @replaces: Block graph node name to replace once the mirror is done. Can
  *            only be used when full mirroring is selected.
+ * @creation_flags: Flags that control the behavior of the Job lifetime.
+ *                  See @BlockJobCreateFlags
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @granularity: The chosen granularity for the dirty bitmap.
  * @buf_size: The amount of data that can be in flight at one time.
@@ -1047,7 +1052,8 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
  */
 void mirror_start(const char *job_id, BlockDriverState *bs,
                   BlockDriverState *target, const char *replaces,
-                  int64_t speed, uint32_t granularity, int64_t buf_size,
+                  int creation_flags, int64_t speed,
+                  uint32_t granularity, int64_t buf_size,
                   MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
                   BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index 32c00b7dc0..ede0bd8dcb 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -70,6 +70,9 @@ typedef struct BlockJob {
     /** Called when the job transitions to READY */
     Notifier ready_notifier;
 
+    /** Called when the job coroutine yields or terminates */
+    Notifier idle_notifier;
+
     /** BlockDriverStates that are involved in this block job */
     GSList *nodes;
 } BlockJob;
diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h
index 6f8a487041..9801e7f5a4 100644
--- a/include/qemu/coroutine.h
+++ b/include/qemu/coroutine.h
@@ -90,6 +90,11 @@ void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co);
 void coroutine_fn qemu_coroutine_yield(void);
 
 /**
+ * Get the AioContext of the given coroutine
+ */
+AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co);
+
+/**
  * Get the currently executing coroutine
  */
 Coroutine *coroutine_fn qemu_coroutine_self(void);
diff --git a/include/qemu/job.h b/include/qemu/job.h
index e0cff702b7..9e7cd1e4a0 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -76,6 +76,9 @@ typedef struct Job {
      * Set to false by the job while the coroutine has yielded and may be
      * re-entered by job_enter(). There may still be I/O or event loop activity
      * pending. Accessed under block_job_mutex (in blockjob.c).
+     *
+     * When the job is deferred to the main loop, busy is true as long as the
+     * bottom half is still pending.
      */
     bool busy;
 
@@ -156,6 +159,9 @@ typedef struct Job {
     /** Notifiers called when the job transitions to READY */
     NotifierList on_ready;
 
+    /** Notifiers called when the job coroutine yields or terminates */
+    NotifierList on_idle;
+
     /** Element of the list of jobs */
     QLIST_ENTRY(Job) job_list;
 
@@ -222,17 +228,6 @@ struct JobDriver {
     void (*drain)(Job *job);
 
     /**
-     * If the callback is not NULL, exit will be invoked from the main thread
-     * when the job's coroutine has finished, but before transactional
-     * convergence; before @prepare or @abort.
-     *
-     * FIXME TODO: This callback is only temporary to transition remaining jobs
-     * to prepare/commit/abort/clean callbacks and will be removed before 3.1.
-     * is released.
-     */
-    void (*exit)(Job *job);
-
-    /**
      * If the callback is not NULL, prepare will be invoked when all the jobs
      * belonging to the same transaction complete; or upon this job's completion
      * if it is not in a transaction.
@@ -532,6 +527,8 @@ void job_user_cancel(Job *job, bool force, Error **errp);
  *
  * Returns the return value from the job if the job actually completed
  * during the call, or -ECANCELED if it was canceled.
+ *
+ * Callers must hold the AioContext lock of job->aio_context.
  */
 int job_cancel_sync(Job *job);
 
@@ -549,6 +546,8 @@ void job_cancel_sync_all(void);
  * function).
  *
  * Returns the return value from the job.
+ *
+ * Callers must hold the AioContext lock of job->aio_context.
  */
 int job_complete_sync(Job *job, Error **errp);
 
@@ -574,6 +573,8 @@ void job_dismiss(Job **job, Error **errp);
  *
  * Returns 0 if the job is successfully completed, -ECANCELED if the job was
  * cancelled before completing, and -errno in other error cases.
+ *
+ * Callers must hold the AioContext lock of job->aio_context.
  */
 int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp);