X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=job.c;h=660ce22c56b6115155451f9b60c4f237ff99b8eb;hb=4d48c1bc079147a02ec1a3df9a41497c515d2e61;hp=3aaaebafe2c87cd83e16ea6bc9577210f1089fa9;hpb=5101d00d2f1138a73344dc4833587f76d7a5fa5c;p=mirror_qemu.git

diff --git a/job.c b/job.c
index 3aaaebafe2..660ce22c56 100644
--- a/job.c
+++ b/job.c
@@ -32,6 +32,27 @@
 #include "trace/trace-root.h"
 #include "qapi/qapi-events-job.h"
 
+/*
+ * The job API is composed of two categories of functions.
+ *
+ * The first includes functions used by the monitor.  The monitor is
+ * peculiar in that it accesses the job list with job_get, and
+ * therefore needs consistency across job_get and the actual operation
+ * (e.g. job_user_cancel). To achieve this consistency, the caller
+ * calls job_lock/job_unlock itself around the whole operation.
+ *
+ *
+ * The second includes functions used by the job drivers and sometimes
+ * by the core block layer. These delegate the locking to the callee instead.
+ */
+
+/*
+ * job_mutex protects the jobs list, but also makes the
+ * struct job fields thread-safe.
+ */
+QemuMutex job_mutex;
+
+/* Protected by job_mutex */
 static QLIST_HEAD(, Job) jobs = QLIST_HEAD_INITIALIZER(jobs);
 
 /* Job State Transition Table */
@@ -56,9 +77,10 @@ bool JobVerbTable[JOB_VERB__MAX][JOB_STATUS__MAX] = {
     [JOB_VERB_PAUSE]                = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
     [JOB_VERB_RESUME]               = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
     [JOB_VERB_SET_SPEED]            = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
-    [JOB_VERB_COMPLETE]             = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0},
+    [JOB_VERB_COMPLETE]             = {0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0},
     [JOB_VERB_FINALIZE]             = {0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0},
     [JOB_VERB_DISMISS]              = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0},
+    [JOB_VERB_CHANGE]               = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
 };
 
 /* Transactional group of jobs */
@@ -74,17 +96,12 @@ struct JobTxn {
     int refcnt;
 };
 
-/* Right now, this mutex is only needed to synchronize accesses to job->busy
- * and job->sleep_timer, such as concurrent calls to job_do_yield and
- * job_enter. */
-static QemuMutex job_mutex;
-
-static void job_lock(void)
+void job_lock(void)
 {
     qemu_mutex_lock(&job_mutex);
 }
 
-static void job_unlock(void)
+void job_unlock(void)
 {
     qemu_mutex_unlock(&job_mutex);
 }
@@ -102,19 +119,38 @@ JobTxn *job_txn_new(void)
     return txn;
 }
 
-static void job_txn_ref(JobTxn *txn)
+/* Called with job_mutex held. */
+static void job_txn_ref_locked(JobTxn *txn)
 {
     txn->refcnt++;
 }
 
-void job_txn_unref(JobTxn *txn)
+void job_txn_unref_locked(JobTxn *txn)
 {
     if (txn && --txn->refcnt == 0) {
         g_free(txn);
     }
 }
 
-void job_txn_add_job(JobTxn *txn, Job *job)
+void job_txn_unref(JobTxn *txn)
+{
+    JOB_LOCK_GUARD();
+    job_txn_unref_locked(txn);
+}
+
+/**
+ * @txn: The transaction (may be NULL)
+ * @job: Job to add to the transaction
+ *
+ * Add @job to the transaction.  The @job must not already be in a transaction.
+ * The caller must call either job_txn_unref() or job_completed() to release
+ * the reference that is automatically grabbed here.
+ *
+ * If @txn is NULL, the function does nothing.
+ *
+ * Called with job_mutex held.
+ */
+static void job_txn_add_job_locked(JobTxn *txn, Job *job)
 {
     if (!txn) {
         return;
@@ -124,21 +160,22 @@ void job_txn_add_job(JobTxn *txn, Job *job)
     job->txn = txn;
 
     QLIST_INSERT_HEAD(&txn->jobs, job, txn_list);
-    job_txn_ref(txn);
+    job_txn_ref_locked(txn);
 }
 
-static void job_txn_del_job(Job *job)
+/* Called with job_mutex held. */
+static void job_txn_del_job_locked(Job *job)
 {
     if (job->txn) {
         QLIST_REMOVE(job, txn_list);
-        job_txn_unref(job->txn);
+        job_txn_unref_locked(job->txn);
         job->txn = NULL;
     }
 }
 
-static int job_txn_apply(Job *job, int fn(Job *))
+/* Called with job_mutex held, but releases it temporarily. */
+static int job_txn_apply_locked(Job *job, int fn(Job *))
 {
-    AioContext *inner_ctx;
     Job *other_job, *next;
     JobTxn *txn = job->txn;
     int rc = 0;
@@ -149,25 +186,16 @@ static int job_txn_apply(Job *job, int fn(Job *))
      * we need to release it here to avoid holding the lock twice - which would
      * break AIO_WAIT_WHILE from within fn.
      */
-    job_ref(job);
-    aio_context_release(job->aio_context);
+    job_ref_locked(job);
 
     QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) {
-        inner_ctx = other_job->aio_context;
-        aio_context_acquire(inner_ctx);
         rc = fn(other_job);
-        aio_context_release(inner_ctx);
         if (rc) {
             break;
         }
     }
 
-    /*
-     * Note that job->aio_context might have been changed by calling fn, so we
-     * can't use a local variable to cache it.
-     */
-    aio_context_acquire(job->aio_context);
-    job_unref(job);
+    job_unref_locked(job);
     return rc;
 }
 
@@ -176,7 +204,8 @@ bool job_is_internal(Job *job)
     return (job->id == NULL);
 }
 
-static void job_state_transition(Job *job, JobStatus s1)
+/* Called with job_mutex held. */
+static void job_state_transition_locked(Job *job, JobStatus s1)
 {
     JobStatus s0 = job->status;
     assert(s1 >= 0 && s1 < JOB_STATUS__MAX);
@@ -191,7 +220,7 @@ static void job_state_transition(Job *job, JobStatus s1)
     }
 }
 
-int job_apply_verb(Job *job, JobVerb verb, Error **errp)
+int job_apply_verb_locked(Job *job, JobVerb verb, Error **errp)
 {
     JobStatus s0 = job->status;
     assert(verb >= 0 && verb < JOB_VERB__MAX);
@@ -215,12 +244,32 @@ const char *job_type_str(const Job *job)
     return JobType_str(job_type(job));
 }
 
+bool job_is_cancelled_locked(Job *job)
+{
+    /* force_cancel may be true only if cancelled is true, too */
+    assert(job->cancelled || !job->force_cancel);
+    return job->force_cancel;
+}
+
 bool job_is_cancelled(Job *job)
+{
+    JOB_LOCK_GUARD();
+    return job_is_cancelled_locked(job);
+}
+
+/* Called with job_mutex held. */
+static bool job_cancel_requested_locked(Job *job)
 {
     return job->cancelled;
 }
 
-bool job_is_ready(Job *job)
+bool job_cancel_requested(Job *job)
+{
+    JOB_LOCK_GUARD();
+    return job_cancel_requested_locked(job);
+}
+
+bool job_is_ready_locked(Job *job)
 {
     switch (job->status) {
     case JOB_STATUS_UNDEFINED:
@@ -242,7 +291,13 @@ bool job_is_ready(Job *job)
     return false;
 }
 
-bool job_is_completed(Job *job)
+bool job_is_ready(Job *job)
+{
+    JOB_LOCK_GUARD();
+    return job_is_ready_locked(job);
+}
+
+bool job_is_completed_locked(Job *job)
 {
     switch (job->status) {
     case JOB_STATUS_UNDEFINED:
@@ -264,17 +319,24 @@ bool job_is_completed(Job *job)
     return false;
 }
 
-static bool job_started(Job *job)
+static bool job_is_completed(Job *job)
+{
+    JOB_LOCK_GUARD();
+    return job_is_completed_locked(job);
+}
+
+static bool job_started_locked(Job *job)
 {
     return job->co;
 }
 
-static bool job_should_pause(Job *job)
+/* Called with job_mutex held. */
+static bool job_should_pause_locked(Job *job)
 {
     return job->pause_count > 0;
 }
 
-Job *job_next(Job *job)
+Job *job_next_locked(Job *job)
 {
     if (!job) {
         return QLIST_FIRST(&jobs);
@@ -282,7 +344,13 @@ Job *job_next(Job *job)
     return QLIST_NEXT(job, job_list);
 }
 
-Job *job_get(const char *id)
+Job *job_next(Job *job)
+{
+    JOB_LOCK_GUARD();
+    return job_next_locked(job);
+}
+
+Job *job_get_locked(const char *id)
 {
     Job *job;
 
@@ -295,6 +363,18 @@ Job *job_get(const char *id)
     return NULL;
 }
 
+void job_set_aio_context(Job *job, AioContext *ctx)
+{
+    /* protect against read in job_finish_sync_locked and job_start */
+    GLOBAL_STATE_CODE();
+    /* protect against read in job_do_yield_locked */
+    JOB_LOCK_GUARD();
+    /* ensure the job is quiescent while the AioContext is changed */
+    assert(job->paused || job_is_completed_locked(job));
+    job->aio_context = ctx;
+}
+
+/* Called with job_mutex *not* held. */
 static void job_sleep_timer_cb(void *opaque)
 {
     Job *job = opaque;
@@ -308,6 +388,8 @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn,
 {
     Job *job;
 
+    JOB_LOCK_GUARD();
+
     if (job_id) {
         if (flags & JOB_INTERNAL) {
             error_setg(errp, "Cannot specify job ID for internal job");
@@ -317,7 +399,7 @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn,
             error_setg(errp, "Invalid job ID '%s'", job_id);
             return NULL;
         }
-        if (job_get(job_id)) {
+        if (job_get_locked(job_id)) {
             error_setg(errp, "Job ID '%s' already in use", job_id);
             return NULL;
         }
@@ -339,12 +421,15 @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn,
     job->cb            = cb;
     job->opaque        = opaque;
 
+    progress_init(&job->progress);
+
     notifier_list_init(&job->on_finalize_cancelled);
     notifier_list_init(&job->on_finalize_completed);
     notifier_list_init(&job->on_pending);
     notifier_list_init(&job->on_ready);
+    notifier_list_init(&job->on_idle);
 
-    job_state_transition(job, JOB_STATUS_CREATED);
+    job_state_transition_locked(job, JOB_STATUS_CREATED);
     aio_timer_init(qemu_get_aio_context(), &job->sleep_timer,
                    QEMU_CLOCK_REALTIME, SCALE_NS,
                    job_sleep_timer_cb, job);
@@ -355,33 +440,38 @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn,
      * consolidating the job management logic */
     if (!txn) {
         txn = job_txn_new();
-        job_txn_add_job(txn, job);
-        job_txn_unref(txn);
+        job_txn_add_job_locked(txn, job);
+        job_txn_unref_locked(txn);
     } else {
-        job_txn_add_job(txn, job);
+        job_txn_add_job_locked(txn, job);
     }
 
     return job;
 }
 
-void job_ref(Job *job)
+void job_ref_locked(Job *job)
 {
     ++job->refcnt;
 }
 
-void job_unref(Job *job)
+void job_unref_locked(Job *job)
 {
+    GLOBAL_STATE_CODE();
+
     if (--job->refcnt == 0) {
         assert(job->status == JOB_STATUS_NULL);
         assert(!timer_pending(&job->sleep_timer));
         assert(!job->txn);
 
         if (job->driver->free) {
+            job_unlock();
             job->driver->free(job);
+            job_lock();
         }
 
         QLIST_REMOVE(job, job_list);
 
+        progress_destroy(&job->progress);
         error_free(job->err);
         g_free(job->id);
         g_free(job);
@@ -403,48 +493,56 @@ void job_progress_increase_remaining(Job *job, uint64_t delta)
     progress_increase_remaining(&job->progress, delta);
 }
 
-void job_event_cancelled(Job *job)
+/**
+ * To be called when a cancelled job is finalised.
+ * Called with job_mutex held.
+ */
+static void job_event_cancelled_locked(Job *job)
 {
     notifier_list_notify(&job->on_finalize_cancelled, job);
 }
 
-void job_event_completed(Job *job)
+/**
+ * To be called when a successfully completed job is finalised.
+ * Called with job_mutex held.
+ */
+static void job_event_completed_locked(Job *job)
 {
     notifier_list_notify(&job->on_finalize_completed, job);
 }
 
-static void job_event_pending(Job *job)
+/* Called with job_mutex held. */
+static void job_event_pending_locked(Job *job)
 {
     notifier_list_notify(&job->on_pending, job);
 }
 
-static void job_event_ready(Job *job)
+/* Called with job_mutex held. */
+static void job_event_ready_locked(Job *job)
 {
     notifier_list_notify(&job->on_ready, job);
 }
 
-static void job_event_idle(Job *job)
+/* Called with job_mutex held. */
+static void job_event_idle_locked(Job *job)
 {
     notifier_list_notify(&job->on_idle, job);
 }
 
-void job_enter_cond(Job *job, bool(*fn)(Job *job))
+void job_enter_cond_locked(Job *job, bool(*fn)(Job *job))
 {
-    if (!job_started(job)) {
+    if (!job_started_locked(job)) {
         return;
     }
     if (job->deferred_to_main_loop) {
         return;
     }
 
-    job_lock();
     if (job->busy) {
-        job_unlock();
         return;
     }
 
     if (fn && !fn(job)) {
-        job_unlock();
         return;
     }
 
@@ -452,12 +550,14 @@ void job_enter_cond(Job *job, bool(*fn)(Job *job))
     timer_del(&job->sleep_timer);
     job->busy = true;
     job_unlock();
-    aio_co_enter(job->aio_context, job->co);
+    aio_co_wake(job->co);
+    job_lock();
 }
 
 void job_enter(Job *job)
 {
-    job_enter_cond(job, NULL);
+    JOB_LOCK_GUARD();
+    job_enter_cond_locked(job, NULL);
 }
 
 /* Yield, and schedule a timer to reenter the coroutine after @ns nanoseconds.
@@ -465,100 +565,137 @@ void job_enter(Job *job)
  * is allowed and cancels the timer.
  *
  * If @ns is (uint64_t) -1, no timer is scheduled and job_enter() must be
- * called explicitly. */
-static void coroutine_fn job_do_yield(Job *job, uint64_t ns)
+ * called explicitly.
+ *
+ * Called with job_mutex held, but releases it temporarily.
+ */
+static void coroutine_fn job_do_yield_locked(Job *job, uint64_t ns)
 {
-    job_lock();
+    AioContext *next_aio_context;
+
     if (ns != -1) {
         timer_mod(&job->sleep_timer, ns);
     }
     job->busy = false;
-    job_event_idle(job);
+    job_event_idle_locked(job);
     job_unlock();
     qemu_coroutine_yield();
+    job_lock();
+
+    next_aio_context = job->aio_context;
+    /*
+     * Coroutine has resumed, but in the meanwhile the job AioContext
+     * might have changed via bdrv_try_change_aio_context(), so we need to move
+     * the coroutine too in the new aiocontext.
+     */
+    while (qemu_get_current_aio_context() != next_aio_context) {
+        job_unlock();
+        aio_co_reschedule_self(next_aio_context);
+        job_lock();
+        next_aio_context = job->aio_context;
+    }
 
-    /* Set by job_enter_cond() before re-entering the coroutine.  */
+    /* Set by job_enter_cond_locked() before re-entering the coroutine.  */
     assert(job->busy);
 }
 
-void coroutine_fn job_pause_point(Job *job)
+/* Called with job_mutex held, but releases it temporarily. */
+static void coroutine_fn job_pause_point_locked(Job *job)
 {
-    assert(job && job_started(job));
+    assert(job && job_started_locked(job));
 
-    if (!job_should_pause(job)) {
+    if (!job_should_pause_locked(job)) {
         return;
     }
-    if (job_is_cancelled(job)) {
+    if (job_is_cancelled_locked(job)) {
         return;
     }
 
     if (job->driver->pause) {
+        job_unlock();
         job->driver->pause(job);
+        job_lock();
     }
 
-    if (job_should_pause(job) && !job_is_cancelled(job)) {
+    if (job_should_pause_locked(job) && !job_is_cancelled_locked(job)) {
         JobStatus status = job->status;
-        job_state_transition(job, status == JOB_STATUS_READY
-                                  ? JOB_STATUS_STANDBY
-                                  : JOB_STATUS_PAUSED);
+        job_state_transition_locked(job, status == JOB_STATUS_READY
+                                    ? JOB_STATUS_STANDBY
+                                    : JOB_STATUS_PAUSED);
         job->paused = true;
-        job_do_yield(job, -1);
+        job_do_yield_locked(job, -1);
         job->paused = false;
-        job_state_transition(job, status);
+        job_state_transition_locked(job, status);
     }
 
     if (job->driver->resume) {
+        job_unlock();
         job->driver->resume(job);
+        job_lock();
     }
 }
 
-void job_yield(Job *job)
+void coroutine_fn job_pause_point(Job *job)
 {
+    JOB_LOCK_GUARD();
+    job_pause_point_locked(job);
+}
+
+void coroutine_fn job_yield(Job *job)
+{
+    JOB_LOCK_GUARD();
     assert(job->busy);
 
     /* Check cancellation *before* setting busy = false, too!  */
-    if (job_is_cancelled(job)) {
+    if (job_is_cancelled_locked(job)) {
         return;
     }
 
-    if (!job_should_pause(job)) {
-        job_do_yield(job, -1);
+    if (!job_should_pause_locked(job)) {
+        job_do_yield_locked(job, -1);
     }
 
-    job_pause_point(job);
+    job_pause_point_locked(job);
 }
 
 void coroutine_fn job_sleep_ns(Job *job, int64_t ns)
 {
+    JOB_LOCK_GUARD();
     assert(job->busy);
 
     /* Check cancellation *before* setting busy = false, too!  */
-    if (job_is_cancelled(job)) {
+    if (job_is_cancelled_locked(job)) {
         return;
     }
 
-    if (!job_should_pause(job)) {
-        job_do_yield(job, qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + ns);
+    if (!job_should_pause_locked(job)) {
+        job_do_yield_locked(job, qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + ns);
     }
 
-    job_pause_point(job);
+    job_pause_point_locked(job);
 }
 
-/* Assumes the block_job_mutex is held */
-static bool job_timer_not_pending(Job *job)
+/* Assumes the job_mutex is held */
+static bool job_timer_not_pending_locked(Job *job)
 {
     return !timer_pending(&job->sleep_timer);
 }
 
-void job_pause(Job *job)
+void job_pause_locked(Job *job)
 {
     job->pause_count++;
     if (!job->paused) {
-        job_enter(job);
+        job_enter_cond_locked(job, NULL);
     }
 }
 
-void job_resume(Job *job)
+void job_pause(Job *job)
+{
+    JOB_LOCK_GUARD();
+    job_pause_locked(job);
+}
+
+void job_resume_locked(Job *job)
 {
     assert(job->pause_count > 0);
     job->pause_count--;
@@ -567,12 +704,18 @@ void job_resume(Job *job)
     }
 
     /* kick only if no timer is pending */
-    job_enter_cond(job, job_timer_not_pending);
+    job_enter_cond_locked(job, job_timer_not_pending_locked);
 }
 
-void job_user_pause(Job *job, Error **errp)
+void job_resume(Job *job)
 {
-    if (job_apply_verb(job, JOB_VERB_PAUSE, errp)) {
+    JOB_LOCK_GUARD();
+    job_resume_locked(job);
+}
+
+void job_user_pause_locked(Job *job, Error **errp)
+{
+    if (job_apply_verb_locked(job, JOB_VERB_PAUSE, errp)) {
         return;
     }
     if (job->user_paused) {
@@ -580,87 +723,95 @@ void job_user_pause(Job *job, Error **errp)
         return;
     }
     job->user_paused = true;
-    job_pause(job);
+    job_pause_locked(job);
 }
 
-bool job_user_paused(Job *job)
+bool job_user_paused_locked(Job *job)
 {
     return job->user_paused;
 }
 
-void job_user_resume(Job *job, Error **errp)
+void job_user_resume_locked(Job *job, Error **errp)
 {
     assert(job);
+    GLOBAL_STATE_CODE();
     if (!job->user_paused || job->pause_count <= 0) {
         error_setg(errp, "Can't resume a job that was not paused");
         return;
     }
-    if (job_apply_verb(job, JOB_VERB_RESUME, errp)) {
+    if (job_apply_verb_locked(job, JOB_VERB_RESUME, errp)) {
         return;
     }
     if (job->driver->user_resume) {
+        job_unlock();
         job->driver->user_resume(job);
+        job_lock();
     }
     job->user_paused = false;
-    job_resume(job);
+    job_resume_locked(job);
 }
 
-static void job_do_dismiss(Job *job)
+/* Called with job_mutex held, but releases it temporarily. */
+static void job_do_dismiss_locked(Job *job)
 {
     assert(job);
     job->busy = false;
     job->paused = false;
     job->deferred_to_main_loop = true;
 
-    job_txn_del_job(job);
+    job_txn_del_job_locked(job);
 
-    job_state_transition(job, JOB_STATUS_NULL);
-    job_unref(job);
+    job_state_transition_locked(job, JOB_STATUS_NULL);
+    job_unref_locked(job);
 }
 
-void job_dismiss(Job **jobptr, Error **errp)
+void job_dismiss_locked(Job **jobptr, Error **errp)
 {
     Job *job = *jobptr;
     /* similarly to _complete, this is QMP-interface only. */
     assert(job->id);
-    if (job_apply_verb(job, JOB_VERB_DISMISS, errp)) {
+    if (job_apply_verb_locked(job, JOB_VERB_DISMISS, errp)) {
         return;
     }
 
-    job_do_dismiss(job);
+    job_do_dismiss_locked(job);
     *jobptr = NULL;
 }
 
 void job_early_fail(Job *job)
 {
+    JOB_LOCK_GUARD();
     assert(job->status == JOB_STATUS_CREATED);
-    job_do_dismiss(job);
+    job_do_dismiss_locked(job);
 }
 
-static void job_conclude(Job *job)
+/* Called with job_mutex held. */
+static void job_conclude_locked(Job *job)
 {
-    job_state_transition(job, JOB_STATUS_CONCLUDED);
-    if (job->auto_dismiss || !job_started(job)) {
-        job_do_dismiss(job);
+    job_state_transition_locked(job, JOB_STATUS_CONCLUDED);
+    if (job->auto_dismiss || !job_started_locked(job)) {
+        job_do_dismiss_locked(job);
     }
 }
 
-static void job_update_rc(Job *job)
+/* Called with job_mutex held. */
+static void job_update_rc_locked(Job *job)
 {
-    if (!job->ret && job_is_cancelled(job)) {
+    if (!job->ret && job_is_cancelled_locked(job)) {
         job->ret = -ECANCELED;
     }
     if (job->ret) {
         if (!job->err) {
             error_setg(&job->err, "%s", strerror(-job->ret));
         }
-        job_state_transition(job, JOB_STATUS_ABORTING);
+        job_state_transition_locked(job, JOB_STATUS_ABORTING);
     }
 }
 
 static void job_commit(Job *job)
 {
     assert(!job->ret);
+    GLOBAL_STATE_CODE();
     if (job->driver->commit) {
         job->driver->commit(job);
     }
@@ -669,6 +820,7 @@ static void job_commit(Job *job)
 static void job_abort(Job *job)
 {
     assert(job->ret);
+    GLOBAL_STATE_CODE();
     if (job->driver->abort) {
         job->driver->abort(job);
     }
@@ -676,19 +828,28 @@ static void job_abort(Job *job)
 
 static void job_clean(Job *job)
 {
+    GLOBAL_STATE_CODE();
     if (job->driver->clean) {
         job->driver->clean(job);
     }
 }
 
-static int job_finalize_single(Job *job)
+/*
+ * Called with job_mutex held, but releases it temporarily.
+ */
+static int job_finalize_single_locked(Job *job)
 {
-    assert(job_is_completed(job));
+    int job_ret;
+
+    assert(job_is_completed_locked(job));
 
     /* Ensure abort is called for late-transactional failures */
-    job_update_rc(job);
+    job_update_rc_locked(job);
 
-    if (!job->ret) {
+    job_ret = job->ret;
+    job_unlock();
+
+    if (!job_ret) {
         job_commit(job);
     } else {
         job_abort(job);
@@ -696,43 +857,71 @@ static int job_finalize_single(Job *job)
     job_clean(job);
 
     if (job->cb) {
-        job->cb(job->opaque, job->ret);
+        job->cb(job->opaque, job_ret);
     }
 
+    job_lock();
+
     /* Emit events only if we actually started */
-    if (job_started(job)) {
-        if (job_is_cancelled(job)) {
-            job_event_cancelled(job);
+    if (job_started_locked(job)) {
+        if (job_is_cancelled_locked(job)) {
+            job_event_cancelled_locked(job);
         } else {
-            job_event_completed(job);
+            job_event_completed_locked(job);
         }
     }
 
-    job_txn_del_job(job);
-    job_conclude(job);
+    job_txn_del_job_locked(job);
+    job_conclude_locked(job);
     return 0;
 }
 
-static void job_cancel_async(Job *job, bool force)
+/*
+ * Called with job_mutex held, but releases it temporarily.
+ */
+static void job_cancel_async_locked(Job *job, bool force)
 {
+    GLOBAL_STATE_CODE();
+    if (job->driver->cancel) {
+        job_unlock();
+        force = job->driver->cancel(job, force);
+        job_lock();
+    } else {
+        /* No .cancel() means the job will behave as if force-cancelled */
+        force = true;
+    }
+
     if (job->user_paused) {
         /* Do not call job_enter here, the caller will handle it.  */
         if (job->driver->user_resume) {
+            job_unlock();
             job->driver->user_resume(job);
+            job_lock();
         }
         job->user_paused = false;
         assert(job->pause_count > 0);
         job->pause_count--;
     }
-    job->cancelled = true;
-    /* To prevent 'force == false' overriding a previous 'force == true' */
-    job->force_cancel |= force;
+
+    /*
+     * Ignore soft cancel requests after the job is already done
+     * (We will still invoke job->driver->cancel() above, but if the
+     * job driver supports soft cancelling and the job is done, that
+     * should be a no-op, too.  We still call it so it can override
+     * @force.)
+     */
+    if (force || !job->deferred_to_main_loop) {
+        job->cancelled = true;
+        /* To prevent 'force == false' overriding a previous 'force == true' */
+        job->force_cancel |= force;
+    }
 }
 
-static void job_completed_txn_abort(Job *job)
+/*
+ * Called with job_mutex held, but releases it temporarily.
+ */
+static void job_completed_txn_abort_locked(Job *job)
 {
-    AioContext *outer_ctx = job->aio_context;
-    AioContext *ctx;
     JobTxn *txn = job->txn;
     Job *other_job;
 
@@ -743,159 +932,161 @@ static void job_completed_txn_abort(Job *job)
         return;
     }
     txn->aborting = true;
-    job_txn_ref(txn);
+    job_txn_ref_locked(txn);
 
-    /* We can only hold the single job's AioContext lock while calling
-     * job_finalize_single() because the finalization callbacks can involve
-     * calls of AIO_WAIT_WHILE(), which could deadlock otherwise. */
-    aio_context_release(outer_ctx);
+    job_ref_locked(job);
 
     /* Other jobs are effectively cancelled by us, set the status for
      * them; this job, however, may or may not be cancelled, depending
      * on the caller, so leave it. */
     QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
         if (other_job != job) {
-            ctx = other_job->aio_context;
-            aio_context_acquire(ctx);
-            job_cancel_async(other_job, false);
-            aio_context_release(ctx);
+            /*
+             * This is a transaction: If one job failed, no result will matter.
+             * Therefore, pass force=true to terminate all other jobs as quickly
+             * as possible.
+             */
+            job_cancel_async_locked(other_job, true);
         }
     }
     while (!QLIST_EMPTY(&txn->jobs)) {
         other_job = QLIST_FIRST(&txn->jobs);
-        ctx = other_job->aio_context;
-        aio_context_acquire(ctx);
-        if (!job_is_completed(other_job)) {
-            assert(job_is_cancelled(other_job));
-            job_finish_sync(other_job, NULL, NULL);
+        if (!job_is_completed_locked(other_job)) {
+            assert(job_cancel_requested_locked(other_job));
+            job_finish_sync_locked(other_job, NULL, NULL);
         }
-        job_finalize_single(other_job);
-        aio_context_release(ctx);
+        job_finalize_single_locked(other_job);
     }
 
-    aio_context_acquire(outer_ctx);
-
-    job_txn_unref(txn);
+    job_unref_locked(job);
+    job_txn_unref_locked(txn);
 }
 
-static int job_prepare(Job *job)
+/* Called with job_mutex held, but releases it temporarily */
+static int job_prepare_locked(Job *job)
 {
+    int ret;
+
+    GLOBAL_STATE_CODE();
+
     if (job->ret == 0 && job->driver->prepare) {
-        job->ret = job->driver->prepare(job);
-        job_update_rc(job);
+        job_unlock();
+        ret = job->driver->prepare(job);
+        job_lock();
+        job->ret = ret;
+        job_update_rc_locked(job);
     }
+
     return job->ret;
 }
 
-static int job_needs_finalize(Job *job)
+/* Called with job_mutex held */
+static int job_needs_finalize_locked(Job *job)
 {
     return !job->auto_finalize;
 }
 
-static void job_do_finalize(Job *job)
+/* Called with job_mutex held */
+static void job_do_finalize_locked(Job *job)
 {
     int rc;
     assert(job && job->txn);
 
     /* prepare the transaction to complete */
-    rc = job_txn_apply(job, job_prepare);
+    rc = job_txn_apply_locked(job, job_prepare_locked);
     if (rc) {
-        job_completed_txn_abort(job);
+        job_completed_txn_abort_locked(job);
     } else {
-        job_txn_apply(job, job_finalize_single);
+        job_txn_apply_locked(job, job_finalize_single_locked);
     }
 }
 
-void job_finalize(Job *job, Error **errp)
+void job_finalize_locked(Job *job, Error **errp)
 {
     assert(job && job->id);
-    if (job_apply_verb(job, JOB_VERB_FINALIZE, errp)) {
+    if (job_apply_verb_locked(job, JOB_VERB_FINALIZE, errp)) {
         return;
     }
-    job_do_finalize(job);
+    job_do_finalize_locked(job);
 }
 
-static int job_transition_to_pending(Job *job)
+/* Called with job_mutex held. */
+static int job_transition_to_pending_locked(Job *job)
 {
-    job_state_transition(job, JOB_STATUS_PENDING);
+    job_state_transition_locked(job, JOB_STATUS_PENDING);
     if (!job->auto_finalize) {
-        job_event_pending(job);
+        job_event_pending_locked(job);
     }
     return 0;
 }
 
 void job_transition_to_ready(Job *job)
 {
-    job_state_transition(job, JOB_STATUS_READY);
-    job_event_ready(job);
+    JOB_LOCK_GUARD();
+    job_state_transition_locked(job, JOB_STATUS_READY);
+    job_event_ready_locked(job);
 }
 
-static void job_completed_txn_success(Job *job)
+/* Called with job_mutex held. */
+static void job_completed_txn_success_locked(Job *job)
 {
     JobTxn *txn = job->txn;
     Job *other_job;
 
-    job_state_transition(job, JOB_STATUS_WAITING);
+    job_state_transition_locked(job, JOB_STATUS_WAITING);
 
     /*
      * Successful completion, see if there are other running jobs in this
      * txn.
      */
     QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
-        if (!job_is_completed(other_job)) {
+        if (!job_is_completed_locked(other_job)) {
             return;
         }
         assert(other_job->ret == 0);
     }
 
-    job_txn_apply(job, job_transition_to_pending);
+    job_txn_apply_locked(job, job_transition_to_pending_locked);
 
     /* If no jobs need manual finalization, automatically do so */
-    if (job_txn_apply(job, job_needs_finalize) == 0) {
-        job_do_finalize(job);
+    if (job_txn_apply_locked(job, job_needs_finalize_locked) == 0) {
+        job_do_finalize_locked(job);
     }
 }
 
-static void job_completed(Job *job)
+/* Called with job_mutex held. */
+static void job_completed_locked(Job *job)
 {
-    assert(job && job->txn && !job_is_completed(job));
+    assert(job && job->txn && !job_is_completed_locked(job));
 
-    job_update_rc(job);
+    job_update_rc_locked(job);
     trace_job_completed(job, job->ret);
     if (job->ret) {
-        job_completed_txn_abort(job);
+        job_completed_txn_abort_locked(job);
     } else {
-        job_completed_txn_success(job);
+        job_completed_txn_success_locked(job);
     }
 }
 
-/** Useful only as a type shim for aio_bh_schedule_oneshot. */
+/**
+ * Useful only as a type shim for aio_bh_schedule_oneshot.
+ * Called with job_mutex *not* held.
+ */
 static void job_exit(void *opaque)
 {
     Job *job = (Job *)opaque;
-    AioContext *ctx;
-
-    job_ref(job);
-    aio_context_acquire(job->aio_context);
+    JOB_LOCK_GUARD();
+    job_ref_locked(job);
 
     /* This is a lie, we're not quiescent, but still doing the completion
      * callbacks. However, completion callbacks tend to involve operations that
      * drain block nodes, and if .drained_poll still returned true, we would
      * deadlock. */
     job->busy = false;
-    job_event_idle(job);
+    job_event_idle_locked(job);
 
-    job_completed(job);
-
-    /*
-     * Note that calling job_completed can move the job to a different
-     * aio_context, so we cannot cache from above. job_txn_apply takes care of
-     * acquiring the new lock, and we ref/unref to avoid job_completed freeing
-     * the job underneath us.
-     */
-    ctx = job->aio_context;
-    job_unref(job);
-    aio_context_release(ctx);
+    job_completed_locked(job);
+    job_unref_locked(job);
 }
 
 /**
@@ -905,118 +1096,169 @@ static void job_exit(void *opaque)
 static void coroutine_fn job_co_entry(void *opaque)
 {
     Job *job = opaque;
+    int ret;
 
     assert(job && job->driver && job->driver->run);
-    job_pause_point(job);
-    job->ret = job->driver->run(job, &job->err);
-    job->deferred_to_main_loop = true;
-    job->busy = true;
+    WITH_JOB_LOCK_GUARD() {
+        assert(job->aio_context == qemu_get_current_aio_context());
+        job_pause_point_locked(job);
+    }
+    ret = job->driver->run(job, &job->err);
+    WITH_JOB_LOCK_GUARD() {
+        job->ret = ret;
+        job->deferred_to_main_loop = true;
+        job->busy = true;
+    }
     aio_bh_schedule_oneshot(qemu_get_aio_context(), job_exit, job);
 }
 
 void job_start(Job *job)
 {
-    assert(job && !job_started(job) && job->paused &&
-           job->driver && job->driver->run);
-    job->co = qemu_coroutine_create(job_co_entry, job);
-    job->pause_count--;
-    job->busy = true;
-    job->paused = false;
-    job_state_transition(job, JOB_STATUS_RUNNING);
+    assert(qemu_in_main_thread());
+
+    WITH_JOB_LOCK_GUARD() {
+        assert(job && !job_started_locked(job) && job->paused &&
+            job->driver && job->driver->run);
+        job->co = qemu_coroutine_create(job_co_entry, job);
+        job->pause_count--;
+        job->busy = true;
+        job->paused = false;
+        job_state_transition_locked(job, JOB_STATUS_RUNNING);
+    }
     aio_co_enter(job->aio_context, job->co);
 }
 
-void job_cancel(Job *job, bool force)
+void job_cancel_locked(Job *job, bool force)
 {
     if (job->status == JOB_STATUS_CONCLUDED) {
-        job_do_dismiss(job);
+        job_do_dismiss_locked(job);
         return;
     }
-    job_cancel_async(job, force);
-    if (!job_started(job)) {
-        job_completed(job);
+    job_cancel_async_locked(job, force);
+    if (!job_started_locked(job)) {
+        job_completed_locked(job);
     } else if (job->deferred_to_main_loop) {
-        job_completed_txn_abort(job);
+        /*
+         * job_cancel_async() ignores soft-cancel requests for jobs
+         * that are already done (i.e. deferred to the main loop).  We
+         * have to check again whether the job is really cancelled.
+         * (job_cancel_requested() and job_is_cancelled() are equivalent
+         * here, because job_cancel_async() will make soft-cancel
+         * requests no-ops when deferred_to_main_loop is true.  We
+         * choose to call job_is_cancelled() to show that we invoke
+         * job_completed_txn_abort() only for force-cancelled jobs.)
+         */
+        if (job_is_cancelled_locked(job)) {
+            job_completed_txn_abort_locked(job);
+        }
     } else {
-        job_enter(job);
+        job_enter_cond_locked(job, NULL);
     }
 }
 
-void job_user_cancel(Job *job, bool force, Error **errp)
+void job_user_cancel_locked(Job *job, bool force, Error **errp)
 {
-    if (job_apply_verb(job, JOB_VERB_CANCEL, errp)) {
+    if (job_apply_verb_locked(job, JOB_VERB_CANCEL, errp)) {
         return;
     }
-    job_cancel(job, force);
+    job_cancel_locked(job, force);
+}
+
+/* A wrapper around job_cancel_locked() taking an Error ** parameter so it may
+ * be used with job_finish_sync_locked() without the need for (rather nasty)
+ * function pointer casts there.
+ *
+ * Called with job_mutex held.
+ */
+static void job_cancel_err_locked(Job *job, Error **errp)
+{
+    job_cancel_locked(job, false);
+}
+
+/**
+ * Same as job_cancel_err(), but force-cancel.
+ * Called with job_mutex held.
+ */
+static void job_force_cancel_err_locked(Job *job, Error **errp)
+{
+    job_cancel_locked(job, true);
 }
 
-/* A wrapper around job_cancel() taking an Error ** parameter so it may be
- * used with job_finish_sync() without the need for (rather nasty) function
- * pointer casts there. */
-static void job_cancel_err(Job *job, Error **errp)
+int job_cancel_sync_locked(Job *job, bool force)
 {
-    job_cancel(job, false);
+    if (force) {
+        return job_finish_sync_locked(job, &job_force_cancel_err_locked, NULL);
+    } else {
+        return job_finish_sync_locked(job, &job_cancel_err_locked, NULL);
+    }
 }
 
-int job_cancel_sync(Job *job)
+int job_cancel_sync(Job *job, bool force)
 {
-    return job_finish_sync(job, &job_cancel_err, NULL);
+    JOB_LOCK_GUARD();
+    return job_cancel_sync_locked(job, force);
 }
 
 void job_cancel_sync_all(void)
 {
     Job *job;
-    AioContext *aio_context;
+    JOB_LOCK_GUARD();
 
-    while ((job = job_next(NULL))) {
-        aio_context = job->aio_context;
-        aio_context_acquire(aio_context);
-        job_cancel_sync(job);
-        aio_context_release(aio_context);
+    while ((job = job_next_locked(NULL))) {
+        job_cancel_sync_locked(job, true);
     }
 }
 
-int job_complete_sync(Job *job, Error **errp)
+int job_complete_sync_locked(Job *job, Error **errp)
 {
-    return job_finish_sync(job, job_complete, errp);
+    return job_finish_sync_locked(job, job_complete_locked, errp);
 }
 
-void job_complete(Job *job, Error **errp)
+void job_complete_locked(Job *job, Error **errp)
 {
     /* Should not be reachable via external interface for internal jobs */
     assert(job->id);
-    if (job_apply_verb(job, JOB_VERB_COMPLETE, errp)) {
+    GLOBAL_STATE_CODE();
+    if (job_apply_verb_locked(job, JOB_VERB_COMPLETE, errp)) {
         return;
     }
-    if (job->pause_count || job_is_cancelled(job) || !job->driver->complete) {
+    if (job_cancel_requested_locked(job) || !job->driver->complete) {
         error_setg(errp, "The active block job '%s' cannot be completed",
                    job->id);
         return;
     }
 
+    job_unlock();
     job->driver->complete(job, errp);
+    job_lock();
 }
 
-int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
+int job_finish_sync_locked(Job *job,
+                           void (*finish)(Job *, Error **errp),
+                           Error **errp)
 {
     Error *local_err = NULL;
     int ret;
+    GLOBAL_STATE_CODE();
 
-    job_ref(job);
+    job_ref_locked(job);
 
     if (finish) {
         finish(job, &local_err);
     }
     if (local_err) {
         error_propagate(errp, local_err);
-        job_unref(job);
+        job_unref_locked(job);
         return -EBUSY;
     }
 
-    AIO_WAIT_WHILE(job->aio_context,
-                   (job_enter(job), !job_is_completed(job)));
+    job_unlock();
+    AIO_WAIT_WHILE_UNLOCKED(job->aio_context,
+                            (job_enter(job), !job_is_completed(job)));
+    job_lock();
 
-    ret = (job_is_cancelled(job) && job->ret == 0) ? -ECANCELED : job->ret;
-    job_unref(job);
+    ret = (job_is_cancelled_locked(job) && job->ret == 0)
+          ? -ECANCELED : job->ret;
+    job_unref_locked(job);
     return ret;
 }