qcow2: Don't assume 0 is an invalid cluster offset

[qemu.git] / job.c

diff --git a/job.c b/job.c
index 192f16842367e676e21df549eaa46825edae37fd..da8e4b7bf2f35ea26262af612b51c7a7f5f72f8d 100644 (file)
--- a/job.c
+++ b/job.c
@@ -29,6 +29,7 @@
 #include "qemu/job.h"
 #include "qemu/id.h"
 #include "qemu/main-loop.h"
+#include "block/aio-wait.h"
 #include "trace-root.h"
 #include "qapi/qapi-events-job.h"
 
@@ -136,21 +137,13 @@ static void job_txn_del_job(Job *job)
     }
 }
 
-static int job_txn_apply(JobTxn *txn, int fn(Job *), bool lock)
+static int job_txn_apply(JobTxn *txn, int fn(Job *))
 {
-    AioContext *ctx;
     Job *job, *next;
     int rc = 0;
 
     QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) {
-        if (lock) {
-            ctx = job->aio_context;
-            aio_context_acquire(ctx);
-        }
         rc = fn(job);
-        if (lock) {
-            aio_context_release(ctx);
-        }
         if (rc) {
             break;
         }
@@ -166,7 +159,7 @@ bool job_is_internal(Job *job)
 static void job_state_transition(Job *job, JobStatus s1)
 {
     JobStatus s0 = job->status;
-    assert(s1 >= 0 && s1 <= JOB_STATUS__MAX);
+    assert(s1 >= 0 && s1 < JOB_STATUS__MAX);
     trace_job_state_transition(job, job->ret,
                                JobSTT[s0][s1] ? "allowed" : "disallowed",
                                JobStatus_str(s0), JobStatus_str(s1));
@@ -181,7 +174,7 @@ static void job_state_transition(Job *job, JobStatus s1)
 int job_apply_verb(Job *job, JobVerb verb, Error **errp)
 {
     JobStatus s0 = job->status;
-    assert(verb >= 0 && verb <= JOB_VERB__MAX);
+    assert(verb >= 0 && verb < JOB_VERB__MAX);
     trace_job_apply_verb(job, JobStatus_str(s0), JobVerb_str(verb),
                          JobVerbTable[verb][s0] ? "allowed" : "prohibited");
     if (JobVerbTable[verb][s0]) {
@@ -410,6 +403,11 @@ static void job_event_ready(Job *job)
     notifier_list_notify(&job->on_ready, job);
 }
 
+static void job_event_idle(Job *job)
+{
+    notifier_list_notify(&job->on_idle, job);
+}
+
 void job_enter_cond(Job *job, bool(*fn)(Job *job))
 {
     if (!job_started(job)) {
@@ -455,6 +453,7 @@ static void coroutine_fn job_do_yield(Job *job, uint64_t ns)
         timer_mod(&job->sleep_timer, ns);
     }
     job->busy = false;
+    job_event_idle(job);
     job_unlock();
     qemu_coroutine_yield();
 
@@ -719,6 +718,7 @@ static void job_cancel_async(Job *job, bool force)
 
 static void job_completed_txn_abort(Job *job)
 {
+    AioContext *outer_ctx = job->aio_context;
     AioContext *ctx;
     JobTxn *txn = job->txn;
     Job *other_job;
@@ -732,23 +732,26 @@ static void job_completed_txn_abort(Job *job)
     txn->aborting = true;
     job_txn_ref(txn);
 
-    /* We are the first failed job. Cancel other jobs. */
-    QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
-        ctx = other_job->aio_context;
-        aio_context_acquire(ctx);
-    }
+    /* 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);
 
     /* 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);
         }
     }
     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);
@@ -757,6 +760,8 @@ static void job_completed_txn_abort(Job *job)
         aio_context_release(ctx);
     }
 
+    aio_context_acquire(outer_ctx);
+
     job_txn_unref(txn);
 }
 
@@ -780,11 +785,11 @@ static void job_do_finalize(Job *job)
     assert(job && job->txn);
 
     /* prepare the transaction to complete */
-    rc = job_txn_apply(job->txn, job_prepare, true);
+    rc = job_txn_apply(job->txn, job_prepare);
     if (rc) {
         job_completed_txn_abort(job);
     } else {
-        job_txn_apply(job->txn, job_finalize_single, true);
+        job_txn_apply(job->txn, job_finalize_single);
     }
 }
 
@@ -830,10 +835,10 @@ static void job_completed_txn_success(Job *job)
         assert(other_job->ret == 0);
     }
 
-    job_txn_apply(txn, job_transition_to_pending, false);
+    job_txn_apply(txn, job_transition_to_pending);
 
     /* If no jobs need manual finalization, automatically do so */
-    if (job_txn_apply(txn, job_needs_finalize, false) == 0) {
+    if (job_txn_apply(txn, job_needs_finalize) == 0) {
         job_do_finalize(job);
     }
 }
@@ -855,7 +860,20 @@ static void job_completed(Job *job)
 static void job_exit(void *opaque)
 {
     Job *job = (Job *)opaque;
+    AioContext *ctx = job->aio_context;
+
+    aio_context_acquire(ctx);
+
+    /* 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_completed(job);
+
+    aio_context_release(ctx);
 }
 
 /**
@@ -870,6 +888,7 @@ static void coroutine_fn job_co_entry(void *opaque)
     job_pause_point(job);
     job->ret = job->driver->run(job, &job->err);
     job->deferred_to_main_loop = true;
+    job->busy = true;
     aio_bh_schedule_oneshot(qemu_get_aio_context(), job_exit, job);
 }
 
@@ -971,14 +990,10 @@ int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
         job_unref(job);
         return -EBUSY;
     }
-    /* job_drain calls job_enter, and it should be enough to induce progress
-     * until the job completes or moves to the main thread. */
-    while (!job->deferred_to_main_loop && !job_is_completed(job)) {
-        job_drain(job);
-    }
-    while (!job_is_completed(job)) {
-        aio_poll(qemu_get_aio_context(), true);
-    }
+
+    AIO_WAIT_WHILE(job->aio_context,
+                   (job_drain(job), !job_is_completed(job)));
+
     ret = (job_is_cancelled(job) && job->ret == 0) ? -ECANCELED : job->ret;
     job_unref(job);
     return ret;