Merge remote-tracking branch 'remotes/famz/tags/block-pull-request' into staging

# gpg: Signature made Tue 11 Apr 2017 13:10:55 BST
# gpg:                using RSA key 0xCA35624C6A9171C6
# gpg: Good signature from "Fam Zheng <famz@redhat.com>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 5003 7CB7 9706 0F76 F021  AD56 CA35 624C 6A91 71C6

* remotes/famz/tags/block-pull-request:
  sheepdog: Use bdrv_coroutine_enter before BDRV_POLL_WHILE
  block: Fix bdrv_co_flush early return
  block: Use bdrv_coroutine_enter to start I/O coroutines
  qemu-io-cmds: Use bdrv_coroutine_enter
  blockjob: Use bdrv_coroutine_enter to start coroutine
  block: Introduce bdrv_coroutine_enter
  async: Introduce aio_co_enter
  coroutine: Extract qemu_aio_coroutine_enter
  tests/block-job-txn: Don't start block job before adding to txn
  block: Quiesce old aio context during bdrv_set_aio_context
  block: Make bdrv_parent_drained_begin/end public

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

14 files changed, 92 insertions, 33 deletions

diff --git a/block.c b/block.c
index b8a30115e1..086a12df97 100644
--- a/block.c
+++ b/block.c
@@ -4324,6 +4324,11 @@ AioContext *bdrv_get_aio_context(BlockDriverState *bs)
     return bs->aio_context;
 }
 
+void bdrv_coroutine_enter(BlockDriverState *bs, Coroutine *co)
+{
+    aio_co_enter(bdrv_get_aio_context(bs), co);
+}
+
 static void bdrv_do_remove_aio_context_notifier(BdrvAioNotifier *ban)
 {
     QLIST_REMOVE(ban, list);
@@ -4396,11 +4401,12 @@ void bdrv_attach_aio_context(BlockDriverState *bs,
 
 void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
 {
-    AioContext *ctx;
+    AioContext *ctx = bdrv_get_aio_context(bs);
 
+    aio_disable_external(ctx);
+    bdrv_parent_drained_begin(bs);
     bdrv_drain(bs); /* ensure there are no in-flight requests */
 
-    ctx = bdrv_get_aio_context(bs);
     while (aio_poll(ctx, false)) {
         /* wait for all bottom halves to execute */
     }
@@ -4412,6 +4418,8 @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
      */
     aio_context_acquire(new_context);
     bdrv_attach_aio_context(bs, new_context);
+    bdrv_parent_drained_end(bs);
+    aio_enable_external(ctx);
     aio_context_release(new_context);
 }
 
diff --git a/block/block-backend.c b/block/block-backend.c
index 18ece99c6e..a8f2b3440f 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1045,7 +1045,7 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
         co_entry(&rwco);
     } else {
         Coroutine *co = qemu_coroutine_create(co_entry, &rwco);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(blk_bs(blk), co);
         BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE);
     }
 
@@ -1152,7 +1152,7 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
     acb->has_returned = false;
 
     co = qemu_coroutine_create(co_entry, acb);
-    qemu_coroutine_enter(co);
+    bdrv_coroutine_enter(blk_bs(blk), co);
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
diff --git a/block/io.c b/block/io.c
index 7321ddab3d..bae6947032 100644
--- a/block/io.c
+++ b/block/io.c
@@ -44,7 +44,7 @@ static void coroutine_fn bdrv_co_do_rw(void *opaque);
 static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
     int64_t offset, int count, BdrvRequestFlags flags);
 
-static void bdrv_parent_drained_begin(BlockDriverState *bs)
+void bdrv_parent_drained_begin(BlockDriverState *bs)
 {
     BdrvChild *c;
 
@@ -55,7 +55,7 @@ static void bdrv_parent_drained_begin(BlockDriverState *bs)
     }
 }
 
-static void bdrv_parent_drained_end(BlockDriverState *bs)
+void bdrv_parent_drained_end(BlockDriverState *bs)
 {
     BdrvChild *c;
 
@@ -616,7 +616,7 @@ static int bdrv_prwv_co(BdrvChild *child, int64_t offset,
         bdrv_rw_co_entry(&rwco);
     } else {
         co = qemu_coroutine_create(bdrv_rw_co_entry, &rwco);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(child->bs, co);
         BDRV_POLL_WHILE(child->bs, rwco.ret == NOT_DONE);
     }
     return rwco.ret;
@@ -1880,7 +1880,7 @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs,
     } else {
         co = qemu_coroutine_create(bdrv_get_block_status_above_co_entry,
                                    &data);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(bs, co);
         BDRV_POLL_WHILE(bs, !data.done);
     }
     return data.ret;
@@ -2006,7 +2006,7 @@ bdrv_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos,
         };
         Coroutine *co = qemu_coroutine_create(bdrv_co_rw_vmstate_entry, &data);
 
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(bs, co);
         while (data.ret == -EINPROGRESS) {
             aio_poll(bdrv_get_aio_context(bs), true);
         }
@@ -2223,7 +2223,7 @@ static BlockAIOCB *bdrv_co_aio_prw_vector(BdrvChild *child,
     acb->is_write = is_write;
 
     co = qemu_coroutine_create(bdrv_co_do_rw, acb);
-    qemu_coroutine_enter(co);
+    bdrv_coroutine_enter(child->bs, co);
 
     bdrv_co_maybe_schedule_bh(acb);
     return &acb->common;
@@ -2254,7 +2254,7 @@ BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs,
     acb->req.error = -EINPROGRESS;
 
     co = qemu_coroutine_create(bdrv_aio_flush_co_entry, acb);
-    qemu_coroutine_enter(co);
+    bdrv_coroutine_enter(bs, co);
 
     bdrv_co_maybe_schedule_bh(acb);
     return &acb->common;
@@ -2278,16 +2278,17 @@ static void coroutine_fn bdrv_flush_co_entry(void *opaque)
 
 int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
 {
-    int ret;
+    int current_gen;
+    int ret = 0;
+
+    bdrv_inc_in_flight(bs);
 
     if (!bs || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs) ||
         bdrv_is_sg(bs)) {
-        return 0;
+        goto early_exit;
     }
 
-    bdrv_inc_in_flight(bs);
-
-    int current_gen = bs->write_gen;
+    current_gen = bs->write_gen;
 
     /* Wait until any previous flushes are completed */
     while (bs->active_flush_req) {
@@ -2370,6 +2371,7 @@ out:
     /* Return value is ignored - it's ok if wait queue is empty */
     qemu_co_queue_next(&bs->flush_queue);
 
+early_exit:
     bdrv_dec_in_flight(bs);
     return ret;
 }
@@ -2387,7 +2389,7 @@ int bdrv_flush(BlockDriverState *bs)
         bdrv_flush_co_entry(&flush_co);
     } else {
         co = qemu_coroutine_create(bdrv_flush_co_entry, &flush_co);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(bs, co);
         BDRV_POLL_WHILE(bs, flush_co.ret == NOT_DONE);
     }
 
@@ -2534,7 +2536,7 @@ int bdrv_pdiscard(BlockDriverState *bs, int64_t offset, int count)
         bdrv_pdiscard_co_entry(&rwco);
     } else {
         co = qemu_coroutine_create(bdrv_pdiscard_co_entry, &rwco);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(bs, co);
         BDRV_POLL_WHILE(bs, rwco.ret == NOT_DONE);
     }
 
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 1b71fc81ec..14d6327209 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -736,7 +736,7 @@ static int do_req(int sockfd, BlockDriverState *bs, SheepdogReq *hdr,
     } else {
         co = qemu_coroutine_create(do_co_req, &srco);
         if (bs) {
-            qemu_coroutine_enter(co);
+            bdrv_coroutine_enter(bs, co);
             BDRV_POLL_WHILE(bs, !srco.finished);
         } else {
             qemu_coroutine_enter(co);
diff --git a/blockjob.c b/blockjob.c
index 9b619f385a..6e489327ff 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -290,7 +290,7 @@ void block_job_start(BlockJob *job)
     job->pause_count--;
     job->busy = true;
     job->paused = false;
-    qemu_coroutine_enter(job->co);
+    bdrv_coroutine_enter(blk_bs(job->blk), job->co);
 }
 
 void block_job_ref(BlockJob *job)
@@ -532,7 +532,7 @@ void block_job_user_resume(BlockJob *job)
 void block_job_enter(BlockJob *job)
 {
     if (job->co && !job->busy) {
-        qemu_coroutine_enter(job->co);
+        bdrv_coroutine_enter(blk_bs(job->blk), job->co);
     }
 }
 
diff --git a/include/block/aio.h b/include/block/aio.h
index 677b6ffc25..406e32305a 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -511,6 +511,15 @@ void aio_co_schedule(AioContext *ctx, struct Coroutine *co);
 void aio_co_wake(struct Coroutine *co);
 
 /**
+ * aio_co_enter:
+ * @ctx: the context to run the coroutine
+ * @co: the coroutine to run
+ *
+ * Enter a coroutine in the specified AioContext.
+ */
+void aio_co_enter(AioContext *ctx, struct Coroutine *co);
+
+/**
  * Return the AioContext whose event loop runs in the current thread.
  *
  * If called from an IOThread this will be the IOThread's AioContext.  If
diff --git a/include/block/block.h b/include/block/block.h
index 3e09222f5f..97d4330292 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -558,6 +558,11 @@ bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
 AioContext *bdrv_get_aio_context(BlockDriverState *bs);
 
 /**
+ * Transfer control to @co in the aio context of @bs
+ */
+void bdrv_coroutine_enter(BlockDriverState *bs, Coroutine *co);
+
+/**
  * bdrv_set_aio_context:
  *
  * Changes the #AioContext used for fd handlers, timers, and BHs by this
@@ -573,6 +578,22 @@ void bdrv_io_plug(BlockDriverState *bs);
 void bdrv_io_unplug(BlockDriverState *bs);
 
 /**
+ * bdrv_parent_drained_begin:
+ *
+ * Begin a quiesced section of all users of @bs. This is part of
+ * bdrv_drained_begin.
+ */
+void bdrv_parent_drained_begin(BlockDriverState *bs);
+
+/**
+ * bdrv_parent_drained_end:
+ *
+ * End a quiesced section of all users of @bs. This is part of
+ * bdrv_drained_end.
+ */
+void bdrv_parent_drained_end(BlockDriverState *bs);
+
+/**
  * bdrv_drained_begin:
  *
  * Begin a quiesced section for exclusive access to the BDS, by disabling
diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h
index e60beaff81..a4509bd977 100644
--- a/include/qemu/coroutine.h
+++ b/include/qemu/coroutine.h
@@ -77,6 +77,11 @@ void qemu_coroutine_enter(Coroutine *coroutine);
 void qemu_coroutine_enter_if_inactive(Coroutine *co);
 
 /**
+ * Transfer control to a coroutine and associate it with ctx
+ */
+void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co);
+
+/**
  * Transfer control back to a coroutine's caller
  *
  * This function does not return until the coroutine is re-entered using
diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c
index 883f53b64d..312fc6d157 100644
--- a/qemu-io-cmds.c
+++ b/qemu-io-cmds.c
@@ -521,7 +521,7 @@ static int do_co_pwrite_zeroes(BlockBackend *blk, int64_t offset,
     }
 
     co = qemu_coroutine_create(co_pwrite_zeroes_entry, &data);
-    qemu_coroutine_enter(co);
+    bdrv_coroutine_enter(blk_bs(blk), co);
     while (!data.done) {
         aio_poll(blk_get_aio_context(blk), true);
     }
diff --git a/tests/qemu-iotests/109.out b/tests/qemu-iotests/109.out
index e5d70d75f1..55fe536d56 100644
--- a/tests/qemu-iotests/109.out
+++ b/tests/qemu-iotests/109.out
@@ -10,7 +10,7 @@ Automatically detecting the format is dangerous for raw images, write operations
 Specify the 'raw' format explicitly to remove the restrictions.
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_ERROR", "data": {"device": "src", "operation": "write", "action": "report"}}
-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 1024, "offset": 0, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 65536, "offset": 0, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
 {"return": []}
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -73,7 +73,7 @@ Automatically detecting the format is dangerous for raw images, write operations
 Specify the 'raw' format explicitly to remove the restrictions.
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_ERROR", "data": {"device": "src", "operation": "write", "action": "report"}}
-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 1024, "offset": 0, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 65536, "offset": 0, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
 {"return": []}
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -115,7 +115,7 @@ Automatically detecting the format is dangerous for raw images, write operations
 Specify the 'raw' format explicitly to remove the restrictions.
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_ERROR", "data": {"device": "src", "operation": "write", "action": "report"}}
-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2560, "offset": 0, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 65536, "offset": 0, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
 {"return": []}
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -135,7 +135,7 @@ Automatically detecting the format is dangerous for raw images, write operations
 Specify the 'raw' format explicitly to remove the restrictions.
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_ERROR", "data": {"device": "src", "operation": "write", "action": "report"}}
-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2560, "offset": OFFSET, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 65536, "offset": OFFSET, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
 {"return": []}
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -195,7 +195,7 @@ Automatically detecting the format is dangerous for raw images, write operations
 Specify the 'raw' format explicitly to remove the restrictions.
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_ERROR", "data": {"device": "src", "operation": "write", "action": "report"}}
-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2048, "offset": OFFSET, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 65536, "offset": OFFSET, "speed": 0, "type": "mirror", "error": "Operation not permitted"}}
 {"return": []}
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
diff --git a/tests/test-blockjob-txn.c b/tests/test-blockjob-txn.c
index 4ccbda14af..0f80194e85 100644
--- a/tests/test-blockjob-txn.c
+++ b/tests/test-blockjob-txn.c
@@ -110,7 +110,6 @@ static BlockJob *test_block_job_start(unsigned int iterations,
     s->result = result;
     data->job = s;
     data->result = result;
-    block_job_start(&s->common);
     return &s->common;
 }
 
@@ -123,6 +122,7 @@ static void test_single_job(int expected)
     txn = block_job_txn_new();
     job = test_block_job_start(1, true, expected, &result);
     block_job_txn_add_job(txn, job);
+    block_job_start(job);
 
     if (expected == -ECANCELED) {
         block_job_cancel(job);
@@ -164,6 +164,8 @@ static void test_pair_jobs(int expected1, int expected2)
     block_job_txn_add_job(txn, job1);
     job2 = test_block_job_start(2, true, expected2, &result2);
     block_job_txn_add_job(txn, job2);
+    block_job_start(job1);
+    block_job_start(job2);
 
     if (expected1 == -ECANCELED) {
         block_job_cancel(job1);
@@ -223,6 +225,8 @@ static void test_pair_jobs_fail_cancel_race(void)
     block_job_txn_add_job(txn, job1);
     job2 = test_block_job_start(2, false, 0, &result2);
     block_job_txn_add_job(txn, job2);
+    block_job_start(job1);
+    block_job_start(job2);
 
     block_job_cancel(job1);
 
diff --git a/util/async.c b/util/async.c
index 663e297e1f..355af73ee7 100644
--- a/util/async.c
+++ b/util/async.c
@@ -453,6 +453,11 @@ void aio_co_wake(struct Coroutine *co)
     smp_read_barrier_depends();
     ctx = atomic_read(&co->ctx);
 
+    aio_co_enter(ctx, co);
+}
+
+void aio_co_enter(AioContext *ctx, struct Coroutine *co)
+{
     if (ctx != qemu_get_current_aio_context()) {
         aio_co_schedule(ctx, co);
         return;
@@ -464,7 +469,7 @@ void aio_co_wake(struct Coroutine *co)
         QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, co, co_queue_next);
     } else {
         aio_context_acquire(ctx);
-        qemu_coroutine_enter(co);
+        qemu_aio_coroutine_enter(ctx, co);
         aio_context_release(ctx);
     }
 }
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 72412e5649..486af9a622 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -102,12 +102,12 @@ static void coroutine_delete(Coroutine *co)
     qemu_coroutine_delete(co);
 }
 
-void qemu_coroutine_enter(Coroutine *co)
+void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co)
 {
     Coroutine *self = qemu_coroutine_self();
     CoroutineAction ret;
 
-    trace_qemu_coroutine_enter(self, co, co->entry_arg);
+    trace_qemu_aio_coroutine_enter(ctx, self, co, co->entry_arg);
 
     if (co->caller) {
         fprintf(stderr, "Co-routine re-entered recursively\n");
@@ -115,7 +115,7 @@ void qemu_coroutine_enter(Coroutine *co)
     }
 
     co->caller = self;
-    co->ctx = qemu_get_current_aio_context();
+    co->ctx = ctx;
 
     /* Store co->ctx before anything that stores co.  Matches
      * barrier in aio_co_wake and qemu_co_mutex_wake.
@@ -139,6 +139,11 @@ void qemu_coroutine_enter(Coroutine *co)
     }
 }
 
+void qemu_coroutine_enter(Coroutine *co)
+{
+    qemu_aio_coroutine_enter(qemu_get_current_aio_context(), co);
+}
+
 void qemu_coroutine_enter_if_inactive(Coroutine *co)
 {
     if (!qemu_coroutine_entered(co)) {
diff --git a/util/trace-events b/util/trace-events
index ac27d94a97..b44ef4f895 100644
--- a/util/trace-events
+++ b/util/trace-events
@@ -22,7 +22,7 @@ buffer_move(const char *buf, size_t len, const char *from) "%s: %zd bytes from %
 buffer_free(const char *buf, size_t len) "%s: capacity %zd"
 
 # util/qemu-coroutine.c
-qemu_coroutine_enter(void *from, void *to, void *opaque) "from %p to %p opaque %p"
+qemu_aio_coroutine_enter(void *ctx, void *from, void *to, void *opaque) "ctx %p from %p to %p opaque %p"
 qemu_coroutine_yield(void *from, void *to) "from %p to %p"
 qemu_coroutine_terminate(void *co) "self %p"