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

# gpg: Signature made Fri 13 Oct 2017 14:49:22 BST
# gpg:                using RSA key 0x9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  block/throttle.c: add bdrv_co_drain_begin/end callbacks
  block: rename bdrv_co_drain to bdrv_co_drain_begin
  block: add bdrv_co_drain_end callback

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

4 files changed, 65 insertions, 20 deletions

diff --git a/block/io.c b/block/io.c
index 8e419070b5..0854e0fdac 100644
--- a/block/io.c
+++ b/block/io.c
@@ -156,6 +156,7 @@ typedef struct {
     Coroutine *co;
     BlockDriverState *bs;
     bool done;
+    bool begin;
 } BdrvCoDrainData;
 
 static void coroutine_fn bdrv_drain_invoke_entry(void *opaque)
@@ -163,18 +164,23 @@ static void coroutine_fn bdrv_drain_invoke_entry(void *opaque)
     BdrvCoDrainData *data = opaque;
     BlockDriverState *bs = data->bs;
 
-    bs->drv->bdrv_co_drain(bs);
+    if (data->begin) {
+        bs->drv->bdrv_co_drain_begin(bs);
+    } else {
+        bs->drv->bdrv_co_drain_end(bs);
+    }
 
     /* Set data->done before reading bs->wakeup.  */
     atomic_mb_set(&data->done, true);
     bdrv_wakeup(bs);
 }
 
-static void bdrv_drain_invoke(BlockDriverState *bs)
+static void bdrv_drain_invoke(BlockDriverState *bs, bool begin)
 {
-    BdrvCoDrainData data = { .bs = bs, .done = false };
+    BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin};
 
-    if (!bs->drv || !bs->drv->bdrv_co_drain) {
+    if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) ||
+            (!begin && !bs->drv->bdrv_co_drain_end)) {
         return;
     }
 
@@ -183,15 +189,16 @@ static void bdrv_drain_invoke(BlockDriverState *bs)
     BDRV_POLL_WHILE(bs, !data.done);
 }
 
-static bool bdrv_drain_recurse(BlockDriverState *bs)
+static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin)
 {
     BdrvChild *child, *tmp;
     bool waited;
 
-    waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0);
-
     /* Ensure any pending metadata writes are submitted to bs->file.  */
-    bdrv_drain_invoke(bs);
+    bdrv_drain_invoke(bs, begin);
+
+    /* Wait for drained requests to finish */
+    waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0);
 
     QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) {
         BlockDriverState *bs = child->bs;
@@ -208,7 +215,7 @@ static bool bdrv_drain_recurse(BlockDriverState *bs)
              */
             bdrv_ref(bs);
         }
-        waited |= bdrv_drain_recurse(bs);
+        waited |= bdrv_drain_recurse(bs, begin);
         if (in_main_loop) {
             bdrv_unref(bs);
         }
@@ -224,12 +231,18 @@ static void bdrv_co_drain_bh_cb(void *opaque)
     BlockDriverState *bs = data->bs;
 
     bdrv_dec_in_flight(bs);
-    bdrv_drained_begin(bs);
+    if (data->begin) {
+        bdrv_drained_begin(bs);
+    } else {
+        bdrv_drained_end(bs);
+    }
+
     data->done = true;
     aio_co_wake(co);
 }
 
-static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs)
+static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
+                                                bool begin)
 {
     BdrvCoDrainData data;
 
@@ -242,6 +255,7 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs)
         .co = qemu_coroutine_self(),
         .bs = bs,
         .done = false,
+        .begin = begin,
     };
     bdrv_inc_in_flight(bs);
     aio_bh_schedule_oneshot(bdrv_get_aio_context(bs),
@@ -256,7 +270,7 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs)
 void bdrv_drained_begin(BlockDriverState *bs)
 {
     if (qemu_in_coroutine()) {
-        bdrv_co_yield_to_drain(bs);
+        bdrv_co_yield_to_drain(bs, true);
         return;
     }
 
@@ -265,17 +279,22 @@ void bdrv_drained_begin(BlockDriverState *bs)
         bdrv_parent_drained_begin(bs);
     }
 
-    bdrv_drain_recurse(bs);
+    bdrv_drain_recurse(bs, true);
 }
 
 void bdrv_drained_end(BlockDriverState *bs)
 {
+    if (qemu_in_coroutine()) {
+        bdrv_co_yield_to_drain(bs, false);
+        return;
+    }
     assert(bs->quiesce_counter > 0);
     if (atomic_fetch_dec(&bs->quiesce_counter) > 1) {
         return;
     }
 
     bdrv_parent_drained_end(bs);
+    bdrv_drain_recurse(bs, false);
     aio_enable_external(bdrv_get_aio_context(bs));
 }
 
@@ -353,7 +372,7 @@ void bdrv_drain_all_begin(void)
             aio_context_acquire(aio_context);
             for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
                 if (aio_context == bdrv_get_aio_context(bs)) {
-                    waited |= bdrv_drain_recurse(bs);
+                    waited |= bdrv_drain_recurse(bs, true);
                 }
             }
             aio_context_release(aio_context);
@@ -374,6 +393,7 @@ void bdrv_drain_all_end(void)
         aio_context_acquire(aio_context);
         aio_enable_external(aio_context);
         bdrv_parent_drained_end(bs);
+        bdrv_drain_recurse(bs, false);
         aio_context_release(aio_context);
     }
 
diff --git a/block/qed.c b/block/qed.c
index 28e2ec89e8..821dcaa055 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -265,7 +265,7 @@ static bool qed_plug_allocating_write_reqs(BDRVQEDState *s)
     assert(!s->allocating_write_reqs_plugged);
     if (s->allocating_acb != NULL) {
         /* Another allocating write came concurrently.  This cannot happen
-         * from bdrv_qed_co_drain, but it can happen when the timer runs.
+         * from bdrv_qed_co_drain_begin, but it can happen when the timer runs.
          */
         qemu_co_mutex_unlock(&s->table_lock);
         return false;
@@ -358,7 +358,7 @@ static void bdrv_qed_attach_aio_context(BlockDriverState *bs,
     }
 }
 
-static void coroutine_fn bdrv_qed_co_drain(BlockDriverState *bs)
+static void coroutine_fn bdrv_qed_co_drain_begin(BlockDriverState *bs)
 {
     BDRVQEDState *s = bs->opaque;
 
@@ -1608,7 +1608,7 @@ static BlockDriver bdrv_qed = {
     .bdrv_check               = bdrv_qed_check,
     .bdrv_detach_aio_context  = bdrv_qed_detach_aio_context,
     .bdrv_attach_aio_context  = bdrv_qed_attach_aio_context,
-    .bdrv_co_drain            = bdrv_qed_co_drain,
+    .bdrv_co_drain_begin      = bdrv_qed_co_drain_begin,
 };
 
 static void bdrv_qed_init(void)
diff --git a/block/throttle.c b/block/throttle.c
index 5bca76300f..833175ac77 100644
--- a/block/throttle.c
+++ b/block/throttle.c
@@ -197,6 +197,21 @@ static bool throttle_recurse_is_first_non_filter(BlockDriverState *bs,
     return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
 }
 
+static void coroutine_fn throttle_co_drain_begin(BlockDriverState *bs)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+    if (atomic_fetch_inc(&tgm->io_limits_disabled) == 0) {
+        throttle_group_restart_tgm(tgm);
+    }
+}
+
+static void coroutine_fn throttle_co_drain_end(BlockDriverState *bs)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+    assert(tgm->io_limits_disabled);
+    atomic_dec(&tgm->io_limits_disabled);
+}
+
 static BlockDriver bdrv_throttle = {
     .format_name                        =   "throttle",
     .protocol_name                      =   "throttle",
@@ -226,6 +241,9 @@ static BlockDriver bdrv_throttle = {
     .bdrv_reopen_abort                  =   throttle_reopen_abort,
     .bdrv_co_get_block_status           =   bdrv_co_get_block_status_from_file,
 
+    .bdrv_co_drain_begin                =   throttle_co_drain_begin,
+    .bdrv_co_drain_end                  =   throttle_co_drain_end,
+
     .is_filter                          =   true,
 };
 
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 7e8a206239..885c08e989 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -354,10 +354,17 @@ struct BlockDriver {
     int (*bdrv_probe_geometry)(BlockDriverState *bs, HDGeometry *geo);
 
     /**
-     * Drain and stop any internal sources of requests in the driver, and
-     * remain so until next I/O callback (e.g. bdrv_co_writev) is called.
+     * bdrv_co_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_co_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.
      */
-    void coroutine_fn (*bdrv_co_drain)(BlockDriverState *bs);
+    void coroutine_fn (*bdrv_co_drain_begin)(BlockDriverState *bs);
+    void coroutine_fn (*bdrv_co_drain_end)(BlockDriverState *bs);
 
     void (*bdrv_add_child)(BlockDriverState *parent, BlockDriverState *child,
                            Error **errp);