aio: stop using .io_flush()

Now that aio_poll() users check their termination condition themselves,
it is no longer necessary to call .io_flush() handlers.

The behavior of aio_poll() changes as follows:

1. .io_flush() is no longer invoked and file descriptors are *always*
monitored.  Previously returning 0 from .io_flush() would skip this file
descriptor.

Due to this change it is essential to check that requests are pending
before calling qemu_aio_wait().  Failure to do so means we block, for
example, waiting for an idle iSCSI socket to become readable when there
are no requests.  Currently all qemu_aio_wait()/aio_poll() callers check
before calling.

2. aio_poll() now returns true if progress was made (BH or fd handlers
executed) and false otherwise.  Previously it would return true whenever
'busy', which means that .io_flush() returned true.  The 'busy' concept
no longer exists so just progress is returned.

Due to this change we need to update tests/test-aio.c which asserts
aio_poll() return values.  Note that QEMU doesn't actually rely on these
return values so only tests/test-aio.c cares.

Note that ctx->notifier, the EventNotifier fd used for aio_notify(), is
now handled as a special case.  This is a little ugly but maintains
aio_poll() semantics, i.e. aio_notify() does not count as 'progress' and
aio_poll() avoids blocking when the user has not set any fd handlers yet.

Patches after this remove .io_flush() handler code until we can finally
drop the io_flush arguments to aio_set_fd_handler() and friends.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 14 insertions, 20 deletions

diff --git a/aio-win32.c b/aio-win32.c
index 38723bf1d3..4309c161ff 100644
--- a/aio-win32.c
+++ b/aio-win32.c
@@ -23,7 +23,6 @@
 struct AioHandler {
     EventNotifier *e;
     EventNotifierHandler *io_notify;
-    AioFlushEventNotifierHandler *io_flush;
     GPollFD pfd;
     int deleted;
     QLIST_ENTRY(AioHandler) node;
@@ -73,7 +72,6 @@ void aio_set_event_notifier(AioContext *ctx,
         }
         /* Update handler with latest information */
         node->io_notify = io_notify;
-        node->io_flush = io_flush;
     }
 
     aio_notify(ctx);
@@ -96,7 +94,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
     HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool busy, progress;
+    bool progress;
     int count;
 
     progress = false;
@@ -126,7 +124,11 @@ bool aio_poll(AioContext *ctx, bool blocking)
         if (node->pfd.revents && node->io_notify) {
             node->pfd.revents = 0;
             node->io_notify(node->e);
-            progress = true;
+
+            /* aio_notify() does not count as progress */
+            if (node->opaque != &ctx->notifier) {
+                progress = true;
+            }
         }
 
         tmp = node;
@@ -147,19 +149,8 @@ bool aio_poll(AioContext *ctx, bool blocking)
     ctx->walking_handlers++;
 
     /* fill fd sets */
-    busy = false;
     count = 0;
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        /* If there aren't pending AIO operations, don't invoke callbacks.
-         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
-         * wait indefinitely.
-         */
-        if (!node->deleted && node->io_flush) {
-            if (node->io_flush(node->e) == 0) {
-                continue;
-            }
-            busy = true;
-        }
         if (!node->deleted && node->io_notify) {
             events[count++] = event_notifier_get_handle(node->e);
         }
@@ -167,8 +158,8 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
     ctx->walking_handlers--;
 
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
+    /* early return if we only have the aio_notify() fd */
+    if (count == 1) {
         return progress;
     }
 
@@ -196,7 +187,11 @@ bool aio_poll(AioContext *ctx, bool blocking)
                 event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
                 node->io_notify) {
                 node->io_notify(node->e);
-                progress = true;
+
+                /* aio_notify() does not count as progress */
+                if (node->opaque != &ctx->notifier) {
+                    progress = true;
+                }
             }
 
             tmp = node;
@@ -214,6 +209,5 @@ bool aio_poll(AioContext *ctx, bool blocking)
         events[ret - WAIT_OBJECT_0] = events[--count];
     }
 
-    assert(progress || busy);
-    return true;
+    return progress;
 }