[Qemu-devel] [PATCH 10/25] aio: add Win32 implementation

[Paolo Bonzini <pbonzini@redhat.com>]

The Win32 implementation will only accept EventNotifiers, thus a few
drivers are disabled under Windows.  EventNotifiers are a good match
for the GSource implementation, too, because the Win32 port of glib
allows to place their HANDLEs in a GPollFD.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Makefile.objs        |   6 +--
 aio.c => aio-posix.c |   0
 aio.c => aio-win32.c | 137 ++++++++++++++++-----------------------------------
 block/Makefile.objs  |   6 ++-
 main-loop.c          |   2 +-
 5 file modificati, 51 inserzioni(+), 100 rimozioni(-)
 copy aio.c => aio-posix.c (100%)
 rename aio.c => aio-win32.c (56%)

diff --git a/Makefile.objs b/Makefile.objs
index 6f7b40b..da744e1 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -42,12 +42,12 @@ coroutine-obj-$(CONFIG_WIN32) += coroutine-win32.o
 # block-obj-y is code used by both qemu system emulation and qemu-img
 
 block-obj-y = cutils.o iov.o cache-utils.o qemu-option.o module.o async.o
-block-obj-y += nbd.o block.o blockjob.o aio.o aes.o qemu-config.o
+block-obj-y += nbd.o block.o blockjob.o aes.o qemu-config.o
 block-obj-y += qemu-progress.o qemu-sockets.o uri.o
 block-obj-y += $(coroutine-obj-y) $(qobject-obj-y) $(version-obj-y)
 block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
-block-obj-$(CONFIG_POSIX) += event_notifier-posix.o
-block-obj-$(CONFIG_WIN32) += event_notifier-win32.o
+block-obj-$(CONFIG_POSIX) += event_notifier-posix.o aio-posix.o
+block-obj-$(CONFIG_WIN32) += event_notifier-win32.o aio-win32.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 block-obj-y += block/
 
diff --git a/aio.c b/aio-posix.c
similarity index 100%
copy from aio.c
copy to aio-posix.c
diff --git a/aio.c b/aio-win32.c
similarity index 56%
rename from aio.c
rename to aio-win32.c
index 4424722..9881fdb 100644
--- a/aio.c
+++ b/aio-win32.c
@@ -1,10 +1,12 @@
 /*
  * QEMU aio implementation
  *
- * Copyright IBM, Corp. 2008
+ * Copyright IBM Corp., 2008
+ * Copyright Red Hat Inc., 2012
  *
  * Authors:
  *  Anthony Liguori   <aliguori@us.ibm.com>
+ *  Paolo Bonzini     <pbonzini@redhat.com>
  *
  * This work is licensed under the terms of the GNU GPL, version 2.  See
  * the COPYING file in the top-level directory.
@@ -18,43 +20,30 @@
 #include "qemu-queue.h"
 #include "qemu_socket.h"
 
-struct AioHandler
-{
+struct AioHandler {
+    EventNotifier *e;
+    EventNotifierHandler *io_notify;
+    AioFlushEventNotifierHandler *io_flush;
     GPollFD pfd;
-    IOHandler *io_read;
-    IOHandler *io_write;
-    AioFlushHandler *io_flush;
     int deleted;
-    void *opaque;
     QLIST_ENTRY(AioHandler) node;
 };
 
-static AioHandler *find_aio_handler(AioContext *ctx, int fd)
+void aio_set_event_notifier(AioContext *ctx,
+                            EventNotifier *e,
+                            EventNotifierHandler *io_notify,
+                            AioFlushEventNotifierHandler *io_flush)
 {
     AioHandler *node;
 
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.fd == fd)
-            if (!node->deleted)
-                return node;
+        if (node->e == e && !node->deleted) {
+            break;
+        }
     }
 
-    return NULL;
-}
-
-void aio_set_fd_handler(AioContext *ctx,
-                        int fd,
-                        IOHandler *io_read,
-                        IOHandler *io_write,
-                        AioFlushHandler *io_flush,
-                        void *opaque)
-{
-    AioHandler *node;
-
-    node = find_aio_handler(ctx, fd);
-
     /* Are we deleting the fd handler? */
-    if (!io_read && !io_write) {
+    if (!io_notify) {
         if (node) {
             /* If the lock is held, just mark the node as deleted */
             if (ctx->walking_handlers) {
@@ -73,49 +62,23 @@ void aio_set_fd_handler(AioContext *ctx,
         if (node == NULL) {
             /* Alloc and insert if it's not already there */
             node = g_malloc0(sizeof(AioHandler));
-            node->pfd.fd = fd;
+            node->e = e;
+            node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
+            node->pfd.events = G_IO_IN;
             QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
         }
         /* Update handler with latest information */
-        node->io_read = io_read;
-        node->io_write = io_write;
+        node->io_notify = io_notify;
         node->io_flush = io_flush;
-        node->opaque = opaque;
-
-        node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP : 0);
-        node->pfd.events |= (io_write ? G_IO_OUT : 0);
     }
 }
 
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *notifier,
-                            EventNotifierHandler *io_read,
-                            AioFlushEventNotifierHandler *io_flush)
-{
-    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
-                       (IOHandler *)io_read, NULL,
-                       (AioFlushHandler *)io_flush, notifier);
-}
-
 bool aio_pending(AioContext *ctx)
 {
     AioHandler *node;
 
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        int revents;
-
-        /*
-         * FIXME: right now we cannot get G_IO_HUP and G_IO_ERR because
-         * main-loop.c is still select based (due to the slirp legacy).
-         * If main-loop.c ever switches to poll, G_IO_ERR should be
-         * tested too.  Dispatching G_IO_ERR to both handlers should be
-         * okay, since handlers need to be ready for spurious wakeups.
-         */
-        revents = node->pfd.revents & node->pfd.events;
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            return true;
-        }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
+        if (node->pfd.revents && node->io_notify) {
             return true;
         }
     }
@@ -125,12 +88,10 @@ bool aio_pending(AioContext *ctx)
 
 bool aio_poll(AioContext *ctx, bool blocking)
 {
-    static struct timeval tv0;
     AioHandler *node;
-    fd_set rdfds, wrfds;
-    int max_fd = -1;
-    int ret;
+    HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
     bool busy, progress;
+    int count;
 
     progress = false;
 
@@ -153,20 +114,12 @@ bool aio_poll(AioContext *ctx, bool blocking)
     node = QLIST_FIRST(&ctx->aio_handlers);
     while (node) {
         AioHandler *tmp;
-        int revents;
 
         ctx->walking_handlers++;
 
-        revents = node->pfd.revents & node->pfd.events;
-        node->pfd.revents = 0;
-
-        /* See comment in aio_pending.  */
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            node->io_read(node->opaque);
-            progress = true;
-        }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
-            node->io_write(node->opaque);
+        if (node->pfd.revents && node->io_notify) {
+            node->pfd.revents = 0;
+            node->io_notify(node->e);
             progress = true;
         }
 
@@ -187,29 +140,22 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
     ctx->walking_handlers++;
 
-    FD_ZERO(&rdfds);
-    FD_ZERO(&wrfds);
-
     /* 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->opaque) == 0) {
+            if (node->io_flush(node->e) == 0) {
                 continue;
             }
             busy = true;
         }
-        if (!node->deleted && node->io_read) {
-            FD_SET(node->pfd.fd, &rdfds);
-            max_fd = MAX(max_fd, node->pfd.fd + 1);
-        }
-        if (!node->deleted && node->io_write) {
-            FD_SET(node->pfd.fd, &wrfds);
-            max_fd = MAX(max_fd, node->pfd.fd + 1);
+        if (!node->deleted && node->io_notify) {
+            events[count++] = event_notifier_get_handle(node->e);
         }
     }
 
@@ -221,10 +167,17 @@ bool aio_poll(AioContext *ctx, bool blocking)
     }
 
     /* wait until next event */
-    ret = select(max_fd, &rdfds, &wrfds, NULL, blocking ? NULL : &tv0);
+    for (;;) {
+        int timeout = blocking ? INFINITE : 0;
+        int ret = WaitForMultipleObjects(count, events, FALSE, timeout);
+
+        /* if we have any signaled events, dispatch event */
+        if ((DWORD) (ret - WAIT_OBJECT_0) >= count) {
+            break;
+        }
+
+        blocking = false;
 
-    /* if we have any readable fds, dispatch event */
-    if (ret > 0) {
         /* we have to walk very carefully in case
          * qemu_aio_set_fd_handler is called while we're walking */
         node = QLIST_FIRST(&ctx->aio_handlers);
@@ -234,15 +187,9 @@ bool aio_poll(AioContext *ctx, bool blocking)
             ctx->walking_handlers++;
 
             if (!node->deleted &&
-                FD_ISSET(node->pfd.fd, &rdfds) &&
-                node->io_read) {
-                node->io_read(node->opaque);
-                progress = true;
-            }
-            if (!node->deleted &&
-                FD_ISSET(node->pfd.fd, &wrfds) &&
-                node->io_write) {
-                node->io_write(node->opaque);
+                event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
+                node->io_notify) {
+                node->io_notify(node->e);
                 progress = true;
             }
 
diff --git a/block/Makefile.objs b/block/Makefile.objs
index 554f429..684765b 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -2,13 +2,17 @@ block-obj-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat
 block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
-block-obj-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
+block-obj-y += parallels.o blkdebug.o blkverify.o
 block-obj-$(CONFIG_WIN32) += raw-win32.o
 block-obj-$(CONFIG_POSIX) += raw-posix.o
+
+ifeq ($(CONFIG_POSIX),y)
+block-obj-y += nbd.o sheepdog.o
 block-obj-$(CONFIG_LIBISCSI) += iscsi.o
 block-obj-$(CONFIG_CURL) += curl.o
 block-obj-$(CONFIG_RBD) += rbd.o
 block-obj-$(CONFIG_GLUSTERFS) += gluster.o
+endif
 
 common-obj-y += stream.o
 common-obj-y += commit.o
diff --git a/main-loop.c b/main-loop.c
index 67800fe..b290c79 100644
--- a/main-loop.c
+++ b/main-loop.c
@@ -534,6 +534,7 @@ bool qemu_aio_wait(void)
     return aio_poll(qemu_aio_context, true);
 }
 
+#ifdef CONFIG_POSIX
 void qemu_aio_set_fd_handler(int fd,
                              IOHandler *io_read,
                              IOHandler *io_write,
@@ -546,7 +547,6 @@ void qemu_aio_set_fd_handler(int fd,
     qemu_set_fd_handler2(fd, NULL, io_read, io_write, opaque);
 }
 
-#ifdef CONFIG_POSIX
 void qemu_aio_set_event_notifier(EventNotifier *notifier,
                                  EventNotifierHandler *io_read,
                                  AioFlushEventNotifierHandler *io_flush)
-- 
1.7.12.1