linux-aio: implement io plug, unplug and flush io queue

This patch implements .bdrv_io_plug, .bdrv_io_unplug and
.bdrv_flush_io_queue callbacks for linux-aio Block Drivers,
so that submitting I/O as a batch can be supported on linux-aio.

[Unprocessed requests are completed with -EIO instead of a bogus ret
value.
--Stefan]

Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

3 files changed, 141 insertions, 2 deletions

diff --git a/block/linux-aio.c b/block/linux-aio.c
index f0a2c087b2..48673690ac 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -25,6 +25,8 @@
  */
 #define MAX_EVENTS 128
 
+#define MAX_QUEUED_IO  128
+
 struct qemu_laiocb {
     BlockDriverAIOCB common;
     struct qemu_laio_state *ctx;
@@ -36,9 +38,19 @@ struct qemu_laiocb {
     QLIST_ENTRY(qemu_laiocb) node;
 };
 
+typedef struct {
+    struct iocb *iocbs[MAX_QUEUED_IO];
+    int plugged;
+    unsigned int size;
+    unsigned int idx;
+} LaioQueue;
+
 struct qemu_laio_state {
     io_context_t ctx;
     EventNotifier e;
+
+    /* io queue for submit at batch */
+    LaioQueue io_q;
 };
 
 static inline ssize_t io_event_ret(struct io_event *ev)
@@ -135,6 +147,79 @@ static const AIOCBInfo laio_aiocb_info = {
     .cancel             = laio_cancel,
 };
 
+static void ioq_init(LaioQueue *io_q)
+{
+    io_q->size = MAX_QUEUED_IO;
+    io_q->idx = 0;
+    io_q->plugged = 0;
+}
+
+static int ioq_submit(struct qemu_laio_state *s)
+{
+    int ret, i = 0;
+    int len = s->io_q.idx;
+
+    do {
+        ret = io_submit(s->ctx, len, s->io_q.iocbs);
+    } while (i++ < 3 && ret == -EAGAIN);
+
+    /* empty io queue */
+    s->io_q.idx = 0;
+
+    if (ret < 0) {
+        i = 0;
+    } else {
+        i = ret;
+    }
+
+    for (; i < len; i++) {
+        struct qemu_laiocb *laiocb =
+            container_of(s->io_q.iocbs[i], struct qemu_laiocb, iocb);
+
+        laiocb->ret = (ret < 0) ? ret : -EIO;
+        qemu_laio_process_completion(s, laiocb);
+    }
+    return ret;
+}
+
+static void ioq_enqueue(struct qemu_laio_state *s, struct iocb *iocb)
+{
+    unsigned int idx = s->io_q.idx;
+
+    s->io_q.iocbs[idx++] = iocb;
+    s->io_q.idx = idx;
+
+    /* submit immediately if queue is full */
+    if (idx == s->io_q.size) {
+        ioq_submit(s);
+    }
+}
+
+void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
+{
+    struct qemu_laio_state *s = aio_ctx;
+
+    s->io_q.plugged++;
+}
+
+int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
+{
+    struct qemu_laio_state *s = aio_ctx;
+    int ret = 0;
+
+    assert(s->io_q.plugged > 0 || !unplug);
+
+    if (unplug && --s->io_q.plugged > 0) {
+        return 0;
+    }
+
+    if (s->io_q.idx > 0) {
+        ret = ioq_submit(s);
+    }
+
+    return ret;
+}
+
 BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque, int type)
@@ -168,8 +253,13 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
     }
     io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
 
-    if (io_submit(s->ctx, 1, &iocbs) < 0)
-        goto out_free_aiocb;
+    if (!s->io_q.plugged) {
+        if (io_submit(s->ctx, 1, &iocbs) < 0) {
+            goto out_free_aiocb;
+        }
+    } else {
+        ioq_enqueue(s, iocbs);
+    }
     return &laiocb->common;
 
 out_free_aiocb:
@@ -204,6 +294,8 @@ void *laio_init(void)
         goto out_close_efd;
     }
 
+    ioq_init(&s->io_q);
+
     return s;
 
 out_close_efd:
diff --git a/block/raw-aio.h b/block/raw-aio.h
index 8cf084eeb5..e18c97509a 100644
--- a/block/raw-aio.h
+++ b/block/raw-aio.h
@@ -40,6 +40,8 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
         BlockDriverCompletionFunc *cb, void *opaque, int type);
 void laio_detach_aio_context(void *s, AioContext *old_context);
 void laio_attach_aio_context(void *s, AioContext *new_context);
+void laio_io_plug(BlockDriverState *bs, void *aio_ctx);
+int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug);
 #endif
 
 #ifdef _WIN32
diff --git a/block/raw-posix.c b/block/raw-posix.c
index fa005b38b7..a857def671 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -1057,6 +1057,36 @@ static BlockDriverAIOCB *raw_aio_submit(BlockDriverState *bs,
                        cb, opaque, type);
 }
 
+static void raw_aio_plug(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+    BDRVRawState *s = bs->opaque;
+    if (s->use_aio) {
+        laio_io_plug(bs, s->aio_ctx);
+    }
+#endif
+}
+
+static void raw_aio_unplug(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+    BDRVRawState *s = bs->opaque;
+    if (s->use_aio) {
+        laio_io_unplug(bs, s->aio_ctx, true);
+    }
+#endif
+}
+
+static void raw_aio_flush_io_queue(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+    BDRVRawState *s = bs->opaque;
+    if (s->use_aio) {
+        laio_io_unplug(bs, s->aio_ctx, false);
+    }
+#endif
+}
+
 static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque)
@@ -1544,6 +1574,9 @@ static BlockDriver bdrv_file = {
     .bdrv_aio_flush = raw_aio_flush,
     .bdrv_aio_discard = raw_aio_discard,
     .bdrv_refresh_limits = raw_refresh_limits,
+    .bdrv_io_plug = raw_aio_plug,
+    .bdrv_io_unplug = raw_aio_unplug,
+    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate = raw_truncate,
     .bdrv_getlength = raw_getlength,
@@ -1943,6 +1976,9 @@ static BlockDriver bdrv_host_device = {
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_aio_discard   = hdev_aio_discard,
     .bdrv_refresh_limits = raw_refresh_limits,
+    .bdrv_io_plug = raw_aio_plug,
+    .bdrv_io_unplug = raw_aio_unplug,
+    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength	= raw_getlength,
@@ -2088,6 +2124,9 @@ static BlockDriver bdrv_host_floppy = {
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_refresh_limits = raw_refresh_limits,
+    .bdrv_io_plug = raw_aio_plug,
+    .bdrv_io_unplug = raw_aio_unplug,
+    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength      = raw_getlength,
@@ -2216,6 +2255,9 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_refresh_limits = raw_refresh_limits,
+    .bdrv_io_plug = raw_aio_plug,
+    .bdrv_io_unplug = raw_aio_unplug,
+    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength      = raw_getlength,
@@ -2350,6 +2392,9 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_refresh_limits = raw_refresh_limits,
+    .bdrv_io_plug = raw_aio_plug,
+    .bdrv_io_unplug = raw_aio_unplug,
+    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength      = raw_getlength,