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

Block pull request

# gpg: Signature made Fri 06 Jun 2014 17:08:50 BST using RSA key ID 81AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"

* remotes/stefanha/tags/block-pull-request: (42 commits)
  qapi: Extract qapi/block.json definitions
  qapi: Extract qapi/block-core.json definitions
  qapi: create two block related json modules
  qapi: Extract qapi/common.json definitions
  sheepdog: reload only header in a case of live snapshot
  sheepdog: fix vdi object update after live snapshot
  rbd: Fix leaks in rbd_start_aio() error path
  qemu-img: Document check exit codes
  block: fix wrong order in live block migration setup
  blockdev: acquire AioContext in block_set_io_throttle
  throttle: add detach/attach test case
  throttle: add throttle_detach/attach_aio_context()
  dataplane: Support VIRTIO_BLK_T_SCSI_CMD
  virtio-blk: Factor out virtio_blk_handle_scsi_req from virtio_blk_handle_scsi
  virtio-blk: Allow config-wce in dataplane
  block: Move declaration of bdrv_get_aio_context to block.h
  raw-posix: drop raw_get_aio_fd() since it is no longer used
  dataplane: implement async flush
  dataplane: delete IOQueue since it is no longer used
  dataplane: use the QEMU block layer for I/O
  ...

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

5 files changed, 149 insertions, 366 deletions

diff --git a/hw/block/dataplane/Makefile.objs b/hw/block/dataplane/Makefile.objs
index 9da2eb82ba..e786f66421 100644
--- a/hw/block/dataplane/Makefile.objs
+++ b/hw/block/dataplane/Makefile.objs
@@ -1 +1 @@
-obj-y += ioq.o virtio-blk.o
+obj-y += virtio-blk.o
diff --git a/hw/block/dataplane/ioq.c b/hw/block/dataplane/ioq.c
deleted file mode 100644
index f709f87ed6..0000000000
--- a/hw/block/dataplane/ioq.c
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
- * Linux AIO request queue
- *
- * Copyright 2012 IBM, Corp.
- * Copyright 2012 Red Hat, Inc. and/or its affiliates
- *
- * Authors:
- *   Stefan Hajnoczi <stefanha@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#include "ioq.h"
-
-void ioq_init(IOQueue *ioq, int fd, unsigned int max_reqs)
-{
-    int rc;
-
-    ioq->fd = fd;
-    ioq->max_reqs = max_reqs;
-
-    memset(&ioq->io_ctx, 0, sizeof ioq->io_ctx);
-    rc = io_setup(max_reqs, &ioq->io_ctx);
-    if (rc != 0) {
-        fprintf(stderr, "ioq io_setup failed %d\n", rc);
-        exit(1);
-    }
-
-    rc = event_notifier_init(&ioq->io_notifier, 0);
-    if (rc != 0) {
-        fprintf(stderr, "ioq io event notifier creation failed %d\n", rc);
-        exit(1);
-    }
-
-    ioq->freelist = g_malloc0(sizeof ioq->freelist[0] * max_reqs);
-    ioq->freelist_idx = 0;
-
-    ioq->queue = g_malloc0(sizeof ioq->queue[0] * max_reqs);
-    ioq->queue_idx = 0;
-}
-
-void ioq_cleanup(IOQueue *ioq)
-{
-    g_free(ioq->freelist);
-    g_free(ioq->queue);
-
-    event_notifier_cleanup(&ioq->io_notifier);
-    io_destroy(ioq->io_ctx);
-}
-
-EventNotifier *ioq_get_notifier(IOQueue *ioq)
-{
-    return &ioq->io_notifier;
-}
-
-struct iocb *ioq_get_iocb(IOQueue *ioq)
-{
-    /* Underflow cannot happen since ioq is sized for max_reqs */
-    assert(ioq->freelist_idx != 0);
-
-    struct iocb *iocb = ioq->freelist[--ioq->freelist_idx];
-    ioq->queue[ioq->queue_idx++] = iocb;
-    return iocb;
-}
-
-void ioq_put_iocb(IOQueue *ioq, struct iocb *iocb)
-{
-    /* Overflow cannot happen since ioq is sized for max_reqs */
-    assert(ioq->freelist_idx != ioq->max_reqs);
-
-    ioq->freelist[ioq->freelist_idx++] = iocb;
-}
-
-struct iocb *ioq_rdwr(IOQueue *ioq, bool read, struct iovec *iov,
-                      unsigned int count, long long offset)
-{
-    struct iocb *iocb = ioq_get_iocb(ioq);
-
-    if (read) {
-        io_prep_preadv(iocb, ioq->fd, iov, count, offset);
-    } else {
-        io_prep_pwritev(iocb, ioq->fd, iov, count, offset);
-    }
-    io_set_eventfd(iocb, event_notifier_get_fd(&ioq->io_notifier));
-    return iocb;
-}
-
-int ioq_submit(IOQueue *ioq)
-{
-    int rc = io_submit(ioq->io_ctx, ioq->queue_idx, ioq->queue);
-    ioq->queue_idx = 0; /* reset */
-    return rc;
-}
-
-int ioq_run_completion(IOQueue *ioq, IOQueueCompletion *completion,
-                       void *opaque)
-{
-    struct io_event events[ioq->max_reqs];
-    int nevents, i;
-
-    do {
-        nevents = io_getevents(ioq->io_ctx, 0, ioq->max_reqs, events, NULL);
-    } while (nevents < 0 && errno == EINTR);
-    if (nevents < 0) {
-        return nevents;
-    }
-
-    for (i = 0; i < nevents; i++) {
-        ssize_t ret = ((uint64_t)events[i].res2 << 32) | events[i].res;
-
-        completion(events[i].obj, ret, opaque);
-        ioq_put_iocb(ioq, events[i].obj);
-    }
-    return nevents;
-}
diff --git a/hw/block/dataplane/ioq.h b/hw/block/dataplane/ioq.h
deleted file mode 100644
index b49b5de7f4..0000000000
--- a/hw/block/dataplane/ioq.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
- * Linux AIO request queue
- *
- * Copyright 2012 IBM, Corp.
- * Copyright 2012 Red Hat, Inc. and/or its affiliates
- *
- * Authors:
- *   Stefan Hajnoczi <stefanha@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#ifndef IOQ_H
-#define IOQ_H
-
-#include <libaio.h>
-#include "qemu/event_notifier.h"
-
-typedef struct {
-    int fd;                         /* file descriptor */
-    unsigned int max_reqs;          /* max length of freelist and queue */
-
-    io_context_t io_ctx;            /* Linux AIO context */
-    EventNotifier io_notifier;      /* Linux AIO eventfd */
-
-    /* Requests can complete in any order so a free list is necessary to manage
-     * available iocbs.
-     */
-    struct iocb **freelist;         /* free iocbs */
-    unsigned int freelist_idx;
-
-    /* Multiple requests are queued up before submitting them all in one go */
-    struct iocb **queue;            /* queued iocbs */
-    unsigned int queue_idx;
-} IOQueue;
-
-void ioq_init(IOQueue *ioq, int fd, unsigned int max_reqs);
-void ioq_cleanup(IOQueue *ioq);
-EventNotifier *ioq_get_notifier(IOQueue *ioq);
-struct iocb *ioq_get_iocb(IOQueue *ioq);
-void ioq_put_iocb(IOQueue *ioq, struct iocb *iocb);
-struct iocb *ioq_rdwr(IOQueue *ioq, bool read, struct iovec *iov,
-                      unsigned int count, long long offset);
-int ioq_submit(IOQueue *ioq);
-
-static inline unsigned int ioq_num_queued(IOQueue *ioq)
-{
-    return ioq->queue_idx;
-}
-
-typedef void IOQueueCompletion(struct iocb *iocb, ssize_t ret, void *opaque);
-int ioq_run_completion(IOQueue *ioq, IOQueueCompletion *completion,
-                       void *opaque);
-
-#endif /* IOQ_H */
diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index e49c2536b1..c10b7b70fb 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -17,7 +17,6 @@
 #include "qemu/thread.h"
 #include "qemu/error-report.h"
 #include "hw/virtio/dataplane/vring.h"
-#include "ioq.h"
 #include "block/block.h"
 #include "hw/virtio/virtio-blk.h"
 #include "virtio-blk.h"
@@ -25,20 +24,14 @@
 #include "hw/virtio/virtio-bus.h"
 #include "qom/object_interfaces.h"
 
-enum {
-    SEG_MAX = 126,                  /* maximum number of I/O segments */
-    VRING_MAX = SEG_MAX + 2,        /* maximum number of vring descriptors */
-    REQ_MAX = VRING_MAX,            /* maximum number of requests in the vring,
-                                     * is VRING_MAX / 2 with traditional and
-                                     * VRING_MAX with indirect descriptors */
-};
-
 typedef struct {
-    struct iocb iocb;               /* Linux AIO control block */
+    VirtIOBlockDataPlane *s;
     QEMUIOVector *inhdr;            /* iovecs for virtio_blk_inhdr */
     VirtQueueElement *elem;         /* saved data from the virtqueue */
-    struct iovec *bounce_iov;       /* used if guest buffers are unaligned */
-    QEMUIOVector *read_qiov;        /* for read completion /w bounce buffer */
+    QEMUIOVector qiov;              /* original request iovecs */
+    struct iovec bounce_iov;        /* used if guest buffers are unaligned */
+    QEMUIOVector bounce_qiov;       /* bounce buffer iovecs */
+    bool read;                      /* read or write? */
 } VirtIOBlockRequest;
 
 struct VirtIOBlockDataPlane {
@@ -47,7 +40,6 @@ struct VirtIOBlockDataPlane {
     bool stopping;
 
     VirtIOBlkConf *blk;
-    int fd;                         /* image file descriptor */
 
     VirtIODevice *vdev;
     Vring vring;                    /* virtqueue vring */
@@ -61,16 +53,8 @@ struct VirtIOBlockDataPlane {
     IOThread *iothread;
     IOThread internal_iothread_obj;
     AioContext *ctx;
-    EventNotifier io_notifier;      /* Linux AIO completion */
     EventNotifier host_notifier;    /* doorbell */
 
-    IOQueue ioqueue;                /* Linux AIO queue (should really be per
-                                       IOThread) */
-    VirtIOBlockRequest requests[REQ_MAX]; /* pool of requests, managed by the
-                                             queue */
-
-    unsigned int num_reqs;
-
     /* Operation blocker on BDS */
     Error *blocker;
 };
@@ -85,33 +69,28 @@ static void notify_guest(VirtIOBlockDataPlane *s)
     event_notifier_set(s->guest_notifier);
 }
 
-static void complete_request(struct iocb *iocb, ssize_t ret, void *opaque)
+static void complete_rdwr(void *opaque, int ret)
 {
-    VirtIOBlockDataPlane *s = opaque;
-    VirtIOBlockRequest *req = container_of(iocb, VirtIOBlockRequest, iocb);
+    VirtIOBlockRequest *req = opaque;
     struct virtio_blk_inhdr hdr;
     int len;
 
-    if (likely(ret >= 0)) {
+    if (likely(ret == 0)) {
         hdr.status = VIRTIO_BLK_S_OK;
-        len = ret;
+        len = req->qiov.size;
     } else {
         hdr.status = VIRTIO_BLK_S_IOERR;
         len = 0;
     }
 
-    trace_virtio_blk_data_plane_complete_request(s, req->elem->index, ret);
+    trace_virtio_blk_data_plane_complete_request(req->s, req->elem->index, ret);
 
-    if (req->read_qiov) {
-        assert(req->bounce_iov);
-        qemu_iovec_from_buf(req->read_qiov, 0, req->bounce_iov->iov_base, len);
-        qemu_iovec_destroy(req->read_qiov);
-        g_slice_free(QEMUIOVector, req->read_qiov);
+    if (req->read && req->bounce_iov.iov_base) {
+        qemu_iovec_from_buf(&req->qiov, 0, req->bounce_iov.iov_base, len);
     }
 
-    if (req->bounce_iov) {
-        qemu_vfree(req->bounce_iov->iov_base);
-        g_slice_free(struct iovec, req->bounce_iov);
+    if (req->bounce_iov.iov_base) {
+        qemu_vfree(req->bounce_iov.iov_base);
     }
 
     qemu_iovec_from_buf(req->inhdr, 0, &hdr, sizeof(hdr));
@@ -122,9 +101,9 @@ static void complete_request(struct iocb *iocb, ssize_t ret, void *opaque)
      * written to, but for virtio-blk it seems to be the number of bytes
      * transferred plus the status bytes.
      */
-    vring_push(&s->vring, req->elem, len + sizeof(hdr));
-    req->elem = NULL;
-    s->num_reqs--;
+    vring_push(&req->s->vring, req->elem, len + sizeof(hdr));
+    notify_guest(req->s);
+    g_slice_free(VirtIOBlockRequest, req);
 }
 
 static void complete_request_early(VirtIOBlockDataPlane *s, VirtQueueElement *elem,
@@ -155,51 +134,87 @@ static void do_get_id_cmd(VirtIOBlockDataPlane *s,
     complete_request_early(s, elem, inhdr, VIRTIO_BLK_S_OK);
 }
 
-static int do_rdwr_cmd(VirtIOBlockDataPlane *s, bool read,
-                       struct iovec *iov, unsigned iov_cnt,
-                       long long offset, VirtQueueElement *elem,
-                       QEMUIOVector *inhdr)
+static void do_rdwr_cmd(VirtIOBlockDataPlane *s, bool read,
+                        struct iovec *iov, unsigned iov_cnt,
+                        int64_t sector_num, VirtQueueElement *elem,
+                        QEMUIOVector *inhdr)
 {
-    struct iocb *iocb;
-    QEMUIOVector qiov;
-    struct iovec *bounce_iov = NULL;
-    QEMUIOVector *read_qiov = NULL;
-
-    qemu_iovec_init_external(&qiov, iov, iov_cnt);
-    if (!bdrv_qiov_is_aligned(s->blk->conf.bs, &qiov)) {
-        void *bounce_buffer = qemu_blockalign(s->blk->conf.bs, qiov.size);
-
-        if (read) {
-            /* Need to copy back from bounce buffer on completion */
-            read_qiov = g_slice_new(QEMUIOVector);
-            qemu_iovec_init(read_qiov, iov_cnt);
-            qemu_iovec_concat_iov(read_qiov, iov, iov_cnt, 0, qiov.size);
-        } else {
-            qemu_iovec_to_buf(&qiov, 0, bounce_buffer, qiov.size);
+    VirtIOBlockRequest *req = g_slice_new0(VirtIOBlockRequest);
+    QEMUIOVector *qiov;
+    int nb_sectors;
+
+    /* Fill in virtio block metadata needed for completion */
+    req->s = s;
+    req->elem = elem;
+    req->inhdr = inhdr;
+    req->read = read;
+    qemu_iovec_init_external(&req->qiov, iov, iov_cnt);
+
+    qiov = &req->qiov;
+
+    if (!bdrv_qiov_is_aligned(s->blk->conf.bs, qiov)) {
+        void *bounce_buffer = qemu_blockalign(s->blk->conf.bs, qiov->size);
+
+        /* Populate bounce buffer with data for writes */
+        if (!read) {
+            qemu_iovec_to_buf(qiov, 0, bounce_buffer, qiov->size);
         }
 
         /* Redirect I/O to aligned bounce buffer */
-        bounce_iov = g_slice_new(struct iovec);
-        bounce_iov->iov_base = bounce_buffer;
-        bounce_iov->iov_len = qiov.size;
-        iov = bounce_iov;
-        iov_cnt = 1;
+        req->bounce_iov.iov_base = bounce_buffer;
+        req->bounce_iov.iov_len = qiov->size;
+        qemu_iovec_init_external(&req->bounce_qiov, &req->bounce_iov, 1);
+        qiov = &req->bounce_qiov;
     }
 
-    iocb = ioq_rdwr(&s->ioqueue, read, iov, iov_cnt, offset);
+    nb_sectors = qiov->size / BDRV_SECTOR_SIZE;
 
-    /* Fill in virtio block metadata needed for completion */
-    VirtIOBlockRequest *req = container_of(iocb, VirtIOBlockRequest, iocb);
+    if (read) {
+        bdrv_aio_readv(s->blk->conf.bs, sector_num, qiov, nb_sectors,
+                       complete_rdwr, req);
+    } else {
+        bdrv_aio_writev(s->blk->conf.bs, sector_num, qiov, nb_sectors,
+                        complete_rdwr, req);
+    }
+}
+
+static void complete_flush(void *opaque, int ret)
+{
+    VirtIOBlockRequest *req = opaque;
+    unsigned char status;
+
+    if (ret == 0) {
+        status = VIRTIO_BLK_S_OK;
+    } else {
+        status = VIRTIO_BLK_S_IOERR;
+    }
+
+    complete_request_early(req->s, req->elem, req->inhdr, status);
+    g_slice_free(VirtIOBlockRequest, req);
+}
+
+static void do_flush_cmd(VirtIOBlockDataPlane *s, VirtQueueElement *elem,
+                         QEMUIOVector *inhdr)
+{
+    VirtIOBlockRequest *req = g_slice_new(VirtIOBlockRequest);
+    req->s = s;
     req->elem = elem;
     req->inhdr = inhdr;
-    req->bounce_iov = bounce_iov;
-    req->read_qiov = read_qiov;
-    return 0;
+
+    bdrv_aio_flush(s->blk->conf.bs, complete_flush, req);
+}
+
+static void do_scsi_cmd(VirtIOBlockDataPlane *s, VirtQueueElement *elem,
+                        QEMUIOVector *inhdr)
+{
+    int status;
+
+    status = virtio_blk_handle_scsi_req(VIRTIO_BLK(s->vdev), elem);
+    complete_request_early(s, elem, inhdr, status);
 }
 
-static int process_request(IOQueue *ioq, VirtQueueElement *elem)
+static int process_request(VirtIOBlockDataPlane *s, VirtQueueElement *elem)
 {
-    VirtIOBlockDataPlane *s = container_of(ioq, VirtIOBlockDataPlane, ioqueue);
     struct iovec *iov = elem->out_sg;
     struct iovec *in_iov = elem->in_sg;
     unsigned out_num = elem->out_num;
@@ -234,25 +249,23 @@ static int process_request(IOQueue *ioq, VirtQueueElement *elem)
 
     switch (outhdr.type) {
     case VIRTIO_BLK_T_IN:
-        do_rdwr_cmd(s, true, in_iov, in_num, outhdr.sector * 512, elem, inhdr);
+        do_rdwr_cmd(s, true, in_iov, in_num,
+                    outhdr.sector * 512 / BDRV_SECTOR_SIZE,
+                    elem, inhdr);
         return 0;
 
     case VIRTIO_BLK_T_OUT:
-        do_rdwr_cmd(s, false, iov, out_num, outhdr.sector * 512, elem, inhdr);
+        do_rdwr_cmd(s, false, iov, out_num,
+                    outhdr.sector * 512 / BDRV_SECTOR_SIZE,
+                    elem, inhdr);
         return 0;
 
     case VIRTIO_BLK_T_SCSI_CMD:
-        /* TODO support SCSI commands */
-        complete_request_early(s, elem, inhdr, VIRTIO_BLK_S_UNSUPP);
+        do_scsi_cmd(s, elem, inhdr);
         return 0;
 
     case VIRTIO_BLK_T_FLUSH:
-        /* TODO fdsync not supported by Linux AIO, do it synchronously here! */
-        if (qemu_fdatasync(s->fd) < 0) {
-            complete_request_early(s, elem, inhdr, VIRTIO_BLK_S_IOERR);
-        } else {
-            complete_request_early(s, elem, inhdr, VIRTIO_BLK_S_OK);
-        }
+        do_flush_cmd(s, elem, inhdr);
         return 0;
 
     case VIRTIO_BLK_T_GET_ID:
@@ -274,7 +287,6 @@ static void handle_notify(EventNotifier *e)
 
     VirtQueueElement *elem;
     int ret;
-    unsigned int num_queued;
 
     event_notifier_test_and_clear(&s->host_notifier);
     for (;;) {
@@ -291,7 +303,7 @@ static void handle_notify(EventNotifier *e)
             trace_virtio_blk_data_plane_process_request(s, elem->out_num,
                                                         elem->in_num, elem->index);
 
-            if (process_request(&s->ioqueue, elem) < 0) {
+            if (process_request(s, elem) < 0) {
                 vring_set_broken(&s->vring);
                 vring_free_element(elem);
                 ret = -EFAULT;
@@ -306,44 +318,10 @@ static void handle_notify(EventNotifier *e)
             if (vring_enable_notification(s->vdev, &s->vring)) {
                 break;
             }
-        } else { /* ret == -ENOBUFS or fatal error, iovecs[] is depleted */
-            /* Since there are no iovecs[] left, stop processing for now.  Do
-             * not re-enable guest->host notifies since the I/O completion
-             * handler knows to check for more vring descriptors anyway.
-             */
+        } else { /* fatal error */
             break;
         }
     }
-
-    num_queued = ioq_num_queued(&s->ioqueue);
-    if (num_queued > 0) {
-        s->num_reqs += num_queued;
-
-        int rc = ioq_submit(&s->ioqueue);
-        if (unlikely(rc < 0)) {
-            fprintf(stderr, "ioq_submit failed %d\n", rc);
-            exit(1);
-        }
-    }
-}
-
-static void handle_io(EventNotifier *e)
-{
-    VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
-                                           io_notifier);
-
-    event_notifier_test_and_clear(&s->io_notifier);
-    if (ioq_run_completion(&s->ioqueue, complete_request, s) > 0) {
-        notify_guest(s);
-    }
-
-    /* If there were more requests than iovecs, the vring will not be empty yet
-     * so check again.  There should now be enough resources to process more
-     * requests.
-     */
-    if (unlikely(vring_more_avail(&s->vring))) {
-        handle_notify(&s->host_notifier);
-    }
 }
 
 /* Context: QEMU global mutex held */
@@ -352,7 +330,6 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
                                   Error **errp)
 {
     VirtIOBlockDataPlane *s;
-    int fd;
     Error *local_err = NULL;
 
     *dataplane = NULL;
@@ -361,18 +338,6 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
         return;
     }
 
-    if (blk->scsi) {
-        error_setg(errp,
-                   "device is incompatible with x-data-plane, use scsi=off");
-        return;
-    }
-
-    if (blk->config_wce) {
-        error_setg(errp, "device is incompatible with x-data-plane, "
-                         "use config-wce=off");
-        return;
-    }
-
     /* If dataplane is (re-)enabled while the guest is running there could be
      * block jobs that can conflict.
      */
@@ -383,16 +348,8 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
         return;
     }
 
-    fd = raw_get_aio_fd(blk->conf.bs);
-    if (fd < 0) {
-        error_setg(errp, "drive is incompatible with x-data-plane, "
-                         "use format=raw,cache=none,aio=native");
-        return;
-    }
-
     s = g_new0(VirtIOBlockDataPlane, 1);
     s->vdev = vdev;
-    s->fd = fd;
     s->blk = blk;
 
     if (blk->iothread) {
@@ -437,7 +394,6 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     VirtQueue *vq;
-    int i;
 
     if (s->started) {
         return;
@@ -470,24 +426,18 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
     }
     s->host_notifier = *virtio_queue_get_host_notifier(vq);
 
-    /* Set up ioqueue */
-    ioq_init(&s->ioqueue, s->fd, REQ_MAX);
-    for (i = 0; i < ARRAY_SIZE(s->requests); i++) {
-        ioq_put_iocb(&s->ioqueue, &s->requests[i].iocb);
-    }
-    s->io_notifier = *ioq_get_notifier(&s->ioqueue);
-
     s->starting = false;
     s->started = true;
     trace_virtio_blk_data_plane_start(s);
 
+    bdrv_set_aio_context(s->blk->conf.bs, s->ctx);
+
     /* Kick right away to begin processing requests already in vring */
     event_notifier_set(virtio_queue_get_host_notifier(vq));
 
     /* Get this show started by hooking up our callbacks */
     aio_context_acquire(s->ctx);
     aio_set_event_notifier(s->ctx, &s->host_notifier, handle_notify);
-    aio_set_event_notifier(s->ctx, &s->io_notifier, handle_io);
     aio_context_release(s->ctx);
 }
 
@@ -507,13 +457,8 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
     /* Stop notifications for new requests from guest */
     aio_set_event_notifier(s->ctx, &s->host_notifier, NULL);
 
-    /* Complete pending requests */
-    while (s->num_reqs > 0) {
-        aio_poll(s->ctx, true);
-    }
-
-    /* Stop ioq callbacks (there are no pending requests left) */
-    aio_set_event_notifier(s->ctx, &s->io_notifier, NULL);
+    /* Drain and switch bs back to the QEMU main loop */
+    bdrv_set_aio_context(s->blk->conf.bs, qemu_get_aio_context());
 
     aio_context_release(s->ctx);
 
@@ -522,7 +467,6 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
      */
     vring_teardown(&s->vring, s->vdev, 0);
 
-    ioq_cleanup(&s->ioqueue);
     k->set_host_notifier(qbus->parent, 0, false);
 
     /* Clean up guest notifier (irq) */
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index b1fc1de0dc..85aa8715ba 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -33,7 +33,6 @@ typedef struct VirtIOBlockReq
     VirtQueueElement elem;
     struct virtio_blk_inhdr *in;
     struct virtio_blk_outhdr *out;
-    struct virtio_scsi_inhdr *scsi;
     QEMUIOVector qiov;
     struct VirtIOBlockReq *next;
     BlockAcctCookie acct;
@@ -125,13 +124,15 @@ static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s)
     return req;
 }
 
-static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
+int virtio_blk_handle_scsi_req(VirtIOBlock *blk,
+                               VirtQueueElement *elem)
 {
+    int status = VIRTIO_BLK_S_OK;
+    struct virtio_scsi_inhdr *scsi = NULL;
 #ifdef __linux__
-    int ret;
     int i;
+    struct sg_io_hdr hdr;
 #endif
-    int status = VIRTIO_BLK_S_OK;
 
     /*
      * We require at least one output segment each for the virtio_blk_outhdr
@@ -140,19 +141,18 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
      * We also at least require the virtio_blk_inhdr, the virtio_scsi_inhdr
      * and the sense buffer pointer in the input segments.
      */
-    if (req->elem.out_num < 2 || req->elem.in_num < 3) {
-        virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
-        g_free(req);
-        return;
+    if (elem->out_num < 2 || elem->in_num < 3) {
+        status = VIRTIO_BLK_S_IOERR;
+        goto fail;
     }
 
     /*
      * The scsi inhdr is placed in the second-to-last input segment, just
      * before the regular inhdr.
      */
-    req->scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;
+    scsi = (void *)elem->in_sg[elem->in_num - 2].iov_base;
 
-    if (!req->dev->blk.scsi) {
+    if (!blk->blk.scsi) {
         status = VIRTIO_BLK_S_UNSUPP;
         goto fail;
     }
@@ -160,43 +160,42 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
     /*
      * No support for bidirection commands yet.
      */
-    if (req->elem.out_num > 2 && req->elem.in_num > 3) {
+    if (elem->out_num > 2 && elem->in_num > 3) {
         status = VIRTIO_BLK_S_UNSUPP;
         goto fail;
     }
 
 #ifdef __linux__
-    struct sg_io_hdr hdr;
     memset(&hdr, 0, sizeof(struct sg_io_hdr));
     hdr.interface_id = 'S';
-    hdr.cmd_len = req->elem.out_sg[1].iov_len;
-    hdr.cmdp = req->elem.out_sg[1].iov_base;
+    hdr.cmd_len = elem->out_sg[1].iov_len;
+    hdr.cmdp = elem->out_sg[1].iov_base;
     hdr.dxfer_len = 0;
 
-    if (req->elem.out_num > 2) {
+    if (elem->out_num > 2) {
         /*
          * If there are more than the minimally required 2 output segments
          * there is write payload starting from the third iovec.
          */
         hdr.dxfer_direction = SG_DXFER_TO_DEV;
-        hdr.iovec_count = req->elem.out_num - 2;
+        hdr.iovec_count = elem->out_num - 2;
 
         for (i = 0; i < hdr.iovec_count; i++)
-            hdr.dxfer_len += req->elem.out_sg[i + 2].iov_len;
+            hdr.dxfer_len += elem->out_sg[i + 2].iov_len;
 
-        hdr.dxferp = req->elem.out_sg + 2;
+        hdr.dxferp = elem->out_sg + 2;
 
-    } else if (req->elem.in_num > 3) {
+    } else if (elem->in_num > 3) {
         /*
          * If we have more than 3 input segments the guest wants to actually
          * read data.
          */
         hdr.dxfer_direction = SG_DXFER_FROM_DEV;
-        hdr.iovec_count = req->elem.in_num - 3;
+        hdr.iovec_count = elem->in_num - 3;
         for (i = 0; i < hdr.iovec_count; i++)
-            hdr.dxfer_len += req->elem.in_sg[i].iov_len;
+            hdr.dxfer_len += elem->in_sg[i].iov_len;
 
-        hdr.dxferp = req->elem.in_sg;
+        hdr.dxferp = elem->in_sg;
     } else {
         /*
          * Some SCSI commands don't actually transfer any data.
@@ -204,11 +203,11 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
         hdr.dxfer_direction = SG_DXFER_NONE;
     }
 
-    hdr.sbp = req->elem.in_sg[req->elem.in_num - 3].iov_base;
-    hdr.mx_sb_len = req->elem.in_sg[req->elem.in_num - 3].iov_len;
+    hdr.sbp = elem->in_sg[elem->in_num - 3].iov_base;
+    hdr.mx_sb_len = elem->in_sg[elem->in_num - 3].iov_len;
 
-    ret = bdrv_ioctl(req->dev->bs, SG_IO, &hdr);
-    if (ret) {
+    status = bdrv_ioctl(blk->bs, SG_IO, &hdr);
+    if (status) {
         status = VIRTIO_BLK_S_UNSUPP;
         goto fail;
     }
@@ -224,23 +223,31 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
         hdr.status = CHECK_CONDITION;
     }
 
-    stl_p(&req->scsi->errors,
+    stl_p(&scsi->errors,
           hdr.status | (hdr.msg_status << 8) |
           (hdr.host_status << 16) | (hdr.driver_status << 24));
-    stl_p(&req->scsi->residual, hdr.resid);
-    stl_p(&req->scsi->sense_len, hdr.sb_len_wr);
-    stl_p(&req->scsi->data_len, hdr.dxfer_len);
+    stl_p(&scsi->residual, hdr.resid);
+    stl_p(&scsi->sense_len, hdr.sb_len_wr);
+    stl_p(&scsi->data_len, hdr.dxfer_len);
 
-    virtio_blk_req_complete(req, status);
-    g_free(req);
-    return;
+    return status;
 #else
     abort();
 #endif
 
 fail:
     /* Just put anything nonzero so that the ioctl fails in the guest.  */
-    stl_p(&req->scsi->errors, 255);
+    if (scsi) {
+        stl_p(&scsi->errors, 255);
+    }
+    return status;
+}
+
+static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
+{
+    int status;
+
+    status = virtio_blk_handle_scsi_req(req->dev, &req->elem);
     virtio_blk_req_complete(req, status);
     g_free(req);
 }
@@ -523,7 +530,10 @@ static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
     struct virtio_blk_config blkcfg;
 
     memcpy(&blkcfg, config, sizeof(blkcfg));
+
+    aio_context_acquire(bdrv_get_aio_context(s->bs));
     bdrv_set_enable_write_cache(s->bs, blkcfg.wce != 0);
+    aio_context_release(bdrv_get_aio_context(s->bs));
 }
 
 static uint32_t virtio_blk_get_features(VirtIODevice *vdev, uint32_t features)
@@ -582,7 +592,10 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
      * s->bs would erroneously be placed in writethrough mode.
      */
     if (!(features & (1 << VIRTIO_BLK_F_CONFIG_WCE))) {
-        bdrv_set_enable_write_cache(s->bs, !!(features & (1 << VIRTIO_BLK_F_WCE)));
+        aio_context_acquire(bdrv_get_aio_context(s->bs));
+        bdrv_set_enable_write_cache(s->bs,
+                                    !!(features & (1 << VIRTIO_BLK_F_WCE)));
+        aio_context_release(bdrv_get_aio_context(s->bs));
     }
 }