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

# gpg: Signature made Tue 28 Jun 2016 14:23:24 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:
  virtio-blk: add num-queues device property
  virtio-blk: dataplane multiqueue support
  virtio-blk: live migrate s->rq with multiqueue
  virtio-blk: associate request with a virtqueue
  virtio-blk: tell dataplane which vq to notify
  virtio-blk: multiqueue batch notify
  virtio-blk: add VirtIOBlockConf->num_queues
  dma-helpers: dma_blk_io() cancel support
  Revert "virtio: sync the dataplane vring state to the virtqueue before virtio_save"

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

6 files changed, 112 insertions, 46 deletions

diff --git a/dma-helpers.c b/dma-helpers.c
index b521d84ebd..9defc101b7 100644
--- a/dma-helpers.c
+++ b/dma-helpers.c
@@ -185,10 +185,17 @@ static void dma_aio_cancel(BlockAIOCB *acb)
     }
 }
 
+static AioContext *dma_get_aio_context(BlockAIOCB *acb)
+{
+    DMAAIOCB *dbs = container_of(acb, DMAAIOCB, common);
+
+    return dbs->ctx;
+}
 
 static const AIOCBInfo dma_aiocb_info = {
     .aiocb_size         = sizeof(DMAAIOCB),
     .cancel_async       = dma_aio_cancel,
+    .get_aio_context    = dma_get_aio_context,
 };
 
 BlockAIOCB *dma_blk_io(AioContext *ctx,
diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 2041b0400b..54b9ac1da6 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -31,11 +31,9 @@ struct VirtIOBlockDataPlane {
     bool stopping;
 
     VirtIOBlkConf *conf;
-
     VirtIODevice *vdev;
-    VirtQueue *vq;                  /* virtqueue vring */
-    EventNotifier *guest_notifier;  /* irq */
     QEMUBH *bh;                     /* bh for guest notification */
+    unsigned long *batch_notify_vqs;
 
     /* Note that these EventNotifiers are assigned by value.  This is
      * fine as long as you do not call event_notifier_cleanup on them
@@ -47,20 +45,36 @@ struct VirtIOBlockDataPlane {
 };
 
 /* Raise an interrupt to signal guest, if necessary */
-void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s)
+void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s, VirtQueue *vq)
 {
+    set_bit(virtio_get_queue_index(vq), s->batch_notify_vqs);
     qemu_bh_schedule(s->bh);
 }
 
 static void notify_guest_bh(void *opaque)
 {
     VirtIOBlockDataPlane *s = opaque;
+    unsigned nvqs = s->conf->num_queues;
+    unsigned long bitmap[BITS_TO_LONGS(nvqs)];
+    unsigned j;
 
-    if (!virtio_should_notify(s->vdev, s->vq)) {
-        return;
-    }
+    memcpy(bitmap, s->batch_notify_vqs, sizeof(bitmap));
+    memset(s->batch_notify_vqs, 0, sizeof(bitmap));
+
+    for (j = 0; j < nvqs; j += BITS_PER_LONG) {
+        unsigned long bits = bitmap[j];
 
-    event_notifier_set(s->guest_notifier);
+        while (bits != 0) {
+            unsigned i = j + ctzl(bits);
+            VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+            if (virtio_should_notify(s->vdev, vq)) {
+                event_notifier_set(virtio_queue_get_guest_notifier(vq));
+            }
+
+            bits &= bits - 1; /* clear right-most bit */
+        }
+    }
 }
 
 /* Context: QEMU global mutex held */
@@ -104,6 +118,7 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
     }
     s->ctx = iothread_get_aio_context(s->iothread);
     s->bh = aio_bh_new(s->ctx, notify_guest_bh, s);
+    s->batch_notify_vqs = bitmap_new(conf->num_queues);
 
     *dataplane = s;
 }
@@ -116,6 +131,7 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
     }
 
     virtio_blk_data_plane_stop(s);
+    g_free(s->batch_notify_vqs);
     qemu_bh_delete(s->bh);
     object_unref(OBJECT(s->iothread));
     g_free(s);
@@ -138,6 +154,8 @@ 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);
     VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
+    unsigned i;
+    unsigned nvqs = s->conf->num_queues;
     int r;
 
     if (vblk->dataplane_started || s->starting) {
@@ -145,22 +163,25 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
     }
 
     s->starting = true;
-    s->vq = virtio_get_queue(s->vdev, 0);
 
     /* Set up guest notifier (irq) */
-    r = k->set_guest_notifiers(qbus->parent, 1, true);
+    r = k->set_guest_notifiers(qbus->parent, nvqs, true);
     if (r != 0) {
         fprintf(stderr, "virtio-blk failed to set guest notifier (%d), "
                 "ensure -enable-kvm is set\n", r);
         goto fail_guest_notifiers;
     }
-    s->guest_notifier = virtio_queue_get_guest_notifier(s->vq);
 
     /* Set up virtqueue notify */
-    r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), 0, true);
-    if (r != 0) {
-        fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);
-        goto fail_host_notifier;
+    for (i = 0; i < nvqs; i++) {
+        r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, true);
+        if (r != 0) {
+            fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);
+            while (i--) {
+                virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
+            }
+            goto fail_guest_notifiers;
+        }
     }
 
     s->starting = false;
@@ -170,17 +191,23 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
     blk_set_aio_context(s->conf->conf.blk, s->ctx);
 
     /* Kick right away to begin processing requests already in vring */
-    event_notifier_set(virtio_queue_get_host_notifier(s->vq));
+    for (i = 0; i < nvqs; i++) {
+        VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+        event_notifier_set(virtio_queue_get_host_notifier(vq));
+    }
 
     /* Get this show started by hooking up our callbacks */
     aio_context_acquire(s->ctx);
-    virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx,
-                                               virtio_blk_data_plane_handle_output);
+    for (i = 0; i < nvqs; i++) {
+        VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+        virtio_queue_aio_set_host_notifier_handler(vq, s->ctx,
+                virtio_blk_data_plane_handle_output);
+    }
     aio_context_release(s->ctx);
     return;
 
-  fail_host_notifier:
-    k->set_guest_notifiers(qbus->parent, 1, false);
   fail_guest_notifiers:
     vblk->dataplane_disabled = true;
     s->starting = false;
@@ -193,6 +220,8 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
+    unsigned i;
+    unsigned nvqs = s->conf->num_queues;
 
     if (!vblk->dataplane_started || s->stopping) {
         return;
@@ -210,17 +239,23 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
     aio_context_acquire(s->ctx);
 
     /* Stop notifications for new requests from guest */
-    virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx, NULL);
+    for (i = 0; i < nvqs; i++) {
+        VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+        virtio_queue_aio_set_host_notifier_handler(vq, s->ctx, NULL);
+    }
 
     /* Drain and switch bs back to the QEMU main loop */
     blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context());
 
     aio_context_release(s->ctx);
 
-    virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), 0, false);
+    for (i = 0; i < nvqs; i++) {
+        virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
+    }
 
     /* Clean up guest notifier (irq) */
-    k->set_guest_notifiers(qbus->parent, 1, false);
+    k->set_guest_notifiers(qbus->parent, nvqs, false);
 
     vblk->dataplane_started = false;
     s->stopping = false;
diff --git a/hw/block/dataplane/virtio-blk.h b/hw/block/dataplane/virtio-blk.h
index 0714c11a2b..b1f0b95b32 100644
--- a/hw/block/dataplane/virtio-blk.h
+++ b/hw/block/dataplane/virtio-blk.h
@@ -26,6 +26,6 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_drain(VirtIOBlockDataPlane *s);
-void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s, VirtQueue *vq);
 
 #endif /* HW_DATAPLANE_VIRTIO_BLK_H */
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 284e64667c..fb43bbaa46 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -29,9 +29,11 @@
 #include "hw/virtio/virtio-bus.h"
 #include "hw/virtio/virtio-access.h"
 
-void virtio_blk_init_request(VirtIOBlock *s, VirtIOBlockReq *req)
+void virtio_blk_init_request(VirtIOBlock *s, VirtQueue *vq,
+                             VirtIOBlockReq *req)
 {
     req->dev = s;
+    req->vq = vq;
     req->qiov.size = 0;
     req->in_len = 0;
     req->next = NULL;
@@ -53,11 +55,11 @@ static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
     trace_virtio_blk_req_complete(req, status);
 
     stb_p(&req->in->status, status);
-    virtqueue_push(s->vq, &req->elem, req->in_len);
+    virtqueue_push(req->vq, &req->elem, req->in_len);
     if (s->dataplane_started && !s->dataplane_disabled) {
-        virtio_blk_data_plane_notify(s->dataplane);
+        virtio_blk_data_plane_notify(s->dataplane, req->vq);
     } else {
-        virtio_notify(vdev, s->vq);
+        virtio_notify(vdev, req->vq);
     }
 }
 
@@ -187,12 +189,12 @@ out:
 
 #endif
 
-static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s)
+static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s, VirtQueue *vq)
 {
-    VirtIOBlockReq *req = virtqueue_pop(s->vq, sizeof(VirtIOBlockReq));
+    VirtIOBlockReq *req = virtqueue_pop(vq, sizeof(VirtIOBlockReq));
 
     if (req) {
-        virtio_blk_init_request(s, req);
+        virtio_blk_init_request(s, vq, req);
     }
     return req;
 }
@@ -583,7 +585,7 @@ void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq)
 
     blk_io_plug(s->blk);
 
-    while ((req = virtio_blk_get_request(s))) {
+    while ((req = virtio_blk_get_request(s, vq))) {
         virtio_blk_handle_request(req, &mrb);
     }
 
@@ -708,6 +710,7 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
     blkcfg.physical_block_exp = get_physical_block_exp(conf);
     blkcfg.alignment_offset = 0;
     blkcfg.wce = blk_enable_write_cache(s->blk);
+    virtio_stw_p(vdev, &blkcfg.num_queues, s->conf.num_queues);
     memcpy(config, &blkcfg, sizeof(struct virtio_blk_config));
 }
 
@@ -751,6 +754,9 @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
     if (blk_is_read_only(s->blk)) {
         virtio_add_feature(&features, VIRTIO_BLK_F_RO);
     }
+    if (s->conf.num_queues > 1) {
+        virtio_add_feature(&features, VIRTIO_BLK_F_MQ);
+    }
 
     return features;
 }
@@ -795,11 +801,6 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
 static void virtio_blk_save(QEMUFile *f, void *opaque)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
-    VirtIOBlock *s = VIRTIO_BLK(vdev);
-
-    if (s->dataplane) {
-        virtio_blk_data_plane_stop(s->dataplane);
-    }
 
     virtio_save(vdev, f);
 }
@@ -811,6 +812,11 @@ static void virtio_blk_save_device(VirtIODevice *vdev, QEMUFile *f)
 
     while (req) {
         qemu_put_sbyte(f, 1);
+
+        if (s->conf.num_queues > 1) {
+            qemu_put_be32(f, virtio_get_queue_index(req->vq));
+        }
+
         qemu_put_virtqueue_element(f, &req->elem);
         req = req->next;
     }
@@ -834,9 +840,22 @@ static int virtio_blk_load_device(VirtIODevice *vdev, QEMUFile *f,
     VirtIOBlock *s = VIRTIO_BLK(vdev);
 
     while (qemu_get_sbyte(f)) {
+        unsigned nvqs = s->conf.num_queues;
+        unsigned vq_idx = 0;
         VirtIOBlockReq *req;
+
+        if (nvqs > 1) {
+            vq_idx = qemu_get_be32(f);
+
+            if (vq_idx >= nvqs) {
+                error_report("Invalid virtqueue index in request list: %#x",
+                             vq_idx);
+                return -EINVAL;
+            }
+        }
+
         req = qemu_get_virtqueue_element(f, sizeof(VirtIOBlockReq));
-        virtio_blk_init_request(s, req);
+        virtio_blk_init_request(s, virtio_get_queue(vdev, vq_idx), req);
         req->next = s->rq;
         s->rq = req;
     }
@@ -862,6 +881,7 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     VirtIOBlkConf *conf = &s->conf;
     Error *err = NULL;
     static int virtio_blk_id;
+    unsigned i;
 
     if (!conf->conf.blk) {
         error_setg(errp, "drive property not set");
@@ -871,6 +891,10 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
         error_setg(errp, "Device needs media, but drive is empty");
         return;
     }
+    if (!conf->num_queues) {
+        error_setg(errp, "num-queues property must be larger than 0");
+        return;
+    }
 
     blkconf_serial(&conf->conf, &conf->serial);
     s->original_wce = blk_enable_write_cache(conf->conf.blk);
@@ -888,7 +912,9 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     s->rq = NULL;
     s->sector_mask = (s->conf.conf.logical_block_size / BDRV_SECTOR_SIZE) - 1;
 
-    s->vq = virtio_add_queue(vdev, 128, virtio_blk_handle_output);
+    for (i = 0; i < conf->num_queues; i++) {
+        virtio_add_queue(vdev, 128, virtio_blk_handle_output);
+    }
     virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
     if (err != NULL) {
         error_propagate(errp, err);
@@ -941,6 +967,7 @@ static Property virtio_blk_properties[] = {
 #endif
     DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0,
                     true),
+    DEFINE_PROP_UINT16("num-queues", VirtIOBlock, conf.num_queues, 1),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 71d09d3ef3..e8179d6616 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -666,11 +666,6 @@ static void virtio_scsi_reset(VirtIODevice *vdev)
 static void virtio_scsi_save(QEMUFile *f, void *opaque)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
-    VirtIOSCSI *s = VIRTIO_SCSI(vdev);
-
-    if (s->dataplane_started) {
-        virtio_scsi_dataplane_stop(s);
-    }
     virtio_save(vdev, f);
 }
 
diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h
index 8f2b056515..e9bf463f53 100644
--- a/include/hw/virtio/virtio-blk.h
+++ b/include/hw/virtio/virtio-blk.h
@@ -38,6 +38,7 @@ struct VirtIOBlkConf
     uint32_t scsi;
     uint32_t config_wce;
     uint32_t request_merging;
+    uint16_t num_queues;
 };
 
 struct VirtIOBlockDataPlane;
@@ -46,7 +47,6 @@ struct VirtIOBlockReq;
 typedef struct VirtIOBlock {
     VirtIODevice parent_obj;
     BlockBackend *blk;
-    VirtQueue *vq;
     void *rq;
     QEMUBH *bh;
     VirtIOBlkConf conf;
@@ -62,6 +62,7 @@ typedef struct VirtIOBlockReq {
     VirtQueueElement elem;
     int64_t sector_num;
     VirtIOBlock *dev;
+    VirtQueue *vq;
     struct virtio_blk_inhdr *in;
     struct virtio_blk_outhdr out;
     QEMUIOVector qiov;
@@ -79,7 +80,8 @@ typedef struct MultiReqBuffer {
     bool is_write;
 } MultiReqBuffer;
 
-void virtio_blk_init_request(VirtIOBlock *s, VirtIOBlockReq *req);
+void virtio_blk_init_request(VirtIOBlock *s, VirtQueue *vq,
+                             VirtIOBlockReq *req);
 void virtio_blk_free_request(VirtIOBlockReq *req);
 
 void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb);