virtio-blk: add iothread-vq-mapping parameter

Add the iothread-vq-mapping parameter to assign virtqueues to IOThreads.
Store the vq:AioContext mapping in the new struct
VirtIOBlockDataPlane->vq_aio_context[] field and refactor the code to
use the per-vq AioContext instead of the BlockDriverState's AioContext.

Reimplement --device virtio-blk-pci,iothread= and non-IOThread mode by
assigning all virtqueues to the IOThread and main loop's AioContext in
vq_aio_context[], respectively.

The comment in struct VirtIOBlockDataPlane about EventNotifiers is
stale. Remove it.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20231220134755.814917-5-stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

hw/block/dataplane/virtio-blk.c

@@ -32,13 +32,11 @@ struct VirtIOBlockDataPlane {
     VirtIOBlkConf *conf;
     VirtIODevice *vdev;
 
-    /* Note that these EventNotifiers are assigned by value.  This is
+    /*
-     * fine as long as you do not call event_notifier_cleanup on them
+     * The AioContext for each virtqueue. The BlockDriverState will use the
-     * (because you don't own the file descriptor or handle; you just
+     * first element as its AioContext.
-     * use it).
      */
-    IOThread *iothread;
+    AioContext **vq_aio_context;
-    AioContext *ctx;
 };
 
 /* Raise an interrupt to signal guest, if necessary */
@@ -47,6 +45,45 @@ void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s, VirtQueue *vq)
     virtio_notify_irqfd(s->vdev, vq);
 }
 
+/* Generate vq:AioContext mappings from a validated iothread-vq-mapping list */
+static void
+apply_vq_mapping(IOThreadVirtQueueMappingList *iothread_vq_mapping_list,
+                 AioContext **vq_aio_context, uint16_t num_queues)
+{
+    IOThreadVirtQueueMappingList *node;
+    size_t num_iothreads = 0;
+    size_t cur_iothread = 0;
+
+    for (node = iothread_vq_mapping_list; node; node = node->next) {
+        num_iothreads++;
+    }
+
+    for (node = iothread_vq_mapping_list; node; node = node->next) {
+        IOThread *iothread = iothread_by_id(node->value->iothread);
+        AioContext *ctx = iothread_get_aio_context(iothread);
+
+        /* Released in virtio_blk_data_plane_destroy() */
+        object_ref(OBJECT(iothread));
+
+        if (node->value->vqs) {
+            uint16List *vq;
+
+            /* Explicit vq:IOThread assignment */
+            for (vq = node->value->vqs; vq; vq = vq->next) {
+                vq_aio_context[vq->value] = ctx;
+            }
+        } else {
+            /* Round-robin vq:IOThread assignment */
+            for (unsigned i = cur_iothread; i < num_queues;
+                 i += num_iothreads) {
+                vq_aio_context[i] = ctx;
+            }
+        }
+
+        cur_iothread++;
+    }
+}
+
 /* Context: QEMU global mutex held */
 bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
                                   VirtIOBlockDataPlane **dataplane,
@@ -58,7 +95,7 @@ bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
 
     *dataplane = NULL;
 
-    if (conf->iothread) {
+    if (conf->iothread || conf->iothread_vq_mapping_list) {
         if (!k->set_guest_notifiers || !k->ioeventfd_assign) {
             error_setg(errp,
                        "device is incompatible with iothread "
@@ -86,13 +123,24 @@ bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
     s = g_new0(VirtIOBlockDataPlane, 1);
     s->vdev = vdev;
     s->conf = conf;
+    s->vq_aio_context = g_new(AioContext *, conf->num_queues);
 
-    if (conf->iothread) {
+    if (conf->iothread_vq_mapping_list) {
-        s->iothread = conf->iothread;
+        apply_vq_mapping(conf->iothread_vq_mapping_list, s->vq_aio_context,
-        object_ref(OBJECT(s->iothread));
+                         conf->num_queues);
-        s->ctx = iothread_get_aio_context(s->iothread);
+    } else if (conf->iothread) {
+        AioContext *ctx = iothread_get_aio_context(conf->iothread);
+        for (unsigned i = 0; i < conf->num_queues; i++) {
+            s->vq_aio_context[i] = ctx;
+        }
+
+        /* Released in virtio_blk_data_plane_destroy() */
+        object_ref(OBJECT(conf->iothread));
     } else {
-        s->ctx = qemu_get_aio_context();
+        AioContext *ctx = qemu_get_aio_context();
+        for (unsigned i = 0; i < conf->num_queues; i++) {
+            s->vq_aio_context[i] = ctx;
+        }
     }
 
     *dataplane = s;
@@ -104,6 +152,7 @@ bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
 void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
 {
     VirtIOBlock *vblk;
+    VirtIOBlkConf *conf = s->conf;
 
     if (!s) {
         return;
@@ -111,9 +160,21 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
 
     vblk = VIRTIO_BLK(s->vdev);
     assert(!vblk->dataplane_started);
-    if (s->iothread) {
+
-        object_unref(OBJECT(s->iothread));
+    if (conf->iothread_vq_mapping_list) {
+        IOThreadVirtQueueMappingList *node;
+
+        for (node = conf->iothread_vq_mapping_list; node; node = node->next) {
+            IOThread *iothread = iothread_by_id(node->value->iothread);
+            object_unref(OBJECT(iothread));
+        }
     }
+
+    if (conf->iothread) {
+        object_unref(OBJECT(conf->iothread));
+    }
+
+    g_free(s->vq_aio_context);
     g_free(s);
 }
 
@@ -177,19 +238,13 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
 
     trace_virtio_blk_data_plane_start(s);
 
-    r = blk_set_aio_context(s->conf->conf.blk, s->ctx, &local_err);
+    r = blk_set_aio_context(s->conf->conf.blk, s->vq_aio_context[0],
+                            &local_err);
     if (r < 0) {
         error_report_err(local_err);
         goto fail_aio_context;
     }
 
-    /* Kick right away to begin processing requests already in vring */
-    for (i = 0; i < nvqs; i++) {
-        VirtQueue *vq = virtio_get_queue(s->vdev, i);
-
-        event_notifier_set(virtio_queue_get_host_notifier(vq));
-    }
-
     /*
      * These fields must be visible to the IOThread when it processes the
      * virtqueue, otherwise it will think dataplane has not started yet.
@@ -206,8 +261,12 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
     if (!blk_in_drain(s->conf->conf.blk)) {
         for (i = 0; i < nvqs; i++) {
             VirtQueue *vq = virtio_get_queue(s->vdev, i);
+            AioContext *ctx = s->vq_aio_context[i];
 
-            virtio_queue_aio_attach_host_notifier(vq, s->ctx);
+            /* Kick right away to begin processing requests already in vring */
+            event_notifier_set(virtio_queue_get_host_notifier(vq));
+
+            virtio_queue_aio_attach_host_notifier(vq, ctx);
         }
     }
     return 0;
@@ -236,23 +295,18 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
  *
  * Context: BH in IOThread
  */
-static void virtio_blk_data_plane_stop_bh(void *opaque)
+static void virtio_blk_data_plane_stop_vq_bh(void *opaque)
 {
-    VirtIOBlockDataPlane *s = opaque;
+    VirtQueue *vq = opaque;
-    unsigned i;
+    EventNotifier *host_notifier = virtio_queue_get_host_notifier(vq);
 
-    for (i = 0; i < s->conf->num_queues; i++) {
+    virtio_queue_aio_detach_host_notifier(vq, qemu_get_current_aio_context());
-        VirtQueue *vq = virtio_get_queue(s->vdev, i);
-        EventNotifier *host_notifier = virtio_queue_get_host_notifier(vq);
 
-        virtio_queue_aio_detach_host_notifier(vq, s->ctx);
+    /*
-
+     * Test and clear notifier after disabling event, in case poll callback
-        /*
+     * didn't have time to run.
-         * Test and clear notifier after disabling event, in case poll callback
+     */
-         * didn't have time to run.
+    virtio_queue_host_notifier_read(host_notifier);
-         */
-        virtio_queue_host_notifier_read(host_notifier);
-    }
 }
 
 /* Context: QEMU global mutex held */
@@ -279,7 +333,12 @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
     trace_virtio_blk_data_plane_stop(s);
 
     if (!blk_in_drain(s->conf->conf.blk)) {
-        aio_wait_bh_oneshot(s->ctx, virtio_blk_data_plane_stop_bh, s);
+        for (i = 0; i < nvqs; i++) {
+            VirtQueue *vq = virtio_get_queue(s->vdev, i);
+            AioContext *ctx = s->vq_aio_context[i];
+
+            aio_wait_bh_oneshot(ctx, virtio_blk_data_plane_stop_vq_bh, vq);
+        }
     }
 
     /*
@@ -322,3 +381,23 @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
 
     s->stopping = false;
 }
+
+void virtio_blk_data_plane_detach(VirtIOBlockDataPlane *s)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(s->vdev);
+
+    for (uint16_t i = 0; i < s->conf->num_queues; i++) {
+        VirtQueue *vq = virtio_get_queue(vdev, i);
+        virtio_queue_aio_detach_host_notifier(vq, s->vq_aio_context[i]);
+    }
+}
+
+void virtio_blk_data_plane_attach(VirtIOBlockDataPlane *s)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(s->vdev);
+
+    for (uint16_t i = 0; i < s->conf->num_queues; i++) {
+        VirtQueue *vq = virtio_get_queue(vdev, i);
+        virtio_queue_aio_attach_host_notifier(vq, s->vq_aio_context[i]);
+    }
+}

hw/block/dataplane/virtio-blk.h

@@ -28,4 +28,7 @@ void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s, VirtQueue *vq);
 int virtio_blk_data_plane_start(VirtIODevice *vdev);
 void virtio_blk_data_plane_stop(VirtIODevice *vdev);
 
+void virtio_blk_data_plane_detach(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_attach(VirtIOBlockDataPlane *s);
+
 #endif /* HW_DATAPLANE_VIRTIO_BLK_H */

hw/block/virtio-blk.c

@@ -1151,6 +1151,7 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
             return;
         }
     }
+
     virtio_blk_handle_vq(s, vq);
 }
 
@@ -1463,6 +1464,68 @@ static int virtio_blk_load_device(VirtIODevice *vdev, QEMUFile *f,
     return 0;
 }
 
+static bool
+validate_iothread_vq_mapping_list(IOThreadVirtQueueMappingList *list,
+        uint16_t num_queues, Error **errp)
+{
+    g_autofree unsigned long *vqs = bitmap_new(num_queues);
+    g_autoptr(GHashTable) iothreads =
+        g_hash_table_new(g_str_hash, g_str_equal);
+
+    for (IOThreadVirtQueueMappingList *node = list; node; node = node->next) {
+        const char *name = node->value->iothread;
+        uint16List *vq;
+
+        if (!iothread_by_id(name)) {
+            error_setg(errp, "IOThread \"%s\" object does not exist", name);
+            return false;
+        }
+
+        if (!g_hash_table_add(iothreads, (gpointer)name)) {
+            error_setg(errp,
+                    "duplicate IOThread name \"%s\" in iothread-vq-mapping",
+                    name);
+            return false;
+        }
+
+        if (node != list) {
+            if (!!node->value->vqs != !!list->value->vqs) {
+                error_setg(errp, "either all items in iothread-vq-mapping "
+                                 "must have vqs or none of them must have it");
+                return false;
+            }
+        }
+
+        for (vq = node->value->vqs; vq; vq = vq->next) {
+            if (vq->value >= num_queues) {
+                error_setg(errp, "vq index %u for IOThread \"%s\" must be "
+                        "less than num_queues %u in iothread-vq-mapping",
+                        vq->value, name, num_queues);
+                return false;
+            }
+
+            if (test_and_set_bit(vq->value, vqs)) {
+                error_setg(errp, "cannot assign vq %u to IOThread \"%s\" "
+                        "because it is already assigned", vq->value, name);
+                return false;
+            }
+        }
+    }
+
+    if (list->value->vqs) {
+        for (uint16_t i = 0; i < num_queues; i++) {
+            if (!test_bit(i, vqs)) {
+                error_setg(errp,
+                        "missing vq %u IOThread assignment in iothread-vq-mapping",
+                        i);
+                return false;
+            }
+        }
+    }
+
+    return true;
+}
+
 static void virtio_resize_cb(void *opaque)
 {
     VirtIODevice *vdev = opaque;
@@ -1487,34 +1550,24 @@ static void virtio_blk_resize(void *opaque)
 static void virtio_blk_drained_begin(void *opaque)
 {
     VirtIOBlock *s = opaque;
-    VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
-    AioContext *ctx = blk_get_aio_context(s->conf.conf.blk);
 
     if (!s->dataplane || !s->dataplane_started) {
         return;
     }
 
-    for (uint16_t i = 0; i < s->conf.num_queues; i++) {
+    virtio_blk_data_plane_detach(s->dataplane);
-        VirtQueue *vq = virtio_get_queue(vdev, i);
-        virtio_queue_aio_detach_host_notifier(vq, ctx);
-    }
 }
 
 /* Resume virtqueue ioeventfd processing after drain */
 static void virtio_blk_drained_end(void *opaque)
 {
     VirtIOBlock *s = opaque;
-    VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
-    AioContext *ctx = blk_get_aio_context(s->conf.conf.blk);
 
     if (!s->dataplane || !s->dataplane_started) {
         return;
     }
 
-    for (uint16_t i = 0; i < s->conf.num_queues; i++) {
+    virtio_blk_data_plane_attach(s->dataplane);
-        VirtQueue *vq = virtio_get_queue(vdev, i);
-        virtio_queue_aio_attach_host_notifier(vq, ctx);
-    }
 }
 
 static const BlockDevOps virtio_block_ops = {
@@ -1600,6 +1653,19 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    if (conf->iothread_vq_mapping_list) {
+        if (conf->iothread) {
+            error_setg(errp, "iothread and iothread-vq-mapping properties "
+                             "cannot be set at the same time");
+            return;
+        }
+
+        if (!validate_iothread_vq_mapping_list(conf->iothread_vq_mapping_list,
+                                               conf->num_queues, errp)) {
+            return;
+        }
+    }
+
     s->config_size = virtio_get_config_size(&virtio_blk_cfg_size_params,
                                             s->host_features);
     virtio_init(vdev, VIRTIO_ID_BLOCK, s->config_size);
@@ -1702,6 +1768,8 @@ static Property virtio_blk_properties[] = {
     DEFINE_PROP_BOOL("seg-max-adjust", VirtIOBlock, conf.seg_max_adjust, true),
     DEFINE_PROP_LINK("iothread", VirtIOBlock, conf.iothread, TYPE_IOTHREAD,
                      IOThread *),
+    DEFINE_PROP_IOTHREAD_VQ_MAPPING_LIST("iothread-vq-mapping", VirtIOBlock,
+                                         conf.iothread_vq_mapping_list),
     DEFINE_PROP_BIT64("discard", VirtIOBlock, host_features,
                       VIRTIO_BLK_F_DISCARD, true),
     DEFINE_PROP_BOOL("report-discard-granularity", VirtIOBlock,

include/hw/virtio/virtio-blk.h

@@ -21,6 +21,7 @@
 #include "sysemu/block-backend.h"
 #include "sysemu/block-ram-registrar.h"
 #include "qom/object.h"
+#include "qapi/qapi-types-virtio.h"
 
 #define TYPE_VIRTIO_BLK "virtio-blk-device"
 OBJECT_DECLARE_SIMPLE_TYPE(VirtIOBlock, VIRTIO_BLK)
@@ -37,6 +38,7 @@ struct VirtIOBlkConf
 {
     BlockConf conf;
     IOThread *iothread;
+    IOThreadVirtQueueMappingList *iothread_vq_mapping_list;
     char *serial;
     uint32_t request_merging;
     uint16_t num_queues;