[PATCH v4 0/4] add generic vDPA device support

[PATCH v4 0/4] add generic vDPA device support

[Longpeng(Mike) via]

From: Longpeng <longpeng2@huawei.com>

Hi guys,

With the generic vDPA device, QEMU won't need to touch the device
types any more, such like vfio.

We can use the generic vDPA device as follow:
  -device vhost-vdpa-device-pci,vhostdev=/dev/vhost-vdpa-X

I've done some simple tests on Huawei's offloading card (net, 0.95).

Changes v3 -> v4:
  v3: https://www.mail-archive.com/qemu-devel@nongnu.org/msg877015.html
  - reorganize the series [Stefano]
  - fix some typos [Stefano]
  - fix logical error in vhost_vdpa_device_realize [Stefano]

Changes v2 -> v3
  Patch 4 & 5:
    - only call vdpa ioctls in vdpa-dev.c [Stefano, Longpeng]
    - s/VQS_NUM/VQS_COUNT  [Stefano]
    - check both vdpa_dev_fd and vdpa_dev [Stefano]
  Patch 6:
    - move all steps into vhost_vdpa_device_unrealize. [Stefano]

Changes RFC -> v2
  Patch 1:
    - rename 'pdev_id' to 'trans_devid'  [Michael]
    - only use transitional device id for the devices
      listed in the spec  [Michael]
    - use macros to make the id_info table clearer  [Longpeng]
    - add some modern devices in the id_info table  [Longpeng]
  Patch 2:
    - remove the GET_VECTORS_NUM command  [Jason]
  Patch 4:
    - expose vdpa_dev_fd as a QOM preperty  [Stefan]
    - introduce vhost_vdpa_device_get_u32 as a common
      function to make the code clearer  [Stefan]
    - fix the misleading description of 'dc->desc'  [Stefano]
  Patch 5:
    - check returned number of virtqueues  [Stefan]
  Patch 6:
    - init s->num_queues  [Stefano]
    - free s->dev.vqs  [Stefano]

Longpeng (Mike) (4):
  linux-headers: Update headers to Linux 5.18-rc6
  virtio: get class_id and pci device id by the virtio id
  vdpa: add vdpa-dev support
  vdpa: add vdpa-dev-pci support

 hw/virtio/Kconfig            |   5 +
 hw/virtio/meson.build        |   2 +
 hw/virtio/vdpa-dev-pci.c     | 101 +++++++++
 hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
 hw/virtio/virtio-pci.c       |  77 +++++++
 hw/virtio/virtio-pci.h       |   5 +
 include/hw/virtio/vdpa-dev.h |  43 ++++
 linux-headers/linux/vhost.h  |   7 +
 8 files changed, 625 insertions(+)
 create mode 100644 hw/virtio/vdpa-dev-pci.c
 create mode 100644 hw/virtio/vdpa-dev.c
 create mode 100644 include/hw/virtio/vdpa-dev.h

-- 
2.23.0

[PATCH v4 1/4] linux-headers: Update headers to Linux 5.18-rc6

[Longpeng(Mike) via]

From: Longpeng <longpeng2@huawei.com>

Update headers to 5.18-rc6. I need latest vhost changes.

Signed-off-by: Longpeng <longpeng2@huawei.com>
---
 linux-headers/linux/vhost.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h
index c998860d7b..5d99e7c242 100644
--- a/linux-headers/linux/vhost.h
+++ b/linux-headers/linux/vhost.h
@@ -150,4 +150,11 @@
 /* Get the valid iova range */
 #define VHOST_VDPA_GET_IOVA_RANGE	_IOR(VHOST_VIRTIO, 0x78, \
 					     struct vhost_vdpa_iova_range)
+
+/* Get the config size */
+#define VHOST_VDPA_GET_CONFIG_SIZE	_IOR(VHOST_VIRTIO, 0x79, __u32)
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
+
 #endif
-- 
2.23.0

[PATCH v4 2/4] virtio: get class_id and pci device id by the virtio id

[Longpeng(Mike) via]

From: Longpeng <longpeng2@huawei.com>

Add helpers to get the "Transitional PCI Device ID" and "class_id"
of the device specified by the "Virtio Device ID".

These helpers will be used to build the generic vDPA device later.

Signed-off-by: Longpeng <longpeng2@huawei.com>
---
 hw/virtio/virtio-pci.c | 77 ++++++++++++++++++++++++++++++++++++++++++
 hw/virtio/virtio-pci.h |  5 +++
 2 files changed, 82 insertions(+)

diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 7cf1231c1c..fdfa205cee 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -19,6 +19,7 @@
 
 #include "exec/memop.h"
 #include "standard-headers/linux/virtio_pci.h"
+#include "standard-headers/linux/virtio_ids.h"
 #include "hw/boards.h"
 #include "hw/virtio/virtio.h"
 #include "migration/qemu-file-types.h"
@@ -212,6 +213,79 @@ static int virtio_pci_load_queue(DeviceState *d, int n, QEMUFile *f)
     return 0;
 }
 
+typedef struct VirtIOPCIIDInfo {
+    /* virtio id */
+    uint16_t vdev_id;
+    /* pci device id for the transitional device */
+    uint16_t trans_devid;
+    uint16_t class_id;
+} VirtIOPCIIDInfo;
+
+#define VIRTIO_TRANS_DEV_ID_INFO(name, class)       \
+    {                                               \
+        .vdev_id = VIRTIO_ID_##name,                \
+        .trans_devid = PCI_DEVICE_ID_VIRTIO_##name, \
+        .class_id = class,                          \
+    }
+
+#define VIRTIO_MODERN_DEV_ID_NFO(name, class)       \
+    {                                               \
+        .vdev_id = VIRTIO_ID_##name,                \
+        .class_id = class,                          \
+    }
+
+static const VirtIOPCIIDInfo virtio_pci_id_info[] = {
+    /* Non-transitional devices */
+    VIRTIO_MODERN_DEV_ID_NFO(CRYPTO,    PCI_CLASS_OTHERS),
+    VIRTIO_MODERN_DEV_ID_NFO(FS,        PCI_CLASS_STORAGE_OTHER),
+    /* Transitional devices */
+    VIRTIO_TRANS_DEV_ID_INFO(NET,       PCI_CLASS_NETWORK_ETHERNET),
+    VIRTIO_TRANS_DEV_ID_INFO(BLOCK,     PCI_CLASS_STORAGE_SCSI),
+    VIRTIO_TRANS_DEV_ID_INFO(CONSOLE,   PCI_CLASS_COMMUNICATION_OTHER),
+    VIRTIO_TRANS_DEV_ID_INFO(SCSI,      PCI_CLASS_STORAGE_SCSI),
+    VIRTIO_TRANS_DEV_ID_INFO(9P,        PCI_BASE_CLASS_NETWORK),
+    VIRTIO_TRANS_DEV_ID_INFO(BALLOON,   PCI_CLASS_OTHERS),
+    VIRTIO_TRANS_DEV_ID_INFO(RNG,       PCI_CLASS_OTHERS),
+};
+
+static const VirtIOPCIIDInfo *virtio_pci_get_id_info(uint16_t vdev_id)
+{
+    const VirtIOPCIIDInfo *info = NULL;
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(virtio_pci_id_info); i++) {
+        if (virtio_pci_id_info[i].vdev_id == vdev_id) {
+            info = &virtio_pci_id_info[i];
+            break;
+        }
+    }
+
+    if (!info) {
+        /* The device id is invalid or not added to the id_info yet. */
+        error_report("Invalid virtio device(id %u)", vdev_id);
+        abort();
+    }
+
+    return info;
+}
+
+/*
+ * Get the Transitional Device ID for the specific device, return
+ * zero if the device is non-transitional.
+ */
+uint16_t virtio_pci_get_trans_devid(uint16_t device_id)
+{
+    return virtio_pci_get_id_info(device_id)->trans_devid;
+}
+
+/*
+ * Get the Class ID for the specific device.
+ */
+uint16_t virtio_pci_get_class_id(uint16_t device_id)
+{
+    return virtio_pci_get_id_info(device_id)->class_id;
+}
+
 static bool virtio_pci_ioeventfd_enabled(DeviceState *d)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
@@ -1675,6 +1749,9 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
          * is set to PCI_SUBVENDOR_ID_REDHAT_QUMRANET by default.
          */
         pci_set_word(config + PCI_SUBSYSTEM_ID, virtio_bus_get_vdev_id(bus));
+        if (proxy->trans_devid) {
+            pci_config_set_device_id(config, proxy->trans_devid);
+        }
     } else {
         /* pure virtio-1.0 */
         pci_set_word(config + PCI_VENDOR_ID,
diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h
index 2446dcd9ae..f08665cd1b 100644
--- a/hw/virtio/virtio-pci.h
+++ b/hw/virtio/virtio-pci.h
@@ -146,6 +146,8 @@ struct VirtIOPCIProxy {
     bool disable_modern;
     bool ignore_backend_features;
     OnOffAuto disable_legacy;
+    /* Transitional device id */
+    uint16_t trans_devid;
     uint32_t class_code;
     uint32_t nvectors;
     uint32_t dfselect;
@@ -158,6 +160,9 @@ struct VirtIOPCIProxy {
     VirtioBusState bus;
 };
 
+uint16_t virtio_pci_get_trans_devid(uint16_t device_id);
+uint16_t virtio_pci_get_class_id(uint16_t device_id);
+
 static inline bool virtio_pci_modern(VirtIOPCIProxy *proxy)
 {
     return !proxy->disable_modern;
-- 
2.23.0

[PATCH v4 3/4] vdpa: add vdpa-dev support

[Longpeng(Mike) via]

From: Longpeng <longpeng2@huawei.com>

Supports vdpa-dev.

Signed-off-by: Longpeng <longpeng2@huawei.com>
---
 hw/virtio/Kconfig            |   5 +
 hw/virtio/meson.build        |   1 +
 hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
 include/hw/virtio/vdpa-dev.h |  43 ++++
 4 files changed, 434 insertions(+)
 create mode 100644 hw/virtio/vdpa-dev.c
 create mode 100644 include/hw/virtio/vdpa-dev.h

diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
index c144d42f9b..2723283382 100644
--- a/hw/virtio/Kconfig
+++ b/hw/virtio/Kconfig
@@ -68,3 +68,8 @@ config VHOST_USER_RNG
     bool
     default y
     depends on VIRTIO && VHOST_USER
+
+config VHOST_VDPA_DEV
+    bool
+    default y if VIRTIO_PCI
+    depends on VIRTIO && VHOST_VDPA && LINUX
diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
index 67dc77e00f..8f6f86db71 100644
--- a/hw/virtio/meson.build
+++ b/hw/virtio/meson.build
@@ -29,6 +29,7 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
 virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c'))
 virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
 virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c'))
+virtio_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev.c'))
 
 virtio_pci_ss = ss.source_set()
 virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c'))
diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
new file mode 100644
index 0000000000..543b5b4b81
--- /dev/null
+++ b/hw/virtio/vdpa-dev.c
@@ -0,0 +1,385 @@
+/*
+ * Vhost Vdpa Device
+ *
+ * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
+ *
+ * Authors:
+ *   Longpeng <longpeng2@huawei.com>
+ *
+ * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
+ *   Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+#include "qemu/osdep.h"
+#include <sys/ioctl.h>
+#include <linux/vhost.h>
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/cutils.h"
+#include "hw/qdev-core.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "hw/virtio/vhost.h"
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/virtio-bus.h"
+#include "hw/virtio/virtio-access.h"
+#include "hw/virtio/vdpa-dev.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/runstate.h"
+
+static void
+vhost_vdpa_device_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
+{
+    /* Nothing to do */
+}
+
+static uint32_t
+vhost_vdpa_device_get_u32(int fd, unsigned long int cmd, Error **errp)
+{
+    uint32_t val = (uint32_t)-1;
+
+    if (ioctl(fd, cmd, &val) < 0) {
+        error_setg(errp, "vhost-vdpa-device: cmd 0x%lx failed: %s",
+                   cmd, strerror(errno));
+    }
+
+    return val;
+}
+
+static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VhostVdpaDevice *v = VHOST_VDPA_DEVICE(vdev);
+    uint16_t max_queue_size;
+    struct vhost_virtqueue *vqs;
+    int i, ret;
+
+    if (!v->vhostdev && v->vhostfd == -1) {
+        error_setg(errp, "both vhostdev and vhostfd are missing");
+        return;
+    }
+
+    if (v->vhostdev && v->vhostfd != -1) {
+        error_setg(errp, "both vhostdev and vhostfd are set");
+        return;
+    }
+
+    if (v->vhostfd == -1) {
+        v->vhostfd = qemu_open(v->vhostdev, O_RDWR, errp);
+        if (*errp) {
+            return;
+        }
+    }
+    v->vdpa.device_fd = v->vhostfd;
+
+    v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
+                                           VHOST_VDPA_GET_DEVICE_ID, errp);
+    if (*errp) {
+        goto out;
+    }
+
+    max_queue_size = vhost_vdpa_device_get_u32(v->vhostfd,
+                                               VHOST_VDPA_GET_VRING_NUM, errp);
+    if (*errp) {
+        goto out;
+    }
+
+    if (v->queue_size > max_queue_size) {
+        error_setg(errp, "vhost-vdpa-device: invalid queue_size: %u (max:%u)",
+                   v->queue_size, max_queue_size);
+        goto out;
+    } else if (!v->queue_size) {
+        v->queue_size = max_queue_size;
+    }
+
+    v->num_queues = vhost_vdpa_device_get_u32(v->vhostfd,
+                                              VHOST_VDPA_GET_VQS_COUNT, errp);
+    if (*errp) {
+        goto out;
+    }
+
+    if (!v->num_queues || v->num_queues > VIRTIO_QUEUE_MAX) {
+        error_setg(errp, "invalid number of virtqueues: %u (max:%u)",
+                   v->num_queues, VIRTIO_QUEUE_MAX);
+        goto out;
+    }
+
+    v->dev.nvqs = v->num_queues;
+    vqs = g_new0(struct vhost_virtqueue, v->dev.nvqs);
+    v->dev.vqs = vqs;
+    v->dev.vq_index = 0;
+    v->dev.vq_index_end = v->dev.nvqs;
+    v->dev.backend_features = 0;
+    v->started = false;
+
+    ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
+    if (ret < 0) {
+        error_setg(errp, "vhost-vdpa-device: vhost initialization failed: %s",
+                   strerror(-ret));
+        goto free_vqs;
+    }
+
+    v->config_size = vhost_vdpa_device_get_u32(v->vhostfd,
+                                               VHOST_VDPA_GET_CONFIG_SIZE, errp);
+    if (*errp) {
+        goto vhost_cleanup;
+    }
+
+    if (v->post_init && v->post_init(v, errp) < 0) {
+        goto free_virtio;
+    }
+
+    v->config = g_malloc0(v->config_size);
+
+    ret = vhost_dev_get_config(&v->dev, v->config, v->config_size, NULL);
+    if (ret < 0) {
+        error_setg(errp, "vhost-vdpa-device: get config failed");
+        goto free_config;
+    }
+
+    virtio_init(vdev, "vhost-vdpa", v->vdev_id, v->config_size);
+
+    v->virtqs = g_new0(VirtQueue *, v->dev.nvqs);
+    for (i = 0; i < v->dev.nvqs; i++) {
+        v->virtqs[i] = virtio_add_queue(vdev, v->queue_size,
+                                        vhost_vdpa_device_dummy_handle_output);
+    }
+
+    return;
+
+free_virtio:
+    for (i = 0; i < v->num_queues; i++) {
+        virtio_delete_queue(v->virtqs[i]);
+    }
+    g_free(v->virtqs);
+    virtio_cleanup(vdev);
+free_config:
+    g_free(v->config);
+vhost_cleanup:
+    vhost_dev_cleanup(&v->dev);
+free_vqs:
+    g_free(vqs);
+out:
+    qemu_close(v->vhostfd);
+    v->vhostfd = -1;
+}
+
+static void vhost_vdpa_device_unrealize(DeviceState *dev)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
+    int i;
+
+    virtio_set_status(vdev, 0);
+
+    for (i = 0; i < s->num_queues; i++) {
+        virtio_delete_queue(s->virtqs[i]);
+    }
+    g_free(s->virtqs);
+    virtio_cleanup(vdev);
+
+    g_free(s->config);
+    g_free(s->dev.vqs);
+    vhost_dev_cleanup(&s->dev);
+    qemu_close(s->vhostfd);
+    s->vhostfd = -1;
+}
+
+static void
+vhost_vdpa_device_get_config(VirtIODevice *vdev, uint8_t *config)
+{
+    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
+
+    memcpy(config, s->config, s->config_size);
+}
+
+static void
+vhost_vdpa_device_set_config(VirtIODevice *vdev, const uint8_t *config)
+{
+    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
+    int ret;
+
+    ret = vhost_dev_set_config(&s->dev, s->config, 0, s->config_size,
+                               VHOST_SET_CONFIG_TYPE_MASTER);
+    if (ret) {
+        error_report("set device config space failed");
+        return;
+    }
+}
+
+static uint64_t vhost_vdpa_device_get_features(VirtIODevice *vdev,
+                                               uint64_t features,
+                                               Error **errp)
+{
+    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
+    uint64_t backend_features = s->dev.features;
+
+    if (!virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM)) {
+        virtio_clear_feature(&backend_features, VIRTIO_F_IOMMU_PLATFORM);
+    }
+
+    return backend_features;
+}
+
+static int vhost_vdpa_device_start(VirtIODevice *vdev, Error **errp)
+{
+    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
+    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+    int i, ret;
+
+    if (!k->set_guest_notifiers) {
+        error_setg(errp, "binding does not support guest notifiers");
+        return -ENOSYS;
+    }
+
+    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Error enabling host notifiers");
+        return ret;
+    }
+
+    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Error binding guest notifier");
+        goto err_host_notifiers;
+    }
+
+    s->dev.acked_features = vdev->guest_features;
+
+    ret = vhost_dev_start(&s->dev, vdev);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Error starting vhost");
+        goto err_guest_notifiers;
+    }
+    s->started = true;
+
+    /*
+     * guest_notifier_mask/pending not used yet, so just unmask
+     * everything here. virtio-pci will do the right thing by
+     * enabling/disabling irqfd.
+     */
+    for (i = 0; i < s->dev.nvqs; i++) {
+        vhost_virtqueue_mask(&s->dev, vdev, i, false);
+    }
+
+    return ret;
+
+err_guest_notifiers:
+    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
+err_host_notifiers:
+    vhost_dev_disable_notifiers(&s->dev, vdev);
+    return ret;
+}
+
+static void vhost_vdpa_device_stop(VirtIODevice *vdev)
+{
+    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
+    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+    int ret;
+
+    if (!s->started) {
+        return;
+    }
+    s->started = false;
+
+    if (!k->set_guest_notifiers) {
+        return;
+    }
+
+    vhost_dev_stop(&s->dev, vdev);
+
+    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
+    if (ret < 0) {
+        error_report("vhost guest notifier cleanup failed: %d", ret);
+        return;
+    }
+
+    vhost_dev_disable_notifiers(&s->dev, vdev);
+}
+
+static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
+{
+    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
+    bool should_start = virtio_device_started(vdev, status);
+    Error *local_err = NULL;
+    int ret;
+
+    if (!vdev->vm_running) {
+        should_start = false;
+    }
+
+    if (s->started == should_start) {
+        return;
+    }
+
+    if (should_start) {
+        ret = vhost_vdpa_device_start(vdev, &local_err);
+        if (ret < 0) {
+            error_reportf_err(local_err, "vhost-vdpa-device: start failed: ");
+        }
+    } else {
+        vhost_vdpa_device_stop(vdev);
+    }
+}
+
+static Property vhost_vdpa_device_properties[] = {
+    DEFINE_PROP_STRING("vhostdev", VhostVdpaDevice, vhostdev),
+    DEFINE_PROP_INT32("vhostfd", VhostVdpaDevice, vhostfd, -1),
+    DEFINE_PROP_UINT16("queue-size", VhostVdpaDevice, queue_size, 0),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static const VMStateDescription vmstate_vhost_vdpa_device = {
+    .name = "vhost-vdpa-device",
+    .unmigratable = 1,
+    .minimum_version_id = 1,
+    .version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_VIRTIO_DEVICE,
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static void vhost_vdpa_device_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
+
+    device_class_set_props(dc, vhost_vdpa_device_properties);
+    dc->desc = "VDPA-based generic device assignment";
+    dc->vmsd = &vmstate_vhost_vdpa_device;
+    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+    vdc->realize = vhost_vdpa_device_realize;
+    vdc->unrealize = vhost_vdpa_device_unrealize;
+    vdc->get_config = vhost_vdpa_device_get_config;
+    vdc->set_config = vhost_vdpa_device_set_config;
+    vdc->get_features = vhost_vdpa_device_get_features;
+    vdc->set_status = vhost_vdpa_device_set_status;
+}
+
+static void vhost_vdpa_device_instance_init(Object *obj)
+{
+    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(obj);
+
+    device_add_bootindex_property(obj, &s->bootindex, "bootindex",
+                                  NULL, DEVICE(obj));
+}
+
+static const TypeInfo vhost_vdpa_device_info = {
+    .name = TYPE_VHOST_VDPA_DEVICE,
+    .parent = TYPE_VIRTIO_DEVICE,
+    .instance_size = sizeof(VhostVdpaDevice),
+    .class_init = vhost_vdpa_device_class_init,
+    .instance_init = vhost_vdpa_device_instance_init,
+};
+
+static void register_vhost_vdpa_device_type(void)
+{
+    type_register_static(&vhost_vdpa_device_info);
+}
+
+type_init(register_vhost_vdpa_device_type);
diff --git a/include/hw/virtio/vdpa-dev.h b/include/hw/virtio/vdpa-dev.h
new file mode 100644
index 0000000000..4dbf98195c
--- /dev/null
+++ b/include/hw/virtio/vdpa-dev.h
@@ -0,0 +1,43 @@
+/*
+ * Vhost Vdpa Device
+ *
+ * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
+ *
+ * Authors:
+ *   Longpeng <longpeng2@huawei.com>
+ *
+ * Largely based on the "vhost-user-blk.h" implemented by:
+ *   Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+#ifndef _VHOST_VDPA_DEVICE_H
+#define _VHOST_VDPA_DEVICE_H
+
+#include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-vdpa.h"
+#include "qom/object.h"
+
+
+#define TYPE_VHOST_VDPA_DEVICE "vhost-vdpa-device"
+OBJECT_DECLARE_SIMPLE_TYPE(VhostVdpaDevice, VHOST_VDPA_DEVICE)
+
+struct VhostVdpaDevice {
+    VirtIODevice parent_obj;
+    char *vhostdev;
+    int vhostfd;
+    int32_t bootindex;
+    uint32_t vdev_id;
+    uint32_t num_queues;
+    struct vhost_dev dev;
+    struct vhost_vdpa vdpa;
+    VirtQueue **virtqs;
+    uint8_t *config;
+    int config_size;
+    uint16_t queue_size;
+    bool started;
+    int (*post_init)(VhostVdpaDevice *v, Error **errp);
+};
+
+#endif
-- 
2.23.0

Re: [PATCH v4 3/4] vdpa: add vdpa-dev support

[Jason Wang]

On Tue, May 10, 2022 at 8:59 PM Longpeng(Mike) <longpeng2@huawei.com> wrote:
>
> From: Longpeng <longpeng2@huawei.com>
>
> Supports vdpa-dev.
>
> Signed-off-by: Longpeng <longpeng2@huawei.com>
> ---
>  hw/virtio/Kconfig            |   5 +
>  hw/virtio/meson.build        |   1 +
>  hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
>  include/hw/virtio/vdpa-dev.h |  43 ++++
>  4 files changed, 434 insertions(+)
>  create mode 100644 hw/virtio/vdpa-dev.c
>  create mode 100644 include/hw/virtio/vdpa-dev.h
>
> diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
> index c144d42f9b..2723283382 100644
> --- a/hw/virtio/Kconfig
> +++ b/hw/virtio/Kconfig
> @@ -68,3 +68,8 @@ config VHOST_USER_RNG
>      bool
>      default y
>      depends on VIRTIO && VHOST_USER
> +
> +config VHOST_VDPA_DEV
> +    bool
> +    default y if VIRTIO_PCI

Do we have the plan to add VIRTIO_MMIO support?

> +    depends on VIRTIO && VHOST_VDPA && LINUX
> diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
> index 67dc77e00f..8f6f86db71 100644
> --- a/hw/virtio/meson.build
> +++ b/hw/virtio/meson.build
> @@ -29,6 +29,7 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
>  virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c'))
>  virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
>  virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c'))
> +virtio_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev.c'))
>
>  virtio_pci_ss = ss.source_set()
>  virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c'))
> diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
> new file mode 100644
> index 0000000000..543b5b4b81
> --- /dev/null
> +++ b/hw/virtio/vdpa-dev.c
> @@ -0,0 +1,385 @@
> +/*
> + * Vhost Vdpa Device
> + *
> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
> + *
> + * Authors:
> + *   Longpeng <longpeng2@huawei.com>
> + *
> + * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
> + *   Changpeng Liu <changpeng.liu@intel.com>
> + *
> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
> + * See the COPYING.LIB file in the top-level directory.
> + */
> +#include "qemu/osdep.h"
> +#include <sys/ioctl.h>
> +#include <linux/vhost.h>
> +#include "qapi/error.h"
> +#include "qemu/error-report.h"
> +#include "qemu/cutils.h"
> +#include "hw/qdev-core.h"
> +#include "hw/qdev-properties.h"
> +#include "hw/qdev-properties-system.h"
> +#include "hw/virtio/vhost.h"
> +#include "hw/virtio/virtio.h"
> +#include "hw/virtio/virtio-bus.h"
> +#include "hw/virtio/virtio-access.h"
> +#include "hw/virtio/vdpa-dev.h"
> +#include "sysemu/sysemu.h"
> +#include "sysemu/runstate.h"
> +
> +static void
> +vhost_vdpa_device_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
> +{
> +    /* Nothing to do */
> +}
> +
> +static uint32_t
> +vhost_vdpa_device_get_u32(int fd, unsigned long int cmd, Error **errp)
> +{
> +    uint32_t val = (uint32_t)-1;
> +
> +    if (ioctl(fd, cmd, &val) < 0) {
> +        error_setg(errp, "vhost-vdpa-device: cmd 0x%lx failed: %s",
> +                   cmd, strerror(errno));
> +    }
> +
> +    return val;
> +}
> +
> +static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
> +{
> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> +    VhostVdpaDevice *v = VHOST_VDPA_DEVICE(vdev);
> +    uint16_t max_queue_size;
> +    struct vhost_virtqueue *vqs;
> +    int i, ret;
> +
> +    if (!v->vhostdev && v->vhostfd == -1) {
> +        error_setg(errp, "both vhostdev and vhostfd are missing");
> +        return;
> +    }
> +
> +    if (v->vhostdev && v->vhostfd != -1) {
> +        error_setg(errp, "both vhostdev and vhostfd are set");
> +        return;
> +    }
> +
> +    if (v->vhostfd == -1) {
> +        v->vhostfd = qemu_open(v->vhostdev, O_RDWR, errp);
> +        if (*errp) {

Is this better to set error messages for all the possible failures
during realization?

> +            return;
> +        }
> +    }
> +    v->vdpa.device_fd = v->vhostfd;
> +
> +    v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
> +                                           VHOST_VDPA_GET_DEVICE_ID, errp);
> +    if (*errp) {
> +        goto out;
> +    }
> +
> +    max_queue_size = vhost_vdpa_device_get_u32(v->vhostfd,
> +                                               VHOST_VDPA_GET_VRING_NUM, errp);
> +    if (*errp) {
> +        goto out;
> +    }
> +
> +    if (v->queue_size > max_queue_size) {
> +        error_setg(errp, "vhost-vdpa-device: invalid queue_size: %u (max:%u)",
> +                   v->queue_size, max_queue_size);
> +        goto out;
> +    } else if (!v->queue_size) {
> +        v->queue_size = max_queue_size;
> +    }
> +
> +    v->num_queues = vhost_vdpa_device_get_u32(v->vhostfd,
> +                                              VHOST_VDPA_GET_VQS_COUNT, errp);
> +    if (*errp) {
> +        goto out;
> +    }
> +
> +    if (!v->num_queues || v->num_queues > VIRTIO_QUEUE_MAX) {
> +        error_setg(errp, "invalid number of virtqueues: %u (max:%u)",
> +                   v->num_queues, VIRTIO_QUEUE_MAX);
> +        goto out;
> +    }
> +
> +    v->dev.nvqs = v->num_queues;
> +    vqs = g_new0(struct vhost_virtqueue, v->dev.nvqs);
> +    v->dev.vqs = vqs;
> +    v->dev.vq_index = 0;
> +    v->dev.vq_index_end = v->dev.nvqs;
> +    v->dev.backend_features = 0;
> +    v->started = false;
> +
> +    ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
> +    if (ret < 0) {
> +        error_setg(errp, "vhost-vdpa-device: vhost initialization failed: %s",
> +                   strerror(-ret));
> +        goto free_vqs;
> +    }
> +
> +    v->config_size = vhost_vdpa_device_get_u32(v->vhostfd,
> +                                               VHOST_VDPA_GET_CONFIG_SIZE, errp);
> +    if (*errp) {
> +        goto vhost_cleanup;
> +    }
> +
> +    if (v->post_init && v->post_init(v, errp) < 0) {
> +        goto free_virtio;
> +    }
> +
> +    v->config = g_malloc0(v->config_size);
> +
> +    ret = vhost_dev_get_config(&v->dev, v->config, v->config_size, NULL);
> +    if (ret < 0) {
> +        error_setg(errp, "vhost-vdpa-device: get config failed");
> +        goto free_config;
> +    }
> +
> +    virtio_init(vdev, "vhost-vdpa", v->vdev_id, v->config_size);
> +
> +    v->virtqs = g_new0(VirtQueue *, v->dev.nvqs);
> +    for (i = 0; i < v->dev.nvqs; i++) {
> +        v->virtqs[i] = virtio_add_queue(vdev, v->queue_size,
> +                                        vhost_vdpa_device_dummy_handle_output);
> +    }
> +
> +    return;
> +
> +free_virtio:
> +    for (i = 0; i < v->num_queues; i++) {
> +        virtio_delete_queue(v->virtqs[i]);
> +    }
> +    g_free(v->virtqs);
> +    virtio_cleanup(vdev);
> +free_config:
> +    g_free(v->config);
> +vhost_cleanup:
> +    vhost_dev_cleanup(&v->dev);
> +free_vqs:
> +    g_free(vqs);
> +out:
> +    qemu_close(v->vhostfd);
> +    v->vhostfd = -1;
> +}
> +
> +static void vhost_vdpa_device_unrealize(DeviceState *dev)
> +{
> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> +    int i;
> +
> +    virtio_set_status(vdev, 0);
> +
> +    for (i = 0; i < s->num_queues; i++) {
> +        virtio_delete_queue(s->virtqs[i]);
> +    }
> +    g_free(s->virtqs);
> +    virtio_cleanup(vdev);
> +
> +    g_free(s->config);
> +    g_free(s->dev.vqs);
> +    vhost_dev_cleanup(&s->dev);
> +    qemu_close(s->vhostfd);
> +    s->vhostfd = -1;
> +}
> +
> +static void
> +vhost_vdpa_device_get_config(VirtIODevice *vdev, uint8_t *config)
> +{
> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> +
> +    memcpy(config, s->config, s->config_size);
> +}
> +
> +static void
> +vhost_vdpa_device_set_config(VirtIODevice *vdev, const uint8_t *config)
> +{
> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> +    int ret;
> +
> +    ret = vhost_dev_set_config(&s->dev, s->config, 0, s->config_size,
> +                               VHOST_SET_CONFIG_TYPE_MASTER);
> +    if (ret) {
> +        error_report("set device config space failed");
> +        return;
> +    }
> +}
> +
> +static uint64_t vhost_vdpa_device_get_features(VirtIODevice *vdev,
> +                                               uint64_t features,
> +                                               Error **errp)
> +{
> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> +    uint64_t backend_features = s->dev.features;
> +
> +    if (!virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM)) {
> +        virtio_clear_feature(&backend_features, VIRTIO_F_IOMMU_PLATFORM);
> +    }
> +
> +    return backend_features;
> +}
> +
> +static int vhost_vdpa_device_start(VirtIODevice *vdev, Error **errp)
> +{
> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
> +    int i, ret;
> +
> +    if (!k->set_guest_notifiers) {
> +        error_setg(errp, "binding does not support guest notifiers");
> +        return -ENOSYS;
> +    }
> +
> +    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
> +    if (ret < 0) {
> +        error_setg_errno(errp, -ret, "Error enabling host notifiers");
> +        return ret;
> +    }
> +
> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
> +    if (ret < 0) {
> +        error_setg_errno(errp, -ret, "Error binding guest notifier");
> +        goto err_host_notifiers;
> +    }
> +
> +    s->dev.acked_features = vdev->guest_features;
> +
> +    ret = vhost_dev_start(&s->dev, vdev);
> +    if (ret < 0) {
> +        error_setg_errno(errp, -ret, "Error starting vhost");
> +        goto err_guest_notifiers;
> +    }
> +    s->started = true;
> +
> +    /*
> +     * guest_notifier_mask/pending not used yet, so just unmask
> +     * everything here. virtio-pci will do the right thing by
> +     * enabling/disabling irqfd.
> +     */
> +    for (i = 0; i < s->dev.nvqs; i++) {
> +        vhost_virtqueue_mask(&s->dev, vdev, i, false);
> +    }
> +
> +    return ret;
> +
> +err_guest_notifiers:
> +    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
> +err_host_notifiers:
> +    vhost_dev_disable_notifiers(&s->dev, vdev);
> +    return ret;
> +}
> +
> +static void vhost_vdpa_device_stop(VirtIODevice *vdev)
> +{
> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
> +    int ret;
> +
> +    if (!s->started) {
> +        return;
> +    }
> +    s->started = false;
> +
> +    if (!k->set_guest_notifiers) {
> +        return;
> +    }
> +
> +    vhost_dev_stop(&s->dev, vdev);
> +
> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
> +    if (ret < 0) {
> +        error_report("vhost guest notifier cleanup failed: %d", ret);
> +        return;
> +    }
> +
> +    vhost_dev_disable_notifiers(&s->dev, vdev);
> +}
> +
> +static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
> +{
> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> +    bool should_start = virtio_device_started(vdev, status);
> +    Error *local_err = NULL;
> +    int ret;
> +
> +    if (!vdev->vm_running) {
> +        should_start = false;
> +    }
> +
> +    if (s->started == should_start) {
> +        return;
> +    }
> +
> +    if (should_start) {
> +        ret = vhost_vdpa_device_start(vdev, &local_err);
> +        if (ret < 0) {
> +            error_reportf_err(local_err, "vhost-vdpa-device: start failed: ");
> +        }
> +    } else {
> +        vhost_vdpa_device_stop(vdev);
> +    }
> +}
> +
> +static Property vhost_vdpa_device_properties[] = {
> +    DEFINE_PROP_STRING("vhostdev", VhostVdpaDevice, vhostdev),
> +    DEFINE_PROP_INT32("vhostfd", VhostVdpaDevice, vhostfd, -1),

This is probably not needed since we can "abuse" /dev/fd/X for vhostdev.

Thanks

> +    DEFINE_PROP_UINT16("queue-size", VhostVdpaDevice, queue_size, 0),
> +    DEFINE_PROP_END_OF_LIST(),
> +};
> +
> +static const VMStateDescription vmstate_vhost_vdpa_device = {
> +    .name = "vhost-vdpa-device",
> +    .unmigratable = 1,
> +    .minimum_version_id = 1,
> +    .version_id = 1,
> +    .fields = (VMStateField[]) {
> +        VMSTATE_VIRTIO_DEVICE,
> +        VMSTATE_END_OF_LIST()
> +    },
> +};
> +
> +static void vhost_vdpa_device_class_init(ObjectClass *klass, void *data)
> +{
> +    DeviceClass *dc = DEVICE_CLASS(klass);
> +    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
> +
> +    device_class_set_props(dc, vhost_vdpa_device_properties);
> +    dc->desc = "VDPA-based generic device assignment";
> +    dc->vmsd = &vmstate_vhost_vdpa_device;
> +    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
> +    vdc->realize = vhost_vdpa_device_realize;
> +    vdc->unrealize = vhost_vdpa_device_unrealize;
> +    vdc->get_config = vhost_vdpa_device_get_config;
> +    vdc->set_config = vhost_vdpa_device_set_config;
> +    vdc->get_features = vhost_vdpa_device_get_features;
> +    vdc->set_status = vhost_vdpa_device_set_status;
> +}
> +
> +static void vhost_vdpa_device_instance_init(Object *obj)
> +{
> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(obj);
> +
> +    device_add_bootindex_property(obj, &s->bootindex, "bootindex",
> +                                  NULL, DEVICE(obj));
> +}
> +
> +static const TypeInfo vhost_vdpa_device_info = {
> +    .name = TYPE_VHOST_VDPA_DEVICE,
> +    .parent = TYPE_VIRTIO_DEVICE,
> +    .instance_size = sizeof(VhostVdpaDevice),
> +    .class_init = vhost_vdpa_device_class_init,
> +    .instance_init = vhost_vdpa_device_instance_init,
> +};
> +
> +static void register_vhost_vdpa_device_type(void)
> +{
> +    type_register_static(&vhost_vdpa_device_info);
> +}
> +
> +type_init(register_vhost_vdpa_device_type);
> diff --git a/include/hw/virtio/vdpa-dev.h b/include/hw/virtio/vdpa-dev.h
> new file mode 100644
> index 0000000000..4dbf98195c
> --- /dev/null
> +++ b/include/hw/virtio/vdpa-dev.h
> @@ -0,0 +1,43 @@
> +/*
> + * Vhost Vdpa Device
> + *
> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
> + *
> + * Authors:
> + *   Longpeng <longpeng2@huawei.com>
> + *
> + * Largely based on the "vhost-user-blk.h" implemented by:
> + *   Changpeng Liu <changpeng.liu@intel.com>
> + *
> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
> + * See the COPYING.LIB file in the top-level directory.
> + */
> +#ifndef _VHOST_VDPA_DEVICE_H
> +#define _VHOST_VDPA_DEVICE_H
> +
> +#include "hw/virtio/vhost.h"
> +#include "hw/virtio/vhost-vdpa.h"
> +#include "qom/object.h"
> +
> +
> +#define TYPE_VHOST_VDPA_DEVICE "vhost-vdpa-device"
> +OBJECT_DECLARE_SIMPLE_TYPE(VhostVdpaDevice, VHOST_VDPA_DEVICE)
> +
> +struct VhostVdpaDevice {
> +    VirtIODevice parent_obj;
> +    char *vhostdev;
> +    int vhostfd;
> +    int32_t bootindex;
> +    uint32_t vdev_id;
> +    uint32_t num_queues;
> +    struct vhost_dev dev;
> +    struct vhost_vdpa vdpa;
> +    VirtQueue **virtqs;
> +    uint8_t *config;
> +    int config_size;
> +    uint16_t queue_size;
> +    bool started;
> +    int (*post_init)(VhostVdpaDevice *v, Error **errp);
> +};
> +
> +#endif
> --
> 2.23.0
>

Re: [PATCH v4 3/4] vdpa: add vdpa-dev support

[longpeng2--- via]

在 2022/5/11 10:56, Jason Wang 写道:
> On Tue, May 10, 2022 at 8:59 PM Longpeng(Mike) <longpeng2@huawei.com> wrote:
>>
>> From: Longpeng <longpeng2@huawei.com>
>>
>> Supports vdpa-dev.
>>
>> Signed-off-by: Longpeng <longpeng2@huawei.com>
>> ---
>>   hw/virtio/Kconfig            |   5 +
>>   hw/virtio/meson.build        |   1 +
>>   hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
>>   include/hw/virtio/vdpa-dev.h |  43 ++++
>>   4 files changed, 434 insertions(+)
>>   create mode 100644 hw/virtio/vdpa-dev.c
>>   create mode 100644 include/hw/virtio/vdpa-dev.h
>>
>> diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
>> index c144d42f9b..2723283382 100644
>> --- a/hw/virtio/Kconfig
>> +++ b/hw/virtio/Kconfig
>> @@ -68,3 +68,8 @@ config VHOST_USER_RNG
>>       bool
>>       default y
>>       depends on VIRTIO && VHOST_USER
>> +
>> +config VHOST_VDPA_DEV
>> +    bool
>> +    default y if VIRTIO_PCI
> 
> Do we have the plan to add VIRTIO_MMIO support?
> 
There is currently no plan. Maybe we can try to support it in the next step.

>> +    depends on VIRTIO && VHOST_VDPA && LINUX
>> diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
>> index 67dc77e00f..8f6f86db71 100644
>> --- a/hw/virtio/meson.build
>> +++ b/hw/virtio/meson.build
>> @@ -29,6 +29,7 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
>>   virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c'))
>>   virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
>>   virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c'))
>> +virtio_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev.c'))
>>
>>   virtio_pci_ss = ss.source_set()
>>   virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c'))
>> diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
>> new file mode 100644
>> index 0000000000..543b5b4b81
>> --- /dev/null
>> +++ b/hw/virtio/vdpa-dev.c
>> @@ -0,0 +1,385 @@
>> +/*
>> + * Vhost Vdpa Device
>> + *
>> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
>> + *
>> + * Authors:
>> + *   Longpeng <longpeng2@huawei.com>
>> + *
>> + * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
>> + *   Changpeng Liu <changpeng.liu@intel.com>
>> + *
>> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
>> + * See the COPYING.LIB file in the top-level directory.
>> + */
>> +#include "qemu/osdep.h"
>> +#include <sys/ioctl.h>
>> +#include <linux/vhost.h>
>> +#include "qapi/error.h"
>> +#include "qemu/error-report.h"
>> +#include "qemu/cutils.h"
>> +#include "hw/qdev-core.h"
>> +#include "hw/qdev-properties.h"
>> +#include "hw/qdev-properties-system.h"
>> +#include "hw/virtio/vhost.h"
>> +#include "hw/virtio/virtio.h"
>> +#include "hw/virtio/virtio-bus.h"
>> +#include "hw/virtio/virtio-access.h"
>> +#include "hw/virtio/vdpa-dev.h"
>> +#include "sysemu/sysemu.h"
>> +#include "sysemu/runstate.h"
>> +
>> +static void
>> +vhost_vdpa_device_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
>> +{
>> +    /* Nothing to do */
>> +}
>> +
>> +static uint32_t
>> +vhost_vdpa_device_get_u32(int fd, unsigned long int cmd, Error **errp)
>> +{
>> +    uint32_t val = (uint32_t)-1;
>> +
>> +    if (ioctl(fd, cmd, &val) < 0) {
>> +        error_setg(errp, "vhost-vdpa-device: cmd 0x%lx failed: %s",
>> +                   cmd, strerror(errno));
>> +    }
>> +
>> +    return val;
>> +}
>> +
>> +static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
>> +{
>> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>> +    VhostVdpaDevice *v = VHOST_VDPA_DEVICE(vdev);
>> +    uint16_t max_queue_size;
>> +    struct vhost_virtqueue *vqs;
>> +    int i, ret;
>> +
>> +    if (!v->vhostdev && v->vhostfd == -1) {
>> +        error_setg(errp, "both vhostdev and vhostfd are missing");
>> +        return;
>> +    }
>> +
>> +    if (v->vhostdev && v->vhostfd != -1) {
>> +        error_setg(errp, "both vhostdev and vhostfd are set");
>> +        return;
>> +    }
>> +
>> +    if (v->vhostfd == -1) {
>> +        v->vhostfd = qemu_open(v->vhostdev, O_RDWR, errp);
>> +        if (*errp) {
> 
> Is this better to set error messages for all the possible failures
> during realization?
>
I think the error messages already set in *errp, right?

>> +            return;
>> +        }
>> +    }
>> +    v->vdpa.device_fd = v->vhostfd;
>> +
>> +    v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
>> +                                           VHOST_VDPA_GET_DEVICE_ID, errp);
>> +    if (*errp) {
>> +        goto out;
>> +    }
>> +
>> +    max_queue_size = vhost_vdpa_device_get_u32(v->vhostfd,
>> +                                               VHOST_VDPA_GET_VRING_NUM, errp);
>> +    if (*errp) {
>> +        goto out;
>> +    }
>> +
>> +    if (v->queue_size > max_queue_size) {
>> +        error_setg(errp, "vhost-vdpa-device: invalid queue_size: %u (max:%u)",
>> +                   v->queue_size, max_queue_size);
>> +        goto out;
>> +    } else if (!v->queue_size) {
>> +        v->queue_size = max_queue_size;
>> +    }
>> +
>> +    v->num_queues = vhost_vdpa_device_get_u32(v->vhostfd,
>> +                                              VHOST_VDPA_GET_VQS_COUNT, errp);
>> +    if (*errp) {
>> +        goto out;
>> +    }
>> +
>> +    if (!v->num_queues || v->num_queues > VIRTIO_QUEUE_MAX) {
>> +        error_setg(errp, "invalid number of virtqueues: %u (max:%u)",
>> +                   v->num_queues, VIRTIO_QUEUE_MAX);
>> +        goto out;
>> +    }
>> +
>> +    v->dev.nvqs = v->num_queues;
>> +    vqs = g_new0(struct vhost_virtqueue, v->dev.nvqs);
>> +    v->dev.vqs = vqs;
>> +    v->dev.vq_index = 0;
>> +    v->dev.vq_index_end = v->dev.nvqs;
>> +    v->dev.backend_features = 0;
>> +    v->started = false;
>> +
>> +    ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
>> +    if (ret < 0) {
>> +        error_setg(errp, "vhost-vdpa-device: vhost initialization failed: %s",
>> +                   strerror(-ret));
>> +        goto free_vqs;
>> +    }
>> +
>> +    v->config_size = vhost_vdpa_device_get_u32(v->vhostfd,
>> +                                               VHOST_VDPA_GET_CONFIG_SIZE, errp);
>> +    if (*errp) {
>> +        goto vhost_cleanup;
>> +    }
>> +
>> +    if (v->post_init && v->post_init(v, errp) < 0) {
>> +        goto free_virtio;
>> +    }
>> +
>> +    v->config = g_malloc0(v->config_size);
>> +
>> +    ret = vhost_dev_get_config(&v->dev, v->config, v->config_size, NULL);
>> +    if (ret < 0) {
>> +        error_setg(errp, "vhost-vdpa-device: get config failed");
>> +        goto free_config;
>> +    }
>> +
>> +    virtio_init(vdev, "vhost-vdpa", v->vdev_id, v->config_size);
>> +
>> +    v->virtqs = g_new0(VirtQueue *, v->dev.nvqs);
>> +    for (i = 0; i < v->dev.nvqs; i++) {
>> +        v->virtqs[i] = virtio_add_queue(vdev, v->queue_size,
>> +                                        vhost_vdpa_device_dummy_handle_output);
>> +    }
>> +
>> +    return;
>> +
>> +free_virtio:
>> +    for (i = 0; i < v->num_queues; i++) {
>> +        virtio_delete_queue(v->virtqs[i]);
>> +    }
>> +    g_free(v->virtqs);
>> +    virtio_cleanup(vdev);
>> +free_config:
>> +    g_free(v->config);
>> +vhost_cleanup:
>> +    vhost_dev_cleanup(&v->dev);
>> +free_vqs:
>> +    g_free(vqs);
>> +out:
>> +    qemu_close(v->vhostfd);
>> +    v->vhostfd = -1;
>> +}
>> +
>> +static void vhost_vdpa_device_unrealize(DeviceState *dev)
>> +{
>> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    int i;
>> +
>> +    virtio_set_status(vdev, 0);
>> +
>> +    for (i = 0; i < s->num_queues; i++) {
>> +        virtio_delete_queue(s->virtqs[i]);
>> +    }
>> +    g_free(s->virtqs);
>> +    virtio_cleanup(vdev);
>> +
>> +    g_free(s->config);
>> +    g_free(s->dev.vqs);
>> +    vhost_dev_cleanup(&s->dev);
>> +    qemu_close(s->vhostfd);
>> +    s->vhostfd = -1;
>> +}
>> +
>> +static void
>> +vhost_vdpa_device_get_config(VirtIODevice *vdev, uint8_t *config)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +
>> +    memcpy(config, s->config, s->config_size);
>> +}
>> +
>> +static void
>> +vhost_vdpa_device_set_config(VirtIODevice *vdev, const uint8_t *config)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    int ret;
>> +
>> +    ret = vhost_dev_set_config(&s->dev, s->config, 0, s->config_size,
>> +                               VHOST_SET_CONFIG_TYPE_MASTER);
>> +    if (ret) {
>> +        error_report("set device config space failed");
>> +        return;
>> +    }
>> +}
>> +
>> +static uint64_t vhost_vdpa_device_get_features(VirtIODevice *vdev,
>> +                                               uint64_t features,
>> +                                               Error **errp)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    uint64_t backend_features = s->dev.features;
>> +
>> +    if (!virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM)) {
>> +        virtio_clear_feature(&backend_features, VIRTIO_F_IOMMU_PLATFORM);
>> +    }
>> +
>> +    return backend_features;
>> +}
>> +
>> +static int vhost_vdpa_device_start(VirtIODevice *vdev, Error **errp)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
>> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>> +    int i, ret;
>> +
>> +    if (!k->set_guest_notifiers) {
>> +        error_setg(errp, "binding does not support guest notifiers");
>> +        return -ENOSYS;
>> +    }
>> +
>> +    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
>> +    if (ret < 0) {
>> +        error_setg_errno(errp, -ret, "Error enabling host notifiers");
>> +        return ret;
>> +    }
>> +
>> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
>> +    if (ret < 0) {
>> +        error_setg_errno(errp, -ret, "Error binding guest notifier");
>> +        goto err_host_notifiers;
>> +    }
>> +
>> +    s->dev.acked_features = vdev->guest_features;
>> +
>> +    ret = vhost_dev_start(&s->dev, vdev);
>> +    if (ret < 0) {
>> +        error_setg_errno(errp, -ret, "Error starting vhost");
>> +        goto err_guest_notifiers;
>> +    }
>> +    s->started = true;
>> +
>> +    /*
>> +     * guest_notifier_mask/pending not used yet, so just unmask
>> +     * everything here. virtio-pci will do the right thing by
>> +     * enabling/disabling irqfd.
>> +     */
>> +    for (i = 0; i < s->dev.nvqs; i++) {
>> +        vhost_virtqueue_mask(&s->dev, vdev, i, false);
>> +    }
>> +
>> +    return ret;
>> +
>> +err_guest_notifiers:
>> +    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
>> +err_host_notifiers:
>> +    vhost_dev_disable_notifiers(&s->dev, vdev);
>> +    return ret;
>> +}
>> +
>> +static void vhost_vdpa_device_stop(VirtIODevice *vdev)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
>> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>> +    int ret;
>> +
>> +    if (!s->started) {
>> +        return;
>> +    }
>> +    s->started = false;
>> +
>> +    if (!k->set_guest_notifiers) {
>> +        return;
>> +    }
>> +
>> +    vhost_dev_stop(&s->dev, vdev);
>> +
>> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
>> +    if (ret < 0) {
>> +        error_report("vhost guest notifier cleanup failed: %d", ret);
>> +        return;
>> +    }
>> +
>> +    vhost_dev_disable_notifiers(&s->dev, vdev);
>> +}
>> +
>> +static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    bool should_start = virtio_device_started(vdev, status);
>> +    Error *local_err = NULL;
>> +    int ret;
>> +
>> +    if (!vdev->vm_running) {
>> +        should_start = false;
>> +    }
>> +
>> +    if (s->started == should_start) {
>> +        return;
>> +    }
>> +
>> +    if (should_start) {
>> +        ret = vhost_vdpa_device_start(vdev, &local_err);
>> +        if (ret < 0) {
>> +            error_reportf_err(local_err, "vhost-vdpa-device: start failed: ");
>> +        }
>> +    } else {
>> +        vhost_vdpa_device_stop(vdev);
>> +    }
>> +}
>> +
>> +static Property vhost_vdpa_device_properties[] = {
>> +    DEFINE_PROP_STRING("vhostdev", VhostVdpaDevice, vhostdev),
>> +    DEFINE_PROP_INT32("vhostfd", VhostVdpaDevice, vhostfd, -1),
> 
> This is probably not needed since we can "abuse" /dev/fd/X for vhostdev.
> 
It seems "vhostdev" is enough. I prefer to remove "vhostfd" if there is 
no objection.

Thanks.

> Thanks
> 
>> +    DEFINE_PROP_UINT16("queue-size", VhostVdpaDevice, queue_size, 0),
>> +    DEFINE_PROP_END_OF_LIST(),
>> +};
>> +
>> +static const VMStateDescription vmstate_vhost_vdpa_device = {
>> +    .name = "vhost-vdpa-device",
>> +    .unmigratable = 1,
>> +    .minimum_version_id = 1,
>> +    .version_id = 1,
>> +    .fields = (VMStateField[]) {
>> +        VMSTATE_VIRTIO_DEVICE,
>> +        VMSTATE_END_OF_LIST()
>> +    },
>> +};
>> +
>> +static void vhost_vdpa_device_class_init(ObjectClass *klass, void *data)
>> +{
>> +    DeviceClass *dc = DEVICE_CLASS(klass);
>> +    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
>> +
>> +    device_class_set_props(dc, vhost_vdpa_device_properties);
>> +    dc->desc = "VDPA-based generic device assignment";
>> +    dc->vmsd = &vmstate_vhost_vdpa_device;
>> +    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
>> +    vdc->realize = vhost_vdpa_device_realize;
>> +    vdc->unrealize = vhost_vdpa_device_unrealize;
>> +    vdc->get_config = vhost_vdpa_device_get_config;
>> +    vdc->set_config = vhost_vdpa_device_set_config;
>> +    vdc->get_features = vhost_vdpa_device_get_features;
>> +    vdc->set_status = vhost_vdpa_device_set_status;
>> +}
>> +
>> +static void vhost_vdpa_device_instance_init(Object *obj)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(obj);
>> +
>> +    device_add_bootindex_property(obj, &s->bootindex, "bootindex",
>> +                                  NULL, DEVICE(obj));
>> +}
>> +
>> +static const TypeInfo vhost_vdpa_device_info = {
>> +    .name = TYPE_VHOST_VDPA_DEVICE,
>> +    .parent = TYPE_VIRTIO_DEVICE,
>> +    .instance_size = sizeof(VhostVdpaDevice),
>> +    .class_init = vhost_vdpa_device_class_init,
>> +    .instance_init = vhost_vdpa_device_instance_init,
>> +};
>> +
>> +static void register_vhost_vdpa_device_type(void)
>> +{
>> +    type_register_static(&vhost_vdpa_device_info);
>> +}
>> +
>> +type_init(register_vhost_vdpa_device_type);
>> diff --git a/include/hw/virtio/vdpa-dev.h b/include/hw/virtio/vdpa-dev.h
>> new file mode 100644
>> index 0000000000..4dbf98195c
>> --- /dev/null
>> +++ b/include/hw/virtio/vdpa-dev.h
>> @@ -0,0 +1,43 @@
>> +/*
>> + * Vhost Vdpa Device
>> + *
>> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
>> + *
>> + * Authors:
>> + *   Longpeng <longpeng2@huawei.com>
>> + *
>> + * Largely based on the "vhost-user-blk.h" implemented by:
>> + *   Changpeng Liu <changpeng.liu@intel.com>
>> + *
>> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
>> + * See the COPYING.LIB file in the top-level directory.
>> + */
>> +#ifndef _VHOST_VDPA_DEVICE_H
>> +#define _VHOST_VDPA_DEVICE_H
>> +
>> +#include "hw/virtio/vhost.h"
>> +#include "hw/virtio/vhost-vdpa.h"
>> +#include "qom/object.h"
>> +
>> +
>> +#define TYPE_VHOST_VDPA_DEVICE "vhost-vdpa-device"
>> +OBJECT_DECLARE_SIMPLE_TYPE(VhostVdpaDevice, VHOST_VDPA_DEVICE)
>> +
>> +struct VhostVdpaDevice {
>> +    VirtIODevice parent_obj;
>> +    char *vhostdev;
>> +    int vhostfd;
>> +    int32_t bootindex;
>> +    uint32_t vdev_id;
>> +    uint32_t num_queues;
>> +    struct vhost_dev dev;
>> +    struct vhost_vdpa vdpa;
>> +    VirtQueue **virtqs;
>> +    uint8_t *config;
>> +    int config_size;
>> +    uint16_t queue_size;
>> +    bool started;
>> +    int (*post_init)(VhostVdpaDevice *v, Error **errp);
>> +};
>> +
>> +#endif
>> --
>> 2.23.0
>>
> 
> .

Re: [PATCH v4 3/4] vdpa: add vdpa-dev support

[Jason Wang]

On Wed, May 11, 2022 at 2:10 PM Longpeng (Mike, Cloud Infrastructure
Service Product Dept.) <longpeng2@huawei.com> wrote:
>
>
>
> 在 2022/5/11 10:56, Jason Wang 写道:
> > On Tue, May 10, 2022 at 8:59 PM Longpeng(Mike) <longpeng2@huawei.com> wrote:
> >>
> >> From: Longpeng <longpeng2@huawei.com>
> >>
> >> Supports vdpa-dev.
> >>
> >> Signed-off-by: Longpeng <longpeng2@huawei.com>
> >> ---
> >>   hw/virtio/Kconfig            |   5 +
> >>   hw/virtio/meson.build        |   1 +
> >>   hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
> >>   include/hw/virtio/vdpa-dev.h |  43 ++++
> >>   4 files changed, 434 insertions(+)
> >>   create mode 100644 hw/virtio/vdpa-dev.c
> >>   create mode 100644 include/hw/virtio/vdpa-dev.h
> >>
> >> diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
> >> index c144d42f9b..2723283382 100644
> >> --- a/hw/virtio/Kconfig
> >> +++ b/hw/virtio/Kconfig
> >> @@ -68,3 +68,8 @@ config VHOST_USER_RNG
> >>       bool
> >>       default y
> >>       depends on VIRTIO && VHOST_USER
> >> +
> >> +config VHOST_VDPA_DEV
> >> +    bool
> >> +    default y if VIRTIO_PCI
> >
> > Do we have the plan to add VIRTIO_MMIO support?
> >
> There is currently no plan. Maybe we can try to support it in the next step.

That would be better, allowing MMIO on top of vhost-vDPA is considered
to be one of the important advantages.

>
> >> +    depends on VIRTIO && VHOST_VDPA && LINUX
> >> diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
> >> index 67dc77e00f..8f6f86db71 100644
> >> --- a/hw/virtio/meson.build
> >> +++ b/hw/virtio/meson.build
> >> @@ -29,6 +29,7 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
> >>   virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c'))
> >>   virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
> >>   virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c'))
> >> +virtio_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev.c'))
> >>
> >>   virtio_pci_ss = ss.source_set()
> >>   virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c'))
> >> diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
> >> new file mode 100644
> >> index 0000000000..543b5b4b81
> >> --- /dev/null
> >> +++ b/hw/virtio/vdpa-dev.c
> >> @@ -0,0 +1,385 @@
> >> +/*
> >> + * Vhost Vdpa Device
> >> + *
> >> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
> >> + *
> >> + * Authors:
> >> + *   Longpeng <longpeng2@huawei.com>
> >> + *
> >> + * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
> >> + *   Changpeng Liu <changpeng.liu@intel.com>
> >> + *
> >> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
> >> + * See the COPYING.LIB file in the top-level directory.
> >> + */
> >> +#include "qemu/osdep.h"
> >> +#include <sys/ioctl.h>
> >> +#include <linux/vhost.h>
> >> +#include "qapi/error.h"
> >> +#include "qemu/error-report.h"
> >> +#include "qemu/cutils.h"
> >> +#include "hw/qdev-core.h"
> >> +#include "hw/qdev-properties.h"
> >> +#include "hw/qdev-properties-system.h"
> >> +#include "hw/virtio/vhost.h"
> >> +#include "hw/virtio/virtio.h"
> >> +#include "hw/virtio/virtio-bus.h"
> >> +#include "hw/virtio/virtio-access.h"
> >> +#include "hw/virtio/vdpa-dev.h"
> >> +#include "sysemu/sysemu.h"
> >> +#include "sysemu/runstate.h"
> >> +
> >> +static void
> >> +vhost_vdpa_device_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
> >> +{
> >> +    /* Nothing to do */
> >> +}
> >> +
> >> +static uint32_t
> >> +vhost_vdpa_device_get_u32(int fd, unsigned long int cmd, Error **errp)
> >> +{
> >> +    uint32_t val = (uint32_t)-1;
> >> +
> >> +    if (ioctl(fd, cmd, &val) < 0) {
> >> +        error_setg(errp, "vhost-vdpa-device: cmd 0x%lx failed: %s",
> >> +                   cmd, strerror(errno));
> >> +    }
> >> +
> >> +    return val;
> >> +}
> >> +
> >> +static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
> >> +{
> >> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> >> +    VhostVdpaDevice *v = VHOST_VDPA_DEVICE(vdev);
> >> +    uint16_t max_queue_size;
> >> +    struct vhost_virtqueue *vqs;
> >> +    int i, ret;
> >> +
> >> +    if (!v->vhostdev && v->vhostfd == -1) {
> >> +        error_setg(errp, "both vhostdev and vhostfd are missing");
> >> +        return;
> >> +    }
> >> +
> >> +    if (v->vhostdev && v->vhostfd != -1) {
> >> +        error_setg(errp, "both vhostdev and vhostfd are set");
> >> +        return;
> >> +    }
> >> +
> >> +    if (v->vhostfd == -1) {
> >> +        v->vhostfd = qemu_open(v->vhostdev, O_RDWR, errp);
> >> +        if (*errp) {
> >
> > Is this better to set error messages for all the possible failures
> > during realization?
> >
> I think the error messages already set in *errp, right?

Oh right.

>
> >> +            return;
> >> +        }
> >> +    }
> >> +    v->vdpa.device_fd = v->vhostfd;
> >> +
> >> +    v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
> >> +                                           VHOST_VDPA_GET_DEVICE_ID, errp);
> >> +    if (*errp) {
> >> +        goto out;
> >> +    }
> >> +
> >> +    max_queue_size = vhost_vdpa_device_get_u32(v->vhostfd,
> >> +                                               VHOST_VDPA_GET_VRING_NUM, errp);
> >> +    if (*errp) {
> >> +        goto out;
> >> +    }
> >> +
> >> +    if (v->queue_size > max_queue_size) {
> >> +        error_setg(errp, "vhost-vdpa-device: invalid queue_size: %u (max:%u)",
> >> +                   v->queue_size, max_queue_size);
> >> +        goto out;
> >> +    } else if (!v->queue_size) {
> >> +        v->queue_size = max_queue_size;
> >> +    }
> >> +
> >> +    v->num_queues = vhost_vdpa_device_get_u32(v->vhostfd,
> >> +                                              VHOST_VDPA_GET_VQS_COUNT, errp);
> >> +    if (*errp) {
> >> +        goto out;
> >> +    }
> >> +
> >> +    if (!v->num_queues || v->num_queues > VIRTIO_QUEUE_MAX) {
> >> +        error_setg(errp, "invalid number of virtqueues: %u (max:%u)",
> >> +                   v->num_queues, VIRTIO_QUEUE_MAX);
> >> +        goto out;
> >> +    }
> >> +
> >> +    v->dev.nvqs = v->num_queues;
> >> +    vqs = g_new0(struct vhost_virtqueue, v->dev.nvqs);
> >> +    v->dev.vqs = vqs;
> >> +    v->dev.vq_index = 0;
> >> +    v->dev.vq_index_end = v->dev.nvqs;
> >> +    v->dev.backend_features = 0;
> >> +    v->started = false;
> >> +
> >> +    ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
> >> +    if (ret < 0) {
> >> +        error_setg(errp, "vhost-vdpa-device: vhost initialization failed: %s",
> >> +                   strerror(-ret));
> >> +        goto free_vqs;
> >> +    }
> >> +
> >> +    v->config_size = vhost_vdpa_device_get_u32(v->vhostfd,
> >> +                                               VHOST_VDPA_GET_CONFIG_SIZE, errp);
> >> +    if (*errp) {
> >> +        goto vhost_cleanup;
> >> +    }
> >> +
> >> +    if (v->post_init && v->post_init(v, errp) < 0) {
> >> +        goto free_virtio;
> >> +    }
> >> +
> >> +    v->config = g_malloc0(v->config_size);
> >> +
> >> +    ret = vhost_dev_get_config(&v->dev, v->config, v->config_size, NULL);
> >> +    if (ret < 0) {
> >> +        error_setg(errp, "vhost-vdpa-device: get config failed");
> >> +        goto free_config;
> >> +    }
> >> +
> >> +    virtio_init(vdev, "vhost-vdpa", v->vdev_id, v->config_size);
> >> +
> >> +    v->virtqs = g_new0(VirtQueue *, v->dev.nvqs);
> >> +    for (i = 0; i < v->dev.nvqs; i++) {
> >> +        v->virtqs[i] = virtio_add_queue(vdev, v->queue_size,
> >> +                                        vhost_vdpa_device_dummy_handle_output);
> >> +    }
> >> +
> >> +    return;
> >> +
> >> +free_virtio:
> >> +    for (i = 0; i < v->num_queues; i++) {
> >> +        virtio_delete_queue(v->virtqs[i]);
> >> +    }
> >> +    g_free(v->virtqs);
> >> +    virtio_cleanup(vdev);
> >> +free_config:
> >> +    g_free(v->config);
> >> +vhost_cleanup:
> >> +    vhost_dev_cleanup(&v->dev);
> >> +free_vqs:
> >> +    g_free(vqs);
> >> +out:
> >> +    qemu_close(v->vhostfd);
> >> +    v->vhostfd = -1;
> >> +}
> >> +
> >> +static void vhost_vdpa_device_unrealize(DeviceState *dev)
> >> +{
> >> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    int i;
> >> +
> >> +    virtio_set_status(vdev, 0);
> >> +
> >> +    for (i = 0; i < s->num_queues; i++) {
> >> +        virtio_delete_queue(s->virtqs[i]);
> >> +    }
> >> +    g_free(s->virtqs);
> >> +    virtio_cleanup(vdev);
> >> +
> >> +    g_free(s->config);
> >> +    g_free(s->dev.vqs);
> >> +    vhost_dev_cleanup(&s->dev);
> >> +    qemu_close(s->vhostfd);
> >> +    s->vhostfd = -1;
> >> +}
> >> +
> >> +static void
> >> +vhost_vdpa_device_get_config(VirtIODevice *vdev, uint8_t *config)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +
> >> +    memcpy(config, s->config, s->config_size);
> >> +}
> >> +
> >> +static void
> >> +vhost_vdpa_device_set_config(VirtIODevice *vdev, const uint8_t *config)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    int ret;
> >> +
> >> +    ret = vhost_dev_set_config(&s->dev, s->config, 0, s->config_size,
> >> +                               VHOST_SET_CONFIG_TYPE_MASTER);
> >> +    if (ret) {
> >> +        error_report("set device config space failed");
> >> +        return;
> >> +    }
> >> +}
> >> +
> >> +static uint64_t vhost_vdpa_device_get_features(VirtIODevice *vdev,
> >> +                                               uint64_t features,
> >> +                                               Error **errp)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    uint64_t backend_features = s->dev.features;
> >> +
> >> +    if (!virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM)) {
> >> +        virtio_clear_feature(&backend_features, VIRTIO_F_IOMMU_PLATFORM);
> >> +    }
> >> +
> >> +    return backend_features;
> >> +}
> >> +
> >> +static int vhost_vdpa_device_start(VirtIODevice *vdev, Error **errp)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
> >> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
> >> +    int i, ret;
> >> +
> >> +    if (!k->set_guest_notifiers) {
> >> +        error_setg(errp, "binding does not support guest notifiers");
> >> +        return -ENOSYS;
> >> +    }
> >> +
> >> +    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
> >> +    if (ret < 0) {
> >> +        error_setg_errno(errp, -ret, "Error enabling host notifiers");
> >> +        return ret;
> >> +    }
> >> +
> >> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
> >> +    if (ret < 0) {
> >> +        error_setg_errno(errp, -ret, "Error binding guest notifier");
> >> +        goto err_host_notifiers;
> >> +    }
> >> +
> >> +    s->dev.acked_features = vdev->guest_features;
> >> +
> >> +    ret = vhost_dev_start(&s->dev, vdev);
> >> +    if (ret < 0) {
> >> +        error_setg_errno(errp, -ret, "Error starting vhost");
> >> +        goto err_guest_notifiers;
> >> +    }
> >> +    s->started = true;
> >> +
> >> +    /*
> >> +     * guest_notifier_mask/pending not used yet, so just unmask
> >> +     * everything here. virtio-pci will do the right thing by
> >> +     * enabling/disabling irqfd.
> >> +     */
> >> +    for (i = 0; i < s->dev.nvqs; i++) {
> >> +        vhost_virtqueue_mask(&s->dev, vdev, i, false);
> >> +    }
> >> +
> >> +    return ret;
> >> +
> >> +err_guest_notifiers:
> >> +    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
> >> +err_host_notifiers:
> >> +    vhost_dev_disable_notifiers(&s->dev, vdev);
> >> +    return ret;
> >> +}
> >> +
> >> +static void vhost_vdpa_device_stop(VirtIODevice *vdev)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
> >> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
> >> +    int ret;
> >> +
> >> +    if (!s->started) {
> >> +        return;
> >> +    }
> >> +    s->started = false;
> >> +
> >> +    if (!k->set_guest_notifiers) {
> >> +        return;
> >> +    }
> >> +
> >> +    vhost_dev_stop(&s->dev, vdev);
> >> +
> >> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
> >> +    if (ret < 0) {
> >> +        error_report("vhost guest notifier cleanup failed: %d", ret);
> >> +        return;
> >> +    }
> >> +
> >> +    vhost_dev_disable_notifiers(&s->dev, vdev);
> >> +}
> >> +
> >> +static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    bool should_start = virtio_device_started(vdev, status);
> >> +    Error *local_err = NULL;
> >> +    int ret;
> >> +
> >> +    if (!vdev->vm_running) {
> >> +        should_start = false;
> >> +    }
> >> +
> >> +    if (s->started == should_start) {
> >> +        return;
> >> +    }
> >> +
> >> +    if (should_start) {
> >> +        ret = vhost_vdpa_device_start(vdev, &local_err);
> >> +        if (ret < 0) {
> >> +            error_reportf_err(local_err, "vhost-vdpa-device: start failed: ");
> >> +        }
> >> +    } else {
> >> +        vhost_vdpa_device_stop(vdev);
> >> +    }
> >> +}
> >> +
> >> +static Property vhost_vdpa_device_properties[] = {
> >> +    DEFINE_PROP_STRING("vhostdev", VhostVdpaDevice, vhostdev),
> >> +    DEFINE_PROP_INT32("vhostfd", VhostVdpaDevice, vhostfd, -1),
> >
> > This is probably not needed since we can "abuse" /dev/fd/X for vhostdev.
> >
> It seems "vhostdev" is enough. I prefer to remove "vhostfd" if there is
> no objection.

Yes, it is the way the current vhost-vDPA networking backend did.

Thanks

>
> Thanks.
>
> > Thanks
> >
> >> +    DEFINE_PROP_UINT16("queue-size", VhostVdpaDevice, queue_size, 0),
> >> +    DEFINE_PROP_END_OF_LIST(),
> >> +};
> >> +
> >> +static const VMStateDescription vmstate_vhost_vdpa_device = {
> >> +    .name = "vhost-vdpa-device",
> >> +    .unmigratable = 1,
> >> +    .minimum_version_id = 1,
> >> +    .version_id = 1,
> >> +    .fields = (VMStateField[]) {
> >> +        VMSTATE_VIRTIO_DEVICE,
> >> +        VMSTATE_END_OF_LIST()
> >> +    },
> >> +};
> >> +
> >> +static void vhost_vdpa_device_class_init(ObjectClass *klass, void *data)
> >> +{
> >> +    DeviceClass *dc = DEVICE_CLASS(klass);
> >> +    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
> >> +
> >> +    device_class_set_props(dc, vhost_vdpa_device_properties);
> >> +    dc->desc = "VDPA-based generic device assignment";
> >> +    dc->vmsd = &vmstate_vhost_vdpa_device;
> >> +    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
> >> +    vdc->realize = vhost_vdpa_device_realize;
> >> +    vdc->unrealize = vhost_vdpa_device_unrealize;
> >> +    vdc->get_config = vhost_vdpa_device_get_config;
> >> +    vdc->set_config = vhost_vdpa_device_set_config;
> >> +    vdc->get_features = vhost_vdpa_device_get_features;
> >> +    vdc->set_status = vhost_vdpa_device_set_status;
> >> +}
> >> +
> >> +static void vhost_vdpa_device_instance_init(Object *obj)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(obj);
> >> +
> >> +    device_add_bootindex_property(obj, &s->bootindex, "bootindex",
> >> +                                  NULL, DEVICE(obj));
> >> +}
> >> +
> >> +static const TypeInfo vhost_vdpa_device_info = {
> >> +    .name = TYPE_VHOST_VDPA_DEVICE,
> >> +    .parent = TYPE_VIRTIO_DEVICE,
> >> +    .instance_size = sizeof(VhostVdpaDevice),
> >> +    .class_init = vhost_vdpa_device_class_init,
> >> +    .instance_init = vhost_vdpa_device_instance_init,
> >> +};
> >> +
> >> +static void register_vhost_vdpa_device_type(void)
> >> +{
> >> +    type_register_static(&vhost_vdpa_device_info);
> >> +}
> >> +
> >> +type_init(register_vhost_vdpa_device_type);
> >> diff --git a/include/hw/virtio/vdpa-dev.h b/include/hw/virtio/vdpa-dev.h
> >> new file mode 100644
> >> index 0000000000..4dbf98195c
> >> --- /dev/null
> >> +++ b/include/hw/virtio/vdpa-dev.h
> >> @@ -0,0 +1,43 @@
> >> +/*
> >> + * Vhost Vdpa Device
> >> + *
> >> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
> >> + *
> >> + * Authors:
> >> + *   Longpeng <longpeng2@huawei.com>
> >> + *
> >> + * Largely based on the "vhost-user-blk.h" implemented by:
> >> + *   Changpeng Liu <changpeng.liu@intel.com>
> >> + *
> >> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
> >> + * See the COPYING.LIB file in the top-level directory.
> >> + */
> >> +#ifndef _VHOST_VDPA_DEVICE_H
> >> +#define _VHOST_VDPA_DEVICE_H
> >> +
> >> +#include "hw/virtio/vhost.h"
> >> +#include "hw/virtio/vhost-vdpa.h"
> >> +#include "qom/object.h"
> >> +
> >> +
> >> +#define TYPE_VHOST_VDPA_DEVICE "vhost-vdpa-device"
> >> +OBJECT_DECLARE_SIMPLE_TYPE(VhostVdpaDevice, VHOST_VDPA_DEVICE)
> >> +
> >> +struct VhostVdpaDevice {
> >> +    VirtIODevice parent_obj;
> >> +    char *vhostdev;
> >> +    int vhostfd;
> >> +    int32_t bootindex;
> >> +    uint32_t vdev_id;
> >> +    uint32_t num_queues;
> >> +    struct vhost_dev dev;
> >> +    struct vhost_vdpa vdpa;
> >> +    VirtQueue **virtqs;
> >> +    uint8_t *config;
> >> +    int config_size;
> >> +    uint16_t queue_size;
> >> +    bool started;
> >> +    int (*post_init)(VhostVdpaDevice *v, Error **errp);
> >> +};
> >> +
> >> +#endif
> >> --
> >> 2.23.0
> >>
> >
> > .
>

Re: [PATCH v4 3/4] vdpa: add vdpa-dev support

[longpeng2--- via]

在 2022/5/11 16:55, Jason Wang 写道:
> On Wed, May 11, 2022 at 2:10 PM Longpeng (Mike, Cloud Infrastructure
> Service Product Dept.) <longpeng2@huawei.com> wrote:
>>
>>
>>
>> 在 2022/5/11 10:56, Jason Wang 写道:
>>> On Tue, May 10, 2022 at 8:59 PM Longpeng(Mike) <longpeng2@huawei.com> wrote:
>>>>
>>>> From: Longpeng <longpeng2@huawei.com>
>>>>
>>>> Supports vdpa-dev.
>>>>
>>>> Signed-off-by: Longpeng <longpeng2@huawei.com>
>>>> ---
>>>>    hw/virtio/Kconfig            |   5 +
>>>>    hw/virtio/meson.build        |   1 +
>>>>    hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
>>>>    include/hw/virtio/vdpa-dev.h |  43 ++++
>>>>    4 files changed, 434 insertions(+)
>>>>    create mode 100644 hw/virtio/vdpa-dev.c
>>>>    create mode 100644 include/hw/virtio/vdpa-dev.h
>>>>
>>>> diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
>>>> index c144d42f9b..2723283382 100644
>>>> --- a/hw/virtio/Kconfig
>>>> +++ b/hw/virtio/Kconfig
>>>> @@ -68,3 +68,8 @@ config VHOST_USER_RNG
>>>>        bool
>>>>        default y
>>>>        depends on VIRTIO && VHOST_USER
>>>> +
>>>> +config VHOST_VDPA_DEV
>>>> +    bool
>>>> +    default y if VIRTIO_PCI
>>>
>>> Do we have the plan to add VIRTIO_MMIO support?
>>>
>> There is currently no plan. Maybe we can try to support it in the next step.
> 
> That would be better, allowing MMIO on top of vhost-vDPA is considered
> to be one of the important advantages.
> 
OK, I've done some simple tests, and it works fine.
I'll send v5 later.

>>
>>>> +    depends on VIRTIO && VHOST_VDPA && LINUX
>>>> diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
>>>> index 67dc77e00f..8f6f86db71 100644
>>>> --- a/hw/virtio/meson.build
>>>> +++ b/hw/virtio/meson.build
>>>> @@ -29,6 +29,7 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
>>>>    virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c'))
>>>>    virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
>>>>    virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c'))
>>>> +virtio_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev.c'))
>>>>
>>>>    virtio_pci_ss = ss.source_set()
>>>>    virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c'))
>>>> diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
>>>> new file mode 100644
>>>> index 0000000000..543b5b4b81
>>>> --- /dev/null
>>>> +++ b/hw/virtio/vdpa-dev.c
>>>> @@ -0,0 +1,385 @@
>>>> +/*
>>>> + * Vhost Vdpa Device
>>>> + *
>>>> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
>>>> + *
>>>> + * Authors:
>>>> + *   Longpeng <longpeng2@huawei.com>
>>>> + *
>>>> + * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
>>>> + *   Changpeng Liu <changpeng.liu@intel.com>
>>>> + *
>>>> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
>>>> + * See the COPYING.LIB file in the top-level directory.
>>>> + */
>>>> +#include "qemu/osdep.h"
>>>> +#include <sys/ioctl.h>
>>>> +#include <linux/vhost.h>
>>>> +#include "qapi/error.h"
>>>> +#include "qemu/error-report.h"
>>>> +#include "qemu/cutils.h"
>>>> +#include "hw/qdev-core.h"
>>>> +#include "hw/qdev-properties.h"
>>>> +#include "hw/qdev-properties-system.h"
>>>> +#include "hw/virtio/vhost.h"
>>>> +#include "hw/virtio/virtio.h"
>>>> +#include "hw/virtio/virtio-bus.h"
>>>> +#include "hw/virtio/virtio-access.h"
>>>> +#include "hw/virtio/vdpa-dev.h"
>>>> +#include "sysemu/sysemu.h"
>>>> +#include "sysemu/runstate.h"
>>>> +
>>>> +static void
>>>> +vhost_vdpa_device_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
>>>> +{
>>>> +    /* Nothing to do */
>>>> +}
>>>> +
>>>> +static uint32_t
>>>> +vhost_vdpa_device_get_u32(int fd, unsigned long int cmd, Error **errp)
>>>> +{
>>>> +    uint32_t val = (uint32_t)-1;
>>>> +
>>>> +    if (ioctl(fd, cmd, &val) < 0) {
>>>> +        error_setg(errp, "vhost-vdpa-device: cmd 0x%lx failed: %s",
>>>> +                   cmd, strerror(errno));
>>>> +    }
>>>> +
>>>> +    return val;
>>>> +}
>>>> +
>>>> +static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
>>>> +{
>>>> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>>>> +    VhostVdpaDevice *v = VHOST_VDPA_DEVICE(vdev);
>>>> +    uint16_t max_queue_size;
>>>> +    struct vhost_virtqueue *vqs;
>>>> +    int i, ret;
>>>> +
>>>> +    if (!v->vhostdev && v->vhostfd == -1) {
>>>> +        error_setg(errp, "both vhostdev and vhostfd are missing");
>>>> +        return;
>>>> +    }
>>>> +
>>>> +    if (v->vhostdev && v->vhostfd != -1) {
>>>> +        error_setg(errp, "both vhostdev and vhostfd are set");
>>>> +        return;
>>>> +    }
>>>> +
>>>> +    if (v->vhostfd == -1) {
>>>> +        v->vhostfd = qemu_open(v->vhostdev, O_RDWR, errp);
>>>> +        if (*errp) {
>>>
>>> Is this better to set error messages for all the possible failures
>>> during realization?
>>>
>> I think the error messages already set in *errp, right?
> 
> Oh right.
> 
>>
>>>> +            return;
>>>> +        }
>>>> +    }
>>>> +    v->vdpa.device_fd = v->vhostfd;
>>>> +
>>>> +    v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
>>>> +                                           VHOST_VDPA_GET_DEVICE_ID, errp);
>>>> +    if (*errp) {
>>>> +        goto out;
>>>> +    }
>>>> +
>>>> +    max_queue_size = vhost_vdpa_device_get_u32(v->vhostfd,
>>>> +                                               VHOST_VDPA_GET_VRING_NUM, errp);
>>>> +    if (*errp) {
>>>> +        goto out;
>>>> +    }
>>>> +
>>>> +    if (v->queue_size > max_queue_size) {
>>>> +        error_setg(errp, "vhost-vdpa-device: invalid queue_size: %u (max:%u)",
>>>> +                   v->queue_size, max_queue_size);
>>>> +        goto out;
>>>> +    } else if (!v->queue_size) {
>>>> +        v->queue_size = max_queue_size;
>>>> +    }
>>>> +
>>>> +    v->num_queues = vhost_vdpa_device_get_u32(v->vhostfd,
>>>> +                                              VHOST_VDPA_GET_VQS_COUNT, errp);
>>>> +    if (*errp) {
>>>> +        goto out;
>>>> +    }
>>>> +
>>>> +    if (!v->num_queues || v->num_queues > VIRTIO_QUEUE_MAX) {
>>>> +        error_setg(errp, "invalid number of virtqueues: %u (max:%u)",
>>>> +                   v->num_queues, VIRTIO_QUEUE_MAX);
>>>> +        goto out;
>>>> +    }
>>>> +
>>>> +    v->dev.nvqs = v->num_queues;
>>>> +    vqs = g_new0(struct vhost_virtqueue, v->dev.nvqs);
>>>> +    v->dev.vqs = vqs;
>>>> +    v->dev.vq_index = 0;
>>>> +    v->dev.vq_index_end = v->dev.nvqs;
>>>> +    v->dev.backend_features = 0;
>>>> +    v->started = false;
>>>> +
>>>> +    ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
>>>> +    if (ret < 0) {
>>>> +        error_setg(errp, "vhost-vdpa-device: vhost initialization failed: %s",
>>>> +                   strerror(-ret));
>>>> +        goto free_vqs;
>>>> +    }
>>>> +
>>>> +    v->config_size = vhost_vdpa_device_get_u32(v->vhostfd,
>>>> +                                               VHOST_VDPA_GET_CONFIG_SIZE, errp);
>>>> +    if (*errp) {
>>>> +        goto vhost_cleanup;
>>>> +    }
>>>> +
>>>> +    if (v->post_init && v->post_init(v, errp) < 0) {
>>>> +        goto free_virtio;
>>>> +    }
>>>> +
>>>> +    v->config = g_malloc0(v->config_size);
>>>> +
>>>> +    ret = vhost_dev_get_config(&v->dev, v->config, v->config_size, NULL);
>>>> +    if (ret < 0) {
>>>> +        error_setg(errp, "vhost-vdpa-device: get config failed");
>>>> +        goto free_config;
>>>> +    }
>>>> +
>>>> +    virtio_init(vdev, "vhost-vdpa", v->vdev_id, v->config_size);
>>>> +
>>>> +    v->virtqs = g_new0(VirtQueue *, v->dev.nvqs);
>>>> +    for (i = 0; i < v->dev.nvqs; i++) {
>>>> +        v->virtqs[i] = virtio_add_queue(vdev, v->queue_size,
>>>> +                                        vhost_vdpa_device_dummy_handle_output);
>>>> +    }
>>>> +
>>>> +    return;
>>>> +
>>>> +free_virtio:
>>>> +    for (i = 0; i < v->num_queues; i++) {
>>>> +        virtio_delete_queue(v->virtqs[i]);
>>>> +    }
>>>> +    g_free(v->virtqs);
>>>> +    virtio_cleanup(vdev);
>>>> +free_config:
>>>> +    g_free(v->config);
>>>> +vhost_cleanup:
>>>> +    vhost_dev_cleanup(&v->dev);
>>>> +free_vqs:
>>>> +    g_free(vqs);
>>>> +out:
>>>> +    qemu_close(v->vhostfd);
>>>> +    v->vhostfd = -1;
>>>> +}
>>>> +
>>>> +static void vhost_vdpa_device_unrealize(DeviceState *dev)
>>>> +{
>>>> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>>>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>>>> +    int i;
>>>> +
>>>> +    virtio_set_status(vdev, 0);
>>>> +
>>>> +    for (i = 0; i < s->num_queues; i++) {
>>>> +        virtio_delete_queue(s->virtqs[i]);
>>>> +    }
>>>> +    g_free(s->virtqs);
>>>> +    virtio_cleanup(vdev);
>>>> +
>>>> +    g_free(s->config);
>>>> +    g_free(s->dev.vqs);
>>>> +    vhost_dev_cleanup(&s->dev);
>>>> +    qemu_close(s->vhostfd);
>>>> +    s->vhostfd = -1;
>>>> +}
>>>> +
>>>> +static void
>>>> +vhost_vdpa_device_get_config(VirtIODevice *vdev, uint8_t *config)
>>>> +{
>>>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>>>> +
>>>> +    memcpy(config, s->config, s->config_size);
>>>> +}
>>>> +
>>>> +static void
>>>> +vhost_vdpa_device_set_config(VirtIODevice *vdev, const uint8_t *config)
>>>> +{
>>>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>>>> +    int ret;
>>>> +
>>>> +    ret = vhost_dev_set_config(&s->dev, s->config, 0, s->config_size,
>>>> +                               VHOST_SET_CONFIG_TYPE_MASTER);
>>>> +    if (ret) {
>>>> +        error_report("set device config space failed");
>>>> +        return;
>>>> +    }
>>>> +}
>>>> +
>>>> +static uint64_t vhost_vdpa_device_get_features(VirtIODevice *vdev,
>>>> +                                               uint64_t features,
>>>> +                                               Error **errp)
>>>> +{
>>>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>>>> +    uint64_t backend_features = s->dev.features;
>>>> +
>>>> +    if (!virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM)) {
>>>> +        virtio_clear_feature(&backend_features, VIRTIO_F_IOMMU_PLATFORM);
>>>> +    }
>>>> +
>>>> +    return backend_features;
>>>> +}
>>>> +
>>>> +static int vhost_vdpa_device_start(VirtIODevice *vdev, Error **errp)
>>>> +{
>>>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>>>> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
>>>> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>>>> +    int i, ret;
>>>> +
>>>> +    if (!k->set_guest_notifiers) {
>>>> +        error_setg(errp, "binding does not support guest notifiers");
>>>> +        return -ENOSYS;
>>>> +    }
>>>> +
>>>> +    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
>>>> +    if (ret < 0) {
>>>> +        error_setg_errno(errp, -ret, "Error enabling host notifiers");
>>>> +        return ret;
>>>> +    }
>>>> +
>>>> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
>>>> +    if (ret < 0) {
>>>> +        error_setg_errno(errp, -ret, "Error binding guest notifier");
>>>> +        goto err_host_notifiers;
>>>> +    }
>>>> +
>>>> +    s->dev.acked_features = vdev->guest_features;
>>>> +
>>>> +    ret = vhost_dev_start(&s->dev, vdev);
>>>> +    if (ret < 0) {
>>>> +        error_setg_errno(errp, -ret, "Error starting vhost");
>>>> +        goto err_guest_notifiers;
>>>> +    }
>>>> +    s->started = true;
>>>> +
>>>> +    /*
>>>> +     * guest_notifier_mask/pending not used yet, so just unmask
>>>> +     * everything here. virtio-pci will do the right thing by
>>>> +     * enabling/disabling irqfd.
>>>> +     */
>>>> +    for (i = 0; i < s->dev.nvqs; i++) {
>>>> +        vhost_virtqueue_mask(&s->dev, vdev, i, false);
>>>> +    }
>>>> +
>>>> +    return ret;
>>>> +
>>>> +err_guest_notifiers:
>>>> +    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
>>>> +err_host_notifiers:
>>>> +    vhost_dev_disable_notifiers(&s->dev, vdev);
>>>> +    return ret;
>>>> +}
>>>> +
>>>> +static void vhost_vdpa_device_stop(VirtIODevice *vdev)
>>>> +{
>>>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>>>> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
>>>> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>>>> +    int ret;
>>>> +
>>>> +    if (!s->started) {
>>>> +        return;
>>>> +    }
>>>> +    s->started = false;
>>>> +
>>>> +    if (!k->set_guest_notifiers) {
>>>> +        return;
>>>> +    }
>>>> +
>>>> +    vhost_dev_stop(&s->dev, vdev);
>>>> +
>>>> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
>>>> +    if (ret < 0) {
>>>> +        error_report("vhost guest notifier cleanup failed: %d", ret);
>>>> +        return;
>>>> +    }
>>>> +
>>>> +    vhost_dev_disable_notifiers(&s->dev, vdev);
>>>> +}
>>>> +
>>>> +static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
>>>> +{
>>>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>>>> +    bool should_start = virtio_device_started(vdev, status);
>>>> +    Error *local_err = NULL;
>>>> +    int ret;
>>>> +
>>>> +    if (!vdev->vm_running) {
>>>> +        should_start = false;
>>>> +    }
>>>> +
>>>> +    if (s->started == should_start) {
>>>> +        return;
>>>> +    }
>>>> +
>>>> +    if (should_start) {
>>>> +        ret = vhost_vdpa_device_start(vdev, &local_err);
>>>> +        if (ret < 0) {
>>>> +            error_reportf_err(local_err, "vhost-vdpa-device: start failed: ");
>>>> +        }
>>>> +    } else {
>>>> +        vhost_vdpa_device_stop(vdev);
>>>> +    }
>>>> +}
>>>> +
>>>> +static Property vhost_vdpa_device_properties[] = {
>>>> +    DEFINE_PROP_STRING("vhostdev", VhostVdpaDevice, vhostdev),
>>>> +    DEFINE_PROP_INT32("vhostfd", VhostVdpaDevice, vhostfd, -1),
>>>
>>> This is probably not needed since we can "abuse" /dev/fd/X for vhostdev.
>>>
>> It seems "vhostdev" is enough. I prefer to remove "vhostfd" if there is
>> no objection.
> 
> Yes, it is the way the current vhost-vDPA networking backend did.
> 
> Thanks
> 
>>
>> Thanks.
>>
>>> Thanks
>>>
>>>> +    DEFINE_PROP_UINT16("queue-size", VhostVdpaDevice, queue_size, 0),
>>>> +    DEFINE_PROP_END_OF_LIST(),
>>>> +};
>>>> +
>>>> +static const VMStateDescription vmstate_vhost_vdpa_device = {
>>>> +    .name = "vhost-vdpa-device",
>>>> +    .unmigratable = 1,
>>>> +    .minimum_version_id = 1,
>>>> +    .version_id = 1,
>>>> +    .fields = (VMStateField[]) {
>>>> +        VMSTATE_VIRTIO_DEVICE,
>>>> +        VMSTATE_END_OF_LIST()
>>>> +    },
>>>> +};
>>>> +
>>>> +static void vhost_vdpa_device_class_init(ObjectClass *klass, void *data)
>>>> +{
>>>> +    DeviceClass *dc = DEVICE_CLASS(klass);
>>>> +    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
>>>> +
>>>> +    device_class_set_props(dc, vhost_vdpa_device_properties);
>>>> +    dc->desc = "VDPA-based generic device assignment";
>>>> +    dc->vmsd = &vmstate_vhost_vdpa_device;
>>>> +    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
>>>> +    vdc->realize = vhost_vdpa_device_realize;
>>>> +    vdc->unrealize = vhost_vdpa_device_unrealize;
>>>> +    vdc->get_config = vhost_vdpa_device_get_config;
>>>> +    vdc->set_config = vhost_vdpa_device_set_config;
>>>> +    vdc->get_features = vhost_vdpa_device_get_features;
>>>> +    vdc->set_status = vhost_vdpa_device_set_status;
>>>> +}
>>>> +
>>>> +static void vhost_vdpa_device_instance_init(Object *obj)
>>>> +{
>>>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(obj);
>>>> +
>>>> +    device_add_bootindex_property(obj, &s->bootindex, "bootindex",
>>>> +                                  NULL, DEVICE(obj));
>>>> +}
>>>> +
>>>> +static const TypeInfo vhost_vdpa_device_info = {
>>>> +    .name = TYPE_VHOST_VDPA_DEVICE,
>>>> +    .parent = TYPE_VIRTIO_DEVICE,
>>>> +    .instance_size = sizeof(VhostVdpaDevice),
>>>> +    .class_init = vhost_vdpa_device_class_init,
>>>> +    .instance_init = vhost_vdpa_device_instance_init,
>>>> +};
>>>> +
>>>> +static void register_vhost_vdpa_device_type(void)
>>>> +{
>>>> +    type_register_static(&vhost_vdpa_device_info);
>>>> +}
>>>> +
>>>> +type_init(register_vhost_vdpa_device_type);
>>>> diff --git a/include/hw/virtio/vdpa-dev.h b/include/hw/virtio/vdpa-dev.h
>>>> new file mode 100644
>>>> index 0000000000..4dbf98195c
>>>> --- /dev/null
>>>> +++ b/include/hw/virtio/vdpa-dev.h
>>>> @@ -0,0 +1,43 @@
>>>> +/*
>>>> + * Vhost Vdpa Device
>>>> + *
>>>> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
>>>> + *
>>>> + * Authors:
>>>> + *   Longpeng <longpeng2@huawei.com>
>>>> + *
>>>> + * Largely based on the "vhost-user-blk.h" implemented by:
>>>> + *   Changpeng Liu <changpeng.liu@intel.com>
>>>> + *
>>>> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
>>>> + * See the COPYING.LIB file in the top-level directory.
>>>> + */
>>>> +#ifndef _VHOST_VDPA_DEVICE_H
>>>> +#define _VHOST_VDPA_DEVICE_H
>>>> +
>>>> +#include "hw/virtio/vhost.h"
>>>> +#include "hw/virtio/vhost-vdpa.h"
>>>> +#include "qom/object.h"
>>>> +
>>>> +
>>>> +#define TYPE_VHOST_VDPA_DEVICE "vhost-vdpa-device"
>>>> +OBJECT_DECLARE_SIMPLE_TYPE(VhostVdpaDevice, VHOST_VDPA_DEVICE)
>>>> +
>>>> +struct VhostVdpaDevice {
>>>> +    VirtIODevice parent_obj;
>>>> +    char *vhostdev;
>>>> +    int vhostfd;
>>>> +    int32_t bootindex;
>>>> +    uint32_t vdev_id;
>>>> +    uint32_t num_queues;
>>>> +    struct vhost_dev dev;
>>>> +    struct vhost_vdpa vdpa;
>>>> +    VirtQueue **virtqs;
>>>> +    uint8_t *config;
>>>> +    int config_size;
>>>> +    uint16_t queue_size;
>>>> +    bool started;
>>>> +    int (*post_init)(VhostVdpaDevice *v, Error **errp);
>>>> +};
>>>> +
>>>> +#endif
>>>> --
>>>> 2.23.0
>>>>
>>>
>>> .
>>
> 
> .

Re: [PATCH v4 3/4] vdpa: add vdpa-dev support

[Stefano Garzarella]

On Wed, May 11, 2022 at 10:56:02AM +0800, Jason Wang wrote:
>On Tue, May 10, 2022 at 8:59 PM Longpeng(Mike) <longpeng2@huawei.com> wrote:
>>
>> From: Longpeng <longpeng2@huawei.com>
>>
>> Supports vdpa-dev.
>>
>> Signed-off-by: Longpeng <longpeng2@huawei.com>
>> ---
>>  hw/virtio/Kconfig            |   5 +
>>  hw/virtio/meson.build        |   1 +
>>  hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
>>  include/hw/virtio/vdpa-dev.h |  43 ++++
>>  4 files changed, 434 insertions(+)
>>  create mode 100644 hw/virtio/vdpa-dev.c
>>  create mode 100644 include/hw/virtio/vdpa-dev.h
>>
>> diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
>> index c144d42f9b..2723283382 100644
>> --- a/hw/virtio/Kconfig
>> +++ b/hw/virtio/Kconfig
>> @@ -68,3 +68,8 @@ config VHOST_USER_RNG
>>      bool
>>      default y
>>      depends on VIRTIO && VHOST_USER
>> +
>> +config VHOST_VDPA_DEV
>> +    bool
>> +    default y if VIRTIO_PCI
>
>Do we have the plan to add VIRTIO_MMIO support?
>
>> +    depends on VIRTIO && VHOST_VDPA && LINUX
>> diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
>> index 67dc77e00f..8f6f86db71 100644
>> --- a/hw/virtio/meson.build
>> +++ b/hw/virtio/meson.build
>> @@ -29,6 +29,7 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
>>  virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c'))
>>  virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
>>  virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c'))
>> +virtio_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev.c'))
>>
>>  virtio_pci_ss = ss.source_set()
>>  virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c'))
>> diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
>> new file mode 100644
>> index 0000000000..543b5b4b81
>> --- /dev/null
>> +++ b/hw/virtio/vdpa-dev.c
>> @@ -0,0 +1,385 @@
>> +/*
>> + * Vhost Vdpa Device
>> + *
>> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
>> + *
>> + * Authors:
>> + *   Longpeng <longpeng2@huawei.com>
>> + *
>> + * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
>> + *   Changpeng Liu <changpeng.liu@intel.com>
>> + *
>> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
>> + * See the COPYING.LIB file in the top-level directory.
>> + */
>> +#include "qemu/osdep.h"
>> +#include <sys/ioctl.h>
>> +#include <linux/vhost.h>
>> +#include "qapi/error.h"
>> +#include "qemu/error-report.h"
>> +#include "qemu/cutils.h"
>> +#include "hw/qdev-core.h"
>> +#include "hw/qdev-properties.h"
>> +#include "hw/qdev-properties-system.h"
>> +#include "hw/virtio/vhost.h"
>> +#include "hw/virtio/virtio.h"
>> +#include "hw/virtio/virtio-bus.h"
>> +#include "hw/virtio/virtio-access.h"
>> +#include "hw/virtio/vdpa-dev.h"
>> +#include "sysemu/sysemu.h"
>> +#include "sysemu/runstate.h"
>> +
>> +static void
>> +vhost_vdpa_device_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
>> +{
>> +    /* Nothing to do */
>> +}
>> +
>> +static uint32_t
>> +vhost_vdpa_device_get_u32(int fd, unsigned long int cmd, Error **errp)
>> +{
>> +    uint32_t val = (uint32_t)-1;
>> +
>> +    if (ioctl(fd, cmd, &val) < 0) {
>> +        error_setg(errp, "vhost-vdpa-device: cmd 0x%lx failed: %s",
>> +                   cmd, strerror(errno));
>> +    }
>> +
>> +    return val;
>> +}
>> +
>> +static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
>> +{
>> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>> +    VhostVdpaDevice *v = VHOST_VDPA_DEVICE(vdev);
>> +    uint16_t max_queue_size;
>> +    struct vhost_virtqueue *vqs;
>> +    int i, ret;
>> +
>> +    if (!v->vhostdev && v->vhostfd == -1) {
>> +        error_setg(errp, "both vhostdev and vhostfd are missing");
>> +        return;
>> +    }
>> +
>> +    if (v->vhostdev && v->vhostfd != -1) {
>> +        error_setg(errp, "both vhostdev and vhostfd are set");
>> +        return;
>> +    }
>> +
>> +    if (v->vhostfd == -1) {
>> +        v->vhostfd = qemu_open(v->vhostdev, O_RDWR, errp);
>> +        if (*errp) {
>
>Is this better to set error messages for all the possible failures
>during realization?
>
>> +            return;
>> +        }
>> +    }
>> +    v->vdpa.device_fd = v->vhostfd;
>> +
>> +    v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
>> +                                           VHOST_VDPA_GET_DEVICE_ID, errp);
>> +    if (*errp) {
>> +        goto out;
>> +    }
>> +
>> +    max_queue_size = vhost_vdpa_device_get_u32(v->vhostfd,
>> +                                               VHOST_VDPA_GET_VRING_NUM, errp);
>> +    if (*errp) {
>> +        goto out;
>> +    }
>> +
>> +    if (v->queue_size > max_queue_size) {
>> +        error_setg(errp, "vhost-vdpa-device: invalid queue_size: %u (max:%u)",
>> +                   v->queue_size, max_queue_size);
>> +        goto out;
>> +    } else if (!v->queue_size) {
>> +        v->queue_size = max_queue_size;
>> +    }
>> +
>> +    v->num_queues = vhost_vdpa_device_get_u32(v->vhostfd,
>> +                                              VHOST_VDPA_GET_VQS_COUNT, errp);
>> +    if (*errp) {
>> +        goto out;
>> +    }
>> +
>> +    if (!v->num_queues || v->num_queues > VIRTIO_QUEUE_MAX) {
>> +        error_setg(errp, "invalid number of virtqueues: %u (max:%u)",
>> +                   v->num_queues, VIRTIO_QUEUE_MAX);
>> +        goto out;
>> +    }
>> +
>> +    v->dev.nvqs = v->num_queues;
>> +    vqs = g_new0(struct vhost_virtqueue, v->dev.nvqs);
>> +    v->dev.vqs = vqs;
>> +    v->dev.vq_index = 0;
>> +    v->dev.vq_index_end = v->dev.nvqs;
>> +    v->dev.backend_features = 0;
>> +    v->started = false;
>> +
>> +    ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
>> +    if (ret < 0) {
>> +        error_setg(errp, "vhost-vdpa-device: vhost initialization failed: %s",
>> +                   strerror(-ret));
>> +        goto free_vqs;
>> +    }
>> +
>> +    v->config_size = vhost_vdpa_device_get_u32(v->vhostfd,
>> +                                               VHOST_VDPA_GET_CONFIG_SIZE, errp);
>> +    if (*errp) {
>> +        goto vhost_cleanup;
>> +    }
>> +
>> +    if (v->post_init && v->post_init(v, errp) < 0) {
>> +        goto free_virtio;
>> +    }
>> +
>> +    v->config = g_malloc0(v->config_size);
>> +
>> +    ret = vhost_dev_get_config(&v->dev, v->config, v->config_size, NULL);
>> +    if (ret < 0) {
>> +        error_setg(errp, "vhost-vdpa-device: get config failed");
>> +        goto free_config;
>> +    }
>> +
>> +    virtio_init(vdev, "vhost-vdpa", v->vdev_id, v->config_size);
>> +
>> +    v->virtqs = g_new0(VirtQueue *, v->dev.nvqs);
>> +    for (i = 0; i < v->dev.nvqs; i++) {
>> +        v->virtqs[i] = virtio_add_queue(vdev, v->queue_size,
>> +                                        vhost_vdpa_device_dummy_handle_output);
>> +    }
>> +
>> +    return;
>> +
>> +free_virtio:
>> +    for (i = 0; i < v->num_queues; i++) {
>> +        virtio_delete_queue(v->virtqs[i]);
>> +    }
>> +    g_free(v->virtqs);
>> +    virtio_cleanup(vdev);
>> +free_config:
>> +    g_free(v->config);
>> +vhost_cleanup:
>> +    vhost_dev_cleanup(&v->dev);
>> +free_vqs:
>> +    g_free(vqs);
>> +out:
>> +    qemu_close(v->vhostfd);
>> +    v->vhostfd = -1;
>> +}
>> +
>> +static void vhost_vdpa_device_unrealize(DeviceState *dev)
>> +{
>> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    int i;
>> +
>> +    virtio_set_status(vdev, 0);
>> +
>> +    for (i = 0; i < s->num_queues; i++) {
>> +        virtio_delete_queue(s->virtqs[i]);
>> +    }
>> +    g_free(s->virtqs);
>> +    virtio_cleanup(vdev);
>> +
>> +    g_free(s->config);
>> +    g_free(s->dev.vqs);
>> +    vhost_dev_cleanup(&s->dev);
>> +    qemu_close(s->vhostfd);
>> +    s->vhostfd = -1;
>> +}
>> +
>> +static void
>> +vhost_vdpa_device_get_config(VirtIODevice *vdev, uint8_t *config)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +
>> +    memcpy(config, s->config, s->config_size);
>> +}
>> +
>> +static void
>> +vhost_vdpa_device_set_config(VirtIODevice *vdev, const uint8_t *config)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    int ret;
>> +
>> +    ret = vhost_dev_set_config(&s->dev, s->config, 0, s->config_size,
>> +                               VHOST_SET_CONFIG_TYPE_MASTER);
>> +    if (ret) {
>> +        error_report("set device config space failed");
>> +        return;
>> +    }
>> +}
>> +
>> +static uint64_t vhost_vdpa_device_get_features(VirtIODevice *vdev,
>> +                                               uint64_t features,
>> +                                               Error **errp)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    uint64_t backend_features = s->dev.features;
>> +
>> +    if (!virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM)) {
>> +        virtio_clear_feature(&backend_features, VIRTIO_F_IOMMU_PLATFORM);
>> +    }
>> +
>> +    return backend_features;
>> +}
>> +
>> +static int vhost_vdpa_device_start(VirtIODevice *vdev, Error **errp)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
>> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>> +    int i, ret;
>> +
>> +    if (!k->set_guest_notifiers) {
>> +        error_setg(errp, "binding does not support guest notifiers");
>> +        return -ENOSYS;
>> +    }
>> +
>> +    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
>> +    if (ret < 0) {
>> +        error_setg_errno(errp, -ret, "Error enabling host notifiers");
>> +        return ret;
>> +    }
>> +
>> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
>> +    if (ret < 0) {
>> +        error_setg_errno(errp, -ret, "Error binding guest notifier");
>> +        goto err_host_notifiers;
>> +    }
>> +
>> +    s->dev.acked_features = vdev->guest_features;
>> +
>> +    ret = vhost_dev_start(&s->dev, vdev);
>> +    if (ret < 0) {
>> +        error_setg_errno(errp, -ret, "Error starting vhost");
>> +        goto err_guest_notifiers;
>> +    }
>> +    s->started = true;
>> +
>> +    /*
>> +     * guest_notifier_mask/pending not used yet, so just unmask
>> +     * everything here. virtio-pci will do the right thing by
>> +     * enabling/disabling irqfd.
>> +     */
>> +    for (i = 0; i < s->dev.nvqs; i++) {
>> +        vhost_virtqueue_mask(&s->dev, vdev, i, false);
>> +    }
>> +
>> +    return ret;
>> +
>> +err_guest_notifiers:
>> +    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
>> +err_host_notifiers:
>> +    vhost_dev_disable_notifiers(&s->dev, vdev);
>> +    return ret;
>> +}
>> +
>> +static void vhost_vdpa_device_stop(VirtIODevice *vdev)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
>> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>> +    int ret;
>> +
>> +    if (!s->started) {
>> +        return;
>> +    }
>> +    s->started = false;
>> +
>> +    if (!k->set_guest_notifiers) {
>> +        return;
>> +    }
>> +
>> +    vhost_dev_stop(&s->dev, vdev);
>> +
>> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
>> +    if (ret < 0) {
>> +        error_report("vhost guest notifier cleanup failed: %d", ret);
>> +        return;
>> +    }
>> +
>> +    vhost_dev_disable_notifiers(&s->dev, vdev);
>> +}
>> +
>> +static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
>> +{
>> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> +    bool should_start = virtio_device_started(vdev, status);
>> +    Error *local_err = NULL;
>> +    int ret;
>> +
>> +    if (!vdev->vm_running) {
>> +        should_start = false;
>> +    }
>> +
>> +    if (s->started == should_start) {
>> +        return;
>> +    }
>> +
>> +    if (should_start) {
>> +        ret = vhost_vdpa_device_start(vdev, &local_err);
>> +        if (ret < 0) {
>> +            error_reportf_err(local_err, "vhost-vdpa-device: start failed: ");
>> +        }
>> +    } else {
>> +        vhost_vdpa_device_stop(vdev);
>> +    }
>> +}
>> +
>> +static Property vhost_vdpa_device_properties[] = {
>> +    DEFINE_PROP_STRING("vhostdev", VhostVdpaDevice, vhostdev),
>> +    DEFINE_PROP_INT32("vhostfd", VhostVdpaDevice, vhostfd, -1),
>
>This is probably not needed since we can "abuse" /dev/fd/X for 
>vhostdev.

IIRC for other vhost devices (e.g. vhost-vsock) the management layer 
(e.g. libvirt) opens the device (because I think QEMU has less 
permissions) and then passes the fd to QEMU, could this be useful for 
this scenario as well?

Thanks,
Stefano

Re: [PATCH v4 3/4] vdpa: add vdpa-dev support

[Jason Wang]

On Wed, May 11, 2022 at 2:32 PM Stefano Garzarella <sgarzare@redhat.com> wrote:
>
> On Wed, May 11, 2022 at 10:56:02AM +0800, Jason Wang wrote:
> >On Tue, May 10, 2022 at 8:59 PM Longpeng(Mike) <longpeng2@huawei.com> wrote:
> >>
> >> From: Longpeng <longpeng2@huawei.com>
> >>
> >> Supports vdpa-dev.
> >>
> >> Signed-off-by: Longpeng <longpeng2@huawei.com>
> >> ---
> >>  hw/virtio/Kconfig            |   5 +
> >>  hw/virtio/meson.build        |   1 +
> >>  hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
> >>  include/hw/virtio/vdpa-dev.h |  43 ++++
> >>  4 files changed, 434 insertions(+)
> >>  create mode 100644 hw/virtio/vdpa-dev.c
> >>  create mode 100644 include/hw/virtio/vdpa-dev.h
> >>
> >> diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
> >> index c144d42f9b..2723283382 100644
> >> --- a/hw/virtio/Kconfig
> >> +++ b/hw/virtio/Kconfig
> >> @@ -68,3 +68,8 @@ config VHOST_USER_RNG
> >>      bool
> >>      default y
> >>      depends on VIRTIO && VHOST_USER
> >> +
> >> +config VHOST_VDPA_DEV
> >> +    bool
> >> +    default y if VIRTIO_PCI
> >
> >Do we have the plan to add VIRTIO_MMIO support?
> >
> >> +    depends on VIRTIO && VHOST_VDPA && LINUX
> >> diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
> >> index 67dc77e00f..8f6f86db71 100644
> >> --- a/hw/virtio/meson.build
> >> +++ b/hw/virtio/meson.build
> >> @@ -29,6 +29,7 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
> >>  virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c'))
> >>  virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
> >>  virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c'))
> >> +virtio_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev.c'))
> >>
> >>  virtio_pci_ss = ss.source_set()
> >>  virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c'))
> >> diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
> >> new file mode 100644
> >> index 0000000000..543b5b4b81
> >> --- /dev/null
> >> +++ b/hw/virtio/vdpa-dev.c
> >> @@ -0,0 +1,385 @@
> >> +/*
> >> + * Vhost Vdpa Device
> >> + *
> >> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
> >> + *
> >> + * Authors:
> >> + *   Longpeng <longpeng2@huawei.com>
> >> + *
> >> + * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
> >> + *   Changpeng Liu <changpeng.liu@intel.com>
> >> + *
> >> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
> >> + * See the COPYING.LIB file in the top-level directory.
> >> + */
> >> +#include "qemu/osdep.h"
> >> +#include <sys/ioctl.h>
> >> +#include <linux/vhost.h>
> >> +#include "qapi/error.h"
> >> +#include "qemu/error-report.h"
> >> +#include "qemu/cutils.h"
> >> +#include "hw/qdev-core.h"
> >> +#include "hw/qdev-properties.h"
> >> +#include "hw/qdev-properties-system.h"
> >> +#include "hw/virtio/vhost.h"
> >> +#include "hw/virtio/virtio.h"
> >> +#include "hw/virtio/virtio-bus.h"
> >> +#include "hw/virtio/virtio-access.h"
> >> +#include "hw/virtio/vdpa-dev.h"
> >> +#include "sysemu/sysemu.h"
> >> +#include "sysemu/runstate.h"
> >> +
> >> +static void
> >> +vhost_vdpa_device_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
> >> +{
> >> +    /* Nothing to do */
> >> +}
> >> +
> >> +static uint32_t
> >> +vhost_vdpa_device_get_u32(int fd, unsigned long int cmd, Error **errp)
> >> +{
> >> +    uint32_t val = (uint32_t)-1;
> >> +
> >> +    if (ioctl(fd, cmd, &val) < 0) {
> >> +        error_setg(errp, "vhost-vdpa-device: cmd 0x%lx failed: %s",
> >> +                   cmd, strerror(errno));
> >> +    }
> >> +
> >> +    return val;
> >> +}
> >> +
> >> +static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
> >> +{
> >> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> >> +    VhostVdpaDevice *v = VHOST_VDPA_DEVICE(vdev);
> >> +    uint16_t max_queue_size;
> >> +    struct vhost_virtqueue *vqs;
> >> +    int i, ret;
> >> +
> >> +    if (!v->vhostdev && v->vhostfd == -1) {
> >> +        error_setg(errp, "both vhostdev and vhostfd are missing");
> >> +        return;
> >> +    }
> >> +
> >> +    if (v->vhostdev && v->vhostfd != -1) {
> >> +        error_setg(errp, "both vhostdev and vhostfd are set");
> >> +        return;
> >> +    }
> >> +
> >> +    if (v->vhostfd == -1) {
> >> +        v->vhostfd = qemu_open(v->vhostdev, O_RDWR, errp);
> >> +        if (*errp) {
> >
> >Is this better to set error messages for all the possible failures
> >during realization?
> >
> >> +            return;
> >> +        }
> >> +    }
> >> +    v->vdpa.device_fd = v->vhostfd;
> >> +
> >> +    v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
> >> +                                           VHOST_VDPA_GET_DEVICE_ID, errp);
> >> +    if (*errp) {
> >> +        goto out;
> >> +    }
> >> +
> >> +    max_queue_size = vhost_vdpa_device_get_u32(v->vhostfd,
> >> +                                               VHOST_VDPA_GET_VRING_NUM, errp);
> >> +    if (*errp) {
> >> +        goto out;
> >> +    }
> >> +
> >> +    if (v->queue_size > max_queue_size) {
> >> +        error_setg(errp, "vhost-vdpa-device: invalid queue_size: %u (max:%u)",
> >> +                   v->queue_size, max_queue_size);
> >> +        goto out;
> >> +    } else if (!v->queue_size) {
> >> +        v->queue_size = max_queue_size;
> >> +    }
> >> +
> >> +    v->num_queues = vhost_vdpa_device_get_u32(v->vhostfd,
> >> +                                              VHOST_VDPA_GET_VQS_COUNT, errp);
> >> +    if (*errp) {
> >> +        goto out;
> >> +    }
> >> +
> >> +    if (!v->num_queues || v->num_queues > VIRTIO_QUEUE_MAX) {
> >> +        error_setg(errp, "invalid number of virtqueues: %u (max:%u)",
> >> +                   v->num_queues, VIRTIO_QUEUE_MAX);
> >> +        goto out;
> >> +    }
> >> +
> >> +    v->dev.nvqs = v->num_queues;
> >> +    vqs = g_new0(struct vhost_virtqueue, v->dev.nvqs);
> >> +    v->dev.vqs = vqs;
> >> +    v->dev.vq_index = 0;
> >> +    v->dev.vq_index_end = v->dev.nvqs;
> >> +    v->dev.backend_features = 0;
> >> +    v->started = false;
> >> +
> >> +    ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
> >> +    if (ret < 0) {
> >> +        error_setg(errp, "vhost-vdpa-device: vhost initialization failed: %s",
> >> +                   strerror(-ret));
> >> +        goto free_vqs;
> >> +    }
> >> +
> >> +    v->config_size = vhost_vdpa_device_get_u32(v->vhostfd,
> >> +                                               VHOST_VDPA_GET_CONFIG_SIZE, errp);
> >> +    if (*errp) {
> >> +        goto vhost_cleanup;
> >> +    }
> >> +
> >> +    if (v->post_init && v->post_init(v, errp) < 0) {
> >> +        goto free_virtio;
> >> +    }
> >> +
> >> +    v->config = g_malloc0(v->config_size);
> >> +
> >> +    ret = vhost_dev_get_config(&v->dev, v->config, v->config_size, NULL);
> >> +    if (ret < 0) {
> >> +        error_setg(errp, "vhost-vdpa-device: get config failed");
> >> +        goto free_config;
> >> +    }
> >> +
> >> +    virtio_init(vdev, "vhost-vdpa", v->vdev_id, v->config_size);
> >> +
> >> +    v->virtqs = g_new0(VirtQueue *, v->dev.nvqs);
> >> +    for (i = 0; i < v->dev.nvqs; i++) {
> >> +        v->virtqs[i] = virtio_add_queue(vdev, v->queue_size,
> >> +                                        vhost_vdpa_device_dummy_handle_output);
> >> +    }
> >> +
> >> +    return;
> >> +
> >> +free_virtio:
> >> +    for (i = 0; i < v->num_queues; i++) {
> >> +        virtio_delete_queue(v->virtqs[i]);
> >> +    }
> >> +    g_free(v->virtqs);
> >> +    virtio_cleanup(vdev);
> >> +free_config:
> >> +    g_free(v->config);
> >> +vhost_cleanup:
> >> +    vhost_dev_cleanup(&v->dev);
> >> +free_vqs:
> >> +    g_free(vqs);
> >> +out:
> >> +    qemu_close(v->vhostfd);
> >> +    v->vhostfd = -1;
> >> +}
> >> +
> >> +static void vhost_vdpa_device_unrealize(DeviceState *dev)
> >> +{
> >> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    int i;
> >> +
> >> +    virtio_set_status(vdev, 0);
> >> +
> >> +    for (i = 0; i < s->num_queues; i++) {
> >> +        virtio_delete_queue(s->virtqs[i]);
> >> +    }
> >> +    g_free(s->virtqs);
> >> +    virtio_cleanup(vdev);
> >> +
> >> +    g_free(s->config);
> >> +    g_free(s->dev.vqs);
> >> +    vhost_dev_cleanup(&s->dev);
> >> +    qemu_close(s->vhostfd);
> >> +    s->vhostfd = -1;
> >> +}
> >> +
> >> +static void
> >> +vhost_vdpa_device_get_config(VirtIODevice *vdev, uint8_t *config)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +
> >> +    memcpy(config, s->config, s->config_size);
> >> +}
> >> +
> >> +static void
> >> +vhost_vdpa_device_set_config(VirtIODevice *vdev, const uint8_t *config)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    int ret;
> >> +
> >> +    ret = vhost_dev_set_config(&s->dev, s->config, 0, s->config_size,
> >> +                               VHOST_SET_CONFIG_TYPE_MASTER);
> >> +    if (ret) {
> >> +        error_report("set device config space failed");
> >> +        return;
> >> +    }
> >> +}
> >> +
> >> +static uint64_t vhost_vdpa_device_get_features(VirtIODevice *vdev,
> >> +                                               uint64_t features,
> >> +                                               Error **errp)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    uint64_t backend_features = s->dev.features;
> >> +
> >> +    if (!virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM)) {
> >> +        virtio_clear_feature(&backend_features, VIRTIO_F_IOMMU_PLATFORM);
> >> +    }
> >> +
> >> +    return backend_features;
> >> +}
> >> +
> >> +static int vhost_vdpa_device_start(VirtIODevice *vdev, Error **errp)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
> >> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
> >> +    int i, ret;
> >> +
> >> +    if (!k->set_guest_notifiers) {
> >> +        error_setg(errp, "binding does not support guest notifiers");
> >> +        return -ENOSYS;
> >> +    }
> >> +
> >> +    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
> >> +    if (ret < 0) {
> >> +        error_setg_errno(errp, -ret, "Error enabling host notifiers");
> >> +        return ret;
> >> +    }
> >> +
> >> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
> >> +    if (ret < 0) {
> >> +        error_setg_errno(errp, -ret, "Error binding guest notifier");
> >> +        goto err_host_notifiers;
> >> +    }
> >> +
> >> +    s->dev.acked_features = vdev->guest_features;
> >> +
> >> +    ret = vhost_dev_start(&s->dev, vdev);
> >> +    if (ret < 0) {
> >> +        error_setg_errno(errp, -ret, "Error starting vhost");
> >> +        goto err_guest_notifiers;
> >> +    }
> >> +    s->started = true;
> >> +
> >> +    /*
> >> +     * guest_notifier_mask/pending not used yet, so just unmask
> >> +     * everything here. virtio-pci will do the right thing by
> >> +     * enabling/disabling irqfd.
> >> +     */
> >> +    for (i = 0; i < s->dev.nvqs; i++) {
> >> +        vhost_virtqueue_mask(&s->dev, vdev, i, false);
> >> +    }
> >> +
> >> +    return ret;
> >> +
> >> +err_guest_notifiers:
> >> +    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
> >> +err_host_notifiers:
> >> +    vhost_dev_disable_notifiers(&s->dev, vdev);
> >> +    return ret;
> >> +}
> >> +
> >> +static void vhost_vdpa_device_stop(VirtIODevice *vdev)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
> >> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
> >> +    int ret;
> >> +
> >> +    if (!s->started) {
> >> +        return;
> >> +    }
> >> +    s->started = false;
> >> +
> >> +    if (!k->set_guest_notifiers) {
> >> +        return;
> >> +    }
> >> +
> >> +    vhost_dev_stop(&s->dev, vdev);
> >> +
> >> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
> >> +    if (ret < 0) {
> >> +        error_report("vhost guest notifier cleanup failed: %d", ret);
> >> +        return;
> >> +    }
> >> +
> >> +    vhost_dev_disable_notifiers(&s->dev, vdev);
> >> +}
> >> +
> >> +static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
> >> +{
> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
> >> +    bool should_start = virtio_device_started(vdev, status);
> >> +    Error *local_err = NULL;
> >> +    int ret;
> >> +
> >> +    if (!vdev->vm_running) {
> >> +        should_start = false;
> >> +    }
> >> +
> >> +    if (s->started == should_start) {
> >> +        return;
> >> +    }
> >> +
> >> +    if (should_start) {
> >> +        ret = vhost_vdpa_device_start(vdev, &local_err);
> >> +        if (ret < 0) {
> >> +            error_reportf_err(local_err, "vhost-vdpa-device: start failed: ");
> >> +        }
> >> +    } else {
> >> +        vhost_vdpa_device_stop(vdev);
> >> +    }
> >> +}
> >> +
> >> +static Property vhost_vdpa_device_properties[] = {
> >> +    DEFINE_PROP_STRING("vhostdev", VhostVdpaDevice, vhostdev),
> >> +    DEFINE_PROP_INT32("vhostfd", VhostVdpaDevice, vhostfd, -1),
> >
> >This is probably not needed since we can "abuse" /dev/fd/X for
> >vhostdev.
>
> IIRC for other vhost devices (e.g. vhost-vsock) the management layer
> (e.g. libvirt) opens the device (because I think QEMU has less
> permissions) and then passes the fd to QEMU, could this be useful for
> this scenario as well?

Yes, it's the way current vhost-vDPA did (the fd is passing via SCM_RIGHTS).

Thanks

>
> Thanks,
> Stefano
>

Re: [PATCH v4 3/4] vdpa: add vdpa-dev support

[Stefano Garzarella]

On Wed, May 11, 2022 at 04:56:23PM +0800, Jason Wang wrote:
>On Wed, May 11, 2022 at 2:32 PM Stefano Garzarella <sgarzare@redhat.com> wrote:
>>
>> On Wed, May 11, 2022 at 10:56:02AM +0800, Jason Wang wrote:
>> >On Tue, May 10, 2022 at 8:59 PM Longpeng(Mike) <longpeng2@huawei.com> wrote:
>> >>
>> >> From: Longpeng <longpeng2@huawei.com>
>> >>
>> >> Supports vdpa-dev.
>> >>
>> >> Signed-off-by: Longpeng <longpeng2@huawei.com>
>> >> ---
>> >>  hw/virtio/Kconfig            |   5 +
>> >>  hw/virtio/meson.build        |   1 +
>> >>  hw/virtio/vdpa-dev.c         | 385 +++++++++++++++++++++++++++++++++++
>> >>  include/hw/virtio/vdpa-dev.h |  43 ++++
>> >>  4 files changed, 434 insertions(+)
>> >>  create mode 100644 hw/virtio/vdpa-dev.c
>> >>  create mode 100644 include/hw/virtio/vdpa-dev.h
>> >>
>> >> diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
>> >> index c144d42f9b..2723283382 100644
>> >> --- a/hw/virtio/Kconfig
>> >> +++ b/hw/virtio/Kconfig
>> >> @@ -68,3 +68,8 @@ config VHOST_USER_RNG
>> >>      bool
>> >>      default y
>> >>      depends on VIRTIO && VHOST_USER
>> >> +
>> >> +config VHOST_VDPA_DEV
>> >> +    bool
>> >> +    default y if VIRTIO_PCI
>> >
>> >Do we have the plan to add VIRTIO_MMIO support?
>> >
>> >> +    depends on VIRTIO && VHOST_VDPA && LINUX
>> >> diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
>> >> index 67dc77e00f..8f6f86db71 100644
>> >> --- a/hw/virtio/meson.build
>> >> +++ b/hw/virtio/meson.build
>> >> @@ -29,6 +29,7 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
>> >>  virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c'))
>> >>  virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
>> >>  virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c'))
>> >> +virtio_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev.c'))
>> >>
>> >>  virtio_pci_ss = ss.source_set()
>> >>  virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c'))
>> >> diff --git a/hw/virtio/vdpa-dev.c b/hw/virtio/vdpa-dev.c
>> >> new file mode 100644
>> >> index 0000000000..543b5b4b81
>> >> --- /dev/null
>> >> +++ b/hw/virtio/vdpa-dev.c
>> >> @@ -0,0 +1,385 @@
>> >> +/*
>> >> + * Vhost Vdpa Device
>> >> + *
>> >> + * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
>> >> + *
>> >> + * Authors:
>> >> + *   Longpeng <longpeng2@huawei.com>
>> >> + *
>> >> + * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
>> >> + *   Changpeng Liu <changpeng.liu@intel.com>
>> >> + *
>> >> + * This work is licensed under the terms of the GNU LGPL, version 2 or later.
>> >> + * See the COPYING.LIB file in the top-level directory.
>> >> + */
>> >> +#include "qemu/osdep.h"
>> >> +#include <sys/ioctl.h>
>> >> +#include <linux/vhost.h>
>> >> +#include "qapi/error.h"
>> >> +#include "qemu/error-report.h"
>> >> +#include "qemu/cutils.h"
>> >> +#include "hw/qdev-core.h"
>> >> +#include "hw/qdev-properties.h"
>> >> +#include "hw/qdev-properties-system.h"
>> >> +#include "hw/virtio/vhost.h"
>> >> +#include "hw/virtio/virtio.h"
>> >> +#include "hw/virtio/virtio-bus.h"
>> >> +#include "hw/virtio/virtio-access.h"
>> >> +#include "hw/virtio/vdpa-dev.h"
>> >> +#include "sysemu/sysemu.h"
>> >> +#include "sysemu/runstate.h"
>> >> +
>> >> +static void
>> >> +vhost_vdpa_device_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
>> >> +{
>> >> +    /* Nothing to do */
>> >> +}
>> >> +
>> >> +static uint32_t
>> >> +vhost_vdpa_device_get_u32(int fd, unsigned long int cmd, Error **errp)
>> >> +{
>> >> +    uint32_t val = (uint32_t)-1;
>> >> +
>> >> +    if (ioctl(fd, cmd, &val) < 0) {
>> >> +        error_setg(errp, "vhost-vdpa-device: cmd 0x%lx failed: %s",
>> >> +                   cmd, strerror(errno));
>> >> +    }
>> >> +
>> >> +    return val;
>> >> +}
>> >> +
>> >> +static void vhost_vdpa_device_realize(DeviceState *dev, Error **errp)
>> >> +{
>> >> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>> >> +    VhostVdpaDevice *v = VHOST_VDPA_DEVICE(vdev);
>> >> +    uint16_t max_queue_size;
>> >> +    struct vhost_virtqueue *vqs;
>> >> +    int i, ret;
>> >> +
>> >> +    if (!v->vhostdev && v->vhostfd == -1) {
>> >> +        error_setg(errp, "both vhostdev and vhostfd are missing");
>> >> +        return;
>> >> +    }
>> >> +
>> >> +    if (v->vhostdev && v->vhostfd != -1) {
>> >> +        error_setg(errp, "both vhostdev and vhostfd are set");
>> >> +        return;
>> >> +    }
>> >> +
>> >> +    if (v->vhostfd == -1) {
>> >> +        v->vhostfd = qemu_open(v->vhostdev, O_RDWR, errp);
>> >> +        if (*errp) {
>> >
>> >Is this better to set error messages for all the possible failures
>> >during realization?
>> >
>> >> +            return;
>> >> +        }
>> >> +    }
>> >> +    v->vdpa.device_fd = v->vhostfd;
>> >> +
>> >> +    v->vdev_id = vhost_vdpa_device_get_u32(v->vhostfd,
>> >> +                                           VHOST_VDPA_GET_DEVICE_ID, errp);
>> >> +    if (*errp) {
>> >> +        goto out;
>> >> +    }
>> >> +
>> >> +    max_queue_size = vhost_vdpa_device_get_u32(v->vhostfd,
>> >> +                                               VHOST_VDPA_GET_VRING_NUM, errp);
>> >> +    if (*errp) {
>> >> +        goto out;
>> >> +    }
>> >> +
>> >> +    if (v->queue_size > max_queue_size) {
>> >> +        error_setg(errp, "vhost-vdpa-device: invalid queue_size: %u (max:%u)",
>> >> +                   v->queue_size, max_queue_size);
>> >> +        goto out;
>> >> +    } else if (!v->queue_size) {
>> >> +        v->queue_size = max_queue_size;
>> >> +    }
>> >> +
>> >> +    v->num_queues = vhost_vdpa_device_get_u32(v->vhostfd,
>> >> +                                              VHOST_VDPA_GET_VQS_COUNT, errp);
>> >> +    if (*errp) {
>> >> +        goto out;
>> >> +    }
>> >> +
>> >> +    if (!v->num_queues || v->num_queues > VIRTIO_QUEUE_MAX) {
>> >> +        error_setg(errp, "invalid number of virtqueues: %u (max:%u)",
>> >> +                   v->num_queues, VIRTIO_QUEUE_MAX);
>> >> +        goto out;
>> >> +    }
>> >> +
>> >> +    v->dev.nvqs = v->num_queues;
>> >> +    vqs = g_new0(struct vhost_virtqueue, v->dev.nvqs);
>> >> +    v->dev.vqs = vqs;
>> >> +    v->dev.vq_index = 0;
>> >> +    v->dev.vq_index_end = v->dev.nvqs;
>> >> +    v->dev.backend_features = 0;
>> >> +    v->started = false;
>> >> +
>> >> +    ret = vhost_dev_init(&v->dev, &v->vdpa, VHOST_BACKEND_TYPE_VDPA, 0, NULL);
>> >> +    if (ret < 0) {
>> >> +        error_setg(errp, "vhost-vdpa-device: vhost initialization failed: %s",
>> >> +                   strerror(-ret));
>> >> +        goto free_vqs;
>> >> +    }
>> >> +
>> >> +    v->config_size = vhost_vdpa_device_get_u32(v->vhostfd,
>> >> +                                               VHOST_VDPA_GET_CONFIG_SIZE, errp);
>> >> +    if (*errp) {
>> >> +        goto vhost_cleanup;
>> >> +    }
>> >> +
>> >> +    if (v->post_init && v->post_init(v, errp) < 0) {
>> >> +        goto free_virtio;
>> >> +    }
>> >> +
>> >> +    v->config = g_malloc0(v->config_size);
>> >> +
>> >> +    ret = vhost_dev_get_config(&v->dev, v->config, v->config_size, NULL);
>> >> +    if (ret < 0) {
>> >> +        error_setg(errp, "vhost-vdpa-device: get config failed");
>> >> +        goto free_config;
>> >> +    }
>> >> +
>> >> +    virtio_init(vdev, "vhost-vdpa", v->vdev_id, v->config_size);
>> >> +
>> >> +    v->virtqs = g_new0(VirtQueue *, v->dev.nvqs);
>> >> +    for (i = 0; i < v->dev.nvqs; i++) {
>> >> +        v->virtqs[i] = virtio_add_queue(vdev, v->queue_size,
>> >> +                                        vhost_vdpa_device_dummy_handle_output);
>> >> +    }
>> >> +
>> >> +    return;
>> >> +
>> >> +free_virtio:
>> >> +    for (i = 0; i < v->num_queues; i++) {
>> >> +        virtio_delete_queue(v->virtqs[i]);
>> >> +    }
>> >> +    g_free(v->virtqs);
>> >> +    virtio_cleanup(vdev);
>> >> +free_config:
>> >> +    g_free(v->config);
>> >> +vhost_cleanup:
>> >> +    vhost_dev_cleanup(&v->dev);
>> >> +free_vqs:
>> >> +    g_free(vqs);
>> >> +out:
>> >> +    qemu_close(v->vhostfd);
>> >> +    v->vhostfd = -1;
>> >> +}
>> >> +
>> >> +static void vhost_vdpa_device_unrealize(DeviceState *dev)
>> >> +{
>> >> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> >> +    int i;
>> >> +
>> >> +    virtio_set_status(vdev, 0);
>> >> +
>> >> +    for (i = 0; i < s->num_queues; i++) {
>> >> +        virtio_delete_queue(s->virtqs[i]);
>> >> +    }
>> >> +    g_free(s->virtqs);
>> >> +    virtio_cleanup(vdev);
>> >> +
>> >> +    g_free(s->config);
>> >> +    g_free(s->dev.vqs);
>> >> +    vhost_dev_cleanup(&s->dev);
>> >> +    qemu_close(s->vhostfd);
>> >> +    s->vhostfd = -1;
>> >> +}
>> >> +
>> >> +static void
>> >> +vhost_vdpa_device_get_config(VirtIODevice *vdev, uint8_t *config)
>> >> +{
>> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> >> +
>> >> +    memcpy(config, s->config, s->config_size);
>> >> +}
>> >> +
>> >> +static void
>> >> +vhost_vdpa_device_set_config(VirtIODevice *vdev, const uint8_t *config)
>> >> +{
>> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> >> +    int ret;
>> >> +
>> >> +    ret = vhost_dev_set_config(&s->dev, s->config, 0, s->config_size,
>> >> +                               VHOST_SET_CONFIG_TYPE_MASTER);
>> >> +    if (ret) {
>> >> +        error_report("set device config space failed");
>> >> +        return;
>> >> +    }
>> >> +}
>> >> +
>> >> +static uint64_t vhost_vdpa_device_get_features(VirtIODevice *vdev,
>> >> +                                               uint64_t features,
>> >> +                                               Error **errp)
>> >> +{
>> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> >> +    uint64_t backend_features = s->dev.features;
>> >> +
>> >> +    if (!virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM)) {
>> >> +        virtio_clear_feature(&backend_features, VIRTIO_F_IOMMU_PLATFORM);
>> >> +    }
>> >> +
>> >> +    return backend_features;
>> >> +}
>> >> +
>> >> +static int vhost_vdpa_device_start(VirtIODevice *vdev, Error **errp)
>> >> +{
>> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> >> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
>> >> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>> >> +    int i, ret;
>> >> +
>> >> +    if (!k->set_guest_notifiers) {
>> >> +        error_setg(errp, "binding does not support guest notifiers");
>> >> +        return -ENOSYS;
>> >> +    }
>> >> +
>> >> +    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
>> >> +    if (ret < 0) {
>> >> +        error_setg_errno(errp, -ret, "Error enabling host notifiers");
>> >> +        return ret;
>> >> +    }
>> >> +
>> >> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
>> >> +    if (ret < 0) {
>> >> +        error_setg_errno(errp, -ret, "Error binding guest notifier");
>> >> +        goto err_host_notifiers;
>> >> +    }
>> >> +
>> >> +    s->dev.acked_features = vdev->guest_features;
>> >> +
>> >> +    ret = vhost_dev_start(&s->dev, vdev);
>> >> +    if (ret < 0) {
>> >> +        error_setg_errno(errp, -ret, "Error starting vhost");
>> >> +        goto err_guest_notifiers;
>> >> +    }
>> >> +    s->started = true;
>> >> +
>> >> +    /*
>> >> +     * guest_notifier_mask/pending not used yet, so just unmask
>> >> +     * everything here. virtio-pci will do the right thing by
>> >> +     * enabling/disabling irqfd.
>> >> +     */
>> >> +    for (i = 0; i < s->dev.nvqs; i++) {
>> >> +        vhost_virtqueue_mask(&s->dev, vdev, i, false);
>> >> +    }
>> >> +
>> >> +    return ret;
>> >> +
>> >> +err_guest_notifiers:
>> >> +    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
>> >> +err_host_notifiers:
>> >> +    vhost_dev_disable_notifiers(&s->dev, vdev);
>> >> +    return ret;
>> >> +}
>> >> +
>> >> +static void vhost_vdpa_device_stop(VirtIODevice *vdev)
>> >> +{
>> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> >> +    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
>> >> +    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>> >> +    int ret;
>> >> +
>> >> +    if (!s->started) {
>> >> +        return;
>> >> +    }
>> >> +    s->started = false;
>> >> +
>> >> +    if (!k->set_guest_notifiers) {
>> >> +        return;
>> >> +    }
>> >> +
>> >> +    vhost_dev_stop(&s->dev, vdev);
>> >> +
>> >> +    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
>> >> +    if (ret < 0) {
>> >> +        error_report("vhost guest notifier cleanup failed: %d", ret);
>> >> +        return;
>> >> +    }
>> >> +
>> >> +    vhost_dev_disable_notifiers(&s->dev, vdev);
>> >> +}
>> >> +
>> >> +static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
>> >> +{
>> >> +    VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
>> >> +    bool should_start = virtio_device_started(vdev, status);
>> >> +    Error *local_err = NULL;
>> >> +    int ret;
>> >> +
>> >> +    if (!vdev->vm_running) {
>> >> +        should_start = false;
>> >> +    }
>> >> +
>> >> +    if (s->started == should_start) {
>> >> +        return;
>> >> +    }
>> >> +
>> >> +    if (should_start) {
>> >> +        ret = vhost_vdpa_device_start(vdev, &local_err);
>> >> +        if (ret < 0) {
>> >> +            error_reportf_err(local_err, "vhost-vdpa-device: start failed: ");
>> >> +        }
>> >> +    } else {
>> >> +        vhost_vdpa_device_stop(vdev);
>> >> +    }
>> >> +}
>> >> +
>> >> +static Property vhost_vdpa_device_properties[] = {
>> >> +    DEFINE_PROP_STRING("vhostdev", VhostVdpaDevice, vhostdev),
>> >> +    DEFINE_PROP_INT32("vhostfd", VhostVdpaDevice, vhostfd, -1),
>> >
>> >This is probably not needed since we can "abuse" /dev/fd/X for
>> >vhostdev.
>>
>> IIRC for other vhost devices (e.g. vhost-vsock) the management layer
>> (e.g. libvirt) opens the device (because I think QEMU has less
>> permissions) and then passes the fd to QEMU, could this be useful for
>> this scenario as well?
>
>Yes, it's the way current vhost-vDPA did (the fd is passing via SCM_RIGHTS).

Okay, I looked at qemu_open() and I see what you mean. Basically libvirt 
can pass the fd directly with vhostdev=/dev/fdset/X instead of having a 
dedicated property.

I did not know that, I agree to remove "vhostfd" then!

Thanks for the clarification,
Stefano

[PATCH v4 4/4] vdpa: add vdpa-dev-pci support

[Longpeng(Mike) via]

From: Longpeng <longpeng2@huawei.com>

Supports vdpa-dev-pci, we can use the device as follow:

-device vhost-vdpa-device-pci,vhostdev=/dev/vhost-vdpa-X

Signed-off-by: Longpeng <longpeng2@huawei.com>
---
 hw/virtio/meson.build    |   1 +
 hw/virtio/vdpa-dev-pci.c | 101 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 102 insertions(+)
 create mode 100644 hw/virtio/vdpa-dev-pci.c

diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
index 8f6f86db71..c2da69616f 100644
--- a/hw/virtio/meson.build
+++ b/hw/virtio/meson.build
@@ -50,6 +50,7 @@ virtio_pci_ss.add(when: 'CONFIG_VIRTIO_SERIAL', if_true: files('virtio-serial-pc
 virtio_pci_ss.add(when: 'CONFIG_VIRTIO_PMEM', if_true: files('virtio-pmem-pci.c'))
 virtio_pci_ss.add(when: 'CONFIG_VIRTIO_IOMMU', if_true: files('virtio-iommu-pci.c'))
 virtio_pci_ss.add(when: 'CONFIG_VIRTIO_MEM', if_true: files('virtio-mem-pci.c'))
+virtio_pci_ss.add(when: 'CONFIG_VHOST_VDPA_DEV', if_true: files('vdpa-dev-pci.c'))
 
 virtio_ss.add_all(when: 'CONFIG_VIRTIO_PCI', if_true: virtio_pci_ss)
 
diff --git a/hw/virtio/vdpa-dev-pci.c b/hw/virtio/vdpa-dev-pci.c
new file mode 100644
index 0000000000..31bd17353a
--- /dev/null
+++ b/hw/virtio/vdpa-dev-pci.c
@@ -0,0 +1,101 @@
+/*
+ * Vhost Vdpa Device PCI Bindings
+ *
+ * Copyright (c) Huawei Technologies Co., Ltd. 2022. All Rights Reserved.
+ *
+ * Authors:
+ *   Longpeng <longpeng2@huawei.com>
+ *
+ * Largely based on the "vhost-user-blk-pci.c" and "vhost-user-blk.c" implemented by:
+ *   Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+#include "qemu/osdep.h"
+#include <sys/ioctl.h>
+#include <linux/vhost.h>
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/vdpa-dev.h"
+#include "hw/pci/pci.h"
+#include "hw/qdev-properties.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/module.h"
+#include "virtio-pci.h"
+#include "qom/object.h"
+
+
+typedef struct VhostVdpaDevicePCI VhostVdpaDevicePCI;
+
+#define TYPE_VHOST_VDPA_DEVICE_PCI "vhost-vdpa-device-pci-base"
+DECLARE_INSTANCE_CHECKER(VhostVdpaDevicePCI, VHOST_VDPA_DEVICE_PCI,
+                         TYPE_VHOST_VDPA_DEVICE_PCI)
+
+struct VhostVdpaDevicePCI {
+    VirtIOPCIProxy parent_obj;
+    VhostVdpaDevice vdev;
+};
+
+static void vhost_vdpa_device_pci_instance_init(Object *obj)
+{
+    VhostVdpaDevicePCI *dev = VHOST_VDPA_DEVICE_PCI(obj);
+
+    virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev),
+                                TYPE_VHOST_VDPA_DEVICE);
+    object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev),
+                              "bootindex");
+}
+
+static Property vhost_vdpa_device_pci_properties[] = {
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static int vhost_vdpa_device_pci_post_init(VhostVdpaDevice *v, Error **errp)
+{
+    VhostVdpaDevicePCI *dev = container_of(v, VhostVdpaDevicePCI, vdev);
+    VirtIOPCIProxy *vpci_dev = &dev->parent_obj;
+
+    vpci_dev->class_code = virtio_pci_get_class_id(v->vdev_id);
+    vpci_dev->trans_devid = virtio_pci_get_trans_devid(v->vdev_id);
+    /* one for config vector */
+    vpci_dev->nvectors = v->num_queues + 1;
+
+    return 0;
+}
+
+static void
+vhost_vdpa_device_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
+{
+    VhostVdpaDevicePCI *dev = VHOST_VDPA_DEVICE_PCI(vpci_dev);
+
+    dev->vdev.post_init = vhost_vdpa_device_pci_post_init;
+    qdev_realize(DEVICE(&dev->vdev), BUS(&vpci_dev->bus), errp);
+}
+
+static void vhost_vdpa_device_pci_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass);
+
+    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+    device_class_set_props(dc, vhost_vdpa_device_pci_properties);
+    k->realize = vhost_vdpa_device_pci_realize;
+}
+
+static const VirtioPCIDeviceTypeInfo vhost_vdpa_device_pci_info = {
+    .base_name               = TYPE_VHOST_VDPA_DEVICE_PCI,
+    .generic_name            = "vhost-vdpa-device-pci",
+    .transitional_name       = "vhost-vdpa-device-pci-transitional",
+    .non_transitional_name   = "vhost-vdpa-device-pci-non-transitional",
+    .instance_size  = sizeof(VhostVdpaDevicePCI),
+    .instance_init  = vhost_vdpa_device_pci_instance_init,
+    .class_init     = vhost_vdpa_device_pci_class_init,
+};
+
+static void vhost_vdpa_device_pci_register(void)
+{
+    virtio_pci_types_register(&vhost_vdpa_device_pci_info);
+}
+
+type_init(vhost_vdpa_device_pci_register);
-- 
2.23.0