virtio,pci,pc: fixes, features

index c5d2c09455..d54d9c916f 100644
@@ -40,7 +40,7 @@ struct VHostSCSICommon {
 };
 
 int vhost_scsi_common_start(VHostSCSICommon *vsc, Error **errp);
-void vhost_scsi_common_stop(VHostSCSICommon *vsc);
+int vhost_scsi_common_stop(VHostSCSICommon *vsc);
 char *vhost_scsi_common_get_fw_dev_path(FWPathProvider *p, BusState *bus,
                                         DeviceState *dev);
 void vhost_scsi_common_set_config(VirtIODevice *vdev, const uint8_t *config);

index 75a74e8a99..01bf6062af 100644
@@ -42,7 +42,7 @@ struct VHostVSockCommon {
 };
 
 int vhost_vsock_common_start(VirtIODevice *vdev);
-void vhost_vsock_common_stop(VirtIODevice *vdev);
+int vhost_vsock_common_stop(VirtIODevice *vdev);
 int vhost_vsock_common_pre_save(void *opaque);
 int vhost_vsock_common_post_load(void *opaque, int version_id);
 void vhost_vsock_common_realize(VirtIODevice *vdev);

index 7e0c471ea4..214d4a77e9 100644
@@ -186,7 +186,7 @@ struct VirtioDeviceClass {
     void (*get_config)(VirtIODevice *vdev, uint8_t *config);
     void (*set_config)(VirtIODevice *vdev, const uint8_t *config);
     void (*reset)(VirtIODevice *vdev);
-    void (*set_status)(VirtIODevice *vdev, uint8_t val);
+    int (*set_status)(VirtIODevice *vdev, uint8_t val);
     /* Device must validate queue_index.  */
     void (*queue_reset)(VirtIODevice *vdev, uint32_t queue_index);
     /* Device must validate queue_index.  */

index 5ed953cd53..5634ebdb2e 100644
@@ -43,6 +43,6 @@ struct VhostUserBackend {
 int vhost_user_backend_dev_init(VhostUserBackend *b, VirtIODevice *vdev,
                                 unsigned nvqs, Error **errp);
 void vhost_user_backend_start(VhostUserBackend *b);
-void vhost_user_backend_stop(VhostUserBackend *b);
+int vhost_user_backend_stop(VhostUserBackend *b);
 
 #endif

index 94274a619d..42845329e7 100644
@@ -97,30 +97,28 @@ err_host_notifiers:
     vhost_dev_disable_notifiers(&b->dev, b->vdev);
 }
 
-void
+int
 vhost_user_backend_stop(VhostUserBackend *b)
 {
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(b->vdev)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
-    int ret = 0;
+    int ret;
 
     if (!b->started) {
-        return;
+        return 0;
     }
 
-    vhost_dev_stop(&b->dev, b->vdev, true);
+    ret = vhost_dev_stop(&b->dev, b->vdev, true);
 
-    if (k->set_guest_notifiers) {
-        ret = k->set_guest_notifiers(qbus->parent,
-                                     b->dev.nvqs, false);
-        if (ret < 0) {
-            error_report("vhost guest notifier cleanup failed: %d", ret);
-        }
+    if (k->set_guest_notifiers &&
+        k->set_guest_notifiers(qbus->parent, b->dev.nvqs, false) < 0) {
+        error_report("vhost guest notifier cleanup failed: %d", ret);
+        return -1;
     }
-    assert(ret >= 0);
 
     vhost_dev_disable_notifiers(&b->dev, b->vdev);
     b->started = false;
+    return ret;
 }
 
 static void set_chardev(Object *obj, const char *value, Error **errp)

index 4bb5ed299e..0eebbcd80d 100644
@@ -204,7 +204,7 @@ err_host_notifiers:
     return ret;
 }
 
-static void vhost_user_blk_stop(VirtIODevice *vdev)
+static int vhost_user_blk_stop(VirtIODevice *vdev)
 {
     VHostUserBlk *s = VHOST_USER_BLK(vdev);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));

@@ -212,26 +212,26 @@ static void vhost_user_blk_stop(VirtIODevice *vdev)
     int ret;
 
     if (!s->started_vu) {
-        return;
+        return 0;
     }
     s->started_vu = false;
 
     if (!k->set_guest_notifiers) {
-        return;
+        return 0;
     }
 
-    vhost_dev_stop(&s->dev, vdev, true);
+    ret = vhost_dev_stop(&s->dev, vdev, true);
 
-    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
-    if (ret < 0) {
+    if (k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false) < 0) {
         error_report("vhost guest notifier cleanup failed: %d", ret);
-        return;
+        return -1;
     }
 
     vhost_dev_disable_notifiers(&s->dev, vdev);
+    return ret;
 }
 
-static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
+static int vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostUserBlk *s = VHOST_USER_BLK(vdev);
     bool should_start = virtio_device_should_start(vdev, status);

@@ -239,11 +239,11 @@ static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
     int ret;
 
     if (!s->connected) {
-        return;
+        return -1;
     }
 
     if (vhost_dev_is_started(&s->dev) == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {

@@ -253,9 +253,12 @@ static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
             qemu_chr_fe_disconnect(&s->chardev);
         }
     } else {
-        vhost_user_blk_stop(vdev);
+        ret = vhost_user_blk_stop(vdev);
+        if (ret < 0) {
+            return ret;
+        }
     }
-
+    return 0;
 }
 
 static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev,

index ea948d18fd..9bab2716c1 100644
@@ -1270,7 +1270,7 @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
     return features;
 }
 
-static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
+static int virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VirtIOBlock *s = VIRTIO_BLK(vdev);
 

@@ -1279,7 +1279,7 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
     }
 
     if (!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
-        return;
+        return 0;
     }
 
     /* A guest that supports VIRTIO_BLK_F_CONFIG_WCE must be able to send

@@ -1302,6 +1302,7 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
                                    virtio_vdev_has_feature(vdev,
                                                            VIRTIO_BLK_F_WCE));
     }
+    return 0;
 }
 
 static void virtio_blk_save_device(VirtIODevice *vdev, QEMUFile *f)

index eb79f5258b..673c50f0be 100644
@@ -622,7 +622,7 @@ static void guest_reset(VirtIOSerial *vser)
     }
 }
 
-static void set_status(VirtIODevice *vdev, uint8_t status)
+static int set_status(VirtIODevice *vdev, uint8_t status)
 {
     VirtIOSerial *vser;
     VirtIOSerialPort *port;

@@ -650,6 +650,7 @@ static void set_status(VirtIODevice *vdev, uint8_t status)
             vsc->enable_backend(port, vdev->vm_running);
         }
     }
+    return 0;
 }
 
 static void vser_reset(VirtIODevice *vdev)

index 43d4c08a2e..9fc6bbcd2c 100644
@@ -516,7 +516,7 @@ vhost_user_gpu_set_config(VirtIODevice *vdev,
     }
 }
 
-static void
+static int
 vhost_user_gpu_set_status(VirtIODevice *vdev, uint8_t val)
 {
     VhostUserGPU *g = VHOST_USER_GPU(vdev);

@@ -525,18 +525,24 @@ vhost_user_gpu_set_status(VirtIODevice *vdev, uint8_t val)
     if (val & VIRTIO_CONFIG_S_DRIVER_OK && vdev->vm_running) {
         if (!vhost_user_gpu_do_set_socket(g, &err)) {
             error_report_err(err);
-            return;
+            return 0;
         }
         vhost_user_backend_start(g->vhost);
     } else {
+        int ret;
+
         /* unblock any wait and stop processing */
         if (g->vhost_gpu_fd != -1) {
             vhost_user_gpu_update_blocked(g, true);
             qemu_chr_fe_deinit(&g->vhost_chr, true);
             g->vhost_gpu_fd = -1;
         }
-        vhost_user_backend_stop(g->vhost);
+        ret = vhost_user_backend_stop(g->vhost);
+        if (ret < 0) {
+            return ret;
+        }
     }
+    return 0;
 }
 
 static bool

index 1818cbddc7..a3f554f211 100644
@@ -189,7 +189,7 @@ static uint64_t virtio_input_get_features(VirtIODevice *vdev, uint64_t f,
     return f;
 }
 
-static void virtio_input_set_status(VirtIODevice *vdev, uint8_t val)
+static int virtio_input_set_status(VirtIODevice *vdev, uint8_t val)
 {
     VirtIOInputClass *vic = VIRTIO_INPUT_GET_CLASS(vdev);
     VirtIOInput *vinput = VIRTIO_INPUT(vdev);

@@ -202,6 +202,7 @@ static void virtio_input_set_status(VirtIODevice *vdev, uint8_t val)
             }
         }
     }
+    return 0;
 }
 
 static void virtio_input_reset(VirtIODevice *vdev)

index 2de037c273..221252e00a 100644
@@ -382,7 +382,7 @@ static void virtio_net_drop_tx_queue_data(VirtIODevice *vdev, VirtQueue *vq)
     }
 }
 
-static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
+static int virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
     VirtIONetQueue *q;

@@ -437,6 +437,7 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
             }
         }
     }
+    return 0;
 }
 
 static void virtio_net_set_link_status(NetClientState *nc)

index 4c8637045d..43525ba46d 100644
@@ -101,24 +101,25 @@ err_host_notifiers:
     return ret;
 }
 
-void vhost_scsi_common_stop(VHostSCSICommon *vsc)
+int vhost_scsi_common_stop(VHostSCSICommon *vsc)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(vsc);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     int ret = 0;
 
-    vhost_dev_stop(&vsc->dev, vdev, true);
+    ret = vhost_dev_stop(&vsc->dev, vdev, true);
 
     if (k->set_guest_notifiers) {
-        ret = k->set_guest_notifiers(qbus->parent, vsc->dev.nvqs, false);
-        if (ret < 0) {
-                error_report("vhost guest notifier cleanup failed: %d", ret);
+        int r = k->set_guest_notifiers(qbus->parent, vsc->dev.nvqs, false);
+        if (r < 0) {
+            error_report("vhost guest notifier cleanup failed: %d", ret);
+            return r;
         }
     }
-    assert(ret >= 0);
 
     vhost_dev_disable_notifiers(&vsc->dev, vdev);
+    return ret;
 }
 
 uint64_t vhost_scsi_common_get_features(VirtIODevice *vdev, uint64_t features,

index 10fde8eee0..dd4250ebe8 100644
@@ -114,7 +114,7 @@ static void vhost_scsi_stop(VHostSCSI *s)
     vhost_scsi_common_stop(vsc);
 }
 
-static void vhost_scsi_set_status(VirtIODevice *vdev, uint8_t val)
+static int vhost_scsi_set_status(VirtIODevice *vdev, uint8_t val)
 {
     VHostSCSI *s = VHOST_SCSI(vdev);
     VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);

@@ -125,7 +125,7 @@ static void vhost_scsi_set_status(VirtIODevice *vdev, uint8_t val)
     }
 
     if (vhost_dev_is_started(&vsc->dev) == start) {
-        return;
+        return 0;
     }
 
     if (start) {

@@ -139,6 +139,7 @@ static void vhost_scsi_set_status(VirtIODevice *vdev, uint8_t val)
     } else {
         vhost_scsi_stop(s);
     }
+    return 0;
 }
 
 static void vhost_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)

index 8298e8cc6d..25f2d894e7 100644
@@ -52,19 +52,19 @@ static int vhost_user_scsi_start(VHostUserSCSI *s, Error **errp)
     return ret;
 }
 
-static void vhost_user_scsi_stop(VHostUserSCSI *s)
+static int vhost_user_scsi_stop(VHostUserSCSI *s)
 {
     VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
 
     if (!s->started_vu) {
-        return;
+        return 0;
     }
     s->started_vu = false;
 
-    vhost_scsi_common_stop(vsc);
+    return vhost_scsi_common_stop(vsc);
 }
 
-static void vhost_user_scsi_set_status(VirtIODevice *vdev, uint8_t status)
+static int vhost_user_scsi_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostUserSCSI *s = (VHostUserSCSI *)vdev;
     DeviceState *dev = DEVICE(vdev);

@@ -75,11 +75,11 @@ static void vhost_user_scsi_set_status(VirtIODevice *vdev, uint8_t status)
     int ret;
 
     if (!s->connected) {
-        return;
+        return -1;
     }
 
     if (vhost_dev_is_started(&vsc->dev) == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {

@@ -91,8 +91,12 @@ static void vhost_user_scsi_set_status(VirtIODevice *vdev, uint8_t status)
             qemu_chr_fe_disconnect(&vs->conf.chardev);
         }
     } else {
-        vhost_user_scsi_stop(s);
+        ret = vhost_user_scsi_stop(s);
+        if (ret) {
+            return ret;
+        }
     }
+    return 0;
 }
 
 static void vhost_user_scsi_handle_output(VirtIODevice *vdev, VirtQueue *vq)

index dd8837ce4e..d1da40afc8 100644
@@ -312,7 +312,7 @@ static void vhost_vdpa_device_stop(VirtIODevice *vdev)
     vhost_dev_disable_notifiers(&s->dev, vdev);
 }
 
-static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
+static int vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VhostVdpaDevice *s = VHOST_VDPA_DEVICE(vdev);
     bool should_start = virtio_device_started(vdev, status);

@@ -324,7 +324,7 @@ static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
     }
 
     if (s->started == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {

@@ -335,6 +335,7 @@ static void vhost_vdpa_device_set_status(VirtIODevice *vdev, uint8_t status)
     } else {
         vhost_vdpa_device_stop(vdev);
     }
+    return 0;
 }
 
 static const Property vhost_vdpa_device_properties[] = {

index 77143320a2..ff67a020b4 100644
@@ -66,7 +66,7 @@ err_host_notifiers:
     vhost_dev_disable_notifiers(&vub->vhost_dev, vdev);
 }
 
-static void vub_stop(VirtIODevice *vdev)
+static int vub_stop(VirtIODevice *vdev)
 {
     VHostUserBase *vub = VHOST_USER_BASE(vdev);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));

@@ -74,34 +74,39 @@ static void vub_stop(VirtIODevice *vdev)
     int ret;
 
     if (!k->set_guest_notifiers) {
-        return;
+        return 0;
     }
 
-    vhost_dev_stop(&vub->vhost_dev, vdev, true);
+    ret = vhost_dev_stop(&vub->vhost_dev, vdev, true);
 
-    ret = k->set_guest_notifiers(qbus->parent, vub->vhost_dev.nvqs, false);
-    if (ret < 0) {
+    if (k->set_guest_notifiers(qbus->parent, vub->vhost_dev.nvqs, false) < 0) {
         error_report("vhost guest notifier cleanup failed: %d", ret);
-        return;
+        return -1;
     }
 
     vhost_dev_disable_notifiers(&vub->vhost_dev, vdev);
+    return ret;
 }
 
-static void vub_set_status(VirtIODevice *vdev, uint8_t status)
+static int vub_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostUserBase *vub = VHOST_USER_BASE(vdev);
     bool should_start = virtio_device_should_start(vdev, status);
 
     if (vhost_dev_is_started(&vub->vhost_dev) == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {
         vub_start(vdev);
     } else {
-        vub_stop(vdev);
+        int ret;
+        ret = vub_stop(vdev);
+        if (ret < 0) {
+            return ret;
+        }
     }
+    return 0;
 }
 
 /*

index f6d1fc8804..e77c69eb12 100644
@@ -100,7 +100,7 @@ err_host_notifiers:
     vhost_dev_disable_notifiers(&fs->vhost_dev, vdev);
 }
 
-static void vuf_stop(VirtIODevice *vdev)
+static int vuf_stop(VirtIODevice *vdev)
 {
     VHostUserFS *fs = VHOST_USER_FS(vdev);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));

@@ -108,34 +108,39 @@ static void vuf_stop(VirtIODevice *vdev)
     int ret;
 
     if (!k->set_guest_notifiers) {
-        return;
+        return 0;
     }
 
-    vhost_dev_stop(&fs->vhost_dev, vdev, true);
+    ret = vhost_dev_stop(&fs->vhost_dev, vdev, true);
 
-    ret = k->set_guest_notifiers(qbus->parent, fs->vhost_dev.nvqs, false);
-    if (ret < 0) {
+    if (k->set_guest_notifiers(qbus->parent, fs->vhost_dev.nvqs, false) < 0) {
         error_report("vhost guest notifier cleanup failed: %d", ret);
-        return;
+        return -1;
     }
 
     vhost_dev_disable_notifiers(&fs->vhost_dev, vdev);
+    return ret;
 }
 
-static void vuf_set_status(VirtIODevice *vdev, uint8_t status)
+static int vuf_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostUserFS *fs = VHOST_USER_FS(vdev);
     bool should_start = virtio_device_should_start(vdev, status);
 
     if (vhost_dev_is_started(&fs->vhost_dev) == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {
         vuf_start(vdev);
     } else {
-        vuf_stop(vdev);
+        int ret;
+        ret = vuf_stop(vdev);
+        if (ret < 0) {
+            return ret;
+        }
     }
+    return 0;
 }
 
 static uint64_t vuf_get_features(VirtIODevice *vdev,

index 7a0f622181..f9264c4374 100644
@@ -83,7 +83,7 @@ err_host_notifiers:
     return ret;
 }
 
-static void vu_scmi_stop(VirtIODevice *vdev)
+static int vu_scmi_stop(VirtIODevice *vdev)
 {
     VHostUserSCMI *scmi = VHOST_USER_SCMI(vdev);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));

@@ -93,41 +93,46 @@ static void vu_scmi_stop(VirtIODevice *vdev)
 
     /* vhost_dev_is_started() check in the callers is not fully reliable. */
     if (!scmi->started_vu) {
-        return;
+        return 0;
     }
     scmi->started_vu = false;
 
     if (!k->set_guest_notifiers) {
-        return;
+        return 0;
     }
 
-    vhost_dev_stop(vhost_dev, vdev, true);
+    ret = vhost_dev_stop(vhost_dev, vdev, true);
 
-    ret = k->set_guest_notifiers(qbus->parent, vhost_dev->nvqs, false);
-    if (ret < 0) {
+    if (k->set_guest_notifiers(qbus->parent, vhost_dev->nvqs, false) < 0) {
         error_report("vhost guest notifier cleanup failed: %d", ret);
-        return;
+        return -1;
     }
     vhost_dev_disable_notifiers(vhost_dev, vdev);
+    return ret;
 }
 
-static void vu_scmi_set_status(VirtIODevice *vdev, uint8_t status)
+static int vu_scmi_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostUserSCMI *scmi = VHOST_USER_SCMI(vdev);
     bool should_start = virtio_device_should_start(vdev, status);
 
     if (!scmi->connected) {
-        return;
+        return -1;
     }
     if (vhost_dev_is_started(&scmi->vhost_dev) == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {
         vu_scmi_start(vdev);
     } else {
-        vu_scmi_stop(vdev);
+        int ret;
+        ret = vu_scmi_stop(vdev);
+        if (ret < 0) {
+            return ret;
+        }
     }
+    return 0;
 }
 
 static uint64_t vu_scmi_get_features(VirtIODevice *vdev, uint64_t features,

index 2776792f59..993c287348 100644
@@ -54,23 +54,28 @@ const VhostDevConfigOps vsock_ops = {
     .vhost_dev_config_notifier = vuv_handle_config_change,
 };
 
-static void vuv_set_status(VirtIODevice *vdev, uint8_t status)
+static int vuv_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev);
     bool should_start = virtio_device_should_start(vdev, status);
+    int ret;
 
     if (vhost_dev_is_started(&vvc->vhost_dev) == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {
-        int ret = vhost_vsock_common_start(vdev);
+        ret = vhost_vsock_common_start(vdev);
         if (ret < 0) {
-            return;
+            return ret;
         }
     } else {
-        vhost_vsock_common_stop(vdev);
+        ret = vhost_vsock_common_stop(vdev);
+        if (ret < 0) {
+            return ret;
+        }
     }
+    return 0;
 }
 
 static uint64_t vuv_get_features(VirtIODevice *vdev,

index 4b4fbb45cc..c6c44d8989 100644
@@ -95,7 +95,7 @@ err_host_notifiers:
     return ret;
 }
 
-void vhost_vsock_common_stop(VirtIODevice *vdev)
+int vhost_vsock_common_stop(VirtIODevice *vdev)
 {
     VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));

@@ -103,18 +103,18 @@ void vhost_vsock_common_stop(VirtIODevice *vdev)
     int ret;
 
     if (!k->set_guest_notifiers) {
-        return;
+        return 0;
     }
 
-    vhost_dev_stop(&vvc->vhost_dev, vdev, true);
+    ret = vhost_dev_stop(&vvc->vhost_dev, vdev, true);
 
-    ret = k->set_guest_notifiers(qbus->parent, vvc->vhost_dev.nvqs, false);
-    if (ret < 0) {
+    if (k->set_guest_notifiers(qbus->parent, vvc->vhost_dev.nvqs, false) < 0) {
         error_report("vhost guest notifier cleanup failed: %d", ret);
-        return;
+        return -1;
     }
 
     vhost_dev_disable_notifiers(&vvc->vhost_dev, vdev);
+    return ret;
 }
 
 

index b73dc723c2..6e4088831f 100644
@@ -67,37 +67,38 @@ static int vhost_vsock_set_running(VirtIODevice *vdev, int start)
 }
 
 
-static void vhost_vsock_set_status(VirtIODevice *vdev, uint8_t status)
+static int vhost_vsock_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev);
     bool should_start = virtio_device_should_start(vdev, status);
     int ret;
 
     if (vhost_dev_is_started(&vvc->vhost_dev) == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {
         ret = vhost_vsock_common_start(vdev);
         if (ret < 0) {
-            return;
+            return 0;
         }
 
         ret = vhost_vsock_set_running(vdev, 1);
         if (ret < 0) {
             vhost_vsock_common_stop(vdev);
             error_report("Error starting vhost vsock: %d", -ret);
-            return;
+            return 0;
         }
     } else {
         ret = vhost_vsock_set_running(vdev, 0);
         if (ret < 0) {
             error_report("vhost vsock set running failed: %d", ret);
-            return;
+            return 0;
         }
 
         vhost_vsock_common_stop(vdev);
     }
+    return 0;
 }
 
 static uint64_t vhost_vsock_get_features(VirtIODevice *vdev,

index 91510ec2e2..db787d00b3 100644
@@ -958,7 +958,7 @@ static void virtio_balloon_device_reset(VirtIODevice *vdev)
     s->poison_val = 0;
 }
 
-static void virtio_balloon_set_status(VirtIODevice *vdev, uint8_t status)
+static int virtio_balloon_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
 

@@ -988,6 +988,7 @@ static void virtio_balloon_set_status(VirtIODevice *vdev, uint8_t status)
             qemu_mutex_unlock(&s->free_page_lock);
         }
     }
+    return 0;
 }
 
 static ResettableState *virtio_balloon_get_reset_state(Object *obj)

index e24d6914b6..517f2089c5 100644
@@ -1197,11 +1197,12 @@ static void virtio_crypto_vhost_status(VirtIOCrypto *c, uint8_t status)
     }
 }
 
-static void virtio_crypto_set_status(VirtIODevice *vdev, uint8_t status)
+static int virtio_crypto_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VirtIOCrypto *vcrypto = VIRTIO_CRYPTO(vdev);
 
     virtio_crypto_vhost_status(vcrypto, status);
+    return 0;
 }
 
 static void virtio_crypto_guest_notifier_mask(VirtIODevice *vdev, int idx,

index 54060988ef..3500f1b082 100644
@@ -1522,9 +1522,10 @@ static void virtio_iommu_device_reset_exit(Object *obj, ResetType type)
                                    NULL, NULL, virtio_iommu_put_endpoint);
 }
 
-static void virtio_iommu_set_status(VirtIODevice *vdev, uint8_t status)
+static int virtio_iommu_set_status(VirtIODevice *vdev, uint8_t status)
 {
     trace_virtio_iommu_device_status(status);
+    return 0;
 }
 
 static void virtio_iommu_instance_init(Object *obj)

index dcb3c71d6a..3df5d2576e 100644
@@ -159,17 +159,18 @@ static void check_rate_limit(void *opaque)
     vrng->activate_timer = true;
 }
 
-static void virtio_rng_set_status(VirtIODevice *vdev, uint8_t status)
+static int virtio_rng_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VirtIORNG *vrng = VIRTIO_RNG(vdev);
 
     if (!vdev->vm_running) {
-        return;
+        return 0;
     }
     vdev->status = status;
 
     /* Something changed, try to process buffers */
     virtio_rng_process(vrng);
+    return 0;
 }
 
 static void virtio_rng_device_realize(DeviceState *dev, Error **errp)

index e3b62522ec..1b55d8d8a2 100644
@@ -2221,12 +2221,12 @@ int virtio_set_status(VirtIODevice *vdev, uint8_t val)
 {
     VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
     trace_virtio_set_status(vdev, val);
+    int ret = 0;
 
     if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) {
         if (!(vdev->status & VIRTIO_CONFIG_S_FEATURES_OK) &&
             val & VIRTIO_CONFIG_S_FEATURES_OK) {
-            int ret = virtio_validate_features(vdev);
-
+            ret = virtio_validate_features(vdev);
             if (ret) {
                 return ret;
             }

@@ -2239,11 +2239,15 @@ int virtio_set_status(VirtIODevice *vdev, uint8_t val)
     }
 
     if (k->set_status) {
-        k->set_status(vdev, val);
+        ret = k->set_status(vdev, val);
+        if (ret) {
+            qemu_log("set %s status to %d failed, old status: %d\n",
+                     vdev->name, val, vdev->status);
+        }
     }
     vdev->status = val;
 
-    return 0;
+    return ret;
 }
 
 static enum virtio_device_endian virtio_default_endian(void)

@@ -3419,7 +3423,7 @@ void virtio_cleanup(VirtIODevice *vdev)
     qemu_del_vm_change_state_handler(vdev->vmstate);
 }
 
-static void virtio_vmstate_change(void *opaque, bool running, RunState state)
+static int virtio_vmstate_change(void *opaque, bool running, RunState state)
 {
     VirtIODevice *vdev = opaque;
     BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));

@@ -3436,8 +3440,12 @@ static void virtio_vmstate_change(void *opaque, bool running, RunState state)
     }
 
     if (!backend_run) {
-        virtio_set_status(vdev, vdev->status);
+        int ret = virtio_set_status(vdev, vdev->status);
+        if (ret) {
+            return ret;
+        }
     }
+    return 0;
 }
 
 void virtio_instance_init_common(Object *proxy_obj, void *data,

@@ -3489,7 +3497,7 @@ void virtio_init(VirtIODevice *vdev, uint16_t device_id, size_t config_size)
         vdev->config = NULL;
     }
     vdev->vmstate = qdev_add_vm_change_state_handler(DEVICE(vdev),
-            virtio_vmstate_change, NULL, vdev);
+            NULL, virtio_vmstate_change, vdev);
     vdev->device_endian = virtio_default_endian();
     vdev->use_guest_notifier_mask = true;
 }

index bd25df033a..79b35d1405 100644
@@ -89,6 +89,7 @@ enum {
     SANITIZE    = 0x44,
         #define OVERWRITE     0x0
         #define SECURE_ERASE  0x1
+        #define MEDIA_OPERATIONS 0x2
     PERSISTENT_MEM = 0x45,
         #define GET_SECURITY_STATE     0x0
     MEDIA_AND_POISON = 0x43,

@@ -1705,6 +1706,126 @@ static CXLRetCode cmd_sanitize_overwrite(const struct cxl_cmd *cmd,
     return CXL_MBOX_BG_STARTED;
 }
 
+enum {
+    MEDIA_OP_CLASS_GENERAL  = 0x0,
+        #define MEDIA_OP_GEN_SUBC_DISCOVERY 0x0
+    MEDIA_OP_CLASS_SANITIZE = 0x1,
+        #define MEDIA_OP_SAN_SUBC_SANITIZE 0x0
+        #define MEDIA_OP_SAN_SUBC_ZERO 0x1
+};
+
+struct media_op_supported_list_entry {
+    uint8_t media_op_class;
+    uint8_t media_op_subclass;
+};
+
+struct media_op_discovery_out_pl {
+    uint64_t dpa_range_granularity;
+    uint16_t total_supported_operations;
+    uint16_t num_of_supported_operations;
+    struct media_op_supported_list_entry entry[];
+} QEMU_PACKED;
+
+static const struct media_op_supported_list_entry media_op_matrix[] = {
+    { MEDIA_OP_CLASS_GENERAL, MEDIA_OP_GEN_SUBC_DISCOVERY },
+    { MEDIA_OP_CLASS_SANITIZE, MEDIA_OP_SAN_SUBC_SANITIZE },
+    { MEDIA_OP_CLASS_SANITIZE, MEDIA_OP_SAN_SUBC_ZERO },
+};
+
+static CXLRetCode media_operations_discovery(uint8_t *payload_in,
+                                             size_t len_in,
+                                             uint8_t *payload_out,
+                                             size_t *len_out)
+{
+    struct {
+        uint8_t media_operation_class;
+        uint8_t media_operation_subclass;
+        uint8_t rsvd[2];
+        uint32_t dpa_range_count;
+        struct {
+            uint16_t start_index;
+            uint16_t num_ops;
+        } discovery_osa;
+    } QEMU_PACKED *media_op_in_disc_pl = (void *)payload_in;
+    struct media_op_discovery_out_pl *media_out_pl =
+        (struct media_op_discovery_out_pl *)payload_out;
+    int num_ops, start_index, i;
+    int count = 0;
+
+    if (len_in < sizeof(*media_op_in_disc_pl)) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
+    num_ops = media_op_in_disc_pl->discovery_osa.num_ops;
+    start_index = media_op_in_disc_pl->discovery_osa.start_index;
+
+    /*
+     * As per spec CXL r3.2 8.2.10.9.5.3 dpa_range_count should be zero and
+     * start index should not exceed the total number of entries for discovery
+     * sub class command.
+     */
+    if (media_op_in_disc_pl->dpa_range_count ||
+        start_index > ARRAY_SIZE(media_op_matrix)) {
+        return CXL_MBOX_INVALID_INPUT;
+    }
+
+    media_out_pl->dpa_range_granularity = CXL_CACHE_LINE_SIZE;
+    media_out_pl->total_supported_operations =
+                                     ARRAY_SIZE(media_op_matrix);
+    if (num_ops > 0) {
+        for (i = start_index; i < start_index + num_ops; i++) {
+            media_out_pl->entry[count].media_op_class =
+                    media_op_matrix[i].media_op_class;
+            media_out_pl->entry[count].media_op_subclass =
+                        media_op_matrix[i].media_op_subclass;
+            count++;
+            if (count == num_ops) {
+                break;
+            }
+        }
+    }
+
+    media_out_pl->num_of_supported_operations = count;
+    *len_out = sizeof(*media_out_pl) + count * sizeof(*media_out_pl->entry);
+    return CXL_MBOX_SUCCESS;
+}
+
+static CXLRetCode cmd_media_operations(const struct cxl_cmd *cmd,
+                                       uint8_t *payload_in,
+                                       size_t len_in,
+                                       uint8_t *payload_out,
+                                       size_t *len_out,
+                                       CXLCCI *cci)
+{
+    struct {
+        uint8_t media_operation_class;
+        uint8_t media_operation_subclass;
+        uint8_t rsvd[2];
+        uint32_t dpa_range_count;
+    } QEMU_PACKED *media_op_in_common_pl = (void *)payload_in;
+    uint8_t media_op_cl = 0;
+    uint8_t media_op_subclass = 0;
+
+    if (len_in < sizeof(*media_op_in_common_pl)) {
+        return CXL_MBOX_INVALID_PAYLOAD_LENGTH;
+    }
+
+    media_op_cl = media_op_in_common_pl->media_operation_class;
+    media_op_subclass = media_op_in_common_pl->media_operation_subclass;
+
+    switch (media_op_cl) {
+    case MEDIA_OP_CLASS_GENERAL:
+        if (media_op_subclass != MEDIA_OP_GEN_SUBC_DISCOVERY) {
+            return CXL_MBOX_UNSUPPORTED;
+        }
+
+        return media_operations_discovery(payload_in, len_in, payload_out,
+                                             len_out);
+    default:
+        return CXL_MBOX_UNSUPPORTED;
+    }
+}
+
 static CXLRetCode cmd_get_security_state(const struct cxl_cmd *cmd,
                                          uint8_t *payload_in,
                                          size_t len_in,

@@ -2850,6 +2971,10 @@ static const struct cxl_cmd cxl_cmd_set[256][256] = {
          CXL_MBOX_SECURITY_STATE_CHANGE |
          CXL_MBOX_BACKGROUND_OPERATION |
          CXL_MBOX_BACKGROUND_OPERATION_ABORT)},
+    [SANITIZE][MEDIA_OPERATIONS] = { "MEDIA_OPERATIONS", cmd_media_operations,
+        ~0,
+        (CXL_MBOX_IMMEDIATE_DATA_CHANGE |
+         CXL_MBOX_BACKGROUND_OPERATION)},
     [PERSISTENT_MEM][GET_SECURITY_STATE] = { "GET_SECURITY_STATE",
         cmd_get_security_state, 0, 0 },
     [MEDIA_AND_POISON][GET_POISON_LIST] = { "MEDIA_AND_POISON_GET_POISON_LIST",

index f75b8f22ee..aeaa38cf34 100644
@@ -43,12 +43,15 @@ void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num,
 
 /**
  * pcie_sriov_pf_init_from_user_created_vfs() - Initialize PF with user-created
- *                                              VFs.
+ *                                              VFs, adding ARI to PF
  * @dev: A PCIe device being realized.
  * @offset: The offset of the SR-IOV capability.
  * @errp: pointer to Error*, to store an error if it happens.
  *
- * Return: The size of added capability. 0 if the user did not create VFs.
+ * Initializes a PF with user-created VFs, adding the ARI extended capability to
+ * the PF. The VFs should call pcie_ari_init() to form an ARI device.
+ *
+ * Return: The size of added capabilities. 0 if the user did not create VFs.
  *         -1 if failed.
  */
 int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,

index 08f707e847..3ad18744f4 100644
@@ -245,6 +245,7 @@ int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
     PCIDevice **vfs;
     BusState *bus = qdev_get_parent_bus(DEVICE(dev));
     uint16_t ven_id = pci_get_word(dev->config + PCI_VENDOR_ID);
+    uint16_t size = PCI_EXT_CAP_SRIOV_SIZEOF;
     uint16_t vf_dev_id;
     uint16_t vf_offset;
     uint16_t vf_stride;

@@ -311,6 +312,11 @@ int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
         return -1;
     }
 
+    if (!pcie_find_capability(dev, PCI_EXT_CAP_ID_ARI)) {
+        pcie_ari_init(dev, offset + size);
+        size += PCI_ARI_SIZEOF;
+    }
+
     for (i = 0; i < pf->len; i++) {
         vfs[i]->exp.sriov_vf.pf = dev;
         vfs[i]->exp.sriov_vf.vf_number = i;

@@ -331,7 +337,7 @@ int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
         }
     }
 
-    return PCI_EXT_CAP_SRIOV_SIZEOF;
+    return size;
 }
 
 bool pcie_sriov_register_device(PCIDevice *dev, Error **errp)

index fee65d3645..9b48aa8c3e 100644
@@ -2111,12 +2111,16 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
                          PCI_BASE_ADDRESS_SPACE_IO, &proxy->bar);
     }
 
-    res = pcie_sriov_pf_init_from_user_created_vfs(&proxy->pci_dev,
-                                                   proxy->last_pcie_cap_offset,
-                                                   errp);
-    if (res > 0) {
-        proxy->last_pcie_cap_offset += res;
-        virtio_add_feature(&vdev->host_features, VIRTIO_F_SR_IOV);
+    if (pci_is_vf(&proxy->pci_dev)) {
+        pcie_ari_init(&proxy->pci_dev, proxy->last_pcie_cap_offset);
+        proxy->last_pcie_cap_offset += PCI_ARI_SIZEOF;
+    } else {
+        res = pcie_sriov_pf_init_from_user_created_vfs(
+            &proxy->pci_dev, proxy->last_pcie_cap_offset, errp);
+        if (res > 0) {
+            proxy->last_pcie_cap_offset += res;
+            virtio_add_feature(&vdev->host_features, VIRTIO_F_SR_IOV);
+        }
     }
 }
 

index 79b35d1405..9f9d475678 100644
@@ -1640,6 +1640,41 @@ static void __do_sanitization(CXLType3Dev *ct3d)
     cxl_discard_all_event_records(&ct3d->cxl_dstate);
 }
 
+static int get_sanitize_duration(uint64_t total_mem)
+{
+    int secs = 0;
+
+    if (total_mem <= 512) {
+        secs = 4;
+    } else if (total_mem <= 1024) {
+        secs = 8;
+    } else if (total_mem <= 2 * 1024) {
+        secs = 15;
+    } else if (total_mem <= 4 * 1024) {
+        secs = 30;
+    } else if (total_mem <= 8 * 1024) {
+        secs = 60;
+    } else if (total_mem <= 16 * 1024) {
+        secs = 2 * 60;
+    } else if (total_mem <= 32 * 1024) {
+        secs = 4 * 60;
+    } else if (total_mem <= 64 * 1024) {
+        secs = 8 * 60;
+    } else if (total_mem <= 128 * 1024) {
+        secs = 15 * 60;
+    } else if (total_mem <= 256 * 1024) {
+        secs = 30 * 60;
+    } else if (total_mem <= 512 * 1024) {
+        secs = 60 * 60;
+    } else if (total_mem <= 1024 * 1024) {
+        secs = 120 * 60;
+    } else {
+        secs = 240 * 60; /* max 4 hrs */
+    }
+
+    return secs;
+}
+
 /*
  * CXL r3.1 Section 8.2.9.9.5.1: Sanitize (Opcode 4400h)
  *

@@ -1668,33 +1703,7 @@ static CXLRetCode cmd_sanitize_overwrite(const struct cxl_cmd *cmd,
     int secs;
 
     total_mem = (ct3d->cxl_dstate.vmem_size + ct3d->cxl_dstate.pmem_size) >> 20;
-    if (total_mem <= 512) {
-        secs = 4;
-    } else if (total_mem <= 1024) {
-        secs = 8;
-    } else if (total_mem <= 2 * 1024) {
-        secs = 15;
-    } else if (total_mem <= 4 * 1024) {
-        secs = 30;
-    } else if (total_mem <= 8 * 1024) {
-        secs = 60;
-    } else if (total_mem <= 16 * 1024) {
-        secs = 2 * 60;
-    } else if (total_mem <= 32 * 1024) {
-        secs = 4 * 60;
-    } else if (total_mem <= 64 * 1024) {
-        secs = 8 * 60;
-    } else if (total_mem <= 128 * 1024) {
-        secs = 15 * 60;
-    } else if (total_mem <= 256 * 1024) {
-        secs = 30 * 60;
-    } else if (total_mem <= 512 * 1024) {
-        secs = 60 * 60;
-    } else if (total_mem <= 1024 * 1024) {
-        secs = 120 * 60;
-    } else {
-        secs = 240 * 60; /* max 4 hrs */
-    }
+    secs = get_sanitize_duration(total_mem);
 
     /* EBUSY other bg cmds as of now */
     cci->bg.runtime = secs * 1000UL;

index dd4250ebe8..cdf405b0f8 100644
@@ -359,6 +359,9 @@ static const Property vhost_scsi_properties[] = {
     DEFINE_PROP_BIT64("t10_pi", VHostSCSICommon, host_features,
                                                  VIRTIO_SCSI_F_T10_PI,
                                                  false),
+    DEFINE_PROP_BIT64("hotplug", VHostSCSICommon, host_features,
+                                                  VIRTIO_SCSI_F_HOTPLUG,
+                                                  false),
     DEFINE_PROP_BOOL("migratable", VHostSCSICommon, migratable, false),
     DEFINE_PROP_BOOL("worker_per_virtqueue", VirtIOSCSICommon,
                      conf.worker_per_virtqueue, false),

index 109b2ebccc..a5b546abe8 100644
@@ -42,6 +42,11 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
     uint8_t *cfg = dev->config + offset;
     uint8_t *wmask;
 
+    if (!pci_is_express(dev)) {
+        error_setg(errp, "PCI Express is required for SR-IOV PF");
+        return false;
+    }
+
     if (pci_is_vf(dev)) {
         error_setg(errp, "a device cannot be a SR-IOV PF and a VF at the same time");
         return false;

index 7a28181d9c..5672bdef89 100644
@@ -329,7 +329,7 @@ struct AMDVIState {
     bool excl_enabled;
 
     hwaddr devtab;               /* base address device table    */
-    size_t devtab_len;           /* device table length          */
+    uint64_t devtab_len;         /* device table length          */
 
     hwaddr cmdbuf;               /* command buffer base address  */
     uint64_t cmdbuf_len;         /* command buffer length        */

62 lines not on this page · raw message

index b925e65b02..69d72ad35c 100644
@@ -4205,9 +4205,30 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus,
     VTDAddressSpace *vtd_dev_as;
     char name[128];
 
+    vtd_iommu_lock(s);
     vtd_dev_as = g_hash_table_lookup(s->vtd_address_spaces, &key);
+    vtd_iommu_unlock(s);
+
     if (!vtd_dev_as) {
-        struct vtd_as_key *new_key = g_malloc(sizeof(*new_key));
+        struct vtd_as_key *new_key;
+        /* Slow path */
+
+        /*
+         * memory_region_add_subregion_overlap requires the bql,
+         * make sure we own it.
+         */
+        BQL_LOCK_GUARD();
+        vtd_iommu_lock(s);
+
+        /* Check again as we released the lock for a moment */
+        vtd_dev_as = g_hash_table_lookup(s->vtd_address_spaces, &key);
+        if (vtd_dev_as) {
+            vtd_iommu_unlock(s);
+            return vtd_dev_as;
+        }
+
+        /* Still nothing, allocate a new address space */
+        new_key = g_malloc(sizeof(*new_key));
 
         new_key->bus = bus;
         new_key->devfn = devfn;

@@ -4298,6 +4319,8 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus,
         vtd_switch_address_space(vtd_dev_as);
 
         g_hash_table_insert(s->vtd_address_spaces, new_key, vtd_dev_as);
+
+        vtd_iommu_unlock(s);
     }
     return vtd_dev_as;
 }

index 31ec144509..1dbc3851b0 100644
@@ -155,6 +155,7 @@ struct VirtIOPCIProxy {
     uint32_t modern_io_bar_idx;
     uint32_t modern_mem_bar_idx;
     int config_cap;
+    uint16_t last_pcie_cap_offset;
     uint32_t flags;
     bool disable_modern;
     bool ignore_backend_features;

index 0fa8fe4955..fee65d3645 100644
@@ -1962,6 +1962,7 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
     uint8_t *config;
     uint32_t size;
     VirtIODevice *vdev = virtio_bus_get_device(bus);
+    int16_t res;
 
     /*
      * Virtio capabilities present without

@@ -2109,6 +2110,14 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
         pci_register_bar(&proxy->pci_dev, proxy->legacy_io_bar_idx,
                          PCI_BASE_ADDRESS_SPACE_IO, &proxy->bar);
     }
+
+    res = pcie_sriov_pf_init_from_user_created_vfs(&proxy->pci_dev,
+                                                   proxy->last_pcie_cap_offset,
+                                                   errp);
+    if (res > 0) {
+        proxy->last_pcie_cap_offset += res;
+        virtio_add_feature(&vdev->host_features, VIRTIO_F_SR_IOV);
+    }
 }
 
 static void virtio_pci_device_unplugged(DeviceState *d)

@@ -2199,7 +2208,7 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
 
     if (pcie_port && pci_is_express(pci_dev)) {
         int pos;
-        uint16_t last_pcie_cap_offset = PCI_CONFIG_SPACE_SIZE;
+        proxy->last_pcie_cap_offset = PCI_CONFIG_SPACE_SIZE;
 
         pos = pcie_endpoint_cap_init(pci_dev, 0);
         assert(pos > 0);

@@ -2216,9 +2225,9 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
         pci_set_word(pci_dev->config + pos + PCI_PM_PMC, 0x3);
 
         if (proxy->flags & VIRTIO_PCI_FLAG_AER) {
-            pcie_aer_init(pci_dev, PCI_ERR_VER, last_pcie_cap_offset,
+            pcie_aer_init(pci_dev, PCI_ERR_VER, proxy->last_pcie_cap_offset,
                           PCI_ERR_SIZEOF, NULL);
-            last_pcie_cap_offset += PCI_ERR_SIZEOF;
+            proxy->last_pcie_cap_offset += PCI_ERR_SIZEOF;
         }
 
         if (proxy->flags & VIRTIO_PCI_FLAG_INIT_DEVERR) {

@@ -2243,9 +2252,9 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
         }
 
         if (proxy->flags & VIRTIO_PCI_FLAG_ATS) {
-            pcie_ats_init(pci_dev, last_pcie_cap_offset,
+            pcie_ats_init(pci_dev, proxy->last_pcie_cap_offset,
                           proxy->flags & VIRTIO_PCI_FLAG_ATS_PAGE_ALIGNED);
-            last_pcie_cap_offset += PCI_EXT_CAP_ATS_SIZEOF;
+            proxy->last_pcie_cap_offset += PCI_EXT_CAP_ATS_SIZEOF;
         }
 
         if (proxy->flags & VIRTIO_PCI_FLAG_INIT_FLR) {

@@ -2273,6 +2282,7 @@ static void virtio_pci_exit(PCIDevice *pci_dev)
                      !pci_bus_is_root(pci_get_bus(pci_dev));
     bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY;
 
+    pcie_sriov_pf_exit(&proxy->pci_dev);
     msix_uninit_exclusive_bar(pci_dev);
     if (proxy->flags & VIRTIO_PCI_FLAG_AER && pcie_port &&
         pci_is_express(pci_dev)) {

index 3ec7be3809..ed6cd50c67 100644
@@ -542,6 +542,19 @@ typedef struct CXLSetFeatureInfo {
 
 struct CXLSanitizeInfo;
 
+typedef struct CXLAlertConfig {
+    uint8_t valid_alerts;
+    uint8_t enable_alerts;
+    uint8_t life_used_crit_alert_thresh;
+    uint8_t life_used_warn_thresh;
+    uint16_t over_temp_crit_alert_thresh;
+    uint16_t under_temp_crit_alert_thresh;
+    uint16_t over_temp_warn_thresh;
+    uint16_t under_temp_warn_thresh;
+    uint16_t cor_vmem_err_warn_thresh;
+    uint16_t cor_pmem_err_warn_thresh;
+} QEMU_PACKED CXLAlertConfig;
+
 struct CXLType3Dev {
     /* Private */
     PCIDevice parent_obj;

@@ -563,6 +576,8 @@ struct CXLType3Dev {
     CXLCCI vdm_fm_owned_ld_mctp_cci;
     CXLCCI ld0_cci;
 
+    CXLAlertConfig alert_config;
+
     /* PCIe link characteristics */
     PCIExpLinkSpeed speed;
     PCIExpLinkWidth width;

129 lines not on this page · raw message

index aacd078118..94e7274912 100644
@@ -843,6 +843,19 @@ static DOEProtocol doe_cdat_prot[] = {
     { }
 };
 
+/* Initialize CXL device alerts with default threshold values. */
+static void init_alert_config(CXLType3Dev *ct3d)
+{
+    ct3d->alert_config = (CXLAlertConfig) {
+        .life_used_crit_alert_thresh = 75,
+        .life_used_warn_thresh = 40,
+        .over_temp_crit_alert_thresh = 35,
+        .under_temp_crit_alert_thresh = 10,
+        .over_temp_warn_thresh = 25,
+        .under_temp_warn_thresh = 20
+    };
+}
+
 static void ct3_realize(PCIDevice *pci_dev, Error **errp)
 {
     ERRP_GUARD();

@@ -910,6 +923,7 @@ static void ct3_realize(PCIDevice *pci_dev, Error **errp)
         goto err_msix_uninit;
     }
 
+    init_alert_config(ct3d);
     pcie_cap_deverr_init(pci_dev);
     /* Leave a bit of room for expansion */
     rc = pcie_aer_init(pci_dev, PCI_ERR_VER, 0x200, PCI_ERR_SIZEOF, errp);

index d21695507f..3ec7be3809 100644
@@ -540,6 +540,8 @@ typedef struct CXLSetFeatureInfo {
     size_t data_size;
 } CXLSetFeatureInfo;
 
+struct CXLSanitizeInfo;
+
 struct CXLType3Dev {
     /* Private */
     PCIDevice parent_obj;

@@ -606,6 +608,8 @@ struct CXLType3Dev {
         uint8_t num_regions; /* 0-8 regions */
         CXLDCRegion regions[DCD_MAX_NUM_REGION];
     } dc;
+
+    struct CXLSanitizeInfo *media_op_sanitize;
 };
 
 #define TYPE_CXL_TYPE3 "cxl-type3"

234 lines not on this page · raw message

index 6d9d3ce90f..039cf1e256 100644
@@ -1594,7 +1594,11 @@ static pcibus_t pci_config_get_bar_addr(PCIDevice *d, int reg,
             pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_OFFSET);
         uint16_t vf_stride =
             pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_STRIDE);
-        uint32_t vf_num = (d->devfn - (pf->devfn + vf_offset)) / vf_stride;
+        uint32_t vf_num = d->devfn - (pf->devfn + vf_offset);
+
+        if (vf_num) {
+            vf_num /= vf_stride;
+        }
 
         if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
             new_addr = pci_get_quad(pf->config + bar);

index 5f8ed1243d..b925e65b02 100644
@@ -1728,8 +1728,6 @@ static bool vtd_as_pt_enabled(VTDAddressSpace *as)
 static bool vtd_switch_address_space(VTDAddressSpace *as)
 {
     bool use_iommu, pt;
-    /* Whether we need to take the BQL on our own */
-    bool take_bql = !bql_locked();
 
     assert(as);
 

@@ -1746,9 +1744,7 @@ static bool vtd_switch_address_space(VTDAddressSpace *as)
      * from vtd_pt_enable_fast_path(). However the memory APIs need
      * it. We'd better make sure we have had it already, or, take it.
      */
-    if (take_bql) {
-        bql_lock();
-    }
+    BQL_LOCK_GUARD();
 
     /* Turn off first then on the other */
     if (use_iommu) {

@@ -1801,10 +1797,6 @@ static bool vtd_switch_address_space(VTDAddressSpace *as)
         memory_region_set_enabled(&as->iommu_ir_fault, false);
     }
 
-    if (take_bql) {
-        bql_unlock();
-    }
-
     return use_iommu;
 }
 

index bffc3719d4..fdd5c4a517 100644
@@ -12,6 +12,7 @@ bool runstate_needs_reset(void);
 void runstate_replay_enable(void);
 
 typedef void VMChangeStateHandler(void *opaque, bool running, RunState state);
+typedef int VMChangeStateHandlerWithRet(void *opaque, bool running, RunState state);
 
 VMChangeStateEntry *qemu_add_vm_change_state_handler(VMChangeStateHandler *cb,
                                                      void *opaque);

@@ -20,21 +21,27 @@ VMChangeStateEntry *qemu_add_vm_change_state_handler_prio(
 VMChangeStateEntry *
 qemu_add_vm_change_state_handler_prio_full(VMChangeStateHandler *cb,
                                            VMChangeStateHandler *prepare_cb,
+                                           VMChangeStateHandlerWithRet *cb_ret,
                                            void *opaque, int priority);
 VMChangeStateEntry *qdev_add_vm_change_state_handler(DeviceState *dev,
                                                      VMChangeStateHandler *cb,
+                                                     VMChangeStateHandlerWithRet *cb_ret,
                                                      void *opaque);
 VMChangeStateEntry *qdev_add_vm_change_state_handler_full(
-    DeviceState *dev, VMChangeStateHandler *cb,
-    VMChangeStateHandler *prepare_cb, void *opaque);
+    DeviceState *dev, VMChangeStateHandler *cb, VMChangeStateHandler *prepare_cb,
+    VMChangeStateHandlerWithRet *cb_ret, void *opaque);
 void qemu_del_vm_change_state_handler(VMChangeStateEntry *e);
 /**
  * vm_state_notify: Notify the state of the VM
  *
  * @running: whether the VM is running or not.
  * @state: the #RunState of the VM.
+ *
+ * Return the result of the callback which has return value.
+ * If no callback has return value, still return 0 and the
+ * upper layer should not do additional processing.
  */
-void vm_state_notify(bool running, RunState state);
+int vm_state_notify(bool running, RunState state);
 
 static inline bool shutdown_caused_by_guest(ShutdownCause cause)
 {

index b54d01d3a2..ea948d18fd 100644
@@ -1802,7 +1802,7 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
      * called after ->start_ioeventfd() has already set blk's AioContext.
      */
     s->change =
-        qdev_add_vm_change_state_handler(dev, virtio_blk_dma_restart_cb, s);
+        qdev_add_vm_change_state_handler(dev, virtio_blk_dma_restart_cb, NULL, s);
 
     blk_ram_registrar_init(&s->blk_ram_registrar, s->blk);
     blk_set_dev_ops(s->blk, &virtio_block_ops, s);

index 7064995578..99c642b558 100644
@@ -40,6 +40,7 @@ static int qdev_get_dev_tree_depth(DeviceState *dev)
  * qdev_add_vm_change_state_handler:
  * @dev: the device that owns this handler
  * @cb: the callback function to be invoked
+ * @cb_ret: the callback function with return value to be invoked
  * @opaque: user data passed to the callback function
  *
  * This function works like qemu_add_vm_change_state_handler() except callbacks

@@ -50,25 +51,30 @@ static int qdev_get_dev_tree_depth(DeviceState *dev)
  * controller's callback is invoked before the children on its bus when the VM
  * starts running.  The order is reversed when the VM stops running.
  *
+ * Note that the parameter `cb` and `cb_ret` are mutually exclusive.
+ *
  * Returns: an entry to be freed with qemu_del_vm_change_state_handler()
  */
 VMChangeStateEntry *qdev_add_vm_change_state_handler(DeviceState *dev,
                                                      VMChangeStateHandler *cb,
+                                                     VMChangeStateHandlerWithRet *cb_ret,
                                                      void *opaque)
 {
-    return qdev_add_vm_change_state_handler_full(dev, cb, NULL, opaque);
+    assert(!cb || !cb_ret);
+    return qdev_add_vm_change_state_handler_full(dev, cb, NULL, cb_ret, opaque);
 }
 
 /*
  * Exactly like qdev_add_vm_change_state_handler() but passes a prepare_cb
- * argument too.
+ * and the cb_ret arguments too.
  */
 VMChangeStateEntry *qdev_add_vm_change_state_handler_full(
-    DeviceState *dev, VMChangeStateHandler *cb,
-    VMChangeStateHandler *prepare_cb, void *opaque)
+    DeviceState *dev, VMChangeStateHandler *cb, VMChangeStateHandler *prepare_cb,
+    VMChangeStateHandlerWithRet *cb_ret, void *opaque)
 {
     int depth = qdev_get_dev_tree_depth(dev);
 
-    return qemu_add_vm_change_state_handler_prio_full(cb, prepare_cb, opaque,
-                                                      depth);
+    assert(!cb || !cb_ret);
+    return qemu_add_vm_change_state_handler_prio_full(cb, prepare_cb, cb_ret,
+                                                      opaque, depth);
 }

index 70be4a7367..9b12ee7f1c 100644
@@ -400,7 +400,7 @@ static void scsi_qdev_realize(DeviceState *qdev, Error **errp)
         return;
     }
     dev->vmsentry = qdev_add_vm_change_state_handler(DEVICE(dev),
-            scsi_dma_restart_cb, dev);
+            scsi_dma_restart_cb, NULL, dev);
 }
 
 static void scsi_qdev_unrealize(DeviceState *qdev)

index 1dceab1b19..b76697bd1a 100644
@@ -1016,7 +1016,7 @@ static int vfio_migration_init(VFIODevice *vbasedev)
                      vfio_vmstate_change_prepare :
                      NULL;
     migration->vm_state = qdev_add_vm_change_state_handler_full(
-        vbasedev->dev, vfio_vmstate_change, prepare_cb, vbasedev);
+        vbasedev->dev, vfio_vmstate_change, prepare_cb, NULL, vbasedev);
     migration_add_notifier(&migration->migration_state,
                            vfio_migration_state_notifier);
 

index 480c2e5036..e3b62522ec 100644
@@ -3489,7 +3489,7 @@ void virtio_init(VirtIODevice *vdev, uint16_t device_id, size_t config_size)
         vdev->config = NULL;
     }
     vdev->vmstate = qdev_add_vm_change_state_handler(DEVICE(vdev),
-            virtio_vmstate_change, vdev);
+            virtio_vmstate_change, NULL, vdev);
     vdev->device_endian = virtio_default_endian();
     vdev->use_guest_notifier_mask = true;
 }

index 2cc5f887ab..d16b0dff98 100644
@@ -299,14 +299,18 @@ static int do_vm_stop(RunState state, bool send_stop)
         if (oldstate == RUN_STATE_RUNNING) {
             pause_all_vcpus();
         }
-        vm_state_notify(0, state);
+        ret = vm_state_notify(0, state);
         if (send_stop) {
             qapi_event_send_stop();
         }
     }
 
     bdrv_drain_all();
-    ret = bdrv_flush_all();
+    /*
+     * Even if vm_state_notify() return failure,
+     * it would be better to flush as before.
+     */
+    ret |= bdrv_flush_all();
     trace_vm_stop_flush_all(ret);
 
     return ret;

index 272801d307..de74d962bc 100644
@@ -297,6 +297,7 @@ void qemu_system_vmstop_request(RunState state)
 struct VMChangeStateEntry {
     VMChangeStateHandler *cb;
     VMChangeStateHandler *prepare_cb;
+    VMChangeStateHandlerWithRet *cb_ret;
     void *opaque;
     QTAILQ_ENTRY(VMChangeStateEntry) entries;
     int priority;

@@ -320,14 +321,15 @@ static QTAILQ_HEAD(, VMChangeStateEntry) vm_change_state_head =
 VMChangeStateEntry *qemu_add_vm_change_state_handler_prio(
         VMChangeStateHandler *cb, void *opaque, int priority)
 {
-    return qemu_add_vm_change_state_handler_prio_full(cb, NULL, opaque,
-                                                      priority);
+    return qemu_add_vm_change_state_handler_prio_full(cb, NULL, NULL,
+                                                      opaque, priority);
 }
 
 /**
  * qemu_add_vm_change_state_handler_prio_full:
  * @cb: the main callback to invoke
  * @prepare_cb: a callback to invoke before the main callback
+ * @cb_ret: the main callback to invoke with return value
  * @opaque: user data passed to the callbacks
  * @priority: low priorities execute first when the vm runs and the reverse is
  *            true when the vm stops

@@ -344,6 +346,7 @@ VMChangeStateEntry *qemu_add_vm_change_state_handler_prio(
 VMChangeStateEntry *
 qemu_add_vm_change_state_handler_prio_full(VMChangeStateHandler *cb,
                                            VMChangeStateHandler *prepare_cb,
+                                           VMChangeStateHandlerWithRet *cb_ret,
                                            void *opaque, int priority)
 {
     VMChangeStateEntry *e;

@@ -352,6 +355,7 @@ qemu_add_vm_change_state_handler_prio_full(VMChangeStateHandler *cb,
     e = g_malloc0(sizeof(*e));
     e->cb = cb;
     e->prepare_cb = prepare_cb;
+    e->cb_ret = cb_ret;
     e->opaque = opaque;
     e->priority = priority;
 

@@ -379,9 +383,10 @@ void qemu_del_vm_change_state_handler(VMChangeStateEntry *e)
     g_free(e);
 }
 
-void vm_state_notify(bool running, RunState state)
+int vm_state_notify(bool running, RunState state)
 {
     VMChangeStateEntry *e, *next;
+    int ret = 0;
 
     trace_vm_state_notify(running, state, RunState_str(state));
 

@@ -393,7 +398,17 @@ void vm_state_notify(bool running, RunState state)
         }
 
         QTAILQ_FOREACH_SAFE(e, &vm_change_state_head, entries, next) {
-            e->cb(e->opaque, running, state);
+            if (e->cb) {
+                e->cb(e->opaque, running, state);
+            } else if (e->cb_ret) {
+                /*
+                 * Here ignore the return value of cb_ret because
+                 * we only care about the stopping the device during
+                 * the VM live migration to indicate whether the
+                 * connection between qemu and backend is normal.
+                 */
+                e->cb_ret(e->opaque, running, state);
+            }
         }
     } else {
         QTAILQ_FOREACH_REVERSE_SAFE(e, &vm_change_state_head, entries, next) {

@@ -403,9 +418,19 @@ void vm_state_notify(bool running, RunState state)
         }
 
         QTAILQ_FOREACH_REVERSE_SAFE(e, &vm_change_state_head, entries, next) {
-            e->cb(e->opaque, running, state);
+            if (e->cb) {
+                e->cb(e->opaque, running, state);
+            } else if (e->cb_ret) {
+                /*
+                 * We should execute all registered callbacks even if
+                 * one of them returns failure, otherwise, some cleanup
+                 * work of the device will be skipped.
+                 */
+                ret |= e->cb_ret(e->opaque, running, state);
+            }
         }
     }
+    return ret;
 }
 
 static ShutdownCause reset_requested;

index 8cf9788bc3..f857a84f11 100644
@@ -74,6 +74,7 @@ static void virtio_net_pci_class_init(ObjectClass *klass, const void *data)
     k->device_id = PCI_DEVICE_ID_VIRTIO_NET;
     k->revision = VIRTIO_PCI_ABI_VERSION;
     k->class_id = PCI_CLASS_NETWORK_ETHERNET;
+    k->sriov_vf_user_creatable = true;
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     device_class_set_props(dc, virtio_net_properties);
     vpciklass->realize = virtio_net_pci_realize;

index 4401f446d9..bd25df033a 100644
@@ -7,6 +7,8 @@
  * COPYING file in the top-level directory.
  */
 
+#include <math.h>
+
 #include "qemu/osdep.h"
 #include "hw/pci/msi.h"
 #include "hw/pci/msix.h"

@@ -56,6 +58,8 @@ enum {
     INFOSTAT    = 0x00,
         #define IS_IDENTIFY   0x1
         #define BACKGROUND_OPERATION_STATUS    0x2
+        #define GET_RESPONSE_MSG_LIMIT         0x3
+        #define SET_RESPONSE_MSG_LIMIT         0x4
         #define BACKGROUND_OPERATION_ABORT     0x5
     EVENTS      = 0x01,
         #define GET_RECORDS   0x0

@@ -413,12 +417,58 @@ static CXLRetCode cmd_infostat_identify(const struct cxl_cmd *cmd,
         is_identify->component_type = 0x3; /* Type 3 */
     }
 
-    /* TODO: Allow this to vary across different CCIs */
-    is_identify->max_message_size = 9; /* 512 bytes - MCTP_CXL_MAILBOX_BYTES */
+    is_identify->max_message_size = (uint8_t)log2(cci->payload_max);
     *len_out = sizeof(*is_identify);
     return CXL_MBOX_SUCCESS;
 }
 
+/* CXL r3.1 section 8.2.9.1.3: Get Response Message Limit (Opcode 0003h) */
+static CXLRetCode cmd_get_response_msg_limit(const struct cxl_cmd *cmd,
+                                             uint8_t *payload_in,
+                                             size_t len_in,
+                                             uint8_t *payload_out,
+                                             size_t *len_out,
+                                             CXLCCI *cci)
+{
+    struct {
+        uint8_t rsp_limit;
+    } QEMU_PACKED *get_rsp_msg_limit = (void *)payload_out;
+    QEMU_BUILD_BUG_ON(sizeof(*get_rsp_msg_limit) != 1);
+
+    get_rsp_msg_limit->rsp_limit = (uint8_t)log2(cci->payload_max);
+
+    *len_out = sizeof(*get_rsp_msg_limit);
+    return CXL_MBOX_SUCCESS;
+}
+
+/* CXL r3.1 section 8.2.9.1.4: Set Response Message Limit (Opcode 0004h) */
+static CXLRetCode cmd_set_response_msg_limit(const struct cxl_cmd *cmd,
+                                             uint8_t *payload_in,
+                                             size_t len_in,
+                                             uint8_t *payload_out,
+                                             size_t *len_out,
+                                             CXLCCI *cci)
+{
+    struct {
+        uint8_t rsp_limit;
+    } QEMU_PACKED *in = (void *)payload_in;
+    QEMU_BUILD_BUG_ON(sizeof(*in) != 1);
+    struct {
+        uint8_t rsp_limit;
+    } QEMU_PACKED *out = (void *)payload_out;
+    QEMU_BUILD_BUG_ON(sizeof(*out) != 1);
+
+    if (in->rsp_limit < 8 || in->rsp_limit > 10) {
+        return CXL_MBOX_INVALID_INPUT;
+    }
+
+    cci->payload_max = 1 << in->rsp_limit;
+    out->rsp_limit = in->rsp_limit;
+
+    *len_out = sizeof(*out);
+    return CXL_MBOX_SUCCESS;
+}
+
 static void cxl_set_dsp_active_bm(PCIBus *b, PCIDevice *d,
                                   void *private)
 {

@@ -3105,6 +3155,10 @@ void cxl_initialize_t3_ld_cci(CXLCCI *cci, DeviceState *d, DeviceState *intf,
 
 static const struct cxl_cmd cxl_cmd_set_t3_fm_owned_ld_mctp[256][256] = {
     [INFOSTAT][IS_IDENTIFY] = { "IDENTIFY", cmd_infostat_identify, 0,  0},
+    [INFOSTAT][GET_RESPONSE_MSG_LIMIT] = { "GET_RESPONSE_MSG_LIMIT",
+                                           cmd_get_response_msg_limit, 0, 0 },
+    [INFOSTAT][SET_RESPONSE_MSG_LIMIT] = { "SET_RESPONSE_MSG_LIMIT",
+                                           cmd_set_response_msg_limit, 1, 0 },
     [LOGS][GET_SUPPORTED] = { "LOGS_GET_SUPPORTED", cmd_logs_get_supported, 0,
                               0 },
     [LOGS][GET_LOG] = { "LOGS_GET_LOG", cmd_logs_get_log, 0x18, 0 },

index 3f6a8bba84..ba71c5069f 100644
@@ -90,6 +90,7 @@ struct PCITestDevState {
     int current;
 
     uint64_t membar_size;
+    bool membar_backed;
     MemoryRegion membar;
 };
 

@@ -258,8 +259,14 @@ static void pci_testdev_realize(PCIDevice *pci_dev, Error **errp)
     pci_register_bar(pci_dev, 1, PCI_BASE_ADDRESS_SPACE_IO, &d->portio);
 
     if (d->membar_size) {
-        memory_region_init(&d->membar, OBJECT(d), "pci-testdev-membar",
-                           d->membar_size);
+        if (d->membar_backed)
+            memory_region_init_ram(&d->membar, OBJECT(d),
+                                   "pci-testdev-membar-backed",
+                                   d->membar_size, NULL);
+        else
+            memory_region_init(&d->membar, OBJECT(d),
+                               "pci-testdev-membar",
+                               d->membar_size);
         pci_register_bar(pci_dev, 2,
                          PCI_BASE_ADDRESS_SPACE_MEMORY |
                          PCI_BASE_ADDRESS_MEM_PREFETCH |

@@ -321,6 +328,7 @@ static void qdev_pci_testdev_reset(DeviceState *dev)
 
 static const Property pci_testdev_properties[] = {
     DEFINE_PROP_SIZE("membar", PCITestDevState, membar_size, 0),
+    DEFINE_PROP_BOOL("membar-backed", PCITestDevState, membar_backed, false),
 };
 
 static void pci_testdev_class_init(ObjectClass *klass, const void *data)

index 345b12eaac..e41d95b0b0 100644
@@ -38,6 +38,8 @@ struct PCIDeviceClass {
     uint16_t subsystem_id;              /* only for header type = 0 */
 
     const char *romfile;                /* rom bar */
+
+    bool sriov_vf_user_creatable;
 };
 
 enum PCIReqIDType {

@@ -177,6 +179,8 @@ struct PCIDevice {
      * realizing the device.
      */
     uint32_t max_bounce_buffer_size;
+
+    char *sriov_pf;
 };
 
 static inline int pci_intx(PCIDevice *pci_dev)

@@ -209,7 +213,7 @@ static inline int pci_is_express_downstream_port(const PCIDevice *d)
 
 static inline int pci_is_vf(const PCIDevice *d)
 {
-    return d->exp.sriov_vf.pf != NULL;
+    return d->sriov_pf || d->exp.sriov_vf.pf != NULL;
 }
 
 static inline uint32_t pci_config_size(const PCIDevice *d)

index c5d2d318d3..f75b8f22ee 100644
@@ -18,6 +18,7 @@
 typedef struct PCIESriovPF {
     uint8_t vf_bar_type[PCI_NUM_REGIONS];   /* Store type for each VF bar */
     PCIDevice **vf;     /* Pointer to an array of num_vfs VF devices */
+    bool vf_user_created; /* If VFs are created by user */
 } PCIESriovPF;
 
 typedef struct PCIESriovVF {

@@ -40,6 +41,23 @@ void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
 void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num,
                                 MemoryRegion *memory);
 
+/**
+ * pcie_sriov_pf_init_from_user_created_vfs() - Initialize PF with user-created
+ *                                              VFs.
+ * @dev: A PCIe device being realized.
+ * @offset: The offset of the SR-IOV capability.
+ * @errp: pointer to Error*, to store an error if it happens.
+ *
+ * Return: The size of added capability. 0 if the user did not create VFs.
+ *         -1 if failed.
+ */
+int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
+                                                 uint16_t offset,
+                                                 Error **errp);
+
+bool pcie_sriov_register_device(PCIDevice *dev, Error **errp);
+void pcie_sriov_unregister_device(PCIDevice *dev);
+
 /*
  * Default (minimal) page size support values
  * as required by the SR/IOV standard:

112 lines not on this page · raw message

343 lines not on this page · raw message

index 3a0ee7e8e7..d21695507f 100644
@@ -176,10 +176,12 @@ typedef struct CXLCCI {
         uint16_t opcode;
         uint16_t complete_pct;
         uint16_t ret_code; /* Current value of retcode */
+        bool aborted;
         uint64_t starttime;
         /* set by each bg cmd, cleared by the bg_timer when complete */
         uint64_t runtime;
         QEMUTimer *timer;
+        QemuMutex lock; /* serializes mbox abort vs timer cb */
     } bg;
 
     /* firmware update */

@@ -201,6 +203,7 @@ typedef struct CXLCCI {
     DeviceState *d;
     /* Pointer to the device hosting the protocol conversion */
     DeviceState *intf;
+    bool initialized;
 } CXLCCI;
 
 typedef struct cxl_device_state {

@@ -316,6 +319,7 @@ void cxl_initialize_mailbox_t3(CXLCCI *cci, DeviceState *d, size_t payload_max);
 void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf,
                                   DeviceState *d, size_t payload_max);
 void cxl_init_cci(CXLCCI *cci, size_t payload_max);
+void cxl_destroy_cci(CXLCCI *cci);
 void cxl_add_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmd_set)[256],
                           size_t payload_max);
 int cxl_process_cci_message(CXLCCI *cci, uint8_t set, uint8_t cmd,

index beb048052e..9008402d1c 100644
@@ -14,5 +14,6 @@
 #define CXL_MBOX_IMMEDIATE_LOG_CHANGE (1 << 4)
 #define CXL_MBOX_SECURITY_STATE_CHANGE (1 << 5)
 #define CXL_MBOX_BACKGROUND_OPERATION (1 << 6)
+#define CXL_MBOX_BACKGROUND_OPERATION_ABORT (1 << 7)
 
 #endif

index 52ad1e4c3f..e150d74457 100644
@@ -95,11 +95,15 @@ static uint64_t mailbox_reg_read(void *opaque, hwaddr offset, unsigned size)
         }
         if (offset == A_CXL_DEV_MAILBOX_STS) {
             uint64_t status_reg = cxl_dstate->mbox_reg_state64[offset / size];
-            if (cci->bg.complete_pct) {
-                status_reg = FIELD_DP64(status_reg, CXL_DEV_MAILBOX_STS, BG_OP,
-                                        0);
-                cxl_dstate->mbox_reg_state64[offset / size] = status_reg;
-            }
+            int bgop;
+
+            qemu_mutex_lock(&cci->bg.lock);
+            bgop = !(cci->bg.complete_pct == 100 || cci->bg.aborted);
+
+            status_reg = FIELD_DP64(status_reg, CXL_DEV_MAILBOX_STS, BG_OP,
+                                    bgop);
+            cxl_dstate->mbox_reg_state64[offset / size] = status_reg;
+            qemu_mutex_unlock(&cci->bg.lock);
         }
         return cxl_dstate->mbox_reg_state64[offset / size];
     default:

146 lines not on this page · raw message

index bba923f8ea..aacd078118 100644
@@ -969,6 +969,7 @@ static void ct3_exit(PCIDevice *pci_dev)
     cxl_doe_cdat_release(cxl_cstate);
     msix_uninit_exclusive_bar(pci_dev);
     g_free(regs->special_ops);
+    cxl_destroy_cci(&ct3d->cci);
     if (ct3d->dc.host_dc) {
         cxl_destroy_dc_regions(ct3d);
         address_space_destroy(&ct3d->dc.host_dc_as);

@@ -1224,12 +1225,17 @@ static void ct3d_reset(DeviceState *dev)
      * Bring up an endpoint to target with MCTP over VDM.
      * This device is emulating an MLD with single LD for now.
      */
+    if (ct3d->vdm_fm_owned_ld_mctp_cci.initialized) {
+        cxl_destroy_cci(&ct3d->vdm_fm_owned_ld_mctp_cci);
+    }
     cxl_initialize_t3_fm_owned_ld_mctpcci(&ct3d->vdm_fm_owned_ld_mctp_cci,
                                           DEVICE(ct3d), DEVICE(ct3d),
                                           512); /* Max payload made up */
+    if (ct3d->ld0_cci.initialized) {
+        cxl_destroy_cci(&ct3d->ld0_cci);
+    }
     cxl_initialize_t3_ld_cci(&ct3d->ld0_cci, DEVICE(ct3d), DEVICE(ct3d),
                              512); /* Max payload made up */
-
 }
 
 static const Property ct3_props[] = {

index bb4b58e115..38800a7156 100644
@@ -232,8 +232,10 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings);
  * Stop the vhost device. After the device is stopped the notifiers
  * can be disabled (@vhost_dev_disable_notifiers) and the device can
  * be torn down (@vhost_dev_cleanup).
+ *
+ * Return: 0 on success, != 0 on error when stopping dev.
  */
-void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings);
+int vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings);
 
 /**
  * DOC: vhost device configuration handling

@@ -333,8 +335,8 @@ int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write);
 
 int vhost_virtqueue_start(struct vhost_dev *dev, struct VirtIODevice *vdev,
                           struct vhost_virtqueue *vq, unsigned idx);
-void vhost_virtqueue_stop(struct vhost_dev *dev, struct VirtIODevice *vdev,
-                          struct vhost_virtqueue *vq, unsigned idx);
+int vhost_virtqueue_stop(struct vhost_dev *dev, struct VirtIODevice *vdev,
+                         struct vhost_virtqueue *vq, unsigned idx);
 
 void vhost_dev_reset_inflight(struct vhost_inflight *inflight);
 void vhost_dev_free_inflight(struct vhost_inflight *inflight);

index 4cae7c1664..fc43853704 100644
@@ -1367,10 +1367,10 @@ fail_alloc_desc:
     return r;
 }
 
-void vhost_virtqueue_stop(struct vhost_dev *dev,
-                          struct VirtIODevice *vdev,
-                          struct vhost_virtqueue *vq,
-                          unsigned idx)
+int vhost_virtqueue_stop(struct vhost_dev *dev,
+                         struct VirtIODevice *vdev,
+                         struct vhost_virtqueue *vq,
+                         unsigned idx)
 {
     int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, idx);
     struct vhost_vring_state state = {

@@ -1380,7 +1380,7 @@ void vhost_virtqueue_stop(struct vhost_dev *dev,
 
     if (virtio_queue_get_desc_addr(vdev, idx) == 0) {
         /* Don't stop the virtqueue which might have not been started */
-        return;
+        return 0;
     }
 
     r = dev->vhost_ops->vhost_get_vring_base(dev, &state);

@@ -1411,6 +1411,7 @@ void vhost_virtqueue_stop(struct vhost_dev *dev,
                        0, virtio_queue_get_avail_size(vdev, idx));
     vhost_memory_unmap(dev, vq->desc, virtio_queue_get_desc_size(vdev, idx),
                        0, virtio_queue_get_desc_size(vdev, idx));
+    return r;
 }
 
 static int vhost_virtqueue_set_busyloop_timeout(struct vhost_dev *dev,

@@ -2135,9 +2136,10 @@ fail_features:
 }
 
 /* Host notifiers must be enabled at this point. */
-void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
+int vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
 {
     int i;
+    int rc = 0;
 
     /* should only be called after backend is connected */
     assert(hdev->vhost_ops);

@@ -2156,10 +2158,10 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
         vhost_dev_set_vring_enable(hdev, false);
     }
     for (i = 0; i < hdev->nvqs; ++i) {
-        vhost_virtqueue_stop(hdev,
-                             vdev,
-                             hdev->vqs + i,
-                             hdev->vq_index + i);
+        rc |= vhost_virtqueue_stop(hdev,
+                                   vdev,
+                                   hdev->vqs + i,
+                                   hdev->vq_index + i);
     }
     if (hdev->vhost_ops->vhost_reset_status) {
         hdev->vhost_ops->vhost_reset_status(hdev);

@@ -2176,6 +2178,7 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
     hdev->started = false;
     vdev->vhost_started = false;
     hdev->vdev = NULL;
+    return rc;
 }
 
 int vhost_net_set_backend(struct vhost_dev *hdev,

index 1eb4358256..109b2ebccc 100644
@@ -42,6 +42,11 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
     uint8_t *cfg = dev->config + offset;
     uint8_t *wmask;
 
+    if (pci_is_vf(dev)) {
+        error_setg(errp, "a device cannot be a SR-IOV PF and a VF at the same time");
+        return false;
+    }
+
     if (total_vfs &&
         (uint32_t)devfn + (uint32_t)(total_vfs - 1) * vf_stride >= PCI_DEVFN_MAX) {
         error_setg(errp, "VF addr overflows");

index 3300f4afb0..2e98cecf64 100644
@@ -2320,51 +2320,6 @@ void virtio_queue_enable(VirtIODevice *vdev, uint32_t queue_index)
     }
 }
 
-static int virtio_set_features_nocheck(VirtIODevice *vdev, uint64_t val);
-
-void virtio_reset(void *opaque)
-{
-    VirtIODevice *vdev = opaque;
-    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
-    int i;
-
-    virtio_set_status(vdev, 0);
-    if (current_cpu) {
-        /* Guest initiated reset */
-        vdev->device_endian = virtio_current_cpu_endian();
-    } else {
-        /* System reset */
-        vdev->device_endian = virtio_default_endian();
-    }
-
-    if (k->get_vhost) {
-        struct vhost_dev *hdev = k->get_vhost(vdev);
-        /* Only reset when vhost back-end is connected */
-        if (hdev && hdev->vhost_ops) {
-            vhost_reset_device(hdev);
-        }
-    }
-
-    if (k->reset) {
-        k->reset(vdev);
-    }
-
-    vdev->start_on_kick = false;
-    vdev->started = false;
-    vdev->broken = false;
-    virtio_set_features_nocheck(vdev, 0);
-    vdev->queue_sel = 0;
-    vdev->status = 0;
-    vdev->disabled = false;
-    qatomic_set(&vdev->isr, 0);
-    vdev->config_vector = VIRTIO_NO_VECTOR;
-    virtio_notify_vector(vdev, vdev->config_vector);
-
-    for(i = 0; i < VIRTIO_QUEUE_MAX; i++) {
-        __virtio_queue_reset(vdev, i);
-    }
-}
-
 void virtio_queue_set_addr(VirtIODevice *vdev, int n, hwaddr addr)
 {
     if (!vdev->vq[n].vring.num) {

@@ -3175,6 +3130,49 @@ int virtio_set_features(VirtIODevice *vdev, uint64_t val)
     return ret;
 }
 
+void virtio_reset(void *opaque)
+{
+    VirtIODevice *vdev = opaque;
+    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
+    int i;
+
+    virtio_set_status(vdev, 0);
+    if (current_cpu) {
+        /* Guest initiated reset */
+        vdev->device_endian = virtio_current_cpu_endian();
+    } else {
+        /* System reset */
+        vdev->device_endian = virtio_default_endian();
+    }
+
+    if (k->get_vhost) {
+        struct vhost_dev *hdev = k->get_vhost(vdev);
+        /* Only reset when vhost back-end is connected */
+        if (hdev && hdev->vhost_ops) {
+            vhost_reset_device(hdev);
+        }
+    }
+
+    if (k->reset) {
+        k->reset(vdev);
+    }
+
+    vdev->start_on_kick = false;
+    vdev->started = false;
+    vdev->broken = false;
+    virtio_set_features_nocheck(vdev, 0);
+    vdev->queue_sel = 0;
+    vdev->status = 0;
+    vdev->disabled = false;
+    qatomic_set(&vdev->isr, 0);
+    vdev->config_vector = VIRTIO_NO_VECTOR;
+    virtio_notify_vector(vdev, vdev->config_vector);
+
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        __virtio_queue_reset(vdev, i);
+    }
+}
+
 static void virtio_device_check_notification_compatibility(VirtIODevice *vdev,
                                                            Error **errp)
 {

index 28125130c6..7a28181d9c 100644
@@ -315,7 +315,8 @@ struct AMDVIPCIState {
 
 struct AMDVIState {
     X86IOMMUState iommu;        /* IOMMU bus device             */
-    AMDVIPCIState pci;          /* IOMMU PCI device             */
+    AMDVIPCIState *pci;         /* IOMMU PCI device             */
+    char *pci_id;               /* ID of AMDVI-PCI device, if user created */
 
     uint32_t version;
 

index f40ad062f9..61851cc840 100644
@@ -2333,10 +2333,10 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id,
     build_append_int_noprefix(table_data, ivhd_blob->len + 24, 2);
     /* DeviceID */
     build_append_int_noprefix(table_data,
-                              object_property_get_int(OBJECT(&s->pci), "addr",
+                              object_property_get_int(OBJECT(s->pci), "addr",
                                                       &error_abort), 2);
     /* Capability offset */
-    build_append_int_noprefix(table_data, s->pci.capab_offset, 2);
+    build_append_int_noprefix(table_data, s->pci->capab_offset, 2);
     /* IOMMU base address */
     build_append_int_noprefix(table_data, s->mr_mmio.addr, 8);
     /* PCI Segment Group */

@@ -2368,10 +2368,10 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id,
     build_append_int_noprefix(table_data, ivhd_blob->len + 40, 2);
     /* DeviceID */
     build_append_int_noprefix(table_data,
-                              object_property_get_int(OBJECT(&s->pci), "addr",
+                              object_property_get_int(OBJECT(s->pci), "addr",
                                                       &error_abort), 2);
     /* Capability offset */
-    build_append_int_noprefix(table_data, s->pci.capab_offset, 2);
+    build_append_int_noprefix(table_data, s->pci->capab_offset, 2);
     /* IOMMU base address */
     build_append_int_noprefix(table_data, s->mr_mmio.addr, 8);
     /* PCI Segment Group */

118 lines not on this page · raw message

index 1b55d8d8a2..3300f4afb0 100644
@@ -2320,6 +2320,8 @@ void virtio_queue_enable(VirtIODevice *vdev, uint32_t queue_index)
     }
 }
 
+static int virtio_set_features_nocheck(VirtIODevice *vdev, uint64_t val);
+
 void virtio_reset(void *opaque)
 {
     VirtIODevice *vdev = opaque;

@@ -2350,7 +2352,7 @@ void virtio_reset(void *opaque)
     vdev->start_on_kick = false;
     vdev->started = false;
     vdev->broken = false;
-    vdev->guest_features = 0;
+    virtio_set_features_nocheck(vdev, 0);
     vdev->queue_sel = 0;
     vdev->status = 0;
     vdev->disabled = false;

index fe38c4c028..6d9d3ce90f 100644
@@ -2522,6 +2522,14 @@ static void pci_add_option_rom(PCIDevice *pdev, bool is_default_rom,
         return;
     }
 
+    if (pci_is_vf(pdev)) {
+        if (pdev->rom_bar > 0) {
+            error_setg(errp, "ROM BAR cannot be enabled for SR-IOV VF");
+        }
+
+        return;
+    }
+
     if (load_file || pdev->romsize == UINT32_MAX) {
         path = qemu_find_file(QEMU_FILE_TYPE_BIOS, pdev->romfile);
         if (path == NULL) {