[Intel-gfx] [PATCH v7 8/9] vfio/pci: Extend VFIO_DEVICE_GET_PCI_HOT_RESET_INFO for vfio device cdev

[Jason Gunthorpe]

On Wed, Jun 14, 2023 at 10:35:10AM +0000, Liu, Yi L wrote:

> > -	if (fill->cur == fill->max)
> > -		return -EAGAIN; /* Something changed, try again */
> > +	if (fill->devices_end >= fill->devices)
> > +		return -ENOSPC;
> 
> This should be fill->devices_end <= fill->devices. 

Yep

> Even it's corrected. The
> new code does not return -EAGAIN. 

Right, there is no EAGAIN. If the caller didn't provide enough space
the previous version returned ENOSPC:

> > -	if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) {
> > -		ret = -ENOSPC;
> > -		hdr.count = fill.max;
> > -		goto reset_info_exit;
> > -	}

-EAGAIN basically means the kernel internally malfunctioned - eg it
allocated too little space for the actual size of devices. That is no
longer possible in this version so it should never return -EAGAIN.

> And if return -ENOSPC, the expected
> size should be returned. But I didn't see it. As the hunk below[1] is removed,
> seems no way to know how many memory it requires.

Yes, I missed that, it should keep counting

Like this then

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index b0eadafcbcf502..05c064896a7a94 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -775,19 +775,25 @@ static int vfio_pci_count_devs(struct pci_dev *pdev, void *data)
 }
 
 struct vfio_pci_fill_info {
-	int max;
-	int cur;
-	struct vfio_pci_dependent_device *devices;
+	struct vfio_pci_dependent_device __user *devices;
+	struct vfio_pci_dependent_device __user *devices_end;
 	struct vfio_device *vdev;
+	u32 count;
 	u32 flags;
 };
 
 static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
 {
+	struct vfio_pci_dependent_device info = {
+		.segment = pci_domain_nr(pdev->bus),
+		.bus = pdev->bus->number,
+		.devfn = pdev->devfn,
+	};
 	struct vfio_pci_fill_info *fill = data;
 
-	if (fill->cur == fill->max)
-		return -EAGAIN; /* Something changed, try again */
+	fill.count++;
+	if (fill->devices >= fill->devices_end)
+		return 0;
 
 	if (fill->flags & VFIO_PCI_HOT_RESET_FLAG_DEV_ID) {
 		struct iommufd_ctx *iommufd = vfio_iommufd_device_ictx(fill->vdev);
@@ -800,12 +806,12 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
 		 */
 		vdev = vfio_find_device_in_devset(dev_set, &pdev->dev);
 		if (!vdev)
-			fill->devices[fill->cur].devid = VFIO_PCI_DEVID_NOT_OWNED;
+			info.devid = VFIO_PCI_DEVID_NOT_OWNED;
 		else
-			fill->devices[fill->cur].devid =
-				vfio_iommufd_device_hot_reset_devid(vdev, iommufd);
+			info.devid = vfio_iommufd_device_hot_reset_devid(
+				vdev, iommufd);
 		/* If devid is VFIO_PCI_DEVID_NOT_OWNED, clear owned flag. */
-		if (fill->devices[fill->cur].devid == VFIO_PCI_DEVID_NOT_OWNED)
+		if (info.devid == VFIO_PCI_DEVID_NOT_OWNED)
 			fill->flags &= ~VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED;
 	} else {
 		struct iommu_group *iommu_group;
@@ -814,13 +820,13 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
 		if (!iommu_group)
 			return -EPERM; /* Cannot reset non-isolated devices */
 
-		fill->devices[fill->cur].group_id = iommu_group_id(iommu_group);
+		info.group_id = iommu_group_id(iommu_group);
 		iommu_group_put(iommu_group);
 	}
-	fill->devices[fill->cur].segment = pci_domain_nr(pdev->bus);
-	fill->devices[fill->cur].bus = pdev->bus->number;
-	fill->devices[fill->cur].devfn = pdev->devfn;
-	fill->cur++;
+
+	if (copy_to_user(fill->devices, &info, sizeof(info)))
+		return -EFAULT;
+	fill->devices++;
 	return 0;
 }
 
@@ -1212,8 +1218,7 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
 	unsigned long minsz =
 		offsetofend(struct vfio_pci_hot_reset_info, count);
 	struct vfio_pci_hot_reset_info hdr;
-	struct vfio_pci_fill_info fill = { 0 };
-	struct vfio_pci_dependent_device *devices = NULL;
+	struct vfio_pci_fill_info fill = {};
 	bool slot = false;
 	int ret = 0;
 
@@ -1231,29 +1236,9 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
 	else if (pci_probe_reset_bus(vdev->pdev->bus))
 		return -ENODEV;
 
-	/* How many devices are affected? */
-	ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs,
-					    &fill.max, slot);
-	if (ret)
-		return ret;
-
-	WARN_ON(!fill.max); /* Should always be at least one */
-
-	/*
-	 * If there's enough space, fill it now, otherwise return -ENOSPC and
-	 * the number of devices affected.
-	 */
-	if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) {
-		ret = -ENOSPC;
-		hdr.count = fill.max;
-		goto reset_info_exit;
-	}
-
-	devices = kcalloc(fill.max, sizeof(*devices), GFP_KERNEL);
-	if (!devices)
-		return -ENOMEM;
-
-	fill.devices = devices;
+	fill.devices = arg->devices;
+	fill.devices_end = arg->devices +
+			   (hdr.argsz - sizeof(hdr)) / sizeof(arg->devices[0]);
 	fill.vdev = &vdev->vdev;
 
 	if (vfio_device_cdev_opened(&vdev->vdev))
@@ -1264,29 +1249,17 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
 	ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_fill_devs,
 					    &fill, slot);
 	mutex_unlock(&vdev->vdev.dev_set->lock);
+	if (ret)
+		return ret;
 
-	/*
-	 * If a device was removed between counting and filling, we may come up
-	 * short of fill.max.  If a device was added, we'll have a return of
-	 * -EAGAIN above.
-	 */
-	if (!ret) {
-		hdr.count = fill.cur;
-		hdr.flags = fill.flags;
-	}
-
-reset_info_exit:
+	hdr.count = fill.count;
+	hdr.flags = fill.flags;
 	if (copy_to_user(arg, &hdr, minsz))
-		ret = -EFAULT;
+		return -EFAULT;
 
-	if (!ret) {
-		if (copy_to_user(&arg->devices, devices,
-				 hdr.count * sizeof(*devices)))
-			ret = -EFAULT;
-	}
-
-	kfree(devices);
-	return ret;
+	if (fill.count != fill.devices - arg->devices)
+		return -ENOSPC;
+	return 0;
 }
 
 static int