vfio/pci: Extend VFIO_DEVICE_GET_PCI_HOT_RESET_INFO for vfio device cdev

This allows VFIO_DEVICE_GET_PCI_HOT_RESET_INFO ioctl use the iommufd_ctx
of the cdev device to check the ownership of the other affected devices.

When VFIO_DEVICE_GET_PCI_HOT_RESET_INFO is called on an IOMMUFD managed
device, the new flag VFIO_PCI_HOT_RESET_FLAG_DEV_ID is reported to indicate
the values returned are IOMMUFD devids rather than group IDs as used when
accessing vfio devices through the conventional vfio group interface.
Additionally the flag VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED will be reported
in this mode if all of the devices affected by the hot-reset are owned by
either virtue of being directly bound to the same iommufd context as the
calling device, or implicitly owned via a shared IOMMU group.

Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Yanting Jiang <yanting.jiang@intel.com>
Tested-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20230718105542.4138-9-yi.l.liu@intel.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 47 insertions, 7 deletions

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 5b5316a5484a..32506c5539b9 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -27,6 +27,7 @@
 #include <linux/vgaarb.h>
 #include <linux/nospec.h>
 #include <linux/sched/mm.h>
+#include <linux/iommufd.h>
 #if IS_ENABLED(CONFIG_EEH)
 #include <asm/eeh.h>
 #endif
@@ -779,26 +780,56 @@ struct vfio_pci_fill_info {
 	int max;
 	int cur;
 	struct vfio_pci_dependent_device *devices;
+	struct vfio_device *vdev;
+	u32 flags;
 };
 
 static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
 {
 	struct vfio_pci_fill_info *fill = data;
-	struct iommu_group *iommu_group;
 
 	if (fill->cur == fill->max)
 		return -EAGAIN; /* Something changed, try again */
 
-	iommu_group = iommu_group_get(&pdev->dev);
-	if (!iommu_group)
-		return -EPERM; /* Cannot reset non-isolated devices */
+	if (fill->flags & VFIO_PCI_HOT_RESET_FLAG_DEV_ID) {
+		struct iommufd_ctx *iommufd = vfio_iommufd_device_ictx(fill->vdev);
+		struct vfio_device_set *dev_set = fill->vdev->dev_set;
+		struct vfio_device *vdev;
 
-	fill->devices[fill->cur].group_id = iommu_group_id(iommu_group);
+		/*
+		 * hot-reset requires all affected devices be represented in
+		 * the dev_set.
+		 */
+		vdev = vfio_find_device_in_devset(dev_set, &pdev->dev);
+		if (!vdev) {
+			fill->devices[fill->cur].devid = VFIO_PCI_DEVID_NOT_OWNED;
+		} else {
+			int id = vfio_iommufd_get_dev_id(vdev, iommufd);
+
+			if (id > 0)
+				fill->devices[fill->cur].devid = id;
+			else if (id == -ENOENT)
+				fill->devices[fill->cur].devid = VFIO_PCI_DEVID_OWNED;
+			else
+				fill->devices[fill->cur].devid = VFIO_PCI_DEVID_NOT_OWNED;
+		}
+		/* If devid is VFIO_PCI_DEVID_NOT_OWNED, clear owned flag. */
+		if (fill->devices[fill->cur].devid == VFIO_PCI_DEVID_NOT_OWNED)
+			fill->flags &= ~VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED;
+	} else {
+		struct iommu_group *iommu_group;
+
+		iommu_group = iommu_group_get(&pdev->dev);
+		if (!iommu_group)
+			return -EPERM; /* Cannot reset non-isolated devices */
+
+		fill->devices[fill->cur].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++;
-	iommu_group_put(iommu_group);
 	return 0;
 }
 
@@ -1270,17 +1301,26 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
 		return -ENOMEM;
 
 	fill.devices = devices;
+	fill.vdev = &vdev->vdev;
 
+	if (vfio_device_cdev_opened(&vdev->vdev))
+		fill.flags |= VFIO_PCI_HOT_RESET_FLAG_DEV_ID |
+			     VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED;
+
+	mutex_lock(&vdev->vdev.dev_set->lock);
 	ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_fill_devs,
 					    &fill, slot);
+	mutex_unlock(&vdev->vdev.dev_set->lock);
 
 	/*
 	 * 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)
+	if (!ret) {
 		hdr.count = fill.cur;
+		hdr.flags = fill.flags;
+	}
 
 reset_info_exit:
 	if (copy_to_user(arg, &hdr, minsz))