[RFC PATCH 3/5] vfio/pci: Refuse to reset an SR-IOV PF with enabled VFs

[Alex Williamson <alex.williamson@nvidia.com>]

The vfio-pci hot-reset interface VFIO_DEVICE_PCI_HOT_RESET does not
take into account whether an SR-IOV PF has active VFs.  The VFs appear
on a virtual bus, which is not enumerated in collecting affected
devices.

Move the burden to the user when active VFs are present, require that
there are no VFs present on SR-IOV capable PFs in order to conduct a
hot reset.

Fixes: 137e5531351d ("vfio/pci: Add sriov_configure support")
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Alex Williamson <alex.williamson@nvidia.com>
---
 drivers/vfio/pci/vfio_pci_core.c | 15 +++++++++++++--
 include/uapi/linux/vfio.h        |  3 +++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 9757b171791c..956a05ca12e5 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -894,6 +894,17 @@ static int vfio_pci_count_devs(struct pci_dev *pdev, void *data)
 	return 0;
 }
 
+/*
+ * PCI walk callback to check for SR-IOV PFs with active VFs.  VFs are not
+ * enumerated when determining affected devices and may be owned by separate
+ * userspace processes from the PF.  It's therefore the user's responsibility
+ * to teardown VFs for any affected PF before performing a hot-reset.
+ */
+static int vfio_pci_dev_has_vfs(struct pci_dev *pdev, void *data)
+{
+	return pci_num_vf(pdev) ? -EBUSY : 0;
+}
+
 struct vfio_pci_fill_info {
 	struct vfio_device *vdev;
 	struct vfio_pci_dependent_device *devices;
@@ -2598,7 +2609,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
 	list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list)
 		vfio_pci_set_power_state(vdev, PCI_D0);
 
-	ret = pci_reset_bus(pdev);
+	ret = pci_reset_bus_cond(pdev, vfio_pci_dev_has_vfs, NULL);
 
 	vdev = list_last_entry(&dev_set->device_list,
 			       struct vfio_pci_core_device, vdev.dev_set_list);
@@ -2661,7 +2672,7 @@ static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
 	if (vfio_pci_dev_set_pm_runtime_get(dev_set))
 		return;
 
-	if (!pci_reset_bus(pdev))
+	if (!pci_reset_bus_cond(pdev, vfio_pci_dev_has_vfs, NULL))
 		reset_done = true;
 
 	list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) {
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 5de618a3a5ee..8603959f1735 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -772,6 +772,9 @@ struct vfio_pci_hot_reset_info {
  * Mixed usage of legacy groups and cdevs across the set of affected
  * devices is not supported.
  *
+ * Hot reset of SR-IOV PFs with active VFs is not supported, SR-IOV
+ * should first be disabled on any affected PF.
+ *
  * Return: 0 on success, -errno on failure.
  */
 struct vfio_pci_hot_reset {
-- 
2.53.0