[PATCH v2] vfio-pci: Accept a non-zero open_count on reset

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



The implementation of close_device() for vfio-pci inspects the
open_count of every device in the device set to determine whether a
reset is needed. This count is always non-zero for the device being
closed, effectively disabling the reset logic.

After commit 2cd8b14aaa66 ("vfio/pci: Move to the device set
infrastructure"), failure to create a new file for a device would cause
the reset to be skipped due to open_count being decremented after
calling close_device() in the error path.

After commit eadd86f835c6 ("vfio: Remove calls to
vfio_group_add_container_user()"), releasing a device would always skip
the reset due to an ordering change in vfio_device_fops_release().

Failing to reset the device leaves it in an unknown state, potentially
causing errors when it is bound to a different driver.

This issue was observed with a Radeon RX Vega 56 [1002:687f] (rev c3)
assigned to a Windows guest. After shutting down the guest, unbinding
the device from vfio-pci, and binding the device to amdgpu:

[  548.007102] [drm:psp_hw_start [amdgpu]] *ERROR* PSP create ring failed!
[  548.027174] [drm:psp_hw_init [amdgpu]] *ERROR* PSP firmware loading failed
[  548.027242] [drm:amdgpu_device_fw_loading [amdgpu]] *ERROR* hw_init of IP block <psp> failed -22
[  548.027306] amdgpu 0000:0a:00.0: amdgpu: amdgpu_device_ip_init failed
[  548.027308] amdgpu 0000:0a:00.0: amdgpu: Fatal error during GPU init

Fixes: 2cd8b14aaa66 ("vfio/pci: Move to the device set infrastructure")
Fixes: eadd86f835c6 ("vfio: Remove calls to vfio_group_add_container_user()")
Signed-off-by: Anthony DeRossi <ajderossi@xxxxxxxxx>
---
v1 -> v2:
- Changed reset behavior instead of open_count ordering
- Retitled from "vfio: Decrement open_count before close_device()"
v1: https://lore.kernel.org/kvm/20221025193820.4412-1-ajderossi@xxxxxxxxx/

 drivers/vfio/pci/vfio_pci_core.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index badc9d828cac..bd50525b8a13 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -174,7 +174,7 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_core_device *vdev)
 }
 
 struct vfio_pci_group_info;
-static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set);
+static void vfio_pci_core_try_reset(struct vfio_pci_core_device *vdev);
 static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
 				      struct vfio_pci_group_info *groups);
 
@@ -667,7 +667,7 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
 out:
 	pci_disable_device(pdev);
 
-	vfio_pci_dev_set_try_reset(vdev->vdev.dev_set);
+	vfio_pci_core_try_reset(vdev);
 
 	/* Put the pm-runtime usage counter acquired during enable */
 	if (!disable_idle_d3)
@@ -2483,14 +2483,18 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
 	return ret;
 }
 
-static bool vfio_pci_dev_set_needs_reset(struct vfio_device_set *dev_set)
+static bool vfio_pci_core_needs_reset(struct vfio_pci_core_device *vdev)
 {
+	struct vfio_device_set *dev_set = vdev->vdev.dev_set;
 	struct vfio_pci_core_device *cur;
 	bool needs_reset = false;
 
+	if (vdev->vdev.open_count > 1)
+		return false;
+
 	list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) {
-		/* No VFIO device in the set can have an open device FD */
-		if (cur->vdev.open_count)
+		/* Only the VFIO device being reset can have an open FD */
+		if (cur != vdev && cur->vdev.open_count)
 			return false;
 		needs_reset |= cur->needs_reset;
 	}
@@ -2498,19 +2502,20 @@ static bool vfio_pci_dev_set_needs_reset(struct vfio_device_set *dev_set)
 }
 
 /*
- * If a bus or slot reset is available for the provided dev_set and:
+ * If a bus or slot reset is available for the provided device and:
  *  - All of the devices affected by that bus or slot reset are unused
  *  - At least one of the affected devices is marked dirty via
  *    needs_reset (such as by lack of FLR support)
  * Then attempt to perform that bus or slot reset.
  */
-static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
+static void vfio_pci_core_try_reset(struct vfio_pci_core_device *vdev)
 {
+	struct vfio_device_set *dev_set = vdev->vdev.dev_set;
 	struct vfio_pci_core_device *cur;
 	struct pci_dev *pdev;
 	bool reset_done = false;
 
-	if (!vfio_pci_dev_set_needs_reset(dev_set))
+	if (!vfio_pci_core_needs_reset(vdev))
 		return;
 
 	pdev = vfio_pci_dev_set_resettable(dev_set);
-- 
2.37.4




[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux