Merge tag 'drm-fixes-2025-12-20' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "rc2 fixes for the week, mostly xe, with amdgpu as usual. Then a
  smattering of small fixes across the core/tests/panel and amdxdna.

  I expect things will be quiet for rc3/4 as teams take a break, and I'm
  travelling but will keep an eye on things.

  core:
   - fix gem handle leak on DRM_IOCTL_GEM_CHANGE_HANDLE

  tests:
   - add EDEADLK handling

  amdgpu:
   - Fix no_console_suspend handling
   - DCN 3.5.x seamless boot fixes
   - DP audio fix
   - Fix race in GPU recovery
   - SMU 14 OD fix

  amdkfd:
   - Event fix

  xe:
   - Limit num_syncs to prevent oversized kernel allocations
   - Disallow 0 OA property values
   - Disallow 0 EU stall property values
   - Fix kobject leak
   - Workaround
   - Loop variable reference fix
   - Fix a CONFIG corner-case incorrect number of argument
   - Skip reason prefix while emitting array
   - VF migration fix
   - Fix context in mei interrupt top half
   - Don't include the CCS metadata in the dma-buf sg-table
   - VF queueing recovery work fix
   - Increase TDF timeout
   - GT reset registers vs scheduler ordering fix
   - Adjust long-running workload timeslices
   - Always set OA_OAGLBCTXCTRL_COUNTER_RESUME
   - Fix a return value
   - Drop preempt-fences when destroying imported dma-bufs
   - Use usleep_range for accurate long-running workload timeslicing

  amdxdna:
   - don't load virtualized

  panel:
   - fix visionox-rm69299 Kconfig dependency
   - sony-td4353-jdi probing fix"

* tag 'drm-fixes-2025-12-20' of https://gitlab.freedesktop.org/drm/kernel: (34 commits)
  drm/xe: Use usleep_range for accurate long-running workload timeslicing
  drm/xe: Drop preempt-fences when destroying imported dma-bufs.
  drm/xe/eustall: Disallow 0 EU stall property values
  drm/xe/oa: Disallow 0 OA property values
  drm/xe/xe_sriov_vfio: Fix return value in xe_sriov_vfio_migration_supported()
  drm/xe/oa: Always set OAG_OAGLBCTXCTRL_COUNTER_RESUME
  drm/xe: Adjust long-running workload timeslices to reasonable values
  drm/xe/oa: Limit num_syncs to prevent oversized allocations
  drm/xe: Limit num_syncs to prevent oversized allocations
  drm/amdkfd: Fix improper NULL termination of queue restore SMI event string
  drm/amd/pm: restore SCLK settings after S0ix resume
  drm/amdgpu: fix a job->pasid access race in gpu recovery
  drm/amd/display: Fix DP no audio issue
  drm/amd/display: Fix scratch registers offsets for DCN351
  drm/amd/display: Fix scratch registers offsets for DCN35
  drm/amd: Resume the device in thaw() callback when console suspend is disabled
  drm/panel: visionox-rm69299: Depend on BACKLIGHT_CLASS_DEVICE
  accel/amdxdna: Block running under a hypervisor
  drm/panel: sony-td4353-jdi: Enable prepare_prev_first
  drm/xe: Restore engine registers before restarting schedulers after GT reset
  ...

2 files changed, 12 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 58c3ffe707d1..12201b8e99b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6613,6 +6613,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	struct amdgpu_hive_info *hive = NULL;
 	int r = 0;
 	bool need_emergency_restart = false;
+	/* save the pasid here as the job may be freed before the end of the reset */
+	int pasid = job ? job->pasid : -EINVAL;
 
 	/*
 	 * If it reaches here because of hang/timeout and a RAS error is
@@ -6713,8 +6715,12 @@ end_reset:
 	if (!r) {
 		struct amdgpu_task_info *ti = NULL;
 
-		if (job)
-			ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid);
+		/*
+		 * The job may already be freed at this point via the sched tdr workqueue so
+		 * use the cached pasid.
+		 */
+		if (pasid >= 0)
+			ti = amdgpu_vm_get_task_info_pasid(adev, pasid);
 
 		drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE,
 				     ti ? &ti->task : NULL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 2dfbddcef9ab..848e6b7db482 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -33,6 +33,7 @@
 #include <drm/drm_vblank.h>
 
 #include <linux/cc_platform.h>
+#include <linux/console.h>
 #include <linux/dynamic_debug.h>
 #include <linux/module.h>
 #include <linux/mmu_notifier.h>
@@ -2704,7 +2705,9 @@ static int amdgpu_pmops_thaw(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
 	/* do not resume device if it's normal hibernation */
-	if (!pm_hibernate_is_recovering() && !pm_hibernation_mode_is_suspend())
+	if (console_suspend_enabled &&
+	    !pm_hibernate_is_recovering() &&
+	    !pm_hibernation_mode_is_suspend())
 		return 0;
 
 	return amdgpu_device_resume(drm_dev, true);