Merge tag 'drm-fixes-2024-02-16' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular weekly fixes, nothing too major, mostly amdgpu, then i915, xe,
  msm and nouveau with some scattered bits elsewhere.

  crtc:
   - fix uninit variable

  prime:
   - support > 4GB page arrays

  buddy:
   - fix error handling in allocations

  i915:
   - fix blankscreen on JSL chromebooks
   - stable fix to limit DP sst link rates

  xe:
   - Fix an out-of-bounds shift.
   - Fix the display code thinking xe uses shmem
   - Fix a warning about index out-of-bound
   - Fix a clang-16 compilation warning

  amdgpu:
   - PSR fixes
   - Suspend/resume fixes
   - Link training fix
   - Aspect ratio fix
   - DCN 3.5 fixes
   - VCN 4.x fix
   - GFX 11 fix
   - Misc display fixes
   - Misc small fixes

  amdkfd:
   - Cache size reporting fix
   - SIMD distribution fix

  msm:
   - GPU:
   - dmabuf vmap fix
   - a610 UBWC corruption fix (incorrect hbb)
   - revert a commit that was making GPU recovery unreliable
   - tlb invalidation fix

  ivpu:
   - suspend/resume fix

  nouveau:
   - fix scheduler cleanup path
   - fix pointless scheduler creation
   - fix kvalloc argument order

  rockchip:
   - vop2 locking fix"

* tag 'drm-fixes-2024-02-16' of git://anongit.freedesktop.org/drm/drm: (38 commits)
  drm/amdgpu: Fix implicit assumtion in gfx11 debug flags
  drm/amdkfd: update SIMD distribution algo for GFXIP 9.4.2 onwards
  drm/amd/display: Increase ips2_eval delay for DCN35
  drm/amdgpu/display: Initialize gamma correction mode variable in dcn30_get_gamcor_current()
  drm/amdgpu/soc21: update VCN 4 max HEVC encoding resolution
  drm/amd/display: fixed integer types and null check locations
  drm/amd/display: Fix array-index-out-of-bounds in dcn35_clkmgr
  drm/amd/display: Preserve original aspect ratio in create stream
  drm/amd/display: Fix possible NULL dereference on device remove/driver unload
  Revert "drm/amd/display: increased min_dcfclk_mhz and min_fclk_mhz"
  drm/amd/display: Add align done check
  Revert "drm/amd: flush any delayed gfxoff on suspend entry"
  drm/amd: Stop evicting resources on APUs in suspend
  drm/amd/display: Fix possible buffer overflow in 'find_dcfclk_for_voltage()'
  drm/amd/display: Fix possible use of uninitialized 'max_chunks_fbc_mode' in 'calculate_bandwidth()'
  drm/amd/display: Initialize 'wait_time_microsec' variable in link_dp_training_dpia.c
  drm/amd/display: Fix && vs || typos
  drm/amdkfd: Fix L2 cache size reporting in GFX9.4.3
  drm/amdgpu: make damage clips support configurable
  drm/msm: Wire up tlb ops
  ...

1 files changed, 9 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fdde7488d0ed..94bdb5fa6ebc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4514,13 +4514,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	int i, r;
 
+	amdgpu_choose_low_power_state(adev);
+
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
 	/* Evict the majority of BOs before starting suspend sequence */
 	r = amdgpu_device_evict_resources(adev);
 	if (r)
-		return r;
+		goto unprepare;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
@@ -4529,10 +4531,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
 			continue;
 		r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev);
 		if (r)
-			return r;
+			goto unprepare;
 	}
 
 	return 0;
+
+unprepare:
+	adev->in_s0ix = adev->in_s3 = false;
+
+	return r;
 }
 
 /**
@@ -4569,7 +4576,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
-	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
 
 	amdgpu_ras_suspend(adev);