Merge tag 'drm-fixes-2024-03-01' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Bunch of fixes, xe, amdgpu, nouveau and tegra all have a few. Then
  drm/bridge including some drivers/soc fallout fixes. The biggest thing
  in here is a new unit test for some buddy allocator fixes, otherwise a
  misc fbcon, ttm unit test and one msm revert.

  Seems pretty normal for this stage.

  buddy:
   - two allocation fixes + unit test

  fbcon:
   - font restore syzkaller fix

  ttm:
   - kunit test fix

  bridge:
   - fix aux-hpd leaks
   - fix aux-hpd registration
   - fix use after free in soc/qcom
   - fix boot on soc/qcom

  xe:
   - A couple of tracepoint updates from Priyanka and Lucas
   - Make sure BINDs are completed before accepting UNBINDs on LR vms
   - Don't arbitrarily restrict max number of batched binds
   - Add uapi for dumpable bos (agreed on IRC)
   - Remove unused uapi flags and a leftover comment
   - A couple of fixes related to the execlist backend

  msm:
   - DP: Revert a change which was causing a HDP regression

  amdgpu:
   - Fix potential buffer overflow
   - Fix power min cap
   - Suspend/resume fix
   - SI PM fix
   - eDP fix

  nouveau:
   - fix a misreported VRAM sizing
   - fix a regression in suspend/resume due to freeing

  tegra:
   - host1x reset fix
   - only remove existing driver if display is possible"

* tag 'drm-fixes-2024-03-01' of https://gitlab.freedesktop.org/drm/kernel: (32 commits)
  drm/nouveau: keep DMA buffers required for suspend/resume
  nouveau: report byte usage in VRAM usage
  drm/xe/xe_trace: Add move_lacks_source detail to xe_bo_move trace
  drm/xe: Deny unbinds if uapi ufence pending
  drm/xe: Expose user fence from xe_sync_entry
  drm/xe: Use pointers in trace events
  drm/xe/xe_bo_move: Enhance xe_bo_move trace
  drm/xe/mmio: fix build warning for BAR resize on 32-bit
  drm/xe: get rid of MAX_BINDS
  drm/xe: Use vmalloc for array of bind allocation in bind IOCTL
  drm/xe: Don't support execlists in xe_gt_tlb_invalidation layer
  drm/xe: Fix execlist splat
  drm/xe/uapi: Remove unused flags
  drm/xe/uapi: Remove DRM_XE_VM_BIND_FLAG_ASYNC comment left over
  drm/xe: Add uapi for dumpable bos
  drm/amd/display: Add monitor patch for specific eDP
  Revert "drm/msm/dp: use drm_bridge_hpd_notify() to report HPD status changes"
  drm/tests/drm_buddy: add alloc_range_bias test
  drm/buddy: check range allocation matches alignment
  drm/buddy: fix range bias
  ...

1 files changed, 25 insertions, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index c64c01e2944a..1c614451dead 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -574,11 +574,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 		return AMD_RESET_METHOD_MODE1;
 }
 
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg;
+
+	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+	 * 2) S3 suspend abort and TOS already launched.
+	 */
+	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+			!adev->suspend_complete &&
+			sol_reg)
+		return true;
+
+	return false;
+}
+
 static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	/* original raven doesn't have full asic reset */
-	if ((adev->apu_flags & AMD_APU_IS_RAVEN) ||
-	    (adev->apu_flags & AMD_APU_IS_RAVEN2))
+	/* On the latest Raven, the GPU reset can be performed
+	 * successfully. So now, temporarily enable it for the
+	 * S3 suspend abort case.
+	 */
+	if (((adev->apu_flags & AMD_APU_IS_RAVEN) ||
+	    (adev->apu_flags & AMD_APU_IS_RAVEN2)) &&
+		!soc15_need_reset_on_resume(adev))
 		return 0;
 
 	switch (soc15_asic_reset_method(adev)) {
@@ -1298,24 +1321,6 @@ static int soc15_common_suspend(void *handle)
 	return soc15_common_hw_fini(adev);
 }
 
-static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
-{
-	u32 sol_reg;
-
-	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
-
-	/* Will reset for the following suspend abort cases.
-	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
-	 * 2) S3 suspend abort and TOS already launched.
-	 */
-	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
-			!adev->suspend_complete &&
-			sol_reg)
-		return true;
-
-	return false;
-}
-
 static int soc15_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;