Merge tag 'drm-next-2023-11-07' of git://anongit.freedesktop.org/drm/drm

Pull more drm updates from Dave Airlie:
 "Geert pointed out I missed the renesas reworks in my main pull, so
  this pull contains the renesas next work for atomic conversion and DT
  support.

  It also contains a bunch of amdgpu and some small ssd13xx fixes.

  renesas:
   - atomic conversion
   - DT support

  ssd13xx:
   - dt binding fix for ssd132x
   - Initialize ssd130x crtc_state to NULL.

  amdgpu:
   - Fix RAS support check
   - RAS fixes
   - MES fixes
   - SMU13 fixes
   - Contiguous memory allocation fix
   - BACO fixes
   - GPU reset fixes
   - Min power limit fixes
   - GFX11 fixes
   - USB4/TB hotplug fixes
   - ARM regression fix
   - GFX9.4.3 fixes
   - KASAN/KCSAN stack size check fixes
   - SR-IOV fixes
   - SMU14 fixes
   - PSP13 fixes
   - Display blend fixes
   - Flexible array size fixes

  amdkfd:
   - GPUVM fix

  radeon:
   - Flexible array size fixes"

* tag 'drm-next-2023-11-07' of git://anongit.freedesktop.org/drm/drm: (83 commits)
  drm/amd/display: Enable fast update on blendTF change
  drm/amd/display: Fix blend LUT programming
  drm/amd/display: Program plane color setting correctly
  drm/amdgpu: Query and report boot status
  drm/amdgpu: Add psp v13 function to query boot status
  drm/amd/swsmu: remove fw version check in sw_init.
  drm/amd/swsmu: update smu v14_0_0 driver if and metrics table
  drm/amdgpu: Add C2PMSG_109/126 reg field shift/masks
  drm/amdgpu: Optimize the asic type fix code
  drm/amdgpu: fix GRBM read timeout when do mes_self_test
  drm/amdgpu: check recovery status of xgmi hive in ras_reset_error_count
  drm/amd/pm: only check sriov vf flag once when creating hwmon sysfs
  drm/amdgpu: Attach eviction fence on alloc
  drm/amdkfd: Improve amdgpu_vm_handle_moved
  drm/amd/display: Increase frame warning limit with KASAN or KCSAN in dml2
  drm/amd/display: Avoid NULL dereference of timing generator
  drm/amdkfd: Update cache info for GFX 9.4.3
  drm/amdkfd: Populate cache info for GFX 9.4.3
  drm/amdgpu: don't put MQDs in VRAM on ARM | ARM64
  drm/amdgpu/smu13: drop compute workload workaround
  ...

1 files changed, 14 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 303fbb6a48b6..b7fe5951b166 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1222,6 +1222,8 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
 	struct amdgpu_ras_block_object *block_obj = amdgpu_ras_get_ras_block(adev, block, 0);
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+	struct amdgpu_hive_info *hive;
+	int hive_ras_recovery = 0;
 
 	if (!block_obj || !block_obj->hw_ops) {
 		dev_dbg_once(adev->dev, "%s doesn't config RAS function\n",
@@ -1229,15 +1231,22 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
 		return -EOPNOTSUPP;
 	}
 
-	/* skip ras error reset in gpu reset */
-	if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery)) &&
-	    mca_funcs && mca_funcs->mca_set_debug_mode)
-		return -EOPNOTSUPP;
-
 	if (!amdgpu_ras_is_supported(adev, block) ||
 	    !amdgpu_ras_get_mca_debug_mode(adev))
 		return -EOPNOTSUPP;
 
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		hive_ras_recovery = atomic_read(&hive->ras_recovery);
+		amdgpu_put_xgmi_hive(hive);
+	}
+
+	/* skip ras error reset in gpu reset */
+	if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery) ||
+	    hive_ras_recovery) &&
+	    mca_funcs && mca_funcs->mca_set_debug_mode)
+		return -EOPNOTSUPP;
+
 	if (block_obj->hw_ops->reset_ras_error_count)
 		block_obj->hw_ops->reset_ras_error_count(adev);