Merge tag 'amd-drm-fixes-6.5-2023-06-30-1' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-fixes-6.5-2023-06-30-1:

amdgpu:
- Misc cleanups
- GFX 9.4.3 fixes
- DEBUGFS build fix
- Fix LPDDR5 reporting
- ASPM fixes
- DCN 3.1.4 fixes
- DP MST fixes
- DCN 3.2.x fixes
- Display PSR TCON fixes
- SMU 13.x fixes
- RAS fixes
- Vega12/20 SMU fixes
- PSP flashing cleanup
- GFX9 MCBP fixes
- SR-IOV fixes
- GPUVM clear mappings fix for always valid BOs
- Add FAMS quirk for problematic monitor
- Fix possible UAF
- Better handle monentary temperature fluctuations
- SDMA 4.4.2 fixes
- Fencing fix

Signed-off-by: Dave Airlie <[email protected]>

From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

1 files changed, 11 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 4769a18304d7..8aaa427f8c0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2065,6 +2065,14 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 				ras->gpu_reset_flags &= ~AMDGPU_RAS_GPU_RESET_MODE2_RESET;
 				reset_context.method = AMD_RESET_METHOD_MODE2;
 			}
+
+			/* Fatal error occurs in poison mode, mode1 reset is used to
+			 * recover gpu.
+			 */
+			if (ras->gpu_reset_flags & AMDGPU_RAS_GPU_RESET_MODE1_RESET) {
+				ras->gpu_reset_flags &= ~AMDGPU_RAS_GPU_RESET_MODE1_RESET;
+				set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+			}
 		}
 
 		amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context);
@@ -2955,9 +2963,12 @@ void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
 		return;
 
 	if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
+		struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+
 		dev_info(adev->dev, "uncorrectable hardware error"
 			"(ERREVENT_ATHUB_INTERRUPT) detected!\n");
 
+		ras->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE1_RESET;
 		amdgpu_ras_reset_gpu(adev);
 	}
 }