drm/amdgpu: Reset dGPU if suspend got aborted

commit 8b2be55 upstream.

For SOC21 ASICs, there is an issue in re-enabling PM features if a
suspend got aborted. In such cases, reset the device during resume
phase. This is a workaround till a proper solution is finalized.

Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Yang Wang <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: [email protected]
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: Lijo Lazar

drivers/gpu/drm/amd/amdgpu/soc21.c

@@ -804,10 +804,35 @@ static int soc21_common_suspend(void *handle)
 	return soc21_common_hw_fini(adev);
 }
 
+static bool soc21_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg1, sol_reg2;
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset dGPU side.
+	 * 2) S3 suspend got aborted and TOS is active.
+	 */
+	if (!(adev->flags & AMD_IS_APU) && adev->in_s3 &&
+	    !adev->suspend_complete) {
+		sol_reg1 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81);
+		msleep(100);
+		sol_reg2 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81);
+
+		return (sol_reg1 != sol_reg2);
+	}
+
+	return false;
+}
+
 static int soc21_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (soc21_need_reset_on_resume(adev)) {
+		dev_info(adev->dev, "S3 suspend aborted, resetting...");
+		soc21_asic_reset(adev);
+	}
+
 	return soc21_common_hw_init(adev);
 }