[PATCH v3] drm/amdgpu: Reset dGPU if suspend got aborted

[Lijo Lazar]

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 <lijo.lazar at amd.com>
Reviewed-by: Alex Deucher <alexander.deucher at amd.com>
Reviewed-by: Yang Wang <kevinyang.wang at amd.com>

Cc: stable at vger.kernel.org
---
v2: Read TOS status only if required (Kevin).
    Refine log message.

v3: Add stable trees tag

 drivers/gpu/drm/amd/amdgpu/soc21.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 8526282f4da1..abe319b0f063 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -867,10 +867,35 @@ 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);
 }
 
-- 
2.25.1