drm/amdgpu: Reset dGPU if suspend got aborted

From Lijo Lazar
1520bf605d2ff0d733648713b5485865dde0dea9 in linux-6.6.y/6.6.28
8b2be55f4d6c1099d7f629b0ed7535a5be788c83 in mainline linux

diff --git a/sys/dev/pci/drm/amd/amdgpu/soc21.c b/sys/dev/pci/drm/amd/amdgpu/soc21.c
index 5a77ab5..10aac1b 100644 (file)
--- a/sys/dev/pci/drm/amd/amdgpu/soc21.c
+++ b/sys/dev/pci/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);
+               drm_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);
 }