drm/amdgpu: change read of GPU clock counter on Vega10 VF

Using unified VBIOS has performance drop in sriov environment.
The fix is switching to another register instead.
Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -3884,9 +3884,22 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 	uint64_t clock;
 
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
-	WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
-	clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
-		((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) {
+		uint32_t tmp, lsb, msb, i = 0;
+		do {
+			if (i != 0)
+				udelay(1);
+			tmp = RREG32_SOC15(GC, 0, mmRLC_REFCLOCK_TIMESTAMP_MSB);
+			lsb = RREG32_SOC15(GC, 0, mmRLC_REFCLOCK_TIMESTAMP_LSB);
+			msb = RREG32_SOC15(GC, 0, mmRLC_REFCLOCK_TIMESTAMP_MSB);
+			i++;
+		} while (unlikely(tmp != msb) && (i < adev->usec_timeout));
+		clock = (uint64_t)lsb | ((uint64_t)msb << 32ULL);
+	} else {
+		WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+		clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
+			((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	}
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
 	return clock;
 }