drm/amdgpu: Read clock counter via MMIO to reduce delay (v5)

[Why]
GPU timing counters are read via KIQ under sriov, which will introduce
a delay.

[How]
It could be directly read by MMIO.

v2: Add additional check to prevent carryover issue.
v3: Only check for carryover for once to prevent performance issue.
v4: Add comments of the rough frequency where carryover happens.
v5: Remove mutex and gfxoff ctrl unused with current timing registers.
Signed-off-by: YuBiao Wang <YuBiao.Wang@amd.com>
Acked-by: Horace Chen <horace.chen@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.co>
Reviewed-by: Monk Liu <monk.liu@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

@@ -7605,10 +7605,8 @@ static int gfx_v10_0_soft_reset(void *handle)
 
 static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
-	uint64_t clock;
+	uint64_t clock, clock_lo, clock_hi, hi_check;
 
-	amdgpu_gfx_off_ctrl(adev, false);
-	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	switch (adev->asic_type) {
 	case CHIP_VANGOGH:
 	case CHIP_YELLOW_CARP:
@@ -7616,12 +7614,21 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
 		break;
 	default:
-		clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
-			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+		preempt_disable();
+		clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER);
+		clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER);
+		hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER);
+		/* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over
+		 * roughly every 42 seconds.
+		 */
+		if (hi_check != clock_hi) {
+			clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER);
+			clock_hi = hi_check;
+		}
+		preempt_enable();
+		clock = clock_lo | (clock_hi << 32ULL);
 		break;
 	}
-	mutex_unlock(&adev->gfx.gpu_clock_mutex);
-	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }