drm/amdgpu/sriov: Use kiq to copy the gpu clock

For vega10 sriov, the register is blocked, use
copy data command to fix the issue.

v2: Rename amdgpu_kiq_read_clock to gfx_v9_0_kiq_read_clock.
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -3963,6 +3963,63 @@ static int gfx_v9_0_soft_reset(void *handle)
 	return 0;
 }
 
+static uint64_t gfx_v9_0_kiq_read_clock(struct amdgpu_device *adev)
+{
+	signed long r, cnt = 0;
+	unsigned long flags;
+	uint32_t seq;
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
+	struct amdgpu_ring *ring = &kiq->ring;
+
+	BUG_ON(!ring->funcs->emit_rreg);
+
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+	amdgpu_ring_alloc(ring, 32);
+	amdgpu_ring_write(ring, PACKET3(PACKET3_COPY_DATA, 4));
+	amdgpu_ring_write(ring, 9 |	/* src: register*/
+				(5 << 8) |	/* dst: memory */
+				(1 << 16) |	/* count sel */
+				(1 << 20));	/* write confirm */
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, lower_32_bits(adev->wb.gpu_addr +
+				kiq->reg_val_offs * 4));
+	amdgpu_ring_write(ring, upper_32_bits(adev->wb.gpu_addr +
+				kiq->reg_val_offs * 4));
+	amdgpu_fence_emit_polling(ring, &seq);
+	amdgpu_ring_commit(ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
+	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+
+	/* don't wait anymore for gpu reset case because this way may
+	 * block gpu_recover() routine forever, e.g. this virt_kiq_rreg
+	 * is triggered in TTM and ttm_bo_lock_delayed_workqueue() will
+	 * never return if we keep waiting in virt_kiq_rreg, which cause
+	 * gpu_recover() hang there.
+	 *
+	 * also don't wait anymore for IRQ context
+	 * */
+	if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+		goto failed_kiq_read;
+
+	might_sleep();
+	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+	}
+
+	if (cnt > MAX_KIQ_REG_TRY)
+		goto failed_kiq_read;
+
+	return (uint64_t)adev->wb.wb[kiq->reg_val_offs] |
+		(uint64_t)adev->wb.wb[kiq->reg_val_offs + 1 ] << 32ULL;
+
+failed_kiq_read:
+	pr_err("failed to read gpu clock\n");
+	return ~0;
+}
+
 static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
 	uint64_t clock;
@@ -3970,16 +4027,7 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	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);
+		clock = gfx_v9_0_kiq_read_clock(adev);
 	} else {
 		WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
 		clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |