Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for 4.5.  I don't think I've missed
  anything too major, I'm mostly back at work now but I'll probably get
  some sleep in 5 years time.

  Summary:

  New drivers:
   - etnaviv:

     GPU driver for the 3D core on the Vivante core used in numerous
     ARM boards.

  Highlights:

  Core:
   - Atomic suspend/resume helpers
   - Move the headers to using userspace friendlier types.
   - Documentation updates
   - Lots of struct_mutex removal.
   - Bunch of DP MST fixes from AMD.

  Panel:
   - More DSI helpers
   - Support for some new basic panels

  i915:
   - Basic Kabylake support
   - DP link training and detect code refactoring
   - fbc/psr fixes
   - FIFO underrun fixes
   - SDE interrupt handling fixes
   - dma-buf/fence support in pageflip path.
   - GPU side for MST audio support

  radeon/amdgpu:
   - Drop UMS support
   - GPUVM/Scheduler optimisations
   - Initial Powerplay support for Tonga/Fiji/CZ/ST
   - ACP audio prerequisites

  nouveau:
   - GK20a instmem improvements
   - PCIE link speed change support

  msm:
   - DSI support for msm8960/apq8064

  tegra:
   - Host1X support for Tegra210 SoC

  vc4:
   - 3D acceleration support

  armada:
   - Get rid of struct mutex

  tda998x:
   - Atomic modesetting support
   - TMDS clock limitations

  omapdrm:
   - Atomic modesetting support
   - improved TILER performance

  rockchip:
   - RK3036 VOP support
   - Atomic modesetting support
   - Synopsys DW MIPI DSI support

  exynos:
   - Runtime PM support
   - of_graph binding for DP panels
   - Cleanup of IPP code
   - Configurable plane support
   - Kernel panic fixes at release time"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (711 commits)
  drm/fb_cma_helper: Remove implicit call to disable_unused_functions
  drm/amdgpu: add missing irq.h include
  drm/vmwgfx: Fix a width / pitch mismatch on framebuffer updates
  drm/vmwgfx: Fix an incorrect lock check
  drm: nouveau: fix nouveau_debugfs_init prototype
  drm/nouveau/pci: fix check in nvkm_pcie_set_link
  drm/amdgpu: validate duplicates first
  drm/amdgpu: move VM page tables to the LRU end on CS v2
  drm/ttm: add ttm_bo_move_to_lru_tail function v2
  drm/ttm: fix adding foreign BOs to the swap LRU
  drm/ttm: fix adding foreign BOs to the LRU during init v2
  drm/radeon: use kobj_to_dev()
  drm/amdgpu: use kobj_to_dev()
  drm/amdgpu/cz: force vce clocks when sclks are forced
  drm/amdgpu/cz: force uvd clocks when sclks are forced
  drm/amdgpu/cz: add code to enable forcing VCE clocks
  drm/amdgpu/cz: add code to enable forcing UVD clocks
  drm/amdgpu: fix lost sync_to if scheduler is enabled.
  drm/amd/powerplay: fix static checker warning for return meaningless value.
  drm/sysfs: use kobj_to_dev()
  ...

1 files changed, 118 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 7253132f04b8..ad54c46751b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -727,18 +727,20 @@ static int sdma_v3_0_start(struct amdgpu_device *adev)
 {
 	int r, i;
 
-	if (!adev->firmware.smu_load) {
-		r = sdma_v3_0_load_microcode(adev);
-		if (r)
-			return r;
-	} else {
-		for (i = 0; i < adev->sdma.num_instances; i++) {
-			r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
-									 (i == 0) ?
-									 AMDGPU_UCODE_ID_SDMA0 :
-									 AMDGPU_UCODE_ID_SDMA1);
+	if (!adev->pp_enabled) {
+		if (!adev->firmware.smu_load) {
+			r = sdma_v3_0_load_microcode(adev);
 			if (r)
-				return -EINVAL;
+				return r;
+		} else {
+			for (i = 0; i < adev->sdma.num_instances; i++) {
+				r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
+										 (i == 0) ?
+										 AMDGPU_UCODE_ID_SDMA0 :
+										 AMDGPU_UCODE_ID_SDMA1);
+				if (r)
+					return -EINVAL;
+			}
 		}
 	}
 
@@ -1427,9 +1429,114 @@ static int sdma_v3_0_process_illegal_inst_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
+static void fiji_update_sdma_medium_grain_clock_gating(
+		struct amdgpu_device *adev,
+		bool enable)
+{
+	uint32_t temp, data;
+
+	if (enable) {
+		temp = data = RREG32(mmSDMA0_CLK_CTRL);
+		data &= ~(SDMA0_CLK_CTRL__SOFT_OVERRIDE7_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE6_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE5_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE4_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE3_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE2_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE1_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE0_MASK);
+		if (data != temp)
+			WREG32(mmSDMA0_CLK_CTRL, data);
+
+		temp = data = RREG32(mmSDMA1_CLK_CTRL);
+		data &= ~(SDMA1_CLK_CTRL__SOFT_OVERRIDE7_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE6_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE5_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE4_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE3_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE2_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE1_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE0_MASK);
+
+		if (data != temp)
+			WREG32(mmSDMA1_CLK_CTRL, data);
+	} else {
+		temp = data = RREG32(mmSDMA0_CLK_CTRL);
+		data |= SDMA0_CLK_CTRL__SOFT_OVERRIDE7_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE6_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE5_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE4_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE3_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE2_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE1_MASK |
+				SDMA0_CLK_CTRL__SOFT_OVERRIDE0_MASK;
+
+		if (data != temp)
+			WREG32(mmSDMA0_CLK_CTRL, data);
+
+		temp = data = RREG32(mmSDMA1_CLK_CTRL);
+		data |= SDMA1_CLK_CTRL__SOFT_OVERRIDE7_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE6_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE5_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE4_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE3_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE2_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE1_MASK |
+				SDMA1_CLK_CTRL__SOFT_OVERRIDE0_MASK;
+
+		if (data != temp)
+			WREG32(mmSDMA1_CLK_CTRL, data);
+	}
+}
+
+static void fiji_update_sdma_medium_grain_light_sleep(
+		struct amdgpu_device *adev,
+		bool enable)
+{
+	uint32_t temp, data;
+
+	if (enable) {
+		temp = data = RREG32(mmSDMA0_POWER_CNTL);
+		data |= SDMA0_POWER_CNTL__MEM_POWER_OVERRIDE_MASK;
+
+		if (temp != data)
+			WREG32(mmSDMA0_POWER_CNTL, data);
+
+		temp = data = RREG32(mmSDMA1_POWER_CNTL);
+		data |= SDMA1_POWER_CNTL__MEM_POWER_OVERRIDE_MASK;
+
+		if (temp != data)
+			WREG32(mmSDMA1_POWER_CNTL, data);
+	} else {
+		temp = data = RREG32(mmSDMA0_POWER_CNTL);
+		data &= ~SDMA0_POWER_CNTL__MEM_POWER_OVERRIDE_MASK;
+
+		if (temp != data)
+			WREG32(mmSDMA0_POWER_CNTL, data);
+
+		temp = data = RREG32(mmSDMA1_POWER_CNTL);
+		data &= ~SDMA1_POWER_CNTL__MEM_POWER_OVERRIDE_MASK;
+
+		if (temp != data)
+			WREG32(mmSDMA1_POWER_CNTL, data);
+	}
+}
+
 static int sdma_v3_0_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	switch (adev->asic_type) {
+	case CHIP_FIJI:
+		fiji_update_sdma_medium_grain_clock_gating(adev,
+				state == AMD_CG_STATE_GATE ? true : false);
+		fiji_update_sdma_medium_grain_light_sleep(adev,
+				state == AMD_CG_STATE_GATE ? true : false);
+		break;
+	default:
+		break;
+	}
 	return 0;
 }