Merge branch 'drm-next-4.14' of git://people.freedesktop.org/~agd5f/linux into drm-next

- Stop reprogramming the MC, the vbios already does this in asic_init
- Reduce internal gart to 256M (this does not affect the ttm GTT pool size)
- Initial support for huge pages
- Rework bo migration logic
- Lots of improvements for vega10
- Powerplay fixes
- Additional Raven enablement
- SR-IOV improvements
- Bug fixes
- Code cleanup

* 'drm-next-4.14' of git://people.freedesktop.org/~agd5f/linux: (138 commits)
  drm/amdgpu: fix header on gfx9 clear state
  drm/amdgpu: reduce the time of reading VBIOS
  drm/amdgpu/virtual_dce: Remove the rmmod error message
  drm/amdgpu/gmc9: disable legacy vga features in gmc init
  drm/amdgpu/gmc8: disable legacy vga features in gmc init
  drm/amdgpu/gmc7: disable legacy vga features in gmc init
  drm/amdgpu/gmc6: disable legacy vga features in gmc init (v2)
  drm/radeon: Set depth on low mem to 16 bpp instead of 8 bpp
  drm/amdgpu: fix the incorrect scratch reg number on gfx v6
  drm/amdgpu: fix the incorrect scratch reg number on gfx v7
  drm/amdgpu: fix the incorrect scratch reg number on gfx v8
  drm/amdgpu: fix the incorrect scratch reg number on gfx v9
  drm/amd/powerplay: add support for 3DP 4K@120Hz on vega10.
  drm/amdgpu: enable huge page handling in the VM v5
  drm/amdgpu: increase fragmentation size for Vega10 v2
  drm/amdgpu: ttm_bind only when user needs gpu_addr in bo pin
  drm/amdgpu: correct clock info for SRIOV
  drm/amdgpu/gmc8: SRIOV need to program fb location
  drm/amdgpu: disable firmware loading for psp v10
  drm/amdgpu:fix gfx fence allocate size
  ...

1 files changed, 39 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 1d766ae98dc8..b1de44f22824 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -551,17 +551,53 @@ static void sdma_v3_0_rlc_stop(struct amdgpu_device *adev)
  */
 static void sdma_v3_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 {
-	u32 f32_cntl;
+	u32 f32_cntl, phase_quantum = 0;
 	int i;
 
+	if (amdgpu_sdma_phase_quantum) {
+		unsigned value = amdgpu_sdma_phase_quantum;
+		unsigned unit = 0;
+
+		while (value > (SDMA0_PHASE0_QUANTUM__VALUE_MASK >>
+				SDMA0_PHASE0_QUANTUM__VALUE__SHIFT)) {
+			value = (value + 1) >> 1;
+			unit++;
+		}
+		if (unit > (SDMA0_PHASE0_QUANTUM__UNIT_MASK >>
+			    SDMA0_PHASE0_QUANTUM__UNIT__SHIFT)) {
+			value = (SDMA0_PHASE0_QUANTUM__VALUE_MASK >>
+				 SDMA0_PHASE0_QUANTUM__VALUE__SHIFT);
+			unit = (SDMA0_PHASE0_QUANTUM__UNIT_MASK >>
+				SDMA0_PHASE0_QUANTUM__UNIT__SHIFT);
+			WARN_ONCE(1,
+			"clamping sdma_phase_quantum to %uK clock cycles\n",
+				  value << unit);
+		}
+		phase_quantum =
+			value << SDMA0_PHASE0_QUANTUM__VALUE__SHIFT |
+			unit  << SDMA0_PHASE0_QUANTUM__UNIT__SHIFT;
+	}
+
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		f32_cntl = RREG32(mmSDMA0_CNTL + sdma_offsets[i]);
-		if (enable)
+		if (enable) {
 			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
 					AUTO_CTXSW_ENABLE, 1);
-		else
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
+					ATC_L1_ENABLE, 1);
+			if (amdgpu_sdma_phase_quantum) {
+				WREG32(mmSDMA0_PHASE0_QUANTUM + sdma_offsets[i],
+				       phase_quantum);
+				WREG32(mmSDMA0_PHASE1_QUANTUM + sdma_offsets[i],
+				       phase_quantum);
+			}
+		} else {
 			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
 					AUTO_CTXSW_ENABLE, 0);
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
+					ATC_L1_ENABLE, 1);
+		}
+
 		WREG32(mmSDMA0_CNTL + sdma_offsets[i], f32_cntl);
 	}
 }