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, 15 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 3a0b69b09ed6..435db6f5efcf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -211,7 +211,7 @@ static void gfx_v9_0_init_golden_registers(struct amdgpu_device *adev)
 
 static void gfx_v9_0_scratch_init(struct amdgpu_device *adev)
 {
-	adev->gfx.scratch.num_reg = 7;
+	adev->gfx.scratch.num_reg = 8;
 	adev->gfx.scratch.reg_base = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG0);
 	adev->gfx.scratch.free_mask = (1u << adev->gfx.scratch.num_reg) - 1;
 }
@@ -1475,21 +1475,23 @@ static void gfx_v9_0_tiling_mode_table_init(struct amdgpu_device *adev)
 
 static void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance)
 {
-	u32 data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1);
+	u32 data;
 
-	if ((se_num == 0xffffffff) && (sh_num == 0xffffffff)) {
-		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SH_BROADCAST_WRITES, 1);
-		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SE_BROADCAST_WRITES, 1);
-	} else if (se_num == 0xffffffff) {
-		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SH_INDEX, sh_num);
+	if (instance == 0xffffffff)
+		data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1);
+	else
+		data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_INDEX, instance);
+
+	if (se_num == 0xffffffff)
 		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SE_BROADCAST_WRITES, 1);
-	} else if (sh_num == 0xffffffff) {
-		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SH_BROADCAST_WRITES, 1);
+	else
 		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SE_INDEX, se_num);
-	} else {
+
+	if (sh_num == 0xffffffff)
+		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SH_BROADCAST_WRITES, 1);
+	else
 		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SH_INDEX, sh_num);
-		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SE_INDEX, se_num);
-	}
+
 	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, data);
 }
 
@@ -2425,7 +2427,7 @@ static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev)
 		/* This situation may be hit in the future if a new HW
 		 * generation exposes more than 64 queues. If so, the
 		 * definition of queue_mask needs updating */
-		if (WARN_ON(i > (sizeof(queue_mask)*8))) {
+		if (WARN_ON(i >= (sizeof(queue_mask)*8))) {
 			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
 			break;
 		}