Merge tag 'drm-next-2020-08-06' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "New xilinx displayport driver, AMD support for two new GPUs (more
  header files), i915 initial support for RocketLake and some work on
  their DG1 (discrete chip).

  The core also grew some lockdep annotations to try and constrain what
  drivers do with dma-fences, and added some documentation on why the
  idea of indefinite fences doesn't work.

  The long list is below.

  I do have some fixes trees outstanding, but I'll follow up with those
  later.

  core:
   - add user def flag to cmd line modes
   - dma_fence_wait added might_sleep
   - dma-fence lockdep annotations
   - indefinite fences are bad documentation
   - gem CMA functions used in more drivers
   - struct mutex removal
   - more drm_ debug macro usage
   - set/drop master api fixes
   - fix for drm/mm hole size comparison
   - drm/mm remove invalid entry optimization
   - optimise drm/mm hole handling
   - VRR debugfs added
   - uncompressed AFBC modifier support
   - multiple display id blocks in EDID
   - multiple driver sg handling fixes
   - __drm_atomic_helper_crtc_reset in all drivers
   - managed vram helpers

  ttm:
   - ttm_mem_reg handling cleanup
   - remove bo offset field
   - drop CMA memtype flag
   - drop mappable flag

  xilinx:
   - New Xilinx ZynqMP DisplayPort Subsystem driver

  nouveau:
   - add CRC support
   - start using NVIDIA published class header files
   - convert all push buffer emission to new macros
   - Proper push buffer space management for EVO/NVD channels.
   - firmware loading fixes
   - 2MiB system memory pages support on Pascal and newer

  vkms:
   - larger cursor support

  i915:
   - Rocketlake platform enablement
   - Early DG1 enablement
   - Numerous GEM refactorings
   - DP MST fixes
   - FBC, PSR, Cursor, Color, Gamma fixes
   - TGL, RKL, EHL workaround updates
   - TGL 8K display support fixes
   - SDVO/HDMI/DVI fixes

  amdgpu:
   - Initial support for Sienna Cichlid GPU
   - Initial support for Navy Flounder GPU
   - SI UVD/VCE support
   - expose rotation property
   - Add support for unique id on Arcturus
   - Enable runtime PM on vega10 boards that support BACO
   - Skip BAR resizing if the bios already did id
   - Major swSMU code cleanup
   - Fixes for DCN bandwidth calculations

  amdkfd:
   - Track SDMA usage per process
   - SMI events interface

  radeon:
   - Default to on chip GART for AGP boards on all arches
   - Runtime PM reference count fixes

  msm:
   - headers regenerated causing churn
   - a650/a640 display and GPU enablement
   - dpu dither support for 6bpc panels
   - dpu cursor fix
   - dsi/mdp5 enablement for sdm630/sdm636/sdm66

  tegra:
   - video capture prep support
   - reflection support

  mediatek:
   - convert mtk_dsi to bridge API

  meson:
   - FBC support

  sun4i:
   - iommu support

  rockchip:
   - register locking fix
   - per-pixel alpha support PX30 VOP

  mgag200:
   - ported to simple and shmem helpers
   - device init cleanups
   - use managed pci functions
   - dropped hw cursor support

  ast:
   - use managed pci functions
   - use managed VRAM helpers
   - rework cursor support

  malidp:
   - dev_groups support

  hibmc:
   - refactor hibmc_drv_vdac:

  vc4:
   - create TXP CRTC

  imx:
   - error path fixes and cleanups

  etnaviv:
   - clock handling and error handling cleanups
   - use pin_user_pages"

* tag 'drm-next-2020-08-06' of git://anongit.freedesktop.org/drm/drm: (1747 commits)
  drm/msm: use kthread_create_worker instead of kthread_run
  drm/msm/mdp5: Add MDP5 configuration for SDM636/660
  drm/msm/dsi: Add DSI configuration for SDM660
  drm/msm/mdp5: Add MDP5 configuration for SDM630
  drm/msm/dsi: Add phy configuration for SDM630/636/660
  drm/msm/a6xx: add A640/A650 hwcg
  drm/msm/a6xx: hwcg tables in gpulist
  drm/msm/dpu: add SM8250 to hw catalog
  drm/msm/dpu: add SM8150 to hw catalog
  drm/msm/dpu: intf timing path for displayport
  drm/msm/dpu: set missing flush bits for INTF_2 and INTF_3
  drm/msm/dpu: don't use INTF_INPUT_CTRL feature on sdm845
  drm/msm/dpu: move some sspp caps to dpu_caps
  drm/msm/dpu: update UBWC config for sm8150 and sm8250
  drm/msm/dpu: use right setup_blend_config for sm8150 and sm8250
  drm/msm/a6xx: set ubwc config for A640 and A650
  drm/msm/adreno: un-open-code some packets
  drm/msm: sync generated headers
  drm/msm/a6xx: add build_bw_table for A640/A650
  drm/msm/a6xx: fix crashstate capture for A650
  ...

1 files changed, 99 insertions, 29 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index fb3f228458e5..757fa8e83f5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -31,18 +31,23 @@
 
 #include "soc15_common.h"
 
+#define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid                      0x064d
+#define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid_BASE_IDX             0
+#define mmDAGB0_CNTL_MISC2_Sienna_Cichlid                       0x0070
+#define mmDAGB0_CNTL_MISC2_Sienna_Cichlid_BASE_IDX              0
+
 void mmhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
 				uint64_t page_table_base)
 {
-	/* two registers distance between mmMMVM_CONTEXT0_* to mmMMVM_CONTEXT1_* */
-	int offset = mmMMVM_CONTEXT1_PAGE_TABLE_BASE_ADDR_LO32
-			- mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32;
+	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 
 	WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
-			offset * vmid, lower_32_bits(page_table_base));
+			    hub->ctx_addr_distance * vmid,
+			    lower_32_bits(page_table_base));
 
 	WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
-			offset * vmid, upper_32_bits(page_table_base));
+			    hub->ctx_addr_distance * vmid,
+			    upper_32_bits(page_table_base));
 }
 
 static void mmhub_v2_0_init_gart_aperture_regs(struct amdgpu_device *adev)
@@ -164,6 +169,10 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL4, VMC_TAP_PDE_REQUEST_PHYSICAL, 0);
 	tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL4, VMC_TAP_PTE_REQUEST_PHYSICAL, 0);
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL4, tmp);
+
+	tmp = mmMMVM_L2_CNTL5_DEFAULT;
+	tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL5, L2_CACHE_SMALLK_FRAGMENT_SIZE, 0);
+	WREG32_SOC15(GC, 0, mmMMVM_L2_CNTL5, tmp);
 }
 
 static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev)
@@ -200,6 +209,7 @@ static void mmhub_v2_0_disable_identity_aperture(struct amdgpu_device *adev)
 
 static void mmhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
 {
+	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 	int i;
 	uint32_t tmp;
 
@@ -230,25 +240,31 @@ static void mmhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
 		tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
 				    !amdgpu_noretry);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL, i, tmp);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, i*2, 0);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32, i*2, 0);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_END_ADDR_LO32, i*2,
-			lower_32_bits(adev->vm_manager.max_pfn - 1));
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_END_ADDR_HI32, i*2,
-			upper_32_bits(adev->vm_manager.max_pfn - 1));
+		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL,
+				    i * hub->ctx_distance, tmp);
+		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
+				    i * hub->ctx_addr_distance, 0);
+		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32,
+				    i * hub->ctx_addr_distance, 0);
+		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_END_ADDR_LO32,
+				    i * hub->ctx_addr_distance,
+				    lower_32_bits(adev->vm_manager.max_pfn - 1));
+		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_END_ADDR_HI32,
+				    i * hub->ctx_addr_distance,
+				    upper_32_bits(adev->vm_manager.max_pfn - 1));
 	}
 }
 
 static void mmhub_v2_0_program_invalidation(struct amdgpu_device *adev)
 {
+	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 	unsigned i;
 
 	for (i = 0; i < 18; ++i) {
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_ADDR_RANGE_LO32,
-				    2 * i, 0xffffffff);
+				    i * hub->eng_addr_distance, 0xffffffff);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_ADDR_RANGE_HI32,
-				    2 * i, 0x1f);
+				    i * hub->eng_addr_distance, 0x1f);
 	}
 }
 
@@ -270,12 +286,14 @@ int mmhub_v2_0_gart_enable(struct amdgpu_device *adev)
 
 void mmhub_v2_0_gart_disable(struct amdgpu_device *adev)
 {
+	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 	u32 tmp;
 	u32 i;
 
 	/* Disable all tables */
 	for (i = 0; i < 16; i++)
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_CNTL, i, 0);
+		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_CNTL,
+				    i * hub->ctx_distance, 0);
 
 	/* Setup TLB control */
 	tmp = RREG32_SOC15(MMHUB, 0, mmMMMC_VM_MX_L1_TLB_CNTL);
@@ -356,6 +374,13 @@ void mmhub_v2_0_init(struct amdgpu_device *adev)
 	hub->vm_l2_pro_fault_cntl =
 		SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_L2_PROTECTION_FAULT_CNTL);
 
+	hub->ctx_distance = mmMMVM_CONTEXT1_CNTL - mmMMVM_CONTEXT0_CNTL;
+	hub->ctx_addr_distance = mmMMVM_CONTEXT1_PAGE_TABLE_BASE_ADDR_LO32 -
+		mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32;
+	hub->eng_distance = mmMMVM_INVALIDATE_ENG1_REQ -
+		mmMMVM_INVALIDATE_ENG0_REQ;
+	hub->eng_addr_distance = mmMMVM_INVALIDATE_ENG1_ADDR_RANGE_LO32 -
+		mmMMVM_INVALIDATE_ENG0_ADDR_RANGE_LO32;
 }
 
 static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
@@ -363,9 +388,17 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 {
 	uint32_t def, data, def1, data1;
 
-	def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
-
-	def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2);
+	switch (adev->asic_type) {
+	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
+		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
+		def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid);
+		break;
+	default:
+		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
+		def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2);
+		break;
+	}
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) {
 		data |= MM_ATC_L2_MISC_CG__ENABLE_MASK;
@@ -388,11 +421,21 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 			  DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK);
 	}
 
-	if (def != data)
-		WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
-
-	if (def1 != data1)
-		WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2, data1);
+	switch (adev->asic_type) {
+	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
+		if (def != data)
+			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid, data);
+		if (def1 != data1)
+			WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid, data1);
+		break;
+	default:
+		if (def != data)
+			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
+		if (def1 != data1)
+			WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2, data1);
+		break;
+	}
 }
 
 static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
@@ -400,15 +443,32 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 {
 	uint32_t def, data;
 
-	def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
+	switch (adev->asic_type) {
+	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
+		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
+		break;
+	default:
+		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
+		break;
+	}
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
 		data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
 	else
 		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
 
-	if (def != data)
-		WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
+	if (def != data) {
+		switch (adev->asic_type) {
+		case CHIP_SIENNA_CICHLID:
+		case CHIP_NAVY_FLOUNDER:
+			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid, data);
+			break;
+		default:
+			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
+			break;
+		}
+	}
 }
 
 int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
@@ -421,6 +481,8 @@ int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
+	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
 		mmhub_v2_0_update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		mmhub_v2_0_update_medium_grain_light_sleep(adev,
@@ -440,9 +502,17 @@ void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
-
-	data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2);
+	switch (adev->asic_type) {
+	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
+		data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
+		data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid);
+		break;
+	default:
+		data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
+		data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2);
+		break;
+	}
 
 	/* AMD_CG_SUPPORT_MC_MGCG */
 	if ((data & MM_ATC_L2_MISC_CG__ENABLE_MASK) &&