Merge tag 'drm-next-2019-11-27' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of stuff in here, though it hasn't been too insane this merge
  apart from dealing with the security fun.

  uapi:
   - export different colorspace properties on DP vs HDMI
   - new fourcc for ARM 16x16 block format
   - syncobj: allow querying last submitted timeline value
   - DRM_FORMAT_BIG_ENDIAN defined as unsigned

  core:
   - allow using gem vma manager in ttm
   - connector/encoder/bridge doc fixes
   - allow more than 3 encoders for a connector
   - displayport mst suspend/resume reprobing support
   - vram lazy unmapping, uniform vram mm and gem vram
   - edid cleanups + AVI informframe bar info
   - displayport helpers - dpcd parser added

  dp_cec:
   - Allow a connector to be associated with a cec device

  ttm:
   - pipelining with no_gpu_wait fix
   - always keep BOs on the LRU

  sched:
   - allow free_job routine to sleep

  i915:
   - Block userptr from mappable GTT
   - i915 perf uapi versioning
   - OA stream dynamic reconfiguration
   - make context persistence optional
   - introduce DRM_I915_UNSTABLE Kconfig
   - add fake lmem testing under unstable
   - BT.2020 support for DP MSA
   - struct mutex elimination
   - Tigerlake display/PLL/power management improvements
   - Jasper Lake PCH support
   - refactor PMU for multiple GPUs
   - Icelake firmware update
   - Split out vga + switcheroo code

  amdgpu:
   - implement dma-buf import/export without helpers
   - vega20 RAS enablement
   - DC i2c over aux fixes
   - renoir GPU reset
   - DC HDCP support
   - BACO support for CI/VI asics
   - MSI-X support
   - Arcturus EEPROM support
   - Arcturus VCN encode support
   - VCN dynamic powergating on RV/RV2

  amdkfd:
   - add navi12/14/renoir support to kfd

  radeon:
   - SI dpm fix ported from amdgpu
   - fix bad DMA on ppc platforms

  gma500:
   - memory leak fixes

  qxl:
   - convert to new gem mmap

  exynos:
   - build warning fix

  komeda:
   - add aclk sysfs attribute

  v3d:
   - userspace cleanup uapi change

  i810:
   - fix for underflow in dispatch ioctls

  ast:
   - refactor show_cursor

  mgag200:
   - refactor show_cursor

  arcgpu:
   - encoder finding improvements

  mediatek:
   - mipi_tx, dsi and partial crtc support for MT8183 SoC
   - rotation support

  meson:
   - add suspend/resume support

  omap:
   - misc refactors

  tegra:
   - DisplayPort support for Tegra 210, 186 and 194.
   - IOMMU-backed DMA API fixes

  panfrost:
   - fix lockdep issue
   - simplify devfreq integration

  rcar-du:
   - R8A774B1 SoC support
   - fixes for H2 ES2.0

  sun4i:
   - vcc-dsi regulator support

  virtio-gpu:
   - vmexit vs spinlock fix
   - move to gem shmem helpers
   - handle large command buffers with cma"

* tag 'drm-next-2019-11-27' of git://anongit.freedesktop.org/drm/drm: (1855 commits)
  drm/amdgpu: invalidate mmhub semaphore workaround in gmc9/gmc10
  drm/amdgpu: initialize vm_inv_eng0_sem for gfxhub and mmhub
  drm/amd/amdgpu/sriov skip RLCG s/r list for arcturus VF.
  drm/amd/amdgpu/sriov temporarily skip ras,dtm,hdcp for arcturus VF
  drm/amdgpu/gfx10: re-init clear state buffer after gpu reset
  merge fix for "ftrace: Rework event_create_dir()"
  drm/amdgpu: Update Arcturus golden registers
  drm/amdgpu/gfx10: fix out-of-bound mqd_backup array access
  drm/amdgpu/gfx10: explicitly wait for cp idle after halt/unhalt
  Revert "drm/amd/display: enable S/G for RAVEN chip"
  drm/amdgpu: disable gfxoff on original raven
  drm/amdgpu: remove experimental flag for Navi14
  drm/amdgpu: disable gfxoff when using register read interface
  drm/amdgpu/powerplay: properly set PP_GFXOFF_MASK (v2)
  drm/amdgpu: fix bad DMA from INTERRUPT_CNTL2
  drm/radeon: fix bad DMA from INTERRUPT_CNTL2
  drm/amd/display: Fix debugfs on MST connectors
  drm/amdgpu/nv: add asic func for fetching vbios from rom directly
  drm/amdgpu: put flush_delayed_work at first
  drm/amdgpu/vcn2.5: fix the enc loop with hw fini
  ...

1 files changed, 45 insertions, 41 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 6d021ecc8d59..ae6f5446262c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -19,9 +19,6 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
 #include <linux/dma-buf.h>
 #include <linux/list.h>
 #include <linux/pagemap.h>
@@ -33,11 +30,6 @@
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_dma_buf.h"
 
-/* Special VM and GART address alignment needed for VI pre-Fiji due to
- * a HW bug.
- */
-#define VI_BO_SIZE_ALIGN (0x8000)
-
 /* BO flag to indicate a KFD userptr BO */
 #define AMDGPU_AMDKFD_USERPTR_BO (1ULL << 63)
 
@@ -349,13 +341,46 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
 	int ret;
 
-	ret = amdgpu_vm_update_directories(adev, vm);
+	ret = amdgpu_vm_update_pdes(adev, vm, false);
 	if (ret)
 		return ret;
 
 	return amdgpu_sync_fence(NULL, sync, vm->last_update, false);
 }
 
+static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
+{
+	struct amdgpu_device *bo_adev = amdgpu_ttm_adev(mem->bo->tbo.bdev);
+	bool coherent = mem->alloc_flags & ALLOC_MEM_FLAGS_COHERENT;
+	uint32_t mapping_flags;
+
+	mapping_flags = AMDGPU_VM_PAGE_READABLE;
+	if (mem->alloc_flags & ALLOC_MEM_FLAGS_WRITABLE)
+		mapping_flags |= AMDGPU_VM_PAGE_WRITEABLE;
+	if (mem->alloc_flags & ALLOC_MEM_FLAGS_EXECUTABLE)
+		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
+
+	switch (adev->asic_type) {
+	case CHIP_ARCTURUS:
+		if (mem->alloc_flags & ALLOC_MEM_FLAGS_VRAM) {
+			if (bo_adev == adev)
+				mapping_flags |= coherent ?
+					AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW;
+			else
+				mapping_flags |= AMDGPU_VM_MTYPE_UC;
+		} else {
+			mapping_flags |= coherent ?
+				AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
+		}
+		break;
+	default:
+		mapping_flags |= coherent ?
+			AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
+	}
+
+	return amdgpu_gem_va_map_flags(adev, mapping_flags);
+}
+
 /* add_bo_to_vm - Add a BO to a VM
  *
  * Everything that needs to bo done only once when a BO is first added
@@ -404,8 +429,7 @@ static int add_bo_to_vm(struct amdgpu_device *adev, struct kgd_mem *mem,
 	}
 
 	bo_va_entry->va = va;
-	bo_va_entry->pte_flags = amdgpu_gmc_get_pte_flags(adev,
-							 mem->mapping_flags);
+	bo_va_entry->pte_flags = get_pte_flags(adev, mem);
 	bo_va_entry->kgd_dev = (void *)adev;
 	list_add(&bo_va_entry->bo_list, list_bo_va);
 
@@ -586,7 +610,7 @@ static int reserve_bo_and_vm(struct kgd_mem *mem,
 	amdgpu_vm_get_pd_bo(vm, &ctx->list, &ctx->vm_pd[0]);
 
 	ret = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->list,
-				     false, &ctx->duplicates, true);
+				     false, &ctx->duplicates);
 	if (!ret)
 		ctx->reserved = true;
 	else {
@@ -659,7 +683,7 @@ static int reserve_bo_and_cond_vms(struct kgd_mem *mem,
 	}
 
 	ret = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->list,
-				     false, &ctx->duplicates, true);
+				     false, &ctx->duplicates);
 	if (!ret)
 		ctx->reserved = true;
 	else
@@ -1079,10 +1103,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	uint64_t user_addr = 0;
 	struct amdgpu_bo *bo;
 	struct amdgpu_bo_param bp;
-	int byte_align;
 	u32 domain, alloc_domain;
 	u64 alloc_flags;
-	uint32_t mapping_flags;
 	int ret;
 
 	/*
@@ -1135,25 +1157,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	if ((*mem)->aql_queue)
 		size = size >> 1;
 
-	/* Workaround for TLB bug on older VI chips */
-	byte_align = (adev->family == AMDGPU_FAMILY_VI &&
-			adev->asic_type != CHIP_FIJI &&
-			adev->asic_type != CHIP_POLARIS10 &&
-			adev->asic_type != CHIP_POLARIS11 &&
-			adev->asic_type != CHIP_POLARIS12 &&
-			adev->asic_type != CHIP_VEGAM) ?
-			VI_BO_SIZE_ALIGN : 1;
-
-	mapping_flags = AMDGPU_VM_PAGE_READABLE;
-	if (flags & ALLOC_MEM_FLAGS_WRITABLE)
-		mapping_flags |= AMDGPU_VM_PAGE_WRITEABLE;
-	if (flags & ALLOC_MEM_FLAGS_EXECUTABLE)
-		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
-	if (flags & ALLOC_MEM_FLAGS_COHERENT)
-		mapping_flags |= AMDGPU_VM_MTYPE_UC;
-	else
-		mapping_flags |= AMDGPU_VM_MTYPE_NC;
-	(*mem)->mapping_flags = mapping_flags;
+	(*mem)->alloc_flags = flags;
 
 	amdgpu_sync_create(&(*mem)->sync);
 
@@ -1168,7 +1172,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 
 	memset(&bp, 0, sizeof(bp));
 	bp.size = size;
-	bp.byte_align = byte_align;
+	bp.byte_align = 1;
 	bp.domain = alloc_domain;
 	bp.flags = alloc_flags;
 	bp.type = bo_type;
@@ -1626,9 +1630,10 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 
 	INIT_LIST_HEAD(&(*mem)->bo_va_list);
 	mutex_init(&(*mem)->lock);
-	(*mem)->mapping_flags =
-		AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
-		AMDGPU_VM_PAGE_EXECUTABLE | AMDGPU_VM_MTYPE_NC;
+	(*mem)->alloc_flags =
+		((bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ?
+		 ALLOC_MEM_FLAGS_VRAM : ALLOC_MEM_FLAGS_GTT) |
+		ALLOC_MEM_FLAGS_WRITABLE | ALLOC_MEM_FLAGS_EXECUTABLE;
 
 	(*mem)->bo = amdgpu_bo_ref(bo);
 	(*mem)->va = va;
@@ -1797,8 +1802,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 	}
 
 	/* Reserve all BOs and page tables for validation */
-	ret = ttm_eu_reserve_buffers(&ticket, &resv_list, false, &duplicates,
-				     true);
+	ret = ttm_eu_reserve_buffers(&ticket, &resv_list, false, &duplicates);
 	WARN(!list_empty(&duplicates), "Duplicates should be empty");
 	if (ret)
 		goto out_free;
@@ -1996,7 +2000,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 	}
 
 	ret = ttm_eu_reserve_buffers(&ctx.ticket, &ctx.list,
-				     false, &duplicate_save, true);
+				     false, &duplicate_save);
 	if (ret) {
 		pr_debug("Memory eviction: TTM Reserve Failed. Try again\n");
 		goto ttm_reserve_fail;