Merge tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux

Pull drm u pdates from Dave Airlie:
 "This is the main drm pull request for v4.12. Apart from two fixes
  pulls, everything should have been in drm-next for at least 2 weeks.

  The biggest thing in here is AMD released the public headers for their
  upcoming VEGA GPUs. These as always are quite a sizeable chunk of
  header files. They've also added initial non-display support for those
  GPUs, though they aren't available in production yet.

  Otherwise it's pretty much normal.

  New bridge drivers:
   - megachips-stdpxxxx-ge-b850v3-fw LVDS->DP++
   - generic LVDS bridge support.

  Core:
   - Displayport link train failure reporting to userspace
   - debugfs interface cleaned up
   - subsystem TODO in kerneldoc now
   - Extended fbdev support (flipping and vblank wait)
   - drm_platform removed
   - EDP CRC support in helper
   - HF-VSDB SCDC support in EDID parser
   - Lots of code cleanups and header extraction
   - Thunderbolt external GPU awareness
   - Atomic helper improvements
   - Documentation improvements

  panel:
   - Sitronix and Samsung new panel support

  amdgpu:
   - Preliminary vega10 support
   - Multi-level page table support
   - GPU sensor support for userspace
   - PRT support for sparse buffers
   - SR-IOV improvements
   - Non-contig VRAM CPU mapping

  i915:
   - Atomic modesetting enabled by default on Gen5+
   - LSPCON improvements
   - Atomic state handling for cdclk
   - GPU reset improvements
   - In-kernel unit tests
   - Geminilake improvements and color manager support
   - Designware i2c fixes
   - vblank evasion improvements
   - Hotplug safe connector iterators
   - GVT scheduler QoS support
   - GVT Kabylake support

  nouveau:
   - Acceleration support for Pascal (GP10x).
   - Rearchitecture of code handling proprietary signed firmware
   - Fix GTX 970 with odd MMU configuration
   - GP10B support
   - GP107 acceleration support

  vmwgfx:
   - Atomic modesetting support for vmwgfx

  omapdrm:
   - Support for render nodes
   - Refactor omapdss code
   - Fix some probe ordering issues
   - Fix too dark RGB565 rendering

  sunxi:
   - prelim rework for multiple pipes.

  mali-dp:
   - Color management support
   - Plane scaling
   - Power management improvements

  imx-drm:
   - Prefetch Resolve Engine/Gasket on i.MX6QP
   - Deferred plane disabling
   - Separate alpha support

  mediatek:
   - Mediatek SoC MT2701 support

  rcar-du:
   - Gen3 HDMI support

  msm:
   - 4k support for newer chips
   - OPP bindings for gpu
   - prep work for per-process pagetables

  vc4:
   - HDMI audio support
   - fixes

  qxl:
   - minor fixes.

  dw-hdmi:
   - PHY improvements
   - CSC fixes
   - Amlogic GX SoC support"

* tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux: (1778 commits)
  drm/nouveau/fb/gf100-: Fix 32 bit wraparound in new ram detection
  drm/nouveau/secboot/gm20b: fix the error return code in gm20b_secboot_tegra_read_wpr()
  drm/nouveau/kms: Increase max retries in scanout position queries.
  drm/nouveau/bios/bitP: check that table is long enough for optional pointers
  drm/nouveau/fifo/nv40: no ctxsw for pre-nv44 mpeg engine
  drm: mali-dp: use div_u64 for expensive 64-bit divisions
  drm/i915: Confirm the request is still active before adding it to the await
  drm/i915: Avoid busy-spinning on VLV_GLTC_PW_STATUS mmio
  drm/i915/selftests: Allocate inode/file dynamically
  drm/i915: Fix system hang with EI UP masked on Haswell
  drm/i915: checking for NULL instead of IS_ERR() in mock selftests
  drm/i915: Perform link quality check unconditionally during long pulse
  drm/i915: Fix use after free in lpe_audio_platdev_destroy()
  drm/i915: Use the right mapping_gfp_mask for final shmem allocation
  drm/i915: Make legacy cursor updates more unsynced
  drm/i915: Apply a cond_resched() to the saturated signaler
  drm/i915: Park the signaler before sleeping
  drm: mali-dp: Check the mclk rate and allow up/down scaling
  drm: mali-dp: Enable image enhancement when scaling
  drm: mali-dp: Add plane upscaling support
  ...

1 files changed, 51 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 18c72c0b478d..d9e57290dc71 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -45,7 +45,7 @@ struct amdgpu_bo_list_entry;
 #define AMDGPU_VM_MAX_UPDATE_SIZE	0x3FFFF
 
 /* number of entries in page table */
-#define AMDGPU_VM_PTE_COUNT (1 << amdgpu_vm_block_size)
+#define AMDGPU_VM_PTE_COUNT(adev) (1 << (adev)->vm_manager.block_size)
 
 /* PTBs (Page Table Blocks) need to be aligned to 32K */
 #define AMDGPU_VM_PTB_ALIGN_SIZE   32768
@@ -53,26 +53,44 @@ struct amdgpu_bo_list_entry;
 /* LOG2 number of continuous pages for the fragment field */
 #define AMDGPU_LOG2_PAGES_PER_FRAG 4
 
-#define AMDGPU_PTE_VALID	(1 << 0)
-#define AMDGPU_PTE_SYSTEM	(1 << 1)
-#define AMDGPU_PTE_SNOOPED	(1 << 2)
+#define AMDGPU_PTE_VALID	(1ULL << 0)
+#define AMDGPU_PTE_SYSTEM	(1ULL << 1)
+#define AMDGPU_PTE_SNOOPED	(1ULL << 2)
 
 /* VI only */
-#define AMDGPU_PTE_EXECUTABLE	(1 << 4)
+#define AMDGPU_PTE_EXECUTABLE	(1ULL << 4)
 
-#define AMDGPU_PTE_READABLE	(1 << 5)
-#define AMDGPU_PTE_WRITEABLE	(1 << 6)
+#define AMDGPU_PTE_READABLE	(1ULL << 5)
+#define AMDGPU_PTE_WRITEABLE	(1ULL << 6)
 
-#define AMDGPU_PTE_FRAG(x)	((x & 0x1f) << 7)
+#define AMDGPU_PTE_FRAG(x)	((x & 0x1fULL) << 7)
+
+#define AMDGPU_PTE_PRT		(1ULL << 63)
+
+/* VEGA10 only */
+#define AMDGPU_PTE_MTYPE(a)    ((uint64_t)a << 57)
+#define AMDGPU_PTE_MTYPE_MASK	AMDGPU_PTE_MTYPE(3ULL)
 
 /* How to programm VM fault handling */
 #define AMDGPU_VM_FAULT_STOP_NEVER	0
 #define AMDGPU_VM_FAULT_STOP_FIRST	1
 #define AMDGPU_VM_FAULT_STOP_ALWAYS	2
 
+/* max number of VMHUB */
+#define AMDGPU_MAX_VMHUBS			2
+#define AMDGPU_GFXHUB				0
+#define AMDGPU_MMHUB				1
+
+/* hardcode that limit for now */
+#define AMDGPU_VA_RESERVED_SIZE			(8 << 20)
+
 struct amdgpu_vm_pt {
 	struct amdgpu_bo	*bo;
 	uint64_t		addr;
+
+	/* array of page tables, one for each directory entry */
+	struct amdgpu_vm_pt	*entries;
+	unsigned		last_entry_used;
 };
 
 struct amdgpu_vm {
@@ -92,14 +110,10 @@ struct amdgpu_vm {
 	struct list_head	freed;
 
 	/* contains the page directory */
-	struct amdgpu_bo	*page_directory;
-	unsigned		max_pde_used;
-	struct dma_fence		*page_directory_fence;
+	struct amdgpu_vm_pt     root;
+	struct dma_fence	*last_dir_update;
 	uint64_t		last_eviction_counter;
 
-	/* array of page tables, one for each page directory entry */
-	struct amdgpu_vm_pt	*page_tables;
-
 	/* for id and flush management per ring */
 	struct amdgpu_vm_id	*ids[AMDGPU_MAX_RINGS];
 
@@ -117,7 +131,6 @@ struct amdgpu_vm {
 
 struct amdgpu_vm_id {
 	struct list_head	list;
-	struct dma_fence		*first;
 	struct amdgpu_sync	active;
 	struct dma_fence		*last_flush;
 	atomic64_t		owner;
@@ -147,7 +160,10 @@ struct amdgpu_vm_manager {
 	u64					fence_context;
 	unsigned				seqno[AMDGPU_MAX_RINGS];
 
-	uint32_t				max_pfn;
+	uint64_t				max_pfn;
+	uint32_t				num_level;
+	uint64_t				vm_size;
+	uint32_t				block_size;
 	/* vram base address for page table entry  */
 	u64					vram_base_offset;
 	/* is vm enabled? */
@@ -159,6 +175,10 @@ struct amdgpu_vm_manager {
 	atomic_t				vm_pte_next_ring;
 	/* client id counter */
 	atomic64_t				client_counter;
+
+	/* partial resident texture handling */
+	spinlock_t				prt_lock;
+	atomic_t				num_prt_users;
 };
 
 void amdgpu_vm_manager_init(struct amdgpu_device *adev);
@@ -173,15 +193,19 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      void *param);
 void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev,
 				  struct amdgpu_vm *vm);
+int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
+			struct amdgpu_vm *vm,
+			uint64_t saddr, uint64_t size);
 int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 		      struct amdgpu_sync *sync, struct dma_fence *fence,
 		      struct amdgpu_job *job);
 int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job);
 void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vm_id);
-int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
-				    struct amdgpu_vm *vm);
+int amdgpu_vm_update_directories(struct amdgpu_device *adev,
+				 struct amdgpu_vm *vm);
 int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
-			  struct amdgpu_vm *vm);
+			  struct amdgpu_vm *vm,
+			  struct dma_fence **fence);
 int amdgpu_vm_clear_invalids(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			     struct amdgpu_sync *sync);
 int amdgpu_vm_bo_update(struct amdgpu_device *adev,
@@ -198,10 +222,18 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		     struct amdgpu_bo_va *bo_va,
 		     uint64_t addr, uint64_t offset,
 		     uint64_t size, uint64_t flags);
+int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
+			     struct amdgpu_bo_va *bo_va,
+			     uint64_t addr, uint64_t offset,
+			     uint64_t size, uint64_t flags);
 int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
 		       struct amdgpu_bo_va *bo_va,
 		       uint64_t addr);
+int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
+				struct amdgpu_vm *vm,
+				uint64_t saddr, uint64_t size);
 void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 		      struct amdgpu_bo_va *bo_va);
+void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size);
 
 #endif