Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.15.

  Core:
   - Atomic object lifetime fixes
   - Atomic iterator improvements
   - Sparse/smatch fixes
   - Legacy kms ioctls to be interruptible
   - EDID override improvements
   - fb/gem helper cleanups
   - Simple outreachy patches
   - Documentation improvements
   - Fix dma-buf rcu races
   - DRM mode object leasing for improving VR use cases.
   - vgaarb improvements for non-x86 platforms.

  New driver:
   - tve200: Faraday Technology TVE200 block.

     This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
     the StorLink SL3516 (later Cortina Systems CS3516) as well as the
     Grain Media GM8180.

  New bridges:
   - SiI9234 support

  New panels:
   - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
     LT089AC19000, Innolux AT043TN24

  i915:
   - Remove Coffeelake from alpha support
   - Cannonlake workarounds
   - Infoframe refactoring for DisplayPort
   - VBT updates
   - DisplayPort vswing/emph/buffer translation refactoring
   - CCS fixes
   - Restore GPU clock boost on missed vblanks
   - Scatter list updates for userptr allocations
   - Gen9+ transition watermarks
   - Display IPC (Isochronous Priority Control)
   - Private PAT management
   - GVT: improved error handling and pci config sanitizing
   - Execlist refactoring
   - Transparent Huge Page support
   - User defined priorities support
   - HuC/GuC firmware refactoring
   - DP MST fixes
   - eDP power sequencing fixes
   - Use RCU instead of stop_machine
   - PSR state tracking support
   - Eviction fixes
   - BDW DP aux channel timeout fixes
   - LSPCON fixes
   - Cannonlake PLL fixes

  amdgpu:
   - Per VM BO support
   - Powerplay cleanups
   - CI powerplay support
   - PASID mgr for kfd
   - SR-IOV fixes
   - initial GPU reset for vega10
   - Prime mmap support
   - TTM updates
   - Clock query interface for Raven
   - Fence to handle ioctl
   - UVD encode ring support on Polaris
   - Transparent huge page DMA support
   - Compute LRU pipe tweaks
   - BO flag to allow buffers to opt out of implicit sync
   - CTX priority setting API
   - VRAM lost infrastructure plumbing

  qxl:
   - fix flicker since atomic rework

  amdkfd:
   - Further improvements from internal AMD tree
   - Usermode events
   - Drop radeon support

  nouveau:
   - Pascal temperature sensor support
   - Improved BAR2 handling
   - MMU rework to support Pascal MMU

  exynos:
   - Improved HDMI/mixer support
   - HDMI audio interface support

  tegra:
   - Prep work for tegra186
   - Cleanup/fixes

  msm:
   - Preemption support for a5xx
   - Display fixes for 8x96 (snapdragon 820)
   - Async cursor plane fixes
   - FW loading rework
   - GPU debugging improvements

  vc4:
   - Prep for DSI panels
   - fix T-format tiling scanout
   - New madvise ioctl

  Rockchip:
   - LVDS support

  omapdrm:
   - omap4 HDMI CEC support

  etnaviv:
   - GPU performance counters groundwork

  sun4i:
   - refactor driver load + TCON backend
   - HDMI improvements
   - A31 support
   - Misc fixes

  udl:
   - Probe/EDID read fixes.

  tilcdc:
   - Misc fixes.

  pl111:
   - Support more variants

  adv7511:
   - Improve EDID handling.
   - HDMI CEC support

  sii8620:
   - Add remote control support"

* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
  drm/rockchip: analogix_dp: Use mutex rather than spinlock
  drm/mode_object: fix documentation for object lookups.
  drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
  drm/i915: Move init_clock_gating() back to where it was
  drm/i915: Prune the reservation shared fence array
  drm/i915: Idle the GPU before shinking everything
  drm/i915: Lock llist_del_first() vs llist_del_all()
  drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
  drm/i915: Disable lazy PPGTT page table optimization for vGPU
  drm/i915/execlists: Remove the priority "optimisation"
  drm/i915: Filter out spurious execlists context-switch interrupts
  drm/amdgpu: use irq-safe lock for kiq->ring_lock
  drm/amdgpu: bypass lru touch for KIQ ring submission
  drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
  drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
  drm/amd/powerplay: initialize a variable before using it
  drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
  drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
  drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
  drm/rockchip: add CONFIG_OF dependency for lvds
  ...

1 files changed, 101 insertions, 39 deletions

diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
index 0fdfc610ceb3..0760b93e9d1f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
@@ -2,68 +2,130 @@
 #ifndef __NVKM_MMU_H__
 #define __NVKM_MMU_H__
 #include <core/subdev.h>
-#include <core/mm.h>
-struct nvkm_device;
-struct nvkm_mem;
-
-struct nvkm_vm_pgt {
-	struct nvkm_memory *mem[2];
-	u32 refcount[2];
-};
-
-struct nvkm_vm_pgd {
-	struct list_head head;
-	struct nvkm_gpuobj *obj;
-};
 
 struct nvkm_vma {
 	struct list_head head;
-	int refcount;
-	struct nvkm_vm *vm;
-	struct nvkm_mm_node *node;
-	u64 offset;
-	u32 access;
+	struct rb_node tree;
+	u64 addr;
+	u64 size:50;
+	bool mapref:1; /* PTs (de)referenced on (un)map (vs pre-allocated). */
+	bool sparse:1; /* Unmapped PDEs/PTEs will not trigger MMU faults. */
+#define NVKM_VMA_PAGE_NONE 7
+	u8   page:3; /* Requested page type (index, or NONE for automatic). */
+	u8   refd:3; /* Current page type (index, or NONE for unreferenced). */
+	bool used:1; /* Region allocated. */
+	bool part:1; /* Region was split from an allocated region by map(). */
+	bool user:1; /* Region user-allocated. */
+	bool busy:1; /* Region busy (for temporarily preventing user access). */
+	struct nvkm_memory *memory; /* Memory currently mapped into VMA. */
+	struct nvkm_tags *tags; /* Compression tag reference. */
 };
 
-struct nvkm_vm {
+struct nvkm_vmm {
+	const struct nvkm_vmm_func *func;
 	struct nvkm_mmu *mmu;
-
+	const char *name;
+	u32 debug;
+	struct kref kref;
 	struct mutex mutex;
-	struct nvkm_mm mm;
-	struct kref refcount;
 
-	struct list_head pgd_list;
+	u64 start;
+	u64 limit;
+
+	struct nvkm_vmm_pt *pd;
+	struct list_head join;
+
+	struct list_head list;
+	struct rb_root free;
+	struct rb_root root;
+
+	bool bootstrapped;
 	atomic_t engref[NVKM_SUBDEV_NR];
 
-	struct nvkm_vm_pgt *pgt;
-	u32 fpde;
-	u32 lpde;
+	dma_addr_t null;
+	void *nullp;
 };
 
-int  nvkm_vm_new(struct nvkm_device *, u64 offset, u64 length, u64 mm_offset,
-		 struct lock_class_key *, struct nvkm_vm **);
-int  nvkm_vm_ref(struct nvkm_vm *, struct nvkm_vm **, struct nvkm_gpuobj *pgd);
-int  nvkm_vm_boot(struct nvkm_vm *, u64 size);
-int  nvkm_vm_get(struct nvkm_vm *, u64 size, u32 page_shift, u32 access,
-		 struct nvkm_vma *);
-void nvkm_vm_put(struct nvkm_vma *);
-void nvkm_vm_map(struct nvkm_vma *, struct nvkm_mem *);
-void nvkm_vm_map_at(struct nvkm_vma *, u64 offset, struct nvkm_mem *);
-void nvkm_vm_unmap(struct nvkm_vma *);
-void nvkm_vm_unmap_at(struct nvkm_vma *, u64 offset, u64 length);
+int nvkm_vmm_new(struct nvkm_device *, u64 addr, u64 size, void *argv, u32 argc,
+		 struct lock_class_key *, const char *name, struct nvkm_vmm **);
+struct nvkm_vmm *nvkm_vmm_ref(struct nvkm_vmm *);
+void nvkm_vmm_unref(struct nvkm_vmm **);
+int nvkm_vmm_boot(struct nvkm_vmm *);
+int nvkm_vmm_join(struct nvkm_vmm *, struct nvkm_memory *inst);
+void nvkm_vmm_part(struct nvkm_vmm *, struct nvkm_memory *inst);
+int nvkm_vmm_get(struct nvkm_vmm *, u8 page, u64 size, struct nvkm_vma **);
+void nvkm_vmm_put(struct nvkm_vmm *, struct nvkm_vma **);
+
+struct nvkm_vmm_map {
+	struct nvkm_memory *memory;
+	u64 offset;
+
+	struct nvkm_mm_node *mem;
+	struct scatterlist *sgl;
+	dma_addr_t *dma;
+	u64 off;
+
+	const struct nvkm_vmm_page *page;
+
+	struct nvkm_tags *tags;
+	u64 next;
+	u64 type;
+	u64 ctag;
+};
+
+int nvkm_vmm_map(struct nvkm_vmm *, struct nvkm_vma *, void *argv, u32 argc,
+		 struct nvkm_vmm_map *);
+void nvkm_vmm_unmap(struct nvkm_vmm *, struct nvkm_vma *);
+
+struct nvkm_memory *nvkm_umem_search(struct nvkm_client *, u64);
+struct nvkm_vmm *nvkm_uvmm_search(struct nvkm_client *, u64 handle);
 
 struct nvkm_mmu {
 	const struct nvkm_mmu_func *func;
 	struct nvkm_subdev subdev;
 
-	u64 limit;
 	u8  dma_bits;
-	u8  lpg_shift;
+
+	int heap_nr;
+	struct {
+#define NVKM_MEM_VRAM                                                      0x01
+#define NVKM_MEM_HOST                                                      0x02
+#define NVKM_MEM_COMP                                                      0x04
+#define NVKM_MEM_DISP                                                      0x08
+		u8  type;
+		u64 size;
+	} heap[4];
+
+	int type_nr;
+	struct {
+#define NVKM_MEM_KIND                                                      0x10
+#define NVKM_MEM_MAPPABLE                                                  0x20
+#define NVKM_MEM_COHERENT                                                  0x40
+#define NVKM_MEM_UNCACHED                                                  0x80
+		u8 type;
+		u8 heap;
+	} type[16];
+
+	struct nvkm_vmm *vmm;
+
+	struct {
+		struct mutex mutex;
+		struct list_head list;
+	} ptc, ptp;
+
+	struct nvkm_device_oclass user;
 };
 
 int nv04_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int nv41_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int nv44_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int nv50_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int g84_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int gf100_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int gk104_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int gk20a_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int gm200_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int gm20b_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int gp100_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int gp10b_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 #endif