drm/i915: Split out GTT specific header file

This file contains all necessary defines, prototypes and typesdefs for
manipulating GEN graphics address translation (this does not include the
legacy AGP driver)

Reiterating the comment in the header,
"Please try to maintain the following order within this file unless it
makes sense to do otherwise. From top to bottom:
1. typedefs
2. #defines, and macros
3. structure definitions
4. function prototypes

Within each section, please try to order by generation in ascending
order, from top to bottom (ie. GEN6 on the top, GEN8 on the bottom)."

I've made some minor cleanups, and fixed a couple of typos while here -
but there should be no functional changes.

The purpose of the patch is to reduce clutter in our main header file,
making room for new growth, and make documentation of our interfaces
easier by splitting things out.

With a little more work, like making i915_gtt a pointer, we could
potentially completely isolate this header from i915_drv.h. At the
moment however, I don't think it's worth the effort.

Personally, I would have liked to put the PTE encoding functions in this
file too, but I didn't want to rock the boat too much.

A similar patch has been in use on my machine for some time. This exact
patch though has only been compile tested.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_drv.h

@@ -35,6 +35,7 @@
 #include "i915_reg.h"
 #include "intel_bios.h"
 #include "intel_ringbuffer.h"
+#include "i915_gem_gtt.h"
 #include <linux/io-mapping.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
@@ -572,168 +573,6 @@ enum i915_cache_level {
 	I915_CACHE_WT, /* hsw:gt3e WriteThrough for scanouts */
 };
 
-typedef uint32_t gen6_gtt_pte_t;
-
-/**
- * A VMA represents a GEM BO that is bound into an address space. Therefore, a
- * VMA's presence cannot be guaranteed before binding, or after unbinding the
- * object into/from the address space.
- *
- * To make things as simple as possible (ie. no refcounting), a VMA's lifetime
- * will always be <= an objects lifetime. So object refcounting should cover us.
- */
-struct i915_vma {
-	struct drm_mm_node node;
-	struct drm_i915_gem_object *obj;
-	struct i915_address_space *vm;
-
-	/** This object's place on the active/inactive lists */
-	struct list_head mm_list;
-
-	struct list_head vma_link; /* Link in the object's VMA list */
-
-	/** This vma's place in the batchbuffer or on the eviction list */
-	struct list_head exec_list;
-
-	/**
-	 * Used for performing relocations during execbuffer insertion.
-	 */
-	struct hlist_node exec_node;
-	unsigned long exec_handle;
-	struct drm_i915_gem_exec_object2 *exec_entry;
-
-	/**
-	 * How many users have pinned this object in GTT space. The following
-	 * users can each hold at most one reference: pwrite/pread, pin_ioctl
-	 * (via user_pin_count), execbuffer (objects are not allowed multiple
-	 * times for the same batchbuffer), and the framebuffer code. When
-	 * switching/pageflipping, the framebuffer code has at most two buffers
-	 * pinned per crtc.
-	 *
-	 * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3
-	 * bits with absolutely no headroom. So use 4 bits. */
-	unsigned int pin_count:4;
-#define DRM_I915_GEM_OBJECT_MAX_PIN_COUNT 0xf
-
-	/** Unmap an object from an address space. This usually consists of
-	 * setting the valid PTE entries to a reserved scratch page. */
-	void (*unbind_vma)(struct i915_vma *vma);
-	/* Map an object into an address space with the given cache flags. */
-#define GLOBAL_BIND (1<<0)
-	void (*bind_vma)(struct i915_vma *vma,
-			 enum i915_cache_level cache_level,
-			 u32 flags);
-};
-
-struct i915_address_space {
-	struct drm_mm mm;
-	struct drm_device *dev;
-	struct list_head global_link;
-	unsigned long start;		/* Start offset always 0 for dri2 */
-	size_t total;		/* size addr space maps (ex. 2GB for ggtt) */
-
-	struct {
-		dma_addr_t addr;
-		struct page *page;
-	} scratch;
-
-	/**
-	 * List of objects currently involved in rendering.
-	 *
-	 * Includes buffers having the contents of their GPU caches
-	 * flushed, not necessarily primitives.  last_rendering_seqno
-	 * represents when the rendering involved will be completed.
-	 *
-	 * A reference is held on the buffer while on this list.
-	 */
-	struct list_head active_list;
-
-	/**
-	 * LRU list of objects which are not in the ringbuffer and
-	 * are ready to unbind, but are still in the GTT.
-	 *
-	 * last_rendering_seqno is 0 while an object is in this list.
-	 *
-	 * A reference is not held on the buffer while on this list,
-	 * as merely being GTT-bound shouldn't prevent its being
-	 * freed, and we'll pull it off the list in the free path.
-	 */
-	struct list_head inactive_list;
-
-	/* FIXME: Need a more generic return type */
-	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
-				     enum i915_cache_level level,
-				     bool valid); /* Create a valid PTE */
-	void (*clear_range)(struct i915_address_space *vm,
-			    uint64_t start,
-			    uint64_t length,
-			    bool use_scratch);
-	void (*insert_entries)(struct i915_address_space *vm,
-			       struct sg_table *st,
-			       uint64_t start,
-			       enum i915_cache_level cache_level);
-	void (*cleanup)(struct i915_address_space *vm);
-};
-
-/* The Graphics Translation Table is the way in which GEN hardware translates a
- * Graphics Virtual Address into a Physical Address. In addition to the normal
- * collateral associated with any va->pa translations GEN hardware also has a
- * portion of the GTT which can be mapped by the CPU and remain both coherent
- * and correct (in cases like swizzling). That region is referred to as GMADR in
- * the spec.
- */
-struct i915_gtt {
-	struct i915_address_space base;
-	size_t stolen_size;		/* Total size of stolen memory */
-
-	unsigned long mappable_end;	/* End offset that we can CPU map */
-	struct io_mapping *mappable;	/* Mapping to our CPU mappable region */
-	phys_addr_t mappable_base;	/* PA of our GMADR */
-
-	/** "Graphics Stolen Memory" holds the global PTEs */
-	void __iomem *gsm;
-
-	bool do_idle_maps;
-
-	int mtrr;
-
-	/* global gtt ops */
-	int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total,
-			  size_t *stolen, phys_addr_t *mappable_base,
-			  unsigned long *mappable_end);
-};
-#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
-
-#define GEN8_LEGACY_PDPS 4
-struct i915_hw_ppgtt {
-	struct i915_address_space base;
-	struct kref ref;
-	struct drm_mm_node node;
-	unsigned num_pd_entries;
-	unsigned num_pd_pages; /* gen8+ */
-	union {
-		struct page **pt_pages;
-		struct page **gen8_pt_pages[GEN8_LEGACY_PDPS];
-	};
-	struct page *pd_pages;
-	union {
-		uint32_t pd_offset;
-		dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS];
-	};
-	union {
-		dma_addr_t *pt_dma_addr;
-		dma_addr_t *gen8_pt_dma_addr[4];
-	};
-
-	struct i915_hw_context *ctx;
-
-	int (*enable)(struct i915_hw_ppgtt *ppgtt);
-	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
-			 struct intel_ring_buffer *ring,
-			 bool synchronous);
-	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
-};
-
 struct i915_ctx_hang_stats {
 	/* This context had batch pending when hang was declared */
 	unsigned batch_pending;
@@ -1523,7 +1362,7 @@ typedef struct drm_i915_private {
 	struct mutex modeset_restore_lock;
 
 	struct list_head vm_list; /* Global list of all address spaces */
-	struct i915_gtt gtt; /* VMA representing the global address space */
+	struct i915_gtt gtt; /* VM representing the global address space */
 
 	struct i915_gem_mm mm;
 
@@ -2467,23 +2306,12 @@ int __must_check i915_gem_evict_something(struct drm_device *dev,
 int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle);
 int i915_gem_evict_everything(struct drm_device *dev);
 
-/* i915_gem_gtt.c */
-void i915_check_and_clear_faults(struct drm_device *dev);
-void i915_gem_suspend_gtt_mappings(struct drm_device *dev);
-void i915_gem_restore_gtt_mappings(struct drm_device *dev);
-int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj);
-void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj);
-void i915_gem_init_global_gtt(struct drm_device *dev);
-void i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start,
-			       unsigned long mappable_end, unsigned long end);
-int i915_gem_gtt_init(struct drm_device *dev);
+/* belongs in i915_gem_gtt.h */
 static inline void i915_gem_chipset_flush(struct drm_device *dev)
 {
 	if (INTEL_INFO(dev)->gen < 6)
 		intel_gtt_chipset_flush();
 }
-int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
-bool intel_enable_ppgtt(struct drm_device *dev, bool full);
 
 /* i915_gem_stolen.c */
 int i915_gem_init_stolen(struct drm_device *dev);

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -55,59 +55,6 @@ bool intel_enable_ppgtt(struct drm_device *dev, bool full)
 		return HAS_ALIASING_PPGTT(dev);
 }
 
-#define GEN6_PPGTT_PD_ENTRIES 512
-#define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t))
-typedef uint64_t gen8_gtt_pte_t;
-typedef gen8_gtt_pte_t gen8_ppgtt_pde_t;
-
-/* PPGTT stuff */
-#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
-#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
-
-#define GEN6_PDE_VALID			(1 << 0)
-/* gen6+ has bit 11-4 for physical addr bit 39-32 */
-#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
-
-#define GEN6_PTE_VALID			(1 << 0)
-#define GEN6_PTE_UNCACHED		(1 << 1)
-#define HSW_PTE_UNCACHED		(0)
-#define GEN6_PTE_CACHE_LLC		(2 << 1)
-#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
-#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
-#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
-
-/* Cacheability Control is a 4-bit value. The low three bits are stored in *
- * bits 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
- */
-#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
-					 (((bits) & 0x8) << (11 - 3)))
-#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
-#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
-#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
-#define HSW_WB_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x8)
-#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
-#define HSW_WT_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x7)
-
-#define GEN8_PTES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_gtt_pte_t))
-#define GEN8_PDES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_ppgtt_pde_t))
-
-/* GEN8 legacy style addressis defined as a 3 level page table:
- * 31:30 | 29:21 | 20:12 |  11:0
- * PDPE  |  PDE  |  PTE  | offset
- * The difference as compared to normal x86 3 level page table is the PDPEs are
- * programmed via register.
- */
-#define GEN8_PDPE_SHIFT			30
-#define GEN8_PDPE_MASK			0x3
-#define GEN8_PDE_SHIFT			21
-#define GEN8_PDE_MASK			0x1ff
-#define GEN8_PTE_SHIFT			12
-#define GEN8_PTE_MASK			0x1ff
-
-#define PPAT_UNCACHED_INDEX		(_PAGE_PWT | _PAGE_PCD)
-#define PPAT_CACHED_PDE_INDEX		0 /* WB LLC */
-#define PPAT_CACHED_INDEX		_PAGE_PAT /* WB LLCeLLC */
-#define PPAT_DISPLAY_ELLC_INDEX		_PAGE_PCD /* WT eLLC */
 
 static void ppgtt_bind_vma(struct i915_vma *vma,
 			   enum i915_cache_level cache_level,
@@ -187,9 +134,6 @@ static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
-#define BYT_PTE_WRITEABLE		(1 << 1)
-#define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
-
 static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
 				     bool valid)
@@ -1057,8 +1001,6 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 
 static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
 {
-#define GEN6_PD_ALIGN (PAGE_SIZE * 16)
-#define GEN6_PD_SIZE (GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE)
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool retried = false;
@@ -1847,17 +1789,6 @@ static int ggtt_probe_common(struct drm_device *dev,
  * writing this data shouldn't be harmful even in those cases. */
 static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv)
 {
-#define GEN8_PPAT_UC		(0<<0)
-#define GEN8_PPAT_WC		(1<<0)
-#define GEN8_PPAT_WT		(2<<0)
-#define GEN8_PPAT_WB		(3<<0)
-#define GEN8_PPAT_ELLC_OVERRIDE	(0<<2)
-/* FIXME(BDW): Bspec is completely confused about cache control bits. */
-#define GEN8_PPAT_LLC		(1<<2)
-#define GEN8_PPAT_LLCELLC	(2<<2)
-#define GEN8_PPAT_LLCeLLC	(3<<2)
-#define GEN8_PPAT_AGE(x)	(x<<4)
-#define GEN8_PPAT(i, x) ((uint64_t) (x) << ((i) * 8))
 	uint64_t pat;
 
 	pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC)     | /* for normal objects, no eLLC */