drm/i915: Add support for mapping an object page by page

Introduced a new vm specfic callback insert_page() to program a single pte in
ggtt or ppgtt. This allows us to map a single page in to the mappable aperture
space. This can be iterated over to access the whole object by using space as
meagre as page size.

v2: Added low level rpm assertions to insert_page routines (Chris)

v3: Added POSTING_READ post register write (Tvrtko)

v4: Rebase (Ankit)

v5: Removed wmb() and FLUSH_CTL from insert_page, caller to take care
of it (Chris)

v6: insert_page not working correctly without FLSH_CNTL write, added the
write again.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ankitprasad Sharma <ankitprasad.r.sharma@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

drivers/char/agp/intel-gtt.c

@@ -840,6 +840,14 @@ static bool i830_check_flags(unsigned int flags)
 	return false;
 }
 
+void intel_gtt_insert_page(dma_addr_t addr,
+			   unsigned int pg,
+			   unsigned int flags)
+{
+	intel_private.driver->write_entry(addr, pg, flags);
+}
+EXPORT_SYMBOL(intel_gtt_insert_page);
+
 void intel_gtt_insert_sg_entries(struct sg_table *st,
 				 unsigned int pg_start,
 				 unsigned int flags)

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -2355,6 +2355,28 @@ static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
 #endif
 }
 
+static void gen8_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  uint64_t offset,
+				  enum i915_cache_level level,
+				  u32 unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(vm->dev);
+	gen8_pte_t __iomem *pte =
+		(gen8_pte_t __iomem *)dev_priv->ggtt.gsm +
+		(offset >> PAGE_SHIFT);
+	int rpm_atomic_seq;
+
+	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);
+
+	gen8_set_pte(pte, gen8_pte_encode(addr, level, true));
+
+	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+
+	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
+}
+
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
 				     uint64_t start,
@@ -2424,6 +2446,28 @@ static void gen8_ggtt_insert_entries__BKL(struct i915_address_space *vm,
 	stop_machine(gen8_ggtt_insert_entries__cb, &arg, NULL);
 }
 
+static void gen6_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  uint64_t offset,
+				  enum i915_cache_level level,
+				  u32 flags)
+{
+	struct drm_i915_private *dev_priv = to_i915(vm->dev);
+	gen6_pte_t __iomem *pte =
+		(gen6_pte_t __iomem *)dev_priv->ggtt.gsm +
+		(offset >> PAGE_SHIFT);
+	int rpm_atomic_seq;
+
+	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);
+
+	iowrite32(vm->pte_encode(addr, level, true, flags), pte);
+
+	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+
+	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
+}
+
 /*
  * Binds an object into the global gtt with the specified cache level. The object
  * will be accessible to the GPU via commands whose operands reference offsets
@@ -2543,6 +2587,24 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
 }
 
+static void i915_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  uint64_t offset,
+				  enum i915_cache_level cache_level,
+				  u32 unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(vm->dev);
+	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+	int rpm_atomic_seq;
+
+	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);
+
+	intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
+
+	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
+}
+
 static void i915_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *pages,
 				     uint64_t start,
@@ -3076,7 +3138,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->base.bind_vma = ggtt_bind_vma;
 	ggtt->base.unbind_vma = ggtt_unbind_vma;
-
+	ggtt->base.insert_page = gen8_ggtt_insert_page;
 	ggtt->base.clear_range = nop_clear_range;
 	if (!USES_FULL_PPGTT(dev_priv))
 		ggtt->base.clear_range = gen8_ggtt_clear_range;
@@ -3116,6 +3178,7 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	ret = ggtt_probe_common(dev, ggtt->size);
 
 	ggtt->base.clear_range = gen6_ggtt_clear_range;
+	ggtt->base.insert_page = gen6_ggtt_insert_page;
 	ggtt->base.insert_entries = gen6_ggtt_insert_entries;
 	ggtt->base.bind_vma = ggtt_bind_vma;
 	ggtt->base.unbind_vma = ggtt_unbind_vma;
@@ -3147,6 +3210,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 		      &ggtt->mappable_base, &ggtt->mappable_end);
 
 	ggtt->do_idle_maps = needs_idle_maps(dev_priv->dev);
+	ggtt->base.insert_page = i915_ggtt_insert_page;
 	ggtt->base.insert_entries = i915_ggtt_insert_entries;
 	ggtt->base.clear_range = i915_ggtt_clear_range;
 	ggtt->base.bind_vma = ggtt_bind_vma;

drivers/gpu/drm/i915/i915_gem_gtt.h

@@ -319,6 +319,11 @@ struct i915_address_space {
 			    uint64_t start,
 			    uint64_t length,
 			    bool use_scratch);
+	void (*insert_page)(struct i915_address_space *vm,
+			    dma_addr_t addr,
+			    uint64_t offset,
+			    enum i915_cache_level cache_level,
+			    u32 flags);
 	void (*insert_entries)(struct i915_address_space *vm,
 			       struct sg_table *st,
 			       uint64_t start,

include/drm/intel-gtt.h

@@ -13,6 +13,9 @@ void intel_gmch_remove(void);
 bool intel_enable_gtt(void);
 
 void intel_gtt_chipset_flush(void);
+void intel_gtt_insert_page(dma_addr_t addr,
+			   unsigned int pg,
+			   unsigned int flags);
 void intel_gtt_insert_sg_entries(struct sg_table *st,
 				 unsigned int pg_start,
 				 unsigned int flags);