[PATCH 26/26] FOR REFERENCE ONLY

[Ben Widawsky <benjamin.widawsky@intel.com>]

Start using size/length through the GEN8 code. The same approach was
taken for gen7. The difference with gen8 to this point is we need to
take care to the do the page directory allocations, as well as the page
tables.

This patch is meant to show how things will look (more or less) if I
keep up in the same direction.
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 104 +++++++++++++++++++++++++++---------
 drivers/gpu/drm/i915/i915_gem_gtt.h |  37 +++++++++++++
 2 files changed, 115 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 846a5b5..1348d48 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -488,29 +488,50 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 		kunmap_atomic(pt_vaddr);
 }
 
-static void gen8_free_page_tables(struct i915_pagedir *pd, struct drm_device *dev)
+static void gen8_free_page_tables(struct i915_pagedir *pd,
+				  uint64_t start, uint64_t length,
+				  struct drm_device *dev)
 {
 	int i;
 
 	if (!pd->page)
 		return;
 
-	for (i = 0; i < I915_PDES_PER_PD; i++) {
+	for (i = gen8_pte_index(start);
+	     length && i < GEN8_PTES_PER_PT; i++, length -= PAGE_SIZE) {
+		if (!pd->page_tables[i])
+			continue;
+
 		free_pt_single(pd->page_tables[i], dev);
 		pd->page_tables[i] = NULL;
 	}
 }
 
-static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
+static void gen8_teardown_va_range(struct i915_hw_ppgtt *ppgtt,
+				   uint64_t start, uint64_t length)
 {
-	int i;
+	struct drm_device *dev = ppgtt->base.dev;
+	struct i915_pagedir *pd;
+	struct i915_pagetab *pt;
+	uint64_t temp, temp2;
+	uint32_t pdpe, pde;
+
+	gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
+		uint64_t pd_start = start;
+		uint64_t pd_len = gen8_bound_pt(start, length);
+		gen8_for_each_pde(pt, pd, pd_start, pd_len, temp2, pde) {
+			gen8_free_page_tables(pd, pd_start, pd_len, dev);
+		}
 
-	for (i = 0; i < ppgtt->num_pd_pages; i++) {
-		gen8_free_page_tables(ppgtt->pdp.pagedir[i], ppgtt->base.dev);
-		free_pd_single(ppgtt->pdp.pagedir[i], ppgtt->base.dev);
+		free_pd_single(pd, dev);
 	}
 }
 
+static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
+{
+	gen8_teardown_va_range(ppgtt, ppgtt->base.start, ppgtt->base.total);
+}
+
 static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct i915_hw_ppgtt *ppgtt =
@@ -537,41 +558,75 @@ static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt)
 
 unwind_out:
 	while (i--)
-		gen8_free_page_tables(ppgtt->pdp.pagedir[i], ppgtt->base.dev);
+		gen8_free_page_tables(ppgtt->pdp.pagedir[i],
+				      i * I915_PDES_PER_PD * GEN8_PTES_PER_PT,
+				      (i + 1)* I915_PDES_PER_PD * GEN8_PTES_PER_PT,
+				      ppgtt->base.dev);
 
 	return -ENOMEM;
 }
 
 static int gen8_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt,
-						const int max_pdp)
+						uint64_t start, uint64_t length)
 {
-	int i;
+	struct i915_pagedir *unused;
+	uint64_t temp;
+	uint32_t pdpe;
 
-	for (i = 0; i < max_pdp; i++) {
-		ppgtt->pdp.pagedir[i] = alloc_pd_single(ppgtt->base.dev);
-		if (IS_ERR(ppgtt->pdp.pagedir[i]))
-			goto unwind_out;
+	gen8_for_each_pdpe(unused, &ppgtt->pdp, start, length, temp, pdpe) {
+		struct i915_pagedir *pd;
+
+		BUG_ON(unused);
+		pd = alloc_pd_single(ppgtt->base.dev);
+		if (!pd)
+			goto pd_fail;
+
+		ppgtt->pdp.pagedir[pdpe] = pd;
+		ppgtt->num_pd_pages++;
 	}
 
-	ppgtt->num_pd_pages = max_pdp;
 	BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS);
 
 	return 0;
 
-unwind_out:
-	while (i--)
-		free_pd_single(ppgtt->pdp.pagedir[i],
-			       ppgtt->base.dev);
+pd_fail:
+	while (pdpe--)
+		free_pd_single(ppgtt->pdp.pagedir[pdpe], ppgtt->base.dev);
 
 	return -ENOMEM;
 }
 
+static void gen8_alloc_va_range(struct i915_hw_ppgtt *ppgtt,
+				uint64_t start, uint64_t length)
+{
+	struct i915_pagedir *pd;
+	struct i915_pagetab *pt;
+	uint64_t temp, temp2;
+	uint32_t pdpe, pde;
+
+	gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
+		uint64_t pd_start = start;
+		uint64_t pd_len = gen8_bound_pt(start, length);
+		gen8_for_each_pde(pt, pd, pd_start, pd_len, temp2, pde) {
+			uint64_t bound = gen8_bound_pt(pd_start, pd_len);
+			int ret = alloc_pt_range(pd,
+						 gen8_pde_index(pd_start),
+						 gen8_pde_index(bound),
+						 ppgtt->base.dev);
+			if (ret) {
+				//gen8_free_page_tables(pd, pd_start, pd_len, dev);
+			}
+
+		}
+	}
+}
+
 static int gen8_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt,
-			    const int max_pdp)
+			    uint64_t start, uint64_t length)
 {
 	int ret;
 
-	ret = gen8_ppgtt_allocate_page_directories(ppgtt, max_pdp);
+	ret = gen8_ppgtt_allocate_page_directories(ppgtt, start, length);
 	if (ret)
 		return ret;
 
@@ -579,7 +634,7 @@ static int gen8_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt,
 	if (ret)
 		goto err_out;
 
-	ppgtt->num_pd_entries = max_pdp * I915_PDES_PER_PD;
+	ppgtt->num_pd_entries = length >> GEN8_PDE_SHIFT;
 
 	return 0;
 
@@ -605,11 +660,8 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
 	const int min_pt_pages = I915_PDES_PER_PD * max_pdp;
 	int i, j, ret;
 
-	if (size % (1<<30))
-		DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);
-
 	/* 1. Do all our allocations for page directories and page tables. */
-	ret = gen8_ppgtt_alloc(ppgtt, max_pdp);
+	ret = gen8_ppgtt_alloc(ppgtt, 0, size);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 6130f3d..91f8a36 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -192,6 +192,43 @@ static inline uint32_t gen8_pml4e_index(uint64_t address)
 	BUG();
 }
 
+/* Either rounds down length to the nearest page table VA boundary, or returns
+ * length
+ */
+static inline uint64_t gen8_bound_pt(uint64_t start, uint64_t length)
+{
+	uint64_t next_pt = ALIGN(start + 1, 1 << GEN8_PDE_SHIFT);
+	if (next_pt > (start + length))
+		return length;
+
+	return next_pt - start;
+}
+
+static inline uint64_t gen8_bound_pd(uint64_t start, uint64_t length)
+{
+	uint64_t next_pt = ALIGN(start + 1, 1 << GEN8_PDPE_SHIFT);
+	if (next_pt > (start + length))
+		return length;
+
+	return next_pt - start;
+}
+
+#define gen8_for_each_pde(pt, pd, start, length, temp, iter) \
+	for (iter = gen8_pde_index(start), pt = (pd)->page_tables[iter]; \
+	     length > 0 && iter < I915_PDES_PER_PD; \
+	     pt = (pd)->page_tables[++iter], \
+	     temp = ALIGN(start+1, 1 << GEN8_PDE_SHIFT) - start, \
+	     temp = min(temp, length), \
+	     start += temp, length -= temp)
+
+#define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter) \
+	for (iter = gen8_pdpe_index(start), pd = (pdp)->pagedir[iter]; \
+	     length > 0 && iter < GEN8_LEGACY_PDPS; \
+	     pd = (pdp)->pagedir[iter++], \
+	     temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT) - start, \
+	     temp = min(temp, length), \
+	     start += temp, length -= temp)
+
 enum i915_cache_level;
 /**
  * A VMA represents a GEM BO that is bound into an address space. Therefore, a
-- 
1.9.0