[Intel-gfx] [PATCH v3 16/25] drm/i915/bdw: Use dynamic allocation idioms on free

[Michel Thierry]

From: Ben Widawsky <benjamin.widawsky at intel.com>

The page directory freer is left here for now as it's still useful given
that GEN8 still preallocates. Once the allocation functions are broken
up into more discrete chunks, we'll follow suit and destroy this
leftover piece.

v2: Match trace_i915_va_teardown params
v3: Multiple rebases.
v4: Updated to use unmap_and_free_pt.

Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry at intel.com> (v2+)
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 54 +++++++++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_gem_gtt.h | 46 +++++++++++++++++++++++++++++++
 2 files changed, 80 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 40996fe..756907f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -580,27 +580,32 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 	}
 }
 
-static void gen8_free_page_tables(struct i915_page_directory_entry *pd, struct drm_device *dev)
+static void gen8_teardown_va_range(struct i915_address_space *vm,
+				   uint64_t start, uint64_t length)
 {
-	int i;
-
-	if (!pd->page)
-		return;
-
-	for (i = 0; i < GEN8_PDES_PER_PAGE; i++) {
-		unmap_and_free_pt(pd->page_tables[i], dev);
-		pd->page_tables[i] = NULL;
+	struct i915_hw_ppgtt *ppgtt =
+				container_of(vm, struct i915_hw_ppgtt, base);
+	struct i915_page_directory_entry *pd;
+	struct i915_page_table_entry *pt;
+	uint64_t temp;
+	uint32_t pdpe, pde;
+
+	gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
+		uint64_t pd_len = gen8_clamp_pd(start, length);
+		uint64_t pd_start = start;
+		gen8_for_each_pde(pt, pd, pd_start, pd_len, temp, pde) {
+			unmap_and_free_pt(pt, vm->dev);
+		}
+		unmap_and_free_pd(pd);
 	}
 }
 
-static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
+/* This function will die soon */
+static void gen8_free_full_page_directory(struct i915_hw_ppgtt *ppgtt, int i)
 {
-	int i;
-
-	for (i = 0; i < ppgtt->num_pd_pages; i++) {
-		gen8_free_page_tables(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
-		unmap_and_free_pd(ppgtt->pdp.page_directory[i]);
-	}
+	gen8_teardown_va_range(&ppgtt->base,
+			       i << GEN8_PDPE_SHIFT,
+			       (1 << GEN8_PDPE_SHIFT));
 }
 
 static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
@@ -615,19 +620,28 @@ static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
 			continue;
 
 		pci_unmap_page(hwdev, ppgtt->pdp.page_directory[i]->daddr, PAGE_SIZE,
-			       PCI_DMA_BIDIRECTIONAL);
+				PCI_DMA_BIDIRECTIONAL);
 
 		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
 			struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[i];
-			struct i915_page_table_entry *pt =  pd->page_tables[j];
+			struct i915_page_table_entry *pt = pd->page_tables[j];
 			dma_addr_t addr = pt->daddr;
 			if (addr)
 				pci_unmap_page(hwdev, addr, PAGE_SIZE,
-					       PCI_DMA_BIDIRECTIONAL);
+						PCI_DMA_BIDIRECTIONAL);
 		}
 	}
 }
 
+static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
+{
+	trace_i915_va_teardown(&ppgtt->base,
+			       ppgtt->base.start, ppgtt->base.total,
+			       VM_TO_TRACE_NAME(&ppgtt->base));
+	gen8_teardown_va_range(&ppgtt->base,
+			       ppgtt->base.start, ppgtt->base.total);
+}
+
 static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct i915_hw_ppgtt *ppgtt =
@@ -652,7 +666,7 @@ static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt)
 
 unwind_out:
 	while (i--)
-		gen8_free_page_tables(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
+		gen8_free_full_page_directory(ppgtt, i);
 
 	return -ENOMEM;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 074b368..c82a029 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -385,6 +385,52 @@ static inline uint32_t gen6_pde_index(uint32_t addr)
 	return i915_pde_index(addr, GEN6_PDE_SHIFT);
 }
 
+#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 < GEN8_PDES_PER_PAGE;			\
+	     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)->page_directory[iter];	\
+	     length > 0 && iter < GEN8_LEGACY_PDPES;			\
+	     pd = (pdp)->page_directory[++iter],				\
+	     temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT) - start,	\
+	     temp = min(temp, length),					\
+	     start += temp, length -= temp)
+
+/* Clamp length to the next page_directory boundary */
+static inline uint64_t gen8_clamp_pd(uint64_t start, uint64_t length)
+{
+	uint64_t next_pd = ALIGN(start + 1, 1 << GEN8_PDPE_SHIFT);
+	if (next_pd > (start + length))
+		return length;
+
+	return next_pd - start;
+}
+
+static inline uint32_t gen8_pte_index(uint64_t address)
+{
+	return i915_pte_index(address, GEN8_PDE_SHIFT);
+}
+
+static inline uint32_t gen8_pde_index(uint64_t address)
+{
+	return i915_pde_index(address, GEN8_PDE_SHIFT);
+}
+
+static inline uint32_t gen8_pdpe_index(uint64_t address)
+{
+	return (address >> GEN8_PDPE_SHIFT) & GEN8_PDPE_MASK;
+}
+
+static inline uint32_t gen8_pml4e_index(uint64_t address)
+{
+	BUG(); /* For 64B */
+}
+
 int i915_gem_gtt_init(struct drm_device *dev);
 void i915_gem_init_global_gtt(struct drm_device *dev);
 void i915_global_gtt_cleanup(struct drm_device *dev);
-- 
2.1.1