[PATCH v5 2/5] arm: arm64: page_alloc: reduce unnecessary binary search in memblock_next_valid_pfn()

[Jia He]

Commit b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns
where possible") optimized the loop in memmap_init_zone(). But there is
still some room for improvement. E.g. if pfn and pfn+1 are in the same
memblock region, we can simply pfn++ instead of doing the binary search
in memblock_next_valid_pfn.

Signed-off-by: Jia He <jia.he@xxxxxxxxxxxxxxxx>
---
 arch/arm/include/asm/page.h   |  1 +
 arch/arm/mm/init.c            | 28 ++++++++++++++++++++++------
 arch/arm64/include/asm/page.h |  1 +
 arch/arm64/mm/init.c          | 28 ++++++++++++++++++++++------
 4 files changed, 46 insertions(+), 12 deletions(-)

diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 489875c..f38909c 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -157,6 +157,7 @@ extern void copy_page(void *to, const void *from);
 typedef struct page *pgtable_t;
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
+extern int early_region_idx;
 extern int pfn_valid(unsigned long);
 extern unsigned long memblock_next_valid_pfn(unsigned long pfn);
 #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1)
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 0fb85ca..06ed190 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -193,6 +193,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
 }
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
+int early_region_idx __meminitdata = -1;
+
 int pfn_valid(unsigned long pfn)
 {
 	return memblock_is_map_memory(__pfn_to_phys(pfn));
@@ -203,28 +205,42 @@ EXPORT_SYMBOL(pfn_valid);
 unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
 {
 	struct memblock_type *type = &memblock.memory;
+	struct memblock_region *regions = type->regions;
 	unsigned int right = type->cnt;
 	unsigned int mid, left = 0;
+	unsigned long start_pfn, end_pfn;
 	phys_addr_t addr = PFN_PHYS(++pfn);
 
+	/* fast path, return pfn+1 if next pfn is in the same region */
+	if (early_region_idx != -1) {
+		start_pfn = PFN_DOWN(regions[early_region_idx].base);
+		end_pfn = PFN_DOWN(regions[early_region_idx].base +
+				regions[early_region_idx].size);
+
+		if (pfn >= start_pfn && pfn < end_pfn)
+			return pfn;
+	}
+
+	/* slow path, do the binary searching */
 	do {
 		mid = (right + left) / 2;
 
-		if (addr < type->regions[mid].base)
+		if (addr < regions[mid].base)
 			right = mid;
-		else if (addr >= (type->regions[mid].base +
-				  type->regions[mid].size))
+		else if (addr >= (regions[mid].base + regions[mid].size))
 			left = mid + 1;
 		else {
-			/* addr is within the region, so pfn is valid */
+			early_region_idx = mid;
 			return pfn;
 		}
 	} while (left < right);
 
 	if (right == type->cnt)
 		return -1UL;
-	else
-		return PHYS_PFN(type->regions[right].base);
+
+	early_region_idx = right;
+
+	return PHYS_PFN(regions[early_region_idx].base);
 }
 EXPORT_SYMBOL(memblock_next_valid_pfn);
 #endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index e57d3f2..f0d8c8e5 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -38,6 +38,7 @@ extern void clear_page(void *to);
 typedef struct page *pgtable_t;
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
+extern int early_region_idx;
 extern int pfn_valid(unsigned long);
 extern unsigned long memblock_next_valid_pfn(unsigned long pfn);
 #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 13e43ff..342e4e2 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -285,6 +285,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
+int early_region_idx __meminitdata = -1;
+
 int pfn_valid(unsigned long pfn)
 {
 	return memblock_is_map_memory(pfn << PAGE_SHIFT);
@@ -295,28 +297,42 @@ EXPORT_SYMBOL(pfn_valid);
 unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
 {
 	struct memblock_type *type = &memblock.memory;
+	struct memblock_region *regions = type->regions;
 	unsigned int right = type->cnt;
 	unsigned int mid, left = 0;
+	unsigned long start_pfn, end_pfn;
 	phys_addr_t addr = PFN_PHYS(++pfn);
 
+	/* fast path, return pfn+1 if next pfn is in the same region */
+	if (early_region_idx != -1) {
+		start_pfn = PFN_DOWN(regions[early_region_idx].base);
+		end_pfn = PFN_DOWN(regions[early_region_idx].base +
+				regions[early_region_idx].size);
+
+		if (pfn >= start_pfn && pfn < end_pfn)
+			return pfn;
+	}
+
+	/* slow path, do the binary searching */
 	do {
 		mid = (right + left) / 2;
 
-		if (addr < type->regions[mid].base)
+		if (addr < regions[mid].base)
 			right = mid;
-		else if (addr >= (type->regions[mid].base +
-				  type->regions[mid].size))
+		else if (addr >= (regions[mid].base + regions[mid].size))
 			left = mid + 1;
 		else {
-			/* addr is within the region, so pfn is valid */
+			early_region_idx = mid;
 			return pfn;
 		}
 	} while (left < right);
 
 	if (right == type->cnt)
 		return -1UL;
-	else
-		return PHYS_PFN(type->regions[right].base);
+
+	early_region_idx = right;
+
+	return PHYS_PFN(regions[early_region_idx].base);
 }
 EXPORT_SYMBOL(memblock_next_valid_pfn);
 #endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
-- 
2.7.4