[PATCH v2 5/5] mm: page_alloc: reduce unnecessary binary search in early_pfn_valid()

[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. in early_pfn_valid(), if pfn and
pfn+1 are in the same memblock region, we can record the last returned
memblock region index and check if pfn++ is still in the same region.

Currently it only improve the performance on arm64 and will have no
impact on other arches.

Signed-off-by: Jia He <jia.he@xxxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/mmzone_32.h |  2 +-
 include/linux/mmzone.h           | 12 +++++++++---
 mm/page_alloc.c                  |  2 +-
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 73d8dd1..329d3ba 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -49,7 +49,7 @@ static inline int pfn_valid(int pfn)
 	return 0;
 }
 
-#define early_pfn_valid(pfn)	pfn_valid((pfn))
+#define early_pfn_valid(pfn, last_region_idx)	pfn_valid((pfn))
 
 #endif /* CONFIG_DISCONTIGMEM */
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d797716..3a686af 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1267,9 +1267,15 @@ static inline int pfn_present(unsigned long pfn)
 })
 #else
 #define pfn_to_nid(pfn)		(0)
-#endif
+#endif /*CONFIG_NUMA*/
+
+#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+#define early_pfn_valid(pfn, last_region_idx) \
+				pfn_valid_region(pfn, last_region_idx)
+#else
+#define early_pfn_valid(pfn, last_region_idx)	pfn_valid(pfn)
+#endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
 
-#define early_pfn_valid(pfn)	pfn_valid(pfn)
 void sparse_init(void);
 #else
 #define sparse_init()	do {} while (0)
@@ -1288,7 +1294,7 @@ struct mminit_pfnnid_cache {
 };
 
 #ifndef early_pfn_valid
-#define early_pfn_valid(pfn)	(1)
+#define early_pfn_valid(pfn, last_region_idx)	(1)
 #endif
 
 void memory_present(int nid, unsigned long start, unsigned long end);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0bb0274..68aef71 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5484,8 +5484,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		if (context != MEMMAP_EARLY)
 			goto not_early;
 
-		if (!early_pfn_valid(pfn)) {
 #if (defined CONFIG_HAVE_MEMBLOCK) && (defined CONFIG_HAVE_ARCH_PFN_VALID)
+		if (!early_pfn_valid(pfn, &idx)) {
 			/*
 			 * Skip to the pfn preceding the next valid one (or
 			 * end_pfn), such that we hit a valid pfn (or end_pfn)
-- 
2.7.4