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>
---
include/linux/arm96_common.h | 31 +++++++++++++++++++++++--------
1 file changed, 23 insertions(+), 8 deletions(-)
diff --git a/include/linux/arm96_common.h b/include/linux/arm96_common.h
index a6f68ea..2f4dea4 100644
--- a/include/linux/arm96_common.h
+++ b/include/linux/arm96_common.h
@@ -5,32 +5,47 @@
#ifndef __ARM96_COMMON_H
#define __ARM96_COMMON_H
#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+static int early_region_idx __init_memblock = -1;
/* HAVE_MEMBLOCK is always enabled on arm and arm64 */
ulong __init_memblock memblock_next_valid_pfn(ulong pfn)
{
struct memblock_type *type = &memblock.memory;
- unsigned int right = type->cnt;
- unsigned int mid, left = 0;
+ struct memblock_region *regions = type->regions;
+ uint right = type->cnt;
+ uint mid, left = 0;
+ ulong 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
