@@ -1224,7 +1224,7 @@ void __meminit __free_pages_core(struct page *page, unsigned int order,
{
unsigned int nr_pages = 1 << order;
struct page *p = page;
- unsigned int loop;
+ unsigned int loop = 0;
/*
* When initializing the memmap, __init_single_page() sets the refcount
@@ -1236,16 +1236,14 @@ void __meminit __free_pages_core(struct page *page, unsigned int order,
*/
if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) &&
unlikely(context == MEMINIT_HOTPLUG)) {
- prefetchw(p);
- for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
- prefetchw(p + 1);
+ for (;;) {
VM_WARN_ON_ONCE(PageReserved(p));
__ClearPageOffline(p);
set_page_count(p, 0);
+ if (++loop >= nr_pages)
+ break;
+ p++;
}
- VM_WARN_ON_ONCE(PageReserved(p));
- __ClearPageOffline(p);
- set_page_count(p, 0);
/*
* Freeing the page with debug_pagealloc enabled will try to
@@ -1255,14 +1253,13 @@ void __meminit __free_pages_core(struct page *page, unsigned int order,
debug_pagealloc_map_pages(page, nr_pages);
adjust_managed_page_count(page, nr_pages);
} else {
- prefetchw(p);
- for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
- prefetchw(p + 1);
+ for (;;) {
__ClearPageReserved(p);
set_page_count(p, 0);
+ if (++loop >= nr_pages)
+ break;
+ p++;
}
- __ClearPageReserved(p);
- set_page_count(p, 0);
/* memblock adjusts totalram_pages() manually. */
atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
The prefetchw() is introduced from an ancient patch[1]. The change log says: The basic idea is to free higher order pages instead of going through every single one. Also, some unnecessary atomic operations are done away with and replaced with non-atomic equivalents, and prefetching is done where it helps the most. For a more in-depth discusion of this patch, please see the linux-ia64 archives (topic is "free bootmem feedback patch"). So there are several changes improve the bootmem freeing, in which the most basic idea is freeing higher order pages. And as Matthew says, "Itanium CPUs of this era had no prefetchers." I did 10 round bootup tests before and after this change, the data doesn't prove prefetchw() help speeding up bootmem freeing. The sum of the 10 round bootmem freeing time after prefetchw() removal even 5.2% faster than before. [1]: https://lore.kernel.org/linux-ia64/40F46962.4090604@sgi.com/ Signed-off-by: Wei Yang <richard.weiyang@gmail.com> Suggested-by: Matthew Wilcox <willy@infradead.org> CC: David Hildenbrand <david@redhat.com> --- v2: slightly adjust the loop based on David's comment The patch is based on mm-stable with David's change. commit 3dadec1babf9eee0c67c967df931d6f0cb124a04 mm: pass meminit_context to __free_pages_core() --- mm/page_alloc.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-)