@@ -718,7 +718,7 @@ static void __meminit init_reserved_page(unsigned long pfn, int nid)
if (zone_spans_pfn(zone, pfn))
break;
}
- __init_single_page(pfn_to_page(pfn), pfn, zid, nid, INIT_PAGE_COUNT);
+ __init_single_page(pfn_to_page(pfn), pfn, zid, nid, 0);
}
#else
static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}
@@ -756,8 +756,11 @@ void __meminit reserve_bootmem_region(phys_addr_t start,
init_reserved_page(start_pfn, nid);
- /* Avoid false-positive PageTail() */
- INIT_LIST_HEAD(&page->lru);
+ /*
+ * We didn't init page count in memmap_init_range when
+ * MEMINIT_EARLY, so it must init page count here.
+ */
+ init_page_count(page);
/*
* no need for atomic set_bit because the struct
@@ -850,6 +853,7 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone
struct vmem_altmap *altmap, int migratetype)
{
unsigned long pfn, end_pfn = start_pfn + size;
+ enum page_init_flags flags = 0;
struct page *page;
if (highest_memmap_pfn < end_pfn - 1)
@@ -888,9 +892,15 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone
}
page = pfn_to_page(pfn);
- __init_single_page(page, pfn, zone, nid, INIT_PAGE_COUNT);
+
+ /* If the context is MEMINIT_EARLY, we will init page count and
+ * mark page reserved in reserve_bootmem_region, the free region
+ * wouldn't have page count and we will check the pages count
+ * in __free_pages_core.
+ */
if (context == MEMINIT_HOTPLUG)
- __SetPageReserved(page);
+ flags = INIT_PAGE_COUNT | INIT_PAGE_RESERVED;
+ __init_single_page(page, pfn, zone, nid, flags);
/*
* Usually, we want to mark the pageblock MIGRATE_MOVABLE,
@@ -1289,18 +1289,22 @@ void __free_pages_core(struct page *page, unsigned int order)
unsigned int loop;
/*
- * When initializing the memmap, __init_single_page() sets the refcount
- * of all pages to 1 ("allocated"/"not free"). We have to set the
- * refcount of all involved pages to 0.
+ * When initializing the memmap, memmap_init_range sets the refcount
+ * of all pages to 1 ("reserved" and "free") in hotplug context. We
+ * have to set the refcount of all involved pages to 0. Otherwise,
+ * we don't do it, as reserve_bootmem_region only set the refcount on
+ * reserve region ("reserved") in early context.
*/
- prefetchw(p);
- for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
- prefetchw(p + 1);
+ if (page_count(page)) {
+ prefetchw(p);
+ for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
+ prefetchw(p + 1);
+ __ClearPageReserved(p);
+ set_page_count(p, 0);
+ }
__ClearPageReserved(p);
set_page_count(p, 0);
}
- __ClearPageReserved(p);
- set_page_count(p, 0);
atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
memmap_init_range() would init page count of all pages, but the free pages count would be reset in __free_pages_core(). There are opposite operations. It's unnecessary and time-consuming when it's MEMINIT_EARLY context. Init page count in reserve_bootmem_region when in MEMINIT_EARLY context, and check the page count before reset it. At the same time, the INIT_LIST_HEAD in reserve_bootmem_region isn't need, as it already done in __init_single_page. The following data was tested on an x86 machine with 190GB of RAM. before: free_low_memory_core_early() 341ms after: free_low_memory_core_early() 285ms Signed-off-by: Yajun Deng <yajun.deng@linux.dev> --- v5: add flags in memmap_init_range. v4: same with v2. v3: same with v2. v2: check page count instead of check context before reset it. v1: https://lore.kernel.org/all/20230922070923.355656-1-yajun.deng@linux.dev/ --- mm/mm_init.c | 20 +++++++++++++++----- mm/page_alloc.c | 20 ++++++++++++-------- 2 files changed, 27 insertions(+), 13 deletions(-)