[PATCH 06/11] mm/hugetlb: initialize all struct pages for bootmem hugepages

[Muchun Song <songmuchun@bytedance.com>]

Boot-time gigantic hugepages currently leave the head struct page to
the generic memmap initialization path while the HugeTLB code
initializes the remaining struct pages itself.

Mark the full hugepage noinit and initialize the head struct page in
hugetlb_folio_init_vmemmap() as well, so the whole compound-page setup
is handled in one place.

This can also reduce memblock metadata overhead when many boot-time
HugeTLB pages are reserved, because physically contiguous hugepages
can be covered by fewer noinit regions.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c | 27 ++++++++++-----------------
 1 file changed, 10 insertions(+), 17 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ff6f837b6df0..d2aaad235458 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3216,15 +3216,7 @@ static bool __init alloc_bootmem_huge_page(struct hstate *h, int nid)
 		list_add_tail(&m->list, &huge_boot_pages[nid]);
 		m->flags |= HUGE_BOOTMEM_ZONES_VALID;
 		hugetlb_vmemmap_optimize_bootmem_page(pfn, huge_page_order(h));
-		/*
-		 * Only initialize the head struct page in memmap_init_reserved_pages,
-		 * rest of the struct pages will be initialized by the HugeTLB
-		 * subsystem itself.
-		 * The head struct page is used to get folio information by the HugeTLB
-		 * subsystem like zone id and node id.
-		 */
-		memblock_reserved_mark_noinit(__pa((void *)m + PAGE_SIZE),
-				huge_page_size(h) - PAGE_SIZE);
+		memblock_reserved_mark_noinit(__pa(m), huge_page_size(h));
 	}
 
 	return true;
@@ -3255,22 +3247,23 @@ static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio,
 }
 
 static void __init hugetlb_folio_init_vmemmap(struct folio *folio,
+					      unsigned long pfn,
 					      struct hstate *h,
+					      enum zone_type zone, int nid,
 					      unsigned long nr_pages)
 {
-	int ret;
+	struct page *head = &folio->page;
 
 	/*
 	 * This is an open-coded prep_compound_page() whereby we avoid
 	 * walking pages twice by initializing/preparing+freezing them in the
 	 * same go.
 	 */
-	__folio_clear_reserved(folio);
+	__init_single_page(head, pfn, zone, nid);
 	__folio_set_head(folio);
-	ret = folio_ref_freeze(folio, 1);
-	VM_BUG_ON(!ret);
+	set_page_count(head, 0);
 	hugetlb_folio_init_tail_vmemmap(folio, h, 1, nr_pages);
-	prep_compound_head(&folio->page, huge_page_order(h));
+	prep_compound_head(head, huge_page_order(h));
 }
 
 /*
@@ -3328,8 +3321,9 @@ static void __init gather_bootmem_prealloc_node(unsigned long nid)
 	list_for_each_entry_safe(m, tm, &huge_boot_pages[nid], list) {
 		struct page *page = virt_to_page(m);
 		struct folio *folio = (void *)page;
-		const unsigned long pfn = folio_pfn(folio);
+		const unsigned long pfn = PHYS_PFN(__pa(m));
 		const unsigned long nr_pages = pages_per_huge_page(m->hstate);
+		const enum zone_type zone = zone_idx(pfn_to_zone(pfn, nid));
 		unsigned long nr_struct_pages = nr_pages;
 
 		h = m->hstate;
@@ -3342,11 +3336,10 @@ static void __init gather_bootmem_prealloc_node(unsigned long nid)
 		prev_h = h;
 
 		VM_BUG_ON(!hstate_is_gigantic(h));
-		WARN_ON(folio_ref_count(folio) != 1);
 
 		if (vmemmap_optimizable_order(pfn_to_section_compound_order(pfn)))
 			nr_struct_pages = VMEMMAP_OPTIMIZATION_NR_STRUCT_PAGES;
-		hugetlb_folio_init_vmemmap(folio, h, nr_struct_pages);
+		hugetlb_folio_init_vmemmap(folio, pfn, h, zone, nid, nr_struct_pages);
 		init_new_hugetlb_folio(folio);
 
 		if (vmemmap_optimizable_order(pfn_to_section_compound_order(pfn)))
-- 
2.54.0