[PATCH 05/11] mm/hugetlb: drop boot-time HVO handling for gigantic folios

[Muchun Song]

HugeTLB HVO is currently supported on x86-64, riscv64, and LoongArch.
On x86-64 and riscv64, gigantic HugeTLB pages are larger than the
section size, so the existing section-based vmemmap optimization
infrastructure is already sufficient to cover the whole folio.  On
LoongArch, HugeTLB HVO is supported without gigantic HugeTLB pages.

Therefore, boot-time HugeTLB HVO folios can rely on the section-based
vmemmap optimization infrastructure directly, without the extra bulk
optimization and fallback handling.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
---
 mm/hugetlb.c         | 25 +++++++------------------
 mm/hugetlb_vmemmap.c | 17 +----------------
 2 files changed, 8 insertions(+), 34 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index da1c17f14a62..ff6f837b6df0 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3305,21 +3305,7 @@ static void __init prep_and_add_bootmem_folios(struct hstate *h,
 	unsigned long flags;
 	struct folio *folio, *tmp_f;
 
-	/* Send list for bulk vmemmap optimization processing */
-	hugetlb_vmemmap_optimize_folios(h, folio_list);
-
 	list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
-		if (!folio_test_hugetlb_vmemmap_optimized(folio)) {
-			/*
-			 * If HVO fails, initialize all tail struct pages
-			 * We do not worry about potential long lock hold
-			 * time as this is early in boot and there should
-			 * be no contention.
-			 */
-			hugetlb_folio_init_tail_vmemmap(folio, h,
-					VMEMMAP_OPTIMIZATION_NR_STRUCT_PAGES,
-					pages_per_huge_page(h));
-		}
 		hugetlb_bootmem_init_migratetype(folio, h);
 		/* Subdivide locks to achieve better parallel performance */
 		spin_lock_irqsave(&hugetlb_lock, flags);
@@ -3343,6 +3329,8 @@ static void __init gather_bootmem_prealloc_node(unsigned long nid)
 		struct page *page = virt_to_page(m);
 		struct folio *folio = (void *)page;
 		const unsigned long pfn = folio_pfn(folio);
+		const unsigned long nr_pages = pages_per_huge_page(m->hstate);
+		unsigned long nr_struct_pages = nr_pages;
 
 		h = m->hstate;
 		/*
@@ -3356,13 +3344,14 @@ static void __init gather_bootmem_prealloc_node(unsigned long nid)
 		VM_BUG_ON(!hstate_is_gigantic(h));
 		WARN_ON(folio_ref_count(folio) != 1);
 
-		hugetlb_folio_init_vmemmap(folio, h,
-					   VMEMMAP_OPTIMIZATION_NR_STRUCT_PAGES);
+		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);
 		init_new_hugetlb_folio(folio);
 
 		if (vmemmap_optimizable_order(pfn_to_section_compound_order(pfn)))
 			folio_set_hugetlb_vmemmap_optimized(folio);
-		section_set_compound_order_range(pfn, folio_nr_pages(folio), 0);
+		section_set_compound_order_range(pfn, nr_pages, 0);
 
 		list_add(&folio->lru, &folio_list);
 
@@ -3377,7 +3366,7 @@ static void __init gather_bootmem_prealloc_node(unsigned long nid)
 		if (hugetlb_early_cma(h))
 			folio_set_hugetlb_cma(folio);
 		else
-			adjust_managed_page_count(page, pages_per_huge_page(h));
+			adjust_managed_page_count(page, nr_pages);
 		cond_resched();
 	}
 
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index ba8e11e399b2..d73ceeef392e 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -552,7 +552,6 @@ static int hugetlb_vmemmap_pteify_folio(const struct hstate *h, struct folio *fo
 void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
 {
 	struct folio *folio;
-	unsigned long nr_to_optimize = 0;
 	LIST_HEAD(vmemmap_pages);
 	unsigned long flags = VMEMMAP_DEFER_TLB_FLUSH;
 
@@ -560,18 +559,7 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 		return;
 
 	list_for_each_entry(folio, folio_list, lru) {
-		int ret;
-
-		/*
-		 * Bootmem gigantic folios may already be marked optimized when
-		 * their vmemmap layout was prepared earlier, so skip them here.
-		 */
-		if (folio_test_hugetlb_vmemmap_optimized(folio))
-			continue;
-
-		nr_to_optimize++;
-
-		ret = hugetlb_vmemmap_pteify_folio(h, folio, flags);
+		int ret = hugetlb_vmemmap_pteify_folio(h, folio, flags);
 
 		/*
 		 * Splitting the PMD requires allocating a page, thus let's fail
@@ -583,9 +571,6 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 			break;
 	}
 
-	if (!nr_to_optimize)
-		return;
-
 	flush_tlb_all();
 
 	list_for_each_entry(folio, folio_list, lru) {
-- 
2.54.0