mm: hugetlb: skip initialization of gigantic tail struct pages if freed by HVO

The new boot flow when it comes to initialization of gigantic pages is as
follows:

- At boot time, for a gigantic page during __alloc_bootmem_hugepage, the
  region after the first struct page is marked as noinit.

- This results in only the first struct page to be initialized in
  reserve_bootmem_region.  As the tail struct pages are not initialized at
  this point, there can be a significant saving in boot time if HVO
  succeeds later on.

- Later on in the boot, the head page is prepped and the first
  HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page) - 1 tail struct pages
  are initialized.

- HVO is attempted.  If it is not successful, then the rest of the tail
  struct pages are initialized.  If it is successful, no more tail struct
  pages need to be initialized saving significant boot time.

The WARN_ON for increased ref count in gather_bootmem_prealloc was changed
to a VM_BUG_ON.  This is OK as there should be no speculative references
this early in boot process.  The VM_BUG_ON's are there just in case such
code is introduced.

[akpm@linux-foundation.org: make it nicer for 80 cols]
Link: https://lkml.kernel.org/r/20230913105401.519709-5-usama.arif@bytedance.com
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Fam Zheng <fam.zheng@bytedance.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Punit Agrawal <punit.agrawal@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/hugetlb.c

@@ -3169,6 +3169,16 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
 	}
 
 found:
+
+	/*
+	 * 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(virt_to_phys((void *)m + PAGE_SIZE),
+		huge_page_size(h) - PAGE_SIZE);
 	/* Put them into a private list first because mem_map is not up yet */
 	INIT_LIST_HEAD(&m->list);
 	list_add(&m->list, &huge_boot_pages);
@@ -3176,6 +3186,43 @@ found:
 	return 1;
 }
 
+/* Initialize [start_page:end_page_number] tail struct pages of a hugepage */
+static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio,
+					unsigned long start_page_number,
+					unsigned long end_page_number)
+{
+	enum zone_type zone = zone_idx(folio_zone(folio));
+	int nid = folio_nid(folio);
+	unsigned long head_pfn = folio_pfn(folio);
+	unsigned long pfn, end_pfn = head_pfn + end_page_number;
+	int ret;
+
+	for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) {
+		struct page *page = pfn_to_page(pfn);
+
+		__init_single_page(page, pfn, zone, nid);
+		prep_compound_tail((struct page *)folio, pfn - head_pfn);
+		ret = page_ref_freeze(page, 1);
+		VM_BUG_ON(!ret);
+	}
+}
+
+static void __init hugetlb_folio_init_vmemmap(struct folio *folio,
+					      struct hstate *h,
+					      unsigned long nr_pages)
+{
+	int ret;
+
+	/* Prepare folio head */
+	__folio_clear_reserved(folio);
+	__folio_set_head(folio);
+	ret = page_ref_freeze(&folio->page, 1);
+	VM_BUG_ON(!ret);
+	/* Initialize the necessary tail struct pages */
+	hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages);
+	prep_compound_head((struct page *)folio, huge_page_order(h));
+}
+
 /*
  * Put bootmem huge pages into the standard lists after mem_map is up.
  * Note: This only applies to gigantic (order > MAX_ORDER) pages.
@@ -3186,19 +3233,21 @@ static void __init gather_bootmem_prealloc(void)
 
 	list_for_each_entry(m, &huge_boot_pages, list) {
 		struct page *page = virt_to_page(m);
-		struct folio *folio = page_folio(page);
+		struct folio *folio = (void *)page;
 		struct hstate *h = m->hstate;
 
 		VM_BUG_ON(!hstate_is_gigantic(h));
 		WARN_ON(folio_ref_count(folio) != 1);
-		if (prep_compound_gigantic_folio(folio, huge_page_order(h))) {
-			WARN_ON(folio_test_reserved(folio));
+
+		hugetlb_folio_init_vmemmap(folio, h,
+					   HUGETLB_VMEMMAP_RESERVE_PAGES);
 		prep_new_hugetlb_folio(h, folio, folio_nid(folio));
+		/* If HVO fails, initialize all tail struct pages */
+		if (!HPageVmemmapOptimized(&folio->page))
+			hugetlb_folio_init_tail_vmemmap(folio,
+						HUGETLB_VMEMMAP_RESERVE_PAGES,
+						pages_per_huge_page(h));
 		free_huge_folio(folio); /* add to the hugepage allocator */
-		} else {
-			/* VERY unlikely inflated ref count on a tail page */
-			free_gigantic_folio(folio, huge_page_order(h));
-		}
 
 		/*
 		 * We need to restore the 'stolen' pages to totalram_pages
@@ -3209,6 +3258,7 @@ static void __init gather_bootmem_prealloc(void)
 		cond_resched();
 	}
 }
+
 static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
 {
 	unsigned long i;

mm/hugetlb_vmemmap.c

@@ -588,7 +588,7 @@ static int __init hugetlb_vmemmap_init(void)
 	const struct hstate *h;
 
 	/* HUGETLB_VMEMMAP_RESERVE_SIZE should cover all used struct pages */
-	BUILD_BUG_ON(__NR_USED_SUBPAGE * sizeof(struct page) > HUGETLB_VMEMMAP_RESERVE_SIZE);
+	BUILD_BUG_ON(__NR_USED_SUBPAGE > HUGETLB_VMEMMAP_RESERVE_PAGES);
 
 	for_each_hstate(h) {
 		if (hugetlb_vmemmap_optimizable(h)) {

mm/hugetlb_vmemmap.h

@@ -10,15 +10,16 @@
 #define _LINUX_HUGETLB_VMEMMAP_H
 #include <linux/hugetlb.h>
 
-#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
-int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head);
-void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head);
-
 /*
  * Reserve one vmemmap page, all vmemmap addresses are mapped to it. See
  * Documentation/vm/vmemmap_dedup.rst.
  */
 #define HUGETLB_VMEMMAP_RESERVE_SIZE	PAGE_SIZE
+#define HUGETLB_VMEMMAP_RESERVE_PAGES	(HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page))
+
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head);
+void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head);
 
 static inline unsigned int hugetlb_vmemmap_size(const struct hstate *h)
 {

mm/internal.h

@@ -1155,6 +1155,9 @@ struct vma_prepare {
 	struct vm_area_struct *remove2;
 };
 
+void __meminit __init_single_page(struct page *page, unsigned long pfn,
+				unsigned long zone, int nid);
+
 /* shrinker related functions */
 unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg,
 			  int priority);

mm/mm_init.c

@@ -555,7 +555,7 @@ out:
 	node_states[N_MEMORY] = saved_node_state;
 }
 
-static void __meminit __init_single_page(struct page *page, unsigned long pfn,
+void __meminit __init_single_page(struct page *page, unsigned long pfn,
 				unsigned long zone, int nid)
 {
 	mm_zero_struct_page(page);