hugetlb: perform vmemmap optimization on a list of pages

When adding hugetlb pages to the pool, we first create a list of the
allocated pages before adding to the pool.  Pass this list of pages to a
new routine hugetlb_vmemmap_optimize_folios() for vmemmap optimization.

Due to significant differences in vmemmmap initialization for bootmem
allocated hugetlb pages, a new routine prep_and_add_bootmem_folios is
created.

We also modify the routine vmemmap_should_optimize() to check for pages
that are already optimized.  There are code paths that might request
vmemmap optimization twice and we want to make sure this is not attempted.

Link: https://lkml.kernel.org/r/20231019023113.345257-4-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Konrad Dybcio <konradybcio@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <naoya.horiguchi@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Usama Arif <usama.arif@bytedance.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Author: mjkravetz

mm/hugetlb.c

@@ -2282,6 +2282,9 @@ static void prep_and_add_allocated_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);
+
 	/* Add all new pool pages to free lists in one lock cycle */
 	spin_lock_irqsave(&hugetlb_lock, flags);
 	list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
@@ -3344,6 +3347,35 @@ static void __init hugetlb_folio_init_vmemmap(struct folio *folio,
 	prep_compound_head((struct page *)folio, huge_page_order(h));
 }
 
+static void __init prep_and_add_bootmem_folios(struct hstate *h,
+					struct list_head *folio_list)
+{
+	unsigned long flags;
+	struct folio *folio, *tmp_f;
+
+	/* Send list for bulk vmemmap optimization processing */
+	hugetlb_vmemmap_optimize_folios(h, folio_list);
+
+	/* Add all new pool pages to free lists in one lock cycle */
+	spin_lock_irqsave(&hugetlb_lock, flags);
+	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,
+					HUGETLB_VMEMMAP_RESERVE_PAGES,
+					pages_per_huge_page(h));
+		}
+		__prep_account_new_huge_page(h, folio_nid(folio));
+		enqueue_hugetlb_folio(h, folio);
+	}
+	spin_unlock_irqrestore(&hugetlb_lock, flags);
+}
+
 /*
  * Put bootmem huge pages into the standard lists after mem_map is up.
  * Note: This only applies to gigantic (order > MAX_ORDER) pages.
@@ -3364,20 +3396,15 @@ static void __init gather_bootmem_prealloc(void)
 		 * in this list.  If so, process each size separately.
 		 */
 		if (h != prev_h && prev_h != NULL)
-			prep_and_add_allocated_folios(prev_h, &folio_list);
+			prep_and_add_bootmem_folios(prev_h, &folio_list);
 		prev_h = h;
 
 		VM_BUG_ON(!hstate_is_gigantic(h));
 		WARN_ON(folio_ref_count(folio) != 1);
 
 		hugetlb_folio_init_vmemmap(folio, h,
 					   HUGETLB_VMEMMAP_RESERVE_PAGES);
-		__prep_new_hugetlb_folio(h, 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));
+		init_new_hugetlb_folio(h, folio);
 		list_add(&folio->lru, &folio_list);
 
 		/*
@@ -3389,7 +3416,7 @@ static void __init gather_bootmem_prealloc(void)
 		cond_resched();
 	}
 
-	prep_and_add_allocated_folios(h, &folio_list);
+	prep_and_add_bootmem_folios(h, &folio_list);
 }
 
 static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)

mm/hugetlb_vmemmap.c

@@ -483,6 +483,9 @@ int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head)
 /* Return true iff a HugeTLB whose vmemmap should and can be optimized. */
 static bool vmemmap_should_optimize(const struct hstate *h, const struct page *head)
 {
+	if (HPageVmemmapOptimized((struct page *)head))
+		return false;
+
 	if (!READ_ONCE(vmemmap_optimize_enabled))
 		return false;
 
@@ -572,6 +575,14 @@ void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
 		SetHPageVmemmapOptimized(head);
 }
 
+void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
+{
+	struct folio *folio;
+
+	list_for_each_entry(folio, folio_list, lru)
+		hugetlb_vmemmap_optimize(h, &folio->page);
+}
+
 static struct ctl_table hugetlb_vmemmap_sysctls[] = {
 	{
 		.procname	= "hugetlb_optimize_vmemmap",

mm/hugetlb_vmemmap.h

@@ -20,6 +20,7 @@
 #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);
+void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list);
 
 static inline unsigned int hugetlb_vmemmap_size(const struct hstate *h)
 {
@@ -48,6 +49,10 @@ static inline void hugetlb_vmemmap_optimize(const struct hstate *h, struct page
 {
 }
 
+static inline void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
+{
+}
+
 static inline unsigned int hugetlb_vmemmap_optimizable_size(const struct hstate *h)
 {
 	return 0;