hugetlb: batch freeing of vmemmap pages

Now that batching of hugetlb vmemmap optimization processing is possible,
batch the freeing of vmemmap pages.  When freeing vmemmap pages for a
hugetlb page, we add them to a list that is freed after the entire batch
has been processed.

This enhances the ability to return contiguous ranges of memory to the low
level allocators.

Link: https://lkml.kernel.org/r/20231019023113.345257-6-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>

mm/hugetlb_vmemmap.c

@@ -251,7 +251,7 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
 	}
 
 	entry = mk_pte(walk->reuse_page, pgprot);
-	list_add_tail(&page->lru, walk->vmemmap_pages);
+	list_add(&page->lru, walk->vmemmap_pages);
 	set_pte_at(&init_mm, addr, pte, entry);
 }
 
@@ -306,18 +306,20 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
  * @end:	end address of the vmemmap virtual address range that we want to
  *		remap.
  * @reuse:	reuse address.
+ * @vmemmap_pages: list to deposit vmemmap pages to be freed.  It is callers
+ *		responsibility to free pages.
  *
  * Return: %0 on success, negative error code otherwise.
  */
 static int vmemmap_remap_free(unsigned long start, unsigned long end,
-			      unsigned long reuse)
+			      unsigned long reuse,
+			      struct list_head *vmemmap_pages)
 {
 	int ret;
-	LIST_HEAD(vmemmap_pages);
 	struct vmemmap_remap_walk walk = {
 		.remap_pte	= vmemmap_remap_pte,
 		.reuse_addr	= reuse,
-		.vmemmap_pages	= &vmemmap_pages,
+		.vmemmap_pages	= vmemmap_pages,
 	};
 	int nid = page_to_nid((struct page *)reuse);
 	gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
@@ -334,7 +336,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
 	if (walk.reuse_page) {
 		copy_page(page_to_virt(walk.reuse_page),
 			  (void *)walk.reuse_addr);
-		list_add(&walk.reuse_page->lru, &vmemmap_pages);
+		list_add(&walk.reuse_page->lru, vmemmap_pages);
 	}
 
 	/*
@@ -365,15 +367,13 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
 		walk = (struct vmemmap_remap_walk) {
 			.remap_pte	= vmemmap_restore_pte,
 			.reuse_addr	= reuse,
-			.vmemmap_pages	= &vmemmap_pages,
+			.vmemmap_pages	= vmemmap_pages,
 		};
 
 		vmemmap_remap_range(reuse, end, &walk);
 	}
 	mmap_read_unlock(&init_mm);
 
-	free_vmemmap_page_list(&vmemmap_pages);
-
 	return ret;
 }
 
@@ -389,7 +389,7 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
 		page = alloc_pages_node(nid, gfp_mask, 0);
 		if (!page)
 			goto out;
-		list_add_tail(&page->lru, list);
+		list_add(&page->lru, list);
 	}
 
 	return 0;
@@ -577,6 +577,39 @@ static bool vmemmap_should_optimize(const struct hstate *h, const struct page *h
 	return true;
 }
 
+static int __hugetlb_vmemmap_optimize(const struct hstate *h,
+					struct page *head,
+					struct list_head *vmemmap_pages)
+{
+	int ret = 0;
+	unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
+	unsigned long vmemmap_reuse;
+
+	VM_WARN_ON_ONCE(!PageHuge(head));
+	if (!vmemmap_should_optimize(h, head))
+		return ret;
+
+	static_branch_inc(&hugetlb_optimize_vmemmap_key);
+
+	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
+	vmemmap_reuse	= vmemmap_start;
+	vmemmap_start	+= HUGETLB_VMEMMAP_RESERVE_SIZE;
+
+	/*
+	 * Remap the vmemmap virtual address range [@vmemmap_start, @vmemmap_end)
+	 * to the page which @vmemmap_reuse is mapped to.  Add pages previously
+	 * mapping the range to vmemmap_pages list so that they can be freed by
+	 * the caller.
+	 */
+	ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse, vmemmap_pages);
+	if (ret)
+		static_branch_dec(&hugetlb_optimize_vmemmap_key);
+	else
+		SetHPageVmemmapOptimized(head);
+
+	return ret;
+}
+
 /**
  * hugetlb_vmemmap_optimize - optimize @head page's vmemmap pages.
  * @h:		struct hstate.
@@ -589,36 +622,33 @@ static bool vmemmap_should_optimize(const struct hstate *h, const struct page *h
  */
 void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
 {
-	unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
+	LIST_HEAD(vmemmap_pages);
-	unsigned long vmemmap_reuse;
 
-	VM_WARN_ON_ONCE(!PageHuge(head));
+	__hugetlb_vmemmap_optimize(h, head, &vmemmap_pages);
-	if (!vmemmap_should_optimize(h, head))
+	free_vmemmap_page_list(&vmemmap_pages);
-		return;
-
-	static_branch_inc(&hugetlb_optimize_vmemmap_key);
-
-	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
-	vmemmap_reuse	= vmemmap_start;
-	vmemmap_start	+= HUGETLB_VMEMMAP_RESERVE_SIZE;
-
-	/*
-	 * Remap the vmemmap virtual address range [@vmemmap_start, @vmemmap_end)
-	 * to the page which @vmemmap_reuse is mapped to, then free the pages
-	 * which the range [@vmemmap_start, @vmemmap_end] is mapped to.
-	 */
-	if (vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse))
-		static_branch_dec(&hugetlb_optimize_vmemmap_key);
-	else
-		SetHPageVmemmapOptimized(head);
 }
 
 void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
 {
 	struct folio *folio;
+	LIST_HEAD(vmemmap_pages);
 
-	list_for_each_entry(folio, folio_list, lru)
+	list_for_each_entry(folio, folio_list, lru) {
-		hugetlb_vmemmap_optimize(h, &folio->page);
+		int ret = __hugetlb_vmemmap_optimize(h, &folio->page,
+								&vmemmap_pages);
+
+		/*
+		 * Pages to be freed may have been accumulated.  If we
+		 * encounter an ENOMEM,  free what we have and try again.
+		 */
+		if (ret == -ENOMEM && !list_empty(&vmemmap_pages)) {
+			free_vmemmap_page_list(&vmemmap_pages);
+			INIT_LIST_HEAD(&vmemmap_pages);
+			__hugetlb_vmemmap_optimize(h, &folio->page, &vmemmap_pages);
+		}
+	}
+
+	free_vmemmap_page_list(&vmemmap_pages);
 }
 
 static struct ctl_table hugetlb_vmemmap_sysctls[] = {