mm: hugetlb_vmemmap: improve hugetlb_vmemmap code readability

There is a discussion about the name of hugetlb_vmemmap_alloc/free in
thread [1].  The suggestion suggested by David is rename "alloc/free" to
"optimize/restore" to make functionalities clearer to users, "optimize"
means the function will optimize vmemmap pages, while "restore" means
restoring its vmemmap pages discared before.  This commit does this.

Another discussion is the confusion RESERVE_VMEMMAP_NR isn't used
explicitly for vmemmap_addr but implicitly for vmemmap_end in
hugetlb_vmemmap_alloc/free.  David suggested we can compute what
hugetlb_vmemmap_init() does now at runtime.  We do not need to worry for
the overhead of computing at runtime since the calculation is simple
enough and those functions are not in a hot path.  This commit has the
following improvements:

  1) The function suffixed name ("optimize/restore") is more expressive.
  2) The logic becomes less weird in hugetlb_vmemmap_optimize/restore().
  3) The hugetlb_vmemmap_init() does not need to be exported anymore.
  4) A ->optimize_vmemmap_pages field in struct hstate is killed.
  5) There is only one place where checks is_power_of_2(sizeof(struct
     page)) instead of two places.
  6) Add more comments for hugetlb_vmemmap_optimize/restore().
  7) For external users, hugetlb_optimize_vmemmap_pages() is used for
     detecting if the HugeTLB's vmemmap pages is optimizable originally.
     In this commit, it is killed and we introduce a new helper
     hugetlb_vmemmap_optimizable() to replace it.  The name is more
     expressive.

Link: https://lore.kernel.org/all/20220404074652.68024-2-songmuchun@bytedance.com/ [1]
Link: https://lkml.kernel.org/r/20220628092235.91270-7-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Will Deacon <will@kernel.org>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 60 insertions, 83 deletions

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 6c7117c30e56..8da2b31bb59f 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -35,16 +35,6 @@ struct vmemmap_remap_walk {
 	struct list_head	*vmemmap_pages;
 };
 
-/*
- * There are a lot of struct page structures associated with each HugeTLB page.
- * For tail pages, the value of compound_head is the same. So we can reuse first
- * page of head page structures. We map the virtual addresses of all the pages
- * of tail page structures to the head page struct, and then free these page
- * frames. Therefore, we need to reserve one pages as vmemmap areas.
- */
-#define RESERVE_VMEMMAP_NR		1U
-#define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
-
 static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
 {
 	pmd_t __pmd;
@@ -426,32 +416,37 @@ EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key);
 static bool vmemmap_optimize_enabled = IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON);
 core_param(hugetlb_free_vmemmap, vmemmap_optimize_enabled, bool, 0);
 
-/*
- * Previously discarded vmemmap pages will be allocated and remapping
- * after this function returns zero.
+/**
+ * hugetlb_vmemmap_restore - restore previously optimized (by
+ *			     hugetlb_vmemmap_optimize()) vmemmap pages which
+ *			     will be reallocated and remapped.
+ * @h:		struct hstate.
+ * @head:	the head page whose vmemmap pages will be restored.
+ *
+ * Return: %0 if @head's vmemmap pages have been reallocated and remapped,
+ * negative error code otherwise.
  */
-int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
+int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head)
 {
 	int ret;
-	unsigned long vmemmap_addr = (unsigned long)head;
-	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
+	unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
+	unsigned long vmemmap_reuse;
 
 	if (!HPageVmemmapOptimized(head))
 		return 0;
 
-	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
-	vmemmap_pages	= hugetlb_optimize_vmemmap_pages(h);
-	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
-	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;
+	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
+	vmemmap_reuse	= vmemmap_start;
+	vmemmap_start	+= HUGETLB_VMEMMAP_RESERVE_SIZE;
 
 	/*
-	 * The pages which the vmemmap virtual address range [@vmemmap_addr,
+	 * The pages which the vmemmap virtual address range [@vmemmap_start,
 	 * @vmemmap_end) are mapped to are freed to the buddy allocator, and
 	 * the range is mapped to the page which @vmemmap_reuse is mapped to.
 	 * When a HugeTLB page is freed to the buddy allocator, previously
 	 * discarded vmemmap pages must be allocated and remapping.
 	 */
-	ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse,
+	ret = vmemmap_remap_alloc(vmemmap_start, vmemmap_end, vmemmap_reuse,
 				  GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE);
 	if (!ret) {
 		ClearHPageVmemmapOptimized(head);
@@ -461,11 +456,14 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
 	return ret;
 }
 
-static unsigned int vmemmap_optimizable_pages(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 (!READ_ONCE(vmemmap_optimize_enabled))
-		return 0;
+		return false;
+
+	if (!hugetlb_vmemmap_optimizable(h))
+		return false;
 
 	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) {
 		pmd_t *pmdp, pmd;
@@ -508,73 +506,47 @@ static unsigned int vmemmap_optimizable_pages(struct hstate *h,
 		 *          +-------------------------------------------+
 		 */
 		if (PageVmemmapSelfHosted(vmemmap_page))
-			return 0;
+			return false;
 	}
 
-	return hugetlb_optimize_vmemmap_pages(h);
+	return true;
 }
 
-void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
+/**
+ * hugetlb_vmemmap_optimize - optimize @head page's vmemmap pages.
+ * @h:		struct hstate.
+ * @head:	the head page whose vmemmap pages will be optimized.
+ *
+ * This function only tries to optimize @head's vmemmap pages and does not
+ * guarantee that the optimization will succeed after it returns. The caller
+ * can use HPageVmemmapOptimized(@head) to detect if @head's vmemmap pages
+ * have been optimized.
+ */
+void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
 {
-	unsigned long vmemmap_addr = (unsigned long)head;
-	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
+	unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
+	unsigned long vmemmap_reuse;
 
-	vmemmap_pages = vmemmap_optimizable_pages(h, head);
-	if (!vmemmap_pages)
+	if (!vmemmap_should_optimize(h, head))
 		return;
 
 	static_branch_inc(&hugetlb_optimize_vmemmap_key);
 
-	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
-	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
-	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;
+	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_addr, @vmemmap_end)
+	 * 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_addr, @vmemmap_end] is mapped to.
+	 * which the range [@vmemmap_start, @vmemmap_end] is mapped to.
 	 */
-	if (vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse))
+	if (vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse))
 		static_branch_dec(&hugetlb_optimize_vmemmap_key);
 	else
 		SetHPageVmemmapOptimized(head);
 }
 
-void __init hugetlb_vmemmap_init(struct hstate *h)
-{
-	unsigned int nr_pages = pages_per_huge_page(h);
-	unsigned int vmemmap_pages;
-
-	/*
-	 * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
-	 * page structs that can be used when HVO is enabled, add a BUILD_BUG_ON
-	 * to catch invalid usage of the tail page structs.
-	 */
-	BUILD_BUG_ON(__NR_USED_SUBPAGE >=
-		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));
-
-	if (!is_power_of_2(sizeof(struct page))) {
-		pr_warn_once("cannot optimize vmemmap pages because \"struct page\" crosses page boundaries\n");
-		return;
-	}
-
-	vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT;
-	/*
-	 * The head page is not to be freed to buddy allocator, the other tail
-	 * pages will map to the head page, so they can be freed.
-	 *
-	 * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? It is true
-	 * on some architectures (e.g. aarch64). See Documentation/arm64/
-	 * hugetlbpage.rst for more details.
-	 */
-	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
-		h->optimize_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
-
-	pr_info("can optimize %d vmemmap pages for %s\n",
-		h->optimize_vmemmap_pages, h->name);
-}
-
-#ifdef CONFIG_PROC_SYSCTL
 static struct ctl_table hugetlb_vmemmap_sysctls[] = {
 	{
 		.procname	= "hugetlb_optimize_vmemmap",
@@ -586,16 +558,21 @@ static struct ctl_table hugetlb_vmemmap_sysctls[] = {
 	{ }
 };
 
-static __init int hugetlb_vmemmap_sysctls_init(void)
+static int __init hugetlb_vmemmap_init(void)
 {
-	/*
-	 * If "struct page" crosses page boundaries, the vmemmap pages cannot
-	 * be optimized.
-	 */
-	if (is_power_of_2(sizeof(struct page)))
-		register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
-
+	/* HUGETLB_VMEMMAP_RESERVE_SIZE should cover all used struct pages */
+	BUILD_BUG_ON(__NR_USED_SUBPAGE * sizeof(struct page) > HUGETLB_VMEMMAP_RESERVE_SIZE);
+
+	if (IS_ENABLED(CONFIG_PROC_SYSCTL)) {
+		const struct hstate *h;
+
+		for_each_hstate(h) {
+			if (hugetlb_vmemmap_optimizable(h)) {
+				register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
+				break;
+			}
+		}
+	}
 	return 0;
 }
-late_initcall(hugetlb_vmemmap_sysctls_init);
-#endif /* CONFIG_PROC_SYSCTL */
+late_initcall(hugetlb_vmemmap_init);