[RFC PATCH 20/24] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap

[Muchun Song <songmuchun@bytedance.com>]

Add a kernel parameter hugetlb_free_vmemmap to disable the feature of
freeing unused vmemmap pages associated with each hugetlb page on boot.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 .../admin-guide/kernel-parameters.txt         |  9 ++++++++
 Documentation/admin-guide/mm/hugetlbpage.rst  |  3 +++
 mm/hugetlb.c                                  | 23 +++++++++++++++++++
 3 files changed, 35 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 5debfe238027..69d18ef6f66b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1551,6 +1551,15 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
+	hugetlb_free_vmemmap=
+			[KNL] When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set,
+			this disables freeing unused vmemmap pages associated
+			each HugeTLB page.
+			Format: { on (default) | off }
+
+			on:  enable the feature
+			off: dosable the feature
+
 	hung_task_panic=
 			[KNL] Should the hung task detector generate panics.
 			Format: 0 | 1
diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst
index f7b1c7462991..7d6129ee97dd 100644
--- a/Documentation/admin-guide/mm/hugetlbpage.rst
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -145,6 +145,9 @@ default_hugepagesz
 
 	will all result in 256 2M huge pages being allocated.  Valid default
 	huge page size is architecture dependent.
+hugetlb_free_vmemmap
+	When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set, this disables freeing
+	unused vmemmap pages associated each HugeTLB page.
 
 When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
 indicates the current number of pre-allocated huge pages of the default size.
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 56c0bf2370ed..28c154679838 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1310,6 +1310,8 @@ static void __free_hugepage(struct hstate *h, struct page *page);
 	(__boundary - 1 < (end) - 1) ? __boundary : (end);		\
 })
 
+static bool hugetlb_free_vmemmap_disabled __initdata;
+
 static inline unsigned int nr_free_vmemmap(struct hstate *h)
 {
 	return h->nr_free_vmemmap_pages;
@@ -1457,6 +1459,13 @@ static void __init hugetlb_vmemmap_init(struct hstate *h)
 	unsigned int order = huge_page_order(h);
 	unsigned int vmemmap_pages;
 
+	if (hugetlb_free_vmemmap_disabled) {
+		h->nr_free_vmemmap_pages = 0;
+		pr_info("HugeTLB: disable free vmemmap pages for %s\n",
+			h->name);
+		return;
+	}
+
 	vmemmap_pages = ((1 << order) * sizeof(struct page)) >> PAGE_SHIFT;
 	/*
 	 * The head page and the first tail page not free to buddy system,
@@ -1867,6 +1876,20 @@ static inline void clear_subpage_hwpoison(struct page *head)
 {
 	set_page_private(head + 4, 0);
 }
+
+static int __init early_hugetlb_free_vmemmap_param(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	if (!strcmp(buf, "off"))
+		hugetlb_free_vmemmap_disabled = true;
+	else if (strcmp(buf, "on"))
+		return -EINVAL;
+
+	return 0;
+}
+early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param);
 #else
 static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
-- 
2.20.1