[PATCH v16 6/9] mm: hugetlb: add a kernel parameter hugetlb_free_vmemmap

[Muchun Song]

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

We disables PMD mapping of vmemmap pages for x86-64 arch when this
feature is enabled. Because vmemmap_remap_free() depends on vmemmap
being base page mapped.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
Reviewed-by: Barry Song <song.bao.hua@xxxxxxxxxxxxx>
Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
---
 Documentation/admin-guide/kernel-parameters.txt | 14 ++++++++++++++
 Documentation/admin-guide/mm/hugetlbpage.rst    | 14 +++++++++-----
 arch/x86/mm/init_64.c                           |  8 ++++++--
 include/linux/hugetlb.h                         | 19 +++++++++++++++++++
 mm/hugetlb_vmemmap.c                            | 24 ++++++++++++++++++++++++
 5 files changed, 72 insertions(+), 7 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 5adf1e57e932..7db2591f3ad3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1577,6 +1577,20 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
+	hugetlb_free_vmemmap=
+			[KNL] When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set,
+			this controls freeing unused vmemmap pages associated
+			with each HugeTLB page. When this option is enabled,
+			we disable PMD/huge page mapping of vmemmap pages which
+			increase page table pages. So if a user/sysadmin only
+			uses a small number of HugeTLB pages (as a percentage
+			of system memory), they could end up using more memory
+			with hugetlb_free_vmemmap on as opposed to off.
+			Format: { on | off (default) }
+
+			on:  enable the feature
+			off: disable 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 fb8f649e5635..3bf494c01da4 100644
--- a/Documentation/admin-guide/mm/hugetlbpage.rst
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -60,8 +60,8 @@ HugePages_Surp
         the pool above the value in ``/proc/sys/vm/nr_hugepages``. The
         maximum number of surplus huge pages is controlled by
         ``/proc/sys/vm/nr_overcommit_hugepages``.
-	Note: When the feature of freeing unused vmemmap pages associated
-	with each hugetlb page is enabled, the number of the surplus huge
+	Note: When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP and the kernel parameter
+	of ``hugetlb_free_vmemmap=on`` are set, the number of the surplus huge
 	pages may be temporarily larger than the maximum number of surplus
 	huge pages when the system is under memory pressure.
 Hugepagesize
@@ -84,9 +84,10 @@ returned to the huge page pool when freed by a task.  A user with root
 privileges can dynamically allocate more or free some persistent huge pages
 by increasing or decreasing the value of ``nr_hugepages``.
 
-Note: When the feature of freeing unused vmemmap pages associated with each
-hugetlb page is enabled, we can failed to free the huge pages triggered by
-the user when ths system is under memory pressure.  Please try again later.
+Note: When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP and the kernel parameter of
+``hugetlb_free_vmemmap=on`` are set, we can failed to free the huge pages
+triggered by the user when ths system is under memory pressure.  Please
+try again later.
 
 Pages that are used as huge pages are reserved inside the kernel and cannot
 be used for other purposes.  Huge pages cannot be swapped out under
@@ -153,6 +154,9 @@ 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 enables freeing
+	unused vmemmap pages associated with 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/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0435bee2e172..39f88c5faadc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,6 +34,7 @@
 #include <linux/gfp.h>
 #include <linux/kcore.h>
 #include <linux/bootmem_info.h>
+#include <linux/hugetlb.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
@@ -1557,7 +1558,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	int err;
 
-	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
+	if ((is_hugetlb_free_vmemmap_enabled()  && !altmap) ||
+	    end - start < PAGES_PER_SECTION * sizeof(struct page))
 		err = vmemmap_populate_basepages(start, end, node, NULL);
 	else if (boot_cpu_has(X86_FEATURE_PSE))
 		err = vmemmap_populate_hugepages(start, end, node, altmap);
@@ -1585,6 +1587,8 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 	pmd_t *pmd;
 	unsigned int nr_pmd_pages;
 	struct page *page;
+	bool base_mapping = !boot_cpu_has(X86_FEATURE_PSE) ||
+			    is_hugetlb_free_vmemmap_enabled();
 
 	for (; addr < end; addr = next) {
 		pte_t *pte = NULL;
@@ -1610,7 +1614,7 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 		}
 		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
 
-		if (!boot_cpu_has(X86_FEATURE_PSE)) {
+		if (base_mapping) {
 			next = (addr + PAGE_SIZE) & PAGE_MASK;
 			pmd = pmd_offset(pud, addr);
 			if (pmd_none(*pmd))
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 37fd248ce271..ad249e56ac49 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -854,6 +854,20 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 
 void set_page_huge_active(struct page *page);
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+extern bool hugetlb_free_vmemmap_enabled;
+
+static inline bool is_hugetlb_free_vmemmap_enabled(void)
+{
+	return hugetlb_free_vmemmap_enabled;
+}
+#else
+static inline bool is_hugetlb_free_vmemmap_enabled(void)
+{
+	return false;
+}
+#endif
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
@@ -1007,6 +1021,11 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 					pte_t *ptep, pte_t pte, unsigned long sz)
 {
 }
+
+static inline bool is_hugetlb_free_vmemmap_enabled(void)
+{
+	return false;
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index f7ab3d99250a..7807ed6678e0 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -169,6 +169,8 @@
  * (last) level. So this type of HugeTLB page can be optimized only when its
  * size of the struct page structs is greater than 2 pages.
  */
+#define pr_fmt(fmt)	"HugeTLB: " fmt
+
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -181,6 +183,28 @@
 #define RESERVE_VMEMMAP_NR		2U
 #define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
 
+bool hugetlb_free_vmemmap_enabled;
+
+static int __init early_hugetlb_free_vmemmap_param(char *buf)
+{
+	/* We cannot optimize if a "struct page" crosses page boundaries. */
+	if ((!is_power_of_2(sizeof(struct page)))) {
+		pr_warn("cannot free vmemmap pages because \"struct page\" crosses page boundaries\n");
+		return 0;
+	}
+
+	if (!buf)
+		return -EINVAL;
+
+	if (!strcmp(buf, "on"))
+		hugetlb_free_vmemmap_enabled = true;
+	else if (strcmp(buf, "off"))
+		return -EINVAL;
+
+	return 0;
+}
+early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param);
+
 static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h)
 {
 	return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
-- 
2.11.0