[PATCH v8 09/12] 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>
---
 Documentation/admin-guide/kernel-parameters.txt |  9 +++++++++
 Documentation/admin-guide/mm/hugetlbpage.rst    |  3 +++
 arch/x86/mm/init_64.c                           |  8 ++++++--
 include/linux/hugetlb.h                         | 19 +++++++++++++++++++
 mm/hugetlb_vmemmap.c                            | 16 ++++++++++++++++
 5 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 3ae25630a223..9e6854f21d55 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 controls freeing unused vmemmap pages associated
+			with each HugeTLB page.
+			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 f7b1c7462991..6a8b57f6d3b7 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 enables 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/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0435bee2e172..fcdc020904a8 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 +1558,9 @@ 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())
+		err = vmemmap_populate_basepages(start, end, node, NULL);
+	else if (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);
@@ -1610,7 +1613,8 @@ 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 (!boot_cpu_has(X86_FEATURE_PSE) ||
+		    is_hugetlb_free_vmemmap_enabled()) {
 			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 ebca2ef02212..7f47f0eeca3b 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -770,6 +770,20 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 }
 #endif
 
+#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 {};
 
@@ -923,6 +937,11 @@ 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 4587a0062808..f0926b382338 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -204,6 +204,22 @@ typedef void (*vmemmap_remap_pte_func_t)(struct page *reuse, pte_t *pte,
 					 unsigned long start, unsigned long end,
 					 void *priv);
 
+bool hugetlb_free_vmemmap_enabled;
+
+static int __init early_hugetlb_free_vmemmap_param(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	/* We cannot optimize if a "struct page" crosses page boundaries. */
+	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 int vmemmap_pages_per_hpage(struct hstate *h)
 {
-- 
2.11.0