[PATCH v14 5/8] mm: hugetlb: add a kernel parameter hugetlb_free_vmemmap

@@ -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

@@ -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 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.

@@ -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))

@@ -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,

@@ -183,6 +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);
+
 /*
  * How many vmemmap pages associated with a HugeTLB page that can be freed
  * to the buddy allocator.