mm: hugetlb: add a kernel parameter hugetlb_free_vmemmap

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

We disable 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.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Muchun Song <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
Reviewed-by: Barry Song <[email protected]>
Reviewed-by: Miaohe Lin <[email protected]>
Tested-by: Chen Huang <[email protected]>
Tested-by: Bodeddula Balasubramaniam <[email protected]>
Reviewed-by: Mike Kravetz <[email protected]>
Cc: Alexander Viro <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Anshuman Khandual <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: HORIGUCHI NAOYA <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Joao Martins <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mina Almasry <[email protected]>
Cc: Oliver Neukum <[email protected]>
Cc: Paul E. McKenney <[email protected]>
Cc: Pawan Gupta <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Xiongchun Duan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Documentation/admin-guide/kernel-parameters.txt

@@ -1567,6 +1567,23 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
+	hugetlb_free_vmemmap=
+			[KNL] Reguires CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+			enabled.
+			Allows heavy hugetlb users to free up some more
+			memory (6 * PAGE_SIZE for each 2MB hugetlb page).
+			This feauture is not free though. Large page
+			tables are not used to back vmemmap pages which
+			can lead to a performance degradation for some
+			workloads. Also there will be memory allocation
+			required when hugetlb pages are freed from the
+			pool which can lead to corner cases under heavy
+			memory pressure.
+			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

Documentation/admin-guide/mm/hugetlbpage.rst

@@ -153,6 +153,9 @@ 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.

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>
@@ -1609,7 +1610,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
 	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));
 
-	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);
@@ -1637,6 +1639,8 @@ 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;
@@ -1662,7 +1666,7 @@ 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))

include/linux/hugetlb.h

@@ -892,6 +892,20 @@ 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 {};
 
@@ -1046,6 +1060,11 @@ 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,

mm/hugetlb_vmemmap.c

@@ -168,6 +168,8 @@
  * (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"
 
 /*
@@ -180,6 +182,28 @@
 #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;