From e9fdff87e893ec5b7c32836675db80cf691b2a8b Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Wed, 30 Jun 2021 18:47:25 -0700
Subject: 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/20210510030027.56044-8-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Barry Song <song.bao.hua@hisilicon.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Tested-by: Chen Huang <chenhuang5@huawei.com>
Tested-by: Bodeddula Balasubramaniam <bodeddub@amazon.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: HORIGUCHI NAOYA <naoya.horiguchi@nec.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Neukum <oneukum@suse.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/init_64.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'arch')

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 65ea58527176..9d9d18d0c2a1 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>
@@ -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))
-- 
cgit v1.2.3