linux-kernel - [PATCH v2 04/17] khugepaged: Generalize __collapse_huge_page

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250211111326.14295-5-dev.jain@arm.com>
Date: Tue, 11 Feb 2025 16:43:13 +0530
From: Dev Jain <dev.jain@....com>
To: akpm@...ux-foundation.org,
	david@...hat.com,
	willy@...radead.org,
	kirill.shutemov@...ux.intel.com
Cc: npache@...hat.com,
	ryan.roberts@....com,
	anshuman.khandual@....com,
	catalin.marinas@....com,
	cl@...two.org,
	vbabka@...e.cz,
	mhocko@...e.com,
	apopple@...dia.com,
	dave.hansen@...ux.intel.com,
	will@...nel.org,
	baohua@...nel.org,
	jack@...e.cz,
	srivatsa@...il.mit.edu,
	haowenchao22@...il.com,
	hughd@...gle.com,
	aneesh.kumar@...nel.org,
	yang@...amperecomputing.com,
	peterx@...hat.com,
	ioworker0@...il.com,
	wangkefeng.wang@...wei.com,
	ziy@...dia.com,
	jglisse@...gle.com,
	surenb@...gle.com,
	vishal.moola@...il.com,
	zokeefe@...gle.com,
	zhengqi.arch@...edance.com,
	jhubbard@...dia.com,
	21cnbao@...il.com,
	linux-mm@...ck.org,
	linux-kernel@...r.kernel.org,
	Dev Jain <dev.jain@....com>
Subject: [PATCH v2 04/17] khugepaged: Generalize __collapse_huge_page_isolate()

Scale down the scan range and the sysfs tunables (to be changed in subsequent patches)
according to the scan order, and isolate the folios.

Signed-off-by: Dev Jain <dev.jain@....com>
---
 mm/khugepaged.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 221823c0d95f..0ea99df115cb 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -565,15 +565,17 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 					unsigned long address,
 					pte_t *pte,
 					struct collapse_control *cc,
-					struct list_head *compound_pagelist)
+					struct list_head *compound_pagelist,
+					int order)
 {
-	struct page *page = NULL;
 	struct folio *folio = NULL;
 	pte_t *_pte;
 	int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0;
 	bool writable = false;
+	unsigned int max_ptes_shared = khugepaged_max_ptes_shared >> (HPAGE_PMD_ORDER - order);
+	unsigned int max_ptes_none = khugepaged_max_ptes_none >> (HPAGE_PMD_ORDER - order);
 
-	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
+	for (_pte = pte; _pte < pte + (1UL << order);
 	     _pte++, address += PAGE_SIZE) {
 		pte_t pteval = ptep_get(_pte);
 		if (pte_none(pteval) || (pte_present(pteval) &&
@@ -581,7 +583,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			++none_or_zero;
 			if (!userfaultfd_armed(vma) &&
 			    (!cc->is_khugepaged ||
-			     none_or_zero <= khugepaged_max_ptes_none)) {
+			     none_or_zero <= max_ptes_none)) {
 				continue;
 			} else {
 				result = SCAN_EXCEED_NONE_PTE;
@@ -597,20 +599,19 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			result = SCAN_PTE_UFFD_WP;
 			goto out;
 		}
-		page = vm_normal_page(vma, address, pteval);
-		if (unlikely(!page) || unlikely(is_zone_device_page(page))) {
+		folio = vm_normal_folio(vma, address, pteval);
+		if (unlikely(!folio) || unlikely(folio_is_zone_device(folio))) {
 			result = SCAN_PAGE_NULL;
 			goto out;
 		}
 
-		folio = page_folio(page);
 		VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio);
 
 		/* See hpage_collapse_scan_pmd(). */
 		if (folio_likely_mapped_shared(folio)) {
 			++shared;
 			if (cc->is_khugepaged &&
-			    shared > khugepaged_max_ptes_shared) {
+			    shared > max_ptes_shared) {
 				result = SCAN_EXCEED_SHARED_PTE;
 				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
 				goto out;
@@ -1201,7 +1202,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
 	if (pte) {
 		result = __collapse_huge_page_isolate(vma, address, pte, cc,
-						      &compound_pagelist);
+						      &compound_pagelist, HPAGE_PMD_ORDER);
 		spin_unlock(pte_ptl);
 	} else {
 		result = SCAN_PMD_NULL;
-- 
2.30.2