From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: stable@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	patches@lists.linux.dev,
	Lance Yang <lance.yang@linux.dev>,
	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
	Nico Pache <npache@redhat.com>,
	Dev Jain <dev.jain@arm.com>,
	Baolin Wang <baolin.wang@linux.alibaba.com>,
	Wei Yang <richard.weiyang@gmail.com>,
	David Hildenbrand <david@redhat.com>,
	Liam Howlett <liam.howlett@oracle.com>,
	Ryan Roberts <ryan.roberts@arm.com>,
	Zi Yan <ziy@nvidia.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Sasha Levin <sashal@kernel.org>
Subject: [PATCH 6.12 120/220] mm/khugepaged: guard is_zero_pfn() calls with pte_present()
Date: Thu, 20 Aug 2026 16:55:10 +0200
Message-ID: <20260820145227.082686941@linuxfoundation.org>
In-Reply-To: <20260820145223.480031205@linuxfoundation.org>
References: <20260820145223.480031205@linuxfoundation.org>
User-Agent: quilt/0.69
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

6.12-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lance Yang <lance.yang@linux.dev>

[ Upstream commit 074f027d15c10cb376b3ad88405b8e512fa5b3a8 ]

A non-present entry, like a swap PTE, contains completely different data
(swap type and offset).  pte_pfn() doesn't know this, so if we feed it a
non-present entry, it will spit out a junk PFN.

What if that junk PFN happens to match the zeropage's PFN by sheer chance?
While really unlikely, this would be really bad if it did.

So, let's fix this potential bug by ensuring all calls to is_zero_pfn() in
khugepaged.c are properly guarded by a pte_present() check.

Link: https://lkml.kernel.org/r/20251020151111.53561-1-lance.yang@linux.dev
Signed-off-by: Lance Yang <lance.yang@linux.dev>
Suggested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Nico Pache <npache@redhat.com>
Reviewed-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stable-dep-of: 3c58f641e813 ("userfaultfd: prevent registration of special VMAs")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 mm/khugepaged.c |   35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -346,6 +346,13 @@ struct attribute_group khugepaged_attr_g
 };
 #endif /* CONFIG_SYSFS */
 
+static bool pte_none_or_zero(pte_t pte)
+{
+	if (pte_none(pte))
+		return true;
+	return pte_present(pte) && is_zero_pfn(pte_pfn(pte));
+}
+
 int hugepage_madvise(struct vm_area_struct *vma,
 		     unsigned long *vm_flags, int advice)
 {
@@ -529,6 +536,7 @@ static void release_pte_pages(pte_t *pte
 
 		if (pte_none(pteval))
 			continue;
+		VM_WARN_ON_ONCE(!pte_present(pteval));
 		pfn = pte_pfn(pteval);
 		if (is_zero_pfn(pfn))
 			continue;
@@ -572,8 +580,7 @@ static int __collapse_huge_page_isolate(
 	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, address += PAGE_SIZE) {
 		pte_t pteval = ptep_get(_pte);
-		if (pte_none(pteval) || (pte_present(pteval) &&
-				is_zero_pfn(pte_pfn(pteval)))) {
+		if (pte_none_or_zero(pteval)) {
 			++none_or_zero;
 			if (!userfaultfd_armed(vma) &&
 			    (!cc->is_khugepaged ||
@@ -716,17 +723,17 @@ static void __collapse_huge_page_copy_su
 	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, address += PAGE_SIZE) {
 		pteval = ptep_get(_pte);
-		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
+		if (pte_none_or_zero(pteval)) {
 			add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
-			if (is_zero_pfn(pte_pfn(pteval))) {
-				/*
-				 * ptl mostly unnecessary.
-				 */
-				spin_lock(ptl);
-				ptep_clear(vma->vm_mm, address, _pte);
-				spin_unlock(ptl);
-				ksm_might_unmap_zero_page(vma->vm_mm, pteval);
-			}
+			if (pte_none(pteval))
+				continue;
+			/*
+			 * ptl mostly unnecessary.
+			 */
+			spin_lock(ptl);
+			ptep_clear(vma->vm_mm, address, _pte);
+			spin_unlock(ptl);
+			ksm_might_unmap_zero_page(vma->vm_mm, pteval);
 		} else {
 			struct page *src_page = pte_page(pteval);
 
@@ -812,7 +819,7 @@ static int __collapse_huge_page_copy(pte
 		unsigned long src_addr = address + i * PAGE_SIZE;
 		struct page *src_page;
 
-		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
+		if (pte_none_or_zero(pteval)) {
 			clear_user_highpage(page, src_addr);
 			continue;
 		}
@@ -1305,7 +1312,7 @@ static int hpage_collapse_scan_pmd(struc
 				goto out_unmap;
 			}
 		}
-		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
+		if (pte_none_or_zero(pteval)) {
 			++none_or_zero;
 			if (!userfaultfd_armed(vma) &&
 			    (!cc->is_khugepaged ||