FAILED: patch "[PATCH] mm: fix address wraparound when scanning large folio PTEs" failed to apply to 6.18-stable tree

FAILED: patch "[PATCH] mm: fix address wraparound when scanning large folio PTEs" failed to apply to 6.18-stable tree

[Sasha Levin]

The patch below does not apply to the 6.18-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.18.y
git checkout FETCH_HEAD
git cherry-pick -x f681d4580d5c3c749f623cda722a21aefd3147b3
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '20261109200351-failed-6.18-f681d4580d5c@kernel.org' --subject-prefix 'PATCH 6.18.y' 'HEAD^..'

Thanks,
Sasha

------------------ original commit in Linus's tree ------------------

From f681d4580d5c3c749f623cda722a21aefd3147b3 Mon Sep 17 00:00:00 2001
From: "David Hildenbrand (Arm)" <david@kernel.org>
Date: Wed, 14 Oct 2026 20:34:28 +0200
Subject: [PATCH] mm: fix address wraparound when scanning large folio PTEs

numa_rebuild_large_mapping() and do_swap_page() can be tricked into
generating an address wraparound, crashing the kernel. All that's required
is to map a tail page of a large folio close enough to the start/end of
the address space to e.g., make

	unsigned long addr_start = addr - (nr << PAGE_SHIFT);

to wrap around.

Let's fix it by providing a better helper, folio_scan_range(), that
takes care of staying within VMA and page table boundaries while
handling possible wraparounds.

There are some nasty details, like not being able to use pmd_addr_end()
in this context. Add some helpful comments for these cases.

Link: https://lore.kernel.org/20261014-folio_pte_scan_range-v2-1-00cf9bbaa364@kernel.org
Fixes: d2136d749d76 ("mm: support multi-size THP numa balancing")
Fixes: 508758960b8d ("mm: swap: entirely map large folios found in swapcache")
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reported-by: Kyle Zeng <kylebot@openai.com>
Reviewed-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Barry Song <baohua@kernel.org>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Ying Huang <huang.ying.caritas@gmail.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Chuanhua Han <hanchuanhua@oppo.com>
Cc: <stable@vger.kernel.org>
---
 mm/memory.c | 50 ++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 36 insertions(+), 14 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 0fb676dd2bd63..591592bc5a941 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4933,6 +4933,34 @@ static void check_swap_exclusive(struct folio *folio, swp_entry_t entry,
 	} while (--nr_pages);
 }
 
+/*
+ * Get the address range in which a folio might be mapped, assuming its pages
+ * are mapped consecutively and the folio page at the given idx is mapped at
+ * the given address.
+ */
+static void folio_pte_range(const struct folio *folio,
+		const struct vm_area_struct *vma, unsigned long addr,
+		unsigned long idx, unsigned long *start, unsigned long *end)
+{
+	/* Stay within the page table and VMA boundaries. */
+	const unsigned long pmd_start = addr & PMD_MASK;
+	const unsigned long pmd_end = pmd_start + PMD_SIZE;
+	const unsigned long lower = max(pmd_start, vma->vm_start);
+	/*
+	 * We cannot use pmd_addr_end(), as it does not clamp reliably. To
+	 * avoid wraparounds, compute using the inclusive end.
+	 */
+	const unsigned long upper = min(pmd_end - 1, vma->vm_end - 1) + 1;
+	const unsigned long offset = idx << PAGE_SHIFT;
+
+	/*
+	 * Avoid start/end addresses wrapping by not adding/subtracting more
+	 * than the lower/upper limits would allow.
+	 */
+	*start = addr - min(addr - lower, offset);
+	*end = addr + min(upper - addr, folio_size(folio) - offset);
+}
+
 /*
  * We enter with either the VMA lock or the mmap_lock held (see
  * FAULT_FLAG_VMA_LOCK), and pte mapped but not yet locked.
@@ -5121,16 +5149,15 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	address = vmf->address;
 	ptep = vmf->pte;
 	if (folio_test_large(folio) && folio_test_swapcache(folio)) {
-		int nr = folio_nr_pages(folio);
-		unsigned long idx = folio_page_idx(folio, page);
-		unsigned long folio_start = address - idx * PAGE_SIZE;
-		unsigned long folio_end = folio_start + nr * PAGE_SIZE;
+		const int nr = folio_nr_pages(folio);
+		const unsigned long idx = folio_page_idx(folio, page);
+		unsigned long folio_start, folio_end;
 		pte_t *folio_ptep;
 		pte_t folio_pte;
 
-		if (unlikely(folio_start < max(address & PMD_MASK, vma->vm_start)))
-			goto check_folio;
-		if (unlikely(folio_end > pmd_addr_end(address, vma->vm_end)))
+		folio_pte_range(folio, vma, address, idx, &folio_start,
+				&folio_end);
+		if (unlikely((folio_end - folio_start) >> PAGE_SHIFT != nr))
 			goto check_folio;
 
 		folio_ptep = vmf->pte - idx;
@@ -6280,16 +6307,11 @@ static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_stru
 				       struct folio *folio, pte_t fault_pte,
 				       bool ignore_writable, bool pte_write_upgrade)
 {
-	int nr = pte_pfn(fault_pte) - folio_pfn(folio);
+	const unsigned long idx = pte_pfn(fault_pte) - folio_pfn(folio);
 	unsigned long start, end, addr = vmf->address;
-	unsigned long addr_start = addr - (nr << PAGE_SHIFT);
-	unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE);
 	pte_t *start_ptep;
 
-	/* Stay within the VMA and within the page table. */
-	start = max3(addr_start, pt_start, vma->vm_start);
-	end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE,
-		   vma->vm_end);
+	folio_pte_range(folio, vma, addr, idx, &start, &end);
 	start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT);
 
 	/* Restore all PTEs' mapping of the large folio */
-- 
2.53.0

[PATCH 6.18.y 1/2] mm/memory: update stale locking comments for fault handlers

[Sasha Levin]

From: Aditya Sharma <adi.sharma@zohomail.in>

[ Upstream commit 214f9ab72ce6e16120c20ad670389656f059e685 ]

Update the comments for wp_page_copy(), do_wp_page(), do_swap_page(),
do_anonymous_page(), __do_fault(), do_fault(), handle_pte_fault(),
__handle_mm_fault(), and handle_mm_fault() to concisely clarify that they
can be entered holding either the mmap_lock or the VMA lock, and that the
lock may be released upon returning VM_FAULT_RETRY.

Additionally, make the following corrections:
- In do_anonymous_page(), correct the outdated claim that the function
  is entered with the PTE "mapped but not yet locked". Since
  handle_pte_fault() unmaps the empty PTE before routing to
  do_pte_missing(), the comment now correctly states it is entered
  with the PTE unmapped and unlocked.
- In __do_fault(), update the stale reference from __lock_page_retry()
  to __folio_lock_or_retry().

Link: https://lore.kernel.org/20260424092217.263648-1-adi.sharma@zohomail.in
Signed-off-by: Aditya Sharma <adi.sharma@zohomail.in>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Liam Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stable-dep-of: f681d4580d5c ("mm: fix address wraparound when scanning large folio PTEs")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 mm/memory.c | 55 ++++++++++++++++++++++++++++-------------------------
 1 file changed, 29 insertions(+), 26 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index e37ae367c8c19..c9597d7f8ba0a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3673,8 +3673,8 @@ vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf)
  * Handle the case of a page which we actually need to copy to a new page,
  * either due to COW or unsharing.
  *
- * Called with mmap_lock locked and the old page referenced, but
- * without the ptl held.
+ * Called with either the VMA lock or the mmap_lock held (see FAULT_FLAG_VMA_LOCK)
+ * and the old page referenced, but without the ptl held.
  *
  * High level logic flow:
  *
@@ -4075,9 +4075,9 @@ static bool wp_can_reuse_anon_folio(struct folio *folio,
  * though the page will change only once the write actually happens. This
  * avoids a few races, and potentially makes it more efficient.
  *
- * We enter with non-exclusive mmap_lock (to exclude vma changes,
- * but allow concurrent faults), with pte both mapped and locked.
- * We return with mmap_lock still held, but pte unmapped and unlocked.
+ * We enter with either the VMA lock or the mmap_lock held (see
+ * FAULT_FLAG_VMA_LOCK) and pte both mapped and locked. We return with
+ * the same lock still held, but pte unmapped and unlocked.
  */
 static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	__releases(vmf->ptl)
@@ -4605,12 +4605,12 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf)
 static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq);
 
 /*
- * We enter with non-exclusive mmap_lock (to exclude vma changes,
- * but allow concurrent faults), and pte mapped but not yet locked.
+ * We enter with either the VMA lock or the mmap_lock held (see
+ * FAULT_FLAG_VMA_LOCK), and pte mapped but not yet locked.
  * We return with pte unmapped and unlocked.
  *
- * We return with the mmap_lock locked or unlocked in the same cases
- * as does filemap_fault().
+ * When returning, the lock may have been released in the same cases
+ * as done by filemap_fault().
  */
 vm_fault_t do_swap_page(struct vm_fault *vmf)
 {
@@ -5161,9 +5161,10 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 }
 
 /*
- * We enter with non-exclusive mmap_lock (to exclude vma changes,
- * but allow concurrent faults), and pte mapped but not yet locked.
- * We return with mmap_lock still held, but pte unmapped and unlocked.
+ * We enter with either the VMA lock or the mmap_lock held (see
+ * FAULT_FLAG_VMA_LOCK), and pte unmapped and unlocked.
+ * We return with the lock still held, but pte unmapped and unlocked.
+ * If VM_FAULT_RETRY is returned, the lock may have been released.
  */
 static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 {
@@ -5281,9 +5282,10 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 }
 
 /*
- * The mmap_lock must have been held on entry, and may have been
- * released depending on flags and vma->vm_ops->fault() return value.
- * See filemap_fault() and __lock_page_retry().
+ * Either the VMA lock or the mmap_lock must have been held on entry
+ * (see FAULT_FLAG_VMA_LOCK) and may have been released depending on
+ * flags and vma->vm_ops->fault() return value.
+ * See filemap_fault() and __folio_lock_or_retry().
  */
 static vm_fault_t __do_fault(struct vm_fault *vmf)
 {
@@ -5844,11 +5846,11 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
 }
 
 /*
- * We enter with non-exclusive mmap_lock (to exclude vma changes,
- * but allow concurrent faults).
- * The mmap_lock may have been released depending on flags and our
+ * We enter with either the VMA lock or the mmap_lock held (see
+ * FAULT_FLAG_VMA_LOCK).
+ * The lock may have been released depending on flags and our
  * return value.  See filemap_fault() and __folio_lock_or_retry().
- * If mmap_lock is released, vma may become invalid (for example
+ * If the lock is released, vma may become invalid (for example
  * by other thread calling munmap()).
  */
 static vm_fault_t do_fault(struct vm_fault *vmf)
@@ -6176,10 +6178,11 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
  * with external mmu caches can use to update those (ie the Sparc or
  * PowerPC hashed page tables that act as extended TLBs).
  *
- * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow
- * concurrent faults).
+ * On entry, we hold either the VMA lock or the mmap_lock
+ * (see FAULT_FLAG_VMA_LOCK).
  *
- * The mmap_lock may have been released depending on flags and our return value.
+ * The mmap_lock or VMA lock may have been released depending on flags
+ * and our return value.
  * See filemap_fault() and __folio_lock_or_retry().
  */
 static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
@@ -6272,8 +6275,8 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 
 /*
  * On entry, we hold either the VMA lock or the mmap_lock
- * (FAULT_FLAG_VMA_LOCK tells you which).  If VM_FAULT_RETRY is set in
- * the result, the mmap_lock is not held on exit.  See filemap_fault()
+ * (see FAULT_FLAG_VMA_LOCK).  If VM_FAULT_RETRY is set in
+ * the result, the lock is not held on exit.  See filemap_fault()
  * and __folio_lock_or_retry().
  */
 static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
@@ -6501,9 +6504,9 @@ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma,
 
 /*
  * By the time we get here, we already hold either the VMA lock or the
- * mmap_lock (FAULT_FLAG_VMA_LOCK tells you which).
+ * mmap_lock (see FAULT_FLAG_VMA_LOCK).
  *
- * The mmap_lock may have been released depending on flags and our
+ * The lock may have been released depending on flags and our
  * return value.  See filemap_fault() and __folio_lock_or_retry().
  */
 vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
-- 
2.53.0

[PATCH 6.18.y 2/2] mm: fix address wraparound when scanning large folio PTEs

[Sasha Levin]

From: "David Hildenbrand (Arm)" <david@kernel.org>

[ Upstream commit f681d4580d5c3c749f623cda722a21aefd3147b3 ]

numa_rebuild_large_mapping() and do_swap_page() can be tricked into
generating an address wraparound, crashing the kernel. All that's required
is to map a tail page of a large folio close enough to the start/end of
the address space to e.g., make

	unsigned long addr_start = addr - (nr << PAGE_SHIFT);

to wrap around.

Let's fix it by providing a better helper, folio_scan_range(), that
takes care of staying within VMA and page table boundaries while
handling possible wraparounds.

There are some nasty details, like not being able to use pmd_addr_end()
in this context. Add some helpful comments for these cases.

Link: https://lore.kernel.org/20261014-folio_pte_scan_range-v2-1-00cf9bbaa364@kernel.org
Fixes: d2136d749d76 ("mm: support multi-size THP numa balancing")
Fixes: 508758960b8d ("mm: swap: entirely map large folios found in swapcache")
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reported-by: Kyle Zeng <kylebot@openai.com>
Reviewed-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Barry Song <baohua@kernel.org>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Ying Huang <huang.ying.caritas@gmail.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Chuanhua Han <hanchuanhua@oppo.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 mm/memory.c | 50 ++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 36 insertions(+), 14 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index c9597d7f8ba0a..e8a5292c5a317 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4604,6 +4604,34 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf)
 
 static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq);
 
+/*
+ * Get the address range in which a folio might be mapped, assuming its pages
+ * are mapped consecutively and the folio page at the given idx is mapped at
+ * the given address.
+ */
+static void folio_pte_range(const struct folio *folio,
+		const struct vm_area_struct *vma, unsigned long addr,
+		unsigned long idx, unsigned long *start, unsigned long *end)
+{
+	/* Stay within the page table and VMA boundaries. */
+	const unsigned long pmd_start = addr & PMD_MASK;
+	const unsigned long pmd_end = pmd_start + PMD_SIZE;
+	const unsigned long lower = max(pmd_start, vma->vm_start);
+	/*
+	 * We cannot use pmd_addr_end(), as it does not clamp reliably. To
+	 * avoid wraparounds, compute using the inclusive end.
+	 */
+	const unsigned long upper = min(pmd_end - 1, vma->vm_end - 1) + 1;
+	const unsigned long offset = idx << PAGE_SHIFT;
+
+	/*
+	 * Avoid start/end addresses wrapping by not adding/subtracting more
+	 * than the lower/upper limits would allow.
+	 */
+	*start = addr - min(addr - lower, offset);
+	*end = addr + min(upper - addr, folio_size(folio) - offset);
+}
+
 /*
  * We enter with either the VMA lock or the mmap_lock held (see
  * FAULT_FLAG_VMA_LOCK), and pte mapped but not yet locked.
@@ -4861,16 +4889,15 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	address = vmf->address;
 	ptep = vmf->pte;
 	if (folio_test_large(folio) && folio_test_swapcache(folio)) {
-		int nr = folio_nr_pages(folio);
-		unsigned long idx = folio_page_idx(folio, page);
-		unsigned long folio_start = address - idx * PAGE_SIZE;
-		unsigned long folio_end = folio_start + nr * PAGE_SIZE;
+		const int nr = folio_nr_pages(folio);
+		const unsigned long idx = folio_page_idx(folio, page);
+		unsigned long folio_start, folio_end;
 		pte_t *folio_ptep;
 		pte_t folio_pte;
 
-		if (unlikely(folio_start < max(address & PMD_MASK, vma->vm_start)))
-			goto check_folio;
-		if (unlikely(folio_end > pmd_addr_end(address, vma->vm_end)))
+		folio_pte_range(folio, vma, address, idx, &folio_start,
+				&folio_end);
+		if (unlikely((folio_end - folio_start) >> PAGE_SHIFT != nr))
 			goto check_folio;
 
 		folio_ptep = vmf->pte - idx;
@@ -5963,16 +5990,11 @@ static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_stru
 				       struct folio *folio, pte_t fault_pte,
 				       bool ignore_writable, bool pte_write_upgrade)
 {
-	int nr = pte_pfn(fault_pte) - folio_pfn(folio);
+	const unsigned long idx = pte_pfn(fault_pte) - folio_pfn(folio);
 	unsigned long start, end, addr = vmf->address;
-	unsigned long addr_start = addr - (nr << PAGE_SHIFT);
-	unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE);
 	pte_t *start_ptep;
 
-	/* Stay within the VMA and within the page table. */
-	start = max3(addr_start, pt_start, vma->vm_start);
-	end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE,
-		   vma->vm_end);
+	folio_pte_range(folio, vma, addr, idx, &start, &end);
 	start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT);
 
 	/* Restore all PTEs' mapping of the large folio */
-- 
2.53.0