[PATCH 1/3] mm/userfaultfd: fix PTE table overruns in UFFDIO_MOVE

From: David Hildenbrand (Arm)

Date: Wed Nov 11 2026 - 17:11:12 EST


With a folded PMD, pmd_addr_end() simply returns the supplied end.
move_present_ptes() can therefore walk past the source or destination
PTE table during UFFDIO_MOVE.

pmd_addr_end() is only intended for page table traversal, in patterns
like "next = pmd_addr_end(addr, end);". With folded PMDs, a higher level
has already clamped the range to the PTE table.

Folded PMDs are uncommon, but can occur even on arm64, for example
with 64K pages and a 42-bit virtual address space.

Extract the calculation from folio_pte_range() into
pte_table_clamped_end() and use it to clamp both ranges. This preserves
the wraparound handling from commit f681d4580d5c ("mm: fix address
wraparound when scanning large folio PTEs").

Fixes: 50944692052b ("userfaultfd: opportunistic TLB-flush batching for present pages in MOVE")
Cc: stable@xxxxxxxxxxxxxxx
Reported-by: Chris Mason <mason@xxxxxxxxxx>
Signed-off-by: David Hildenbrand (Arm) <david@xxxxxxxxxx>
---
include/linux/pgtable.h | 24 ++++++++++++++++++++++++
mm/memory.c | 7 +------
mm/userfaultfd.c | 4 ++--
3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 780fe849ff8b7..66d369870a740 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -12,6 +12,7 @@
#ifdef CONFIG_MMU

#include <linux/mm_types.h>
+#include <linux/minmax.h>
#include <linux/bug.h>
#include <linux/errno.h>
#include <asm-generic/pgtable_uffd.h>
@@ -1518,6 +1519,29 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
})
#endif

+/**
+ * pte_table_clamped_end() - Limit a range to a single PTE table.
+ * @addr: Start address.
+ * @end: Exclusive end address.
+ *
+ * Only use pmd_addr_end() when traversing page tables, in a pattern like::
+ *
+ * next = pmd_addr_end(addr, end);
+ *
+ * Higher levels already bound the range when PMDs are folded. Use this
+ * helper elsewhere to clamp the range regardless of PMD folding.
+ *
+ * Return: The exclusive end of the PTE table containing @addr, capped at @end.
+ */
+static inline unsigned long pte_table_clamped_end(unsigned long addr,
+ unsigned long end)
+{
+ const unsigned long pmd_end = (addr & PMD_MASK) + PMD_SIZE;
+
+ /* Compare inclusive ends to avoid wraparounds. */
+ return min(pmd_end - 1, end - 1) + 1;
+}
+
/*
* When walking page tables, we usually want to skip any p?d_none entries;
* and any p?d_bad entries - reporting the error before resetting to none.
diff --git a/mm/memory.c b/mm/memory.c
index ec3d9d99ccee2..ee792a2c0ccea 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4959,13 +4959,8 @@ static void folio_pte_range(const struct folio *folio,
{
/* 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 upper = pte_table_clamped_end(addr, vma->vm_end);
const unsigned long offset = idx << PAGE_SHIFT;

/*
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 169f681f9849b..57650e6f040d1 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1266,8 +1266,8 @@ static long move_present_ptes(struct mm_struct *mm,
unsigned long src_start = src_addr;
unsigned long src_end;

- len = pmd_addr_end(dst_addr, dst_addr + len) - dst_addr;
- src_end = pmd_addr_end(src_addr, src_addr + len);
+ len = pte_table_clamped_end(dst_addr, dst_addr + len) - dst_addr;
+ src_end = pte_table_clamped_end(src_addr, src_addr + len);
flush_cache_range(src_vma, src_addr, src_end);
double_pt_lock(dst_ptl, src_ptl);


--
2.43.0