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

[Sasha Levin <sashal@kernel.org>]

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