1 files changed, 40 insertions, 22 deletions

diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index 589bcf878938..b929a455103f 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -26,6 +26,26 @@ static inline pte_t *contpte_align_down(pte_t *ptep)
 	return PTR_ALIGN_DOWN(ptep, sizeof(*ptep) * CONT_PTES);
 }
 
+static inline pte_t *contpte_align_addr_ptep(unsigned long *start,
+					     unsigned long *end, pte_t *ptep,
+					     unsigned int nr)
+{
+	/*
+	 * Note: caller must ensure these nr PTEs are consecutive (present)
+	 * PTEs that map consecutive pages of the same large folio within a
+	 * single VMA and a single page table.
+	 */
+	if (pte_cont(__ptep_get(ptep + nr - 1)))
+		*end = ALIGN(*end, CONT_PTE_SIZE);
+
+	if (pte_cont(__ptep_get(ptep))) {
+		*start = ALIGN_DOWN(*start, CONT_PTE_SIZE);
+		ptep = contpte_align_down(ptep);
+	}
+
+	return ptep;
+}
+
 static void contpte_try_unfold_partial(struct mm_struct *mm, unsigned long addr,
 					pte_t *ptep, unsigned int nr)
 {
@@ -488,8 +508,9 @@ pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes);
 
-int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
-					unsigned long addr, pte_t *ptep)
+int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
+					unsigned long addr, pte_t *ptep,
+					unsigned int nr)
 {
 	/*
 	 * ptep_clear_flush_young() technically requires us to clear the access
@@ -498,41 +519,45 @@ int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
 	 * contig range when the range is covered by a single folio, we can get
 	 * away with clearing young for the whole contig range here, so we avoid
 	 * having to unfold.
+	 *
+	 * The 'nr' means consecutive (present) PTEs that map consecutive pages
+	 * of the same large folio in a single VMA and a single page table.
 	 */
 
+	unsigned long end = addr + nr * PAGE_SIZE;
 	int young = 0;
-	int i;
-
-	ptep = contpte_align_down(ptep);
-	addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
 
-	for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
+	ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr);
+	for (; addr != end; ptep++, addr += PAGE_SIZE)
 		young |= __ptep_test_and_clear_young(vma, addr, ptep);
 
 	return young;
 }
-EXPORT_SYMBOL_GPL(contpte_ptep_test_and_clear_young);
+EXPORT_SYMBOL_GPL(contpte_test_and_clear_young_ptes);
 
-int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
-					unsigned long addr, pte_t *ptep)
+int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep,
+				unsigned int nr)
 {
 	int young;
 
-	young = contpte_ptep_test_and_clear_young(vma, addr, ptep);
+	young = contpte_test_and_clear_young_ptes(vma, addr, ptep, nr);
 
 	if (young) {
+		unsigned long end = addr + nr * PAGE_SIZE;
+
+		contpte_align_addr_ptep(&addr, &end, ptep, nr);
 		/*
 		 * See comment in __ptep_clear_flush_young(); same rationale for
 		 * eliding the trailing DSB applies here.
 		 */
-		addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
-		__flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE,
+		__flush_tlb_range_nosync(vma->vm_mm, addr, end,
 					 PAGE_SIZE, true, 3);
 	}
 
 	return young;
 }
-EXPORT_SYMBOL_GPL(contpte_ptep_clear_flush_young);
+EXPORT_SYMBOL_GPL(contpte_clear_flush_young_ptes);
 
 void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
 					pte_t *ptep, unsigned int nr)
@@ -569,14 +594,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
 	unsigned long start = addr;
 	unsigned long end = start + nr * PAGE_SIZE;
 
-	if (pte_cont(__ptep_get(ptep + nr - 1)))
-		end = ALIGN(end, CONT_PTE_SIZE);
-
-	if (pte_cont(__ptep_get(ptep))) {
-		start = ALIGN_DOWN(start, CONT_PTE_SIZE);
-		ptep = contpte_align_down(ptep);
-	}
-
+	ptep = contpte_align_addr_ptep(&start, &end, ptep, nr);
 	__clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags);
 }
 EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes);