[PATCH v4 1/2] mm/madvise: introduce mkold_clean_ptes() batch helper

[Lance Yang]

Change the code that clears young and dirty bits from the PTEs to use
ptep_get_and_clear_full() and set_pte_at(), via the new mkold_clean_ptes()
batch helper function.

Unfortunately, the per-pte get_and_clear/modify/set approach would result
in unfolding/refolding for contpte mappings on arm64. So we need to
override mkold_clean_ptes() for arm64 to avoid it.

Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
Suggested-by: Barry Song <21cnbao@xxxxxxxxx>
Suggested-by: Ryan Roberts <ryan.roberts@xxxxxxx>
Signed-off-by: Lance Yang <ioworker0@xxxxxxxxx>
---
 arch/arm64/include/asm/pgtable.h | 36 ++++++++++++++++++++++++++++++++
 arch/arm64/mm/contpte.c          | 10 +++++++++
 include/linux/pgtable.h          | 30 ++++++++++++++++++++++++++
 3 files changed, 76 insertions(+)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9fd8613b2db2..b032c107090c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1086,6 +1086,27 @@ static inline bool pud_user_accessible_page(pud_t pud)
 }
 #endif
 
+static inline void __mkold_clean_pte(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep)
+{
+	pte_t old_pte, pte;
+
+	pte = __ptep_get(ptep);
+	do {
+		old_pte = pte;
+		pte = pte_mkclean(pte_mkold(pte));
+		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+					       pte_val(old_pte), pte_val(pte));
+	} while (pte_val(pte) != pte_val(old_pte));
+}
+
+static inline void mkold_clean_ptes(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep, unsigned int nr, int full)
+{
+	for (; nr-- > 0; ptep++, addr += PAGE_SIZE)
+		__mkold_clean_pte(vma, addr, ptep);
+}
+
 /*
  * Atomic pte/pmd modifications.
  */
@@ -1379,6 +1400,8 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
 extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep,
 				pte_t entry, int dirty);
+extern void contpte_ptep_mkold_clean(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep);
 
 static __always_inline void contpte_try_fold(struct mm_struct *mm,
 				unsigned long addr, pte_t *ptep, pte_t pte)
@@ -1603,6 +1626,18 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 	return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty);
 }
 
+#define mkold_clean_ptes mkold_clean_ptes
+static inline void mkold_clean_ptes(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep, unsigned int nr, int full)
+{
+	pte_t orig_pte = __ptep_get(ptep);
+
+	if (likely(!pte_valid_cont(orig_pte)))
+		return __mkold_clean_ptes(vma, addr, ptep, nr, full);
+
+	return contpte_ptep_mkold_clean(vma, addr, ptep);
+}
+
 #else /* CONFIG_ARM64_CONTPTE */
 
 #define ptep_get				__ptep_get
@@ -1622,6 +1657,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 #define wrprotect_ptes				__wrprotect_ptes
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 #define ptep_set_access_flags			__ptep_set_access_flags
+#define mkold_clean_ptes			__mkold_clean_ptes
 
 #endif /* CONFIG_ARM64_CONTPTE */
 
diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index 1b64b4c3f8bf..560622cfb2a9 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -322,6 +322,16 @@ int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(contpte_ptep_test_and_clear_young);
 
+void contpte_ptep_mkold_clean(struct vm_area_struct *vma, unsigned long addr,
+			      pte_t *ptep)
+{
+	ptep = contpte_align_down(ptep);
+	addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
+
+	__mkold_clean_ptes(vma, addr, ptep, CONT_PTES, 0);
+}
+EXPORT_SYMBOL_GPL(contpte_ptep_mkold_clean);
+
 int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
 					unsigned long addr, pte_t *ptep)
 {
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index fa8f92f6e2d7..fd30779fe487 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -391,6 +391,36 @@ static inline void mkold_ptes(struct vm_area_struct *vma, unsigned long addr,
 }
 #endif
 
+#ifndef mkold_clean_ptes
+/**
+ * mkold_clean_ptes - Mark PTEs that map consecutive pages of the same folio
+ *		as old and clean.
+ * @vma: VMA the pages are mapped into.
+ * @addr: Address the first page is mapped at.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries to mark old and clean.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over ptep_get_and_clear_full().
+ *
+ * Note that PTE bits in the PTE range besides the PFN can differ. For example,
+ * some PTEs might be write-protected.
+ *
+ * Context: The caller holds the page table lock.  The PTEs map consecutive
+ * pages that belong to the same folio.  The PTEs are all in the same PMD.
+ */
+static inline void mkold_clean_ptes(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep, unsigned int nr, int full)
+{
+	pte_t pte;
+
+	for (; nr-- > 0; ptep++, addr += PAGE_SIZE) {
+		pte = ptep_get_and_clear_full(vma->vm_mm, addr, ptep, full);
+		set_pte_at(vma->vm_mm, addr, ptep, pte_mkclean(pte_mkold(pte)));
+	}
+}
+#endif
+
 #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
-- 
2.33.1