[PATCH v4 1/5] mm: rmap: support batched checks of the references for large folios

[Baolin Wang <baolin.wang@linux.alibaba.com>]

Currently, folio_referenced_one() always checks the young flag for each PTE
sequentially, which is inefficient for large folios. This inefficiency is
especially noticeable when reclaiming clean file-backed large folios, where
folio_referenced() is observed as a significant performance hotspot.

Moreover, on Arm64 architecture, which supports contiguous PTEs, there is already
an optimization to clear the young flags for PTEs within a contiguous range.
However, this is not sufficient. We can extend this to perform batched operations
for the entire large folio (which might exceed the contiguous range: CONT_PTE_SIZE).

Introduce a new API: clear_flush_young_ptes() to facilitate batched checking
of the young flags and flushing TLB entries, thereby improving performance
during large folio reclamation. And it will be overridden by the architecture
that implements a more efficient batch operation in the following patches.

Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
---
 include/linux/mmu_notifier.h |  9 +++++----
 include/linux/pgtable.h      | 35 +++++++++++++++++++++++++++++++++++
 mm/rmap.c                    | 29 +++++++++++++++++++++++++++--
 3 files changed, 67 insertions(+), 6 deletions(-)

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index d1094c2d5fb6..dbbdcef4abf1 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -515,16 +515,17 @@ static inline void mmu_notifier_range_init_owner(
 	range->owner = owner;
 }
 
-#define ptep_clear_flush_young_notify(__vma, __address, __ptep)		\
+#define ptep_clear_flush_young_notify(__vma, __address, __ptep, __nr)	\
 ({									\
 	int __young;							\
 	struct vm_area_struct *___vma = __vma;				\
 	unsigned long ___address = __address;				\
-	__young = ptep_clear_flush_young(___vma, ___address, __ptep);	\
+	unsigned int ___nr = __nr;					\
+	__young = clear_flush_young_ptes(___vma, ___address, __ptep, ___nr);	\
 	__young |= mmu_notifier_clear_flush_young(___vma->vm_mm,	\
 						  ___address,		\
 						  ___address +		\
-							PAGE_SIZE);	\
+						  ___nr * PAGE_SIZE);	\
 	__young;							\
 })
 
@@ -650,7 +651,7 @@ static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
 
 #define mmu_notifier_range_update_to_read_only(r) false
 
-#define ptep_clear_flush_young_notify ptep_clear_flush_young
+#define ptep_clear_flush_young_notify clear_flush_young_ptes
 #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
 #define ptep_clear_young_notify ptep_test_and_clear_young
 #define pmdp_clear_young_notify pmdp_test_and_clear_young
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 2f0dd3a4ace1..fcf7a7820061 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1087,6 +1087,41 @@ static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 
+#ifndef clear_flush_young_ptes
+/**
+ * clear_flush_young_ptes - Clear the access bit and perform a TLB flush for PTEs
+ *			    that map consecutive pages of the same folio.
+ * @vma: The virtual memory area 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 clear access bit.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over ptep_clear_flush_young().
+ *
+ * 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 int clear_flush_young_ptes(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 unsigned int nr)
+{
+	int young;
+
+	young = ptep_clear_flush_young(vma, addr, ptep);
+	while (--nr) {
+		ptep++;
+		addr += PAGE_SIZE;
+		young |= ptep_clear_flush_young(vma, addr, ptep);
+	}
+
+	return young;
+}
+#endif
+
 /*
  * On some architectures hardware does not set page access bit when accessing
  * memory page, it is responsibility of software setting this bit. It brings
diff --git a/mm/rmap.c b/mm/rmap.c
index d6799afe1114..a0fc05f5966f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -827,9 +827,11 @@ static bool folio_referenced_one(struct folio *folio,
 	struct folio_referenced_arg *pra = arg;
 	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
 	int ptes = 0, referenced = 0;
+	unsigned int nr;
 
 	while (page_vma_mapped_walk(&pvmw)) {
 		address = pvmw.address;
+		nr = 1;
 
 		if (vma->vm_flags & VM_LOCKED) {
 			ptes++;
@@ -874,9 +876,24 @@ static bool folio_referenced_one(struct folio *folio,
 			if (lru_gen_look_around(&pvmw))
 				referenced++;
 		} else if (pvmw.pte) {
+			if (folio_test_large(folio)) {
+				unsigned long end_addr =
+					pmd_addr_end(address, vma->vm_end);
+				unsigned int max_nr =
+					(end_addr - address) >> PAGE_SHIFT;
+				pte_t pteval = ptep_get(pvmw.pte);
+
+				nr = folio_pte_batch(folio, pvmw.pte,
+						     pteval, max_nr);
+			}
+
+			ptes += nr;
 			if (ptep_clear_flush_young_notify(vma, address,
-						pvmw.pte))
+						pvmw.pte, nr))
 				referenced++;
+			/* Skip the batched PTEs */
+			pvmw.pte += nr - 1;
+			pvmw.address += (nr - 1) * PAGE_SIZE;
 		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 			if (pmdp_clear_flush_young_notify(vma, address,
 						pvmw.pmd))
@@ -886,7 +903,15 @@ static bool folio_referenced_one(struct folio *folio,
 			WARN_ON_ONCE(1);
 		}
 
-		pra->mapcount--;
+		pra->mapcount -= nr;
+		/*
+		 * If we are sure that we batched the entire folio,
+		 * we can just optimize and stop right here.
+		 */
+		if (ptes == pvmw.nr_pages) {
+			page_vma_mapped_walk_done(&pvmw);
+			break;
+		}
 	}
 
 	if (referenced)
-- 
2.47.3