[PATCH v2 1/1] mm/contpte: Optimize loop to reduce redundant operations

[Xavier]

This commit optimizes the contpte_ptep_get function by adding early
 termination logic. It checks if the dirty and young bits of orig_pte
 are already set and skips redundant bit-setting operations during
 the loop. This reduces unnecessary iterations and improves performance.

Signed-off-by: Xavier <xavier_qy at 163.com>
---
 arch/arm64/mm/contpte.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index bcac4f55f9c1..034d153d7d19 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -152,6 +152,18 @@ void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(__contpte_try_unfold);
 
+#define CHECK_CONTPTE_FLAG(start, ptep, orig_pte, flag) \
+	do { \
+		int _start = start; \
+		pte_t *_ptep = ptep; \
+		while (_start++ < CONT_PTES) { \
+			if (pte_##flag(__ptep_get(_ptep++))) { \
+				orig_pte = pte_mk##flag(orig_pte); \
+				break; \
+			} \
+		} \
+	} while (0)
+
 pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte)
 {
 	/*
@@ -169,11 +181,17 @@ pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte)
 	for (i = 0; i < CONT_PTES; i++, ptep++) {
 		pte = __ptep_get(ptep);
 
-		if (pte_dirty(pte))
+		if (pte_dirty(pte)) {
 			orig_pte = pte_mkdirty(orig_pte);
+			CHECK_CONTPTE_FLAG(i, ptep, orig_pte, young);
+			break;
+		}
 
-		if (pte_young(pte))
+		if (pte_young(pte)) {
 			orig_pte = pte_mkyoung(orig_pte);
+			CHECK_CONTPTE_FLAG(i, ptep, orig_pte, dirty);
+			break;
+		}
 	}
 
 	return orig_pte;
-- 
2.34.1