[PATCH v1] 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@xxxxxxx>
---
 arch/arm64/mm/contpte.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index bcac4f55f9c1..ca15d8f52d14 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -163,17 +163,26 @@ pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte)
 
 	pte_t pte;
 	int i;
+	bool dirty = false;
+	bool young = false;
 
 	ptep = contpte_align_down(ptep);
 
 	for (i = 0; i < CONT_PTES; i++, ptep++) {
 		pte = __ptep_get(ptep);
 
-		if (pte_dirty(pte))
+		if (!dirty && pte_dirty(pte)) {
+			dirty = true;
 			orig_pte = pte_mkdirty(orig_pte);
+		}
 
-		if (pte_young(pte))
+		if (!young && pte_young(pte)) {
+			young = true;
 			orig_pte = pte_mkyoung(orig_pte);
+		}
+
+		if (dirty && young)
+			break;
 	}
 
 	return orig_pte;
-- 
2.34.1