[PATCH v2 08/15] riscv/mm: avoid redundant Svnapot A/D aggregation

Svnapot mappings encode a 64KB range as a NAPOT PTE block, while the
public getter returns a logical base-page PTE. To preserve that PTE view,
the getter folds accessed and dirty information from the whole NAPOT block
into the returned PTE.

This aggregation is an OR-style operation. Once the returned PTE has both
accessed and dirty state set, later entries in the block cannot change the
result. Avoid reading the rest of the block in that case.

The lockless getter still validates each entry before consuming its A/D
state, so it preserves the self-consistent range requirement while also
avoiding reads that cannot affect the returned PTE.

Signed-off-by: Yunhui Cui <[email protected]>
---
 arch/riscv/mm/contpte.c | 60 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 56 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/mm/contpte.c b/arch/riscv/mm/contpte.c
index 9ffdffdc2b0c0..70f9a0668b50c 100644
--- a/arch/riscv/mm/contpte.c
+++ b/arch/riscv/mm/contpte.c
@@ -309,10 +309,34 @@ pte_t napotpte_ptep_get(pte_t *ptep, pte_t orig_pte)
 		cur = READ_ONCE(start[i]);
 		if (!napotpte_is_consistent(cur, orig_pte))
 			return napotpte_subpte(ptep, orig_pte);
-		if (pte_dirty(cur))
+		if (pte_dirty(cur)) {
 			pte = riscv_pte_mkhwdirty(pte);
-		if (pte_young(cur))
+			for (; i < nr; i++) {
+				cur = READ_ONCE(start[i]);
+				if (!napotpte_is_consistent(cur, orig_pte))
+					return napotpte_subpte(ptep, orig_pte);
+				if (pte_young(cur)) {
+					pte = pte_mkyoung(pte);
+					break;
+				}
+			}
+			break;
+		}
+
+		if (pte_young(cur)) {
 			pte = pte_mkyoung(pte);
+			i++;
+			for (; i < nr; i++) {
+				cur = READ_ONCE(start[i]);
+				if (!napotpte_is_consistent(cur, orig_pte))
+					return napotpte_subpte(ptep, orig_pte);
+				if (pte_dirty(cur)) {
+					pte = riscv_pte_mkhwdirty(pte);
+					break;
+				}
+			}
+			break;
+		}
 	}
 
 	return napotpte_subpte(ptep, pte);
@@ -343,11 +367,39 @@ pte_t napotpte_ptep_get_lockless(pte_t *orig_ptep)
 		if (!napotpte_is_consistent(pte, orig_pte))
 			goto retry;
 
-		if (pte_dirty(pte))
+		if (pte_dirty(pte)) {
 			orig_pte = riscv_pte_mkhwdirty(orig_pte);
+			for (; i < nr; i++, ptep++) {
+				pte = READ_ONCE(*ptep);
+
+				if (!napotpte_is_consistent(pte, orig_pte))
+					goto retry;
 
-		if (pte_young(pte))
+				if (pte_young(pte)) {
+					orig_pte = pte_mkyoung(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
+
+		if (pte_young(pte)) {
 			orig_pte = pte_mkyoung(orig_pte);
+			i++;
+			ptep++;
+			for (; i < nr; i++, ptep++) {
+				pte = READ_ONCE(*ptep);
+
+				if (!napotpte_is_consistent(pte, orig_pte))
+					goto retry;
+
+				if (pte_dirty(pte)) {
+					orig_pte = riscv_pte_mkhwdirty(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
 	}
 
 	return napotpte_subpte(orig_ptep, orig_pte);
-- 
2.39.5