[2/2] arm64: Enable ARCH_HAS_NONLEAF_PMD_YOUNG

Commit Message

Yicong Yang Aug. 2, 2024, 9:34 a.m. UTC

From: Yicong Yang <[e-mail]>

With the support of FEAT_HAFT, the NONLEAF_PMD_YOUNG can be enabled
on arm64 since the hardware is capable of updating the AF flag for
PMD table descriptor. Since the AF bit of the table descriptor
shares the same bit position in block descriptors, we only need
to implement arch_has_hw_nonleaf_pmd_young() and select related
configs. The related pmd_young test/update operations keeps the
same with and already implemented for transparent page support.

Currently ARCH_HAS_NONLEAF_PMD_YOUNG is used to improve the
efficiency of lru-gen aging.

Signed-off-by: Yicong Yang <[e-mail]>
---
 arch/arm64/Kconfig               |  1 +
 arch/arm64/include/asm/pgtable.h | 14 ++++++++++++--
 2 files changed, 13 insertions(+), 2 deletions(-)

Patch

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f263ae4139a5..d1103a3f4a8d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -36,6 +36,7 @@  config ARM64
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	select ARCH_HAS_NONLEAF_PMD_YOUNG if ARM64_HAFT
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_HW_PTE_YOUNG
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7a4f5604be3f..077bea37867e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1205,7 +1205,7 @@  static inline int __ptep_clear_flush_young(struct vm_area_struct *vma,
 	return young;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
@@ -1213,7 +1213,7 @@  static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 {
 	return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
 }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
 
 static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address, pte_t *ptep)
@@ -1448,6 +1448,16 @@  static inline void update_mmu_cache_range(struct vm_fault *vmf,
  */
 #define arch_has_hw_pte_young		cpu_has_hw_af
 
+#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
+
+#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young
+static inline bool arch_has_hw_nonleaf_pmd_young(void)
+{
+	return cpus_have_final_cap(ARM64_HAFT);
+}
+
+#endif
+
 /*
  * Experimentally, it's cheap to set the access flag in hardware and we
  * benefit from prefaulting mappings as 'old' to start with.