summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorBaolin Wang <baolin.wang@linux.alibaba.com>2026-02-09 22:07:27 +0800
committerAndrew Morton <akpm@linux-foundation.org>2026-02-12 15:43:00 -0800
commit07f440c23a197616f7b7607b98b9427da23f9f6f (patch)
tree1c018e21ed690b38cbacef1bd8e14424a876d18d /arch
parent6f0e1142173a54b8a18c59fc3cbae3b31ee423d9 (diff)
arm64: mm: implement the architecture-specific clear_flush_young_ptes()
Implement the Arm64 architecture-specific clear_flush_young_ptes() to enable batched checking of young flags and TLB flushing, improving performance during large folio reclamation. Performance testing: Allocate 10G clean file-backed folios by mmap() in a memory cgroup, and try to reclaim 8G file-backed folios via the memory.reclaim interface. I can observe 33% performance improvement on my Arm64 32-core server (and 10%+ improvement on my X86 machine). Meanwhile, the hotspot folio_check_references() dropped from approximately 35% to around 5%. W/o patchset: real 0m1.518s user 0m0.000s sys 0m1.518s W/ patchset: real 0m1.018s user 0m0.000s sys 0m1.018s Link: https://lkml.kernel.org/r/ce749fbae3e900e733fa104a16fcb3ca9fe4f9bd.1770645603.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: David Hildenbrand (Arm) <david@kernel.org> Cc: Barry Song <baohua@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Harry Yoo <harry.yoo@oracle.com> Cc: Jann Horn <jannh@google.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Rik van Riel <riel@surriel.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/include/asm/pgtable.h11
1 files changed, 11 insertions, 0 deletions
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 3dabf5ea17fa..a17eb8a76788 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1838,6 +1838,17 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
return contpte_clear_flush_young_ptes(vma, addr, ptep, 1);
}
+#define clear_flush_young_ptes clear_flush_young_ptes
+static inline int clear_flush_young_ptes(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ unsigned int nr)
+{
+ if (likely(nr == 1 && !pte_cont(__ptep_get(ptep))))
+ return __ptep_clear_flush_young(vma, addr, ptep);
+
+ return contpte_clear_flush_young_ptes(vma, addr, ptep, nr);
+}
+
#define wrprotect_ptes wrprotect_ptes
static __always_inline void wrprotect_ptes(struct mm_struct *mm,
unsigned long addr, pte_t *ptep, unsigned int nr)