Received-SPF: pass (google.com: domain of linux-kernel+bounces-146181-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Lance Yang <ioworker0@gmail.com>
To: akpm@linux-foundation.org
Cc: ryan.roberts@arm.com,
	david@redhat.com,
	21cnbao@gmail.com,
	mhocko@suse.com,
	fengwei.yin@intel.com,
	zokeefe@google.com,
	shy828301@gmail.com,
	xiehuan09@gmail.com,
	wangkefeng.wang@huawei.com,
	songmuchun@bytedance.com,
	peterx@redhat.com,
	minchan@kernel.org,
	linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	Lance Yang <ioworker0@gmail.com>
Subject: [PATCH v7 2/3] mm/arm64: override clear_young_dirty_ptes() batch helper
Date: Tue, 16 Apr 2024 11:34:56 +0800
Message-Id: <20240416033457.32154-3-ioworker0@gmail.com>
In-Reply-To: <20240416033457.32154-1-ioworker0@gmail.com>
References: <20240416033457.32154-1-ioworker0@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

The per-pte get_and_clear/modify/set approach would result in
unfolding/refolding for contpte mappings on arm64. So we need
to override clear_young_dirty_ptes() for arm64 to avoid it.

Suggested-by: David Hildenbrand <david@redhat.com>
Suggested-by: Barry Song <21cnbao@gmail.com>
Suggested-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
---
 arch/arm64/include/asm/pgtable.h | 55 ++++++++++++++++++++++++++++++++
 arch/arm64/mm/contpte.c          | 29 +++++++++++++++++
 2 files changed, 84 insertions(+)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9fd8613b2db2..1303d30287dc 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1223,6 +1223,46 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address,
 		__ptep_set_wrprotect(mm, address, ptep);
 }
 
+static inline void __clear_young_dirty_pte(struct vm_area_struct *vma,
+					   unsigned long addr, pte_t *ptep,
+					   pte_t pte, cydp_t flags)
+{
+	pte_t old_pte;
+
+	do {
+		old_pte = pte;
+
+		if (flags & CYDP_CLEAR_YOUNG)
+			pte = pte_mkold(pte);
+		if (flags & CYDP_CLEAR_DIRTY)
+			pte = pte_mkclean(pte);
+
+		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+					       pte_val(old_pte), pte_val(pte));
+	} while (pte_val(pte) != pte_val(old_pte));
+}
+
+static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma,
+					    unsigned long addr, pte_t *ptep,
+					    unsigned int nr, cydp_t flags)
+{
+	pte_t pte;
+
+	for (;;) {
+		pte = __ptep_get(ptep);
+
+		if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY))
+			__set_pte(ptep, pte_mkclean(pte_mkold(pte)));
+		else
+			__clear_young_dirty_pte(vma, addr, ptep, pte, flags);
+
+		if (--nr == 0)
+			break;
+		ptep++;
+		addr += PAGE_SIZE;
+	}
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
 static inline void pmdp_set_wrprotect(struct mm_struct *mm,
@@ -1379,6 +1419,9 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
 extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep,
 				pte_t entry, int dirty);
+extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep,
+				unsigned int nr, cydp_t flags);
 
 static __always_inline void contpte_try_fold(struct mm_struct *mm,
 				unsigned long addr, pte_t *ptep, pte_t pte)
@@ -1603,6 +1646,17 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 	return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty);
 }
 
+#define clear_young_dirty_ptes clear_young_dirty_ptes
+static inline void clear_young_dirty_ptes(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep,
+					  unsigned int nr, cydp_t flags)
+{
+	if (likely(nr == 1 && !pte_cont(__ptep_get(ptep))))
+		__clear_young_dirty_ptes(vma, addr, ptep, nr, flags);
+	else
+		contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags);
+}
+
 #else /* CONFIG_ARM64_CONTPTE */
 
 #define ptep_get				__ptep_get
@@ -1622,6 +1676,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 #define wrprotect_ptes				__wrprotect_ptes
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 #define ptep_set_access_flags			__ptep_set_access_flags
+#define clear_young_dirty_ptes			__clear_young_dirty_ptes
 
 #endif /* CONFIG_ARM64_CONTPTE */
 
diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index 1b64b4c3f8bf..9f9486de0004 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -361,6 +361,35 @@ void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes);
 
+void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep,
+				    unsigned int nr, cydp_t flags)
+{
+	/*
+	 * We can safely clear access/dirty without needing to unfold from
+	 * the architectures perspective, even when contpte is set. If the
+	 * range starts or ends midway through a contpte block, we can just
+	 * expand to include the full contpte block. While this is not
+	 * exactly what the core-mm asked for, it tracks access/dirty per
+	 * folio, not per page. And since we only create a contpte block
+	 * when it is covered by a single folio, we can get away with
+	 * clearing access/dirty for the whole block.
+	 */
+	unsigned long start = addr;
+	unsigned long end = start + nr;
+
+	if (pte_cont(__ptep_get(ptep + nr - 1)))
+		end = ALIGN(end, CONT_PTE_SIZE);
+
+	if (pte_cont(__ptep_get(ptep))) {
+		start = ALIGN_DOWN(start, CONT_PTE_SIZE);
+		ptep = contpte_align_down(ptep);
+	}
+
+	__clear_young_dirty_ptes(vma, start, ptep, end - start, flags);
+}
+EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes);
+
 int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 					unsigned long addr, pte_t *ptep,
 					pte_t entry, int dirty)
-- 
2.33.1