linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
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 v5 2/2] mm/arm64: override mkold_clean_ptes() batch helper
Date: Mon,  8 Apr 2024 12:24:37 +0800	[thread overview]
Message-ID: <20240408042437.10951-3-ioworker0@gmail.com> (raw)
In-Reply-To: <20240408042437.10951-1-ioworker0@gmail.com>

The per-pte get_and_clear/modify/set approach would result in
unfolding/refolding for contpte mappings on arm64. So we need
to override mkold_clean_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          | 15 +++++++++
 2 files changed, 70 insertions(+)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9fd8613b2db2..395754638a9a 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1223,6 +1223,34 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address,
 		__ptep_set_wrprotect(mm, address, ptep);
 }
 
+static inline void ___ptep_mkold_clean(struct mm_struct *mm, unsigned long addr,
+				       pte_t *ptep, pte_t pte)
+{
+	pte_t old_pte;
+
+	do {
+		old_pte = pte;
+		pte = pte_mkclean(pte_mkold(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 __ptep_mkold_clean(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+	___ptep_mkold_clean(mm, addr, ptep, __ptep_get(ptep));
+}
+
+static inline void __mkold_clean_ptes(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep, unsigned int nr)
+{
+	unsigned int i;
+
+	for (i = 0; i < nr; i++, addr += PAGE_SIZE, ptep++)
+		__ptep_mkold_clean(mm, addr, ptep);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
 static inline void pmdp_set_wrprotect(struct mm_struct *mm,
@@ -1379,6 +1407,8 @@ 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_mkold_clean_ptes(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, unsigned int nr);
 
 static __always_inline void contpte_try_fold(struct mm_struct *mm,
 				unsigned long addr, pte_t *ptep, pte_t pte)
@@ -1603,6 +1633,30 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 	return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty);
 }
 
+#define mkold_clean_ptes mkold_clean_ptes
+static inline void mkold_clean_ptes(struct mm_struct *mm, unsigned long addr,
+				    pte_t *ptep, unsigned int nr)
+{
+	if (likely(nr == 1)) {
+		/*
+		 * Optimization: mkold_clean_ptes() can only be called for present
+		 * ptes so we only need to check contig bit as condition for unfold,
+		 * and we can remove the contig bit from the pte we read to avoid
+		 * re-reading. This speeds up madvise(MADV_FREE) which is sensitive
+		 * for order-0 folios. Equivalent to contpte_try_unfold().
+		 */
+		pte_t orig_pte = __ptep_get(ptep);
+
+		if (unlikely(pte_cont(orig_pte))) {
+			__contpte_try_unfold(mm, addr, ptep, orig_pte);
+			orig_pte = pte_mknoncont(orig_pte);
+		}
+		___ptep_mkold_clean(mm, addr, ptep, orig_pte);
+	} else {
+		contpte_mkold_clean_ptes(mm, addr, ptep, nr);
+	}
+}
+
 #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 mkold_clean_ptes			__mkold_clean_ptes
 
 #endif /* CONFIG_ARM64_CONTPTE */
 
diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index 1b64b4c3f8bf..dbff9c5e9eff 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -361,6 +361,21 @@ void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes);
 
+void contpte_mkold_clean_ptes(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned int nr)
+{
+	/*
+	 * If clearing the young and dirty bits for an entire contig range, we can
+	 * avoid unfolding. Just set old/clean and wait for the later mmu_gather
+	 * flush to invalidate the tlb. If it's a partial range though, we need to
+	 * unfold.
+	 */
+
+	contpte_try_unfold_partial(mm, addr, ptep, nr);
+	__mkold_clean_ptes(mm, addr, ptep, nr);
+}
+EXPORT_SYMBOL_GPL(contpte_mkold_clean_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



  parent reply	other threads:[~2024-04-08  4:25 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-04-08  4:24 [PATCH v5 0/2] mm/madvise: enhance lazyfreeing with mTHP in madvise_free Lance Yang
2024-04-08  4:24 ` [PATCH v5 1/2] mm/madvise: optimize " Lance Yang
2024-04-11 11:11   ` Ryan Roberts
2024-04-11 11:20     ` David Hildenbrand
2024-04-11 11:27       ` Ryan Roberts
2024-04-11 12:23         ` Lance Yang
2024-04-11 13:51           ` Ryan Roberts
2024-04-11 13:55             ` David Hildenbrand
2024-04-11 12:46     ` Lance Yang
2024-04-11 13:48       ` Ryan Roberts
2024-04-11 14:07         ` Lance Yang
2024-04-11 14:39           ` Ryan Roberts
2024-04-11 14:42             ` David Hildenbrand
2024-04-12  1:48             ` Lance Yang
2024-04-08  4:24 ` Lance Yang [this message]
2024-04-11 13:17   ` [PATCH v5 2/2] mm/arm64: override mkold_clean_ptes() batch helper Ryan Roberts
2024-04-12  2:09     ` Lance Yang
2024-04-12 11:21       ` Ryan Roberts
2024-04-10 21:50 ` [PATCH v5 0/2] mm/madvise: enhance lazyfreeing with mTHP in madvise_free Andrew Morton
2024-04-11  5:01   ` Lance Yang
2024-04-11 10:29     ` Ryan Roberts

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240408042437.10951-3-ioworker0@gmail.com \
    --to=ioworker0@gmail.com \
    --cc=21cnbao@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=david@redhat.com \
    --cc=fengwei.yin@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=minchan@kernel.org \
    --cc=peterx@redhat.com \
    --cc=ryan.roberts@arm.com \
    --cc=shy828301@gmail.com \
    --cc=songmuchun@bytedance.com \
    --cc=wangkefeng.wang@huawei.com \
    --cc=xiehuan09@gmail.com \
    --cc=zokeefe@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox