From: Lance Yang <ioworker0@gmail.com>
To: akpm@linux-foundation.org
Cc: zokeefe@google.com, ryan.roberts@arm.com, 21cnbao@gmail.com,
shy828301@gmail.com, david@redhat.com, mhocko@suse.com,
fengwei.yin@intel.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 v6 2/2] mm/arm64: override clear_young_dirty_ptes() batch helper
Date: Sat, 13 Apr 2024 08:22:19 +0800 [thread overview]
Message-ID: <20240413002219.71246-3-ioworker0@gmail.com> (raw)
In-Reply-To: <20240413002219.71246-1-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 clear_young_dirty_ptes() for arm64 to avoid it.
Suggested-by: David Hildenbrand <david@redhat.com>
Suggested-by: Barry Song <21cnbao@gmail.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
---
arch/arm64/include/asm/pgtable.h | 37 ++++++++++++++++++++++++++++++++
arch/arm64/mm/contpte.c | 28 ++++++++++++++++++++++++
2 files changed, 65 insertions(+)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9fd8613b2db2..f951774dd2d6 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1223,6 +1223,28 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address,
__ptep_set_wrprotect(mm, address, ptep);
}
+static inline void __clear_young_dirty_ptes(struct mm_struct *mm,
+ 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)
+ pte = pte_mkold(pte);
+ if (flags | CYDP_CLEAR_DIRTY)
+ pte = pte_mkclean(pte);
+
+ __set_pte(ptep, pte);
+ 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 +1401,9 @@ 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 mm_struct *mm,
+ 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 +1628,17 @@ 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 mm_struct *mm,
+ 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(mm, addr, ptep, nr, flags);
+ else
+ contpte_clear_young_dirty_ptes(mm, addr, ptep, nr, flags);
+}
+
#else /* CONFIG_ARM64_CONTPTE */
#define ptep_get __ptep_get
@@ -1622,6 +1658,7 @@ 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..bf3b089d9641 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -361,6 +361,34 @@ void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
}
EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes);
+void contpte_clear_young_dirty_ptes(struct mm_struct *mm, 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 int start = addr;
+ unsigned int 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(mm, 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
next prev parent reply other threads:[~2024-04-13 0:22 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-13 0:22 [PATCH v6 0/2] mm/madvise: enhance lazyfreeing with mTHP in madvise_free Lance Yang
2024-04-13 0:22 ` [PATCH v6 1/2] mm/madvise: optimize " Lance Yang
2024-04-15 8:47 ` Ryan Roberts
2024-04-15 9:23 ` Lance Yang
2024-04-13 0:22 ` Lance Yang [this message]
2024-04-15 8:59 ` [PATCH v6 2/2] mm/arm64: override clear_young_dirty_ptes() batch helper Ryan Roberts
2024-04-15 9:41 ` Lance Yang
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=20240413002219.71246-3-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
all inboxes | Powered by JetHome®