From: Andrew Morton <akpm@linux-foundation.org>
To: mm-commits@vger.kernel.org,zokeefe@google.com,xiehuan09@gmail.com,wangkefeng.wang@huawei.com,songmuchun@bytedance.com,shy828301@gmail.com,ryan.roberts@arm.com,peterx@redhat.com,minchan@kernel.org,mhocko@suse.com,fengwei.yin@intel.com,david@redhat.com,21cnbao@gmail.com,ioworker0@gmail.com,akpm@linux-foundation.org
Subject: [merged mm-stable] mm-arm64-override-clear_young_dirty_ptes-batch-helper.patch removed from -mm tree
Date: Sun, 05 May 2024 17:57:54 -0700 [thread overview]
Message-ID: <20240506005755.25062C113CC@smtp.kernel.org> (raw)
The quilt patch titled
Subject: mm/arm64: override clear_young_dirty_ptes() batch helper
has been removed from the -mm tree. Its filename was
mm-arm64-override-clear_young_dirty_ptes-batch-helper.patch
This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Lance Yang <ioworker0@gmail.com>
Subject: mm/arm64: override clear_young_dirty_ptes() batch helper
Date: Thu, 18 Apr 2024 21:44:33 +0800
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.
Link: https://lkml.kernel.org/r/20240418134435.6092-3-ioworker0@gmail.com
Signed-off-by: Lance Yang <ioworker0@gmail.com>
Suggested-by: Barry Song <21cnbao@gmail.com>
Suggested-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jeff Xie <xiehuan09@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/arm64/include/asm/pgtable.h | 55 +++++++++++++++++++++++++++++
arch/arm64/mm/contpte.c | 29 +++++++++++++++
2 files changed, 84 insertions(+)
--- a/arch/arm64/include/asm/pgtable.h~mm-arm64-override-clear_young_dirty_ptes-batch-helper
+++ a/arch/arm64/include/asm/pgtable.h
@@ -1223,6 +1223,46 @@ static inline void __wrprotect_ptes(stru
__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(struc
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(
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(
#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 */
--- a/arch/arm64/mm/contpte.c~mm-arm64-override-clear_young_dirty_ptes-batch-helper
+++ a/arch/arm64/mm/contpte.c
@@ -361,6 +361,35 @@ void contpte_wrprotect_ptes(struct mm_st
}
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)
_
Patches currently in -mm which might be from ioworker0@gmail.com are
reply other threads:[~2024-05-06 0:57 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20240506005755.25062C113CC@smtp.kernel.org \
--to=akpm@linux-foundation.org \
--cc=21cnbao@gmail.com \
--cc=david@redhat.com \
--cc=fengwei.yin@intel.com \
--cc=ioworker0@gmail.com \
--cc=mhocko@suse.com \
--cc=minchan@kernel.org \
--cc=mm-commits@vger.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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).