From: Dev Jain <dev.jain@arm.com>
To: akpm@linux-foundation.org, david@kernel.org, ljs@kernel.org,
chrisl@kernel.org, kasong@tencent.com, hughd@google.com,
liam@infradead.org
Cc: Dev Jain <dev.jain@arm.com>,
riel@surriel.com, vbabka@kernel.org, harry@kernel.org,
jannh@google.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, rppt@kernel.org, surenb@google.com,
mhocko@suse.com, qi.zheng@linux.dev, shakeel.butt@linux.dev,
baohua@kernel.org, axelrasmussen@google.com, yuanchu@google.com,
weixugc@google.com, shikemeng@huaweicloud.com, nphamcs@gmail.com,
bhe@redhat.com, youngjun.park@lge.com,
baolin.wang@linux.alibaba.com, pfalcato@suse.de,
ryan.roberts@arm.com, anshuman.khandual@arm.com
Subject: [PATCH v4 04/12] mm/memory: Batch set uffd-wp markers during zapping
Date: Tue, 26 May 2026 12:06:27 +0530 [thread overview]
Message-ID: <20260526063635.61721-5-dev.jain@arm.com> (raw)
In-Reply-To: <20260526063635.61721-1-dev.jain@arm.com>
In preparation for the next patch, enable batch setting of uffd-wp ptes.
The code paths passing nr > 1 to zap_install_uffd_wp_if_needed() produce
that nr through either folio_pte_batch or swap_pte_batch, therefore
batching is correct:
1) all ptes belong to the same type of VMA (anonymous or non-anonymous,
wp-armed or non-wp-armed)
2) all ptes being marked with uffd-wp or all being not marked (same is the
case with the pte_swp_uffd_wp_any check)
3) uffd_supports_wp_marker() is independent of the function parameters
Note that we will have to use set_pte_at() in a loop instead of set_ptes()
since the latter cannot handle present->non-present conversion for
nr_pages > 1.
Rename the function to cond_install_uffd_wp_ptes, and convert the
documentation to kerneldoc format.
Move the function to memory.c since this has grown too long to be kept
in mm_inline.h, while retaining the inline hint.
Rename pte->ptep and pteval->pte.
Signed-off-by: Dev Jain <dev.jain@arm.com>
---
include/linux/mm.h | 4 ++
include/linux/mm_inline.h | 53 -------------------------
mm/memory.c | 81 ++++++++++++++++++++++++++++++---------
mm/rmap.c | 2 +-
4 files changed, 67 insertions(+), 73 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 31e27ff6a35fa..3169bd6d69f5a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -5216,4 +5216,8 @@ void map_anon_folio_pte_nopf(struct folio *folio, pte_t *pte,
struct vm_area_struct *vma, unsigned long addr,
bool uffd_wp);
+bool cond_install_uffd_wp_ptes(struct vm_area_struct *vma, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long nr_ptes);
+
+
#endif /* _LINUX_MM_H */
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index a171070e15f05..1a65c2bda2398 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -566,59 +566,6 @@ static inline pte_marker copy_pte_marker(
return dstm;
}
-/*
- * If this pte is wr-protected by uffd-wp in any form, arm the special pte to
- * replace a none pte. NOTE! This should only be called when *pte is already
- * cleared so we will never accidentally replace something valuable. Meanwhile
- * none pte also means we are not demoting the pte so tlb flushed is not needed.
- * E.g., when pte cleared the caller should have taken care of the tlb flush.
- *
- * Must be called with pgtable lock held so that no thread will see the none
- * pte, and if they see it, they'll fault and serialize at the pgtable lock.
- *
- * Returns true if an uffd-wp pte was installed, false otherwise.
- */
-static inline bool
-pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
- pte_t *pte, pte_t pteval)
-{
- bool arm_uffd_pte = false;
-
- if (!uffd_supports_wp_marker())
- return false;
-
- /* The current status of the pte should be "cleared" before calling */
- WARN_ON_ONCE(!pte_none(ptep_get(pte)));
-
- /*
- * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole
- * thing, because when zapping either it means it's dropping the
- * page, or in TTU where the present pte will be quickly replaced
- * with a swap pte. There's no way of leaking the bit.
- */
- if (vma_is_anonymous(vma) || !userfaultfd_wp(vma))
- return false;
-
- /* A uffd-wp wr-protected normal pte */
- if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval)))
- arm_uffd_pte = true;
-
- /*
- * A uffd-wp wr-protected swap pte. Note: this should even cover an
- * existing pte marker with uffd-wp bit set.
- */
- if (unlikely(pte_swp_uffd_wp_any(pteval)))
- arm_uffd_pte = true;
-
- if (unlikely(arm_uffd_pte)) {
- set_pte_at(vma->vm_mm, addr, pte,
- make_pte_marker(PTE_MARKER_UFFD_WP));
- return true;
- }
-
- return false;
-}
-
static inline bool vma_has_recency(const struct vm_area_struct *vma)
{
if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))
diff --git a/mm/memory.c b/mm/memory.c
index 0c9d9c2cbf0e0..767c033e95da9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1599,6 +1599,67 @@ static inline bool zap_drop_markers(struct zap_details *details)
return details->zap_flags & ZAP_FLAG_DROP_MARKER;
}
+/**
+ * cond_install_uffd_wp_ptes - install uffd-wp marker after clearing PTEs
+ * that mapped consecutive pages of the same
+ * large folio.
+ * @vma: The VMA the pages are mapped into.
+ * @addr: Address the first page of this batch is mapped at.
+ * @ptep: Page table pointer for the first entry of this batch.
+ * @pte: old value of the entry pointed to by ptep.
+ * @nr_ptes: Number of entries to clear (batch size).
+ *
+ * If the ptes were wr-protected by uffd-wp in any form, arm special ptes to
+ * replace none ptes. NOTE! This should only be called when *pte is already
+ * cleared so we will never accidentally replace something valuable. Meanwhile
+ * none pte also means we are not demoting the pte so tlb flushed is not needed.
+ * E.g., when pte cleared the caller should have taken care of the tlb flush.
+ *
+ * Must be called with pgtable lock held so that no thread will see the none
+ * pte, and if they see it, they'll fault and serialize at the pgtable lock.
+ *
+ * Returns true if uffd-wp ptes were installed, false otherwise.
+ */
+inline bool cond_install_uffd_wp_ptes(struct vm_area_struct *vma, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long nr_ptes)
+{
+ bool arm_uffd_pte = false;
+
+ if (!uffd_supports_wp_marker())
+ return false;
+
+ /* The current status of the pte should be "cleared" before calling */
+ WARN_ON_ONCE(!pte_none(ptep_get(ptep)));
+
+ /*
+ * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole
+ * thing, because when zapping either it means it's dropping the
+ * page, or in TTU where the present pte will be quickly replaced
+ * with a swap pte. There's no way of leaking the bit.
+ */
+ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma))
+ return false;
+
+ /* A uffd-wp wr-protected normal pte */
+ if (unlikely(pte_present(pte) && pte_uffd_wp(pte)))
+ arm_uffd_pte = true;
+
+ /*
+ * A uffd-wp wr-protected swap pte. Note: this should even cover an
+ * existing pte marker with uffd-wp bit set.
+ */
+ if (unlikely(pte_swp_uffd_wp_any(pte)))
+ arm_uffd_pte = true;
+
+ if (likely(!arm_uffd_pte))
+ return false;
+
+ for (int i = 0; i < nr_ptes; ++i, ++ptep, addr += PAGE_SIZE)
+ set_pte_at(vma->vm_mm, addr, ptep, make_pte_marker(PTE_MARKER_UFFD_WP));
+
+ return true;
+}
+
/*
* This function makes sure that we'll replace the none pte with an uffd-wp
* swap special pte marker when necessary. Must be with the pgtable lock held.
@@ -1610,29 +1671,11 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
unsigned long addr, pte_t *pte, int nr,
struct zap_details *details, pte_t pteval)
{
- bool was_installed = false;
-
- if (!uffd_supports_wp_marker())
- return false;
-
- /* Zap on anonymous always means dropping everything */
- if (vma_is_anonymous(vma))
- return false;
-
if (zap_drop_markers(details))
return false;
- for (;;) {
- /* the PFN in the PTE is irrelevant. */
- if (pte_install_uffd_wp_if_needed(vma, addr, pte, pteval))
- was_installed = true;
- if (--nr == 0)
- break;
- pte++;
- addr += PAGE_SIZE;
- }
+ return cond_install_uffd_wp_ptes(vma, addr, pte, pteval, nr);
- return was_installed;
}
static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
diff --git a/mm/rmap.c b/mm/rmap.c
index 12bbee57f20da..6a0b43856d6c0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2288,7 +2288,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
* we may want to replace a none pte with a marker pte if
* it's file-backed, so we don't lose the tracking info.
*/
- pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval);
+ cond_install_uffd_wp_ptes(vma, address, pvmw.pte, pteval, 1);
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
--
2.34.1
next prev parent reply other threads:[~2026-05-26 6:37 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-26 6:36 [PATCH v4 00/12] Optimize anonymous large folio unmapping Dev Jain
2026-05-26 6:36 ` [PATCH v4 01/12] mm/rmap: convert page -> folio for hwpoison checks Dev Jain
2026-05-26 6:36 ` [PATCH v4 02/12] mm/rmap: Add try_to_unmap_hugetlb_one Dev Jain
2026-05-26 6:36 ` [PATCH v4 03/12] mm/rmap: refactor some code around lazyfree folio unmapping Dev Jain
2026-05-26 6:36 ` Dev Jain [this message]
2026-05-26 6:36 ` [PATCH v4 05/12] mm/rmap: batch unmap folios belonging to uffd-wp VMAs Dev Jain
2026-05-26 6:36 ` [PATCH v4 06/12] mm/swap: rename subpage->page in folio_dup_swap/folio_put_swap Dev Jain
2026-05-26 6:36 ` [PATCH v4 07/12] mm/swapfile: Add batched version of folio_dup_swap Dev Jain
2026-05-26 6:36 ` [PATCH v4 08/12] mm/swapfile: Add batched version of folio_put_swap Dev Jain
2026-05-26 6:36 ` [PATCH v4 09/12] mm/rmap: Add batched version of folio_try_share_anon_rmap_pte Dev Jain
2026-05-26 6:36 ` [PATCH v4 10/12] mm/rmap: refactor anon folio unmap in try_to_unmap_one Dev Jain
2026-05-26 6:36 ` [PATCH v4 11/12] mm/mprotect: drop 'sub' from page_anon_exclusive_sub_batch Dev Jain
2026-05-26 6:36 ` [PATCH v4 12/12] mm/rmap: enable batch unmapping of anonymous folios Dev Jain
2026-05-28 16:50 ` [PATCH v4 00/12] Optimize anonymous large folio unmapping Dev Jain
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=20260526063635.61721-5-dev.jain@arm.com \
--to=dev.jain@arm.com \
--cc=akpm@linux-foundation.org \
--cc=anshuman.khandual@arm.com \
--cc=axelrasmussen@google.com \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=bhe@redhat.com \
--cc=chrisl@kernel.org \
--cc=david@kernel.org \
--cc=harry@kernel.org \
--cc=hughd@google.com \
--cc=jannh@google.com \
--cc=kasong@tencent.com \
--cc=liam@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mhocko@suse.com \
--cc=nphamcs@gmail.com \
--cc=pfalcato@suse.de \
--cc=qi.zheng@linux.dev \
--cc=riel@surriel.com \
--cc=rppt@kernel.org \
--cc=ryan.roberts@arm.com \
--cc=shakeel.butt@linux.dev \
--cc=shikemeng@huaweicloud.com \
--cc=surenb@google.com \
--cc=vbabka@kernel.org \
--cc=weixugc@google.com \
--cc=youngjun.park@lge.com \
--cc=yuanchu@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.