From: Mike Rapoport <rppt@kernel.org>
To: linux-mm@kvack.org
Cc: Andrea Arcangeli <aarcange@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Axel Rasmussen <axelrasmussen@google.com>,
Baolin Wang <baolin.wang@linux.alibaba.com>,
David Hildenbrand <david@redhat.com>,
Hugh Dickins <hughd@google.com>,
James Houghton <jthoughton@google.com>,
"Liam R. Howlett" <Liam.Howlett@oracle.com>,
Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
Michal Hocko <mhocko@suse.com>, Mike Rapoport <rppt@kernel.org>,
Muchun Song <muchun.song@linux.dev>,
Nikita Kalyazin <kalyazin@amazon.com>,
Oscar Salvador <osalvador@suse.de>,
Paolo Bonzini <pbonzini@redhat.com>, Peter Xu <peterx@redhat.com>,
Sean Christopherson <seanjc@google.com>,
Shuah Khan <shuah@kernel.org>,
Suren Baghdasaryan <surenb@google.com>,
Vlastimil Babka <vbabka@suse.cz>,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
linux-kselftest@vger.kernel.org
Subject: [PATCH RFC 03/17] userfaultfd: introduce mfill_get_pmd() helper.
Date: Tue, 27 Jan 2026 21:29:22 +0200 [thread overview]
Message-ID: <20260127192936.1250096-4-rppt@kernel.org> (raw)
In-Reply-To: <20260127192936.1250096-1-rppt@kernel.org>
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
There is a lengthy code chunk in mfill_atomic() that establishes the PMD
for UFFDIO operations. This code may be called twice: first time when
the copy is performed with VMA/mm locks held and the other time after
the copy is retried with locks dropped.
Move the code that establishes a PMD into a helper function so it can be
reused later during refactoring of mfill_atomic_pte_copy().
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
mm/userfaultfd.c | 103 ++++++++++++++++++++++++-----------------------
1 file changed, 53 insertions(+), 50 deletions(-)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 6a0697c93ff4..9dd285b13f3b 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -157,6 +157,57 @@ static void uffd_mfill_unlock(struct vm_area_struct *vma)
}
#endif
+static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+
+ pgd = pgd_offset(mm, address);
+ p4d = p4d_alloc(mm, pgd, address);
+ if (!p4d)
+ return NULL;
+ pud = pud_alloc(mm, p4d, address);
+ if (!pud)
+ return NULL;
+ /*
+ * Note that we didn't run this because the pmd was
+ * missing, the *pmd may be already established and in
+ * turn it may also be a trans_huge_pmd.
+ */
+ return pmd_alloc(mm, pud, address);
+}
+
+static int mfill_get_pmd(struct mfill_state *state)
+{
+ struct mm_struct *dst_mm = state->ctx->mm;
+ pmd_t *dst_pmd;
+ pmd_t dst_pmdval;
+
+ dst_pmd = mm_alloc_pmd(dst_mm, state->dst_addr);
+ if (unlikely(!dst_pmd))
+ return -ENOMEM;
+
+ dst_pmdval = pmdp_get_lockless(dst_pmd);
+ if (unlikely(pmd_none(dst_pmdval)) &&
+ unlikely(__pte_alloc(dst_mm, dst_pmd)))
+ return -ENOMEM;
+
+ dst_pmdval = pmdp_get_lockless(dst_pmd);
+ /*
+ * If the dst_pmd is THP don't override it and just be strict.
+ * (This includes the case where the PMD used to be THP and
+ * changed back to none after __pte_alloc().)
+ */
+ if (unlikely(!pmd_present(dst_pmdval) || pmd_trans_huge(dst_pmdval)))
+ return -EEXIST;
+ if (unlikely(pmd_bad(dst_pmdval)))
+ return -EFAULT;
+
+ state->pmd = dst_pmd;
+ return 0;
+}
+
/* Check if dst_addr is outside of file's size. Must be called with ptl held. */
static bool mfill_file_over_size(struct vm_area_struct *dst_vma,
unsigned long dst_addr)
@@ -489,27 +540,6 @@ static int mfill_atomic_pte_poison(struct mfill_state *state)
return ret;
}
-static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
-{
- pgd_t *pgd;
- p4d_t *p4d;
- pud_t *pud;
-
- pgd = pgd_offset(mm, address);
- p4d = p4d_alloc(mm, pgd, address);
- if (!p4d)
- return NULL;
- pud = pud_alloc(mm, p4d, address);
- if (!pud)
- return NULL;
- /*
- * Note that we didn't run this because the pmd was
- * missing, the *pmd may be already established and in
- * turn it may also be a trans_huge_pmd.
- */
- return pmd_alloc(mm, pud, address);
-}
-
#ifdef CONFIG_HUGETLB_PAGE
/*
* mfill_atomic processing for HUGETLB vmas. Note that this routine is
@@ -742,7 +772,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
struct vm_area_struct *dst_vma;
long copied = 0;
ssize_t err;
- pmd_t *dst_pmd;
/*
* Sanitize the command parameters:
@@ -809,41 +838,15 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
while (state.src_addr < src_start + len) {
VM_WARN_ON_ONCE(state.dst_addr >= dst_start + len);
- pmd_t dst_pmdval;
-
- dst_pmd = mm_alloc_pmd(dst_mm, state.dst_addr);
- if (unlikely(!dst_pmd)) {
- err = -ENOMEM;
+ err = mfill_get_pmd(&state);
+ if (err)
break;
- }
- dst_pmdval = pmdp_get_lockless(dst_pmd);
- if (unlikely(pmd_none(dst_pmdval)) &&
- unlikely(__pte_alloc(dst_mm, dst_pmd))) {
- err = -ENOMEM;
- break;
- }
- dst_pmdval = pmdp_get_lockless(dst_pmd);
- /*
- * If the dst_pmd is THP don't override it and just be strict.
- * (This includes the case where the PMD used to be THP and
- * changed back to none after __pte_alloc().)
- */
- if (unlikely(!pmd_present(dst_pmdval) ||
- pmd_trans_huge(dst_pmdval))) {
- err = -EEXIST;
- break;
- }
- if (unlikely(pmd_bad(dst_pmdval))) {
- err = -EFAULT;
- break;
- }
/*
* For shmem mappings, khugepaged is allowed to remove page
* tables under us; pte_offset_map_lock() will deal with that.
*/
- state.pmd = dst_pmd;
err = mfill_atomic_pte(&state);
cond_resched();
--
2.51.0
next prev parent reply other threads:[~2026-01-27 19:30 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-27 19:29 [PATCH RFC 00/17] mm, kvm: allow uffd suppot in guest_memfd Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 01/17] userfaultfd: introduce mfill_copy_folio_locked() helper Mike Rapoport
2026-02-03 17:45 ` Peter Xu
2026-02-08 9:49 ` Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 02/17] userfaultfd: introduce struct mfill_state Mike Rapoport
2026-01-27 19:29 ` Mike Rapoport [this message]
2026-01-27 19:29 ` [PATCH RFC 04/17] userfaultfd: introduce mfill_get_vma() and mfill_put_vma() Mike Rapoport
2026-02-02 21:49 ` Peter Xu
2026-02-08 9:54 ` Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 05/17] userfaultfd: retry copying with locks dropped in mfill_atomic_pte_copy() Mike Rapoport
2026-02-02 21:23 ` Peter Xu
2026-02-08 10:01 ` Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 06/17] userfaultfd: move vma_can_userfault out of line Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 07/17] userfaultfd: introduce vm_uffd_ops Mike Rapoport
2026-02-02 21:36 ` Peter Xu
2026-02-08 10:13 ` Mike Rapoport
2026-02-11 19:35 ` Peter Xu
2026-02-15 17:47 ` Mike Rapoport
2026-02-18 21:34 ` Peter Xu
2026-01-27 19:29 ` [PATCH RFC 08/17] userfaultfd, shmem: use a VMA callback to handle UFFDIO_CONTINUE Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 09/17] userfaultfd: introduce vm_uffd_ops->alloc_folio() Mike Rapoport
2026-02-02 22:13 ` Peter Xu
2026-02-08 10:22 ` Mike Rapoport
2026-02-11 19:37 ` Peter Xu
2026-01-27 19:29 ` [PATCH RFC 10/17] shmem, userfaultfd: implement shmem uffd operations using vm_uffd_ops Mike Rapoport
2026-02-03 17:40 ` Peter Xu
2026-02-08 10:35 ` Mike Rapoport
2026-02-11 20:00 ` Peter Xu
2026-02-15 17:45 ` Mike Rapoport
2026-02-18 21:45 ` Peter Xu
2026-01-27 19:29 ` [PATCH RFC 11/17] userfaultfd: mfill_atomic() remove retry logic Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 12/17] mm: introduce VM_FAULT_UFFD_MINOR fault reason Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 13/17] mm: introduce VM_FAULT_UFFD_MISSING " Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 14/17] KVM: guest_memfd: implement userfaultfd minor mode Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 15/17] KVM: guest_memfd: implement userfaultfd missing mode Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 16/17] KVM: selftests: test userfaultfd minor for guest_memfd Mike Rapoport
2026-01-27 19:29 ` [PATCH RFC 17/17] KVM: selftests: test userfaultfd missing " Mike Rapoport
2026-02-03 20:56 ` [PATCH RFC 00/17] mm, kvm: allow uffd suppot in guest_memfd Peter Xu
2026-02-09 15:35 ` David Hildenbrand (Arm)
2026-02-11 6:04 ` Mike Rapoport
2026-02-11 9:52 ` David Hildenbrand (Arm)
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=20260127192936.1250096-4-rppt@kernel.org \
--to=rppt@kernel.org \
--cc=Liam.Howlett@oracle.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=baolin.wang@linux.alibaba.com \
--cc=david@redhat.com \
--cc=hughd@google.com \
--cc=jthoughton@google.com \
--cc=kalyazin@amazon.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=mhocko@suse.com \
--cc=muchun.song@linux.dev \
--cc=osalvador@suse.de \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=seanjc@google.com \
--cc=shuah@kernel.org \
--cc=surenb@google.com \
--cc=vbabka@suse.cz \
/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