[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20260127192936.1250096-4-rppt@kernel.org>
Date: Tue, 27 Jan 2026 21:29:22 +0200
From: Mike Rapoport <rppt@...nel.org>
To: linux-mm@...ck.org
Cc: Andrea Arcangeli <aarcange@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Axel Rasmussen <axelrasmussen@...gle.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>,
David Hildenbrand <david@...hat.com>,
Hugh Dickins <hughd@...gle.com>,
James Houghton <jthoughton@...gle.com>,
"Liam R. Howlett" <Liam.Howlett@...cle.com>,
Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
Michal Hocko <mhocko@...e.com>,
Mike Rapoport <rppt@...nel.org>,
Muchun Song <muchun.song@...ux.dev>,
Nikita Kalyazin <kalyazin@...zon.com>,
Oscar Salvador <osalvador@...e.de>,
Paolo Bonzini <pbonzini@...hat.com>,
Peter Xu <peterx@...hat.com>,
Sean Christopherson <seanjc@...gle.com>,
Shuah Khan <shuah@...nel.org>,
Suren Baghdasaryan <surenb@...gle.com>,
Vlastimil Babka <vbabka@...e.cz>,
linux-kernel@...r.kernel.org,
kvm@...r.kernel.org,
linux-kselftest@...r.kernel.org
Subject: [PATCH RFC 03/17] userfaultfd: introduce mfill_get_pmd() helper.
From: "Mike Rapoport (Microsoft)" <rppt@...nel.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@...nel.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
Powered by blists - more mailing lists