All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mike Rapoport <rppt@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>,
	Andrei Vagin <avagin@google.com>,
	Axel Rasmussen <axelrasmussen@google.com>,
	Baolin Wang <baolin.wang@linux.alibaba.com>,
	David Hildenbrand <david@kernel.org>,
	Harry Yoo <harry.yoo@oracle.com>, Hugh Dickins <hughd@google.com>,
	James Houghton <jthoughton@google.com>,
	"Liam R. Howlett" <Liam.Howlett@oracle.com>,
	"Lorenzo Stoakes (Oracle)" <ljs@kernel.org>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	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>,
	kvm@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	linux-mm@kvack.org
Subject: [PATCH v3 03/15] userfaultfd: introduce mfill_establish_pmd() helper
Date: Mon, 30 Mar 2026 13:11:04 +0300	[thread overview]
Message-ID: <20260330101116.1117699-4-rppt@kernel.org> (raw)
In-Reply-To: <20260330101116.1117699-1-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 | 102 ++++++++++++++++++++++++-----------------------
 1 file changed, 52 insertions(+), 50 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index fa9622ec7279..291e5cfed431 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -157,6 +157,56 @@ 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_establish_pmd(struct mfill_state *state)
+{
+	struct mm_struct *dst_mm = state->ctx->mm;
+	pmd_t *dst_pmd, 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_leaf(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 +539,6 @@ 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 +771,6 @@ 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 +837,15 @@ 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_establish_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();
 
-- 
2.53.0


  parent reply	other threads:[~2026-03-30 10:11 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-30 10:11 [PATCH v3 00/15] mm, kvm: allow uffd support in guest_memfd Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 01/15] userfaultfd: introduce mfill_copy_folio_locked() helper Mike Rapoport
2026-03-31  3:33   ` Harry Yoo (Oracle)
2026-03-30 10:11 ` [PATCH v3 02/15] userfaultfd: introduce struct mfill_state Mike Rapoport
2026-03-31  7:03   ` Harry Yoo (Oracle)
2026-03-31 14:32     ` Mike Rapoport
2026-03-31 15:24       ` Harry Yoo (Oracle)
2026-04-01  7:36         ` Mike Rapoport
2026-04-01 17:37           ` Andrew Morton
2026-04-01 17:44             ` Andrew Morton
2026-04-02  4:36               ` Mike Rapoport
2026-03-30 10:11 ` Mike Rapoport [this message]
2026-03-31  7:50   ` [PATCH v3 03/15] userfaultfd: introduce mfill_establish_pmd() helper Harry Yoo (Oracle)
2026-03-30 10:11 ` [PATCH v3 04/15] userfaultfd: introduce mfill_get_vma() and mfill_put_vma() Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 05/15] userfaultfd: retry copying with locks dropped in mfill_atomic_pte_copy() Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 06/15] userfaultfd: move vma_can_userfault out of line Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 07/15] userfaultfd: introduce vm_uffd_ops Mike Rapoport
2026-03-30 16:58   ` Matthew Wilcox
2026-03-31 11:42     ` Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 08/15] shmem, userfaultfd: use a VMA callback to handle UFFDIO_CONTINUE Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 09/15] userfaultfd: introduce vm_uffd_ops->alloc_folio() Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 10/15] shmem, userfaultfd: implement shmem uffd operations using vm_uffd_ops Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 11/15] userfaultfd: mfill_atomic(): remove retry logic Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 12/15] mm: generalize handling of userfaults in __do_fault() Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 13/15] KVM: guest_memfd: implement userfaultfd operations Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 14/15] KVM: selftests: test userfaultfd minor for guest_memfd Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 15/15] KVM: selftests: test userfaultfd missing " Mike Rapoport
2026-03-30 19:54 ` [PATCH v3 00/15] mm, kvm: allow uffd support in guest_memfd Andrew Morton

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=20260330101116.1117699-4-rppt@kernel.org \
    --to=rppt@kernel.org \
    --cc=Liam.Howlett@oracle.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=avagin@google.com \
    --cc=axelrasmussen@google.com \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=david@kernel.org \
    --cc=harry.yoo@oracle.com \
    --cc=hughd@google.com \
    --cc=jthoughton@google.com \
    --cc=kalyazin@amazon.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --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 \
    --cc=willy@infradead.org \
    /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.