linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
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 08/17] userfaultfd, shmem: use a VMA callback to handle UFFDIO_CONTINUE
Date: Tue, 27 Jan 2026 21:29:27 +0200	[thread overview]
Message-ID: <20260127192936.1250096-9-rppt@kernel.org> (raw)
In-Reply-To: <20260127192936.1250096-1-rppt@kernel.org>

From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

When userspace resolves a page fault in a shmem VMA with UFFDIO_CONTINUE
it needs to get a folio that already exists in the pagecache backing
that VMA.

Instead of using shmem_get_folio() for that, add a get_folio_noalloc()
method to 'struct vm_uffd_ops' that will return a folio if it exists in
the VMA's pagecache at given pgoff.

Implement get_folio_noalloc() method for shmem and slightly refactor
userfaultfd's mfill_get_vma() and mfill_atomic_pte_continue() to support
this new API.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 include/linux/userfaultfd_k.h |  7 +++++++
 mm/shmem.c                    | 15 ++++++++++++++-
 mm/userfaultfd.c              | 32 ++++++++++++++++----------------
 3 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 56e85ab166c7..66dfc3c164e6 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -84,6 +84,13 @@ extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 struct vm_uffd_ops {
 	/* Checks if a VMA can support userfaultfd */
 	bool (*can_userfault)(struct vm_area_struct *vma, vm_flags_t vm_flags);
+	/*
+	 * Called to resolve UFFDIO_CONTINUE request.
+	 * Should return the folio found at pgoff in the VMA's pagecache if it
+	 * exists or ERR_PTR otherwise.
+	 * The returned folio is locked and with reference held.
+	 */
+	struct folio *(*get_folio_noalloc)(struct inode *inode, pgoff_t pgoff);
 };
 
 /* A combined operation mode + behavior flags. */
diff --git a/mm/shmem.c b/mm/shmem.c
index 9b82cda271c4..87cd8d2fdb97 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -5291,6 +5291,18 @@ static const struct super_operations shmem_ops = {
 };
 
 #ifdef CONFIG_USERFAULTFD
+static struct folio *shmem_get_folio_noalloc(struct inode *inode, pgoff_t pgoff)
+{
+	struct folio *folio;
+	int err;
+
+	err = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC);
+	if (err)
+		return ERR_PTR(err);
+
+	return folio;
+}
+
 static bool shmem_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
 {
 	/*
@@ -5303,7 +5315,8 @@ static bool shmem_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
 }
 
 static const struct vm_uffd_ops shmem_uffd_ops = {
-	.can_userfault	= shmem_can_userfault,
+	.can_userfault		= shmem_can_userfault,
+	.get_folio_noalloc	= shmem_get_folio_noalloc,
 };
 #endif
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index d035f5e17f07..f0e6336015f1 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -188,6 +188,7 @@ static int mfill_get_vma(struct mfill_state *state)
 	struct userfaultfd_ctx *ctx = state->ctx;
 	uffd_flags_t flags = state->flags;
 	struct vm_area_struct *dst_vma;
+	const struct vm_uffd_ops *ops;
 	int err;
 
 	/*
@@ -228,10 +229,12 @@ static int mfill_get_vma(struct mfill_state *state)
 	if (is_vm_hugetlb_page(dst_vma))
 		goto out;
 
-	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
+	ops = vma_uffd_ops(dst_vma);
+	if (!ops)
 		goto out_unlock;
-	if (!vma_is_shmem(dst_vma) &&
-	    uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
+
+	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE) &&
+	    !ops->get_folio_noalloc)
 		goto out_unlock;
 
 out:
@@ -568,6 +571,7 @@ static int mfill_atomic_pte_zeropage(struct mfill_state *state)
 static int mfill_atomic_pte_continue(struct mfill_state *state)
 {
 	struct vm_area_struct *dst_vma = state->vma;
+	const struct vm_uffd_ops *ops = vma_uffd_ops(dst_vma);
 	unsigned long dst_addr = state->dst_addr;
 	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
 	struct inode *inode = file_inode(dst_vma->vm_file);
@@ -577,16 +581,13 @@ static int mfill_atomic_pte_continue(struct mfill_state *state)
 	struct page *page;
 	int ret;
 
-	ret = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC);
+	if (!ops)
+		return -EOPNOTSUPP;
+
+	folio = ops->get_folio_noalloc(inode, pgoff);
 	/* Our caller expects us to return -EFAULT if we failed to find folio */
-	if (ret == -ENOENT)
-		ret = -EFAULT;
-	if (ret)
-		goto out;
-	if (!folio) {
-		ret = -EFAULT;
-		goto out;
-	}
+	if (IS_ERR_OR_NULL(folio))
+		return -EFAULT;
 
 	page = folio_file_page(folio, pgoff);
 	if (PageHWPoison(page)) {
@@ -600,13 +601,12 @@ static int mfill_atomic_pte_continue(struct mfill_state *state)
 		goto out_release;
 
 	folio_unlock(folio);
-	ret = 0;
-out:
-	return ret;
+	return 0;
+
 out_release:
 	folio_unlock(folio);
 	folio_put(folio);
-	goto out;
+	return ret;
 }
 
 /* Handles UFFDIO_POISON for all non-hugetlb VMAs. */
-- 
2.51.0



  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 ` [PATCH RFC 03/17] userfaultfd: introduce mfill_get_pmd() helper Mike Rapoport
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 ` Mike Rapoport [this message]
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=20260127192936.1250096-9-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