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 08/15] shmem, userfaultfd: use a VMA callback to handle UFFDIO_CONTINUE
Date: Mon, 30 Mar 2026 13:11:09 +0300	[thread overview]
Message-ID: <20260330101116.1117699-9-rppt@kernel.org> (raw)
In-Reply-To: <20260330101116.1117699-1-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>
Reviewed-by: James Houghton <jthoughton@google.com>
---
 include/linux/userfaultfd_k.h |  7 +++++++
 mm/shmem.c                    | 15 ++++++++++++++-
 mm/userfaultfd.c              | 34 ++++++++++++++++++----------------
 3 files changed, 39 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 f2a25805b9bf..7bd887b64f62 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3295,13 +3295,26 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd,
 	return ret;
 }
 
+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)
 {
 	return true;
 }
 
 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 /* CONFIG_USERFAULTFD */
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index e3024a39c19d..832dbdde5868 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -191,6 +191,7 @@ 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;
 
 	/*
@@ -232,10 +233,12 @@ static int mfill_get_vma(struct mfill_state *state)
 	if (is_vm_hugetlb_page(dst_vma))
 		return 0;
 
-	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;
 
 	return 0;
@@ -575,6 +578,7 @@ 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);
@@ -584,17 +588,16 @@ 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);
-	/* 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 (!ops) {
+		VM_WARN_ONCE(1, "UFFDIO_CONTINUE for unsupported VMA");
+		return -EOPNOTSUPP;
 	}
 
+	folio = ops->get_folio_noalloc(inode, pgoff);
+	/* Our caller expects us to return -EFAULT if we failed to find folio */
+	if (IS_ERR_OR_NULL(folio))
+		return -EFAULT;
+
 	page = folio_file_page(folio, pgoff);
 	if (PageHWPoison(page)) {
 		ret = -EIO;
@@ -607,13 +610,12 @@ 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. */
-- 
2.53.0


  parent reply	other threads:[~2026-03-30 10:12 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 ` [PATCH v3 03/15] userfaultfd: introduce mfill_establish_pmd() helper Mike Rapoport
2026-03-31  7:50   ` 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 ` Mike Rapoport [this message]
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=20260330101116.1117699-9-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.