From nobody Sun Feb 8 14:10:32 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id C1D7136CDFD; Tue, 27 Jan 2026 19:30:37 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1769542237; cv=none; b=Y4G6clJxAgZkUUx+ANmOJreklJ9s7dIegsBKmKr8yZnhLNuqmGEBh4WoQklimPAuvMPXgsrcV4imYyMWY+ixePW9O768D3y6bZcG6Wdg8xCNp5RH8Kh0WqyZNRYrrWsum+IcFGDSkrGzSDDkARWkQbZLSDCRUjl25OdZzVaT/1E= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1769542237; c=relaxed/simple; bh=dEjTs4g7Ldzs6VFuT/arDcgalMO2GCfU8tcBpfF3p8M=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=AEbqZ3Xyg07cLcBUh8o0L7gJ+NeHZo0KWNOWDxG6rxC2nsf4XzEYiIu4xy55yeWE1PRfjbQ4xOMgx1sS6N+nxpaxQ9Oojv/CfsUk+kcSjY3brPrF5lfQSBbrBycMpZmMA1YU/+nTLYK8EOG7j8BrwGv6LskQBvM/yyXRflgot/Y= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=ZIFX02kq; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="ZIFX02kq" Received: by smtp.kernel.org (Postfix) with ESMTPSA id E9613C19422; Tue, 27 Jan 2026 19:30:31 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1769542237; bh=dEjTs4g7Ldzs6VFuT/arDcgalMO2GCfU8tcBpfF3p8M=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=ZIFX02kq/eb3tdlUyK3+ux/FsIlLOYCqnviY6Ie7P/JoMu0xpvH0YAzid+JPgh/wf ZeqTvHI90vv1ymfJ5mKlTSi7ENxzGNs0eiDNpe7SKCKi9YBeblG/mupcmyOBTb5lfi Du+zzNcONbAQnPXllF3puU5zkWcn3oJA5C6i24cg0xb6cyKMIBRz1sxJDbetb+GomZ ebsMHkfKrgYOtfle3aDrqX/AIg7yiUZwWzJrbevM5HsVJ7crsBY9sWOs1mGJLRC+4t QtQE0BT8W2UM4lZNTM8NJDoKhmUDX5AtUDIRlY1FGik8uzBb19PN6zjwHOtAQvIeoq e5OQTmT8pAcFQ== From: Mike Rapoport To: linux-mm@kvack.org Cc: Andrea Arcangeli , Andrew Morton , Axel Rasmussen , Baolin Wang , David Hildenbrand , Hugh Dickins , James Houghton , "Liam R. Howlett" , Lorenzo Stoakes , Michal Hocko , Mike Rapoport , Muchun Song , Nikita Kalyazin , Oscar Salvador , Paolo Bonzini , Peter Xu , Sean Christopherson , Shuah Khan , Suren Baghdasaryan , Vlastimil Babka , 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 Message-ID: <20260127192936.1250096-9-rppt@kernel.org> X-Mailer: git-send-email 2.51.0 In-Reply-To: <20260127192936.1250096-1-rppt@kernel.org> References: <20260127192936.1250096-1-rppt@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: "Mike Rapoport (Microsoft)" 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) --- 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); }; =20 /* 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 =3D { }; =20 #ifdef CONFIG_USERFAULTFD +static struct folio *shmem_get_folio_noalloc(struct inode *inode, pgoff_t = pgoff) +{ + struct folio *folio; + int err; + + err =3D 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) } =20 static const struct vm_uffd_ops shmem_uffd_ops =3D { - .can_userfault =3D shmem_can_userfault, + .can_userfault =3D shmem_can_userfault, + .get_folio_noalloc =3D shmem_get_folio_noalloc, }; #endif =20 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 =3D state->ctx; uffd_flags_t flags =3D state->flags; struct vm_area_struct *dst_vma; + const struct vm_uffd_ops *ops; int err; =20 /* @@ -228,10 +229,12 @@ static int mfill_get_vma(struct mfill_state *state) if (is_vm_hugetlb_page(dst_vma)) goto out; =20 - if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) + ops =3D 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; =20 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 =3D state->vma; + const struct vm_uffd_ops *ops =3D vma_uffd_ops(dst_vma); unsigned long dst_addr =3D state->dst_addr; pgoff_t pgoff =3D linear_page_index(dst_vma, dst_addr); struct inode *inode =3D file_inode(dst_vma->vm_file); @@ -577,16 +581,13 @@ static int mfill_atomic_pte_continue(struct mfill_sta= te *state) struct page *page; int ret; =20 - ret =3D shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC); + if (!ops) + return -EOPNOTSUPP; + + folio =3D ops->get_folio_noalloc(inode, pgoff); /* Our caller expects us to return -EFAULT if we failed to find folio */ - if (ret =3D=3D -ENOENT) - ret =3D -EFAULT; - if (ret) - goto out; - if (!folio) { - ret =3D -EFAULT; - goto out; - } + if (IS_ERR_OR_NULL(folio)) + return -EFAULT; =20 page =3D folio_file_page(folio, pgoff); if (PageHWPoison(page)) { @@ -600,13 +601,12 @@ static int mfill_atomic_pte_continue(struct mfill_sta= te *state) goto out_release; =20 folio_unlock(folio); - ret =3D 0; -out: - return ret; + return 0; + out_release: folio_unlock(folio); folio_put(folio); - goto out; + return ret; } =20 /* Handles UFFDIO_POISON for all non-hugetlb VMAs. */ --=20 2.51.0