From nobody Mon Apr 6 11:53:32 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 8EDA13BADA1; Mon, 30 Mar 2026 10:12:27 +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=1774865547; cv=none; b=fjrUPvuc1zI9asqETIFOSbVZDTYw2XOQ/UC3UcekgNahCey7qnupBOVxEBSTmuWDR/9UQsXyKHoD7u3GLYzSkzgtxhAJBcVnsLzkVbZH2KrTB2t9f8i93XrUrT3+wjesBha2bSvvAgSn5DpO6g/79nQSk0YDiYTnGGhPRzOF0eM= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774865547; c=relaxed/simple; bh=Ye6Z7TrGAOPgV52cgsTw8VTKwOK2VRWtWU0AJXFZvYo=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=sTjSykPYgoTsLe5VHHO862a6he9k3emV+Iy1V2xh1pUn+6S8NvPXYlCh1oBD4H74rohpJnmQLWUTn0/+hX6L5vBzC6fNkrHnR0EjioFiomBJyamHSGSTyCfA3f8FFnQvqlSGKb6lTcs58ZIHdVVqOnf78IsS5nWWD73+d3T55zg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=Lu59ZX2u; 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="Lu59ZX2u" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 3C476C4CEF7; Mon, 30 Mar 2026 10:12:21 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1774865547; bh=Ye6Z7TrGAOPgV52cgsTw8VTKwOK2VRWtWU0AJXFZvYo=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=Lu59ZX2uIJSAIeywrbsygWg/5qzBa3IGe/RNVZ7WYLUz4Xw5N5r0bIAABe6VFbP8O NtvKLDmvOZTz7qbBMsAPf/3U5xw7mvmT14XtWNEFof/m2zDo3fr2yPWC1tOqk9f9+y ELzQHIM5cBjVZSVPFUkiFgzGXGWXPBRk6Ig9Kok7voNr2Q+48CH2wFCbk9Ppf7Odsp 4mBV6rOhbzSAfBYSXV9ppyddFAaRhWFeGAPj8AKJP6mU3btMnqVtJV9pHMdnAitQVX LE6JlgEMOx98MNXXHElnfiP4Ss2smtFP/c27xZsZopXraSOUFqIynaqSs07w2x3gdX ZFbtPlVAcNraQ== From: Mike Rapoport To: Andrew Morton Cc: Andrea Arcangeli , Andrei Vagin , Axel Rasmussen , Baolin Wang , David Hildenbrand , Harry Yoo , Hugh Dickins , James Houghton , "Liam R. Howlett" , "Lorenzo Stoakes (Oracle)" , "Matthew Wilcox (Oracle)" , Michal Hocko , Mike Rapoport , Muchun Song , Nikita Kalyazin , Oscar Salvador , Paolo Bonzini , Peter Xu , Sean Christopherson , Shuah Khan , Suren Baghdasaryan , Vlastimil Babka , 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 09/15] userfaultfd: introduce vm_uffd_ops->alloc_folio() Date: Mon, 30 Mar 2026 13:11:10 +0300 Message-ID: <20260330101116.1117699-10-rppt@kernel.org> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260330101116.1117699-1-rppt@kernel.org> References: <20260330101116.1117699-1-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)" and use it to refactor mfill_atomic_pte_zeroed_folio() and mfill_atomic_pte_copy(). mfill_atomic_pte_zeroed_folio() and mfill_atomic_pte_copy() perform almost identical actions: * allocate a folio * update folio contents (either copy from userspace of fill with zeros) * update page tables with the new folio Split a __mfill_atomic_pte() helper that handles both cases and uses newly introduced vm_uffd_ops->alloc_folio() to allocate the folio. Pass the ops structure from the callers to __mfill_atomic_pte() to later allow using anon_uffd_ops for MAP_PRIVATE mappings of file-backed VMAs. Note, that the new ops method is called alloc_folio() rather than folio_alloc() to avoid clash with alloc_tag macro folio_alloc(). Signed-off-by: Mike Rapoport (Microsoft) Reviewed-by: James Houghton --- include/linux/userfaultfd_k.h | 6 +++ mm/userfaultfd.c | 92 ++++++++++++++++++----------------- 2 files changed, 54 insertions(+), 44 deletions(-) diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 66dfc3c164e6..55a67421de0a 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -91,6 +91,12 @@ struct vm_uffd_ops { * The returned folio is locked and with reference held. */ struct folio *(*get_folio_noalloc)(struct inode *inode, pgoff_t pgoff); + /* + * Called during resolution of UFFDIO_COPY request. + * Should allocate and return a folio or NULL if allocation fails. + */ + struct folio *(*alloc_folio)(struct vm_area_struct *vma, + unsigned long addr); }; =20 /* A combined operation mode + behavior flags. */ diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 832dbdde5868..771a1e607c4c 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -42,8 +42,26 @@ static bool anon_can_userfault(struct vm_area_struct *vm= a, vm_flags_t vm_flags) return true; } =20 +static struct folio *anon_alloc_folio(struct vm_area_struct *vma, + unsigned long addr) +{ + struct folio *folio =3D vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, + addr); + + if (!folio) + return NULL; + + if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL)) { + folio_put(folio); + return NULL; + } + + return folio; +} + static const struct vm_uffd_ops anon_uffd_ops =3D { .can_userfault =3D anon_can_userfault, + .alloc_folio =3D anon_alloc_folio, }; =20 static const struct vm_uffd_ops *vma_uffd_ops(struct vm_area_struct *vma) @@ -456,7 +474,8 @@ static int mfill_copy_folio_retry(struct mfill_state *s= tate, struct folio *folio return 0; } =20 -static int mfill_atomic_pte_copy(struct mfill_state *state) +static int __mfill_atomic_pte(struct mfill_state *state, + const struct vm_uffd_ops *ops) { unsigned long dst_addr =3D state->dst_addr; unsigned long src_addr =3D state->src_addr; @@ -464,16 +483,12 @@ static int mfill_atomic_pte_copy(struct mfill_state *= state) struct folio *folio; int ret; =20 - folio =3D vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, state->vma, dst_addr); + folio =3D ops->alloc_folio(state->vma, state->dst_addr); if (!folio) return -ENOMEM; =20 - ret =3D -ENOMEM; - if (mem_cgroup_charge(folio, state->vma->vm_mm, GFP_KERNEL)) - goto out_release; - - ret =3D mfill_copy_folio_locked(folio, src_addr); - if (unlikely(ret)) { + if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) { + ret =3D mfill_copy_folio_locked(folio, src_addr); /* * Fallback to copy_from_user outside mmap_lock. * If retry is successful, mfill_copy_folio_locked() returns @@ -481,9 +496,15 @@ static int mfill_atomic_pte_copy(struct mfill_state *s= tate) * If there was an error, we must mfill_put_vma() anyway and it * will take care of unlocking if needed. */ - ret =3D mfill_copy_folio_retry(state, folio); - if (ret) - goto out_release; + if (unlikely(ret)) { + ret =3D mfill_copy_folio_retry(state, folio); + if (ret) + goto err_folio_put; + } + } else if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) { + clear_user_highpage(&folio->page, state->dst_addr); + } else { + VM_WARN_ONCE(1, "Unknown UFFDIO operation, flags: %x", flags); } =20 /* @@ -496,47 +517,30 @@ static int mfill_atomic_pte_copy(struct mfill_state *= state) ret =3D mfill_atomic_install_pte(state->pmd, state->vma, dst_addr, &folio->page, true, flags); if (ret) - goto out_release; -out: - return ret; -out_release: + goto err_folio_put; + + return 0; + +err_folio_put: + folio_put(folio); /* Don't return -ENOENT so that our caller won't retry */ if (ret =3D=3D -ENOENT) ret =3D -EFAULT; - folio_put(folio); - goto out; + return ret; } =20 -static int mfill_atomic_pte_zeroed_folio(pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr) +static int mfill_atomic_pte_copy(struct mfill_state *state) { - struct folio *folio; - int ret =3D -ENOMEM; - - folio =3D vma_alloc_zeroed_movable_folio(dst_vma, dst_addr); - if (!folio) - return ret; - - if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL)) - goto out_put; + const struct vm_uffd_ops *ops =3D vma_uffd_ops(state->vma); =20 - /* - * The memory barrier inside __folio_mark_uptodate makes sure that - * zeroing out the folio become visible before mapping the page - * using set_pte_at(). See do_anonymous_page(). - */ - __folio_mark_uptodate(folio); + return __mfill_atomic_pte(state, ops); +} =20 - ret =3D mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, - &folio->page, true, 0); - if (ret) - goto out_put; +static int mfill_atomic_pte_zeroed_folio(struct mfill_state *state) +{ + const struct vm_uffd_ops *ops =3D vma_uffd_ops(state->vma); =20 - return 0; -out_put: - folio_put(folio); - return ret; + return __mfill_atomic_pte(state, ops); } =20 static int mfill_atomic_pte_zeropage(struct mfill_state *state) @@ -549,7 +553,7 @@ static int mfill_atomic_pte_zeropage(struct mfill_state= *state) int ret; =20 if (mm_forbids_zeropage(dst_vma->vm_mm)) - return mfill_atomic_pte_zeroed_folio(dst_pmd, dst_vma, dst_addr); + return mfill_atomic_pte_zeroed_folio(state); =20 _dst_pte =3D pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); --=20 2.53.0