From mboxrd@z Thu Jan 1 00:00:00 1970 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 E34AC3BADA1; Mon, 30 Mar 2026 10:12:20 +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=1774865541; cv=none; b=ILTQ2VShVeCkQY92UAEByo5GGiK+t4rBa8Q2dhTmvMvHbPevPuDHa/3YB+l4ir1dne8SVGFkS5qTkv7nrXs/ZJdQcW+4LnL1VCr7hdKg3meYtYYjBQnXlnqmM3laKDS5jpftfSv+f8vSw7elhbkhbmeHfIILUmqZLh7imUhyki4= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774865541; c=relaxed/simple; bh=lxXvlQh8xQ0EBf3to4Jw9wikE7NXPrSIjYbQ7Uoyt4w=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=LW1n0IAs59/3Y1sCm7sdqQGeM1gcHsfCAsFEqqUP/88ezMGPr4HpAdAT5QUZUb0YtcB74kfeB1IZKjziPNEynHIJzSJEL0y/e9WKK9RoqG+xzLShHZ4tyc9jEL+WNCRD6+dplr0thY8E22+dlF8zJGWdWksQRTWZLWA7Hbat/Y0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=aS25XSKy; 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="aS25XSKy" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 7DF22C4CEF7; Mon, 30 Mar 2026 10:12:14 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1774865540; bh=lxXvlQh8xQ0EBf3to4Jw9wikE7NXPrSIjYbQ7Uoyt4w=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=aS25XSKyFpLRnOPX75HHRFZnJUfjixxOpkn2kTiFc06LCUfoedxT59el843/Qqbu/ hdj96YV/8MKR8RoOHQO3cSOxL6i1h6/pKmv6pMaaVH09KWfD5LC5NpJMuxZyRhHNFv OPlzbePKfMxLK71YRJjPAYBlBZNj3ztqyu7ADE3u4UK3sB8wOqPG1x81pa84IfP5ck FAIYO65JKH8d2o209unwereERqUUjHXzSUydWn7nIIsEDVGMqCpbCsVMbTOPNpwHpk HHJWD57DRZBfCNIdGHt99Pagc9jwhjvb0DWX4TxU51aQTEKG4dga61EpmCXGcZTjfO ovs80lRwcCs4g== 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 08/15] shmem, userfaultfd: use a VMA callback to handle UFFDIO_CONTINUE Date: Mon, 30 Mar 2026 13:11:09 +0300 Message-ID: <20260330101116.1117699-9-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: kvm@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit 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) Reviewed-by: James Houghton --- 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