Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20220915142913.2213336-1-chao.p.peng@linux.intel.com> <20220915142913.2213336-2-chao.p.peng@linux.intel.com>
In-Reply-To: <20220915142913.2213336-2-chao.p.peng@linux.intel.com>
From:   Fuad Tabba <tabba@google.com>
Date:   Thu, 6 Oct 2022 09:50:28 +0100
Message-ID: <CA+EHjTz=o9M47frGCXgNJ8J5_Rn=YjzZR5uvCTxStw+GfGE5kg@mail.gmail.com>
Subject: Re: [PATCH v8 1/8] mm/memfd: Introduce userspace inaccessible memfd
To:     Chao Peng <chao.p.peng@linux.intel.com>
Cc:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
        linux-api@vger.kernel.org, linux-doc@vger.kernel.org,
        qemu-devel@nongnu.org, Paolo Bonzini <pbonzini@redhat.com>,
        Jonathan Corbet <corbet@lwn.net>,
        Sean Christopherson <seanjc@google.com>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Joerg Roedel <joro@8bytes.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
        Hugh Dickins <hughd@google.com>,
        Jeff Layton <jlayton@kernel.org>,
        "J . Bruce Fields" <bfields@fieldses.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Shuah Khan <shuah@kernel.org>, Mike Rapoport <rppt@kernel.org>,
        Steven Price <steven.price@arm.com>,
        "Maciej S . Szmigiero" <mail@maciej.szmigiero.name>,
        Vlastimil Babka <vbabka@suse.cz>,
        Vishal Annapurve <vannapurve@google.com>,
        Yu Zhang <yu.c.zhang@linux.intel.com>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        luto@kernel.org, jun.nakajima@intel.com, dave.hansen@intel.com,
        ak@linux.intel.com, david@redhat.com, aarcange@redhat.com,
        ddutile@redhat.com, dhildenb@redhat.com,
        Quentin Perret <qperret@google.com>,
        Michael Roth <michael.roth@amd.com>, mhocko@suse.com,
        Muchun Song <songmuchun@bytedance.com>, wei.w.wang@intel.com
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Hi,

<...>


> diff --git a/mm/memfd_inaccessible.c b/mm/memfd_inaccessible.c
> new file mode 100644
> index 000000000000..2d33cbdd9282
> --- /dev/null
> +++ b/mm/memfd_inaccessible.c

<...>

> +struct file *memfd_mkinaccessible(struct file *memfd)
> +{
> +       struct inaccessible_data *data;
> +       struct address_space *mapping;
> +       struct inode *inode;
> +       struct file *file;
> +
> +       data = kzalloc(sizeof(*data), GFP_KERNEL);
> +       if (!data)
> +               return ERR_PTR(-ENOMEM);
> +
> +       data->memfd = memfd;
> +       mutex_init(&data->lock);
> +       INIT_LIST_HEAD(&data->notifiers);
> +
> +       inode = alloc_anon_inode(inaccessible_mnt->mnt_sb);
> +       if (IS_ERR(inode)) {
> +               kfree(data);
> +               return ERR_CAST(inode);
> +       }
> +
> +       inode->i_mode |= S_IFREG;
> +       inode->i_op = &inaccessible_iops;
> +       inode->i_mapping->private_data = data;
> +
> +       file = alloc_file_pseudo(inode, inaccessible_mnt,
> +                                "[memfd:inaccessible]", O_RDWR,
> +                                &inaccessible_fops);
> +       if (IS_ERR(file)) {
> +               iput(inode);
> +               kfree(data);

I think this might be missing a return at this point.

> +       }
> +
> +       file->f_flags |= O_LARGEFILE;
> +
> +       mapping = memfd->f_mapping;
> +       mapping_set_unevictable(mapping);
> +       mapping_set_gfp_mask(mapping,
> +                            mapping_gfp_mask(mapping) & ~__GFP_MOVABLE);
> +
> +       return file;
> +}

Thanks,
/fuad


> +
> +void inaccessible_register_notifier(struct file *file,
> +                                   struct inaccessible_notifier *notifier)
> +{
> +       struct inaccessible_data *data = file->f_mapping->private_data;
> +
> +       mutex_lock(&data->lock);
> +       list_add(&notifier->list, &data->notifiers);
> +       mutex_unlock(&data->lock);
> +}
> +EXPORT_SYMBOL_GPL(inaccessible_register_notifier);
> +
> +void inaccessible_unregister_notifier(struct file *file,
> +                                     struct inaccessible_notifier *notifier)
> +{
> +       struct inaccessible_data *data = file->f_mapping->private_data;
> +
> +       mutex_lock(&data->lock);
> +       list_del(&notifier->list);
> +       mutex_unlock(&data->lock);
> +}
> +EXPORT_SYMBOL_GPL(inaccessible_unregister_notifier);
> +
> +int inaccessible_get_pfn(struct file *file, pgoff_t offset, pfn_t *pfn,
> +                        int *order)
> +{
> +       struct inaccessible_data *data = file->f_mapping->private_data;
> +       struct file *memfd = data->memfd;
> +       struct page *page;
> +       int ret;
> +
> +       ret = shmem_getpage(file_inode(memfd), offset, &page, SGP_WRITE);
> +       if (ret)
> +               return ret;
> +
> +       *pfn = page_to_pfn_t(page);
> +       *order = thp_order(compound_head(page));
> +       SetPageUptodate(page);
> +       unlock_page(page);
> +
> +       return 0;
> +}
> +EXPORT_SYMBOL_GPL(inaccessible_get_pfn);
> +
> +void inaccessible_put_pfn(struct file *file, pfn_t pfn)
> +{
> +       struct page *page = pfn_t_to_page(pfn);
> +
> +       if (WARN_ON_ONCE(!page))
> +               return;
> +
> +       put_page(page);
> +}
> +EXPORT_SYMBOL_GPL(inaccessible_put_pfn);
> --
> 2.25.1
>