From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755631AbbCERUA (ORCPT ); Thu, 5 Mar 2015 12:20:00 -0500 Received: from mx1.redhat.com ([209.132.183.28]:60885 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754666AbbCERTW (ORCPT ); Thu, 5 Mar 2015 12:19:22 -0500 From: Andrea Arcangeli To: qemu-devel@nongnu.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-api@vger.kernel.org, Android Kernel Team Cc: "Kirill A. Shutemov" , Pavel Emelyanov , Sanidhya Kashyap , zhang.zhanghailiang@huawei.com, Linus Torvalds , Andres Lagar-Cavilla , Dave Hansen , Paolo Bonzini , Rik van Riel , Mel Gorman , Andy Lutomirski , Andrew Morton , Sasha Levin , Hugh Dickins , Peter Feiner , "Dr. David Alan Gilbert" , Christopher Covington , Johannes Weiner , Robert Love , Dmitry Adamushko , Neil Brown , Mike Hommey , Taras Glek , Jan Kara , KOSAKI Motohiro , Michel Lespinasse , Minchan Kim , Keith Packard , "Huangpeng (Peter)" , Anthony Liguori , Stefan Hajnoczi , Wenchao Xia , Andrew Jones , Juan Quintela Subject: [PATCH 15/21] userfaultfd: UFFDIO_COPY and UFFDIO_ZEROPAGE Date: Thu, 5 Mar 2015 18:17:58 +0100 Message-Id: <1425575884-2574-16-git-send-email-aarcange@redhat.com> In-Reply-To: <1425575884-2574-1-git-send-email-aarcange@redhat.com> References: <1425575884-2574-1-git-send-email-aarcange@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org These two ioctl allows to either atomically copy or to map zeropages into the virtual address space. This is used by the thread that opened the userfaultfd to resolve the userfaults. Signed-off-by: Andrea Arcangeli --- fs/userfaultfd.c | 100 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 100 insertions(+) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 6b31967..6230f22 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -798,6 +798,100 @@ out: return ret; } +static int userfaultfd_copy(struct userfaultfd_ctx *ctx, + unsigned long arg) +{ + __s64 ret; + struct uffdio_copy uffdio_copy; + struct uffdio_copy __user *user_uffdio_copy; + struct userfaultfd_wake_range range; + + user_uffdio_copy = (struct uffdio_copy __user *) arg; + + ret = -EFAULT; + if (copy_from_user(&uffdio_copy, user_uffdio_copy, + /* don't copy "copy" and "wake" last field */ + sizeof(uffdio_copy)-sizeof(__s64)*2)) + goto out; + + ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); + if (ret) + goto out; + /* + * double check for wraparound just in case. copy_from_user() + * will later check uffdio_copy.src + uffdio_copy.len to fit + * in the userland range. + */ + ret = -EINVAL; + if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src) + goto out; + if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE) + goto out; + + ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, + uffdio_copy.len); + if (unlikely(put_user(ret, &user_uffdio_copy->copy))) + return -EFAULT; + if (ret < 0) + goto out; + BUG_ON(!ret); + /* len == 0 would wake all */ + range.len = ret; + if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) { + range.start = uffdio_copy.dst; + ret = wake_userfault(ctx, &range); + if (unlikely(put_user(ret, &user_uffdio_copy->wake))) + return -EFAULT; + } + ret = range.len == uffdio_copy.len ? 0 : -EAGAIN; +out: + return ret; +} + +static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, + unsigned long arg) +{ + __s64 ret; + struct uffdio_zeropage uffdio_zeropage; + struct uffdio_zeropage __user *user_uffdio_zeropage; + struct userfaultfd_wake_range range; + + user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; + + ret = -EFAULT; + if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, + /* don't copy "zeropage" and "wake" last field */ + sizeof(uffdio_zeropage)-sizeof(__s64)*2)) + goto out; + + ret = validate_range(ctx->mm, uffdio_zeropage.range.start, + uffdio_zeropage.range.len); + if (ret) + goto out; + ret = -EINVAL; + if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE) + goto out; + + ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start, + uffdio_zeropage.range.len); + if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) + return -EFAULT; + if (ret < 0) + goto out; + /* len == 0 would wake all */ + BUG_ON(!ret); + range.len = ret; + if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) { + range.start = uffdio_zeropage.range.start; + ret = wake_userfault(ctx, &range); + if (unlikely(put_user(ret, &user_uffdio_zeropage->wake))) + return -EFAULT; + } + ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN; +out: + return ret; +} + /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API @@ -855,6 +949,12 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd, case UFFDIO_WAKE: ret = userfaultfd_wake(ctx, arg); break; + case UFFDIO_COPY: + ret = userfaultfd_copy(ctx, arg); + break; + case UFFDIO_ZEROPAGE: + ret = userfaultfd_zeropage(ctx, arg); + break; } return ret; }