From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754221Ab1LLVx3 (ORCPT ); Mon, 12 Dec 2011 16:53:29 -0500 Received: from mail.linuxfoundation.org ([140.211.169.12]:56772 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751549Ab1LLVxZ (ORCPT ); Mon, 12 Dec 2011 16:53:25 -0500 Date: Mon, 12 Dec 2011 13:53:23 -0800 From: Andrew Morton To: Cyrill Gorcunov Cc: Kees Cook , LKML , Tejun Heo , Andrew Vagin , Serge Hallyn , Vasiliy Kulikov , KAMEZAWA Hiroyuki , Alexey Dobriyan , "Eric W. Biederman" , Pavel Emelyanov , Michael Kerrisk Subject: Re: [patch 3/3] [PATCH] prctl: Add PR_SET_MM codes to set up mm_struct entires v3 Message-Id: <20111212135323.2f757d9b.akpm@linux-foundation.org> In-Reply-To: <20111212205114.GR2199@moon> References: <20111212200642.836001668@openvz.org> <20111212201715.244414996@openvz.org> <20111212205114.GR2199@moon> X-Mailer: Sylpheed 3.0.2 (GTK+ 2.20.1; x86_64-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 13 Dec 2011 00:51:14 +0400 Cyrill Gorcunov wrote: > > When we restore a task we need to set up text, data and data > heap sizes from userspace to the values a task had at > checkpoint time. This patch adds auxilary prctl codes for that. > > While most of them have a statistical nature (their values > are involved into calculation of /proc//statm output) > the start_brk and brk values are used to compute an allowed > size of program data segment expansion. Which means an arbitrary > changes of this values might be dangerous operation. So to restrict > access the following requirements applied to prctl calls: > > - The process has to have CAP_SYS_ADMIN capability granted. > - For all opcodes except start_brk/brk members an appropriate > VMA area must exist and should fit certain VMA flags, > such as: > - code segment must be executable but not writable; > - data segment must not be executable. > > start_brk/brk values must not intersect with data segment > and must not exceed RLIMIT_DATA resource limit. > > Still the main guard is CAP_SYS_ADMIN capability check. > > Note the kernel should be compiled with CONFIG_CHECKPOINT_RESTORE > support otherwise these prctl calls will return -EINVAL. > > ... > > +#ifdef CONFIG_CHECKPOINT_RESTORE > +static int prctl_set_mm(int opt, unsigned long addr, > + unsigned long arg4, unsigned long arg5) > +{ > + unsigned long rlim = rlimit(RLIMIT_DATA); > + unsigned long vm_req_flags; > + unsigned long vm_bad_flags; > + struct vm_area_struct *vma; > + int error = 0; > + > + if (arg4 | arg5) > + return -EINVAL; > + > + if (!capable(CAP_SYS_ADMIN)) > + return -EPERM; > + > + if (addr >= TASK_SIZE) > + return -EINVAL; > + > + down_read(¤t->mm->mmap_sem); This may not be true of all compiler versions, but when I cache current->mm in a local, the code size is reduced rather a lot: akpm:/usr/src/25> size kernel/sys.o text data bss dec hex filename 22685 14376 7616 44677 ae85 kernel/sys.o 22489 14376 7616 44481 adc1 kernel/sys.o diff -puN kernel/sys.c~c-r-prctl-add-pr_set_mm-codes-to-set-up-mm_struct-entries-fix kernel/sys.c --- a/kernel/sys.c~c-r-prctl-add-pr_set_mm-codes-to-set-up-mm_struct-entries-fix +++ a/kernel/sys.c @@ -1701,6 +1701,7 @@ static int prctl_set_mm(int opt, unsigne unsigned long vm_bad_flags; struct vm_area_struct *vma; int error = 0; + struct mm_struct *mm = current->mm; if (arg4 | arg5) return -EINVAL; @@ -1711,8 +1712,8 @@ static int prctl_set_mm(int opt, unsigne if (addr >= TASK_SIZE) return -EINVAL; - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, addr); + down_read(&mm->mmap_sem); + vma = find_vma(mm, addr); if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) { /* It must be existing VMA */ @@ -1732,9 +1733,9 @@ static int prctl_set_mm(int opt, unsigne goto out; if (opt == PR_SET_MM_START_CODE) - current->mm->start_code = addr; + mm->start_code = addr; else - current->mm->end_code = addr; + mm->end_code = addr; break; case PR_SET_MM_START_DATA: @@ -1747,9 +1748,9 @@ static int prctl_set_mm(int opt, unsigne goto out; if (opt == PR_SET_MM_START_DATA) - current->mm->start_data = addr; + mm->start_data = addr; else - current->mm->end_data = addr; + mm->end_data = addr; break; case PR_SET_MM_START_STACK: @@ -1762,31 +1763,31 @@ static int prctl_set_mm(int opt, unsigne if ((vma->vm_flags & vm_req_flags) != vm_req_flags) goto out; - current->mm->start_stack = addr; + mm->start_stack = addr; break; case PR_SET_MM_START_BRK: - if (addr <= current->mm->end_data) + if (addr <= mm->end_data) goto out; if (rlim < RLIM_INFINITY && - (current->mm->brk - addr) + - (current->mm->end_data - current->mm->start_data) > rlim) + (mm->brk - addr) + + (mm->end_data - mm->start_data) > rlim) goto out; - current->mm->start_brk = addr; + mm->start_brk = addr; break; case PR_SET_MM_BRK: - if (addr <= current->mm->end_data) + if (addr <= mm->end_data) goto out; if (rlim < RLIM_INFINITY && - (addr - current->mm->start_brk) + - (current->mm->end_data - current->mm->start_data) > rlim) + (addr - mm->start_brk) + + (mm->end_data - mm->start_data) > rlim) goto out; - current->mm->brk = addr; + mm->brk = addr; break; default: @@ -1797,7 +1798,7 @@ static int prctl_set_mm(int opt, unsigne error = 0; out: - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); return error; } _