From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752349AbeCWND3 (ORCPT ); Fri, 23 Mar 2018 09:03:29 -0400 Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:57070 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751963AbeCWND1 (ORCPT ); Fri, 23 Mar 2018 09:03:27 -0400 Subject: Re: [RFC PATCH 1/8] mm: mmap: unmap large mapping by section To: Yang Shi , Matthew Wilcox Cc: Michal Hocko , akpm@linux-foundation.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org References: <1521581486-99134-1-git-send-email-yang.shi@linux.alibaba.com> <1521581486-99134-2-git-send-email-yang.shi@linux.alibaba.com> <20180321130833.GM23100@dhcp22.suse.cz> <20180321172932.GE4780@bombadil.infradead.org> <20180321224631.GB3969@bombadil.infradead.org> <18a727fd-f006-9fae-d9ca-74b9004f0a8b@linux.vnet.ibm.com> <20180322154055.GB28468@bombadil.infradead.org> <0442fb0e-3da3-3f23-ce4d-0f6cbc3eac9a@linux.vnet.ibm.com> <20180322160547.GC28468@bombadil.infradead.org> <55ac947f-fd77-3754-ebfe-30d458c54403@linux.vnet.ibm.com> From: Laurent Dufour Date: Fri, 23 Mar 2018 14:03:19 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.6.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 8bit X-TM-AS-GCONF: 00 x-cbid: 18032313-0020-0000-0000-000004089C36 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 18032313-0021-0000-0000-0000429CC3C0 Message-Id: X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2018-03-23_08:,, signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 priorityscore=1501 malwarescore=0 suspectscore=0 phishscore=0 bulkscore=0 spamscore=0 clxscore=1015 lowpriorityscore=0 impostorscore=0 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1709140000 definitions=main-1803230150 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 22/03/2018 17:46, Yang Shi wrote: > > > On 3/22/18 9:18 AM, Laurent Dufour wrote: >> >> On 22/03/2018 17:05, Matthew Wilcox wrote: >>> On Thu, Mar 22, 2018 at 04:54:52PM +0100, Laurent Dufour wrote: >>>> On 22/03/2018 16:40, Matthew Wilcox wrote: >>>>> On Thu, Mar 22, 2018 at 04:32:00PM +0100, Laurent Dufour wrote: >>>>>> Regarding the page fault, why not relying on the PTE locking ? >>>>>> >>>>>> When munmap() will unset the PTE it will have to held the PTE lock, so this >>>>>> will serialize the access. >>>>>> If the page fault occurs before the mmap(MAP_FIXED), the page mapped will be >>>>>> removed when mmap(MAP_FIXED) would do the cleanup. Fair enough. >>>>> The page fault handler will walk the VMA tree to find the correct >>>>> VMA and then find that the VMA is marked as deleted.  If it assumes >>>>> that the VMA has been deleted because of munmap(), then it can raise >>>>> SIGSEGV immediately.  But if the VMA is marked as deleted because of >>>>> mmap(MAP_FIXED), it must wait until the new VMA is in place. >>>> I'm wondering if such a complexity is required. >>>> If the user space process try to access the page being overwritten through >>>> mmap(MAP_FIXED) by another thread, there is no guarantee that it will >>>> manipulate the *old* page or *new* one. >>> Right; but it must return one or the other, it can't segfault. >> Good point, I missed that... >> >>>> I'd think this is up to the user process to handle that concurrency. >>>> What needs to be guaranteed is that once mmap(MAP_FIXED) returns the old page >>>> are no more there, which is done through the mmap_sem and PTE locking. >>> Yes, and allowing the fault handler to return the *old* page risks the >>> old page being reinserted into the page tables after the unmapping task >>> has done its work. >> The PTE locking should prevent that. >> >>> It's *really* rare to page-fault on a VMA which is in the middle of >>> being replaced.  Why are you trying to optimise it? >> I was not trying to optimize it, but to not wait in the page fault handler. >> This could become tricky in the case the VMA is removed once mmap(MAP_FIXED) is >> done and before the waiting page fault got woken up. This means that the >> removed VMA structure will have to remain until all the waiters are woken up >> which implies ref_count or similar. > > We may not need ref_count. After removing "locked-for-deletion" vmas when > mmap(MAP_FIXED) is done, just wake up page fault to re-lookup vma, then it will > find the new vma installed by mmap(MAP_FIXED), right? I do agree, as far as waking up would not require access to the VMA. > I'm not sure if completion can do this or not since I'm not quite familiar with > it :-( I don't know either :/ Laurent. > Yang > >> >>>>> I think I was wrong to describe VMAs as being *deleted*.  I think we >>>>> instead need the concept of a *locked* VMA that page faults will block on. >>>>> Conceptually, it's a per-VMA rwsem, but I'd use a completion instead of >>>>> an rwsem since the only reason to write-lock the VMA is because it is >>>>> being deleted. >>>> Such a lock would only makes sense in the case of mmap(MAP_FIXED) since when >>>> the VMA is removed there is no need to wait. Isn't it ? >>> I can't think of another reason.  I suppose we could mark the VMA as >>> locked-for-deletion or locked-for-replacement and have the SIGSEGV happen >>> early.  But I'm not sure that optimising for SIGSEGVs is a worthwhile >>> use of our time.  Just always have the pagefault sleep for a deleted VMA. > > > >