From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Subject: Re: [PATCH v5 00/11] Introduces new count-based method for tracking lockless pagetable walks Date: Thu, 3 Oct 2019 09:29:52 +0200 Message-ID: <20191003072952.GN4536@hirez.programming.kicks-ass.net> References: <20191003013325.2614-1-leonardo@linux.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20191003013325.2614-1-leonardo@linux.ibm.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: linuxppc-dev-bounces+glppe-linuxppc-embedded-2=m.gmane.org@lists.ozlabs.org Sender: "Linuxppc-dev" To: Leonardo Bras Cc: Song Liu , Michal Hocko , "Dmitry V. Levin" , Keith Busch , linux-mm@kvack.org, Paul Mackerras , Christoph Lameter , Ira Weiny , Dan Williams , Elena Reshetova , linux-arch@vger.kernel.org, Santosh Sivaraj , Davidlohr Bueso , "Aneesh Kumar K.V" , Bartlomiej Zolnierkiewicz , Mike Rapoport , Jason Gunthorpe , Vlastimil Babka , Mahesh Salgaonkar , Andrey Ryabinin , Alexey Dobriyan , Ingo Molnar , Andrea Arcangeli , Ralph Campbell List-Id: linux-arch.vger.kernel.org On Wed, Oct 02, 2019 at 10:33:14PM -0300, Leonardo Bras wrote: > If a process (qemu) with a lot of CPUs (128) try to munmap() a large > chunk of memory (496GB) mapped with THP, it takes an average of 275 > seconds, which can cause a lot of problems to the load (in qemu case, > the guest will lock for this time). > > Trying to find the source of this bug, I found out most of this time is > spent on serialize_against_pte_lookup(). This function will take a lot > of time in smp_call_function_many() if there is more than a couple CPUs > running the user process. Since it has to happen to all THP mapped, it > will take a very long time for large amounts of memory. > > By the docs, serialize_against_pte_lookup() is needed in order to avoid > pmd_t to pte_t casting inside find_current_mm_pte(), or any lockless > pagetable walk, to happen concurrently with THP splitting/collapsing. > > It does so by calling a do_nothing() on each CPU in mm->cpu_bitmap[], > after interrupts are re-enabled. > Since, interrupts are (usually) disabled during lockless pagetable > walk, and serialize_against_pte_lookup will only return after > interrupts are enabled, it is protected. This is something entirely specific to Power, you shouldn't be touching generic code at all. Also, I'm not sure I understand things properly. So serialize_against_pte_lookup() wants to wait for all currently out-standing __find_linux_pte() instances (which are very similar to gup_fast). It seems to want to do this before flushing the THP TLB for some reason; why? Should not THP observe the normal page table freeing rules which includes a RCU-like grace period like this already. Why is THP special here? This doesn't seem adequately explained. Also, specifically to munmap(), this seems entirely superfluous, munmap() uses the normal page-table freeing code and should be entirely fine without additional waiting. Furthermore, Power never accurately tracks mm_cpumask(), so using that makes the whole thing more expensive than it needs to be. Also, I suppose that is buggered vs file backed THP.