From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35200 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229468AbhAaDbd (ORCPT ); Sat, 30 Jan 2021 22:31:33 -0500 Date: Sun, 31 Jan 2021 13:30:45 +1000 From: Nicholas Piggin Subject: Re: [RFC 00/20] TLB batching consolidation and enhancements References: <20210131001132.3368247-1-namit@vmware.com> In-Reply-To: <20210131001132.3368247-1-namit@vmware.com> MIME-Version: 1.0 Message-Id: <1612063149.2awdsvvmhj.astroid@bobo.none> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable List-ID: To: linux-kernel@vger.kernel.org, linux-mm@kvack.org, Nadav Amit Cc: Andrea Arcangeli , Andrew Morton , Dave Hansen , linux-csky@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-s390@vger.kernel.org, Andy Lutomirski , Mel Gorman , Nadav Amit , Peter Zijlstra , Thomas Gleixner , Will Deacon , x86@kernel.org, Yu Zhao Excerpts from Nadav Amit's message of January 31, 2021 10:11 am: > From: Nadav Amit >=20 > There are currently (at least?) 5 different TLB batching schemes in the > kernel: >=20 > 1. Using mmu_gather (e.g., zap_page_range()). >=20 > 2. Using {inc|dec}_tlb_flush_pending() to inform other threads on the > ongoing deferred TLB flush and flushing the entire range eventually > (e.g., change_protection_range()). >=20 > 3. arch_{enter|leave}_lazy_mmu_mode() for sparc and powerpc (and Xen?). >=20 > 4. Batching per-table flushes (move_ptes()). >=20 > 5. By setting a flag on that a deferred TLB flush operation takes place, > flushing when (try_to_unmap_one() on x86). >=20 > It seems that (1)-(4) can be consolidated. In addition, it seems that > (5) is racy. It also seems there can be many redundant TLB flushes, and > potentially TLB-shootdown storms, for instance during batched > reclamation (using try_to_unmap_one()) if at the same time mmu_gather > defers TLB flushes. >=20 > More aggressive TLB batching may be possible, but this patch-set does > not add such batching. The proposed changes would enable such batching > in a later time. >=20 > Admittedly, I do not understand how things are not broken today, which > frightens me to make further batching before getting things in order. > For instance, why is ok for zap_pte_range() to batch dirty-PTE flushes > for each page-table (but not in greater granularity). Can't > ClearPageDirty() be called before the flush, causing writes after > ClearPageDirty() and before the flush to be lost? Because it's holding the page table lock which stops page_mkclean from=20 cleaning the page. Or am I misunderstanding the question? I'll go through the patches a bit more closely when they all come=20 through. Sparc and powerpc of course need the arch lazy mode to get=20 per-page/pte information for operations that are not freeing pages,=20 which is what mmu gather is designed for. I wouldn't mind using a similar API so it's less of a black box when=20 reading generic code, but it might not quite fit the mmu gather API exactly (most of these paths don't want a full mmu_gather on stack). >=20 > This patch-set therefore performs the following changes: >=20 > 1. Change mprotect, task_mmu and mapping_dirty_helpers to use mmu_gather > instead of {inc|dec}_tlb_flush_pending(). >=20 > 2. Avoid TLB flushes if PTE permission is not demoted. >=20 > 3. Cleans up mmu_gather to be less arch-dependant. >=20 > 4. Uses mm's generations to track in finer granularity, either per-VMA > or per page-table, whether a pending mmu_gather operation is > outstanding. This should allow to avoid some TLB flushes when KSM or > memory reclamation takes place while another operation such as > munmap() or mprotect() is running. >=20 > 5. Changes try_to_unmap_one() flushing scheme, as the current seems > broken to track in a bitmap which CPUs have outstanding TLB flushes > instead of having a flag. Putting fixes first, and cleanups and independent patches (like #2) next would help with getting stuff merged and backported. Thanks, Nick