From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Xu Date: Fri, 27 May 2022 14:53:36 +0000 Subject: Re: [PATCH v3] mm: Avoid unnecessary page fault retires on shared memory types Message-Id: List-Id: References: <20220524234531.1949-1-peterx@redhat.com> In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Ingo Molnar Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, Richard Henderson , David Hildenbrand , Matt Turner , Albert Ou , Michal Simek , Russell King , Ivan Kokshaysky , linux-riscv@lists.infradead.org, Alexander Gordeev , Dave Hansen , Jonas Bonn , Will Deacon , "James E . J . Bottomley" , "H . Peter Anvin" , Andrea Arcangeli , openrisc@lists.librecores.org, linux-s390@vger.kernel.org, Ingo Molnar , linux-m68k@lists.linux-m68k.org, Palmer Dabbelt , Heiko Carstens , Chris Zankel , Peter Zijlstra , Alistair Popple , linux-csky@vger.kernel.org, linux-hexagon@vger.kernel.org, Vlastimil Babka , Thomas Gleixner , sparclinux@vger.kernel.org, Christian Borntraeger , Stafford Horne , Michael Ellerman , x86@kernel.org, Thomas Bogendoerfer , Paul Mackerras , linux-arm-kernel@lists.infradead.org, Sven Schnelle , Benjamin Herrenschmidt , linux-xtensa@linux-xtensa.org, Nicholas Piggin , linux-sh@vger.kernel.org, Vasily Gorbik , Borislav Petkov , linux-mips@vger.kernel.org, Max Filippov , Helge Deller , Vineet Gupta , Al Viro , Paul Walmsley , Johannes Weiner , Anton Ivanov , Catalin Marinas , linux-um@lists.infradead.org, linux-alpha@vger.kernel.org, Johannes Berg , linux-ia64@vger.kernel.org, Geert Uytterhoeven , Dinh Nguyen , Guo Ren , linux-snps-arc@lists.infradead.org, Hugh Dickins , Rich Felker , Andy Lutomirski , Richard Weinberger , linuxppc-dev@lists.ozlabs.org, Brian Cain , Yoshinori Sato , Andrew Morton , Stefan Kristiansson , linux-parisc@vger.kernel.org, "David S . Miller" On Fri, May 27, 2022 at 12:46:31PM +0200, Ingo Molnar wrote: > > * Peter Xu wrote: > > > This patch provides a ~12% perf boost on my aarch64 test VM with a simple > > program sequentially dirtying 400MB shmem file being mmap()ed and these are > > the time it needs: > > > > Before: 650.980 ms (+-1.94%) > > After: 569.396 ms (+-1.38%) > > Nice! > > > arch/x86/mm/fault.c | 4 ++++ > > Reviewed-by: Ingo Molnar > > Minor comment typo: > > > + /* > > + * We should do the same as VM_FAULT_RETRY, but let's not > > + * return -EBUSY since that's not reflecting the reality on > > + * what has happened - we've just fully completed a page > > + * fault, with the mmap lock released. Use -EAGAIN to show > > + * that we want to take the mmap lock _again_. > > + */ > > s/reflecting the reality on what has happened > /reflecting the reality of what has happened Will fix. > > > ret = handle_mm_fault(vma, address, fault_flags, NULL); > > + > > + if (ret & VM_FAULT_COMPLETED) { > > + /* > > + * NOTE: it's a pity that we need to retake the lock here > > + * to pair with the unlock() in the callers. Ideally we > > + * could tell the callers so they do not need to unlock. > > + */ > > + mmap_read_lock(mm); > > + *unlocked = true; > > + return 0; > > Indeed that's a pity - I guess more performance could be gained here, > especially in highly parallel threaded workloads? Yes I think so. The patch avoids the page fault retry, including the mmap lock/unlock side. Now if we retake the lock for fixup_user_fault() we still safe time for pgtable walks but the lock overhead will be somehow kept, just with smaller critical sections. Some fixup_user_fault() callers won't be affected as long as unlocked=NULL is passed - e.g. the futex code path (fault_in_user_writeable). After all they never needed to retake the lock before/after this patch. It's about the other callers, and they may need some more touch-ups case by case. Examples are follow_fault_pfn() in vfio and hva_to_pfn_remapped() in KVM: both of them returns -EAGAIN when *unlocked=true. We need to teach them to know "*unlocked=true" does not necessarily mean a retry attempt. I think I can look into them if this patch can be accepted as a follow up. Thanks for taking a look! -- Peter Xu