From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 54710C433EF for ; Fri, 27 May 2022 19:39:57 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1354578AbiE0Tjx (ORCPT ); Fri, 27 May 2022 15:39:53 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:55074 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1354543AbiE0Tjv (ORCPT ); Fri, 27 May 2022 15:39:51 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id EAA951269B9 for ; Fri, 27 May 2022 12:39:49 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1653680389; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=Xqn33tBQSqeKb5h7UBUCWe0hU2Z/Y9n8sp4SwTfC2uo0P3gxvsExYI4b6BEwBnY6sftxP1 lGehbQSpjyRn57O5+a9I+cshFP8YP5a1ze3yR4zYHuE7dnmGbXjLUz5ztI355BjZSHxn2n EotYfun8CvpcBBFYwbanJonOWzORpu4= Received: from mail-il1-f198.google.com (mail-il1-f198.google.com [209.85.166.198]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-310-ygLEewMYOhCdivwFF7pX8A-1; Fri, 27 May 2022 15:39:46 -0400 X-MC-Unique: ygLEewMYOhCdivwFF7pX8A-1 Received: by mail-il1-f198.google.com with SMTP id m9-20020a927109000000b002d1af1ed294so3646979ilc.5 for ; Fri, 27 May 2022 12:39:44 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=bN67pcwAGaZNhdz7XLavXtQX2W/R2bV05bePWea5agZMzOU2t2Y6lWLljAzdDi0kgM WJEw8yGUsxlYSL/6WMP3COM+fNiNoky+4QieMSYM56qtvbJ1lXhs30LdGpHyAAHHlc7a W4WH0djyP+BxA3Qmq6YMZ3Nd6nOT+kzYA/2/6hgmwFBOFbb96CaWZoJEtUuYwmO5Fltr 3BFp3/aaWMFQkP7Q4UC6vttoB73ZHFNQzf8aZvaY5jIBe7gbhor7xTW+VQ3FmPctXIp6 RACR5+aQUwaDnHNfstTIU05434od+bwkj35rSSUCZUIXTXiO6pBWKKJRhZ9KpStijD6z 1VBA== X-Gm-Message-State: AOAM531eaoOYM7egfqDiQAFGj1bUK/WLmcg2Xr4yV/9BF6CcHkJFL3TW C8Fh4dqwLiTMekhEDvKDvErJiIYbveYF6zdD2LJeAWYjaokU5KEwVGGv6uquF515nBxT2JsE9hu 8p7u6y9Yi1X5SA18zcn8= X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834903jal.212.1653680383720; Fri, 27 May 2022 12:39:43 -0700 (PDT) X-Google-Smtp-Source: ABdhPJycszExypDCmz/kq06KoOIqbe7IWTgWCyXrKhxfATY7rwpEo/+Qx+suJB7x0DjnJcxaZa6AhQ== X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834857jal.212.1653680383300; Fri, 27 May 2022 12:39:43 -0700 (PDT) Received: from localhost.localdomain (cpec09435e3e0ee-cmc09435e3e0ec.cpe.net.cable.rogers.com. [99.241.198.116]) by smtp.gmail.com with ESMTPSA id t2-20020a92c902000000b002d10291f973sm1530215ilp.4.2022.05.27.12.39.37 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Fri, 27 May 2022 12:39:42 -0700 (PDT) From: Peter Xu To: linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: Will Deacon , Matt Turner , linux-s390@vger.kernel.org, Andrew Morton , Brian Cain , Borislav Petkov , linux-alpha@vger.kernel.org, Alistair Popple , Jonas Bonn , linux-arm-kernel@lists.infradead.org, linux-ia64@vger.kernel.org, Michael Ellerman , Stefan Kristiansson , linux-snps-arc@lists.infradead.org, Vineet Gupta , Vasily Gorbik , Vlastimil Babka , Ivan Kokshaysky , Rich Felker , sparclinux@vger.kernel.org, Russell King , David Hildenbrand , Benjamin Herrenschmidt , Nicholas Piggin , "James E . J . Bottomley" , linux-xtensa@linux-xtensa.org, linux-sh@vger.kernel.org, Paul Walmsley , linux-m68k@lists.linux-m68k.org, linuxppc-dev@lists.ozlabs.org, Richard Henderson , Guo Ren , linux-parisc@vger.kernel.org, Andrea Arcangeli , Helge Deller , Al Viro , Albert Ou , linux-um@lists.infradead.org, "H . Peter Anvin" , Janosch Frank , Sven Schnelle , Anton Ivanov , openrisc@lists.librecores.org, Thomas Bogendoerfer , linux-hexagon@vger.kernel.org, Andy Lutomirski , Stafford Horne , linux-csky@vger.kernel.org, Heiko Carstens , Thomas Gleixner , linux-mips@vger.kernel.org, Paul Mackerras , Alexander Gordeev , Dinh Nguyen , Palmer Dabbelt , "David S . Miller" , Johannes Weiner , Hugh Dickins , Ingo Molnar , Peter Zijlstra , linux-riscv@lists.infradead.org, Max Filippov , Catalin Marinas , Geert Uytterhoeven , Christian Borntraeger , Johannes Berg , Chris Zankel , Michal Simek , x86@kernel.org, Yoshinori Sato , peterx@redhat.com, Dave Hansen , Richard Weinberger , Ingo Molnar Subject: [PATCH v4] mm: Avoid unnecessary page fault retires on shared memory types Date: Fri, 27 May 2022 15:39:36 -0400 Message-Id: <20220527193936.30678-1-peterx@redhat.com> X-Mailer: git-send-email 2.32.0 MIME-Version: 1.0 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=peterx@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-type: text/plain Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-sh@vger.kernel.org I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. 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%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Signed-off-by: Peter Xu --- v4: - Picked up a-bs and r-bs - Fix grammar in the comment of faultin_page() [Ingo] - Fix s390 for gmap since gmap needs the mmap lock [Heiko] v3: - Rebase to akpm/mm-unstable - Copy arch maintainers --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ do_page_fault(unsigned long address, unsigned long mmcsr, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 77341b160aca..e401d416bbd6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned int esr, return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 44f98100e84e..6f72bac39bf2 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 80bb66ad42f6..c18f7abd64df 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -167,6 +167,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..fe57175a7792 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -309,6 +309,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 4e9efbe46d5f..d6a87f4137ca 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -330,6 +330,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..4608cc962ecf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + /* + * Gmap will need the mmap lock again, so retake it. TODO: + * only conditionally take the lock when CONFIG_PGSTE set. + */ + mmap_read_lock(mm); + goto out_gmap; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..12ed70b432d6 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ void do_user_addr_fault(struct pt_regs *regs, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 06d0973a0d74..5f64305ba8d7 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -118,6 +118,10 @@ void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c09b7f0555b8..decc275db3c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 2e07cff3b31b..a63d330b9d43 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * 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_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ static long __get_user_pages(struct mm_struct *mm, case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ int fixup_user_fault(struct mm_struct *mm, return -EINTR; 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; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 54d106e0c999..a8be2d7a8718 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- 2.32.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 3EFE7C433FE for ; Fri, 27 May 2022 19:40:05 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:Message-Id:Date:Subject:Cc :To:From:Reply-To:Content-ID:Content-Description:Resent-Date:Resent-From: Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:In-Reply-To:References: List-Owner; bh=wkwk2lWCAEgrUXzb6612wd2OdnNR9oOEKwJmcbyd5Jk=; b=3rbQCzc9AvnmLM v+q02iHjU/wcF5ToFzcj+4JMvcjMD/7jjUnKJTQAglcxw0/0wP1I9GqI0xTTeHWhEyHWl9FSdotee bt+avwNzeQR4oC2RGBM+VvepC4F68EAbtas7QcE6lgoMHCDJtSJ3fz/xkTrSOWBBqOI4dXfKjwxoh uxx/lPuKsKbjAwK7veSUNJrE+QV4cAfV2mK+LN1I1hVdMmka/8WntA32EkDs14J4ZVbpK5gYB1e8J elt17d6y+NIio0jCcHtguoiAoYy7+N4hs0g1A72WokqnLnfr9Q1BJ/k+NwuyNJbU0FEGT3Fv+chjh o7KDhUAUsPu0b67OZtrQ==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.94.2 #2 (Red Hat Linux)) id 1nufoP-000qxp-F2; Fri, 27 May 2022 19:39:53 +0000 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by bombadil.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1nufoL-000qws-23 for linux-riscv@lists.infradead.org; Fri, 27 May 2022 19:39:51 +0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1653680388; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=P+nCP3hGDIQjbSUxetjfsWamQ5hkJV0AFxpgoYCmvzQ7q8pCR076MkQ42jTe5t4jnLMrjZ WOlqBl9E2dk3wMnPZBRcdzV1QIX0Aor8CsdwK8eMRTt0jL72t7s9HzcdxOdBbC2oY9232g HRBDOHYVTbNUY2VTjYlcj1zY1uinMp0= Received: from mail-io1-f70.google.com (mail-io1-f70.google.com [209.85.166.70]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-226-NkcoFktqMjWsEIXRDb91hw-1; Fri, 27 May 2022 15:39:47 -0400 X-MC-Unique: NkcoFktqMjWsEIXRDb91hw-1 Received: by mail-io1-f70.google.com with SMTP id u18-20020a5d8712000000b0064c7a7c497aso3289606iom.18 for ; Fri, 27 May 2022 12:39:45 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=NPk1WLbYSZz24wMdMWP1/BdSLaPzhN5bsu/5SrW71SoGg61/0esMQdIohvPLGo7DxK behPAtdct5PtP8W4K8O9sDbHtRE+TkoaWsIq/jN9qeo2dJJAXYJV90Xb9EAQWcV62CtU idN6dxhAg47FV9yb7/rSX74Ruc7elSW4mYGMcEMI60ryW2+1Oiqk8BOu6e78zMR88YLZ bRFsmV6PqpsMo9vw03r508VtERnusqkW4XZxe2Jweijc0mCcDWvsLRtmxggN76ti+HS7 4S3+QjzaLYZsD9/Frbre43F52VUIOIhNCfdwSkuV/lfG+SoJXwrgBH0mYaYgjoDA776y TuBA== X-Gm-Message-State: AOAM531gWzAUBjgh2lDPlQAZLhV9+IkSIYHHLMKxnuqQ59dXWl0StcWA NGIGh4zZznfFSEeSZN23oS1IExDf2bq9RmZUL4O9tVtJDk25GK0lDJcxSJStM3/gMy0iBW10lc/ kYVfj+PtPUJNrAs9KDeSHv4UBvgMI X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834910jal.212.1653680383726; Fri, 27 May 2022 12:39:43 -0700 (PDT) X-Google-Smtp-Source: ABdhPJycszExypDCmz/kq06KoOIqbe7IWTgWCyXrKhxfATY7rwpEo/+Qx+suJB7x0DjnJcxaZa6AhQ== X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834857jal.212.1653680383300; Fri, 27 May 2022 12:39:43 -0700 (PDT) Received: from localhost.localdomain (cpec09435e3e0ee-cmc09435e3e0ec.cpe.net.cable.rogers.com. [99.241.198.116]) by smtp.gmail.com with ESMTPSA id t2-20020a92c902000000b002d10291f973sm1530215ilp.4.2022.05.27.12.39.37 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Fri, 27 May 2022 12:39:42 -0700 (PDT) From: Peter Xu To: linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: Will Deacon , Matt Turner , linux-s390@vger.kernel.org, Andrew Morton , Brian Cain , Borislav Petkov , linux-alpha@vger.kernel.org, Alistair Popple , Jonas Bonn , linux-arm-kernel@lists.infradead.org, linux-ia64@vger.kernel.org, Michael Ellerman , Stefan Kristiansson , linux-snps-arc@lists.infradead.org, Vineet Gupta , Vasily Gorbik , Vlastimil Babka , Ivan Kokshaysky , Rich Felker , sparclinux@vger.kernel.org, Russell King , David Hildenbrand , Benjamin Herrenschmidt , Nicholas Piggin , "James E . J . Bottomley" , linux-xtensa@linux-xtensa.org, linux-sh@vger.kernel.org, Paul Walmsley , linux-m68k@lists.linux-m68k.org, linuxppc-dev@lists.ozlabs.org, Richard Henderson , Guo Ren , linux-parisc@vger.kernel.org, Andrea Arcangeli , Helge Deller , Al Viro , Albert Ou , linux-um@lists.infradead.org, "H . Peter Anvin" , Janosch Frank , Sven Schnelle , Anton Ivanov , openrisc@lists.librecores.org, Thomas Bogendoerfer , linux-hexagon@vger.kernel.org, Andy Lutomirski , Stafford Horne , linux-csky@vger.kernel.org, Heiko Carstens , Thomas Gleixner , linux-mips@vger.kernel.org, Paul Mackerras , Alexander Gordeev , Dinh Nguyen , Palmer Dabbelt , "David S . Miller" , Johannes Weiner , Hugh Dickins , Ingo Molnar , Peter Zijlstra , linux-riscv@lists.infradead.org, Max Filippov , Catalin Marinas , Geert Uytterhoeven , Christian Borntraeger , Johannes Berg , Chris Zankel , Michal Simek , x86@kernel.org, Yoshinori Sato , peterx@redhat.com, Dave Hansen , Richard Weinberger , Ingo Molnar Subject: [PATCH v4] mm: Avoid unnecessary page fault retires on shared memory types Date: Fri, 27 May 2022 15:39:36 -0400 Message-Id: <20220527193936.30678-1-peterx@redhat.com> X-Mailer: git-send-email 2.32.0 MIME-Version: 1.0 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=peterx@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20220527_123949_281148_CD4BBEDB X-CRM114-Status: GOOD ( 26.03 ) X-BeenThere: linux-riscv@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-riscv" Errors-To: linux-riscv-bounces+linux-riscv=archiver.kernel.org@lists.infradead.org I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. 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%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Signed-off-by: Peter Xu --- v4: - Picked up a-bs and r-bs - Fix grammar in the comment of faultin_page() [Ingo] - Fix s390 for gmap since gmap needs the mmap lock [Heiko] v3: - Rebase to akpm/mm-unstable - Copy arch maintainers --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ do_page_fault(unsigned long address, unsigned long mmcsr, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 77341b160aca..e401d416bbd6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned int esr, return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 44f98100e84e..6f72bac39bf2 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 80bb66ad42f6..c18f7abd64df 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -167,6 +167,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..fe57175a7792 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -309,6 +309,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 4e9efbe46d5f..d6a87f4137ca 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -330,6 +330,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..4608cc962ecf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + /* + * Gmap will need the mmap lock again, so retake it. TODO: + * only conditionally take the lock when CONFIG_PGSTE set. + */ + mmap_read_lock(mm); + goto out_gmap; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..12ed70b432d6 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ void do_user_addr_fault(struct pt_regs *regs, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 06d0973a0d74..5f64305ba8d7 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -118,6 +118,10 @@ void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c09b7f0555b8..decc275db3c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 2e07cff3b31b..a63d330b9d43 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * 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_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ static long __get_user_pages(struct mm_struct *mm, case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ int fixup_user_fault(struct mm_struct *mm, return -EINTR; 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; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 54d106e0c999..a8be2d7a8718 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- 2.32.0 _______________________________________________ linux-riscv mailing list linux-riscv@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-riscv From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id F0B60C433F5 for ; Fri, 27 May 2022 19:40:05 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:Message-Id:Date:Subject:Cc :To:From:Reply-To:Content-ID:Content-Description:Resent-Date:Resent-From: Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:In-Reply-To:References: List-Owner; bh=CY1/ZBbEJrDQ1QWa4kS9T/auELI39g/lgJ5RiemoUuY=; b=MdNUcGzZVe9Wzq QJuj+lh7AYwTyKnJ41960hezMxlUd2rw+ndL2IkmJbTzqmgjT+IxHnJE0c6e57fUjQbe7851ggt0B zNaabhqqlwaYiC/3M9vDP0ubvceEeoF6qR5rV/XQYhNKTaS74TuIUxKn4bbp4LsEtD6xPpbERWK/E 3K6RQ8HGRjc8KorFZNNMS/OvSmtZ7AUYo9jlRLeE8sEV7i5ozdR6U5TV/R9hrBObKMEG+33y7+Oq8 2slMFxBVrgqF6uaoPwAdhyJQ87uCPHVumZzMNoPewb95yeU1BfDeLcrLMXWE+noQWvQrWlNJCwHEp T3pOZ2HcsdF9oejoyE1A==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.94.2 #2 (Red Hat Linux)) id 1nufoY-000r0n-Fr; Fri, 27 May 2022 19:40:02 +0000 Received: from us-smtp-delivery-124.mimecast.com ([170.10.129.124]) by bombadil.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1nufoT-000qyy-9t for linux-snps-arc@lists.infradead.org; Fri, 27 May 2022 19:40:01 +0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1653680396; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=TzjzUrMW8JfAo4I9QLpGdajU44zE1VN4zaLEj8caEs13dlUZTOnkL9dYjQ6wDLZY7mSCGK PSndsl+Z65W5fE/0l0ZHSaHIQS11cOHmjW2CZgT+5aYiWp3VurulHIx+ezpUHdWoXxdmpR yvnu5QK+G21OCknLM2a/cDbl98DsJnI= Received: from mail-il1-f200.google.com (mail-il1-f200.google.com [209.85.166.200]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-271-q4LAWRjpN0mY7Q4YLPl4nw-1; Fri, 27 May 2022 15:39:47 -0400 X-MC-Unique: q4LAWRjpN0mY7Q4YLPl4nw-1 Received: by mail-il1-f200.google.com with SMTP id x1-20020a056e020f0100b002c98fce9c13so3646733ilj.3 for ; Fri, 27 May 2022 12:39:44 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=niGmSq4iJ3R1QV2j6hJxwRe5kZ+4uIj2dVW4WUelXlHoz8hMZomxwmu2HPmJ04wfnT oeJTDoml6ljJMozqzFbMXtQafWjAebJjARpeJaV1FBDVuI+csox+3JFglsWpzcmz1Xpj N7Fi7mX6NG55X9FN9mCvgGIXO/0Yh1k03Ex9vA+4VX6+PDsWomamim9eb126XdUoEqnF uGEe88XxDgjndnS8uId5Bdi9e6v5fffGLkq68tgkMILhbXIeoqu07VJRNjWZIoXfrYR2 CoA+vBa1O/h0RFesaYzgh77mcbOJzNI0Dqrb2kYwcJ1qWrm7fVs1xXQBynpT7qtmWGqa K4/A== X-Gm-Message-State: AOAM530BDrlo2EvXLB5f7mQQxzlgk59xugYYbAviNlCtaa797fecPwUL EAmNfgc/Oe0JDIFXWFVIfd0Rgh7fVgJdlsD2y1BGpyCcL+SGnDnU14ENRAhKqzYdEHU+0ZbClVX pRsU1udTcVkLSDPDnmzbGXwb1xHNqhiTv X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834901jal.212.1653680383717; Fri, 27 May 2022 12:39:43 -0700 (PDT) X-Google-Smtp-Source: ABdhPJycszExypDCmz/kq06KoOIqbe7IWTgWCyXrKhxfATY7rwpEo/+Qx+suJB7x0DjnJcxaZa6AhQ== X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834857jal.212.1653680383300; Fri, 27 May 2022 12:39:43 -0700 (PDT) Received: from localhost.localdomain (cpec09435e3e0ee-cmc09435e3e0ec.cpe.net.cable.rogers.com. [99.241.198.116]) by smtp.gmail.com with ESMTPSA id t2-20020a92c902000000b002d10291f973sm1530215ilp.4.2022.05.27.12.39.37 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Fri, 27 May 2022 12:39:42 -0700 (PDT) From: Peter Xu To: linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: Will Deacon , Matt Turner , linux-s390@vger.kernel.org, Andrew Morton , Brian Cain , Borislav Petkov , linux-alpha@vger.kernel.org, Alistair Popple , Jonas Bonn , linux-arm-kernel@lists.infradead.org, linux-ia64@vger.kernel.org, Michael Ellerman , Stefan Kristiansson , linux-snps-arc@lists.infradead.org, Vineet Gupta , Vasily Gorbik , Vlastimil Babka , Ivan Kokshaysky , Rich Felker , sparclinux@vger.kernel.org, Russell King , David Hildenbrand , Benjamin Herrenschmidt , Nicholas Piggin , "James E . J . Bottomley" , linux-xtensa@linux-xtensa.org, linux-sh@vger.kernel.org, Paul Walmsley , linux-m68k@lists.linux-m68k.org, linuxppc-dev@lists.ozlabs.org, Richard Henderson , Guo Ren , linux-parisc@vger.kernel.org, Andrea Arcangeli , Helge Deller , Al Viro , Albert Ou , linux-um@lists.infradead.org, "H . Peter Anvin" , Janosch Frank , Sven Schnelle , Anton Ivanov , openrisc@lists.librecores.org, Thomas Bogendoerfer , linux-hexagon@vger.kernel.org, Andy Lutomirski , Stafford Horne , linux-csky@vger.kernel.org, Heiko Carstens , Thomas Gleixner , linux-mips@vger.kernel.org, Paul Mackerras , Alexander Gordeev , Dinh Nguyen , Palmer Dabbelt , "David S . Miller" , Johannes Weiner , Hugh Dickins , Ingo Molnar , Peter Zijlstra , linux-riscv@lists.infradead.org, Max Filippov , Catalin Marinas , Geert Uytterhoeven , Christian Borntraeger , Johannes Berg , Chris Zankel , Michal Simek , x86@kernel.org, Yoshinori Sato , peterx@redhat.com, Dave Hansen , Richard Weinberger , Ingo Molnar Subject: [PATCH v4] mm: Avoid unnecessary page fault retires on shared memory types Date: Fri, 27 May 2022 15:39:36 -0400 Message-Id: <20220527193936.30678-1-peterx@redhat.com> X-Mailer: git-send-email 2.32.0 MIME-Version: 1.0 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=peterx@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20220527_123957_531421_7F3A6128 X-CRM114-Status: GOOD ( 26.03 ) X-BeenThere: linux-snps-arc@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: Linux on Synopsys ARC Processors List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-snps-arc" Errors-To: linux-snps-arc-bounces+linux-snps-arc=archiver.kernel.org@lists.infradead.org I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. 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%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Signed-off-by: Peter Xu --- v4: - Picked up a-bs and r-bs - Fix grammar in the comment of faultin_page() [Ingo] - Fix s390 for gmap since gmap needs the mmap lock [Heiko] v3: - Rebase to akpm/mm-unstable - Copy arch maintainers --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ do_page_fault(unsigned long address, unsigned long mmcsr, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 77341b160aca..e401d416bbd6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned int esr, return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 44f98100e84e..6f72bac39bf2 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 80bb66ad42f6..c18f7abd64df 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -167,6 +167,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..fe57175a7792 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -309,6 +309,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 4e9efbe46d5f..d6a87f4137ca 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -330,6 +330,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..4608cc962ecf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + /* + * Gmap will need the mmap lock again, so retake it. TODO: + * only conditionally take the lock when CONFIG_PGSTE set. + */ + mmap_read_lock(mm); + goto out_gmap; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..12ed70b432d6 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ void do_user_addr_fault(struct pt_regs *regs, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 06d0973a0d74..5f64305ba8d7 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -118,6 +118,10 @@ void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c09b7f0555b8..decc275db3c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 2e07cff3b31b..a63d330b9d43 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * 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_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ static long __get_user_pages(struct mm_struct *mm, case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ int fixup_user_fault(struct mm_struct *mm, return -EINTR; 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; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 54d106e0c999..a8be2d7a8718 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- 2.32.0 _______________________________________________ linux-snps-arc mailing list linux-snps-arc@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-snps-arc From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.librecores.org (lists.librecores.org [88.198.125.70]) by smtp.lore.kernel.org (Postfix) with ESMTP id C8A3FC433EF for ; Fri, 27 May 2022 19:39:52 +0000 (UTC) Received: from [172.31.1.100] (localhost.localdomain [127.0.0.1]) by mail.librecores.org (Postfix) with ESMTP id A9F11248E4; Fri, 27 May 2022 21:39:51 +0200 (CEST) Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by mail.librecores.org (Postfix) with ESMTP id A2111247C2 for ; Fri, 27 May 2022 21:39:49 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1653680388; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=P+nCP3hGDIQjbSUxetjfsWamQ5hkJV0AFxpgoYCmvzQ7q8pCR076MkQ42jTe5t4jnLMrjZ WOlqBl9E2dk3wMnPZBRcdzV1QIX0Aor8CsdwK8eMRTt0jL72t7s9HzcdxOdBbC2oY9232g HRBDOHYVTbNUY2VTjYlcj1zY1uinMp0= Received: from mail-il1-f199.google.com (mail-il1-f199.google.com [209.85.166.199]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-307-SpD4_0-eOgKZt4S7FBAoLw-1; Fri, 27 May 2022 15:39:47 -0400 X-MC-Unique: SpD4_0-eOgKZt4S7FBAoLw-1 Received: by mail-il1-f199.google.com with SMTP id i18-20020a926d12000000b002d1b13b896cso3652984ilc.7 for ; Fri, 27 May 2022 12:39:44 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=IHRkli6m/7zFUvjVY1MyL9LnGnvjnse4bCil3eSZgN2Wbu9I0UDwdcE8T01/5QqX+6 KAQ2WEpS5eOunEI+JwCJe1XRyWX6EbC/ViRrtsbHO/JZaESn7cEswlaA1VHmqG8UVQkg XRjHt71URrO1gL7lZUNt4IAVvTAoxSu2rsIyoh3i0OU1nW8ehhmzOlCQSezlb11yhkpl dt7xvWlsdjB3UHI4ig/nhFRY9eDxKWzij/PiVoE05dwHXrGKP64Oj8CvCKl+csM56kmT wN5yUWe/hoJN3X9FGsOOM+iRq5I7Bji2b8o8xp+k7rVWGPsnNtphoI182QySkih5RNGU Lvyw== X-Gm-Message-State: AOAM533AFnZRAe7FWxBzNYtWc+ySGLVnKzM+fQh0aplyOUmH1TVCsBi6 u51GFoHwlYtOuG4lsmxJjHrGoQ1+wifdWoDOcRXxITOVQG0EzbQ1ssJ2ITRC86NXHVnaYqdkFrg g3sh4ZSUzlgAWF3fZciuA/dGQ5w== X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834930jal.212.1653680383783; Fri, 27 May 2022 12:39:43 -0700 (PDT) X-Google-Smtp-Source: ABdhPJycszExypDCmz/kq06KoOIqbe7IWTgWCyXrKhxfATY7rwpEo/+Qx+suJB7x0DjnJcxaZa6AhQ== X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834857jal.212.1653680383300; Fri, 27 May 2022 12:39:43 -0700 (PDT) Received: from localhost.localdomain (cpec09435e3e0ee-cmc09435e3e0ec.cpe.net.cable.rogers.com. [99.241.198.116]) by smtp.gmail.com with ESMTPSA id t2-20020a92c902000000b002d10291f973sm1530215ilp.4.2022.05.27.12.39.37 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Fri, 27 May 2022 12:39:42 -0700 (PDT) From: Peter Xu To: linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: [PATCH v4] mm: Avoid unnecessary page fault retires on shared memory types Date: Fri, 27 May 2022 15:39:36 -0400 Message-Id: <20220527193936.30678-1-peterx@redhat.com> X-Mailer: git-send-email 2.32.0 MIME-Version: 1.0 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=peterx@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-type: text/plain Content-Transfer-Encoding: 8bit X-BeenThere: openrisc@lists.librecores.org X-Mailman-Version: 2.1.26 Precedence: list List-Id: Discussion around the OpenRISC processor List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Christian Borntraeger , Rich Felker , linux-ia64@vger.kernel.org, David Hildenbrand , Peter Zijlstra , Benjamin Herrenschmidt , Dave Hansen , x86@kernel.org, peterx@redhat.com, "James E . J . Bottomley" , Max Filippov , Guo Ren , "H . Peter Anvin" , sparclinux@vger.kernel.org, linux-hexagon@vger.kernel.org, Alexander Gordeev , Will Deacon , Thomas Gleixner , Paul Mackerras , Anton Ivanov , Jonas Bonn , linux-s390@vger.kernel.org, Janosch Frank , Yoshinori Sato , linux-sh@vger.kernel.org, Michael Ellerman , Helge Deller , Alistair Popple , Hugh Dickins , Russell King , linux-csky@vger.kernel.org, Ingo Molnar , Andrea Arcangeli , linux-arm-kernel@lists.infradead.org, Vineet Gupta , Matt Turner , linux-snps-arc@lists.infradead.org, Catalin Marinas , linux-xtensa@linux-xtensa.org, Albert Ou , Vasily Gorbik , Chris Zankel , Heiko Carstens , Johannes Weiner , linux-um@lists.infradead.org, Nicholas Piggin , Richard Weinberger , linux-m68k@lists.linux-m68k.org, openrisc@lists.librecores.org, Borislav Petkov , Al Viro , Andy Lutomirski , Paul Walmsley , Ingo Molnar , Vlastimil Babka , Richard Henderson , Brian Cain , Michal Simek , Thomas Bogendoerfer , linux-parisc@vger.kernel.org, linux-mips@vger.kernel.org, Johannes Berg , Dinh Nguyen , linux-riscv@lists.infradead.org, Palmer Dabbelt , Sven Schnelle , linux-alpha@vger.kernel.org, Ivan Kokshaysky , Andrew Morton , linuxppc-dev@lists.ozlabs.org, "David S . Miller" Errors-To: openrisc-bounces@lists.librecores.org Sender: "OpenRISC" I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. 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%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Signed-off-by: Peter Xu --- v4: - Picked up a-bs and r-bs - Fix grammar in the comment of faultin_page() [Ingo] - Fix s390 for gmap since gmap needs the mmap lock [Heiko] v3: - Rebase to akpm/mm-unstable - Copy arch maintainers --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ do_page_fault(unsigned long address, unsigned long mmcsr, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 77341b160aca..e401d416bbd6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned int esr, return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 44f98100e84e..6f72bac39bf2 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 80bb66ad42f6..c18f7abd64df 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -167,6 +167,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..fe57175a7792 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -309,6 +309,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 4e9efbe46d5f..d6a87f4137ca 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -330,6 +330,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..4608cc962ecf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + /* + * Gmap will need the mmap lock again, so retake it. TODO: + * only conditionally take the lock when CONFIG_PGSTE set. + */ + mmap_read_lock(mm); + goto out_gmap; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..12ed70b432d6 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ void do_user_addr_fault(struct pt_regs *regs, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 06d0973a0d74..5f64305ba8d7 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -118,6 +118,10 @@ void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c09b7f0555b8..decc275db3c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 2e07cff3b31b..a63d330b9d43 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * 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_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ static long __get_user_pages(struct mm_struct *mm, case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ int fixup_user_fault(struct mm_struct *mm, return -EINTR; 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; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 54d106e0c999..a8be2d7a8718 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- 2.32.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from lists.ozlabs.org (lists.ozlabs.org [112.213.38.117]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id B782BC433F5 for ; Fri, 27 May 2022 22:28:30 +0000 (UTC) Received: from boromir.ozlabs.org (localhost [IPv6:::1]) by lists.ozlabs.org (Postfix) with ESMTP id 4L8zwX6rrKz3cfy for ; Sat, 28 May 2022 08:28:28 +1000 (AEST) Authentication-Results: lists.ozlabs.org; dkim=fail reason="signature verification failed" (1024-bit key; unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=br3/8/79; dkim=fail reason="signature verification failed" (1024-bit key) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=TzjzUrMW; dkim-atps=neutral Authentication-Results: lists.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=redhat.com (client-ip=170.10.129.124; helo=us-smtp-delivery-124.mimecast.com; envelope-from=peterx@redhat.com; receiver=) Authentication-Results: lists.ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=br3/8/79; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=TzjzUrMW; dkim-atps=neutral Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 4L8wB85j6rz3bkb for ; Sat, 28 May 2022 05:39:58 +1000 (AEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1653680395; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=br3/8/79OR4qbsSN25sZWO8LPgJOSdEdBfttZJ81qfiDlSWRzZ9kCXUnKIeHnWp5bO2+Od JHefyhatVCYKaXBiyEoGgR3AXopNeusBIXQVYjHrLcuoak/J7EMKrmfhriSv33kYBOF48v lQDuxLYPp3IAjuq2eVNy/48b9Agqf6c= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1653680396; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=TzjzUrMW8JfAo4I9QLpGdajU44zE1VN4zaLEj8caEs13dlUZTOnkL9dYjQ6wDLZY7mSCGK PSndsl+Z65W5fE/0l0ZHSaHIQS11cOHmjW2CZgT+5aYiWp3VurulHIx+ezpUHdWoXxdmpR yvnu5QK+G21OCknLM2a/cDbl98DsJnI= Received: from mail-il1-f200.google.com (mail-il1-f200.google.com [209.85.166.200]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-363-IxWvsZncPVO8pqT1Xfz6mA-1; Fri, 27 May 2022 15:39:47 -0400 X-MC-Unique: IxWvsZncPVO8pqT1Xfz6mA-1 Received: by mail-il1-f200.google.com with SMTP id x8-20020a056e021ca800b002d1332831deso3618820ill.23 for ; Fri, 27 May 2022 12:39:44 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=fCtMhDzDVGSC7jFQFMcI2fB77euLRrXSudOcTvWuY5aaXi7zQk+s3RPsNHuzJYJUoL 3VOhzUQ/8NgSO7H+Lk4L7g079HTL13Bt02G0/XkRUyGFV9Wzqz7XU8xy4s+Q5dIR21Lj aCecLE/AXR3vymewxbIZb0ClvEFJoP7ZLSSF4JHicyeF+u0ZB/zM7C/gDeuaDfC1GJ+F Ax00QAHiq78ZiUl2gQmM/T10hMcQ4lLkvPD6iZi+hX1CAV/u3wVdYC+a6X5vk81a6Unf bg0doCIl9H75SMaGILNVJGu0FNR8enbdSNBtol50nWYjDWM8c9lvDfYg5eLTXfUy/qQd RMJg== X-Gm-Message-State: AOAM533qAfIZT+Nyc+QsvQ7QFhwXEtLdMiMxH0iDZ4lgrGvEoyXFwqgY 4sBm+mVBJcvD/PzJN22XC2XD2hM5utlme89E6L+yXMlgKzjuJa7lBTrG0MSmkiZ1ZRaoawv/Hg7 p64AOpAL/1HnPTZsdckvrA2jsFw== X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834919jal.212.1653680383742; Fri, 27 May 2022 12:39:43 -0700 (PDT) X-Google-Smtp-Source: ABdhPJycszExypDCmz/kq06KoOIqbe7IWTgWCyXrKhxfATY7rwpEo/+Qx+suJB7x0DjnJcxaZa6AhQ== X-Received: by 2002:a05:6638:1925:b0:32e:dc08:ced3 with SMTP id p37-20020a056638192500b0032edc08ced3mr11834857jal.212.1653680383300; Fri, 27 May 2022 12:39:43 -0700 (PDT) Received: from localhost.localdomain (cpec09435e3e0ee-cmc09435e3e0ec.cpe.net.cable.rogers.com. [99.241.198.116]) by smtp.gmail.com with ESMTPSA id t2-20020a92c902000000b002d10291f973sm1530215ilp.4.2022.05.27.12.39.37 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Fri, 27 May 2022 12:39:42 -0700 (PDT) From: Peter Xu To: linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: [PATCH v4] mm: Avoid unnecessary page fault retires on shared memory types Date: Fri, 27 May 2022 15:39:36 -0400 Message-Id: <20220527193936.30678-1-peterx@redhat.com> X-Mailer: git-send-email 2.32.0 MIME-Version: 1.0 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=peterx@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-type: text/plain Content-Transfer-Encoding: 8bit X-Mailman-Approved-At: Sat, 28 May 2022 08:25:59 +1000 X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Christian Borntraeger , Rich Felker , linux-ia64@vger.kernel.org, David Hildenbrand , Peter Zijlstra , Dave Hansen , x86@kernel.org, peterx@redhat.com, "James E . J . Bottomley" , Max Filippov , Guo Ren , "H . Peter Anvin" , sparclinux@vger.kernel.org, linux-hexagon@vger.kernel.org, Alexander Gordeev , Will Deacon , Thomas Gleixner , Paul Mackerras , Anton Ivanov , Jonas Bonn , linux-s390@vger.kernel.org, Janosch Frank , Yoshinori Sato , linux-sh@vger.kernel.org, Helge Deller , Alistair Popple , Hugh Dickins , Russell King , linux-csky@vger.kernel.org, Ingo Molnar , Andrea Arcangeli , Geert Uytterhoeven , linux-arm-kernel@lists.infradead.org, Vineet Gupta , Matt Turner , linux-snps-arc@lists.infradead.org, Catalin Marinas , linux-xtensa@linux-xtensa.org, Albert Ou , Vasily Gorbik , Chris Zankel , Heiko Carstens , Johannes Weiner , linux-um@lists.infradead.org, Nicholas Piggin , Stefan Kristiansson , Richard Weinberger , linux-m68k@lists.linux-m68k.org, openrisc@lists.librecores.org, Borislav Petkov , Al Viro , Andy Lutomirski , Paul Walmsley , Stafford Horne , Ingo Molnar , Vlastimil Babka , Richard Henderson , Brian Cain , Michal Simek , Thomas Bogendoerfer , linux-parisc@vger.kernel.org, linux-mips@vger.kernel.org, Johannes Berg , Dinh Nguyen , linux-riscv@lists.infradead.org, Palmer Dabbelt , Sven Schnelle , linux-alpha@vger.kernel.org, Ivan Kokshaysky , Andrew Morton , linuxppc-dev@lists.ozlabs.org, "David S . Miller" Errors-To: linuxppc-dev-bounces+linuxppc-dev=archiver.kernel.org@lists.ozlabs.org Sender: "Linuxppc-dev" I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. 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%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Signed-off-by: Peter Xu --- v4: - Picked up a-bs and r-bs - Fix grammar in the comment of faultin_page() [Ingo] - Fix s390 for gmap since gmap needs the mmap lock [Heiko] v3: - Rebase to akpm/mm-unstable - Copy arch maintainers --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ do_page_fault(unsigned long address, unsigned long mmcsr, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 77341b160aca..e401d416bbd6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned int esr, return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 44f98100e84e..6f72bac39bf2 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 80bb66ad42f6..c18f7abd64df 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -167,6 +167,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..fe57175a7792 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -309,6 +309,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 4e9efbe46d5f..d6a87f4137ca 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -330,6 +330,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..4608cc962ecf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + /* + * Gmap will need the mmap lock again, so retake it. TODO: + * only conditionally take the lock when CONFIG_PGSTE set. + */ + mmap_read_lock(mm); + goto out_gmap; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..12ed70b432d6 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ void do_user_addr_fault(struct pt_regs *regs, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 06d0973a0d74..5f64305ba8d7 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -118,6 +118,10 @@ void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c09b7f0555b8..decc275db3c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 2e07cff3b31b..a63d330b9d43 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * 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_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ static long __get_user_pages(struct mm_struct *mm, case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ int fixup_user_fault(struct mm_struct *mm, return -EINTR; 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; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 54d106e0c999..a8be2d7a8718 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- 2.32.0 From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Xu Date: Fri, 27 May 2022 19:39:36 +0000 Subject: [PATCH v4] mm: Avoid unnecessary page fault retires on shared memory types Message-Id: <20220527193936.30678-1-peterx@redhat.com> List-Id: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: Will Deacon , Matt Turner , linux-s390@vger.kernel.org, Andrew Morton , Brian Cain , Borislav Petkov , linux-alpha@vger.kernel.org, Alistair Popple , Jonas Bonn , linux-arm-kernel@lists.infradead.org, linux-ia64@vger.kernel.org, Michael Ellerman , Stefan Kristiansson , linux-snps-arc@lists.infradead.org, Vineet Gupta , Vasily Gorbik , Vlastimil Babka , Ivan Kokshaysky , Rich Felker , sparclinux@vger.kernel.org, Russell King , David Hildenbrand , Benjamin Herrenschmidt , Nicholas Piggin , "James E . J . Bottomley" , linux-xtensa@linux-xtensa.org, linux-sh@vger.kernel.org, Paul Walmsley , linux-m68k@lists.linux-m68k.org, linuxppc-dev@lists.ozlabs.org, Richard Henderson , Guo Ren , linux-parisc@vger.kernel.org, Andrea Arcangeli , Helge Deller , Al Viro , Albert Ou , linux-um@lists.infradead.org, "H . Peter Anvin" , Janosch Frank , Sven Schnelle , Anton Ivanov , openrisc@lists.librecores.org, Thomas Bogendoerfer , linux-hexagon@vger.kernel.org, Andy Lutomirski , Stafford Horne , linux-csky@vger.kernel.org, Heiko Carstens , Thomas Gleixner , linux-mips@vger.kernel.org, Paul Mackerras , Alexander Gordeev , Dinh Nguyen , Palmer Dabbelt , "David S . Miller" , Johannes Weiner , Hugh Dickins , Ingo Molnar , Peter Zijlstra , linux-riscv@lists.infradead.org, Max Filippov , Catalin Marinas , Geert Uytterhoeven , Christian Borntraeger , Johannes Berg , Chris Zankel , Michal Simek , x86@kernel.org, Yoshinori Sato , peterx@redhat.com, Dave Hansen , Richard Weinberger , Ingo Molnar I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. 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%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Signed-off-by: Peter Xu --- v4: - Picked up a-bs and r-bs - Fix grammar in the comment of faultin_page() [Ingo] - Fix s390 for gmap since gmap needs the mmap lock [Heiko] v3: - Rebase to akpm/mm-unstable - Copy arch maintainers --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ do_page_fault(unsigned long address, unsigned long mmcsr, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 77341b160aca..e401d416bbd6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned int esr, return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 44f98100e84e..6f72bac39bf2 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 80bb66ad42f6..c18f7abd64df 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -167,6 +167,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..fe57175a7792 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -309,6 +309,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 4e9efbe46d5f..d6a87f4137ca 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -330,6 +330,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..4608cc962ecf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + /* + * Gmap will need the mmap lock again, so retake it. TODO: + * only conditionally take the lock when CONFIG_PGSTE set. + */ + mmap_read_lock(mm); + goto out_gmap; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..12ed70b432d6 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ void do_user_addr_fault(struct pt_regs *regs, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 06d0973a0d74..5f64305ba8d7 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -118,6 +118,10 @@ void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c09b7f0555b8..decc275db3c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 2e07cff3b31b..a63d330b9d43 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * 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_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ static long __get_user_pages(struct mm_struct *mm, case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ int fixup_user_fault(struct mm_struct *mm, return -EINTR; 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; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 54d106e0c999..a8be2d7a8718 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- 2.32.0 From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Xu Subject: [PATCH v4] mm: Avoid unnecessary page fault retires on shared memory types Date: Fri, 27 May 2022 15:39:36 -0400 Message-ID: <20220527193936.30678-1-peterx@redhat.com> Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1653680387; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=zdu7Pg4zKxm1uKLLvvDVMRmZFDVUqRIRXozl857+hu4=; b=L0kMBCHt15CG6+V7WoGbVztagBXB5ENxlWVIb9hi6uRzrpjLsXcQX2qcw5KvkP7ajKqVEr LzTqHav4hVbT1GhDwMtQ9DCYcQG7FZVQTBei/CMO0cNjtY2Du0PHfx+wKnKkFJgmLiFOxD 60G5HGDyiXUMIAmRf9k551KAuA5E/4A= List-ID: Content-Type: text/plain; charset="us-ascii" To: linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: Will Deacon , Matt Turner , linux-s390@vger.kernel.org, Andrew Morton , Brian Cain , Borislav Petkov , linux-alpha@vger.kernel.org, Alistair Popple , Jonas Bonn , linux-arm-kernel@lists.infradead.org, linux-ia64@vger.kernel.org, Michael Ellerman , Stefan Kristiansson , linux-snps-arc@lists.infradead.org, Vineet Gupta , Vasily Gorbik , Vlastimil Babka , Ivan Kokshaysky , Rich Felker , sparclinux@vger.kernel.org, Russell King , David Hildenbrand I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. 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%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Signed-off-by: Peter Xu --- v4: - Picked up a-bs and r-bs - Fix grammar in the comment of faultin_page() [Ingo] - Fix s390 for gmap since gmap needs the mmap lock [Heiko] v3: - Rebase to akpm/mm-unstable - Copy arch maintainers --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ do_page_fault(unsigned long address, unsigned long mmcsr, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 77341b160aca..e401d416bbd6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned int esr, return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 44f98100e84e..6f72bac39bf2 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 80bb66ad42f6..c18f7abd64df 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -167,6 +167,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..fe57175a7792 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -309,6 +309,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 4e9efbe46d5f..d6a87f4137ca 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -330,6 +330,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..4608cc962ecf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + /* + * Gmap will need the mmap lock again, so retake it. TODO: + * only conditionally take the lock when CONFIG_PGSTE set. + */ + mmap_read_lock(mm); + goto out_gmap; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..12ed70b432d6 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ void do_user_addr_fault(struct pt_regs *regs, return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 06d0973a0d74..5f64305ba8d7 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -118,6 +118,10 @@ void do_page_fault(struct pt_regs *regs) return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c09b7f0555b8..decc275db3c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 2e07cff3b31b..a63d330b9d43 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * 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_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ static long __get_user_pages(struct mm_struct *mm, case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ int fixup_user_fault(struct mm_struct *mm, return -EINTR; 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; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 54d106e0c999..a8be2d7a8718 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- 2.32.0