From mboxrd@z Thu Jan 1 00:00:00 1970 From: Leonardo Bras Subject: [PATCH v3 00/11] Introduces new count-based method for monitoring lockless pagetable walks Date: Tue, 24 Sep 2019 18:24:17 -0300 Message-ID: <20190924212427.7734-1-leonardo@linux.ibm.com> Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Return-path: Sender: linux-kernel-owner@vger.kernel.org To: linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, kvm-ppc@vger.kernel.org, linux-arch@vger.kernel.org, linux-mm@kvack.org Cc: Leonardo Bras , Benjamin Herrenschmidt , Paul Mackerras , Michael Ellerman , Arnd Bergmann , "Aneesh Kumar K.V" , Christophe Leroy , Andrew Morton , Dan Williams , Nicholas Piggin , Mahesh Salgaonkar , Greg Kroah-Hartman , Thomas Gleixner , Ganesh Goudar , Allison Randal , Mike Rapoport , YueHaibing , Ira Weiny , Jason Gunthorpe List-Id: linux-arch.vger.kernel.org If a process (qemu) with a lot of CPUs (128) try to munmap() a large chunk of memory (496GB) mapped with THP, it takes an average of 275 seconds, which can cause a lot of problems to the load (in qemu case, the guest will lock for this time). Trying to find the source of this bug, I found out most of this time is spent on serialize_against_pte_lookup(). This function will take a lot of time in smp_call_function_many() if there is more than a couple CPUs running the user process. Since it has to happen to all THP mapped, it will take a very long time for large amounts of memory. By the docs, serialize_against_pte_lookup() is needed in order to avoid pmd_t to pte_t casting inside find_current_mm_pte(), or any lockless pagetable walk, to happen concurrently with THP splitting/collapsing. It does so by calling a do_nothing() on each CPU in mm->cpu_bitmap[], after interrupts are re-enabled. Since, interrupts are (usually) disabled during lockless pagetable walk, and serialize_against_pte_lookup will only return after interrupts are enabled, it is protected. So, by what I could understand, if there is no lockless pagetable walk running, there is no need to call serialize_against_pte_lookup(). So, to avoid the cost of running serialize_against_pte_lookup(), I propose a counter that keeps track of how many find_current_mm_pte() are currently running, and if there is none, just skip smp_call_function_many(). The related functions are: start_lockless_pgtbl_walk(mm) Insert before starting any lockless pgtable walk end_lockless_pgtbl_walk(mm) Insert after the end of any lockless pgtable walk (Mostly after the ptep is last used) running_lockless_pgtbl_walk(mm) Returns the number of lockless pgtable walks running On my workload (qemu), I could see munmap's time reduction from 275 seconds to 418ms. Changes since v2: Rebased to v5.3 Adds support on __get_user_pages_fast Adds usage decription to *_lockless_pgtbl_walk() Better style to dummy functions Link: http://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=131839 Changes since v1: Isolated atomic operations in functions *_lockless_pgtbl_walk() Fixed behavior of decrementing before last ptep was used Link: http://patchwork.ozlabs.org/patch/1163093/ Leonardo Bras (11): powerpc/mm: Adds counting method to monitor lockless pgtable walks asm-generic/pgtable: Adds dummy functions to monitor lockless pgtable walks mm/gup: Applies counting method to monitor gup_pgd_range powerpc/mce_power: Applies counting method to monitor lockless pgtbl walks powerpc/perf: Applies counting method to monitor lockless pgtbl walks powerpc/mm/book3s64/hash: Applies counting method to monitor lockless pgtbl walks powerpc/kvm/e500: Applies counting method to monitor lockless pgtbl walks powerpc/kvm/book3s_hv: Applies counting method to monitor lockless pgtbl walks powerpc/kvm/book3s_64: Applies counting method to monitor lockless pgtbl walks powerpc/book3s_64: Enables counting method to monitor lockless pgtbl walk powerpc/mm/book3s64/pgtable: Uses counting method to skip serializing arch/powerpc/include/asm/book3s/64/mmu.h | 3 ++ arch/powerpc/include/asm/book3s/64/pgtable.h | 5 +++ arch/powerpc/kernel/mce_power.c | 13 +++++-- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 + arch/powerpc/kvm/book3s_64_mmu_radix.c | 20 +++++++++- arch/powerpc/kvm/book3s_64_vio_hv.c | 4 ++ arch/powerpc/kvm/book3s_hv_nested.c | 8 ++++ arch/powerpc/kvm/book3s_hv_rm_mmu.c | 9 ++++- arch/powerpc/kvm/e500_mmu_host.c | 4 ++ arch/powerpc/mm/book3s64/hash_tlb.c | 2 + arch/powerpc/mm/book3s64/hash_utils.c | 7 ++++ arch/powerpc/mm/book3s64/mmu_context.c | 1 + arch/powerpc/mm/book3s64/pgtable.c | 40 +++++++++++++++++++- arch/powerpc/perf/callchain.c | 5 ++- include/asm-generic/pgtable.h | 15 ++++++++ mm/gup.c | 8 ++++ 16 files changed, 138 insertions(+), 8 deletions(-) -- 2.20.1 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0a-001b2d01.pphosted.com ([148.163.156.1]:33788 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728386AbfIXVZZ (ORCPT ); Tue, 24 Sep 2019 17:25:25 -0400 From: Leonardo Bras Subject: [PATCH v3 00/11] Introduces new count-based method for monitoring lockless pagetable walks Date: Tue, 24 Sep 2019 18:24:17 -0300 Message-ID: <20190924212427.7734-1-leonardo@linux.ibm.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: linux-arch-owner@vger.kernel.org List-ID: To: linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, kvm-ppc@vger.kernel.org, linux-arch@vger.kernel.org, linux-mm@kvack.org Cc: Leonardo Bras , Benjamin Herrenschmidt , Paul Mackerras , Michael Ellerman , Arnd Bergmann , "Aneesh Kumar K.V" , Christophe Leroy , Andrew Morton , Dan Williams , Nicholas Piggin , Mahesh Salgaonkar , Greg Kroah-Hartman , Thomas Gleixner , Ganesh Goudar , Allison Randal , Mike Rapoport , YueHaibing , Ira Weiny , Jason Gunthorpe , John Hubbard , Keith Busch Message-ID: <20190924212417.SP8F0h9OYL0SH6g09EXsD5iEmBokPtTkc8UYs8xcqqc@z> If a process (qemu) with a lot of CPUs (128) try to munmap() a large chunk of memory (496GB) mapped with THP, it takes an average of 275 seconds, which can cause a lot of problems to the load (in qemu case, the guest will lock for this time). Trying to find the source of this bug, I found out most of this time is spent on serialize_against_pte_lookup(). This function will take a lot of time in smp_call_function_many() if there is more than a couple CPUs running the user process. Since it has to happen to all THP mapped, it will take a very long time for large amounts of memory. By the docs, serialize_against_pte_lookup() is needed in order to avoid pmd_t to pte_t casting inside find_current_mm_pte(), or any lockless pagetable walk, to happen concurrently with THP splitting/collapsing. It does so by calling a do_nothing() on each CPU in mm->cpu_bitmap[], after interrupts are re-enabled. Since, interrupts are (usually) disabled during lockless pagetable walk, and serialize_against_pte_lookup will only return after interrupts are enabled, it is protected. So, by what I could understand, if there is no lockless pagetable walk running, there is no need to call serialize_against_pte_lookup(). So, to avoid the cost of running serialize_against_pte_lookup(), I propose a counter that keeps track of how many find_current_mm_pte() are currently running, and if there is none, just skip smp_call_function_many(). The related functions are: start_lockless_pgtbl_walk(mm) Insert before starting any lockless pgtable walk end_lockless_pgtbl_walk(mm) Insert after the end of any lockless pgtable walk (Mostly after the ptep is last used) running_lockless_pgtbl_walk(mm) Returns the number of lockless pgtable walks running On my workload (qemu), I could see munmap's time reduction from 275 seconds to 418ms. Changes since v2: Rebased to v5.3 Adds support on __get_user_pages_fast Adds usage decription to *_lockless_pgtbl_walk() Better style to dummy functions Link: http://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=131839 Changes since v1: Isolated atomic operations in functions *_lockless_pgtbl_walk() Fixed behavior of decrementing before last ptep was used Link: http://patchwork.ozlabs.org/patch/1163093/ Leonardo Bras (11): powerpc/mm: Adds counting method to monitor lockless pgtable walks asm-generic/pgtable: Adds dummy functions to monitor lockless pgtable walks mm/gup: Applies counting method to monitor gup_pgd_range powerpc/mce_power: Applies counting method to monitor lockless pgtbl walks powerpc/perf: Applies counting method to monitor lockless pgtbl walks powerpc/mm/book3s64/hash: Applies counting method to monitor lockless pgtbl walks powerpc/kvm/e500: Applies counting method to monitor lockless pgtbl walks powerpc/kvm/book3s_hv: Applies counting method to monitor lockless pgtbl walks powerpc/kvm/book3s_64: Applies counting method to monitor lockless pgtbl walks powerpc/book3s_64: Enables counting method to monitor lockless pgtbl walk powerpc/mm/book3s64/pgtable: Uses counting method to skip serializing arch/powerpc/include/asm/book3s/64/mmu.h | 3 ++ arch/powerpc/include/asm/book3s/64/pgtable.h | 5 +++ arch/powerpc/kernel/mce_power.c | 13 +++++-- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 + arch/powerpc/kvm/book3s_64_mmu_radix.c | 20 +++++++++- arch/powerpc/kvm/book3s_64_vio_hv.c | 4 ++ arch/powerpc/kvm/book3s_hv_nested.c | 8 ++++ arch/powerpc/kvm/book3s_hv_rm_mmu.c | 9 ++++- arch/powerpc/kvm/e500_mmu_host.c | 4 ++ arch/powerpc/mm/book3s64/hash_tlb.c | 2 + arch/powerpc/mm/book3s64/hash_utils.c | 7 ++++ arch/powerpc/mm/book3s64/mmu_context.c | 1 + arch/powerpc/mm/book3s64/pgtable.c | 40 +++++++++++++++++++- arch/powerpc/perf/callchain.c | 5 ++- include/asm-generic/pgtable.h | 15 ++++++++ mm/gup.c | 8 ++++ 16 files changed, 138 insertions(+), 8 deletions(-) -- 2.20.1