From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Subject: Re: [RFC PATCH v5 4/8] mm: tlb: Pass struct mmu_gather to flush_pmd_tlb_range Date: Thu, 2 Apr 2020 18:38:49 +0200 Message-ID: <20200402163849.GM20713@hirez.programming.kicks-ass.net> References: <20200331142927.1237-1-yezhenyu2@huawei.com> <20200331142927.1237-5-yezhenyu2@huawei.com> <20200331151331.GS20730@hirez.programming.kicks-ass.net> <20200401122004.GE20713@hirez.programming.kicks-ass.net> <53675fb9-21c7-5309-07b8-1bbc1e775f9b@huawei.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: <53675fb9-21c7-5309-07b8-1bbc1e775f9b@huawei.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=m.gmane-mx.org@lists.infradead.org To: Zhenyu Ye Cc: mark.rutland@arm.com, catalin.marinas@arm.com, linux-mm@kvack.org, guohanjun@huawei.com, will@kernel.org, linux-arch@vger.kernel.org, yuzhao@google.com, corbet@lwn.net, maz@kernel.org, steven.price@arm.com, arm@kernel.org, Dave.Martin@arm.com, arnd@arndb.de, suzuki.poulose@arm.com, npiggin@gmail.com, zhangshaokun@hisilicon.com, broonie@kernel.org, rostedt@goodmis.org, prime.zeng@hisilicon.com, kuhn.chenqun@huawei.com, tglx@linutronix.de, linux-arm-kernel@lists.infradead.org, xiexiangyou@huawei.com, tony.luck@intel.com, vgupta@synopsys.com, linux-kernel@vger.kernel.org, aneesh.kumar@linux.ibm.com, akpm@linux-foundation.org List-Id: linux-arch.vger.kernel.org On Thu, Apr 02, 2020 at 07:24:04PM +0800, Zhenyu Ye wrote: > Thanks for your detailed explanation. I notice that you used > `tlb_end_vma` replace `flush_tlb_range`, which will call `tlb_flush`, > then finally call `flush_tlb_range` in generic code. However, some > architectures define tlb_end_vma|tlb_flush|flush_tlb_range themselves, > so this may cause problems. > > For example, in s390, it defines: > > #define tlb_end_vma(tlb, vma) do { } while (0) > > And it doesn't define it's own flush_pmd_tlb_range(). So there will be > a mistake if we changed flush_pmd_tlb_range() using tlb_end_vma(). > > Is this really a problem or something I understand wrong ? If tlb_end_vma() is a no-op, then tlb_finish_mmu() will do: tlb_flush_mmu() -> tlb_flush_mmu_tlbonly() -> tlb_flush() And s390 has tlb_flush(). If tlb_end_vma() is not a no-op and it calls tlb_flush_mmu_tlbonly(), then tlb_finish_mmu()'s invocation of tlb_flush_mmu_tlbonly() will terniate early due o no flags set. IOW, it should all just work. FYI the whole tlb_{start,end}_vma() thing is a only needed when the architecture doesn't implement tlb_flush() and instead default to using flush_tlb_range(), at which point we need to provide a 'fake' vma. At the time I audited all architectures and they only look at VM_EXEC (to do $I invalidation) and VM_HUGETLB (for pmd level invalidations), but I forgot which architectures that were. But that is all legacy code; eventually we'll get all archs a native tlb_flush() and this can go away. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Thu, 2 Apr 2020 18:38:49 +0200 From: Peter Zijlstra Subject: Re: [RFC PATCH v5 4/8] mm: tlb: Pass struct mmu_gather to flush_pmd_tlb_range Message-ID: <20200402163849.GM20713@hirez.programming.kicks-ass.net> References: <20200331142927.1237-1-yezhenyu2@huawei.com> <20200331142927.1237-5-yezhenyu2@huawei.com> <20200331151331.GS20730@hirez.programming.kicks-ass.net> <20200401122004.GE20713@hirez.programming.kicks-ass.net> <53675fb9-21c7-5309-07b8-1bbc1e775f9b@huawei.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <53675fb9-21c7-5309-07b8-1bbc1e775f9b@huawei.com> Sender: owner-linux-mm@kvack.org To: Zhenyu Ye Cc: mark.rutland@arm.com, will@kernel.org, catalin.marinas@arm.com, aneesh.kumar@linux.ibm.com, akpm@linux-foundation.org, npiggin@gmail.com, arnd@arndb.de, rostedt@goodmis.org, maz@kernel.org, suzuki.poulose@arm.com, tglx@linutronix.de, yuzhao@google.com, Dave.Martin@arm.com, steven.price@arm.com, broonie@kernel.org, guohanjun@huawei.com, corbet@lwn.net, vgupta@synopsys.com, tony.luck@intel.com, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linux-mm@kvack.org, arm@kernel.org, xiexiangyou@huawei.com, prime.zeng@hisilicon.com, zhangshaokun@hisilicon.com, kuhn.chenqun@huawei.com List-ID: Message-ID: <20200402163849.8PaLnsXpUNKYw7MZw9UXHchyP0AkWxaXitTymXHD4ug@z> On Thu, Apr 02, 2020 at 07:24:04PM +0800, Zhenyu Ye wrote: > Thanks for your detailed explanation. I notice that you used > `tlb_end_vma` replace `flush_tlb_range`, which will call `tlb_flush`, > then finally call `flush_tlb_range` in generic code. However, some > architectures define tlb_end_vma|tlb_flush|flush_tlb_range themselves, > so this may cause problems. > > For example, in s390, it defines: > > #define tlb_end_vma(tlb, vma) do { } while (0) > > And it doesn't define it's own flush_pmd_tlb_range(). So there will be > a mistake if we changed flush_pmd_tlb_range() using tlb_end_vma(). > > Is this really a problem or something I understand wrong ? If tlb_end_vma() is a no-op, then tlb_finish_mmu() will do: tlb_flush_mmu() -> tlb_flush_mmu_tlbonly() -> tlb_flush() And s390 has tlb_flush(). If tlb_end_vma() is not a no-op and it calls tlb_flush_mmu_tlbonly(), then tlb_finish_mmu()'s invocation of tlb_flush_mmu_tlbonly() will terniate early due o no flags set. IOW, it should all just work. FYI the whole tlb_{start,end}_vma() thing is a only needed when the architecture doesn't implement tlb_flush() and instead default to using flush_tlb_range(), at which point we need to provide a 'fake' vma. At the time I audited all architectures and they only look at VM_EXEC (to do $I invalidation) and VM_HUGETLB (for pmd level invalidations), but I forgot which architectures that were. But that is all legacy code; eventually we'll get all archs a native tlb_flush() and this can go away.