Received-SPF: pass (google.com: domain of linux-kernel+bounces-5079-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Message-ID: <9d473ac7-ef52-4fa4-bb54-900176d987c9@redhat.com>
Date: Tue, 19 Dec 2023 12:29:23 +0100
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v4 02/16] mm: Batch-copy PTE ranges during fork()
Content-Language: en-US
To: Ryan Roberts <ryan.roberts@arm.com>,
 Catalin Marinas <catalin.marinas@arm.com>, Will Deacon <will@kernel.org>,
 Ard Biesheuvel <ardb@kernel.org>, Marc Zyngier <maz@kernel.org>,
 Oliver Upton <oliver.upton@linux.dev>, James Morse <james.morse@arm.com>,
 Suzuki K Poulose <suzuki.poulose@arm.com>, Zenghui Yu
 <yuzenghui@huawei.com>, Andrey Ryabinin <ryabinin.a.a@gmail.com>,
 Alexander Potapenko <glider@google.com>,
 Andrey Konovalov <andreyknvl@gmail.com>, Dmitry Vyukov <dvyukov@google.com>,
 Vincenzo Frascino <vincenzo.frascino@arm.com>,
 Andrew Morton <akpm@linux-foundation.org>,
 Anshuman Khandual <anshuman.khandual@arm.com>,
 Matthew Wilcox <willy@infradead.org>, Yu Zhao <yuzhao@google.com>,
 Mark Rutland <mark.rutland@arm.com>, Kefeng Wang
 <wangkefeng.wang@huawei.com>, John Hubbard <jhubbard@nvidia.com>,
 Zi Yan <ziy@nvidia.com>, Barry Song <21cnbao@gmail.com>,
 Alistair Popple <apopple@nvidia.com>, Yang Shi <shy828301@gmail.com>
Cc: linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org,
 linux-kernel@vger.kernel.org
References: <20231218105100.172635-1-ryan.roberts@arm.com>
 <20231218105100.172635-3-ryan.roberts@arm.com>
 <0bef5423-6eea-446b-8854-980e9c23a948@redhat.com>
 <db1be625-33e4-4d07-8500-3f7d3c8f9937@arm.com>
From: David Hildenbrand <david@redhat.com>
Autocrypt: addr=david@redhat.com; keydata=
 xsFNBFXLn5EBEAC+zYvAFJxCBY9Tr1xZgcESmxVNI/0ffzE/ZQOiHJl6mGkmA1R7/uUpiCjJ
 dBrn+lhhOYjjNefFQou6478faXE6o2AhmebqT4KiQoUQFV4R7y1KMEKoSyy8hQaK1umALTdL
 QZLQMzNE74ap+GDK0wnacPQFpcG1AE9RMq3aeErY5tujekBS32jfC/7AnH7I0v1v1TbbK3Gp
 XNeiN4QroO+5qaSr0ID2sz5jtBLRb15RMre27E1ImpaIv2Jw8NJgW0k/D1RyKCwaTsgRdwuK
 Kx/Y91XuSBdz0uOyU/S8kM1+ag0wvsGlpBVxRR/xw/E8M7TEwuCZQArqqTCmkG6HGcXFT0V9
 PXFNNgV5jXMQRwU0O/ztJIQqsE5LsUomE//bLwzj9IVsaQpKDqW6TAPjcdBDPLHvriq7kGjt
 WhVhdl0qEYB8lkBEU7V2Yb+SYhmhpDrti9Fq1EsmhiHSkxJcGREoMK/63r9WLZYI3+4W2rAc
 UucZa4OT27U5ZISjNg3Ev0rxU5UH2/pT4wJCfxwocmqaRr6UYmrtZmND89X0KigoFD/XSeVv
 jwBRNjPAubK9/k5NoRrYqztM9W6sJqrH8+UWZ1Idd/DdmogJh0gNC0+N42Za9yBRURfIdKSb
 B3JfpUqcWwE7vUaYrHG1nw54pLUoPG6sAA7Mehl3nd4pZUALHwARAQABzSREYXZpZCBIaWxk
 ZW5icmFuZCA8ZGF2aWRAcmVkaGF0LmNvbT7CwZgEEwEIAEICGwMGCwkIBwMCBhUIAgkKCwQW
 AgMBAh4BAheAAhkBFiEEG9nKrXNcTDpGDfzKTd4Q9wD/g1oFAl8Ox4kFCRKpKXgACgkQTd4Q
 9wD/g1oHcA//a6Tj7SBNjFNM1iNhWUo1lxAja0lpSodSnB2g4FCZ4R61SBR4l/psBL73xktp
 rDHrx4aSpwkRP6Epu6mLvhlfjmkRG4OynJ5HG1gfv7RJJfnUdUM1z5kdS8JBrOhMJS2c/gPf
 wv1TGRq2XdMPnfY2o0CxRqpcLkx4vBODvJGl2mQyJF/gPepdDfcT8/PY9BJ7FL6Hrq1gnAo4
 3Iv9qV0JiT2wmZciNyYQhmA1V6dyTRiQ4YAc31zOo2IM+xisPzeSHgw3ONY/XhYvfZ9r7W1l
 pNQdc2G+o4Di9NPFHQQhDw3YTRR1opJaTlRDzxYxzU6ZnUUBghxt9cwUWTpfCktkMZiPSDGd
 KgQBjnweV2jw9UOTxjb4LXqDjmSNkjDdQUOU69jGMUXgihvo4zhYcMX8F5gWdRtMR7DzW/YE
 BgVcyxNkMIXoY1aYj6npHYiNQesQlqjU6azjbH70/SXKM5tNRplgW8TNprMDuntdvV9wNkFs
 9TyM02V5aWxFfI42+aivc4KEw69SE9KXwC7FSf5wXzuTot97N9Phj/Z3+jx443jo2NR34XgF
 89cct7wJMjOF7bBefo0fPPZQuIma0Zym71cP61OP/i11ahNye6HGKfxGCOcs5wW9kRQEk8P9
 M/k2wt3mt/fCQnuP/mWutNPt95w9wSsUyATLmtNrwccz63XOwU0EVcufkQEQAOfX3n0g0fZz
 Bgm/S2zF/kxQKCEKP8ID+Vz8sy2GpDvveBq4H2Y34XWsT1zLJdvqPI4af4ZSMxuerWjXbVWb
 T6d4odQIG0fKx4F8NccDqbgHeZRNajXeeJ3R7gAzvWvQNLz4piHrO/B4tf8svmRBL0ZB5P5A
 2uhdwLU3NZuK22zpNn4is87BPWF8HhY0L5fafgDMOqnf4guJVJPYNPhUFzXUbPqOKOkL8ojk
 CXxkOFHAbjstSK5Ca3fKquY3rdX3DNo+EL7FvAiw1mUtS+5GeYE+RMnDCsVFm/C7kY8c2d0G
 NWkB9pJM5+mnIoFNxy7YBcldYATVeOHoY4LyaUWNnAvFYWp08dHWfZo9WCiJMuTfgtH9tc75
 7QanMVdPt6fDK8UUXIBLQ2TWr/sQKE9xtFuEmoQGlE1l6bGaDnnMLcYu+Asp3kDT0w4zYGsx
 5r6XQVRH4+5N6eHZiaeYtFOujp5n+pjBaQK7wUUjDilPQ5QMzIuCL4YjVoylWiBNknvQWBXS
 lQCWmavOT9sttGQXdPCC5ynI+1ymZC1ORZKANLnRAb0NH/UCzcsstw2TAkFnMEbo9Zu9w7Kv
 AxBQXWeXhJI9XQssfrf4Gusdqx8nPEpfOqCtbbwJMATbHyqLt7/oz/5deGuwxgb65pWIzufa
 N7eop7uh+6bezi+rugUI+w6DABEBAAHCwXwEGAEIACYCGwwWIQQb2cqtc1xMOkYN/MpN3hD3
 AP+DWgUCXw7HsgUJEqkpoQAKCRBN3hD3AP+DWrrpD/4qS3dyVRxDcDHIlmguXjC1Q5tZTwNB
 boaBTPHSy/Nksu0eY7x6HfQJ3xajVH32Ms6t1trDQmPx2iP5+7iDsb7OKAb5eOS8h+BEBDeq
 3ecsQDv0fFJOA9ag5O3LLNk+3x3q7e0uo06XMaY7UHS341ozXUUI7wC7iKfoUTv03iO9El5f
 XpNMx/YrIMduZ2+nd9Di7o5+KIwlb2mAB9sTNHdMrXesX8eBL6T9b+MZJk+mZuPxKNVfEQMQ
 a5SxUEADIPQTPNvBewdeI80yeOCrN+Zzwy/Mrx9EPeu59Y5vSJOx/z6OUImD/GhX7Xvkt3kq
 Er5KTrJz3++B6SH9pum9PuoE/k+nntJkNMmQpR4MCBaV/J9gIOPGodDKnjdng+mXliF3Ptu6
 3oxc2RCyGzTlxyMwuc2U5Q7KtUNTdDe8T0uE+9b8BLMVQDDfJjqY0VVqSUwImzTDLX9S4g/8
 kC4HRcclk8hpyhY2jKGluZO0awwTIMgVEzmTyBphDg/Gx7dZU1Xf8HFuE+UZ5UDHDTnwgv7E
 th6RC9+WrhDNspZ9fJjKWRbveQgUFCpe1sa77LAw+XFrKmBHXp9ZVIe90RMe2tRL06BGiRZr
 jPrnvUsUUsjRoRNJjKKA/REq+sAnhkNPPZ/NNMjaZ5b8Tovi8C0tmxiCHaQYqj7G2rgnT0kt
 WNyWQQ==
Organization: Red Hat
In-Reply-To: <db1be625-33e4-4d07-8500-3f7d3c8f9937@arm.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit

On 19.12.23 09:30, Ryan Roberts wrote:
> On 18/12/2023 17:47, David Hildenbrand wrote:
>> On 18.12.23 11:50, Ryan Roberts wrote:
>>> Convert copy_pte_range() to copy a batch of ptes in one go. A given
>>> batch is determined by the architecture with the new helper,
>>> pte_batch_remaining(), and maps a physically contiguous block of memory,
>>> all belonging to the same folio. A pte batch is then write-protected in
>>> one go in the parent using the new helper, ptep_set_wrprotects() and is
>>> set in one go in the child using the new helper, set_ptes_full().
>>>
>>> The primary motivation for this change is to reduce the number of tlb
>>> maintenance operations that the arm64 backend has to perform during
>>> fork, as it is about to add transparent support for the "contiguous bit"
>>> in its ptes. By write-protecting the parent using the new
>>> ptep_set_wrprotects() (note the 's' at the end) function, the backend
>>> can avoid having to unfold contig ranges of PTEs, which is expensive,
>>> when all ptes in the range are being write-protected. Similarly, by
>>> using set_ptes_full() rather than set_pte_at() to set up ptes in the
>>> child, the backend does not need to fold a contiguous range once they
>>> are all populated - they can be initially populated as a contiguous
>>> range in the first place.
>>>
>>> This code is very performance sensitive, and a significant amount of
>>> effort has been put into not regressing performance for the order-0
>>> folio case. By default, pte_batch_remaining() is compile constant 1,
>>> which enables the compiler to simplify the extra loops that are added
>>> for batching and produce code that is equivalent (and equally
>>> performant) as the previous implementation.
>>>
>>> This change addresses the core-mm refactoring only and a separate change
>>> will implement pte_batch_remaining(), ptep_set_wrprotects() and
>>> set_ptes_full() in the arm64 backend to realize the performance
>>> improvement as part of the work to enable contpte mappings.
>>>
>>> To ensure the arm64 is performant once implemented, this change is very
>>> careful to only call ptep_get() once per pte batch.
>>>
>>> The following microbenchmark results demonstate that there is no
>>> significant performance change after this patch. Fork is called in a
>>> tight loop in a process with 1G of populated memory and the time for the
>>> function to execute is measured. 100 iterations per run, 8 runs
>>> performed on both Apple M2 (VM) and Ampere Altra (bare metal). Tests
>>> performed for case where 1G memory is comprised of order-0 folios and
>>> case where comprised of pte-mapped order-9 folios. Negative is faster,
>>> positive is slower, compared to baseline upon which the series is based:
>>>
>>> | Apple M2 VM   | order-0 (pte-map) | order-9 (pte-map) |
>>> | fork          |-------------------|-------------------|
>>> | microbench    |    mean |   stdev |    mean |   stdev |
>>> |---------------|---------|---------|---------|---------|
>>> | baseline      |    0.0% |    1.1% |    0.0% |    1.2% |
>>> | after-change  |   -1.0% |    2.0% |   -0.1% |    1.1% |
>>>
>>> | Ampere Altra  | order-0 (pte-map) | order-9 (pte-map) |
>>> | fork          |-------------------|-------------------|
>>> | microbench    |    mean |   stdev |    mean |   stdev |
>>> |---------------|---------|---------|---------|---------|
>>> | baseline      |    0.0% |    1.0% |    0.0% |    0.1% |
>>> | after-change  |   -0.1% |    1.2% |   -0.1% |    0.1% |
>>>
>>> Tested-by: John Hubbard <jhubbard@nvidia.com>
>>> Reviewed-by: Alistair Popple <apopple@nvidia.com>
>>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>>> ---
>>>    include/linux/pgtable.h | 80 +++++++++++++++++++++++++++++++++++
>>>    mm/memory.c             | 92 ++++++++++++++++++++++++++---------------
>>>    2 files changed, 139 insertions(+), 33 deletions(-)
>>>
>>> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
>>> index af7639c3b0a3..db93fb81465a 100644
>>> --- a/include/linux/pgtable.h
>>> +++ b/include/linux/pgtable.h
>>> @@ -205,6 +205,27 @@ static inline int pmd_young(pmd_t pmd)
>>>    #define arch_flush_lazy_mmu_mode()    do {} while (0)
>>>    #endif
>>>    +#ifndef pte_batch_remaining
>>> +/**
>>> + * pte_batch_remaining - Number of pages from addr to next batch boundary.
>>> + * @pte: Page table entry for the first page.
>>> + * @addr: Address of the first page.
>>> + * @end: Batch ceiling (e.g. end of vma).
>>> + *
>>> + * Some architectures (arm64) can efficiently modify a contiguous batch of ptes.
>>> + * In such cases, this function returns the remaining number of pages to the end
>>> + * of the current batch, as defined by addr. This can be useful when iterating
>>> + * over ptes.
>>> + *
>>> + * May be overridden by the architecture, else batch size is always 1.
>>> + */
>>> +static inline unsigned int pte_batch_remaining(pte_t pte, unsigned long addr,
>>> +                        unsigned long end)
>>> +{
>>> +    return 1;
>>> +}
>>> +#endif
>>
>> It's a shame we now lose the optimization for all other archtiectures.
>>
>> Was there no way to have some basic batching mechanism that doesn't require arch
>> specifics?
> 
> I tried a bunch of things but ultimately the way I've done it was the only way
> to reduce the order-0 fork regression to 0.

Let me give it a churn today. I think we should really focus on having 
only a single folio_test_large() check on the fast path for order-0. And 
not even try doing batching for anything that works on bare PFNs.

Off to prototyping ... :)

-- 
Cheers,

David / dhildenb