Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Message-ID: <88a8b1a3-232d-df9c-d7f6-0ea9f2dd4b36@redhat.com>
Date:   Thu, 20 Jan 2022 16:51:47 +0100
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.4.0
Subject: Re: [PATCH] mm: reuse the unshared swapcache page in do_wp_page
Content-Language: en-US
To:     Matthew Wilcox <willy@infradead.org>
Cc:     "zhangliang (AG)" <zhangliang5@huawei.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Linux-MM <linux-mm@kvack.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        wangzhigang17@huawei.com,
        Linus Torvalds <torvalds@linux-foundation.org>
References: <a93988da-80fb-dd32-4717-a6a0bae9e4ee@huawei.com>
 <dc415c4a-63aa-19b0-0fbc-795989970f6d@redhat.com>
 <fb02087a-b102-c91e-ab65-fb02cc8ee0a2@huawei.com>
 <9cd7eee2-91fd-ddb8-e47d-e8585e5baa05@redhat.com>
 <b6df4f7f-c080-ad6c-d1ad-098115f016f3@huawei.com>
 <747ff31c-6c9e-df6c-f14d-c43aa1c77b4a@redhat.com>
 <Yel0BXVyj8uvsWJX@casper.infradead.org>
 <e2580cfa-a529-934d-861a-091c4a9714d4@redhat.com>
 <YemBl4ZVtJqtAVwV@casper.infradead.org>
 <759f9bc8-0b10-7f0f-28a6-f292bed9053f@redhat.com>
 <YemDry2rkD2VUcw9@casper.infradead.org>
From:   David Hildenbrand <david@redhat.com>
Organization: Red Hat
In-Reply-To: <YemDry2rkD2VUcw9@casper.infradead.org>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk


>> Yes, we are talking past each other and no, I am talking about fully
>> mapped THP, just mapped via PTEs.
>>
>> Please refer to our THP COW logic: do_huge_pmd_wp_page()
> 
> You're going to have to be a bit more explicit.  That's clearly handling
> the case where there's a PMD mapping.  If there is _also_ a PTE mapping,
> then obviously the page is mapped more than once and can't be reused!
> 
>>>
>>>>> Anon THP is always going to start out aligned (and can be moved by
>>>>> mremap()).  Arguably it should be broken up if it's moved so it can be
>>>>> reformed into aligned THPs by khugepaged.
>>>>
>>>> Can you elaborate, I'm missing the point where something gets moved. I
>>>> don't care about mremap() at all here.
>>>>
>>>>
>>>> 1. You have a read-only, PTE mapped THP
>>>> 2. Write fault on the THP
>>>> 3. We PTE-map the THP because we run into a false positive in our COW
>>>>    logic to handle COW on PTE
>>>> 4. Write fault on the PTE
>>>> 5. We always have to COW each and every sub-page and can never reuse,
>>>>    because page_count() > 1
>>>>
>>>> That's essentially what reuse_swap_page() tried to handle before.
>>>> Eventually optimizing for this is certainly the next step, but I'd like
>>>> to document which effect the removal of reuse_swap_page() will have to THP.
>>>
>>> I'm talking about step 0.  How do we get a read-only, PTE-mapped THP?
>>> Through mremap() or perhaps through an mprotect()/mmap()/munmap() that
>>> failed to split the THP.
>>
>> do_huge_pmd_wp_page()
> 
> I feel you could be a little more verbose about what you think is
> going on here.  Are you talking about the fallback: path where we
> call __split_huge_pmd()?

Sorry, I was less verbose because I was just sending out the
patch+description to Linus' reply and was assuming you're going to read
it anyways ;)

Yes, I'm speaking about exactly that fallback path.

-- 
Thanks,

David / dhildenb