Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <8e1aaa19-0d28-3381-3ec6-920a474f5f3f@redhat.com>
Date:   Mon, 5 Sep 2022 10:38:51 +0200
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.2.0
Subject: Re: [PATCH v1] mm/gup: adjust stale comment for RCU GUP-fast
Content-Language: en-US
To:     Aneesh Kumar K V <aneesh.kumar@linux.ibm.com>,
        Yang Shi <shy828301@gmail.com>, Peter Xu <peterx@redhat.com>
Cc:     linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Jerome Marchand <jmarchan@redhat.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Hugh Dickins <hughd@google.com>,
        Jason Gunthorpe <jgg@nvidia.com>,
        John Hubbard <jhubbard@nvidia.com>
References: <20220901072119.37588-1-david@redhat.com>
 <YxDdycTur733hMgt@xz-m1.local>
 <fa0bb4b1-3edd-eb5a-7ad6-dff785d88d8f@redhat.com>
 <YxDghv54uHYMGCfG@xz-m1.local>
 <c9dc3f22-4a72-9b9d-7a74-ad77fe4f3b6e@redhat.com>
 <CAHbLzkpdUMq2fMxqx-NgSZ2VLBU5RGqSpJRWH6eRrYymErAbaw@mail.gmail.com>
 <YxD00K1lv151X/eq@xz-m1.local>
 <CAHbLzkrA-jKzTBq_Mn3NZYc91exovv1gH2LNzetCNiVu8+W6Kg@mail.gmail.com>
 <2368d91f-8442-076f-f33a-64b51b44825c@redhat.com>
 <e87bad0c-47fa-5e6d-9c43-f2f66da32a76@linux.ibm.com>
From:   David Hildenbrand <david@redhat.com>
Organization: Red Hat
In-Reply-To: <e87bad0c-47fa-5e6d-9c43-f2f66da32a76@linux.ibm.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 04.09.22 18:52, Aneesh Kumar K V wrote:
> On 9/2/22 12:02 PM, David Hildenbrand wrote:
>> On 01.09.22 20:35, Yang Shi wrote:
>>> On Thu, Sep 1, 2022 at 11:07 AM Peter Xu <peterx@redhat.com> wrote:
>>>>
>>>> On Thu, Sep 01, 2022 at 10:50:48AM -0700, Yang Shi wrote:
>>>>> Yeah, because THP collapse does copy the data before clearing pte. If
>>>>> we want to remove pmdp_collapse_flush() by just clearing pmd, we
>>>>> should clear *AND* flush pte before copying the data IIRC.
>>>>
>>>> Yes tlb flush is still needed.  IIUC the generic pmdp_collapse_flush() will
>>>> still be working (with the pte level flushing there) but it should just
>>>> start to work for all archs, so potentially we could drop the arch-specific
>>>> pmdp_collapse_flush()s, mostly the ppc impl.
>>>
>>> I'm don't know why powperpc needs to have its specific
>>> pmdp_collapse_flush() in the first place, not only the mandatory IPI
>>> broadcast, but also the specific implementation of pmd tlb flush. But
>>> anyway the IPI broadcast could be removed at least IMO.
>>>
>>
>> pmdp_collapse_flush() is overwritten on book3s only. It either translates
>> to radix__pmdp_collapse_flush() or hash__pmdp_collapse_flush().
>>
>>
>> radix__pmdp_collapse_flush() has a comment explaining the situation:
>>
>>
>> +       /*
>> +        * pmdp collapse_flush need to ensure that there are no parallel gup
>> +        * walk after this call. This is needed so that we can have stable
>> +        * page ref count when collapsing a page. We don't allow a collapse page
>> +        * if we have gup taken on the page. We can ensure that by sending IPI
>> +        * because gup walk happens with IRQ disabled.
>> +        */
>>
>>
>> The comment for hash__pmdp_collapse_flush() is a bit more involved:
>>
>> 	/*
>> 	 * Wait for all pending hash_page to finish. This is needed
>> 	 * in case of subpage collapse. When we collapse normal pages
>> 	 * to hugepage, we first clear the pmd, then invalidate all
>> 	 * the PTE entries. The assumption here is that any low level
>> 	 * page fault will see a none pmd and take the slow path that
>> 	 * will wait on mmap_lock. But we could very well be in a
>> 	 * hash_page with local ptep pointer value. Such a hash page
>> 	 * can result in adding new HPTE entries for normal subpages.
>> 	 * That means we could be modifying the page content as we
>> 	 * copy them to a huge page. So wait for parallel hash_page
>> 	 * to finish before invalidating HPTE entries. We can do this
>> 	 * by sending an IPI to all the cpus and executing a dummy
>> 	 * function there.
>> 	 */
>>
>> I'm not sure if that implies that the IPI is needed for some other hash-magic.
>>
>> Maybe Aneesh can clarify.
>>
> 
> We still need the IPI for the hash. Another reason for architecture to override that
> function is to help them use the right page size when flushing the TLB.

Thanks for clarifying. So the radix variant wouldn't need the IPI 
anymore, once GUP-fast is handled differently, correct?

-- 
Thanks,

David / dhildenb