[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <17777b93-41f0-4943-963f-0330489b01bc@redhat.com>
Date: Wed, 2 Jul 2025 11:05:17 +0200
From: David Hildenbrand <david@...hat.com>
To: Oscar Salvador <osalvador@...e.de>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Andrew Morton <akpm@...ux-foundation.org>,
"Liam R. Howlett" <Liam.Howlett@...cle.com>,
Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
Vlastimil Babka <vbabka@...e.cz>, Jann Horn <jannh@...gle.com>,
Mike Rapoport <rppt@...nel.org>, Suren Baghdasaryan <surenb@...gle.com>,
Michal Hocko <mhocko@...e.com>, Zi Yan <ziy@...dia.com>,
Matthew Brost <matthew.brost@...el.com>,
Joshua Hahn <joshua.hahnjy@...il.com>, Rakie Kim <rakie.kim@...com>,
Byungchul Park <byungchul@...com>, Gregory Price <gourry@...rry.net>,
Ying Huang <ying.huang@...ux.alibaba.com>,
Alistair Popple <apopple@...dia.com>, Pedro Falcato <pfalcato@...e.de>,
Rik van Riel <riel@...riel.com>, Harry Yoo <harry.yoo@...cle.com>
Subject: Re: [PATCH v1 3/4] mm: split folio_pte_batch() into folio_pte_batch()
and folio_pte_batch_ext()
On 02.07.25 11:02, Oscar Salvador wrote:
> On Fri, Jun 27, 2025 at 01:55:09PM +0200, David Hildenbrand wrote:
>> Many users (including upcoming ones) don't really need the flags etc,
>> and can live with a function call.
>>
>> So let's provide a basic, non-inlined folio_pte_batch().
>>
>> In zap_present_ptes(), where we care about performance, the compiler
>> already seem to generate a call to a common inlined folio_pte_batch()
>> variant, shared with fork() code. So calling the new non-inlined variant
>> should not make a difference.
>>
>> While at it, drop the "addr" parameter that is unused.
>>
>> Signed-off-by: David Hildenbrand <david@...hat.com>
>
> So, let me see if I get this.
>
> Before this, every other user that doesn't use the extra flags (dirty,
> etc...) will end up with the code, optimized out, inlined within its body?
Not necessarily inlined into the body (there might still be a function
call, depending on what the compiler decides), but inlined into the
object file and optimized by propagating constants.
>
> With this change, a single function, folio_pte_batch(), identical to folio_pte_batch_ext
> but without the runtime checks for those arguments will be created (folio_pte_batch()),
> and so the users of it won't have it inlined in their body ?
Right. We have a single folio_pte_batch() that is optimized by
propagating all constants. Instead of having one per object file, we
have a single shared one.
--
Cheers,
David / dhildenb
Powered by blists - more mailing lists