[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <9D248293-2456-4642-9F18-8075F0596EC2@gmail.com>
Date: Mon, 4 Aug 2025 16:01:37 +0300
From: Nadav Amit <nadav.amit@...il.com>
To: David Hildenbrand <david@...hat.com>
Cc: Li Qiang <liqiang01@...inos.cn>,
Andrew Morton <akpm@...ux-foundation.org>,
"open list:MEMORY MANAGEMENT" <linux-mm@...ck.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
lorenzo.stoakes@...cle.com,
"Liam R . Howlett" <Liam.Howlett@...cle.com>,
Vlastimil Babka <vbabka@...e.cz>,
Mike Rapoport <rppt@...nel.org>,
Suren Baghdasarya <surenb@...gle.com>,
Michal Hocko <mhocko@...e.com>
Subject: Re: [PATCH] mm: memory: Force-inline PTE/PMD zapping functions for
performance
> On 4 Aug 2025, at 15:51, David Hildenbrand <david@...hat.com> wrote:
>
> On 04.08.25 14:39, Li Qiang wrote:
>> This change converts several critical page table zapping functions from
>> `inline` to `__always_inline`, resulting in measurable performance
>> improvements in process spawning workloads.
>> Performance Impact (Intel Xeon Gold 6430 2.1GHz):
>> - UnixBench 'context1' test shows ~6% improvement (single-core)
>> - UnixBench shows ~0.6% improvement (single-core)
>> - mm/memory.o size reduced by 2.49% (70190 -> 68445 bytes)
>> - Net code reduction of 1745 bytes (add/remove: 211/166)
>> The modified functions form a hot path during process teardown:
>> 1. zap_present_ptes()
>> 2. do_zap_pte_range()
>> 3. zap_pte_range()
>> 4. zap_pmd_range()
>> Signed-off-by: Li Qiang <liqiang01@...inos.cn>
>> ---
>
> What's the object file size change?
I think that Li wrote that the size is reduced by 2.49% .
My 2 cents is that usually it may be better to understand why it is
not inlined and address that (e.g., likely() hints or something else)
instead of blindly putting __always_inline. The __always_inline might
stay there for no reason after some code changes and therefore become
a maintenance burden. Concretely, in this case, where there is a single
caller, one can expect the compiler to really prefer to inline the
callees.
Perhaps it is beneficial to compile with flags such as
"-fopt-info-inline-optimized-missed=inline.txt” to better understand
the reason.
Powered by blists - more mailing lists