From: "David Hildenbrand (Arm)" <david@kernel.org>
To: "Christoph Lameter (Ampere)" <cl@gentwo.org>
Cc: "Lorenzo Stoakes (ARM)" <ljs@kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Mark Rutland <mark.rutland@arm.com>,
Yang Shi <yang@os.amperecomputing.com>,
Ryan Roberts <ryan.roberts@arm.com>,
dennis@kernel.org, tj@kernel.org, urezki@gmail.com,
catalin.marinas@arm.com, will@kernel.org,
akpm@linux-foundation.org, hca@linux.ibm.com, gor@linux.ibm.com,
agordeev@linux.ibm.com, linux-mm@kvack.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, Jason Gunthorpe <jgg@nvidia.com>
Subject: Re: [RFC v2 PATCH 0/16] Optimize this_cpu_*() ops for non-x86 (ARM64 for this series)
Date: Wed, 5 Aug 2026 00:01:22 +0200 [thread overview]
Message-ID: <44a20360-c791-491d-bd84-e161b7c6a9f0@kernel.org> (raw)
In-Reply-To: <7f2b2030-b912-70ee-5019-02dad2e87ca6@gentwo.org>
On 8/4/26 23:56, Christoph Lameter (Ampere) wrote:
> On Tue, 4 Aug 2026, David Hildenbrand (Arm) wrote:
>
>>> These are operations that are key to the performance in critical parts of
>>> memory management and this code is replicated by being inlined thousands
>>> of times in the kernel.
>>
>> Cool, then it is easy to show the difference by running micro + macro benchmarks.
>
> And we have done so repeatedly. Look at Yang's posts.
>
I'm getting tired of this.
So to be clear: claiming that the additional instructions are unacceptable I'd
expect something minimal like: "removing these 3 instructions speeds up
micro-benchmark (a, b, c) by X% and macro-benchmarks (d, e, f) by Y% compared to
Mark's approach". [1]
https://lore.kernel.org/r/ea268481-d584-4744-99d6-0b05aade7d5d@kernel.org
--
Cheers,
David
next prev parent reply other threads:[~2026-08-04 22:01 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-15 18:04 [RFC v2 PATCH 0/16] Optimize this_cpu_*() ops for non-x86 (ARM64 for this series) Yang Shi
2026-07-15 18:04 ` [PATCH 01/16] drivers: arch_numa: move percpu set up code to arch Yang Shi
2026-07-15 18:04 ` [PATCH 02/16] arm64: kconfig: make percpu related configs not depend on NUMA Yang Shi
2026-07-15 18:04 ` [PATCH 03/16] mm: pgalloc: introduce {pud|pmd}_populate_sync() Yang Shi
2026-07-15 18:04 ` [PATCH 04/16] vmalloc: pass in pgd pointer for vmap{__vunmap}_range_noflush() Yang Shi
2026-07-29 9:32 ` Lorenzo Stoakes (ARM)
2026-08-03 19:12 ` Yang Shi
2026-08-04 13:47 ` Lorenzo Stoakes (ARM)
2026-07-15 18:04 ` [PATCH 05/16] arm64: mm: enable percpu kernel page table Yang Shi
2026-07-15 18:04 ` [PATCH 06/16] arm64: mm: defined {pud|pmd}_populate_sync() Yang Shi
2026-07-15 18:04 ` [PATCH 07/16] arm64: mm: sync percpu page table for memory hotplug/unplug Yang Shi
2026-07-15 18:04 ` [PATCH 08/16] arm64: kasan: sync up kasan shadow area page table Yang Shi
2026-07-15 18:04 ` [PATCH 09/16] arm64: mm: define percpu virtual space area Yang Shi
2026-07-15 18:04 ` [PATCH 10/16] mm: percpu: prepare to use dedicated percpu area Yang Shi
2026-07-15 18:04 ` [PATCH 11/16] arm64: mm: map local percpu first chunk Yang Shi
2026-07-15 18:04 ` [PATCH 12/16] mm: percpu: set up first chunk and reserve chunk Yang Shi
2026-07-15 18:04 ` [PATCH 13/16] arm64: mm: introduce __per_cpu_local_off Yang Shi
2026-07-15 18:04 ` [PATCH 14/16] mm: percpu: allocate and free local percpu vm area Yang Shi
2026-07-15 18:04 ` [PATCH 15/16] arm64: kconfig: select HAVE_LOCAL_PER_CPU_MAP Yang Shi
2026-07-15 18:04 ` [PATCH 16/16] arm64: percpu: use local percpu for this_cpu_*() APIs Yang Shi
2026-07-16 13:23 ` [RFC v2 PATCH 0/16] Optimize this_cpu_*() ops for non-x86 (ARM64 for this series) Ryan Roberts
2026-07-21 19:08 ` Mark Rutland
2026-07-21 23:20 ` Yang Shi
2026-07-22 9:36 ` Mark Rutland
2026-07-27 21:10 ` Yang Shi
2026-07-27 22:06 ` Christoph Lameter (Ampere)
2026-07-29 9:28 ` David Hildenbrand (Arm)
2026-08-04 14:15 ` Lorenzo Stoakes (ARM)
2026-08-04 14:21 ` Lorenzo Stoakes (ARM)
2026-08-04 14:40 ` Jason Gunthorpe
2026-08-04 18:06 ` Matthew Wilcox
2026-08-04 18:16 ` Jason Gunthorpe
2026-08-04 15:21 ` Linus Torvalds
2026-08-04 16:15 ` Christoph Lameter (Ampere)
2026-08-04 16:30 ` Linus Torvalds
2026-08-04 16:54 ` David Hildenbrand (Arm)
2026-08-04 17:01 ` Linus Torvalds
2026-08-04 17:32 ` Lorenzo Stoakes (ARM)
2026-08-04 21:40 ` Christoph Lameter (Ampere)
2026-08-04 21:48 ` David Hildenbrand (Arm)
2026-08-04 21:56 ` Christoph Lameter (Ampere)
2026-08-04 22:01 ` David Hildenbrand (Arm) [this message]
2026-08-05 8:16 ` Lorenzo Stoakes (ARM)
2026-08-04 17:23 ` Lorenzo Stoakes (ARM)
2026-08-04 17:28 ` Linus Torvalds
2026-08-04 21:51 ` Yang Shi
2026-08-04 22:05 ` David Hildenbrand (Arm)
2026-08-04 22:35 ` Christoph Lameter (Ampere)
2026-08-05 6:11 ` David Hildenbrand (Arm)
2026-08-05 14:48 ` Mark Rutland
2026-08-05 7:52 ` Lorenzo Stoakes (ARM)
2026-08-06 17:15 ` Will Deacon
2026-08-06 17:31 ` Lorenzo Stoakes (ARM)
2026-08-04 16:19 ` Christoph Lameter (Ampere)
2026-08-04 16:47 ` David Hildenbrand (Arm)
2026-08-04 21:25 ` Christoph Lameter (Ampere)
2026-08-04 21:47 ` David Hildenbrand (Arm)
2026-08-04 22:01 ` Christoph Lameter (Ampere)
2026-08-05 6:12 ` David Hildenbrand (Arm)
2026-08-05 8:45 ` Heiko Carstens
2026-08-05 11:10 ` David Laight
2026-08-05 14:53 ` Mark Rutland
2026-07-30 6:06 ` [RFC v2 PATCH 0/16] Optimize this_cpu_*() ops for non-x86 (ARM64 for this series)~ Mete Durlu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=44a20360-c791-491d-bd84-e161b7c6a9f0@kernel.org \
--to=david@kernel.org \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=catalin.marinas@arm.com \
--cc=cl@gentwo.org \
--cc=dennis@kernel.org \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=jgg@nvidia.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mark.rutland@arm.com \
--cc=ryan.roberts@arm.com \
--cc=tj@kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=urezki@gmail.com \
--cc=will@kernel.org \
--cc=yang@os.amperecomputing.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox