linux-kernel - Re: [PATCH 3/3] Set the subfunctions called by finish_task

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251025185120.6760-1-qq570070308@gmail.com>
Date: Sun, 26 Oct 2025 02:51:20 +0800
From: Xie Yuanbin <qq570070308@...il.com>
To: tglx@...utronix.de
Cc: acme@...nel.org,
	adrian.hunter@...el.com,
	agordeev@...ux.ibm.com,
	akpm@...ux-foundation.org,
	alex@...ti.fr,
	alexander.shishkin@...ux.intel.com,
	andreas@...sler.com,
	anna-maria@...utronix.de,
	aou@...s.berkeley.edu,
	borntraeger@...ux.ibm.com,
	bp@...en8.de,
	bsegall@...gle.com,
	dave.hansen@...ux.intel.com,
	davem@...emloft.net,
	david@...hat.com,
	dietmar.eggemann@....com,
	frederic@...nel.org,
	gor@...ux.ibm.com,
	hca@...ux.ibm.com,
	hpa@...or.com,
	irogers@...gle.com,
	jolsa@...nel.org,
	juri.lelli@...hat.com,
	linux-arm-kernel@...ts.infradead.org,
	linux-kernel@...r.kernel.org,
	linux-perf-users@...r.kernel.org,
	linux-riscv@...ts.infradead.org,
	linux-s390@...r.kernel.org,
	linux@...linux.org.uk,
	lorenzo.stoakes@...cle.com,
	luto@...nel.org,
	mark.rutland@....com,
	mathieu.desnoyers@...icios.com,
	max.kellermann@...os.com,
	mgorman@...e.de,
	mingo@...hat.com,
	namhyung@...nel.org,
	nysal@...ux.ibm.com,
	palmer@...belt.com,
	paulmck@...nel.org,
	peterz@...radead.org,
	pjw@...nel.org,
	qq570070308@...il.com,
	riel@...riel.com,
	rostedt@...dmis.org,
	ryan.roberts@....com,
	segher@...nel.crashing.org,
	sparclinux@...r.kernel.org,
	svens@...ux.ibm.com,
	thuth@...hat.com,
	urezki@...il.com,
	vincent.guittot@...aro.org,
	vschneid@...hat.com,
	will@...nel.org,
	x86@...nel.org
Subject: Re: [PATCH 3/3] Set the subfunctions called by finish_task_switch to be inline

On Fri, 24 Oct 2025 21:44:10 +0200, Thomas Gleixner wrote:
> What is exactly the point of this indirection. Why can't you just mark
> finish_arch_post_lock_switch() __always_inline and be done with it?

In this patch, I've added an always inline version of the function,
finish_arch_post_lock_switch_ainline. The original function,
finish_arch_post_lock_switch, retains its original inline attribute.

The reason for this is that this function is called not only during
context switches but also from other code, and I don't want to affect
those parts. In fact, with Os/Oz-level optimizations, if this function
is called multiple times within one .c file, it will most likely not be
inlined, even if it's marked as inline.

Context switching is a hot code, I hope it will be always inlined here to
improve performance. In other places, if it is not a performance-critical
function, then it can be not inlined to gain codesize benefits.

Look at your opinions. I have no objection to setting
finish_arch_post_lock_switch directly to __always_inline.

Xie Yuanbin