linux-kernel - Re: [PATCH 3/5] sched_ext: Implement scx_bpf_clock_get

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: <20241118094430.GH39245@noisy.programming.kicks-ass.net>
Date: Mon, 18 Nov 2024 10:44:30 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Changwoo Min <changwoo@...lia.com>
Cc: tj@...nel.org, void@...ifault.com, mingo@...hat.com,
	kernel-dev@...lia.com, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 3/5] sched_ext: Implement scx_bpf_clock_get_ns()

On Mon, Nov 18, 2024 at 12:48:35AM +0900, Changwoo Min wrote:
> Hello,
> 
> On 24. 11. 17. 04:31, Peter Zijlstra wrote:
> > Have you seen the insides of kernel/sched/clock.c ?
> 
> Of course. :-) It would be super helpful if you could let me know
> specific questions or comments.

Well, mostly I don't understand anything about what you're doing.
Perhaps if you explain what's wrong with the bits we have ?

If you're looking at the scheduler, then rq->clock really should be
sufficient.

If you're looking at rando BPF crud, then what's wrong with
local_clock()?

Also, why are we still caring about systems that have crazy TSC?