linux-kernel - Re: [PATCH] hrtimer: Update softirq_expires_next correctly after __hrtimer_get_next

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]

Date:   Tue, 20 Apr 2021 17:15:03 +0900
From:   Lorenzo Colitti <lorenzo@...gle.com>
To:     Thomas Gleixner <tglx@...utronix.de>
Cc:     Greg KH <gregkh@...uxfoundation.org>,
        Maciej Żenczykowski <zenczykowski@...il.com>,
        Ingo Molnar <mingo@...nel.org>,
        Anna-Maria Behnsen <anna-maria@...utronix.de>,
        lkml <linux-kernel@...r.kernel.org>,
        mikael.beckius@...driver.com,
        Maciej Żenczykowski <maze@...gle.com>
Subject: Re: [PATCH] hrtimer: Update softirq_expires_next correctly after __hrtimer_get_next_event()

On Fri, Apr 16, 2021 at 1:47 AM Thomas Gleixner <tglx@...utronix.de> wrote:
> Enable tracing and enable the following tracepoints:
> [...]

Sorry for the delay. I had to learn a bit about how to use the tracing
infrastructure. I don't know if I can post here, but to my untrained
eye, one big difference between the old (fast) code and the new (slow)
code is that the new code calls tick_program_event() much more. It
looks like that makes most of the difference.

With the old code, hrtimer_start_range_ns almost never calls
tick_program_event at all, but the new code seems to call it twice on
every timer update.