linux-kernel - Re: [RFC PATCH 0/3] Add accurate boot timing to a Linux system

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: <CAPnjgZ0yt2VGUHB+deb4BQ_dto8Jd+W8mxw7PjNYO9oiqEObuw@mail.gmail.com>
Date:	Sat, 24 Sep 2011 07:06:47 -0700
From:	Simon Glass <sjg@...omium.org>
To:	Russell King - ARM Linux <linux@....linux.org.uk>
Cc:	linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org
Subject: Re: [RFC PATCH 0/3] Add accurate boot timing to a Linux system

Hi Russell,

On Sat, Sep 24, 2011 at 1:32 AM, Russell King - ARM Linux
<linux@....linux.org.uk> wrote:
> On Fri, Sep 23, 2011 at 04:03:15PM -0700, Simon Glass wrote:
>> An accurate timer is required to make the numbers meaningful. Many
>> modern platforms have a microsecond timer. This patch set uses a
>> function called timer_get_us() to read the timer.
>
> Not another 'get a time value' function.  Why do we need soo many?
> We have - at least:
>
> ktime_get (and various flavours of it)
> do_gettimeofday
> getnstimeofday
> sched_clock
>
> Do we really need yet another one which will have to be multiplexed
> amongst platforms, requiring scaling and so forth from whatever the
> platform provides?

No we don't need another! It is just a convenience for this RFC since
the actual timer mechanism is not clear and not important for this
RFC. Insert your favourite timer mechanism instead.

>
> Remember that ARM timers are virtually all MMIO mapped, which means
> they don't work during early kernel bringup when the MMU mappings for
> the hardware have not been setup.  (That's the reason stuff like
> sched_clock for printk doesn't work early.)  That can't be solved by
> creating yet another per-platform method to get microseconds.
>

While it would be useful to measure early things like kernel
decompression, it's hard to make that work cross-platform and there
are other problems like you raise, and where to store timing info.
>From the POV of kernel timing this RFC is about start_kernel() and
onwards. I should have been more clear in the description.

Regards,
Simon
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/