Re: [RFC PATCH 0/0 v3] callchain fixes and cleanups

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Will Deacon
Date: Wednesday, August 18, 2010 - 2:08 am

On Wed, 2010-08-18 at 04:55 +0100, Frederic Weisbecker wrote:


We don't have NMIs on ARM [so obviously we can't use them!] but
you're right to point out the FIQ. I've actually been thinking about
this during the past week, but there are the following problems:

(1) The FIQ isn't always wired up in the hardware, so you can't
    assume that it is available.

(2) The FIQ can only have a single handler at a given time. This
    is because it is a separate exception mode, with its own banked
    registers. Consequently, we might not be able to use it if it's
    being used for something else.

(3) The Trustzone security extensions may reserve the FIQ for secure
    use only or make it available only via the secure monitor [which
    will increase latency].

Of course, the advantage is that we could then use sample-based
profiling techniques in sections of code where the interrupts are
disabled.

The only way I can think of adding this is as a Kconfig option,
which, when selected, tries to use the FIQ and then falls back to
normal IRQs if it fails.

Cheers,

Will

--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[RFC PATCH 0/0 v3] callchain fixes and cleanups , Frederic Weisbecker, (Mon Aug 16, 1:48 pm)
[RFC PATCH 1/6] perf: Drop unappropriate tests on arch cal ..., Frederic Weisbecker, (Mon Aug 16, 1:48 pm)
[RFC PATCH 2/6] perf: Generalize callchain_store(), Frederic Weisbecker, (Mon Aug 16, 1:48 pm)
[RFC PATCH 3/6] perf: Generalize some arch callchain code, Frederic Weisbecker, (Mon Aug 16, 1:48 pm)
[RFC PATCH 4/6] perf: Factorize callchain context handling, Frederic Weisbecker, (Mon Aug 16, 1:48 pm)
[RFC PATCH 5/6] perf: Fix race in callchains, Frederic Weisbecker, (Mon Aug 16, 1:48 pm)
[RFC PATCH 6/6] perf: Humanize the number of contexts, Frederic Weisbecker, (Mon Aug 16, 1:48 pm)
[RFC PATCH 5/6 v4] perf: Fix race in callchains, Frederic Weisbecker, (Mon Aug 16, 6:34 pm)
Re: [RFC PATCH 2/6] perf: Generalize callchain_store(), Paul Mackerras, (Mon Aug 16, 9:37 pm)
Re: [RFC PATCH 5/6 v4] perf: Fix race in callchains, Paul Mackerras, (Mon Aug 16, 9:53 pm)
Re: [RFC PATCH 0/0 v3] callchain fixes and cleanups, Borislav Petkov, (Mon Aug 16, 9:58 pm)
Re: [RFC PATCH 0/0 v3] callchain fixes and cleanups, Will Deacon, (Tue Aug 17, 3:32 am)
Re: [RFC PATCH 5/6 v4] perf: Fix race in callchains, Frederic Weisbecker, (Tue Aug 17, 8:49 pm)
Re: [RFC PATCH 3/6] perf: Generalize some arch callchain code, Frederic Weisbecker, (Tue Aug 17, 8:51 pm)
Re: [RFC PATCH 0/0 v3] callchain fixes and cleanups, Frederic Weisbecker, (Tue Aug 17, 8:53 pm)
Re: [RFC PATCH 0/0 v3] callchain fixes and cleanups, Frederic Weisbecker, (Tue Aug 17, 8:55 pm)
Re: [RFC PATCH 0/0 v3] callchain fixes and cleanups, Will Deacon, (Wed Aug 18, 2:08 am)
Re: [RFC PATCH 0/0 v3] callchain fixes and cleanups, Ingo Molnar, (Wed Aug 18, 9:15 am)