This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: [PATCH 05/05] Linux Kernel Markers, non optimised architectures
- From: Mathieu Desnoyers <compudj at krystal dot dyndns dot org>
- To: Nick Piggin <nickpiggin at yahoo dot com dot au>
- Cc: Andrew Morton <akpm at osdl dot org>, Greg Kroah-Hartman <gregkh at suse dot de>, linux-kernel at vger dot kernel dot org, Christoph Hellwig <hch at infradead dot org>, Linus Torvalds <torvalds at osdl dot org>, Ingo Molnar <mingo at redhat dot com>, ltt-dev at shafik dot org, systemtap at sources dot redhat dot com, Thomas Gleixner <tglx at linutronix dot de>, Douglas Niehaus <niehaus at eecs dot ku dot edu>
- Date: Fri, 12 Jan 2007 12:43:12 -0500
- Subject: Re: [PATCH 05/05] Linux Kernel Markers, non optimised architectures
- References: <11685601382063-git-send-email-mathieu.desnoyers@polymtl.ca> <11685601404005-git-send-email-mathieu.desnoyers@polymtl.ca> <45A710F8.7000405@yahoo.com.au> <20070112050032.GA14100@Krystal> <45A71827.6020300@yahoo.com.au> <20070112171512.GB2888@Krystal>
* Mathieu Desnoyers (mathieu.desnoyers@polymtl.ca) wrote:
> >
> > OK, well one problem is that it can cause a resched event to be lost, so
> > you might say it has more side-effects without checking resched.
> >
[...]
> If we are sure that we expect calls to preempt_schedule() from each of these
> contexts, then it's ok to put preempt_enable(). It is important to note that a
> marker would then act as a source of scheduler events in code paths where
> disabling interrupts is expected to disable the scheduler.
>
Sorry for self-reply, but the above mentioned issue is dealt by the
irqs_disabled() check at the beginning of preempt_schedule().
Mathieu
--
OpenPGP public key: http://krystal.dyndns.org:8080/key/compudj.gpg
Key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68