[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 18 Nov 2009 20:22:47 -0500
From: Steven Rostedt <rostedt@...dmis.org>
To: paulmck@...ux.vnet.ibm.com
Cc: Mathieu Desnoyers <mathieu.desnoyers@...ymtl.ca>,
Jason Baron <jbaron@...hat.com>, mingo@...e.hu,
mhiramat@...hat.com, linux-kernel@...r.kernel.org, hpa@...or.com,
tglx@...utronix.de, andi@...stfloor.org, roland@...hat.com,
rth@...hat.com
Subject: Re: [RFC PATCH 2/6] jump label v3 - x86: Introduce generic jump
patching without stop_machine
On Wed, 2009-11-18 at 16:58 -0800, Paul E. McKenney wrote:
> I do invoke smp_send_reschedule() with irqs disabled, which did arouse my
> suspicions of late. But this seems to bypass the smp_call_function()
> code that is most definitely illegal to invoke with irqs disabled,
> so no smoking gun. All that aside, if invoking smp_send_reschedule()
> with irqs disabled is in any way a bad idea, please let me know so I
> can rearrange the code appropriately.
I don't think you have anything to worry about here. If calling
smp_send_reschedule was bad with keeping interrupts disabled, then we
would have a lot of problems with the scheduler. That is called with the
rq lock held and with interrupts disabled.
-- Steve
--
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/
Powered by blists - more mailing lists