[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20150501162731.GA1327@gmail.com>
Date: Fri, 1 May 2015 18:27:31 +0200
From: Ingo Molnar <mingo@...nel.org>
To: Rik van Riel <riel@...hat.com>
Cc: Andy Lutomirski <luto@...capital.net>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
X86 ML <x86@...nel.org>, williams@...hat.com,
Andrew Lutomirski <luto@...nel.org>, fweisbec@...hat.com,
Peter Zijlstra <peterz@...radead.org>,
Heiko Carstens <heiko.carstens@...ibm.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>,
Paolo Bonzini <pbonzini@...hat.com>
Subject: Re: [PATCH 3/3] context_tracking,x86: remove extraneous irq disable
& enable from context tracking on syscall entry
* Rik van Riel <riel@...hat.com> wrote:
> On 05/01/2015 12:03 PM, Andy Lutomirski wrote:
>
> > The last time I asked, the impression I got was that we needed two things:
> >
> > 1. We can't pluck things from the RCU list without knowing whether the
> > CPU is in an RCU read-side critical section, and we can't know that
> > unless we have regular grade periods or we know that the CPU is idle.
> > To make the CPU detectably idle, we need to set a bit somewhere.
>
> More than that. We also need a way for another CPU to identify the
> callbacks they could run for us, without confusing them with new
> callbacks queued after we transitioned back from USER to KERNEL
> context.
That's easy: a simple, constant-work IPI sent to nohz-full CPUs could
just dequeue these callbacks, if it sees that we are still in
user-mode.
It's super easy because such an IPI would essentially be equivalent to
a system call context from RCU's POV, if it uses this test:
if (user_mode(regs)) {
... pluck RCU callbacks ...
}
That way we can have lots of overhead removed from the syscall call
path ...
Thanks,
Ingo
--
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