[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <48AD9614.6060701@qumranet.com>
Date: Thu, 21 Aug 2008 19:21:40 +0300
From: Avi Kivity <avi@...ranet.com>
To: Peter Zijlstra <peterz@...radead.org>
CC: Nick Piggin <nickpiggin@...oo.com.au>,
jmerkey@...fmountaingroup.com,
Stefan Richter <stefanr@...6.in-berlin.de>,
paulmck@...ux.vnet.ibm.com, linux-kernel@...r.kernel.org,
Linus Torvalds <torvalds@...ux-foundation.org>,
David Howells <dhowells@...hat.com>
Subject: Re: [ANNOUNCE] mdb: Merkey's Linux Kernel Debugger 2.6.27-rc4 released
Peter Zijlstra wrote:
> Not sure - I think all barrier clobber the full register and memory set.
> So if you access a variable after a barrier it will have to issue a
> load.
>
IIRC a barrier only clobbers memory. gcc must reload a variable from
memory unless it can prove the variable's address has not escaped anywhere.
So:
void f()
{
int v;
v = g();
barrier();
do_domething_with(v);
}
Need not reload v from memory (indeed, v can be in a register for its
entire lifetime), but
void f()
{
int v;
v = g();
h(&v);
barrier();
do_domething_with(v);
}
Will force v into memory, and reload it after the barrier.
--
error compiling committee.c: too many arguments to function
--
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