Date: Thu, 11 Oct 2007 21:41:43 -0500
From: Olof Johansson <olof@lixom.net>
To: Kyle McMartin <kyle@mcmartin.ca>
Cc: Paul Mackerras <paulus@samba.org>, linux-kernel@vger.kernel.org,
       akpm@linux-foundation.org, lethal@linux-sh.org, kyle@parisc-linux.org,
       grundler@parisc-linux.org, linuxppc-dev@ozlabs.org
Subject: Re: [PATCH 2/2] powerpc: Switch to generic WARN_ON()/BUG_ON()
Message-ID: <20071012024143.GA20475@lixom.net>
References: <20071011171211.GB10877@lixom.net> <20071011171413.GC10877@lixom.net> <18190.52379.97647.468384@cargo.ozlabs.ibm.com> <20071012020419.GB19268@fattire.cabal.ca>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20071012020419.GB19268@fattire.cabal.ca>
User-Agent: Mutt/1.5.16 (2007-06-11)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1025
Lines: 25

On Thu, Oct 11, 2007 at 10:04:19PM -0400, Kyle McMartin wrote:
> On Fri, Oct 12, 2007 at 11:23:39AM +1000, Paul Mackerras wrote:
> > Olof Johansson writes:
> > 
> > > Not using the ppc-specific WARN_ON/BUG_ON constructs actually saves about
> > > 4K text on a ppc64_defconfig. The main reason seems to be that prepping
> > > the arguments to the conditional trap instructions is more work than
> > > just doing a compare and branch.
> > 
> > It might be more instructions but it takes fewer cycles, I would
> > expect.  Do you have the actual instruction sequences to compare?
> > 
> 
> I really hope WARN_ON/BUG_ON aren't hotpaths on powerpc. ;-)

Not the taken branch of them, no. :)  But making it past them as fast
as possible when they're not tripping is always good.


-Olof
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/