From mboxrd@z Thu Jan 1 00:00:00 1970 From: Russell King - ARM Linux Subject: Re: [RFC] change non-atomic bitops method Date: Mon, 2 Feb 2015 23:31:36 +0000 Message-ID: <20150202233136.GL8656@n2100.arm.linux.org.uk> References: <35FD53F367049845BC99AC72306C23D1044A02027E0A@CNBJMBX05.corpusers.net> <20150202152909.13bfd11f192fb0268b2ab4bf@linux-foundation.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20150202152909.13bfd11f192fb0268b2ab4bf@linux-foundation.org> Sender: linux-kernel-owner@vger.kernel.org To: Andrew Morton Cc: "Wang, Yalin" , "'arnd@arndb.de'" , "'linux-arch@vger.kernel.org'" , "'linux-kernel@vger.kernel.org'" , "'linux-arm-kernel@lists.infradead.org'" List-Id: linux-arch.vger.kernel.org On Mon, Feb 02, 2015 at 03:29:09PM -0800, Andrew Morton wrote: > On Mon, 2 Feb 2015 11:55:03 +0800 "Wang, Yalin" wrote: > > > This patch change non-atomic bitops, > > add a if() condition to test it, before set/clear the bit. > > so that we don't need dirty the cache line, if this bit > > have been set or clear. On SMP system, dirty cache line will > > need invalidate other processors cache line, this will have > > some impact on SMP systems. > > > > --- a/include/asm-generic/bitops/non-atomic.h > > +++ b/include/asm-generic/bitops/non-atomic.h > > @@ -17,7 +17,9 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) > > unsigned long mask = BIT_MASK(nr); > > unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); > > > > - *p |= mask; > > + if ((*p & mask) == 0) > > + *p |= mask; > > + > > } > > hm, maybe. > > It will speed up set_bit on an already-set bit. But it will slow down > set_bit on a not-set bit. And the latter case is presumably much, much > more common. > > How do we know the patch is a net performance gain? Yes, we do need to know the performance impact of changes like this - as Laura said in her reply already... -- FTTC broadband for 0.8mile line: currently at 10.5Mbps down 400kbps up according to speedtest.net. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from pandora.arm.linux.org.uk ([78.32.30.218]:43813 "EHLO pandora.arm.linux.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752461AbbBBXbr (ORCPT ); Mon, 2 Feb 2015 18:31:47 -0500 Date: Mon, 2 Feb 2015 23:31:36 +0000 From: Russell King - ARM Linux Subject: Re: [RFC] change non-atomic bitops method Message-ID: <20150202233136.GL8656@n2100.arm.linux.org.uk> References: <35FD53F367049845BC99AC72306C23D1044A02027E0A@CNBJMBX05.corpusers.net> <20150202152909.13bfd11f192fb0268b2ab4bf@linux-foundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150202152909.13bfd11f192fb0268b2ab4bf@linux-foundation.org> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Andrew Morton Cc: "Wang, Yalin" , "'arnd@arndb.de'" , "'linux-arch@vger.kernel.org'" , "'linux-kernel@vger.kernel.org'" , "'linux-arm-kernel@lists.infradead.org'" Message-ID: <20150202233136.h_-ExbBPsdtrStF4quAxR5yMpEvlEHMCA7bA5pB8xMM@z> On Mon, Feb 02, 2015 at 03:29:09PM -0800, Andrew Morton wrote: > On Mon, 2 Feb 2015 11:55:03 +0800 "Wang, Yalin" wrote: > > > This patch change non-atomic bitops, > > add a if() condition to test it, before set/clear the bit. > > so that we don't need dirty the cache line, if this bit > > have been set or clear. On SMP system, dirty cache line will > > need invalidate other processors cache line, this will have > > some impact on SMP systems. > > > > --- a/include/asm-generic/bitops/non-atomic.h > > +++ b/include/asm-generic/bitops/non-atomic.h > > @@ -17,7 +17,9 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) > > unsigned long mask = BIT_MASK(nr); > > unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); > > > > - *p |= mask; > > + if ((*p & mask) == 0) > > + *p |= mask; > > + > > } > > hm, maybe. > > It will speed up set_bit on an already-set bit. But it will slow down > set_bit on a not-set bit. And the latter case is presumably much, much > more common. > > How do we know the patch is a net performance gain? Yes, we do need to know the performance impact of changes like this - as Laura said in her reply already... -- FTTC broadband for 0.8mile line: currently at 10.5Mbps down 400kbps up according to speedtest.net.