From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Paul E. McKenney" Subject: Re: [v3,11/41] mips: reuse asm-generic/barrier.h Date: Wed, 27 Jan 2016 15:30:18 -0800 Message-ID: <20160127233018.GN4503@linux.vnet.ibm.com> References: <20160118081929.GA30420@gondor.apana.org.au> <20160118154629.GB3818@linux.vnet.ibm.com> <20160126165207.GB6029@fixme-laptop.cn.ibm.com> <20160126172227.GG6357@twins.programming.kicks-ass.net> <20160126201037.GU4503@linux.vnet.ibm.com> <20160126232921.GY4503@linux.vnet.ibm.com> <20160127020447.GA1293@fixme-laptop.cn.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from e34.co.us.ibm.com ([32.97.110.152]:50975 "EHLO e34.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S967507AbcA1Apt (ORCPT ); Wed, 27 Jan 2016 19:45:49 -0500 Received: from localhost by e34.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Wed, 27 Jan 2016 17:45:49 -0700 Content-Disposition: inline In-Reply-To: <20160127020447.GA1293@fixme-laptop.cn.ibm.com> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Boqun Feng Cc: Linus Torvalds , Peter Zijlstra , Herbert Xu , Leonid Yegoshin , linux-mips , "linux-ia64@vger.kernel.org" , "Michael S. Tsirkin" , Will Deacon , virtualization , Peter Anvin , sparclinux@vger.kernel.org, Ingo Molnar , "linux-arch@vger.kernel.org" , linux-s390 , Russell King - ARM Linux , uml-devel , linux-sh@vger.kernel.org, Michael Ellerman , the arch/x86 maintainers , xen-devel@lists.xenproject.org, Ingo Molnar linu On Wed, Jan 27, 2016 at 10:04:47AM +0800, Boqun Feng wrote: > On Tue, Jan 26, 2016 at 03:29:21PM -0800, Paul E. McKenney wrote: > > On Tue, Jan 26, 2016 at 02:33:40PM -0800, Linus Torvalds wrote: > > > On Tue, Jan 26, 2016 at 2:15 PM, Linus Torvalds > > > wrote: > > > > > > > > You might as well just write it as > > > > > > > > struct foo x = READ_ONCE(*ptr); > > > > x->bar = 5; > > > > > > > > because that "smp_read_barrier_depends()" does NOTHING wrt the second write. > > > > > > Just to clarify: on alpha it adds a memory barrier, but that memory > > > barrier is useless. > > > > No trailing data-dependent read, so agreed, no smp_read_barrier_depends() > > needed. That said, I believe that we should encourage rcu_dereference*() > > or lockless_dereference() instead of READ_ONCE() for documentation > > reasons, though. > > > > > On non-alpha, it is a no-op, and obviously does nothing simply because > > > it generates no code. > > > > > > So if anybody believes that the "smp_read_barrier_depends()" does > > > something, they are *wrong*. > > > > The other problem with smp_read_barrier_depends() is that it is often > > a pain figuring out which prior load it is supposed to apply to. > > Hence my preference for rcu_dereference*() and lockless_dereference(). > > > > Because semantically speaking, rcu_derefence*() and > lockless_dereference() are CONSUME(i.e. data/address dependent > read->read and read->write pairs are ordered), whereas > smp_read_barrier_depends() only guarantees read->read pairs with data > dependency are ordered, right? > > If so, maybe we need to call it out in memory-barriers.txt, for example: > > diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt > index 904ee42..6b262c2 100644 > --- a/Documentation/memory-barriers.txt > +++ b/Documentation/memory-barriers.txt > @@ -1703,8 +1703,8 @@ There are some more advanced barrier functions: > > > (*) lockless_dereference(); > - This can be thought of as a pointer-fetch wrapper around the > - smp_read_barrier_depends() data-dependency barrier. > + This is a load, and any load or store that has a data dependency on the > + value returned by this load won't be reordered before this load. This is a good start, but more is needed to warn people off of smp_read_barrier_depends(). But yes, better explanation would be good. Thanx, Paul > This is also similar to rcu_dereference(), but in cases where > object lifetime is handled by some mechanism other than RCU, for > > > Regards, > Boqun > > > > And if anybody sends out an email with that smp_read_barrier_depends() > > > in an example, they are actively just confusing other people, which is > > > even worse than just being wrong. Which is why I jumped in. > > > > > > So stop perpetuating the myth that smp_read_barrier_depends() does > > > something here. It does not. It's a bug, and it has become this "mind > > > virus" for some people that seem to believe that it does something. > > > > It looks like I should add words to memory-barriers.txt de-emphasizing > > smp_read_barrier_depends(). I will take a look at that. > > > > > I had to remove this crap once from the kernel already, see commit > > > 105ff3cbf225 ("atomic: remove all traces of READ_ONCE_CTRL() and > > > atomic*_read_ctrl()"). > > > > > > I don't want to ever see that broken construct again. And I want to > > > make sure that everybody is educated about how broken it was. I'm > > > extremely unhappy that it came up again. > > > > Well, if it makes you feel better, that was control dependencies and this > > was data dependencies. So it was not -exactly- the same. ;-) > > > > (Sorry, couldn't resist...) > > > > > If it turns out that some architecture does actually need a barrier > > > between a read and a dependent write, then that will mean that > > > > > > (a) we'll have to make up a _new_ barrier, because > > > "smp_read_barrier_depends()" is not that barrier. We'll presumably > > > then have to make that new barrier part of "rcu_derefence()" and > > > friends. > > > > Agreed. We can worry about whether or not we replace the current > > smp_read_barrier_depends() with that new barrier when and if such > > hardware appears. > > > > > (b) we will have found an architecture with even worse memory > > > ordering semantics than alpha, and we'll have to stop castigating > > > alpha for being the worst memory ordering ever. > > > > ;-) ;-) ;-) > > > > > but I sincerely hope that we'll never find that kind of broken architecture. > > > > Apparently at least some hardware vendors are reading memory-barriers.txt, > > so perhaps the odds of that kind of breakage have reduced. > > > > Thanx, Paul > > From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from e34.co.us.ibm.com ([32.97.110.152]:50975 "EHLO e34.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S967507AbcA1Apt (ORCPT ); Wed, 27 Jan 2016 19:45:49 -0500 Received: from localhost by e34.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Wed, 27 Jan 2016 17:45:49 -0700 Date: Wed, 27 Jan 2016 15:30:18 -0800 From: "Paul E. McKenney" Subject: Re: [v3,11/41] mips: reuse asm-generic/barrier.h Message-ID: <20160127233018.GN4503@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <20160118081929.GA30420@gondor.apana.org.au> <20160118154629.GB3818@linux.vnet.ibm.com> <20160126165207.GB6029@fixme-laptop.cn.ibm.com> <20160126172227.GG6357@twins.programming.kicks-ass.net> <20160126201037.GU4503@linux.vnet.ibm.com> <20160126232921.GY4503@linux.vnet.ibm.com> <20160127020447.GA1293@fixme-laptop.cn.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20160127020447.GA1293@fixme-laptop.cn.ibm.com> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Boqun Feng Cc: Linus Torvalds , Peter Zijlstra , Herbert Xu , Leonid Yegoshin , linux-mips , "linux-ia64@vger.kernel.org" , "Michael S. Tsirkin" , Will Deacon , virtualization , Peter Anvin , sparclinux@vger.kernel.org, Ingo Molnar , "linux-arch@vger.kernel.org" , linux-s390 , Russell King - ARM Linux , uml-devel , linux-sh@vger.kernel.org, Michael Ellerman , the arch/x86 maintainers , xen-devel@lists.xenproject.org, Ingo Molnar , linux-xtensa@linux-xtensa.org, James Hogan , Arnd Bergmann , Stefano Stabellini , adi-buildroot-devel@lists.sourceforge.net, David Daney , Thomas Gleixner , linux-metag@vger.kernel.org, "linux-arm-kernel@lists.infradead.org" , Andrew Cooper , Linux Kernel Mailing List , Ralf Baechle , Joe Perches , ppc-dev , David Miller Message-ID: <20160127233018.SOdncxuJgv-lnLrkPlUl4hGM1xpPk4KgqkSLY1feGN0@z> On Wed, Jan 27, 2016 at 10:04:47AM +0800, Boqun Feng wrote: > On Tue, Jan 26, 2016 at 03:29:21PM -0800, Paul E. McKenney wrote: > > On Tue, Jan 26, 2016 at 02:33:40PM -0800, Linus Torvalds wrote: > > > On Tue, Jan 26, 2016 at 2:15 PM, Linus Torvalds > > > wrote: > > > > > > > > You might as well just write it as > > > > > > > > struct foo x = READ_ONCE(*ptr); > > > > x->bar = 5; > > > > > > > > because that "smp_read_barrier_depends()" does NOTHING wrt the second write. > > > > > > Just to clarify: on alpha it adds a memory barrier, but that memory > > > barrier is useless. > > > > No trailing data-dependent read, so agreed, no smp_read_barrier_depends() > > needed. That said, I believe that we should encourage rcu_dereference*() > > or lockless_dereference() instead of READ_ONCE() for documentation > > reasons, though. > > > > > On non-alpha, it is a no-op, and obviously does nothing simply because > > > it generates no code. > > > > > > So if anybody believes that the "smp_read_barrier_depends()" does > > > something, they are *wrong*. > > > > The other problem with smp_read_barrier_depends() is that it is often > > a pain figuring out which prior load it is supposed to apply to. > > Hence my preference for rcu_dereference*() and lockless_dereference(). > > > > Because semantically speaking, rcu_derefence*() and > lockless_dereference() are CONSUME(i.e. data/address dependent > read->read and read->write pairs are ordered), whereas > smp_read_barrier_depends() only guarantees read->read pairs with data > dependency are ordered, right? > > If so, maybe we need to call it out in memory-barriers.txt, for example: > > diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt > index 904ee42..6b262c2 100644 > --- a/Documentation/memory-barriers.txt > +++ b/Documentation/memory-barriers.txt > @@ -1703,8 +1703,8 @@ There are some more advanced barrier functions: > > > (*) lockless_dereference(); > - This can be thought of as a pointer-fetch wrapper around the > - smp_read_barrier_depends() data-dependency barrier. > + This is a load, and any load or store that has a data dependency on the > + value returned by this load won't be reordered before this load. This is a good start, but more is needed to warn people off of smp_read_barrier_depends(). But yes, better explanation would be good. Thanx, Paul > This is also similar to rcu_dereference(), but in cases where > object lifetime is handled by some mechanism other than RCU, for > > > Regards, > Boqun > > > > And if anybody sends out an email with that smp_read_barrier_depends() > > > in an example, they are actively just confusing other people, which is > > > even worse than just being wrong. Which is why I jumped in. > > > > > > So stop perpetuating the myth that smp_read_barrier_depends() does > > > something here. It does not. It's a bug, and it has become this "mind > > > virus" for some people that seem to believe that it does something. > > > > It looks like I should add words to memory-barriers.txt de-emphasizing > > smp_read_barrier_depends(). I will take a look at that. > > > > > I had to remove this crap once from the kernel already, see commit > > > 105ff3cbf225 ("atomic: remove all traces of READ_ONCE_CTRL() and > > > atomic*_read_ctrl()"). > > > > > > I don't want to ever see that broken construct again. And I want to > > > make sure that everybody is educated about how broken it was. I'm > > > extremely unhappy that it came up again. > > > > Well, if it makes you feel better, that was control dependencies and this > > was data dependencies. So it was not -exactly- the same. ;-) > > > > (Sorry, couldn't resist...) > > > > > If it turns out that some architecture does actually need a barrier > > > between a read and a dependent write, then that will mean that > > > > > > (a) we'll have to make up a _new_ barrier, because > > > "smp_read_barrier_depends()" is not that barrier. We'll presumably > > > then have to make that new barrier part of "rcu_derefence()" and > > > friends. > > > > Agreed. We can worry about whether or not we replace the current > > smp_read_barrier_depends() with that new barrier when and if such > > hardware appears. > > > > > (b) we will have found an architecture with even worse memory > > > ordering semantics than alpha, and we'll have to stop castigating > > > alpha for being the worst memory ordering ever. > > > > ;-) ;-) ;-) > > > > > but I sincerely hope that we'll never find that kind of broken architecture. > > > > Apparently at least some hardware vendors are reading memory-barriers.txt, > > so perhaps the odds of that kind of breakage have reduced. > > > > Thanx, Paul > >