linux-arch.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Michael Ellerman <mpe@ellerman.id.au>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Nicholas Piggin <npiggin@gmail.com>,
	linux-arch <linux-arch@vger.kernel.org>,
	Will Deacon <will.deacon@arm.com>,
	Andrea Parri <andrea.parri@amarulasolutions.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Rich Felker <dalias@libc.org>,
	David Howells <dhowells@redhat.com>,
	Daniel Lustig <dlustig@nvidia.com>,
	Linux List Kernel Mailing <linux-kernel@vger.kernel.org>,
	"Maciej W. Rozycki" <macro@linux-mips.org>,
	Ingo Molnar <mingo@kernel.org>,
	Palmer Dabbelt <palmer@sifive.com>,
	Paul Burton <paul.burton@mips.com>,
	"Paul E. McKenney" <paulmck@linux.ibm.com>,
	Alan Stern <stern@rowland.harvard.edu>,
	Tony Luck <tony.luck@intel.com>,
	Yoshinori Sato <ysato@users.sour>
Subject: Re: [PATCH 01/20] asm-generic/mmiowb: Add generic implementation of mmiowb() tracking
Date: Thu, 7 Mar 2019 10:13:18 +0100	[thread overview]
Message-ID: <20190307091318.GA32477@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <87k1hbv7ba.fsf@concordia.ellerman.id.au>

On Thu, Mar 07, 2019 at 11:47:53AM +1100, Michael Ellerman wrote:
> The mutex unlock fast path is just:
> 
> 	if (atomic_long_cmpxchg_release(&lock->owner, curr, 0UL) == curr)
> 		return true;
> 
> And because it's the "release" variant we just use lwsync, which doesn't
> order MMIO. If it was just atomic_long_cmpxchg() that would work because
> we use sync for those.
> 
> __up_write() uses atomic_long_sub_return_release(), so same story.

As does spin_unlock() of course, which is a great segway into...

  my RCsc desires :-)

If all your unlocks were to have SYNC, your locks would, aside from
ordering MMIO, also be RCsc, Win-Win :-)

There is, of course, that pesky little performance detail that keeps
getting in the way.

WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: Michael Ellerman <mpe@ellerman.id.au>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Nicholas Piggin <npiggin@gmail.com>,
	linux-arch <linux-arch@vger.kernel.org>,
	Will Deacon <will.deacon@arm.com>,
	Andrea Parri <andrea.parri@amarulasolutions.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Rich Felker <dalias@libc.org>,
	David Howells <dhowells@redhat.com>,
	Daniel Lustig <dlustig@nvidia.com>,
	Linux List Kernel Mailing <linux-kernel@vger.kernel.org>,
	"Maciej W. Rozycki" <macro@linux-mips.org>,
	Ingo Molnar <mingo@kernel.org>,
	Palmer Dabbelt <palmer@sifive.com>,
	Paul Burton <paul.burton@mips.com>,
	"Paul E. McKenney" <paulmck@linux.ibm.com>,
	Alan Stern <stern@rowland.harvard.edu>,
	Tony Luck <tony.luck@intel.com>,
	Yoshinori Sato <ysato@users.sourceforge.jp>
Subject: Re: [PATCH 01/20] asm-generic/mmiowb: Add generic implementation of mmiowb() tracking
Date: Thu, 7 Mar 2019 10:13:18 +0100	[thread overview]
Message-ID: <20190307091318.GA32477@hirez.programming.kicks-ass.net> (raw)
Message-ID: <20190307091318.BnTesp7HlyWrUZ1_Xf9xSybigYrJtX-TaVqjSPWV3fc@z> (raw)
In-Reply-To: <87k1hbv7ba.fsf@concordia.ellerman.id.au>

On Thu, Mar 07, 2019 at 11:47:53AM +1100, Michael Ellerman wrote:
> The mutex unlock fast path is just:
> 
> 	if (atomic_long_cmpxchg_release(&lock->owner, curr, 0UL) == curr)
> 		return true;
> 
> And because it's the "release" variant we just use lwsync, which doesn't
> order MMIO. If it was just atomic_long_cmpxchg() that would work because
> we use sync for those.
> 
> __up_write() uses atomic_long_sub_return_release(), so same story.

As does spin_unlock() of course, which is a great segway into...

  my RCsc desires :-)

If all your unlocks were to have SYNC, your locks would, aside from
ordering MMIO, also be RCsc, Win-Win :-)

There is, of course, that pesky little performance detail that keeps
getting in the way.

  parent reply	other threads:[~2019-03-07  9:13 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-01 14:03 [PATCH 00/20] Remove Mysterious Macro Intended to Obscure Weird Behaviours (mmiowb()) Will Deacon
2019-03-01 14:03 ` Will Deacon
2019-03-01 14:03 ` [PATCH 01/20] asm-generic/mmiowb: Add generic implementation of mmiowb() tracking Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-03  1:43   ` Nicholas Piggin
2019-03-03  1:43     ` Nicholas Piggin
2019-03-03  2:18     ` Linus Torvalds
2019-03-03  2:18       ` Linus Torvalds
2019-03-03  3:34       ` Nicholas Piggin
2019-03-03  3:34         ` Nicholas Piggin
     [not found]         ` <CAHk-=whVN58nWh29jvXx+X-Yx9dCC6BeAZOtKak+d01y_UVg=A@mail.gmail.com>
2019-03-03 10:05           ` Nicholas Piggin
2019-03-03 10:05             ` Nicholas Piggin
2019-03-03 18:48             ` Linus Torvalds
2019-03-03 18:48               ` Linus Torvalds
2019-03-05  0:21               ` Nicholas Piggin
2019-03-05  0:21                 ` Nicholas Piggin
2019-03-05  0:33                 ` Linus Torvalds
2019-03-05  0:33                   ` Linus Torvalds
2019-03-03  9:26     ` Michael Ellerman
2019-03-03  9:26       ` Michael Ellerman
2019-03-03 10:07       ` Nicholas Piggin
2019-03-03 10:07         ` Nicholas Piggin
2019-03-04  1:01         ` Michael Ellerman
2019-03-04  1:01           ` Michael Ellerman
2019-03-05  0:21           ` Nicholas Piggin
2019-03-05  0:21             ` Nicholas Piggin
2019-03-04 10:24     ` Michael Ellerman
2019-03-04 10:24       ` Michael Ellerman
2019-03-05  0:19       ` Linus Torvalds
2019-03-05  0:19         ` Linus Torvalds
2019-03-07  0:47         ` Michael Ellerman
2019-03-07  0:47           ` Michael Ellerman
2019-03-07  1:13           ` Linus Torvalds
2019-03-07  1:13             ` Linus Torvalds
2019-03-07  9:13           ` Peter Zijlstra [this message]
2019-03-07  9:13             ` Peter Zijlstra
2019-03-01 14:03 ` [PATCH 02/20] arch: Use asm-generic header for asm/mmiowb.h Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 03/20] mmiowb: Hook up mmiowb helpers to spinlocks and generic I/O accessors Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-03  1:47   ` Nicholas Piggin
2019-03-03  1:47     ` Nicholas Piggin
2019-03-01 14:03 ` [PATCH 04/20] ARM/io: Remove useless definition of mmiowb() Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 05/20] arm64/io: " Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 06/20] x86/io: " Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 07/20] nds32/io: " Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 08/20] m68k/io: " Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 09/20] sh/mmiowb: Add unconditional mmiowb() to arch_spin_unlock() Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 10/20] mips/mmiowb: " Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 22:16   ` Paul Burton
2019-03-01 22:16     ` Paul Burton
2019-03-01 14:03 ` [PATCH 11/20] ia64/mmiowb: " Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 12/20] powerpc/mmiowb: Hook up mmwiob() implementation to asm-generic code Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-02 12:46   ` Michael Ellerman
2019-03-02 12:46     ` Michael Ellerman
2019-03-01 14:03 ` [PATCH 13/20] riscv/mmiowb: " Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 21:13   ` Palmer Dabbelt
2019-03-01 21:13     ` Palmer Dabbelt
2019-03-01 14:03 ` [PATCH 14/20] Documentation: Kill all references to mmiowb() Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 15/20] drivers: Remove useless trailing comments from mmiowb() invocations Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 16/20] drivers: Remove explicit invocations of mmiowb() Will Deacon
2019-03-01 14:03 ` [PATCH 17/20] scsi/qla1280: Remove stale comment about mmiowb() Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 18/20] i40iw: Redefine i40iw_mmiowb() to do nothing Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 19/20] net/ethernet/silan/sc92031: Remove stale comment about mmiowb() Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 14:03 ` [PATCH 20/20] arch: Remove dummy mmiowb() definitions from arch code Will Deacon
2019-03-01 14:03   ` Will Deacon
2019-03-01 16:41 ` [PATCH 00/20] Remove Mysterious Macro Intended to Obscure Weird Behaviours (mmiowb()) Linus Torvalds
2019-03-01 16:41   ` Linus Torvalds
2019-03-02 12:56   ` Michael Ellerman
2019-03-02 12:56     ` Michael Ellerman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190307091318.GA32477@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=andrea.parri@amarulasolutions.com \
    --cc=arnd@arndb.de \
    --cc=benh@kernel.crashing.org \
    --cc=dalias@libc.org \
    --cc=dhowells@redhat.com \
    --cc=dlustig@nvidia.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=macro@linux-mips.org \
    --cc=mingo@kernel.org \
    --cc=mpe@ellerman.id.au \
    --cc=npiggin@gmail.com \
    --cc=palmer@sifive.com \
    --cc=paul.burton@mips.com \
    --cc=paulmck@linux.ibm.com \
    --cc=stern@rowland.harvard.edu \
    --cc=tony.luck@intel.com \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    --cc=ysato@users.sour \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).