Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1473473

Re: [PATCH 06/10] MIPS: pm-cps: Use MIPS standard lightweight ordering barrier

From Matt Redfearn <matt.redfearn@imgtec.com>
Newsgroups linux.kernel
Subject Re: [PATCH 06/10] MIPS: pm-cps: Use MIPS standard lightweight ordering barrier
Date 2016-08-31 15:40 +0200
Message-ID <scdUd-2XV-9@gated-at.bofh.it> (permalink)
References <scbfH-1kx-7@gated-at.bofh.it> <scbfI-1kx-31@gated-at.bofh.it> <sccbM-1TJ-21@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw



On 31/08/16 12:48, Peter Zijlstra wrote:
> On Wed, Aug 31, 2016 at 11:44:35AM +0100, Matt Redfearn wrote:
>> Since R2 of the MIPS architecture, SYNC(0x10) has been an optional but
>> architecturally defined ordering barrier. If a CPU does not implement it,
>> the arch specifies that it must fall back to SYNC(0).
>>
>> Define the barrier type and always use it in the pm-cps code rather than
>> falling back to the heavyweight sync(0) such that we can benefit from
>> the lighter weight sync.
>>
> Changelog does not explain what 0x10 is, nor why its sufficient for this
> case.

Hi Peter,

The code previously had 0x10 as a magic number, this patch just replaces 
that with a #defined name. The value is documented in the MIPS64 
instruction set manual, https://imgtec.com/?do-download=4302, table 6.5.

This sync type has been standard since MIPSr2. That document also states 
that "If an implementation does not use one of these non-zero values to 
define a different synchronization behavior, then that non-zero value of 
stype must act the same as stype zero completion barrier." As such, 
stype_ordering can always be set to this sync type rather than setting 
it only for certain CPUs.

Thanks,
Matt

>
> Changelog also fails to explain why you do this.
> How do you expect anybody to review this?

Back to linux.kernel | Previous | NextPrevious in thread | Next in thread | Find similar | Unroll thread


Thread

[PATCH 00/10] MIPS CPC fixup and CPU Idle for MIPSr6 CPUs Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
  [PATCH 05/10] MIPS: pm-cps: Add P6600 implementation lightweight sync types Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
  [PATCH 09/10] MIPS: SMP: Wrap call to mips_cpc_lock_other in mips_cm_lock_other Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
  [PATCH 10/10] cpuidle: cpuidle-cps: Enable use with MIPSr6 CPUs. Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
  [PATCH 03/10] MIPS: pm-cps: Change FSB workaround to CPU blacklist Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
  [PATCH 02/10] MIPS: CPC: Avoid lock when MIPS CM >= 3 is present Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
  [PATCH 08/10] MIPS: pm-cps: Support CM3 changes to Coherence Enable Register Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
  [PATCH 06/10] MIPS: pm-cps: Use MIPS standard lightweight ordering barrier Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
    Re: [PATCH 06/10] MIPS: pm-cps: Use MIPS standard lightweight  ordering barrier Peter Zijlstra <peterz@infradead.org> - 2016-08-31 13:50 +0200
      Re: [PATCH 06/10] MIPS: pm-cps: Use MIPS standard lightweight  ordering barrier Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 15:40 +0200
        Re: [PATCH 06/10] MIPS: pm-cps: Use MIPS standard lightweight  ordering barrier Peter Zijlstra <peterz@infradead.org> - 2016-08-31 16:30 +0200
          Re: [PATCH 06/10] MIPS: pm-cps: Use MIPS standard lightweight  ordering barrier Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 17:50 +0200
  [PATCH 04/10] MIPS: pm-cps: Remove I6400 sync types Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200
  [PATCH 07/10] MIPS: pm-cps: Add MIPSr6 CPU support Matt Redfearn <matt.redfearn@imgtec.com> - 2016-08-31 12:50 +0200

csiph-web