mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Daniel J Blueman <daniel@numascale.com>
To: paulmck@linux.vnet.ibm.com, Richard Henderson <rth@twiddle.net>
Cc: Matt Turner <mattst88@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Waiman Long <waiman.long@hp.com>,
	Linux Kernel <linux-kernel@vger.kernel.org>,
	Ivan Kokshaysky <ink@jurassic.park.msu.ru>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH v8 4/4] qrwlock: Use smp_store_release() in write_unlock()
Date: Wed, 15 Jan 2014 11:08:16 +0800	[thread overview]
Message-ID: <52D5FBA0.8070500@numascale.com> (raw)
In-Reply-To: <20140114234443.GY10038@linux.vnet.ibm.com>

On 01/15/2014 07:44 AM, Paul E. McKenney wrote:
> On Tue, Jan 14, 2014 at 10:01:04AM -0800, Richard Henderson wrote:
>> On 01/14/2014 09:08 AM, Matt Turner wrote:
>>> On Tue, Jan 14, 2014 at 3:03 AM, Peter Zijlstra <peterz@infradead.org> wrote:
>>>> On Tue, Jan 14, 2014 at 10:28:23AM +0800, Daniel J Blueman wrote:
>>>>>> Peter,
>>>>>>
>>>>>> I found out that the build failure was caused by the fact that the
>>>>>> __native_word() macro (used internally by compiletime_assert_atomic())
>>>>>> allows only a size of 4 or 8 for x86-64. The data type that I used is a
>>>>>> byte. Is there a reason why byte and short are not considered native?
>>>>>
>>>>> It seems likely it was implemented like that since there was no existing
>>>>> need; long can be relied on as the largest native type, so this should
>>>>> suffice and works here:
>>>>
>>>> There's Alphas that cannot actually atomically adres a byte; I do not
>>>> konw if Linux cares about them, but if it does, we cannot in fact rely
>>>> on this in generic primitives like this.
>>>
>>> That's right, and thanks for the heads-up. Alpha can only address 4
>>> and 8 bytes atomically. (LDL_L, LDQ_L, STL_C, STQ_C).
>>>
>>> The Byte-Word extension in EV56 doesn't add new atomics, so in fact no
>>> Alphas can address < 4 bytes atomically.
>>
>> Emulated with aligned 4 byte atomics, and masking.  The same is true for arm,
>> ppc, mips which, depending on cpu, also lack < 4 byte atomics.
>
> Which means that Alpha should be able to similarly emulate 1-byte and
> 2-byte atomics, correct?

If it's not possible to guarantee that GCC emits the 4-byte atomics by 
using a union, then we could emit the instructions via assembly. We'd 
introduce a macro to ensure lock word alignment, and this would be safe 
for unsigned counting up to the packed type limit. Maybe that's just too 
over-constrained though.

Thanks,
   Daniel
-- 
Daniel J Blueman
Principal Software Engineer, Numascale

  parent reply	other threads:[~2014-01-15  3:08 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-01-13  2:47 Daniel J Blueman
2014-01-13  3:49 ` Paul E. McKenney
2014-01-13 16:41 ` Waiman Long
2014-01-14  2:28   ` Daniel J Blueman
2014-01-14 11:03     ` Peter Zijlstra
2014-01-14 15:25       ` Waiman Long
2014-01-14 17:08       ` Matt Turner
2014-01-14 18:01         ` Richard Henderson
2014-01-14 19:09           ` Waiman Long
2014-01-14 20:20             ` Peter Zijlstra
2014-01-14 23:44           ` Paul E. McKenney
2014-01-15  0:25             ` Linus Torvalds
2014-01-15  2:39               ` Paul E. McKenney
2014-01-15  8:07                 ` Peter Zijlstra
2014-01-15 20:53                   ` Paul E. McKenney
2014-01-15 23:21                     ` Peter Zijlstra
     [not found]                       ` <CA+55aFydYLQeBq=4AQQp_4dAnq09ocLmde1LFaXiNAJ=wJzfFA@mail.gmail.com>
2014-01-16 10:36                         ` Peter Zijlstra
2014-01-18 10:01                           ` Paul E. McKenney
2014-01-18 11:34                             ` Peter Zijlstra
2014-01-18 12:25                               ` Paul E. McKenney
2014-01-18 12:41                                 ` Peter Zijlstra
2014-01-18 21:22                                   ` Paul E. McKenney
2014-01-19  0:57                                     ` Linus Torvalds
2014-01-19  8:04                                       ` Paul E. McKenney
2014-01-19 19:56                                         ` Linus Torvalds
2014-01-20  0:52                                           ` Paul E. McKenney
2014-01-21 15:02                                         ` Waiman Long
2014-01-21 15:41                                           ` Peter Zijlstra
2014-01-21 16:16                                             ` Waiman Long
2014-01-15  3:08             ` Daniel J Blueman [this message]
  -- strict thread matches above, loose matches on Subject: below --
2014-01-08 16:59 [PATCH v8 0/4] qrwlock: Introducing a queue read/write lock implementation Waiman Long
2014-01-08 16:59 ` [PATCH v8 4/4] qrwlock: Use smp_store_release() in write_unlock() Waiman Long

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=52D5FBA0.8070500@numascale.com \
    --to=daniel@numascale.com \
    --cc=ink@jurassic.park.msu.ru \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mattst88@gmail.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=rth@twiddle.net \
    --cc=torvalds@linux-foundation.org \
    --cc=waiman.long@hp.com \
    /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

Powered by JetHome