mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Nicholas Piggin <npiggin@gmail.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>,
	linux-kernel@vger.kernel.org, Waiman Long <longman@redhat.com>,
	Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>
Subject: Re: [PATCH 05/13] locking/qspinlock: be less clever with the preprocessor
Date: Tue, 12 Jul 2022 10:29:17 +1000	[thread overview]
Message-ID: <1657585289.3ylf8n6zpa.astroid@bobo.none> (raw)
In-Reply-To: <YsRwJdjJqpXEFTnO@worktop.programming.kicks-ass.net>

Excerpts from Peter Zijlstra's message of July 6, 2022 3:08 am:
> On Tue, Jul 05, 2022 at 12:38:12AM +1000, Nicholas Piggin wrote:
>> Stop qspinlock.c including itself and avoid most of the function
>> renaming with the preprocessor.
>> 
>> This is mostly done by having the common slowpath code take a 'bool
>> paravirt' argument and adjusting code based on that.
> 
> What does code-gen do? Is it clever enough to constant fold the lot?
> 
> Should we be using __always_inline to ensure the compiler doesn't decide
> against inlining because $raisin and then emitting extra condtionals?
> 

It seems to fold it. Code is just different enough to make it hard
to follow what the asm differences are exactly but doesn't seem to
pass 'paravirt' anywhere.

Yes it does need __always_inline certainly. Only one path will ever
be used at runtime so any icache sharing decision by the compiler
would be wrong (and we don't care about image size very much).

Thanks,
Nick

  reply	other threads:[~2022-07-12  0:29 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-04 14:38 [PATCH 00/13] locking/qspinlock: simplify code generation Nicholas Piggin
2022-07-04 14:38 ` [PATCH 01/13] locking/qspinlock: remove pv_node abstraction Nicholas Piggin
2022-07-06 23:23   ` Boqun Feng
2022-07-04 14:38 ` [PATCH 02/13] locking/qspinlock: inline mcs_spinlock functions into qspinlock Nicholas Piggin
2022-07-05 16:57   ` Peter Zijlstra
2022-07-12  0:06     ` Nicholas Piggin
2022-07-04 14:38 ` [PATCH 03/13] locking/qspinlock: split common mcs queueing code into its own function Nicholas Piggin
2022-07-05 17:01   ` Peter Zijlstra
2022-07-12  0:10     ` Nicholas Piggin
2022-07-04 14:38 ` [PATCH 04/13] locking/qspinlock: move pv lock word helpers into qspinlock.c Nicholas Piggin
2022-07-05 19:34   ` Waiman Long
2022-07-12  0:11     ` Nicholas Piggin
2022-07-04 14:38 ` [PATCH 05/13] locking/qspinlock: be less clever with the preprocessor Nicholas Piggin
2022-07-05 17:08   ` Peter Zijlstra
2022-07-12  0:29     ` Nicholas Piggin [this message]
2022-07-05 20:02   ` Waiman Long
2022-07-12  0:33     ` Nicholas Piggin
2022-07-04 14:38 ` [PATCH 06/13] locking/qspinlock: merge qspinlock_paravirt.h into qspinlock.c Nicholas Piggin
2022-07-05 17:20   ` Peter Zijlstra
2022-07-05 17:36     ` Peter Zijlstra
2022-07-12  0:46       ` Nicholas Piggin
2022-07-06 13:35     ` Waiman Long
2022-07-06 14:16       ` Peter Zijlstra
2022-07-04 14:38 ` [PATCH 07/13] locking/qspinlock: remove arch qspinlock_paravirt.h includes Nicholas Piggin
2022-07-04 14:38 ` [PATCH 08/13] locking/qspinlock: stop renaming queued_spin_lock_slowpath to native_queued_spin_lock_slowpath Nicholas Piggin
2022-07-05 17:28   ` Peter Zijlstra
2022-07-04 14:38 ` [PATCH 09/13] locking/qspinlock: rename __pv_init_lock_hash to pv_spinlocks_init Nicholas Piggin
2022-07-04 14:38 ` [PATCH 10/13] locking/qspinlock: paravirt use simple trylock in case idx overflows Nicholas Piggin
2022-07-04 14:38 ` [PATCH 11/13] locking/qspinlock: Use queued_spin_trylock in pv_hybrid_queued_unfair_trylock Nicholas Piggin
2022-07-05 17:31   ` Peter Zijlstra
2022-07-05 20:15   ` Waiman Long
2022-07-12  0:48     ` Nicholas Piggin
2022-07-04 14:38 ` [PATCH 12/13] locking/qspinlock: separate pv_wait_node from the non-paravirt path Nicholas Piggin
2022-07-05 17:34   ` Peter Zijlstra
2022-07-12  0:50     ` Nicholas Piggin
2022-07-04 14:38 ` [PATCH 13/13] locking/qspinlock: simplify pv_wait_head_or_lock calling scheme Nicholas Piggin
2022-07-05 17:59 ` [PATCH 00/13] locking/qspinlock: simplify code generation Peter Zijlstra
2022-07-12  0:56   ` Nicholas Piggin

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=1657585289.3ylf8n6zpa.astroid@bobo.none \
    --to=npiggin@gmail.com \
    --cc=boqun.feng@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longman@redhat.com \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=will@kernel.org \
    /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
all inboxes | Powered by JetHome®