Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <79b1b62c-8ea1-5f47-bf80-3e003f7a3ac7@rasmusvillemoes.dk>
Date:   Tue, 9 Aug 2022 14:29:12 +0200
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.11.0
Subject: Re: [PATCH 11/16] time: optimize tick_check_preferred()
Content-Language: en-US
To:     Yury Norov <yury.norov@gmail.com>,
        Thomas Gleixner <tglx@linutronix.de>
Cc:     linux-kernel@vger.kernel.org,
        Alexander Lobakin <alexandr.lobakin@intel.com>,
        Alexei Starovoitov <ast@kernel.org>,
        Alexey Klimov <aklimov@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Andrii Nakryiko <andrii@kernel.org>,
        Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
        Ben Segall <bsegall@google.com>,
        Christoph Lameter <cl@linux.com>,
        Dan Williams <dan.j.williams@intel.com>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Dennis Zhou <dennis@kernel.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Eric Dumazet <edumazet@google.com>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Guenter Roeck <linux@roeck-us.net>,
        Ingo Molnar <mingo@redhat.com>,
        Isabella Basso <isabbasso@riseup.net>,
        John Fastabend <john.fastabend@gmail.com>,
        Josh Poimboeuf <jpoimboe@kernel.org>,
        Juergen Gross <jgross@suse.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        KP Singh <kpsingh@kernel.org>,
        Kees Cook <keescook@chromium.org>,
        Martin KaFai Lau <kafai@fb.com>,
        Mel Gorman <mgorman@suse.de>, Miroslav Benes <mbenes@suse.cz>,
        Nathan Chancellor <nathan@kernel.org>,
        "Paul E . McKenney" <paulmck@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Randy Dunlap <rdunlap@infradead.org>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
        Song Liu <songliubraving@fb.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Tejun Heo <tj@kernel.org>,
        Valentin Schneider <vschneid@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Vlastimil Babka <vbabka@suse.cz>, Yonghong Song <yhs@fb.com>,
        linux-mm@kvack.org, netdev@vger.kernel.org, bpf@vger.kernel.org
References: <20220718192844.1805158-1-yury.norov@gmail.com>
 <20220718192844.1805158-12-yury.norov@gmail.com> <87fsi9rcxu.ffs@tglx>
 <87czdbq7up.ffs@tglx> <YvE8HGXFDicr/zI5@yury-laptop>
From:   Rasmus Villemoes <linux@rasmusvillemoes.dk>
In-Reply-To: <YvE8HGXFDicr/zI5@yury-laptop>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 08/08/2022 18.38, Yury Norov wrote:
> On Mon, Aug 08, 2022 at 01:42:54PM +0200, Thomas Gleixner wrote:
>> On Sat, Aug 06 2022 at 10:30, Thomas Gleixner wrote:
>>> On Mon, Jul 18 2022 at 12:28, Yury Norov wrote:
>>>
>>>> tick_check_preferred() calls cpumask_equal() even if
>>>> curdev->cpumask == newdev->cpumask. Fix it.
>>>
>>> What's to fix here? It's a pointless operation in a slow path and all
>>> your "fix' is doing is to make the code larger.
> 
> Pointless operation in a slow path is still pointless.
>  
>> In fact cpumask_equal() should have the ptr1 == ptr2 check, so you don't
>> have to add it all over the place.
> 
> This adds to the image size:
> add/remove: 1/1 grow/shrink: 24/3 up/down: 507/-46 (461)
> 
> The more important, cpumask shouldn't check parameters because this is
> an internal function. This whole series point is about adding such checks
> under DEBUG_BITMAP config, and not affecting general case.

Yury, calling bitmap_equal (and by extension cpumask_equal) with
something that happens in some cases to be the same pointer for both
operands is not a bug.

If you want to optimize that case, add a check in __bitmap_equal(), it
will add a few bytes (maybe 2-4 instructions) to the kernel image, much
less than what this whole series does by open-coding that check all
over, and since it's comparing two registers, it won't in any way affect
the performance of the case where the pointers are distinct.

Rasmus