From: Peter Zijlstra <peterz@infradead.org>
To: "Huang, Ying" <ying.huang@intel.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@kernel.org>,
Michael Ellerman <mpe@ellerman.id.au>,
Borislav Petkov <bp@suse.de>,
Thomas Gleixner <tglx@linutronix.de>,
Juergen Gross <jgross@suse.com>, Aaron Lu <aaron.lu@intel.com>
Subject: Re: [PATCH 3/3] IPI: Avoid to use 2 cache lines for one call_single_data
Date: Fri, 4 Aug 2017 11:20:39 +0200 [thread overview]
Message-ID: <20170804092039.ezsxko32a6n5ra4v@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <87wp6kyvda.fsf@yhuang-dev.intel.com>
On Fri, Aug 04, 2017 at 09:28:17AM +0800, Huang, Ying wrote:
> Peter Zijlstra <peterz@infradead.org> writes:
> [snip]
> > diff --git a/include/linux/smp.h b/include/linux/smp.h
> > index 68123c1fe549..8d817cb80a38 100644
> > --- a/include/linux/smp.h
> > +++ b/include/linux/smp.h
> > @@ -14,13 +14,16 @@
> > #include <linux/llist.h>
> >
> > typedef void (*smp_call_func_t)(void *info);
> > -struct call_single_data {
> > +struct __call_single_data {
> > struct llist_node llist;
> > smp_call_func_t func;
> > void *info;
> > unsigned int flags;
> > };
> >
> > +typedef struct __call_single_data call_single_data_t
> > + __aligned(sizeof(struct __call_single_data));
> > +
>
> Another requirement of the alignment is that it should be the power of
> 2. Otherwise, for example, if someone adds a field to struct, so that
> the size becomes 40 on x86_64. The alignment should be 64 instead of
> 40.
Yes I know. This generates a compiler error if sizeof() isn't a
power of 2. That's similar to the BUILD_BUG_ON() you added.
next prev parent reply other threads:[~2017-08-04 9:20 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-08-02 8:52 [PATCH 0/3] IPI: Avoid to use 2 cache lines for one call_single_data Huang, Ying
2017-08-02 8:52 ` [PATCH 1/3] percpu: Add alloc_percpu_aligned() Huang, Ying
2017-08-02 13:50 ` Christopher Lameter
2017-08-03 0:33 ` Huang, Ying
2017-08-02 8:52 ` [PATCH 2/3] iova: Use alloc_percpu_aligned() Huang, Ying
2017-08-02 8:52 ` [PATCH 3/3] IPI: Avoid to use 2 cache lines for one call_single_data Huang, Ying
2017-08-02 10:18 ` Eric Dumazet
2017-08-02 10:53 ` Peter Zijlstra
2017-08-03 8:35 ` Huang, Ying
2017-08-03 8:57 ` Peter Zijlstra
2017-08-04 1:28 ` Huang, Ying
2017-08-04 2:05 ` Huang, Ying
2017-08-04 9:27 ` Peter Zijlstra
2017-08-05 0:47 ` Huang, Ying
2017-08-07 8:28 ` Peter Zijlstra
2017-08-08 4:30 ` Huang, Ying
2017-08-14 5:44 ` Huang, Ying
2017-08-28 5:19 ` Huang, Ying
2017-08-28 8:49 ` Peter Zijlstra
2017-08-29 14:23 ` [tip:locking/core] smp: Avoid using two cache lines for struct call_single_data tip-bot for Ying Huang
2017-08-04 9:20 ` Peter Zijlstra [this message]
2017-08-02 13:54 ` [PATCH 0/3] IPI: Avoid to use 2 cache lines for one call_single_data Christopher Lameter
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=20170804092039.ezsxko32a6n5ra4v@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=aaron.lu@intel.com \
--cc=bp@suse.de \
--cc=eric.dumazet@gmail.com \
--cc=jgross@suse.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=tglx@linutronix.de \
--cc=ying.huang@intel.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;
as well as URLs for NNTP newsgroup(s).