From: Peter Zijlstra <peterz@infradead.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org,
mhiramat@kernel.org, bristot@redhat.com, jbaron@akamai.com,
torvalds@linux-foundation.org, tglx@linutronix.de,
mingo@kernel.org, namit@vmware.com, hpa@zytor.com,
luto@kernel.org, ard.biesheuvel@linaro.org, jpoimboe@redhat.com,
pbonzini@redhat.com, mathieu.desnoyers@efficios.com,
linux@rasmusvillemoes.dk
Subject: Re: [PATCH v6 15/17] static_call: Allow early init
Date: Tue, 14 Jul 2020 11:51:17 +0200 [thread overview]
Message-ID: <20200714095117.GS10769@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20200713162419.3a45f334@oasis.local.home>
On Mon, Jul 13, 2020 at 04:24:19PM -0400, Steven Rostedt wrote:
> On Sat, 11 Jul 2020 07:08:31 +0200
> Peter Zijlstra <peterz@infradead.org> wrote:
>
> > On Fri, Jul 10, 2020 at 09:14:26PM -0400, Steven Rostedt wrote:
> > > On Fri, 10 Jul 2020 15:38:46 +0200
> > > Peter Zijlstra <peterz@infradead.org> wrote:
> > >
> > > > In order to use static_call() to wire up x86_pmu, we need to
> > > > initialize earlier; copy some of the tricks from jump_label to enable
> > > > this.
> > > >
> > > > Primarily we overload key->next to store a sites pointer when there
> > > > are no modules, this avoids having to use kmalloc() to initialize the
> > > > sites and allows us to run much earlier.
> > > >
> > >
> > > I'm confused. What was the need to have key->next store site pointers
> > > in order to move it up earlier?
> >
> > The critical part was to not need an allocation.
>
> Why is an allocation needed? What's different about calling it early
> that we need an allocation or this trick?
>
> The two paragraphs above seem totally disconnected.
>
> "In order to use static_call() to wire up x86_pmu, we need to
> initialize earlier; copy some of the tricks from jump_label to enable
> this."
>
> What tricks were copied?
>
> "Primarily we overload key->next to store a sites pointer when there
^^ this trick...
+ union {
+ /* bit 0: 0 = mods, 1 = sites */
+ unsigned long type;
+ struct static_call_mod *mods;
+ struct static_call_site *sites;
+ };
If that isn't a trick, I don't know ;-)
> are no modules, this avoids having to use kmalloc() to initialize the
> sites and allows us to run much earlier."
>
> Why is kmalloc() (or this trick) needed to initialize the sites?
That's just how the code was; it treated vmlinux as the NULL module, and
as such needed a static_call_mod allocated to host the static_call_sites
pointer.
That is, the static_call_key has a single linked list pointer to
static_call_mod, and every module has an entry on that list with a
pointer to their sites. Very simple and straight forward.
Except it requires an allocation to set up, which is a pain is you want
it initialized very early.
next prev parent reply other threads:[~2020-07-14 9:51 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-10 13:38 [PATCH v6 00/17] Add static_call Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 01/17] notifier: Fix broken error handling pattern Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 02/17] module: Fix up module_notifier return values Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 03/17] module: Properly propagate MODULE_STATE_COMING failure Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 04/17] jump_label,module: Fix module lifetime for __jump_label_mod_text_reserved Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 05/17] compiler.h: Make __ADDRESSABLE() symbol truly unique Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 06/17] static_call: Add basic static call infrastructure Peter Zijlstra
2020-07-10 21:56 ` Steven Rostedt
2020-07-10 13:38 ` [PATCH v6 07/17] static_call: Add inline " Peter Zijlstra
2020-07-10 21:57 ` Steven Rostedt
2020-07-10 13:38 ` [PATCH v6 08/17] static_call: Avoid kprobes on inline static_call()s Peter Zijlstra
2020-07-10 22:00 ` Steven Rostedt
2020-07-11 10:30 ` Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 09/17] x86/static_call: Add out-of-line static call implementation Peter Zijlstra
2020-07-10 22:13 ` Steven Rostedt
2020-07-11 10:11 ` Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 10/17] x86/static_call: Add inline static call implementation for x86-64 Peter Zijlstra
2020-07-10 22:31 ` Steven Rostedt
2020-07-11 9:56 ` Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 11/17] static_call: Simple self-test Peter Zijlstra
2020-07-10 22:42 ` Steven Rostedt
2020-07-11 10:27 ` Peter Zijlstra
2020-07-13 20:26 ` Steven Rostedt
2020-07-10 13:38 ` [PATCH v6 12/17] x86/alternatives: Teach text_poke_bp() to emulate RET Peter Zijlstra
2020-07-10 22:44 ` Steven Rostedt
2020-07-10 13:38 ` [PATCH v6 13/17] static_call: Add static_call_cond() Peter Zijlstra
2020-07-10 23:08 ` Steven Rostedt
2020-07-11 5:09 ` Peter Zijlstra
2020-07-11 10:49 ` Peter Zijlstra
2020-07-13 20:32 ` Steven Rostedt
2020-07-14 9:53 ` Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 14/17] static_call: Handle tail-calls Peter Zijlstra
2020-07-11 0:23 ` Steven Rostedt
2020-07-11 5:06 ` Peter Zijlstra
2020-07-11 5:08 ` Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 15/17] static_call: Allow early init Peter Zijlstra
2020-07-11 1:14 ` Steven Rostedt
2020-07-11 5:08 ` Peter Zijlstra
2020-07-13 20:24 ` Steven Rostedt
2020-07-14 9:51 ` Peter Zijlstra [this message]
2020-07-14 14:16 ` Steven Rostedt
2020-07-14 15:54 ` Peter Zijlstra
2020-07-14 16:07 ` Steven Rostedt
2020-07-14 18:31 ` Peter Zijlstra
2020-07-14 19:38 ` Steven Rostedt
2020-07-10 13:38 ` [PATCH v6 16/17] tracepoint: Optimize using static_call() Peter Zijlstra
2020-07-10 13:38 ` [PATCH v6 17/17] x86/perf, static_call: Optimize x86_pmu methods Peter Zijlstra
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=20200714095117.GS10769@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=ard.biesheuvel@linaro.org \
--cc=bristot@redhat.com \
--cc=hpa@zytor.com \
--cc=jbaron@akamai.com \
--cc=jpoimboe@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@rasmusvillemoes.dk \
--cc=luto@kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=mingo@kernel.org \
--cc=namit@vmware.com \
--cc=pbonzini@redhat.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=x86@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