Re: [PATCH V2 7/7] x86,rcu: use percpu rcu_preempt_depth

From: Borislav Petkov <bp@alien8.de>
To: Lai Jiangshan <laijs@linux.alibaba.com>
Cc: linux-kernel@vger.kernel.org,
	Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
	x86@kernel.org, "Paul E. McKenney" <paulmck@kernel.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Lai Jiangshan <jiangshanlai@gmail.com>,
	Joel Fernandes <joel@joelfernandes.org>,
	Andi Kleen <ak@linux.intel.com>,
	Andy Lutomirski <luto@kernel.org>,
	Fenghua Yu <fenghua.yu@intel.com>,
	Kees Cook <keescook@chromium.org>,
	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Dave Hansen <dave.hansen@intel.com>,
	Babu Moger <Babu.Moger@amd.com>, Rik van Riel <riel@surriel.com>,
	"Chang S. Bae" <chang.seok.bae@intel.com>,
	Jann Horn <jannh@google.com>, David Windsor <dwindsor@gmail.com>,
	Elena Reshetova <elena.reshetova@intel.com>,
	Yuyang Du <duyuyang@gmail.com>,
	Anshuman Khandual <anshuman.khandual@arm.com>,
	Richard Guy Briggs <rgb@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Christian Brauner <christian.brauner@ubuntu.com>,
	Michal Hocko <mhocko@suse.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Al Viro <viro@zeniv.linux.org.uk>,
	"Dmitry V. Levin" <ldv@altlinux.org>,
	rcu@vger.kernel.org
Subject: Re: [PATCH V2 7/7] x86,rcu: use percpu rcu_preempt_depth
Date: Sat, 2 Nov 2019 17:30:05 +0100	[thread overview]
Message-ID: <20191102163005.GA11705@nazgul.tnic> (raw)
In-Reply-To: <20191102124559.1135-8-laijs@linux.alibaba.com>

Resending again because your mail has the craziest header:

Reply-To: 20191101162109.GN20975@paulmck-ThinkPad-P72

and hitting Reply-to-all creates only confusion. WTF?

On Sat, Nov 02, 2019 at 12:45:59PM +0000, Lai Jiangshan wrote:
> Convert x86 to use a per-cpu rcu_preempt_depth. The reason for doing so
> is that accessing per-cpu variables is a lot cheaper than accessing
> task_struct or thread_info variables.
> 
> We need to save/restore the actual rcu_preempt_depth when switch.
> We also place the per-cpu rcu_preempt_depth close to __preempt_count
> and current_task variable.
> 
> Using the idea of per-cpu __preempt_count.
> 
> No function call when using rcu_read_[un]lock().
> Single instruction for rcu_read_lock().
> 2 instructions for fast path of rcu_read_unlock().
> 
> CC: Peter Zijlstra <peterz@infradead.org>
> Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
> ---
>  arch/x86/Kconfig                         |  2 +
>  arch/x86/include/asm/rcu_preempt_depth.h | 87 ++++++++++++++++++++++++
>  arch/x86/kernel/cpu/common.c             |  7 ++
>  arch/x86/kernel/process_32.c             |  2 +
>  arch/x86/kernel/process_64.c             |  2 +
>  include/linux/rcupdate.h                 | 24 +++++++
>  init/init_task.c                         |  2 +-
>  kernel/fork.c                            |  2 +-
>  kernel/rcu/Kconfig                       |  3 +
>  kernel/rcu/tree_exp.h                    |  2 +
>  kernel/rcu/tree_plugin.h                 | 37 +++++++---
>  11 files changed, 158 insertions(+), 12 deletions(-)
>  create mode 100644 arch/x86/include/asm/rcu_preempt_depth.h
> 
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index d6e1faa28c58..af9fedc0fdc4 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -18,6 +18,7 @@ config X86_32
>  	select MODULES_USE_ELF_REL
>  	select OLD_SIGACTION
>  	select GENERIC_VDSO_32
> +	select ARCH_HAVE_RCU_PREEMPT_DEEPTH

WTF is a "DEEPTH"?

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.
--