Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Wed, 13 May 2020 13:14:47 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Marco Elver <elver@google.com>
Cc:     Will Deacon <will@kernel.org>, LKML <linux-kernel@vger.kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        "Paul E. McKenney" <paulmck@kernel.org>,
        Ingo Molnar <mingo@kernel.org>, dvyukov@google.com
Subject: Re: [PATCH v5 00/18] Rework READ_ONCE() to improve codegen
Message-ID: <20200513111447.GE3001@hirez.programming.kicks-ass.net>
References: <20200511204150.27858-1-will@kernel.org>
 <20200512081826.GE2978@hirez.programming.kicks-ass.net>
 <CANpmjNNo3rhwqG=xEbpP9JiSd8-Faw8fkoUhYJjesHK5S5_KQQ@mail.gmail.com>
 <20200512190755.GL2957@hirez.programming.kicks-ass.net>
 <CANpmjNNeSnrAgfkskE5Y0NNu3-DS6hk+SwjkBunrr8FRxwwT-Q@mail.gmail.com>
 <20200513111057.GN2957@hirez.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200513111057.GN2957@hirez.programming.kicks-ass.net>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, May 13, 2020 at 01:10:57PM +0200, Peter Zijlstra wrote:

> So then I end up with something like the below, and I've validated that
> does not generate instrumentation... HOWEVER, I now need ~10g of memory
> and many seconds to compile each file in arch/x86/kernel/.

> diff --git a/include/linux/compiler.h b/include/linux/compiler.h
> index 3bb962959d8b..48f85d1d2db6 100644
> --- a/include/linux/compiler.h
> +++ b/include/linux/compiler.h
> @@ -241,7 +241,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
>   * atomicity or dependency ordering guarantees. Note that this may result
>   * in tears!
>   */
> -#define __READ_ONCE(x)	(*(const volatile __unqual_scalar_typeof(x) *)&(x))
> +#define __READ_ONCE(x)	data_race((*(const volatile __unqual_scalar_typeof(x) *)&(x)))
>  
>  #define __READ_ONCE_SCALAR(x)						\
>  ({									\
> @@ -260,7 +260,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
>  
>  #define __WRITE_ONCE(x, val)						\
>  do {									\
> -	*(volatile typeof(x) *)&(x) = (val);				\
> +	data_race(*(volatile typeof(x) *)&(x) = (val));			\
>  } while (0)
>  
>  #define __WRITE_ONCE_SCALAR(x, val)					\

The above is responsible for that, the below variant is _MUCH_ better
again. It really doesn't like nested data_race(), as in _REALLY_ doesn't
like.

---

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 3bb962959d8b..2ea532b19e75 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -241,12 +241,12 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  * atomicity or dependency ordering guarantees. Note that this may result
  * in tears!
  */
-#define __READ_ONCE(x)	(*(const volatile __unqual_scalar_typeof(x) *)&(x))
+#define __READ_ONCE(x)	data_race((*(const volatile __unqual_scalar_typeof(x) *)&(x)))
 
 #define __READ_ONCE_SCALAR(x)						\
 ({									\
 	typeof(x) *__xp = &(x);						\
-	__unqual_scalar_typeof(x) __x = data_race(__READ_ONCE(*__xp));	\
+	__unqual_scalar_typeof(x) __x = __READ_ONCE(*__xp);		\
 	kcsan_check_atomic_read(__xp, sizeof(*__xp));			\
 	smp_read_barrier_depends();					\
 	(typeof(x))__x;							\
@@ -260,14 +260,14 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 #define __WRITE_ONCE(x, val)						\
 do {									\
-	*(volatile typeof(x) *)&(x) = (val);				\
+	data_race(*(volatile typeof(x) *)&(x) = (val));			\
 } while (0)
 
 #define __WRITE_ONCE_SCALAR(x, val)					\
 do {									\
 	typeof(x) *__xp = &(x);						\
 	kcsan_check_atomic_write(__xp, sizeof(*__xp));			\
-	data_race(({ __WRITE_ONCE(*__xp, val); 0; }));			\
+	__WRITE_ONCE(*__xp, val);					\
 } while (0)
 
 #define WRITE_ONCE(x, val)						\