From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: paulmck <paulmck@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Will Deacon <will@kernel.org>,
linux-kernel <linux-kernel@vger.kernel.org>,
lttng-dev <lttng-dev@lists.lttng.org>,
Carlos O'Donell <carlos@redhat.com>
Subject: Re: liburcu: LTO breaking rcu_dereference on arm64 and possibly other architectures ?
Date: Fri, 16 Apr 2021 15:30:53 -0400 (EDT) [thread overview]
Message-ID: <2056094038.84390.1618601453585.JavaMail.zimbra@efficios.com> (raw)
In-Reply-To: <20210416190244.GJ4212@paulmck-ThinkPad-P17-Gen-1>
----- On Apr 16, 2021, at 3:02 PM, paulmck paulmck@kernel.org wrote:
[...]
>
> If it can be done reasonably, I suggest also having some way for the
> person building userspace RCU to say "I know what I am doing, so do
> it with volatile rather than memory_order_consume."
Like so ?
#define CMM_ACCESS_ONCE(x) (*(__volatile__ __typeof__(x) *)&(x))
#define CMM_LOAD_SHARED(p) CMM_ACCESS_ONCE(p)
/*
* By defining URCU_DEREFERENCE_USE_VOLATILE, the user requires use of
* volatile access to implement rcu_dereference rather than
* memory_order_consume load from the C11/C++11 standards.
*
* This may improve performance on weakly-ordered architectures where
* the compiler implements memory_order_consume as a
* memory_order_acquire, which is stricter than required by the
* standard.
*
* Note that using volatile accesses for rcu_dereference may cause
* LTO to generate incorrectly ordered code starting from C11/C++11.
*/
#ifdef URCU_DEREFERENCE_USE_VOLATILE
# define rcu_dereference(x) CMM_LOAD_SHARED(x)
#else
# if defined (__cplusplus)
# if __cplusplus >= 201103L
# include <atomic>
# define rcu_dereference(x) ((std::atomic<__typeof__(x)>)(x)).load(std::memory_order_consume)
# else
# define rcu_dereference(x) CMM_LOAD_SHARED(x)
# endif
# else
# if (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L)
# include <stdatomic.h>
# define rcu_dereference(x) atomic_load_explicit(&(x), memory_order_consume)
# else
# define rcu_dereference(x) CMM_LOAD_SHARED(x)
# endif
# endif
#endif
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
WARNING: multiple messages have this Message-ID (diff)
From: Mathieu Desnoyers via lttng-dev <lttng-dev@lists.lttng.org>
To: paulmck <paulmck@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Will Deacon <will@kernel.org>,
linux-kernel <linux-kernel@vger.kernel.org>,
lttng-dev <lttng-dev@lists.lttng.org>,
Carlos O'Donell <carlos@redhat.com>
Subject: Re: [lttng-dev] liburcu: LTO breaking rcu_dereference on arm64 and possibly other architectures ?
Date: Fri, 16 Apr 2021 15:30:53 -0400 (EDT) [thread overview]
Message-ID: <2056094038.84390.1618601453585.JavaMail.zimbra@efficios.com> (raw)
In-Reply-To: <20210416190244.GJ4212@paulmck-ThinkPad-P17-Gen-1>
----- On Apr 16, 2021, at 3:02 PM, paulmck paulmck@kernel.org wrote:
[...]
>
> If it can be done reasonably, I suggest also having some way for the
> person building userspace RCU to say "I know what I am doing, so do
> it with volatile rather than memory_order_consume."
Like so ?
#define CMM_ACCESS_ONCE(x) (*(__volatile__ __typeof__(x) *)&(x))
#define CMM_LOAD_SHARED(p) CMM_ACCESS_ONCE(p)
/*
* By defining URCU_DEREFERENCE_USE_VOLATILE, the user requires use of
* volatile access to implement rcu_dereference rather than
* memory_order_consume load from the C11/C++11 standards.
*
* This may improve performance on weakly-ordered architectures where
* the compiler implements memory_order_consume as a
* memory_order_acquire, which is stricter than required by the
* standard.
*
* Note that using volatile accesses for rcu_dereference may cause
* LTO to generate incorrectly ordered code starting from C11/C++11.
*/
#ifdef URCU_DEREFERENCE_USE_VOLATILE
# define rcu_dereference(x) CMM_LOAD_SHARED(x)
#else
# if defined (__cplusplus)
# if __cplusplus >= 201103L
# include <atomic>
# define rcu_dereference(x) ((std::atomic<__typeof__(x)>)(x)).load(std::memory_order_consume)
# else
# define rcu_dereference(x) CMM_LOAD_SHARED(x)
# endif
# else
# if (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L)
# include <stdatomic.h>
# define rcu_dereference(x) atomic_load_explicit(&(x), memory_order_consume)
# else
# define rcu_dereference(x) CMM_LOAD_SHARED(x)
# endif
# endif
#endif
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
_______________________________________________
lttng-dev mailing list
lttng-dev@lists.lttng.org
https://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
next prev parent reply other threads:[~2021-04-16 19:30 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-16 14:52 liburcu: LTO breaking rcu_dereference on arm64 and possibly other architectures ? Mathieu Desnoyers
2021-04-16 14:52 ` [lttng-dev] " Mathieu Desnoyers via lttng-dev
2021-04-16 15:17 ` Peter Zijlstra
2021-04-16 15:17 ` [lttng-dev] " Peter Zijlstra via lttng-dev
2021-04-16 16:01 ` Paul E. McKenney
2021-04-16 16:01 ` [lttng-dev] " Paul E. McKenney via lttng-dev
2021-04-16 18:40 ` Mathieu Desnoyers
2021-04-16 18:40 ` [lttng-dev] " Mathieu Desnoyers via lttng-dev
2021-04-16 19:02 ` Paul E. McKenney
2021-04-16 19:02 ` [lttng-dev] " Paul E. McKenney via lttng-dev
2021-04-16 19:30 ` Mathieu Desnoyers [this message]
2021-04-16 19:30 ` Mathieu Desnoyers via lttng-dev
2021-04-16 20:01 ` Paul E. McKenney
2021-04-16 20:01 ` [lttng-dev] " Paul E. McKenney via lttng-dev
2021-04-16 15:22 ` Duncan Sands via lttng-dev
2021-04-16 20:39 ` Mathieu Desnoyers via lttng-dev
[not found] ` <7972b031-59b9-7fb5-6379-58bcec13a769@free.fr>
2021-04-19 15:31 ` Mathieu Desnoyers via lttng-dev
2021-04-19 15:41 ` Duncan Sands via lttng-dev
2021-04-19 15:54 ` Mathieu Desnoyers via lttng-dev
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=2056094038.84390.1618601453585.JavaMail.zimbra@efficios.com \
--to=mathieu.desnoyers@efficios.com \
--cc=carlos@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lttng-dev@lists.lttng.org \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=will@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.