linux-kernel - [for-next][PATCH 5/8] tracing: Remove pointless memory barriers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250723144928.172299624@kernel.org>
Date: Wed, 23 Jul 2025 10:49:12 -0400
From: Steven Rostedt <rostedt@...nel.org>
To: linux-kernel@...r.kernel.org
Cc: Masami Hiramatsu <mhiramat@...nel.org>,
 Mark Rutland <mark.rutland@....com>,
 Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
 Andrew Morton <akpm@...ux-foundation.org>,
 Gabriele Monaco <gmonaco@...hat.com>,
 Nam Cao <namcao@...utronix.de>
Subject: [for-next][PATCH 5/8] tracing: Remove pointless memory barriers

From: Nam Cao <namcao@...utronix.de>

Memory barriers are useful to ensure memory accesses from one CPU appear in
the original order as seen by other CPUs.

Some smp_rmb() and smp_wmb() are used, but they are not ordering multiple
memory accesses.

Remove them.

Cc: Masami Hiramatsu <mhiramat@...nel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Cc: Gabriele Monaco <gmonaco@...hat.com>
Link: https://lore.kernel.org/20250626151940.1756398-1-namcao@linutronix.de
Signed-off-by: Nam Cao <namcao@...utronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@...dmis.org>
---
 kernel/trace/rv/rv.c | 6 ------
 kernel/trace/trace.c | 7 -------
 2 files changed, 13 deletions(-)

diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index e4077500a91d..c04a49da4328 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -675,8 +675,6 @@ static bool __read_mostly monitoring_on;
  */
 bool rv_monitoring_on(void)
 {
-	/* Ensures that concurrent monitors read consistent monitoring_on */
-	smp_rmb();
 	return READ_ONCE(monitoring_on);
 }
 
@@ -696,8 +694,6 @@ static ssize_t monitoring_on_read_data(struct file *filp, char __user *user_buf,
 static void turn_monitoring_off(void)
 {
 	WRITE_ONCE(monitoring_on, false);
-	/* Ensures that concurrent monitors read consistent monitoring_on */
-	smp_wmb();
 }
 
 static void reset_all_monitors(void)
@@ -713,8 +709,6 @@ static void reset_all_monitors(void)
 static void turn_monitoring_on(void)
 {
 	WRITE_ONCE(monitoring_on, true);
-	/* Ensures that concurrent monitors read consistent monitoring_on */
-	smp_wmb();
 }
 
 static void turn_monitoring_on_with_reset(void)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 95ae7c4e5835..0dff4298fc0e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -936,7 +936,6 @@ int tracing_is_enabled(void)
 	 * return the mirror variable of the state of the ring buffer.
 	 * It's a little racy, but we don't really care.
 	 */
-	smp_rmb();
 	return !global_trace.buffer_disabled;
 }
 
@@ -1107,8 +1106,6 @@ void tracer_tracing_on(struct trace_array *tr)
 	 * important to be fast than accurate.
 	 */
 	tr->buffer_disabled = 0;
-	/* Make the flag seen by readers */
-	smp_wmb();
 }
 
 /**
@@ -1640,8 +1637,6 @@ void tracer_tracing_off(struct trace_array *tr)
 	 * important to be fast than accurate.
 	 */
 	tr->buffer_disabled = 1;
-	/* Make the flag seen by readers */
-	smp_wmb();
 }
 
 /**
@@ -2710,8 +2705,6 @@ void trace_buffered_event_enable(void)
 
 static void enable_trace_buffered_event(void *data)
 {
-	/* Probably not needed, but do it anyway */
-	smp_rmb();
 	this_cpu_dec(trace_buffered_event_cnt);
 }
 
-- 
2.47.2