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;
From:   "Ahmed S. Darwish" <a.darwish@linutronix.de>
To:     Thomas Gleixner <tglx@linutronix.de>,
        Peter Zijlstra <peterz@infradead.org>,
        Leo Yan <leo.yan@linaro.org>
Cc:     Will Deacon <will@kernel.org>, John Ogness <jogness@linutronix.de>,
        "Sebastian A. Siewior" <bigeasy@linutronix.de>,
        LKML <linux-kernel@vger.kernel.org>,
        "Ahmed S. Darwish" <a.darwish@linutronix.de>
Subject: [PATCH] time/sched_clock: Use raw_read_seqcount_latch()
Date:   Wed, 15 Jul 2020 13:59:01 +0200
Message-Id: <20200715115901.515956-1-a.darwish@linutronix.de>
In-Reply-To: <20200715095220.GH10769@hirez.programming.kicks-ass.net>
References: <20200715095220.GH10769@hirez.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

sched_clock uses seqcount_t latching to switch between two storage
places protected by the sequence counter. This allows it to have
interruptible, NMI-safe, seqcount_t write side critical sections.

Since 7fc26327b756 ("seqlock: Introduce raw_read_seqcount_latch()"),
raw_read_seqcount_latch() became the standardized way for seqcount_t
latch read paths. Due to the dependent load, it also has one read
memory barrier less than the currently used raw_read_seqcount() API.

Use raw_read_seqcount_latch() for the seqcount_t latch read path.

Link: https://lkml.kernel.org/r/20200625085745.GD117543@hirez.programming.kicks-ass.net
Link: https://lkml.kernel.org/r/20200715092345.GA231464@debian-buster-darwi.lab.linutronix.de
References: 1809bfa44e10 ("timers, sched/clock: Avoid deadlock during read from NMI")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
---
 kernel/time/sched_clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index fa3f800d7d76..ea007928d681 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -100,7 +100,7 @@ unsigned long long notrace sched_clock(void)
 	struct clock_read_data *rd;

 	do {
-		seq = raw_read_seqcount(&cd.seq);
+		seq = raw_read_seqcount_latch(&cd.seq);
 		rd = cd.read_data + (seq & 1);

 		cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
--
2.20.1