[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <d3f76f84-9d4c-4fdb-9642-6eed9c62f8c7@paulmck-laptop>
Date: Sun, 17 Nov 2024 10:37:34 -0800
From: "Paul E. McKenney" <paulmck@...nel.org>
To: torvalds@...ux-foundation.org
Cc: linux-kernel@...r.kernel.org, kernel-team@...a.com, riel@...riel.com,
neeraj.upadhyay@...nel.org, leobras@...hat.com, tglx@...utronix.de,
peterz@...radead.org
Subject: [GIT PULL] CSD-lock changes for v6.13
Hello, Linus,
When the v6.13 merge window opens, please pull this CSD-lock update from:
git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git tags/csd-lock.2024.11.16a
# HEAD: 9861f7f66f98a6358c944c17a5d4acd07abcb1a7: locking/csd-lock: Switch from sched_clock() to ktime_get_mono_fast_ns() (2024-10-11 09:31:21 -0700)
----------------------------------------------------------------
CSD-lock diagnostic updates for v6.13
This commit switches from sched_clock() to ktime_get_mono_fast_ns(), which
on x86 switches from the rdtsc instruction to the rdtscp instruction,
thus avoiding instruction reorderings that cause false-positive reports
of CSD-lock stalls of almost 2^46 nanoseconds. These false positives
are rare, but really are seen in the wild.
----------------------------------------------------------------
Paul E. McKenney (1):
locking/csd-lock: Switch from sched_clock() to ktime_get_mono_fast_ns()
kernel/smp.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
Powered by blists - more mailing lists