linux-kernel - [tip: sched/urgent] sched/fair: Fix frequency selection for non-invariant case

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]

Date: Tue, 16 Jan 2024 10:08:20 -0000
From: "tip-bot2 for Vincent Guittot" <tip-bot2@...utronix.de>
To: linux-tip-commits@...r.kernel.org
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
 Wyes Karny <wkarny@...il.com>, Vincent Guittot <vincent.guittot@...aro.org>,
 Ingo Molnar <mingo@...nel.org>, x86@...nel.org, linux-kernel@...r.kernel.org
Subject: [tip: sched/urgent] sched/fair: Fix frequency selection for
 non-invariant case

The following commit has been merged into the sched/urgent branch of tip:

Commit-ID:     e37617c8e53a1f7fcba6d5e1041f4fd8a2425c27
Gitweb:        https://git.kernel.org/tip/e37617c8e53a1f7fcba6d5e1041f4fd8a2425c27
Author:        Vincent Guittot <vincent.guittot@...aro.org>
AuthorDate:    Sun, 14 Jan 2024 19:36:00 +01:00
Committer:     Ingo Molnar <mingo@...nel.org>
CommitterDate: Tue, 16 Jan 2024 10:41:25 +01:00

sched/fair: Fix frequency selection for non-invariant case

Linus reported a ~50% performance regression on single-threaded
workloads on his AMD Ryzen system, and bisected it to:

  9c0b4bb7f630 ("sched/cpufreq: Rework schedutil governor performance estimation")

When frequency invariance is not enabled, get_capacity_ref_freq(policy)
is supposed to return the current frequency and the performance margin
applied by map_util_perf(), enabling the utilization to go above the
maximum compute capacity and to select a higher frequency than the current one.

After the changes in 9c0b4bb7f630, the performance margin was applied
earlier in the path to take into account utilization clampings and
we couldn't get a utilization higher than the maximum compute capacity,
and the CPU remained 'stuck' at lower frequencies.

To fix this, we must use a frequency above the current frequency to
get a chance to select a higher OPP when the current one becomes fully used.
Apply the same margin and return a frequency 25% higher than the current
one in order to switch to the next OPP before we fully use the CPU
at the current one.

[ mingo: Clarified the changelog. ]

Fixes: 9c0b4bb7f630 ("sched/cpufreq: Rework schedutil governor performance estimation")
Reported-by: Linus Torvalds <torvalds@...ux-foundation.org>
Bisected-by: Linus Torvalds <torvalds@...ux-foundation.org>
Reported-by: Wyes Karny <wkarny@...il.com>
Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
Signed-off-by: Ingo Molnar <mingo@...nel.org>
Tested-by: Wyes Karny <wkarny@...il.com>
Link: https://lore.kernel.org/r/20240114183600.135316-1-vincent.guittot@linaro.org
---
 kernel/sched/cpufreq_schedutil.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 95c3c09..eece624 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -133,7 +133,11 @@ unsigned long get_capacity_ref_freq(struct cpufreq_policy *policy)
 	if (arch_scale_freq_invariant())
 		return policy->cpuinfo.max_freq;

-	return policy->cur;
+	/*
+	 * Apply a 25% margin so that we select a higher frequency than
+	 * the current one before the CPU is fully busy:
+	 */
+	return policy->cur + (policy->cur >> 2);
 }

 /**