linux-kernel - [PATCH v3] sched/clock: Avoid false sharing for sched_clock

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-next>] [day] [month] [year] [list]

Message-ID: <20260116023945.1849329-1-wangyang.guo@intel.com>
Date: Fri, 16 Jan 2026 10:39:45 +0800
From: Wangyang Guo <wangyang.guo@...el.com>
To: K Prateek Nayak <kprateek.nayak@....com>,
	Ingo Molnar <mingo@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Juri Lelli <juri.lelli@...hat.com>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Dietmar Eggemann <dietmar.eggemann@....com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>,
	Mel Gorman <mgorman@...e.de>,
	Valentin Schneider <vschneid@...hat.com>
Cc: linux-kernel@...r.kernel.org,
	Wangyang Guo <wangyang.guo@...el.com>,
	Shrikanth Hegde <sshegde@...ux.ibm.com>,
	Benjamin Lei <benjamin.lei@...el.com>,
	Tim Chen <tim.c.chen@...ux.intel.com>,
	Tianyou Li <tianyou.li@...el.com>
Subject: [PATCH v3] sched/clock: Avoid false sharing for sched_clock_irqtime

Read-mostly sched_clock_irqtime may share the same cacheline with
frequently updated nohz struct. Make it as static_key to avoid
false sharing issue.

Details:
We observed ~3% cycles hotspots in irqtime_account_irq when running
SPECjbb2015 in a 2-sockets system. Most of cycles spent in reading
sched_clock_irqtime, which is a read-mostly var.

perf c2c (cachelien view) shows it has false sharing with nohz struct:
     Num RmtHitm LclHitm  Offset records             Symbol
   6.25%   0.00%   0.00%   0x0       4   [k] _nohz_idle_balance.isra.0
  18.75% 100.00%   0.00%   0x8      14   [k] nohz_balance_exit_idle
   6.25%   0.00%   0.00%   0x8       8   [k] nohz_balance_enter_idle
   6.25%   0.00%   0.00%   0xc       8   [k] sched_balance_newidle
   6.25%   0.00%   0.00%  0x10      31   [k] nohz_balancer_kick
   6.25%   0.00%   0.00%  0x20      16   [k] sched_balance_newidle
  37.50%   0.00%   0.00%  0x38      50   [k] irqtime_account_irq
   6.25%   0.00%   0.00%  0x38      47   [k] account_process_tick
   6.25%   0.00%   0.00%  0x38      12   [k] account_idle_ticks

Offsets:
*  0x0 -- nohz.idle_cpu_mask (r)
*  0x8 -- nohz.nr_cpus (w)
* 0x38 -- sched_clock_irqtime (r), not in nohz, but share cacheline

The layout in /proc/kallsyms can also confirm that:
ffffffff88600d40 b nohz
ffffffff88600d68 B arch_needs_tick_broadcast
ffffffff88600d6c b __key.264
ffffffff88600d6c b __key.265
ffffffff88600d70 b dl_generation
ffffffff88600d78 b sched_clock_irqtime

With the patch applied, irqtime_account_irq hotspot disappear.

---
V2 -> V3:
- Use static_key instead of a __read_mostly var.

V1 -> V2:
- Use __read_mostly instead of __cacheline_aligned to avoid wasting
  spaces.

History:
  v2: https://lore.kernel.org/all/20260113074807.3404180-1-wangyang.guo@intel.com/
  v1: https://lore.kernel.org/all/20260113022958.3379650-1-wangyang.guo@intel.com/
  prev discussions: https://lore.kernel.org/all/20251211055612.4071266-1-wangyang.guo@intel.com/T/#u

Suggested-by: Peter Zijlstra <peterz@...radead.org>
Suggested-by: Shrikanth Hegde <sshegde@...ux.ibm.com>
Reported-by: Benjamin Lei <benjamin.lei@...el.com>
Reviewed-by: Tim Chen <tim.c.chen@...ux.intel.com>
Reviewed-by: Tianyou Li <tianyou.li@...el.com>
Signed-off-by: Wangyang Guo <wangyang.guo@...el.com>
---
 kernel/sched/cputime.c | 20 ++++++++++++++++----
 kernel/sched/sched.h   |  4 ++--
 2 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 7097de2c8cda..f37a27ed51d7 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -12,6 +12,8 @@
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
+DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
+
 /*
  * There are no locks covering percpu hardirq/softirq time.
  * They are only modified in vtime_account, on corresponding CPU
@@ -25,16 +27,26 @@
  */
 DEFINE_PER_CPU(struct irqtime, cpu_irqtime);
 
-int sched_clock_irqtime;
-
 void enable_sched_clock_irqtime(void)
 {
-	sched_clock_irqtime = 1;
+	static_branch_enable(&sched_clock_irqtime);
 }
 
+static void __disable_sched_clock_irqtime(struct work_struct *work)
+{
+	static_branch_disable(&sched_clock_irqtime);
+}
+
+static DECLARE_WORK(sched_clock_irqtime_work, __disable_sched_clock_irqtime);
+
 void disable_sched_clock_irqtime(void)
 {
-	sched_clock_irqtime = 0;
+	/* disable_sched_clock_irqtime can be called in atomic
+	 * context with mark_tsc_unstable(), use wq to avoid
+	 * "sleeping in atomic context" warning.
+	 */
+	if (irqtime_enabled())
+		schedule_work(&sched_clock_irqtime_work);
 }
 
 static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index adfb6e3409d7..ec963314287a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3172,11 +3172,11 @@ struct irqtime {
 };
 
 DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
-extern int sched_clock_irqtime;
+DECLARE_STATIC_KEY_FALSE(sched_clock_irqtime);
 
 static inline int irqtime_enabled(void)
 {
-	return sched_clock_irqtime;
+	return static_branch_likely(&sched_clock_irqtime);
 }
 
 /*
-- 
2.47.3