[PATCH v7] sched/clock: Avoid false sharing for sched_clock_irqtime

[Wangyang Guo <wangyang.guo@intel.com>]

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.

The only user of disable_sched_clock_irqtime()
is tsc_.*mark_unstable() which may be invoked under atomic context
and require a workqueue to disable static_key. But both of them
calls clear_sched_clock_stable() just before doing
disable_sched_clock_irqtime(). We can reuse
"sched_clock_work" to also disable sched_clock_irqtime().

One additional case need to handle is if the tsc is marked unstable
before late_initcall() phase, sched_clock_work will not be invoked
and sched_clock_irqtime will stay enabled although clock is unstable:
  tsc_init()
    enable_sched_clock_irqtime() # irqtime accounting is enabled here
    ...
    if (unsynchronized_tsc()) # true
      mark_tsc_unstable()
        clear_sched_clock_stable()
          __sched_clock_stable_early = 0;
          ...
          if (static_key_count(&sched_clock_running.key) == 2)
            # Only happens at sched_clock_init_late()
            __clear_sched_clock_stable(); # Never executed
  ...

  # late_initcall() phase
  sched_clock_init_late()
    if (__sched_clock_stable_early) # Already false
      __set_sched_clock_stable(); # sched_clock is never marked stable
  # TSC unstable, but sched_clock_work won't run to disable irqtime

So we need to disable_sched_clock_irqtime() in sched_clock_init_late()
if clock is unstable.

Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Suggested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Reported-by: Benjamin Lei <benjamin.lei@intel.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Signed-off-by: Wangyang Guo <wangyang.guo@intel.com>
---
v7 -> v6:
- move irqtime_enabled() check to disable_sched_clock_irqtime()

v6 -> v5:
- Only disable_sched_clock_irqtime() if irqtime_enabled() in
  sched_lock_init_late() to avoid unnessary overhead.

V5 -> v4:
- Changelog update to reflect static_key changes

V4 -> V3:
- Avoid creating a new workqueue to disable static_key
- Specify kernel version for c2c result in changelog

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:
  v6: https://lore.kernel.org/all/20260127044159.2254247-1-wangyang.guo@intel.com/
  v5: https://lore.kernel.org/all/20260127031602.1907377-1-wangyang.guo@intel.com/
  v4: https://lore.kernel.org/all/20260126021401.1490163-1-wangyang.guo@intel.com/
  v3: https://lore.kernel.org/all/20260116023945.1849329-1-wangyang.guo@intel.com/
  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
---
 arch/x86/kernel/tsc.c  | 2 --
 kernel/sched/clock.c   | 3 +++
 kernel/sched/cputime.c | 9 +++++----
 kernel/sched/sched.h   | 4 ++--
 4 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 87e749106dda..9a62e18d1bff 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1142,7 +1142,6 @@ static void tsc_cs_mark_unstable(struct clocksource *cs)
 	tsc_unstable = 1;
 	if (using_native_sched_clock())
 		clear_sched_clock_stable();
-	disable_sched_clock_irqtime();
 	pr_info("Marking TSC unstable due to clocksource watchdog\n");
 }
 
@@ -1212,7 +1211,6 @@ void mark_tsc_unstable(char *reason)
 	tsc_unstable = 1;
 	if (using_native_sched_clock())
 		clear_sched_clock_stable();
-	disable_sched_clock_irqtime();
 	pr_info("Marking TSC unstable due to %s\n", reason);
 
 	clocksource_mark_unstable(&clocksource_tsc_early);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index f5e6dd6a6b3a..2ae4fbf13431 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -173,6 +173,7 @@ notrace static void __sched_clock_work(struct work_struct *work)
 			scd->tick_gtod, __gtod_offset,
 			scd->tick_raw,  __sched_clock_offset);
 
+	disable_sched_clock_irqtime();
 	static_branch_disable(&__sched_clock_stable);
 }
 
@@ -238,6 +239,8 @@ static int __init sched_clock_init_late(void)
 
 	if (__sched_clock_stable_early)
 		__set_sched_clock_stable();
+	else
+		disable_sched_clock_irqtime();  /* disable if clock unstable. */
 
 	return 0;
 }
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 7097de2c8cda..556a70f344d0 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 +27,15 @@
  */
 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);
 }
 
 void disable_sched_clock_irqtime(void)
 {
-	sched_clock_irqtime = 0;
+	if (irqtime_enabled())
+		static_branch_disable(&sched_clock_irqtime);
 }
 
 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