arch/x86/kernel/tsc.c | 2 -- kernel/sched/clock.c | 3 +++ kernel/sched/cputime.c | 8 ++++---- kernel/sched/sched.h | 4 ++-- 4 files changed, 9 insertions(+), 8 deletions(-)
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:
In kernel 6.14, 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.
---
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:
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
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>
---
arch/x86/kernel/tsc.c | 2 --
kernel/sched/clock.c | 3 +++
kernel/sched/cputime.c | 8 ++++----
kernel/sched/sched.h | 4 ++--
4 files changed, 9 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..959a86206c64 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 +27,14 @@
*/
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;
+ 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);
}
/*
--
2.47.3Hi Wangyang.
On 1/26/26 7:44 AM, Wangyang Guo wrote:
> 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:
> In kernel 6.14, 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.
>
IMHO, this changelog is meant for latest sched/core. having 6.14 data won't be
that relevant.
Also, changelog should be mentioning essence of calling disable in
sched_clock_init_late which was in v3 discussions.
> 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.
>
> ---
Please dont put a --- here.
git am will strip everything after this and actual diff. So the your
signed-off-by and other details won't be captured.
If the intention was keep version history, put it after the signed-off-by
for example:
https://lore.kernel.org/lkml/20260120113246.27987-2-kprateek.nayak@amd.com/
> 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:
> 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
>
> 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>
> ---
> arch/x86/kernel/tsc.c | 2 --
> kernel/sched/clock.c | 3 +++
> kernel/sched/cputime.c | 8 ++++----
> kernel/sched/sched.h | 4 ++--
> 4 files changed, 9 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..959a86206c64 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 +27,14 @@
> */
> 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;
> + 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);
> }
>
> /*
On 1/27/2026 2:45 AM, Shrikanth Hegde wrote: > Hi Wangyang. > > On 1/26/26 7:44 AM, Wangyang Guo wrote: >> 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: >> In kernel 6.14, 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. >> > > IMHO, this changelog is meant for latest sched/core. having 6.14 data > won't be > that relevant. > > Also, changelog should be mentioning essence of calling disable in > sched_clock_init_late which was in v3 discussions. > >> 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. >> >> --- > > Please dont put a --- here. > > git am will strip everything after this and actual diff. So the your > signed-off-by and other details won't be captured. > > If the intention was keep version history, put it after the signed-off-by > for example: > https://lore.kernel.org/lkml/20260120113246.27987-2-kprateek.nayak@amd.com/ Changelog updated in v5: https://lore.kernel.org/all/20260127031602.1907377-1-wangyang.guo@intel.com/ BR Wangyang
© 2016 - 2026 Red Hat, Inc.