[PATCH] sched: generalize CONFIG_IRQ_TIME_ACCOUNTING for X86 and ARM

[Venki Pallipadi]

On Wed, Feb 8, 2012 at 8:08 AM, Dmitry Antipov
<dmitry.antipov at linaro.org> wrote:
> Generalize CONFIG_IRQ_TIME_ACCOUNTING  between X86 and
> ARM, move "noirqtime=" option to common debugging code.
> For a bit of backward compatibility, X86-specific option
> "tsc=noirqtime" is preserved, but issues a warning.
>
> Suggested-by: Russell King <rmk+kernel at arm.linux.org.uk>
> Suggested-by: Venki Pallipadi <venki at google.com>
> Signed-off-by: Dmitry Antipov <dmitry.antipov at linaro.org>
> ---
>  arch/arm/kernel/sched_clock.c |    3 +++
>  arch/x86/Kconfig              |   11 -----------
>  arch/x86/kernel/tsc.c         |    7 ++++---
>  include/linux/sched.h         |    2 ++
>  lib/Kconfig.debug             |   12 ++++++++++++
>  lib/Makefile                  |    2 ++
>  lib/irqtime.c                 |   12 ++++++++++++
>  7 files changed, 35 insertions(+), 14 deletions(-)
>  create mode 100644 lib/irqtime.c
>
> diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
> index 5416c7c..961bd2d 100644
> --- a/arch/arm/kernel/sched_clock.c
> +++ b/arch/arm/kernel/sched_clock.c
> @@ -144,6 +144,9 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
>         */
>        cd.epoch_ns = 0;
>
> +       if (!no_sched_irq_time)
> +               enable_sched_clock_irqtime();
> +
>        pr_debug("Registered %pF as sched_clock source\n", read);
>  }
>
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index 5bed94e..4759676 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -805,17 +805,6 @@ config SCHED_MC
>          making when dealing with multi-core CPU chips at a cost of slightly
>          increased overhead in some places. If unsure say N here.
>
> -config IRQ_TIME_ACCOUNTING
> -       bool "Fine granularity task level IRQ time accounting"
> -       default n
> -       ---help---
> -         Select this option to enable fine granularity task irq time
> -         accounting. This is done by reading a timestamp on each
> -         transitions between softirq and hardirq state, so there can be a
> -         small performance impact.
> -
> -         If in doubt, say N here.
> -
>  source "kernel/Kconfig.preempt"
>
>  config X86_UP_APIC
> diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
> index a62c201..70510a3 100644
> --- a/arch/x86/kernel/tsc.c
> +++ b/arch/x86/kernel/tsc.c
> @@ -103,14 +103,15 @@ int __init notsc_setup(char *str)
>
>  __setup("notsc", notsc_setup);
>
> -static int no_sched_irq_time;
> -
>  static int __init tsc_setup(char *str)
>  {
>        if (!strcmp(str, "reliable"))
>                tsc_clocksource_reliable = 1;
> -       if (!strncmp(str, "noirqtime", 9))
> +       if (!strncmp(str, "noirqtime", 9)) {
> +               printk(KERN_WARNING "tsc: tsc=noirqtime is "
> +                      "obsolete, use noirqtime instead\n");
>                no_sched_irq_time = 1;
> +       }
>        return 1;
>  }
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 7d379a6..b3575b5 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1966,9 +1966,11 @@ extern void sched_clock_idle_wakeup_event(u64 delta_ns);
>  * The reason for this explicit opt-in is not to have perf penalty with
>  * slow sched_clocks.
>  */
> +extern int no_sched_irq_time;
>  extern void enable_sched_clock_irqtime(void);
>  extern void disable_sched_clock_irqtime(void);
>  #else
> +#define no_sched_irq_time 1
>  static inline void enable_sched_clock_irqtime(void) {}
>  static inline void disable_sched_clock_irqtime(void) {}
>  #endif
> diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
> index 8745ac7..236e814 100644
> --- a/lib/Kconfig.debug
> +++ b/lib/Kconfig.debug
> @@ -299,6 +299,18 @@ config SCHEDSTATS
>          application, you can say N to avoid the very slight overhead
>          this adds.
>
> +config IRQ_TIME_ACCOUNTING
> +       bool "Fine granularity task level IRQ time accounting"
> +       depends on X86 || ARM
> +       default n
> +       ---help---
> +         Select this option to enable fine granularity task irq time
> +         accounting. This is done by reading a timestamp on each
> +         transitions between softirq and hardirq state, so there can be a
> +         small performance impact.
> +
> +         If in doubt, say N here.
> +
>  config TIMER_STATS
>        bool "Collect kernel timers statistics"
>        depends on DEBUG_KERNEL && PROC_FS
> diff --git a/lib/Makefile b/lib/Makefile
> index 18515f0..44d67d4 100644
> --- a/lib/Makefile
> +++ b/lib/Makefile
> @@ -49,6 +49,8 @@ obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
>  obj-$(CONFIG_DEBUG_LIST) += list_debug.o
>  obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
>
> +obj-$(CONFIG_IRQ_TIME_ACCOUNTING) += irqtime.o
> +
>  ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
>   lib-y += dec_and_lock.o
>  endif
> diff --git a/lib/irqtime.c b/lib/irqtime.c
> new file mode 100644
> index 0000000..10d440d
> --- /dev/null
> +++ b/lib/irqtime.c
> @@ -0,0 +1,12 @@
> +#include <linux/kernel.h>
> +#include <linux/sched.h>
> +
> +int no_sched_irq_time;
> +
> +static int __init irqtime_setup(char *str)
> +{
> +       no_sched_irq_time = 1;
> +       return 1;
> +}
> +
> +__setup("noirqtime", irqtime_setup);
> --

One more nit-pick. We need corresponding change in
Documentation/kernel-parameters.txt to  deprecate tsc=irqtime and add
this new param.

> 1.7.7.6
>