Re: [PATCH v3 1/3] perf core: Factor out __perf_sw_event_sched

From: Stephane Eranian
Date: Thu Feb 25 2021 - 04:01:06 EST


Hi Peter,

Any comments on this patch series?

It is quite useful to be able to count the number of cgroup switches
simply using perf stat/record.
Not all context switches (cs) are necessarily cgroup switches.
Thanks.

On Wed, Feb 10, 2021 at 12:33 AM Namhyung Kim <namhyung@xxxxxxxxxx> wrote:
>
> In some cases, we need to check more than whether the software event
> is enabled. So split the condition check and the actual event
> handling. This is a preparation for the next change.
>
> Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
> ---
> include/linux/perf_event.h | 33 ++++++++++++---------------------
> 1 file changed, 12 insertions(+), 21 deletions(-)
>
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index fab42cfbd350..2a1be6026a2f 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -1174,30 +1174,24 @@ DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
> * which is guaranteed by us not actually scheduling inside other swevents
> * because those disable preemption.
> */
> -static __always_inline void
> -perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
> +static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
> {
> - if (static_key_false(&perf_swevent_enabled[event_id])) {
> - struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
> + struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
>
> - perf_fetch_caller_regs(regs);
> - ___perf_sw_event(event_id, nr, regs, addr);
> - }
> + perf_fetch_caller_regs(regs);
> + ___perf_sw_event(event_id, nr, regs, addr);
> }
>
> extern struct static_key_false perf_sched_events;
>
> -static __always_inline bool
> -perf_sw_migrate_enabled(void)
> +static __always_inline bool __perf_sw_enabled(int swevt)
> {
> - if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS]))
> - return true;
> - return false;
> + return static_key_false(&perf_swevent_enabled[swevt]);
> }
>
> static inline void perf_event_task_migrate(struct task_struct *task)
> {
> - if (perf_sw_migrate_enabled())
> + if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS))
> task->sched_migrated = 1;
> }
>
> @@ -1207,11 +1201,9 @@ static inline void perf_event_task_sched_in(struct task_struct *prev,
> if (static_branch_unlikely(&perf_sched_events))
> __perf_event_task_sched_in(prev, task);
>
> - if (perf_sw_migrate_enabled() && task->sched_migrated) {
> - struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
> -
> - perf_fetch_caller_regs(regs);
> - ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0);
> + if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) &&
> + task->sched_migrated) {
> + __perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
> task->sched_migrated = 0;
> }
> }
> @@ -1219,7 +1211,8 @@ static inline void perf_event_task_sched_in(struct task_struct *prev,
> static inline void perf_event_task_sched_out(struct task_struct *prev,
> struct task_struct *next)
> {
> - perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
> + if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES))
> + __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
>
> if (static_branch_unlikely(&perf_sched_events))
> __perf_event_task_sched_out(prev, next);
> @@ -1475,8 +1468,6 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh)
> static inline void
> perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { }
> static inline void
> -perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { }
> -static inline void
> perf_bp_event(struct perf_event *event, void *data) { }
>
> static inline int perf_register_guest_info_callbacks
> --
> 2.30.0.478.g8a0d178c01-goog
>