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
>