On 2024-10-11 2:42 p.m., Peter Zijlstra wrote:
>
> Can you rework this one along these lines?
Sure.
I probably also add macros to replace the magic number 0 and 1. For example,
#define T_TOTAL 0
#define T_GUEST 1
Thanks,
Kan
>
> ---
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -975,6 +975,7 @@ struct perf_event_context {
> * Context clock, runs when context enabled.
> */
> struct perf_time_ctx time;
> + struct perf_time_ctx timeguest;
>
> /*
> * These fields let us detect when two contexts have both
> @@ -1066,6 +1067,7 @@ struct bpf_perf_event_data_kern {
> */
> struct perf_cgroup_info {
> struct perf_time_ctx time;
> + struct perf_time_ctx timeguest;
> int active;
> };
>
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -782,12 +782,44 @@ static inline int is_cgroup_event(struct
> return event->cgrp != NULL;
> }
>
> +static_assert(offsetof(struct perf_event, timeguest) -
> + offsetof(struct perf_event, time) ==
> + sizeof(struct perf_time_ctx));
> +
> +static_assert(offsetof(struct perf_cgroup_info, timeguest) -
> + offsetof(struct perf_cgroup_info, time) ==
> + sizeof(struct perf_time_ctx));
> +
> +static inline u64 __perf_event_time_ctx(struct perf_event *event,
> + struct perf_time_ctx *times)
> +{
> + u64 time = times[0].time;
> + if (event->attr.exclude_guest)
> + time -= times[1].time;
> + return time;
> +}
> +
> +static inline u64 __perf_event_time_ctx_now(struct perf_event *event,
> + struct perf_time_ctx *times,
> + u64 now)
> +{
> + if (event->attr.exclude_guest) {
> + /*
> + * (now + times[0].offset) - (now + times[1].offset) :=
> + * times[0].offset - times[1].offset
> + */
> + return READ_ONCE(times[0].offset) - READ_ONCE(times[1].offset);
> + }
> +
> + return now + READ_ONCE(times[0].offset);
> +}
> +
> static inline u64 perf_cgroup_event_time(struct perf_event *event)
> {
> struct perf_cgroup_info *t;
>
> t = per_cpu_ptr(event->cgrp->info, event->cpu);
> - return t->time.time;
> + return __perf_event_time_ctx(event, &t->time);
> }
>
> static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now)
> @@ -796,12 +828,12 @@ static inline u64 perf_cgroup_event_time
>
> t = per_cpu_ptr(event->cgrp->info, event->cpu);
> if (!__load_acquire(&t->active))
> - return t->time.time;
> + return __perf_event_time_ctx(event, &t->time);
> now += READ_ONCE(t->time.offset);
> - return now;
> + return __perf_event_time_ctx_now(event, &t->time, now);
> }
>
> -static inline void update_perf_time_ctx(struct perf_time_ctx *time, u64 now, bool adv)
> +static inline void __update_perf_time_ctx(struct perf_time_ctx *time, u64 now, bool adv)
> {
> if (adv)
> time->time += now - time->stamp;
> @@ -819,6 +851,13 @@ static inline void update_perf_time_ctx(
> WRITE_ONCE(time->offset, time->time - time->stamp);
> }
>
> +static inline void update_perf_time_ctx(struct perf_time_ctx *time, u64 now, bool adv)
> +{
> + __update_perf_time_ctx(time + 0, now, adv);
> + if (__this_cpu_read(perf_in_guest))
> + __update_perf_time_ctx(time + 1, now, adv)
> +}
> +
> static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final)
> {
> struct perf_cgroup *cgrp = cpuctx->cgrp;
>
