From b9c44b91476b67327a521568a854babecc4070ab Mon Sep 17 00:00:00 2001 From: Yabin Cui Date: Wed, 15 May 2024 12:36:07 -0700 Subject: perf/core: Save raw sample data conditionally based on sample type Currently, space for raw sample data is always allocated within sample records for both BPF output and tracepoint events. This leads to unused space in sample records when raw sample data is not requested. This patch enforces checking sample type of an event in perf_sample_save_raw_data(). So raw sample data will only be saved if explicitly requested, reducing overhead when it is not needed. Fixes: 0a9081cf0a11 ("perf/core: Add perf_sample_save_raw_data() helper") Signed-off-by: Yabin Cui Signed-off-by: Ingo Molnar Reviewed-by: Ian Rogers Acked-by: Namhyung Kim Link: https://lore.kernel.org/r/20240515193610.2350456-2-yabinc@google.com --- kernel/trace/bpf_trace.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index fdab7ecd8dfa..162bacf8aa5d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -619,7 +619,8 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = { static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, - u64 flags, struct perf_sample_data *sd) + u64 flags, struct perf_raw_record *raw, + struct perf_sample_data *sd) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); @@ -644,6 +645,8 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; + perf_sample_save_raw_data(sd, event, raw); + return perf_event_output(event, sd, regs); } @@ -687,9 +690,8 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, } perf_sample_data_init(sd, 0, 0); - perf_sample_save_raw_data(sd, &raw); - err = __bpf_perf_event_output(regs, map, flags, sd); + err = __bpf_perf_event_output(regs, map, flags, &raw, sd); out: this_cpu_dec(bpf_trace_nest_level); preempt_enable(); @@ -748,9 +750,8 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); - perf_sample_save_raw_data(sd, &raw); - ret = __bpf_perf_event_output(regs, map, flags, sd); + ret = __bpf_perf_event_output(regs, map, flags, &raw, sd); out: this_cpu_dec(bpf_event_output_nest_level); preempt_enable(); -- cgit v1.2.3