perf stat: Enable counting events for BPF programs

Introduce 'perf stat -b' option, which counts events for BPF programs, like:

  [root@localhost ~]# ~/perf stat -e ref-cycles,cycles -b 254 -I 1000
     1.487903822            115,200      ref-cycles
     1.487903822             86,012      cycles
     2.489147029             80,560      ref-cycles
     2.489147029             73,784      cycles
     3.490341825             60,720      ref-cycles
     3.490341825             37,797      cycles
     4.491540887             37,120      ref-cycles
     4.491540887             31,963      cycles

The example above counts 'cycles' and 'ref-cycles' of BPF program of id
254.  This is similar to bpftool-prog-profile command, but more
flexible.

'perf stat -b' creates per-cpu perf_event and loads fentry/fexit BPF
programs (monitor-progs) to the target BPF program (target-prog). The
monitor-progs read perf_event before and after the target-prog, and
aggregate the difference in a BPF map. Then the user space reads data
from these maps.

A new 'struct bpf_counter' is introduced to provide a common interface
that uses BPF programs/maps to count perf events.

Committer notes:

Removed all but bpf_counter.h includes from evsel.h, not needed at all.

Also BPF map lookups for PERCPU_ARRAYs need to have as its value receive
buffer passed to the kernel libbpf_num_possible_cpus() entries, not
evsel__nr_cpus(evsel), as the former uses
/sys/devices/system/cpu/possible while the later uses
/sys/devices/system/cpu/online, which may be less than the 'possible'
number making the bpf map lookup overwrite memory and cause hard to
debug memory corruption.

We need to continue using evsel__nr_cpus(evsel) when accessing the
perf_counts array tho, not to overwrite another are of memory :-)

Signed-off-by: Song Liu <songliubraving@fb.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/lkml/20210120163031.GU12699@kernel.org/
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Link: http://lore.kernel.org/lkml/20201229214214.3413833-4-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 93 insertions, 0 deletions

diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
new file mode 100644
index 000000000000..c7cec92d0236
--- /dev/null
+++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2020 Facebook
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* map of perf event fds, num_cpu * num_metric entries */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(int));
+} events SEC(".maps");
+
+/* readings at fentry */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} fentry_readings SEC(".maps");
+
+/* accumulated readings */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} accum_readings SEC(".maps");
+
+const volatile __u32 num_cpu = 1;
+
+SEC("fentry/XXX")
+int BPF_PROG(fentry_XXX)
+{
+	__u32 key = bpf_get_smp_processor_id();
+	struct bpf_perf_event_value *ptr;
+	__u32 zero = 0;
+	long err;
+
+	/* look up before reading, to reduce error */
+	ptr = bpf_map_lookup_elem(&fentry_readings, &zero);
+	if (!ptr)
+		return 0;
+
+	err = bpf_perf_event_read_value(&events, key, ptr, sizeof(*ptr));
+	if (err)
+		return 0;
+
+	return 0;
+}
+
+static inline void
+fexit_update_maps(struct bpf_perf_event_value *after)
+{
+	struct bpf_perf_event_value *before, diff, *accum;
+	__u32 zero = 0;
+
+	before = bpf_map_lookup_elem(&fentry_readings, &zero);
+	/* only account samples with a valid fentry_reading */
+	if (before && before->counter) {
+		struct bpf_perf_event_value *accum;
+
+		diff.counter = after->counter - before->counter;
+		diff.enabled = after->enabled - before->enabled;
+		diff.running = after->running - before->running;
+
+		accum = bpf_map_lookup_elem(&accum_readings, &zero);
+		if (accum) {
+			accum->counter += diff.counter;
+			accum->enabled += diff.enabled;
+			accum->running += diff.running;
+		}
+	}
+}
+
+SEC("fexit/XXX")
+int BPF_PROG(fexit_XXX)
+{
+	struct bpf_perf_event_value reading;
+	__u32 cpu = bpf_get_smp_processor_id();
+	__u32 one = 1, zero = 0;
+	int err;
+
+	/* read all events before updating the maps, to reduce error */
+	err = bpf_perf_event_read_value(&events, cpu, &reading, sizeof(reading));
+	if (err)
+		return 0;
+
+	fexit_update_maps(&reading);
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";