[PATCH 3/7] perf record: Add BPF event filter support
From: Namhyung Kim
Date: Tue Feb 14 2023 - 00:05:14 EST
Use --filter option to set BPF filter for any events. The filter string
must start with 'bpf:' prefix. Then the BPF program will check the sample
data and filter according to the expression.
For example, the below is the typical perf record for frequency mode.
The sample period started from 1 and increased gradually.
$ sudo ./perf record -e cycles true
$ sudo ./perf script
perf-exec 2272336 546683.916875: 1 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms])
perf-exec 2272336 546683.916892: 1 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms])
perf-exec 2272336 546683.916899: 3 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms])
perf-exec 2272336 546683.916905: 17 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms])
perf-exec 2272336 546683.916911: 100 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms])
perf-exec 2272336 546683.916917: 589 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms])
perf-exec 2272336 546683.916924: 3470 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms])
perf-exec 2272336 546683.916930: 20465 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms])
true 2272336 546683.916940: 119873 cycles: ffffffff8283afdd perf_iterate_ctx+0x2d ([kernel.kallsyms])
true 2272336 546683.917003: 461349 cycles: ffffffff82892517 vma_interval_tree_insert+0x37 ([kernel.kallsyms])
true 2272336 546683.917237: 635778 cycles: ffffffff82a11400 security_mmap_file+0x20 ([kernel.kallsyms])
When you add a BPF filter to get samples having periods greater than 1000,
the output would look like below:
$ sudo ./perf record -e cycles --filter 'bpf: period > 1000' true
$ sudo ./perf script
perf-exec 2273949 546850.708501: 5029 cycles: ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms])
perf-exec 2273949 546850.708508: 32409 cycles: ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms])
perf-exec 2273949 546850.708526: 143369 cycles: ffffffff82b4cdbf xas_start+0x5f ([kernel.kallsyms])
perf-exec 2273949 546850.708600: 372650 cycles: ffffffff8286b8f7 __pagevec_lru_add+0x117 ([kernel.kallsyms])
perf-exec 2273949 546850.708791: 482953 cycles: ffffffff829190de __mod_memcg_lruvec_state+0x4e ([kernel.kallsyms])
true 2273949 546850.709036: 501985 cycles: ffffffff828add7c tlb_gather_mmu+0x4c ([kernel.kallsyms])
true 2273949 546850.709292: 503065 cycles: 7f2446d97c03 _dl_map_object_deps+0x973 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2)
Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
---
tools/perf/Documentation/perf-record.txt | 10 +++++++++-
tools/perf/builtin-record.c | 9 +++++++++
tools/perf/util/bpf_counter.c | 3 +--
tools/perf/util/evsel.c | 2 ++
tools/perf/util/parse-events.c | 4 ++++
5 files changed, 25 insertions(+), 3 deletions(-)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index ff815c2f67e8..7c6bb3be842a 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -121,7 +121,9 @@ OPTIONS
--filter=<filter>::
Event filter. This option should follow an event selector (-e) which
selects either tracepoint event(s) or a hardware trace PMU
- (e.g. Intel PT or CoreSight).
+ (e.g. Intel PT or CoreSight). If the filter string starts with 'bpf:'
+ it means a general filter using BPF which can be applied for any kind
+ of events.
- tracepoint filters
@@ -174,6 +176,12 @@ OPTIONS
within a single mapping. MMAP events (or /proc/<pid>/maps) can be
examined to determine if that is a possibility.
+ - bpf filters
+
+ BPF filter can access the sample data and make a decision based on the
+ data. Users need to set the appropriate sample type to use the BPF
+ filter.
+
Multiple filters can be separated with space or comma.
--exclude-perf::
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 29dcd454b8e2..c81047a78f3e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -52,6 +52,7 @@
#include "util/pmu-hybrid.h"
#include "util/evlist-hybrid.h"
#include "util/off_cpu.h"
+#include "util/bpf-filter.h"
#include "asm/bug.h"
#include "perf.h"
#include "cputopo.h"
@@ -1368,6 +1369,14 @@ static int record__open(struct record *rec)
session->evlist = evlist;
perf_session__set_id_hdr_size(session);
+
+ evlist__for_each_entry(evlist, pos) {
+ if (list_empty(&pos->bpf_filters))
+ continue;
+ rc = perf_bpf_filter__prepare(pos);
+ if (rc)
+ break;
+ }
out:
return rc;
}
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index eeee899fcf34..0414385794ee 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -781,8 +781,7 @@ extern struct bpf_counter_ops bperf_cgrp_ops;
static inline bool bpf_counter_skip(struct evsel *evsel)
{
- return list_empty(&evsel->bpf_counter_list) &&
- evsel->follower_skel == NULL;
+ return evsel->bpf_counter_ops == NULL;
}
int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 51e8ce6edddc..cae624fde026 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -50,6 +50,7 @@
#include "off_cpu.h"
#include "../perf-sys.h"
#include "util/parse-branch-options.h"
+#include "util/bpf-filter.h"
#include <internal/xyarray.h>
#include <internal/lib.h>
#include <internal/threadmap.h>
@@ -1494,6 +1495,7 @@ void evsel__exit(struct evsel *evsel)
assert(list_empty(&evsel->core.node));
assert(evsel->evlist == NULL);
bpf_counter__destroy(evsel);
+ perf_bpf_filter__destroy(evsel);
evsel__free_counts(evsel);
perf_evsel__free_fd(&evsel->core);
perf_evsel__free_id(&evsel->core);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 0336ff27c15f..33f654be6fcc 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -27,6 +27,7 @@
#include "perf.h"
#include "util/parse-events-hybrid.h"
#include "util/pmu-hybrid.h"
+#include "util/bpf-filter.h"
#include "tracepoint.h"
#include "thread_map.h"
@@ -2517,6 +2518,9 @@ static int set_filter(struct evsel *evsel, const void *arg)
return -1;
}
+ if (!strncmp(str, "bpf:", 4))
+ return perf_bpf_filter__parse(&evsel->bpf_filters, str+4);
+
if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
if (evsel__append_tp_filter(evsel, str) < 0) {
fprintf(stderr,
--
2.39.1.581.gbfd45094c4-goog