perf record: Add BPF event filter support

Use --filter option to set BPF filter for generic events other than the
tracepoints or Intel PT.  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 '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)

Committer notes:

Add stubs for perf_bpf_filter__prepare() and perf_bpf_filter__destroy()
to tools/perf/util/python.c to keep it building.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@arm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Song Liu <song@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index ff815c2..122f717 100644 (file)
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -119,9 +119,12 @@ OPTIONS
          "perf report" to view group events together.
 
 --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).
+       Event filter.  This option should follow an event selector (-e).
+       If the event is a tracepoint, the filter string will be parsed by
+       the kernel.  If the event is a hardware trace PMU (e.g. Intel PT
+       or CoreSight), it'll be processed as an address filter.  Otherwise
+       it means a general filter using BPF which can be applied for any
+       kind of event.
 
        - tracepoint filters
 
@@ -176,6 +179,12 @@ OPTIONS
 
        Multiple filters can be separated with space or comma.
 
+       - bpf filters
+
+       A BPF filter can access the sample data and make a decision based on the
+       data.  Users need to set an appropriate sample type to use the BPF
+       filter.
+
 --exclude-perf::
        Don't record events issued by perf itself. This option should follow
        an event selector (-e) which selects tracepoint event(s). It adds a

diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index aa78a15..1b77436 100644 (file)
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -763,8 +763,7 @@ 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/evlist.c b/tools/perf/util/evlist.c
index b74e122..cc491a0 100644 (file)
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -31,6 +31,7 @@
 #include "util/evlist-hybrid.h"
 #include "util/pmu.h"
 #include "util/sample.h"
+#include "util/bpf-filter.h"
 #include <signal.h>
 #include <unistd.h>
 #include <sched.h>
@@ -1086,17 +1087,27 @@ int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
        int err = 0;
 
        evlist__for_each_entry(evlist, evsel) {
-               if (evsel->filter == NULL)
-                       continue;
-
                /*
                 * filters only work for tracepoint event, which doesn't have cpu limit.
                 * So evlist and evsel should always be same.
                 */
-               err = perf_evsel__apply_filter(&evsel->core, evsel->filter);
-               if (err) {
-                       *err_evsel = evsel;
-                       break;
+               if (evsel->filter) {
+                       err = perf_evsel__apply_filter(&evsel->core, evsel->filter);
+                       if (err) {
+                               *err_evsel = evsel;
+                               break;
+                       }
+               }
+
+               /*
+                * non-tracepoint events can have BPF filters.
+                */
+               if (!list_empty(&evsel->bpf_filters)) {
+                       err = perf_bpf_filter__prepare(evsel);
+                       if (err) {
+                               *err_evsel = evsel;
+                               break;
+                       }
                }
        }
 

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a83d8cd..dc3faf0 100644 (file)
--- 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>
@@ -1517,6 +1518,7 @@ 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 3b2e5bb..6c5cf52 100644 (file)
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -28,6 +28,7 @@
 #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"
 
@@ -2542,11 +2543,8 @@ static int set_filter(struct evsel *evsel, const void *arg)
                perf_pmu__scan_file(pmu, "nr_addr_filters",
                                    "%d", &nr_addr_filters);
 
-       if (!nr_addr_filters) {
-               fprintf(stderr,
-                       "This CPU does not support address filtering\n");
-               return -1;
-       }
+       if (!nr_addr_filters)
+               return perf_bpf_filter__parse(&evsel->bpf_filters, str);
 
        if (evsel__append_addr_filter(evsel, str) < 0) {
                fprintf(stderr,

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index be336f1..0faea4c 100644 (file)
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -19,6 +19,7 @@
 #include "mmap.h"
 #include "stat.h"
 #include "metricgroup.h"
+#include "util/bpf-filter.h"
 #include "util/env.h"
 #include "util/pmu.h"
 #include <internal/lib.h>
@@ -135,6 +136,19 @@ int bpf_counter__disable(struct evsel *evsel __maybe_unused)
        return 0;
 }
 
+// not to drag util/bpf-filter.c
+#ifdef HAVE_BPF_SKEL
+int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused)
+{
+       return 0;
+}
+
+int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused)
+{
+       return 0;
+}
+#endif
+
 /*
  * Support debug printing even though util/debug.c is not linked.  That means
  * implementing 'verbose' and 'eprintf'.