perf bpf filter: Implement event sample filtering

The BPF program will be attached to a perf_event and be triggered when
it overflows.  It'd iterate the filters map and compare the sample
value according to the expression.  If any of them fails, the sample
would be dropped.

Also it needs to have the corresponding sample data for the expression
so it compares data->sample_flags with the given value.  To access the
sample data, it uses the bpf_cast_to_kern_ctx() kfunc which was added
in v6.2 kernel.
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.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Makefile.perf

@@ -1050,7 +1050,7 @@ SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
 SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h
-SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h
+SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h
 
 $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT):
 	$(Q)$(MKDIR) -p $@

tools/perf/util/bpf-filter.c

 /* SPDX-License-Identifier: GPL-2.0 */
 #include <stdlib.h>
 
+#include <bpf/bpf.h>
+#include <linux/err.h>
+#include <internal/xyarray.h>
+
+#include "util/debug.h"
+#include "util/evsel.h"
+
 #include "util/bpf-filter.h"
 #include "util/bpf-filter-flex.h"
 #include "util/bpf-filter-bison.h"
 
+#include "bpf_skel/sample-filter.h"
+#include "bpf_skel/sample_filter.skel.h"
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
+
+int perf_bpf_filter__prepare(struct evsel *evsel)
+{
+	int i, x, y, fd;
+	struct sample_filter_bpf *skel;
+	struct bpf_program *prog;
+	struct bpf_link *link;
+	struct perf_bpf_filter_expr *expr;
+
+	skel = sample_filter_bpf__open_and_load();
+	if (!skel) {
+		pr_err("Failed to load perf sample-filter BPF skeleton\n");
+		return -1;
+	}
+
+	i = 0;
+	fd = bpf_map__fd(skel->maps.filters);
+	list_for_each_entry(expr, &evsel->bpf_filters, list) {
+		struct perf_bpf_filter_entry entry = {
+			.op = expr->op,
+			.flags = expr->sample_flags,
+			.value = expr->val,
+		};
+		bpf_map_update_elem(fd, &i, &entry, BPF_ANY);
+		i++;
+	}
+
+	prog = skel->progs.perf_sample_filter;
+	for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) {
+		for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) {
+			link = bpf_program__attach_perf_event(prog, FD(evsel, x, y));
+			if (IS_ERR(link)) {
+				pr_err("Failed to attach perf sample-filter program\n");
+				return PTR_ERR(link);
+			}
+		}
+	}
+	evsel->bpf_skel = skel;
+	return 0;
+}
+
+int perf_bpf_filter__destroy(struct evsel *evsel)
+{
+	struct perf_bpf_filter_expr *expr, *tmp;
+
+	list_for_each_entry_safe(expr, tmp, &evsel->bpf_filters, list) {
+		list_del(&expr->list);
+		free(expr);
+	}
+	sample_filter_bpf__destroy(evsel->bpf_skel);
+	return 0;
+}
+
 struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags,
 						       enum perf_bpf_filter_op op,
 						       unsigned long val)

tools/perf/util/bpf-filter.h

@@ -4,15 +4,7 @@
 
 #include <linux/list.h>
 
-enum perf_bpf_filter_op {
-	PBF_OP_EQ,
-	PBF_OP_NEQ,
-	PBF_OP_GT,
-	PBF_OP_GE,
-	PBF_OP_LT,
-	PBF_OP_LE,
-	PBF_OP_AND,
-};
+#include "bpf_skel/sample-filter.h"
 
 struct perf_bpf_filter_expr {
 	struct list_head list;
@@ -21,16 +13,30 @@ struct perf_bpf_filter_expr {
 	unsigned long val;
 };
 
+struct evsel;
+
 #ifdef HAVE_BPF_SKEL
 struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags,
 						       enum perf_bpf_filter_op op,
 						       unsigned long val);
 int perf_bpf_filter__parse(struct list_head *expr_head, const char *str);
+int perf_bpf_filter__prepare(struct evsel *evsel);
+int perf_bpf_filter__destroy(struct evsel *evsel);
+
 #else /* !HAVE_BPF_SKEL */
+
 static inline int perf_bpf_filter__parse(struct list_head *expr_head __maybe_unused,
 					 const char *str __maybe_unused)
 {
-	return -ENOSYS;
+	return -EOPNOTSUPP;
+}
+static inline int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused)
+{
+	return -EOPNOTSUPP;
+}
+static inline int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused)
+{
+	return -EOPNOTSUPP;
 }
 #endif /* HAVE_BPF_SKEL*/
 #endif /* PERF_UTIL_BPF_FILTER_H */

tools/perf/util/bpf_skel/sample-filter.h

+#ifndef PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H
+#define PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H
+
+#define MAX_FILTERS  32
+
+/* supported filter operations */
+enum perf_bpf_filter_op {
+	PBF_OP_EQ,
+	PBF_OP_NEQ,
+	PBF_OP_GT,
+	PBF_OP_GE,
+	PBF_OP_LT,
+	PBF_OP_LE,
+	PBF_OP_AND
+};
+
+/* BPF map entry for filtering */
+struct perf_bpf_filter_entry {
+	enum perf_bpf_filter_op op;
+	__u64 flags;
+	__u64 value;
+};
+
+#endif /* PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H */
\ No newline at end of file

tools/perf/util/bpf_skel/sample_filter.bpf.c

+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2023 Google
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#include "sample-filter.h"
+
+/* BPF map that will be filled by user space */
+struct filters {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct perf_bpf_filter_entry);
+	__uint(max_entries, MAX_FILTERS);
+} filters SEC(".maps");
+
+int dropped;
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+
+/* new kernel perf_sample_data definition */
+struct perf_sample_data___new {
+	__u64 sample_flags;
+} __attribute__((preserve_access_index));
+
+/* helper function to return the given perf sample data */
+static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx,
+				    struct perf_bpf_filter_entry *entry)
+{
+	struct perf_sample_data___new *data = (void *)kctx->data;
+
+	if (!bpf_core_field_exists(data->sample_flags) ||
+	    (data->sample_flags & entry->flags) == 0)
+		return 0;
+
+	switch (entry->flags) {
+	case PERF_SAMPLE_IP:
+		return kctx->data->ip;
+	case PERF_SAMPLE_ID:
+		return kctx->data->id;
+	case PERF_SAMPLE_TID:
+		return kctx->data->tid_entry.tid;
+	case PERF_SAMPLE_CPU:
+		return kctx->data->cpu_entry.cpu;
+	case PERF_SAMPLE_TIME:
+		return kctx->data->time;
+	case PERF_SAMPLE_ADDR:
+		return kctx->data->addr;
+	case PERF_SAMPLE_PERIOD:
+		return kctx->data->period;
+	case PERF_SAMPLE_TRANSACTION:
+		return kctx->data->txn;
+	case PERF_SAMPLE_WEIGHT:
+		return kctx->data->weight.full;
+	case PERF_SAMPLE_PHYS_ADDR:
+		return kctx->data->phys_addr;
+	case PERF_SAMPLE_CODE_PAGE_SIZE:
+		return kctx->data->code_page_size;
+	case PERF_SAMPLE_DATA_PAGE_SIZE:
+		return kctx->data->data_page_size;
+	default:
+		break;
+	}
+	return 0;
+}
+
+/* BPF program to be called from perf event overflow handler */
+SEC("perf_event")
+int perf_sample_filter(void *ctx)
+{
+	struct bpf_perf_event_data_kern *kctx;
+	struct perf_bpf_filter_entry *entry;
+	__u64 sample_data;
+	int i;
+
+	kctx = bpf_cast_to_kern_ctx(ctx);
+
+	for (i = 0; i < MAX_FILTERS; i++) {
+		int key = i; /* needed for verifier :( */
+
+		entry = bpf_map_lookup_elem(&filters, &key);
+		if (entry == NULL)
+			break;
+		sample_data = perf_get_sample(kctx, entry);
+
+		switch (entry->op) {
+		case PBF_OP_EQ:
+			if (!(sample_data == entry->value))
+				goto drop;
+			break;
+		case PBF_OP_NEQ:
+			if (!(sample_data != entry->value))
+				goto drop;
+			break;
+		case PBF_OP_GT:
+			if (!(sample_data > entry->value))
+				goto drop;
+			break;
+		case PBF_OP_GE:
+			if (!(sample_data >= entry->value))
+				goto drop;
+			break;
+		case PBF_OP_LT:
+			if (!(sample_data < entry->value))
+				goto drop;
+			break;
+		case PBF_OP_LE:
+			if (!(sample_data <= entry->value))
+				goto drop;
+			break;
+		case PBF_OP_AND:
+			if (!(sample_data & entry->value))
+				goto drop;
+			break;
+		}
+	}
+	/* generate sample data */
+	return 1;
+
+drop:
+	__sync_fetch_and_add(&dropped, 1);
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";

tools/perf/util/evsel.h

@@ -150,8 +150,10 @@ struct evsel {
 	 */
 	struct bpf_counter_ops	*bpf_counter_ops;
 
-	/* for perf-stat -b */
-	struct list_head	bpf_counter_list;
+	union {
+		struct list_head	bpf_counter_list; /* for perf-stat -b */
+		struct list_head	bpf_filters; /* for perf-record --filter */
+	};
 
 	/* for perf-stat --use-bpf */
 	int			bperf_leader_prog_fd;
@@ -159,6 +161,7 @@ struct evsel {
 	union {
 		struct bperf_leader_bpf *leader_skel;
 		struct bperf_follower_bpf *follower_skel;
+		void *bpf_skel;
 	};
 	unsigned long		open_flags;
 	int			precise_ip_original;