perf bpf filter: Introduce basic BPF filter expression

This implements a tiny parser for the filter expressions used for BPF.
Each expression will be converted to struct perf_bpf_filter_expr and
be passed to a BPF map.

For now, I'd like to start with the very basic comparisons like EQ or
GT.  The LHS should be a term for sample data and the RHS is a number.
The expressions are connected by a comma.  For example,

    period > 10000
    ip < 0x1000000000000, cpu == 3

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>

5 files changed, 225 insertions, 0 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 0806bc0361ad..bd18fe5f2719 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -154,6 +154,9 @@ perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-flex.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-bison.o
 
 ifeq ($(CONFIG_LIBTRACEEVENT),y)
   perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o
@@ -267,6 +270,16 @@ $(OUTPUT)util/pmu-bison.c $(OUTPUT)util/pmu-bison.h: util/pmu.y
 	$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \
 		-o $(OUTPUT)util/pmu-bison.c -p perf_pmu_
 
+$(OUTPUT)util/bpf-filter-flex.c $(OUTPUT)util/bpf-filter-flex.h: util/bpf-filter.l $(OUTPUT)util/bpf-filter-bison.c
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $(OUTPUT)util/bpf-filter-flex.c \
+		--header-file=$(OUTPUT)util/bpf-filter-flex.h $(PARSER_DEBUG_FLEX) $<
+
+$(OUTPUT)util/bpf-filter-bison.c $(OUTPUT)util/bpf-filter-bison.h: util/bpf-filter.y
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \
+		-o $(OUTPUT)util/bpf-filter-bison.c -p perf_bpf_filter_
+
 FLEX_GE_26 := $(shell expr $(shell $(FLEX) --version | sed -e  's/flex \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 26)
 ifeq ($(FLEX_GE_26),1)
   flex_flags := -Wno-switch-enum -Wno-switch-default -Wno-unused-function -Wno-redundant-decls -Wno-sign-compare -Wno-unused-parameter -Wno-missing-prototypes -Wno-missing-declarations
@@ -280,6 +293,7 @@ endif
 CFLAGS_parse-events-flex.o  += $(flex_flags)
 CFLAGS_pmu-flex.o           += $(flex_flags)
 CFLAGS_expr-flex.o          += $(flex_flags)
+CFLAGS_bpf-filter-flex.o    += $(flex_flags)
 
 bison_flags := -DYYENABLE_NLS=0
 BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35)
@@ -291,10 +305,12 @@ endif
 CFLAGS_parse-events-bison.o += $(bison_flags)
 CFLAGS_pmu-bison.o          += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
 CFLAGS_expr-bison.o         += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
+CFLAGS_bpf-filter-bison.o   += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 $(OUTPUT)util/expr.o: $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-bison.c
+$(OUTPUT)util/bpf-filter.o: $(OUTPUT)util/bpf-filter-flex.c $(OUTPUT)util/bpf-filter-bison.c
 
 CFLAGS_bitmap.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_find_bit.o      += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c
new file mode 100644
index 000000000000..c72e35d51240
--- /dev/null
+++ b/tools/perf/util/bpf-filter.c
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+
+#include "util/bpf-filter.h"
+#include "util/bpf-filter-flex.h"
+#include "util/bpf-filter-bison.h"
+
+struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags,
+						       enum perf_bpf_filter_op op,
+						       unsigned long val)
+{
+	struct perf_bpf_filter_expr *expr;
+
+	expr = malloc(sizeof(*expr));
+	if (expr != NULL) {
+		expr->sample_flags = sample_flags;
+		expr->op = op;
+		expr->val = val;
+	}
+	return expr;
+}
+
+int perf_bpf_filter__parse(struct list_head *expr_head, const char *str)
+{
+	YY_BUFFER_STATE buffer;
+	int ret;
+
+	buffer = perf_bpf_filter__scan_string(str);
+
+	ret = perf_bpf_filter_parse(expr_head);
+
+	perf_bpf_filter__flush_buffer(buffer);
+	perf_bpf_filter__delete_buffer(buffer);
+	perf_bpf_filter_lex_destroy();
+
+	return ret;
+}
diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h
new file mode 100644
index 000000000000..93a0d3de038c
--- /dev/null
+++ b/tools/perf/util/bpf-filter.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_UTIL_BPF_FILTER_H
+#define PERF_UTIL_BPF_FILTER_H
+
+#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,
+};
+
+struct perf_bpf_filter_expr {
+	struct list_head list;
+	enum perf_bpf_filter_op op;
+	unsigned long sample_flags;
+	unsigned long val;
+};
+
+#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);
+#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;
+}
+#endif /* HAVE_BPF_SKEL*/
+#endif /* PERF_UTIL_BPF_FILTER_H */
diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l
new file mode 100644
index 000000000000..f6c0b74ea285
--- /dev/null
+++ b/tools/perf/util/bpf-filter.l
@@ -0,0 +1,82 @@
+%option prefix="perf_bpf_filter_"
+%option noyywrap
+
+%{
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/perf_event.h>
+
+#include "bpf-filter.h"
+#include "bpf-filter-bison.h"
+
+static int sample(unsigned long sample_flag)
+{
+	perf_bpf_filter_lval.sample = sample_flag;
+	return BFT_SAMPLE;
+}
+
+static int operator(enum perf_bpf_filter_op op)
+{
+	perf_bpf_filter_lval.op = op;
+	return BFT_OP;
+}
+
+static int value(int base)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(perf_bpf_filter_text, NULL, base);
+	if (errno)
+		return BFT_ERROR;
+
+	perf_bpf_filter_lval.num = num;
+	return BFT_NUM;
+}
+
+static int error(const char *str)
+{
+	printf("perf_bpf_filter: Unexpected filter %s: %s\n", str, perf_bpf_filter_text);
+	return BFT_ERROR;
+}
+
+%}
+
+num_dec		[0-9]+
+num_hex		0[Xx][0-9a-fA-F]+
+space		[ \t]+
+ident		[_a-zA-Z][_a-zA-Z0-9]+
+
+%%
+
+{num_dec}	{ return value(10); }
+{num_hex}	{ return value(16); }
+{space}		{ }
+
+ip		{ return sample(PERF_SAMPLE_IP); }
+id		{ return sample(PERF_SAMPLE_ID); }
+tid		{ return sample(PERF_SAMPLE_TID); }
+cpu		{ return sample(PERF_SAMPLE_CPU); }
+time		{ return sample(PERF_SAMPLE_TIME); }
+addr		{ return sample(PERF_SAMPLE_ADDR); }
+period		{ return sample(PERF_SAMPLE_PERIOD); }
+txn		{ return sample(PERF_SAMPLE_TRANSACTION); }
+weight		{ return sample(PERF_SAMPLE_WEIGHT); }
+phys_addr	{ return sample(PERF_SAMPLE_PHYS_ADDR); }
+code_pgsz	{ return sample(PERF_SAMPLE_CODE_PAGE_SIZE); }
+data_pgsz	{ return sample(PERF_SAMPLE_DATA_PAGE_SIZE); }
+
+"=="		{ return operator(PBF_OP_EQ); }
+"!="		{ return operator(PBF_OP_NEQ); }
+">"		{ return operator(PBF_OP_GT); }
+"<"		{ return operator(PBF_OP_LT); }
+">="		{ return operator(PBF_OP_GE); }
+"<="		{ return operator(PBF_OP_LE); }
+"&"		{ return operator(PBF_OP_AND); }
+
+","		{ return ','; }
+
+{ident}		{ return error("ident"); }
+.		{ return error("input"); }
+
+%%
diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y
new file mode 100644
index 000000000000..13eca612ecca
--- /dev/null
+++ b/tools/perf/util/bpf-filter.y
@@ -0,0 +1,54 @@
+%parse-param {struct list_head *expr_head}
+%define parse.error verbose
+
+%{
+
+#include <stdio.h>
+#include <string.h>
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include "bpf-filter.h"
+
+static void perf_bpf_filter_error(struct list_head *expr __maybe_unused,
+				  char const *msg)
+{
+	printf("perf_bpf_filter: %s\n", msg);
+}
+
+%}
+
+%union
+{
+	unsigned long num;
+	unsigned long sample;
+	enum perf_bpf_filter_op op;
+	struct perf_bpf_filter_expr *expr;
+}
+
+%token BFT_SAMPLE BFT_OP BFT_ERROR BFT_NUM
+%type <expr> filter_term
+%destructor { free ($$); } <expr>
+%type <sample> BFT_SAMPLE
+%type <op> BFT_OP
+%type <num> BFT_NUM
+
+%%
+
+filter:
+filter ',' filter_term
+{
+	list_add_tail(&$3->list, expr_head);
+}
+|
+filter_term
+{
+	list_add_tail(&$1->list, expr_head);
+}
+
+filter_term:
+BFT_SAMPLE BFT_OP BFT_NUM
+{
+	$$ = perf_bpf_filter_expr__new($1, $2, $3);
+}
+
+%%