[PATCH] perf evsel: Rename get_states() to parse_task_states() and make it public

[Ze Gao]

Since get_states() assumes the existence of libtraceevent, so move
to where it should belong, i.e, util/trace-event-parse.c, and also
rename it to parse_task_states().

Leave evsel_getstate() untouched as it fits well in the evsel
category.

Also make some necessary tweaks for python support, and get it
verified with: perf test python.

Signed-off-by: Ze Gao <zegao@xxxxxxxxxxx>
---

Hi Namhyung,

This is the promised refactoring patch for [1], and hopefully it
works as what we all expected.

[1]: https://lore.kernel.org/all/20240122070859.1394479-2-zegao@xxxxxxxxxxx/


Regards,
        -- Ze

 tools/perf/Makefile.perf            |   2 +-
 tools/perf/util/evsel.c             | 115 +---------------------------
 tools/perf/util/python-ext-sources  |   1 +
 tools/perf/util/setup.py            |   1 +
 tools/perf/util/trace-event-parse.c | 113 +++++++++++++++++++++++++++
 tools/perf/util/trace-event.h       |   3 +
 6 files changed, 120 insertions(+), 115 deletions(-)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 27e7c478880f..a5d274bd804b 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -370,7 +370,7 @@ python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT
 ifeq ($(CONFIG_LIBTRACEEVENT),y)
   PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 else
-  PYTHON_EXT_SRCS := $(shell grep -v ^\#\\\|util/trace-event.c util/python-ext-sources)
+  PYTHON_EXT_SRCS := $(shell grep -v ^\#\\\|util/trace-event.c\\\|util/trace-event-parse.c util/python-ext-sources)
 endif
 
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBAPI)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4d14f14f2506..9e67324b1608 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2851,119 +2851,6 @@ u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const
 	return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
 }
 
-/*
- * prev_state is of size long, which is 32 bits on 32 bit architectures.
- * As it needs to have the same bits for both 32 bit and 64 bit architectures
- * we can just assume that the flags we care about will all be within
- * the 32 bits.
- */
-#define MAX_STATE_BITS 32
-
-static const char *convert_sym(struct tep_print_flag_sym *sym)
-{
-	static char save_states[MAX_STATE_BITS + 1];
-
-	memset(save_states, 0, sizeof(save_states));
-
-	/* This is the flags for the prev_state_field, now make them into a string */
-	for (; sym; sym = sym->next) {
-		long bitmask = strtoul(sym->value, NULL, 0);
-		int i;
-
-		for (i = 0; !(bitmask & 1); i++)
-			bitmask >>= 1;
-
-		if (i >= MAX_STATE_BITS)
-			continue;
-
-		save_states[i] = sym->str[0];
-	}
-
-	return save_states;
-}
-
-static struct tep_print_arg_field *
-find_arg_field(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
-{
-	struct tep_print_arg_field *field;
-
-	if (!arg)
-		return NULL;
-
-	if (arg->type == TEP_PRINT_FIELD)
-		return &arg->field;
-
-	if (arg->type == TEP_PRINT_OP) {
-		field = find_arg_field(prev_state_field, arg->op.left);
-		if (field && field->field == prev_state_field)
-			return field;
-		field = find_arg_field(prev_state_field, arg->op.right);
-		if (field && field->field == prev_state_field)
-			return field;
-	}
-	return NULL;
-}
-
-static struct tep_print_flag_sym *
-test_flags(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
-{
-	struct tep_print_arg_field *field;
-
-	field = find_arg_field(prev_state_field, arg->flags.field);
-	if (!field)
-		return NULL;
-
-	return arg->flags.flags;
-}
-
-static struct tep_print_flag_sym *
-search_op(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
-{
-	struct tep_print_flag_sym *sym = NULL;
-
-	if (!arg)
-		return NULL;
-
-	if (arg->type == TEP_PRINT_OP) {
-		sym = search_op(prev_state_field, arg->op.left);
-		if (sym)
-			return sym;
-
-		sym = search_op(prev_state_field, arg->op.right);
-		if (sym)
-			return sym;
-	} else if (arg->type == TEP_PRINT_FLAGS) {
-		sym = test_flags(prev_state_field, arg);
-	}
-
-	return sym;
-}
-
-static const char *get_states(struct tep_format_field *prev_state_field)
-{
-	struct tep_print_flag_sym *sym;
-	struct tep_print_arg *arg;
-	struct tep_event *event;
-
-	event = prev_state_field->event;
-
-	/*
-	 * Look at the event format fields, and search for where
-	 * the prev_state is parsed via the format flags.
-	 */
-	for (arg = event->print_fmt.args; arg; arg = arg->next) {
-		/*
-		 * Currently, the __print_flags() for the prev_state
-		 * is embedded in operations, so they too must be
-		 * searched.
-		 */
-		sym = search_op(prev_state_field, arg);
-		if (sym)
-			return convert_sym(sym);
-	}
-	return NULL;
-}
-
 char evsel__taskstate(struct evsel *evsel, struct perf_sample *sample, const char *name)
 {
 	static struct tep_format_field *prev_state_field;
@@ -2979,7 +2866,7 @@ char evsel__taskstate(struct evsel *evsel, struct perf_sample *sample, const cha
 		return state;
 
 	if (!states || field != prev_state_field) {
-		states = get_states(field);
+		states = parse_task_states(field);
 		if (!states)
 			return state;
 		prev_state_field = field;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 593b660ec75e..1bec945f4838 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -31,6 +31,7 @@ util/counts.c
 util/print_binary.c
 util/strlist.c
 util/trace-event.c
+util/trace-event-parse.c
 ../lib/rbtree.c
 util/string.c
 util/symbol_fprintf.c
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 79d5e2955f85..3107f5aa8c9a 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -85,6 +85,7 @@ if '-DHAVE_LIBTRACEEVENT' in cflags:
     extra_libraries += [ 'traceevent' ]
 else:
     ext_sources.remove('util/trace-event.c')
+    ext_sources.remove('util/trace-event-parse.c')
 
 # use full paths with source files
 ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources))
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 2d3c2576bab7..f0332bd3a501 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -122,6 +122,119 @@ void event_format__print(struct tep_event *event,
 	return event_format__fprintf(event, cpu, data, size, stdout);
 }
 
+/*
+ * prev_state is of size long, which is 32 bits on 32 bit architectures.
+ * As it needs to have the same bits for both 32 bit and 64 bit architectures
+ * we can just assume that the flags we care about will all be within
+ * the 32 bits.
+ */
+#define MAX_STATE_BITS 32
+
+static const char *convert_sym(struct tep_print_flag_sym *sym)
+{
+	static char save_states[MAX_STATE_BITS + 1];
+
+	memset(save_states, 0, sizeof(save_states));
+
+	/* This is the flags for the prev_state_field, now make them into a string */
+	for (; sym; sym = sym->next) {
+		long bitmask = strtoul(sym->value, NULL, 0);
+		int i;
+
+		for (i = 0; !(bitmask & 1); i++)
+			bitmask >>= 1;
+
+		if (i >= MAX_STATE_BITS)
+			continue;
+
+		save_states[i] = sym->str[0];
+	}
+
+	return save_states;
+}
+
+static struct tep_print_arg_field *
+find_arg_field(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
+{
+	struct tep_print_arg_field *field;
+
+	if (!arg)
+		return NULL;
+
+	if (arg->type == TEP_PRINT_FIELD)
+		return &arg->field;
+
+	if (arg->type == TEP_PRINT_OP) {
+		field = find_arg_field(prev_state_field, arg->op.left);
+		if (field && field->field == prev_state_field)
+			return field;
+		field = find_arg_field(prev_state_field, arg->op.right);
+		if (field && field->field == prev_state_field)
+			return field;
+	}
+	return NULL;
+}
+
+static struct tep_print_flag_sym *
+test_flags(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
+{
+	struct tep_print_arg_field *field;
+
+	field = find_arg_field(prev_state_field, arg->flags.field);
+	if (!field)
+		return NULL;
+
+	return arg->flags.flags;
+}
+
+static struct tep_print_flag_sym *
+search_op(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
+{
+	struct tep_print_flag_sym *sym = NULL;
+
+	if (!arg)
+		return NULL;
+
+	if (arg->type == TEP_PRINT_OP) {
+		sym = search_op(prev_state_field, arg->op.left);
+		if (sym)
+			return sym;
+
+		sym = search_op(prev_state_field, arg->op.right);
+		if (sym)
+			return sym;
+	} else if (arg->type == TEP_PRINT_FLAGS) {
+		sym = test_flags(prev_state_field, arg);
+	}
+
+	return sym;
+}
+
+const char *parse_task_states(struct tep_format_field *state_field)
+{
+	struct tep_print_flag_sym *sym;
+	struct tep_print_arg *arg;
+	struct tep_event *event;
+
+	event = state_field->event;
+
+	/*
+	 * Look at the event format fields, and search for where
+	 * the prev_state is parsed via the format flags.
+	 */
+	for (arg = event->print_fmt.args; arg; arg = arg->next) {
+		/*
+		 * Currently, the __print_flags() for the prev_state
+		 * is embedded in operations, so they too must be
+		 * searched.
+		 */
+		sym = search_op(state_field, arg);
+		if (sym)
+			return convert_sym(sym);
+	}
+	return NULL;
+}
+
 void parse_ftrace_printk(struct tep_handle *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index a69ee29419f3..bbf8b26bc8da 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -15,6 +15,7 @@ struct perf_tool;
 struct thread;
 struct tep_plugin_list;
 struct evsel;
+struct tep_format_field;
 
 struct trace_event {
 	struct tep_handle	*pevent;
@@ -51,6 +52,8 @@ int parse_event_file(struct tep_handle *pevent,
 unsigned long long
 raw_field_value(struct tep_event *event, const char *name, void *data);
 
+const char *parse_task_states(struct tep_format_field *state_field);
+
 void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size);
 void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size);
-- 
2.41.0