Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Ze Gao <zegao2021@gmail.com>
To:     Peter Zijlstra <peterz@infradead.org>,
        Steven Rostedt <rostedt@goodmis.org>,
        Namhyung Kim <namhyung@kernel.org>
Cc:     Adrian Hunter <adrian.hunter@intel.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Ian Rogers <irogers@google.com>,
        Ingo Molnar <mingo@redhat.com>, Jiri Olsa <jolsa@kernel.org>,
        Mark Rutland <mark.rutland@arm.com>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
        linux-trace-kernel@vger.kernel.org,
        linux-trace-devel@vger.kernel.org, Ze Gao <zegao@tencent.com>
Subject: [RFC PATCH v2 2/3] perf sched: use the new prev_state_char instead in tracepoint sched_switch
Date:   Wed, 26 Jul 2023 20:16:17 +0800
Message-Id: <20230726121618.19198-3-zegao@tencent.com>
In-Reply-To: <20230726121618.19198-1-zegao@tencent.com>
References: <20230726121618.19198-1-zegao@tencent.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Since the sched_switch tracepoint introduces a new variable to
report sched-out task state in symbolic char, we switch to use
that instead to spare from knowing internal implementations
in kernel.

Signed-off-by: Ze Gao <zegao@tencent.com>
---
 tools/perf/builtin-sched.c | 57 +++++++-------------------------------
 1 file changed, 10 insertions(+), 47 deletions(-)

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index cc4ba506e119..e3b31d526bc8 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -92,24 +92,6 @@ struct sched_atom {
 	struct task_desc	*wakee;
 };
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
-
-/* task state bitmask, copied from include/linux/sched.h */
-#define TASK_RUNNING		0
-#define TASK_INTERRUPTIBLE	1
-#define TASK_UNINTERRUPTIBLE	2
-#define __TASK_STOPPED		4
-#define __TASK_TRACED		8
-/* in tsk->exit_state */
-#define EXIT_DEAD		16
-#define EXIT_ZOMBIE		32
-#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
-/* in tsk->state again */
-#define TASK_DEAD		64
-#define TASK_WAKEKILL		128
-#define TASK_WAKING		256
-#define TASK_PARKED		512
-
 enum thread_state {
 	THREAD_SLEEPING = 0,
 	THREAD_WAIT_CPU,
@@ -266,7 +248,7 @@ struct thread_runtime {
 	u64 total_preempt_time;
 	u64 total_delay_time;
 
-	int last_state;
+	char last_state;
 
 	char shortname[3];
 	bool comm_changed;
@@ -436,7 +418,7 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *t
 }
 
 static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *task,
-				  u64 timestamp, u64 task_state __maybe_unused)
+				  u64 timestamp, char task_state __maybe_unused)
 {
 	struct sched_atom *event = get_new_event(task, timestamp);
 
@@ -860,7 +842,7 @@ static int replay_switch_event(struct perf_sched *sched,
 		   *next_comm  = evsel__strval(evsel, sample, "next_comm");
 	const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
 		  next_pid = evsel__intval(evsel, sample, "next_pid");
-	const u64 prev_state = evsel__intval(evsel, sample, "prev_state");
+	const char prev_state = evsel__intval(evsel, sample, "prev_state_char");
 	struct task_desc *prev, __maybe_unused *next;
 	u64 timestamp0, timestamp = sample->time;
 	int cpu = sample->cpu;
@@ -1050,13 +1032,6 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
 	return 0;
 }
 
-static char sched_out_state(u64 prev_state)
-{
-	const char *str = TASK_STATE_TO_CHAR_STR;
-
-	return str[prev_state];
-}
-
 static int
 add_sched_out_event(struct work_atoms *atoms,
 		    char run_state,
@@ -1132,7 +1107,7 @@ static int latency_switch_event(struct perf_sched *sched,
 {
 	const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
 		  next_pid = evsel__intval(evsel, sample, "next_pid");
-	const u64 prev_state = evsel__intval(evsel, sample, "prev_state");
+	const char prev_state = evsel__intval(evsel, sample, "prev_state_char");
 	struct work_atoms *out_events, *in_events;
 	struct thread *sched_out, *sched_in;
 	u64 timestamp0, timestamp = sample->time;
@@ -1168,7 +1143,7 @@ static int latency_switch_event(struct perf_sched *sched,
 			goto out_put;
 		}
 	}
-	if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp))
+	if (add_sched_out_event(out_events, prev_state, timestamp))
 		return -1;
 
 	in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
@@ -2026,24 +2001,12 @@ static void timehist_header(struct perf_sched *sched)
 	printf("\n");
 }
 
-static char task_state_char(struct thread *thread, int state)
-{
-	static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
-	unsigned bit = state ? ffs(state) : 0;
-
-	/* 'I' for idle */
-	if (thread->tid == 0)
-		return 'I';
-
-	return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
-}
-
 static void timehist_print_sample(struct perf_sched *sched,
 				  struct evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
 				  struct thread *thread,
-				  u64 t, int state)
+				  u64 t, char state)
 {
 	struct thread_runtime *tr = thread__priv(thread);
 	const char *next_comm = evsel__strval(evsel, sample, "next_comm");
@@ -2084,7 +2047,7 @@ static void timehist_print_sample(struct perf_sched *sched,
 	print_sched_time(tr->dt_run, 6);
 
 	if (sched->show_state)
-		printf(" %5c ", task_state_char(thread, state));
+		printf(" %5c ", thread->tid == 0 ? 'I' : state);
 
 	if (sched->show_next) {
 		snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid);
@@ -2156,9 +2119,9 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 		else if (r->last_time) {
 			u64 dt_wait = tprev - r->last_time;
 
-			if (r->last_state == TASK_RUNNING)
+			if (r->last_state == 'R' || r->last_state == 'p')
 				r->dt_preempt = dt_wait;
-			else if (r->last_state == TASK_UNINTERRUPTIBLE)
+			else if (r->last_state == 'D')
 				r->dt_iowait = dt_wait;
 			else
 				r->dt_sleep = dt_wait;
@@ -2575,7 +2538,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	struct thread_runtime *tr = NULL;
 	u64 tprev, t = sample->time;
 	int rc = 0;
-	int state = evsel__intval(evsel, sample, "prev_state");
+	char state = evsel__intval(evsel, sample, "prev_state_char");
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event. skipping it\n",
-- 
2.40.1