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 1/3] sched, tracing: add to report task state in symbolic chars
Date:   Wed, 26 Jul 2023 20:16:16 +0800
Message-Id: <20230726121618.19198-2-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

Internal representations of task state are likely to be changed or
ordered, and reporting them to userspace without exporting them as
part of API is not a good choice, which can easily break a userspace
observability tool as kernel evolves. For example, perf suffers from
this and still reports wrong states by this patch.

OTOH, some masqueraded state like TASK_REPORT_IDLE and TASK_REPORT_MAX
are also reported inadvertently, which confuses things even more.

So add a new variable in company with the old raw value to report task
state in symbolic char, which is self-explaining and no further
translation is needed, and also report priorities in 'short' to save
some buffer space.  Of course this does not break any userspace tool.

Note for PREEMPT_ACTIVE, we introduce 'p' to report it and use the old
conventions for the rest.

Signed-off-by: Ze Gao <zegao@tencent.com>
---
 include/trace/events/sched.h | 60 +++++++++++++++++++++---------------
 1 file changed, 35 insertions(+), 25 deletions(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index fbb99a61f714..0fcf68f49e45 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -6,6 +6,7 @@
 #define _TRACE_SCHED_H
 
 #include <linux/kthread.h>
+#include <linux/sched.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/tracepoint.h>
 #include <linux/binfmts.h>
@@ -214,6 +215,27 @@ static inline long __trace_sched_switch_state(bool preempt,
 
 	return state ? (1 << (state - 1)) : state;
 }
+
+static inline char __trace_sched_switch_state_char(bool preempt,
+						   unsigned int prev_state,
+						   struct task_struct *p)
+{
+	long state;
+
+#ifdef CONFIG_SCHED_DEBUG
+	BUG_ON(p != current);
+#endif /* CONFIG_SCHED_DEBUG */
+
+	/*
+	 * For PREEMPT_ACTIVE, we introduce 'p' to report it and use the old
+	 * conventions for the rest.
+	 */
+	if (preempt)
+		return 'p';
+
+	state = __task_state_index(prev_state, p->exit_state);
+	return task_index_to_char(state);
+}
 #endif /* CREATE_TRACE_POINTS */
 
 /*
@@ -231,41 +253,29 @@ TRACE_EVENT(sched_switch,
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	prev_pid			)
-		__field(	int,	prev_prio			)
-		__field(	long,	prev_state			)
+		__field(	short,	prev_prio			)
+		__field(	int,	prev_state			)
+		__field(	char,	prev_state_char			)
 		__array(	char,	next_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	next_pid			)
-		__field(	int,	next_prio			)
+		__field(	short,	next_prio			)
 	),
 
 	TP_fast_assign(
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
-		__entry->prev_pid	= prev->pid;
-		__entry->prev_prio	= prev->prio;
-		__entry->prev_state	= __trace_sched_switch_state(preempt, prev_state, prev);
+		__entry->prev_pid		= prev->pid;
+		__entry->prev_prio		= (short) prev->prio;
+		__entry->prev_state		= __trace_sched_switch_state(preempt, prev_state, prev);
+		__entry->prev_state_char	= __trace_sched_switch_state_char(preempt, prev_state, prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
-		__entry->next_pid	= next->pid;
-		__entry->next_prio	= next->prio;
+		__entry->next_pid		= next->pid;
+		__entry->next_prio		= (short) next->prio;
 		/* XXX SCHED_DEADLINE */
 	),
 
-	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
-		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
-
-		(__entry->prev_state & (TASK_REPORT_MAX - 1)) ?
-		  __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|",
-				{ TASK_INTERRUPTIBLE, "S" },
-				{ TASK_UNINTERRUPTIBLE, "D" },
-				{ __TASK_STOPPED, "T" },
-				{ __TASK_TRACED, "t" },
-				{ EXIT_DEAD, "X" },
-				{ EXIT_ZOMBIE, "Z" },
-				{ TASK_PARKED, "P" },
-				{ TASK_DEAD, "I" }) :
-		  "R",
-
-		__entry->prev_state & TASK_REPORT_MAX ? "+" : "",
-		__entry->next_comm, __entry->next_pid, __entry->next_prio)
+	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%c ==> next_comm=%s next_pid=%d next_prio=%d",
+		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio, __entry->prev_state_char, __entry->next_comm,
+		__entry->next_pid, __entry->next_prio)
 );
 
 /*
-- 
2.40.1