sched/debug: Add explicit TASK_IDLE printing

Markus reported that kthreads that idle using TASK_IDLE instead of
TASK_INTERRUPTIBLE are reported in as TASK_UNINTERRUPTIBLE and things
like htop mark those red.

This is undesirable, so add an explicit state for TASK_IDLE.

Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 01196d3..a120a45 100644 (file)
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -119,18 +119,23 @@ static inline void task_name(struct seq_file *m, struct task_struct *p)
  * simple bit tests.
  */
 static const char * const task_state_array[] = {
-       "R (running)",          /*   0 */
-       "S (sleeping)",         /*   1 */
-       "D (disk sleep)",       /*   2 */
-       "T (stopped)",          /*   4 */
-       "t (tracing stop)",     /*   8 */
-       "X (dead)",             /*  16 */
-       "Z (zombie)",           /*  32 */
+
+       /* states in TASK_REPORT: */
+       "R (running)",          /* 0x00 */
+       "S (sleeping)",         /* 0x01 */
+       "D (disk sleep)",       /* 0x02 */
+       "T (stopped)",          /* 0x04 */
+       "t (tracing stop)",     /* 0x08 */
+       "X (dead)",             /* 0x10 */
+       "Z (zombie)",           /* 0x20 */
+
+       /* states beyond TASK_REPORT: */
+       "I (idle)",             /* 0x40 */
 };
 
 static inline const char *get_task_state(struct task_struct *tsk)
 {
-       BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array) - 1);
+       BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array));
        return task_state_array[__get_task_state(tsk)];
 }
 

diff --git a/include/linux/sched.h b/include/linux/sched.h
index bc78079..286fc11 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1241,22 +1241,30 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
        return task_pgrp_nr_ns(tsk, &init_pid_ns);
 }
 
+#define TASK_REPORT_IDLE       (TASK_REPORT + 1)
+#define TASK_REPORT_MAX                (TASK_REPORT_IDLE << 1)
+
 static inline unsigned int __get_task_state(struct task_struct *tsk)
 {
        unsigned int tsk_state = READ_ONCE(tsk->state);
        unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
 
+       BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
+
        if (tsk_state == TASK_PARKED)
                state = TASK_INTERRUPTIBLE;
 
+       if (tsk_state == TASK_IDLE)
+               state = TASK_REPORT_IDLE;
+
        return fls(state);
 }
 
 static inline char __task_state_to_char(unsigned int state)
 {
-       static const char state_char[] = "RSDTtXZ";
+       static const char state_char[] = "RSDTtXZI";
 
-       BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != sizeof(state_char) - 2);
+       BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1);
 
        return state_char[state];
 }

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index c63e20c..b371ef8 100644 (file)
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -156,10 +156,11 @@ TRACE_EVENT(sched_switch,
        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) ?
-                 __print_flags(__entry->prev_state & TASK_REPORT, "|",
+               (__entry->prev_state & (TASK_REPORT_MAX - 1)) ?
+                 __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|",
                                { 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" },
-                               { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" }) :
+                               { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" },
+                               { 0x40, "I" }) :
                  "R",
 
                __entry->prev_state & TASK_STATE_MAX ? "+" : "",