Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Thomas Gleixner:
 "The scheduler pull request comes with the following updates:

   - Prevent a divide by zero issue by validating the input value of
     sysctl_sched_time_avg

   - Make task state printing consistent all over the place and have
     explicit state characters for IDLE and PARKED so they wont be
     displayed as 'D' state which confuses tools"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/sysctl: Check user input value of sysctl_sched_time_avg
  sched/debug: Add explicit TASK_PARKED printing
  sched/debug: Ignore TASK_IDLE for SysRq-W
  sched/debug: Add explicit TASK_IDLE printing
  sched/tracing: Use common task-state helpers
  sched/tracing: Fix trace_sched_switch task-state printing
  sched/debug: Remove unused variable
  sched/debug: Convert TASK_state to hex
  sched/debug: Implement consistent task-state printing

2 files changed, 52 insertions, 31 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 92fb8dd5a9e4..26a7df4e558c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -65,25 +65,23 @@ struct task_group;
  */
 
 /* Used in tsk->state: */
-#define TASK_RUNNING			0
-#define TASK_INTERRUPTIBLE		1
-#define TASK_UNINTERRUPTIBLE		2
-#define __TASK_STOPPED			4
-#define __TASK_TRACED			8
+#define TASK_RUNNING			0x0000
+#define TASK_INTERRUPTIBLE		0x0001
+#define TASK_UNINTERRUPTIBLE		0x0002
+#define __TASK_STOPPED			0x0004
+#define __TASK_TRACED			0x0008
 /* Used in tsk->exit_state: */
-#define EXIT_DEAD			16
-#define EXIT_ZOMBIE			32
+#define EXIT_DEAD			0x0010
+#define EXIT_ZOMBIE			0x0020
 #define EXIT_TRACE			(EXIT_ZOMBIE | EXIT_DEAD)
 /* Used in tsk->state again: */
-#define TASK_DEAD			64
-#define TASK_WAKEKILL			128
-#define TASK_WAKING			256
-#define TASK_PARKED			512
-#define TASK_NOLOAD			1024
-#define TASK_NEW			2048
-#define TASK_STATE_MAX			4096
-
-#define TASK_STATE_TO_CHAR_STR		"RSDTtXZxKWPNn"
+#define TASK_PARKED			0x0040
+#define TASK_DEAD			0x0080
+#define TASK_WAKEKILL			0x0100
+#define TASK_WAKING			0x0200
+#define TASK_NOLOAD			0x0400
+#define TASK_NEW			0x0800
+#define TASK_STATE_MAX			0x1000
 
 /* Convenience macros for the sake of set_current_state: */
 #define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
@@ -99,7 +97,8 @@ struct task_group;
 /* get_task_state(): */
 #define TASK_REPORT			(TASK_RUNNING | TASK_INTERRUPTIBLE | \
 					 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
-					 __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)
+					 __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \
+					 TASK_PARKED)
 
 #define task_is_traced(task)		((task->state & __TASK_TRACED) != 0)
 
@@ -1243,17 +1242,34 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 	return task_pgrp_nr_ns(tsk, &init_pid_ns);
 }
 
-static inline char task_state_to_char(struct task_struct *task)
+#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_IDLE)
+		state = TASK_REPORT_IDLE;
+
+	return fls(state);
+}
+
+static inline char __task_state_to_char(unsigned int state)
 {
-	const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
-	unsigned long state = task->state;
+	static const char state_char[] = "RSDTtXZPI";
 
-	state = state ? __ffs(state) + 1 : 0;
+	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1);
 
-	/* Make sure the string lines up properly with the number of task states: */
-	BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1);
+	return state_char[state];
+}
 
-	return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?';
+static inline char task_state_to_char(struct task_struct *tsk)
+{
+	return __task_state_to_char(__get_task_state(tsk));
 }
 
 /**
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index ae1409ffe99a..3c8b7f625670 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -114,7 +114,10 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
 	 * Preemption ignores task state, therefore preempted tasks are always
 	 * RUNNING (we will not have dequeued if state != RUNNING).
 	 */
-	return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state;
+	if (preempt)
+		return TASK_STATE_MAX;
+
+	return __get_task_state(p);
 }
 #endif /* CREATE_TRACE_POINTS */
 
@@ -152,12 +155,14 @@ 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_STATE_MAX-1) ?
-		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
-				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
-				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
-				{ 128, "K" }, { 256, "W" }, { 512, "P" },
-				{ 1024, "N" }) : "R",
+
+		(__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" },
+				{ 0x40, "P" }, { 0x80, "I" }) :
+		  "R",
+
 		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );