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

Pull scheduler updates from Ingo Molnar:
 "The biggest change in this cycle is the rewrite of the main SMP load
  balancing metric: the CPU load/utilization.  The main goal was to make
  the metric more precise and more representative - see the changelog of
  this commit for the gory details:

    9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking")

  It is done in a way that significantly reduces complexity of the code:

    5 files changed, 249 insertions(+), 494 deletions(-)

  and the performance testing results are encouraging.  Nevertheless we
  need to keep an eye on potential regressions, since this potentially
  affects every SMP workload in existence.

  This work comes from Yuyang Du.

  Other changes:

   - SCHED_DL updates.  (Andrea Parri)

   - Simplify architecture callbacks by removing finish_arch_switch().
     (Peter Zijlstra et al)

   - cputime accounting: guarantee stime + utime == rtime.  (Peter
     Zijlstra)

   - optimize idle CPU wakeups some more - inspired by Facebook server
     loads.  (Mike Galbraith)

   - stop_machine fixes and updates.  (Oleg Nesterov)

   - Introduce the 'trace_sched_waking' tracepoint.  (Peter Zijlstra)

   - sched/numa tweaks.  (Srikar Dronamraju)

   - misc fixes and small cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  sched/deadline: Fix comment in enqueue_task_dl()
  sched/deadline: Fix comment in push_dl_tasks()
  sched: Change the sched_class::set_cpus_allowed() calling context
  sched: Make sched_class::set_cpus_allowed() unconditional
  sched: Fix a race between __kthread_bind() and sched_setaffinity()
  sched: Ensure a task has a non-normalized vruntime when returning back to CFS
  sched/numa: Fix NUMA_DIRECT topology identification
  tile: Reorganize _switch_to()
  sched, sparc32: Update scheduler comments in copy_thread()
  sched: Remove finish_arch_switch()
  sched, tile: Remove finish_arch_switch
  sched, sh: Fold finish_arch_switch() into switch_to()
  sched, score: Remove finish_arch_switch()
  sched, avr32: Remove finish_arch_switch()
  sched, MIPS: Get rid of finish_arch_switch()
  sched, arm: Remove finish_arch_switch()
  sched/fair: Clean up load average references
  sched/fair: Provide runnable_load_avg back to cfs_rq
  sched/fair: Remove task and group entity load when they are dead
  sched/fair: Init cfs_rq's sched_entity load average
  ...

1 files changed, 60 insertions, 41 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index f5a64ff..8cbc3db 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -555,48 +555,43 @@ drop_precision:
 }
 
 /*
- * Atomically advance counter to the new value. Interrupts, vcpu
- * scheduling, and scaling inaccuracies can cause cputime_advance
- * to be occasionally called with a new value smaller than counter.
- * Let's enforce atomicity.
+ * Adjust tick based cputime random precision against scheduler runtime
+ * accounting.
  *
- * Normally a caller will only go through this loop once, or not
- * at all in case a previous caller updated counter the same jiffy.
- */
-static void cputime_advance(cputime_t *counter, cputime_t new)
-{
-	cputime_t old;
-
-	while (new > (old = READ_ONCE(*counter)))
-		cmpxchg_cputime(counter, old, new);
-}
-
-/*
- * Adjust tick based cputime random precision against scheduler
- * runtime accounting.
+ * Tick based cputime accounting depend on random scheduling timeslices of a
+ * task to be interrupted or not by the timer.  Depending on these
+ * circumstances, the number of these interrupts may be over or
+ * under-optimistic, matching the real user and system cputime with a variable
+ * precision.
+ *
+ * Fix this by scaling these tick based values against the total runtime
+ * accounted by the CFS scheduler.
+ *
+ * This code provides the following guarantees:
+ *
+ *   stime + utime == rtime
+ *   stime_i+1 >= stime_i, utime_i+1 >= utime_i
+ *
+ * Assuming that rtime_i+1 >= rtime_i.
  */
 static void cputime_adjust(struct task_cputime *curr,
-			   struct cputime *prev,
+			   struct prev_cputime *prev,
 			   cputime_t *ut, cputime_t *st)
 {
 	cputime_t rtime, stime, utime;
+	unsigned long flags;
 
-	/*
-	 * Tick based cputime accounting depend on random scheduling
-	 * timeslices of a task to be interrupted or not by the timer.
-	 * Depending on these circumstances, the number of these interrupts
-	 * may be over or under-optimistic, matching the real user and system
-	 * cputime with a variable precision.
-	 *
-	 * Fix this by scaling these tick based values against the total
-	 * runtime accounted by the CFS scheduler.
-	 */
+	/* Serialize concurrent callers such that we can honour our guarantees */
+	raw_spin_lock_irqsave(&prev->lock, flags);
 	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
 
 	/*
-	 * Update userspace visible utime/stime values only if actual execution
-	 * time is bigger than already exported. Note that can happen, that we
-	 * provided bigger values due to scaling inaccuracy on big numbers.
+	 * This is possible under two circumstances:
+	 *  - rtime isn't monotonic after all (a bug);
+	 *  - we got reordered by the lock.
+	 *
+	 * In both cases this acts as a filter such that the rest of the code
+	 * can assume it is monotonic regardless of anything else.
 	 */
 	if (prev->stime + prev->utime >= rtime)
 		goto out;
@@ -606,22 +601,46 @@ static void cputime_adjust(struct task_cputime *curr,
 
 	if (utime == 0) {
 		stime = rtime;
-	} else if (stime == 0) {
-		utime = rtime;
-	} else {
-		cputime_t total = stime + utime;
+		goto update;
+	}
 
-		stime = scale_stime((__force u64)stime,
-				    (__force u64)rtime, (__force u64)total);
-		utime = rtime - stime;
+	if (stime == 0) {
+		utime = rtime;
+		goto update;
 	}
 
-	cputime_advance(&prev->stime, stime);
-	cputime_advance(&prev->utime, utime);
+	stime = scale_stime((__force u64)stime, (__force u64)rtime,
+			    (__force u64)(stime + utime));
+
+	/*
+	 * Make sure stime doesn't go backwards; this preserves monotonicity
+	 * for utime because rtime is monotonic.
+	 *
+	 *  utime_i+1 = rtime_i+1 - stime_i
+	 *            = rtime_i+1 - (rtime_i - utime_i)
+	 *            = (rtime_i+1 - rtime_i) + utime_i
+	 *            >= utime_i
+	 */
+	if (stime < prev->stime)
+		stime = prev->stime;
+	utime = rtime - stime;
+
+	/*
+	 * Make sure utime doesn't go backwards; this still preserves
+	 * monotonicity for stime, analogous argument to above.
+	 */
+	if (utime < prev->utime) {
+		utime = prev->utime;
+		stime = rtime - utime;
+	}
 
+update:
+	prev->stime = stime;
+	prev->utime = utime;
 out:
 	*ut = prev->utime;
 	*st = prev->stime;
+	raw_spin_unlock_irqrestore(&prev->lock, flags);
 }
 
 void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)