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

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  sched/tracing: Add a new tracepoint for sleeptime
  sched: Disable scheduler warnings during oopses
  sched: Fix cgroup movement of waking process
  sched: Fix cgroup movement of newly created process
  sched: Fix cgroup movement of forking process
  sched: Remove cfs bandwidth period check in tg_set_cfs_period()
  sched: Fix load-balance lock-breaking
  sched: Replace all_pinned with a generic flags field
  sched: Only queue remote wakeups when crossing cache boundaries
  sched: Add missing rcu_dereference() around ->real_parent usage
  [S390] fix cputime overflow in uptime_proc_show
  [S390] cputime: add sparse checking and cleanup
  sched: Mark parent and real_parent as __rcu
  sched, nohz: Fix missing RCU read lock
  sched, nohz: Set the NOHZ_BALANCE_KICK flag for idle load balancer
  sched, nohz: Fix the idle cpu check in nohz_idle_balance
  sched: Use jump_labels for sched_feat
  sched/accounting: Fix parameter passing in task_group_account_field
  sched/accounting: Fix user/system tick double accounting
  sched/accounting: Re-use scheduler statistics for the root cgroup
  ...

Fix up conflicts in
 - arch/ia64/include/asm/cputime.h, include/asm-generic/cputime.h
	usecs_to_cputime64() vs the sparse cleanups
 - kernel/sched/fair.c, kernel/time/tick-sched.c
	scheduler changes in multiple branches

1 files changed, 57 insertions, 0 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 959ff18b63b6..6ba596b07a72 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -331,6 +331,13 @@ DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
              TP_ARGS(tsk, delay));
 
 /*
+ * Tracepoint for accounting blocked time (time the task is in uninterruptible).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
+             TP_PROTO(struct task_struct *tsk, u64 delay),
+             TP_ARGS(tsk, delay));
+
+/*
  * Tracepoint for accounting runtime (time the task is executing
  * on a CPU).
  */
@@ -363,6 +370,56 @@ TRACE_EVENT(sched_stat_runtime,
                         (unsigned long long)__entry->vruntime)
 );
 
+#ifdef CREATE_TRACE_POINTS
+static inline u64 trace_get_sleeptime(struct task_struct *tsk)
+{
+#ifdef CONFIG_SCHEDSTATS
+        u64 block, sleep;
+
+        block = tsk->se.statistics.block_start;
+        sleep = tsk->se.statistics.sleep_start;
+        tsk->se.statistics.block_start = 0;
+        tsk->se.statistics.sleep_start = 0;
+
+        return block ? block : sleep ? sleep : 0;
+#else
+        return 0;
+#endif
+}
+#endif
+
+/*
+ * Tracepoint for accounting sleeptime (time the task is sleeping
+ * or waiting for I/O).
+ */
+TRACE_EVENT(sched_stat_sleeptime,
+
+        TP_PROTO(struct task_struct *tsk, u64 now),
+
+        TP_ARGS(tsk, now),
+
+        TP_STRUCT__entry(
+                __array( char,  comm,   TASK_COMM_LEN   )
+                __field( pid_t, pid                     )
+                __field( u64,   sleeptime               )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+                __entry->pid            = tsk->pid;
+                __entry->sleeptime = trace_get_sleeptime(tsk);
+                __entry->sleeptime = __entry->sleeptime ?
+                                now - __entry->sleeptime : 0;
+        )
+        TP_perf_assign(
+                __perf_count(__entry->sleeptime);
+        ),
+
+        TP_printk("comm=%s pid=%d sleeptime=%Lu [ns]",
+                        __entry->comm, __entry->pid,
+                        (unsigned long long)__entry->sleeptime)
+);
+
 /*
  * Tracepoint for showing priority inheritance modifying a tasks
  * priority.