Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (64 commits)
  sched: Fix sched::sched_stat_wait tracepoint field
  sched: Disable NEW_FAIR_SLEEPERS for now
  sched: Keep kthreads at default priority
  sched: Re-tune the scheduler latency defaults to decrease worst-case latencies
  sched: Turn off child_runs_first
  sched: Ensure that a child can't gain time over it's parent after fork()
  sched: enable SD_WAKE_IDLE
  sched: Deal with low-load in wake_affine()
  sched: Remove short cut from select_task_rq_fair()
  sched: Turn on SD_BALANCE_NEWIDLE
  sched: Clean up topology.h
  sched: Fix dynamic power-balancing crash
  sched: Remove reciprocal for cpu_power
  sched: Try to deal with low capacity, fix update_sd_power_savings_stats()
  sched: Try to deal with low capacity
  sched: Scale down cpu_power due to RT tasks
  sched: Implement dynamic cpu_power
  sched: Add smt_gain
  sched: Update the cpu_power sum during load-balance
  sched: Add SD_PREFER_SIBLING
  ...

1 files changed, 95 insertions, 0 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 8949bb7eb082..a4c369ec328f 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -340,6 +340,101 @@ TRACE_EVENT(sched_signal_send,
                   __entry->sig, __entry->comm, __entry->pid)
 );
 
+/*
+ * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
+ *     adding sched_stat support to SCHED_FIFO/RR would be welcome.
+ */
+
+/*
+ * Tracepoint for accounting wait time (time the task is runnable
+ * but not actually running due to scheduler contention).
+ */
+TRACE_EVENT(sched_stat_wait,
+
+        TP_PROTO(struct task_struct *tsk, u64 delay),
+
+        TP_ARGS(tsk, delay),
+
+        TP_STRUCT__entry(
+                __array( char,  comm,   TASK_COMM_LEN   )
+                __field( pid_t, pid                     )
+                __field( u64,   delay                   )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+                __entry->pid    = tsk->pid;
+                __entry->delay  = delay;
+        )
+        TP_perf_assign(
+                __perf_count(delay);
+        ),
+
+        TP_printk("task: %s:%d wait: %Lu [ns]",
+                        __entry->comm, __entry->pid,
+                        (unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting sleep time (time the task is not runnable,
+ * including iowait, see below).
+ */
+TRACE_EVENT(sched_stat_sleep,
+
+        TP_PROTO(struct task_struct *tsk, u64 delay),
+
+        TP_ARGS(tsk, delay),
+
+        TP_STRUCT__entry(
+                __array( char,  comm,   TASK_COMM_LEN   )
+                __field( pid_t, pid                     )
+                __field( u64,   delay                   )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+                __entry->pid    = tsk->pid;
+                __entry->delay  = delay;
+        )
+        TP_perf_assign(
+                __perf_count(delay);
+        ),
+
+        TP_printk("task: %s:%d sleep: %Lu [ns]",
+                        __entry->comm, __entry->pid,
+                        (unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting iowait time (time the task is not runnable
+ * due to waiting on IO to complete).
+ */
+TRACE_EVENT(sched_stat_iowait,
+
+        TP_PROTO(struct task_struct *tsk, u64 delay),
+
+        TP_ARGS(tsk, delay),
+
+        TP_STRUCT__entry(
+                __array( char,  comm,   TASK_COMM_LEN   )
+                __field( pid_t, pid                     )
+                __field( u64,   delay                   )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+                __entry->pid    = tsk->pid;
+                __entry->delay  = delay;
+        )
+        TP_perf_assign(
+                __perf_count(delay);
+        ),
+
+        TP_printk("task: %s:%d iowait: %Lu [ns]",
+                        __entry->comm, __entry->pid,
+                        (unsigned long long)__entry->delay)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */