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

[safe/jmp/linux-2.6] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index 076e403..14c447a 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -72,13 +72,15 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
-#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
 
 #include "sched_cpupri.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
@@ -118,12 +120,6 @@
  */
 #define RUNTIME_INF    ((u64)~0ULL)
 
-DEFINE_TRACE(sched_wait_task);
-DEFINE_TRACE(sched_wakeup);
-DEFINE_TRACE(sched_wakeup_new);
-DEFINE_TRACE(sched_switch);
-DEFINE_TRACE(sched_migrate_task);
-
 #ifdef CONFIG_SMP
 
 static void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -1964,7 +1960,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
        clock_offset = old_rq->clock - new_rq->clock;
 
-       trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+       trace_sched_migrate_task(p, new_cpu);
 
 #ifdef CONFIG_SCHEDSTATS
        if (p->se.wait_start)
@@ -2021,6 +2017,49 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 }
 
 /*
+ * wait_task_context_switch -  wait for a thread to complete at least one
+ *                             context switch.
+ *
+ * @p must not be current.
+ */
+void wait_task_context_switch(struct task_struct *p)
+{
+       unsigned long nvcsw, nivcsw, flags;
+       int running;
+       struct rq *rq;
+
+       nvcsw   = p->nvcsw;
+       nivcsw  = p->nivcsw;
+       for (;;) {
+               /*
+                * The runqueue is assigned before the actual context
+                * switch. We need to take the runqueue lock.
+                *
+                * We could check initially without the lock but it is
+                * very likely that we need to take the lock in every
+                * iteration.
+                */
+               rq = task_rq_lock(p, &flags);
+               running = task_running(rq, p);
+               task_rq_unlock(rq, &flags);
+
+               if (likely(!running))
+                       break;
+               /*
+                * The switch count is incremented before the actual
+                * context switch. We thus wait for two switches to be
+                * sure at least one completed.
+                */
+               if ((p->nvcsw - nvcsw) > 1)
+                       break;
+               if ((p->nivcsw - nivcsw) > 1)
+                       break;
+
+               cpu_relax();
+       }
+}
+
+/*
  * wait_task_inactive - wait for a thread to unschedule.
  *
  * If @match_state is nonzero, it's the @p->state value just checked and