Merge branch 'tracing/ftrace' into auto-ftrace-next

[mv-sheeva.git] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index 4a3cb0614158b5e99fb24ccbab906d641e8d56d5..42899dce837d6f27a5f90db3d2037c2ff0a05489 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -70,6 +70,7 @@
 #include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
+#include <linux/ftrace.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -607,6 +608,24 @@ static inline void update_rq_clock(struct rq *rq)
 # define const_debug static const
 #endif
 
+/**
+ * runqueue_is_locked
+ *
+ * Returns true if the current cpu runqueue is locked.
+ * This interface allows printk to be called with the runqueue lock
+ * held and know whether or not it is OK to wake up the klogd.
+ */
+int runqueue_is_locked(void)
+{
+       int cpu = get_cpu();
+       struct rq *rq = cpu_rq(cpu);
+       int ret;
+
+       ret = spin_is_locked(&rq->lock);
+       put_cpu();
+       return ret;
+}
+
 /*
  * Debugging: various feature bits
  */
@@ -831,7 +850,7 @@ static unsigned long long __cpu_clock(int cpu)
  * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
  * clock constructed from sched_clock():
  */
-unsigned long long cpu_clock(int cpu)
+unsigned long long notrace cpu_clock(int cpu)
 {
        unsigned long long prev_cpu_time, time, delta_time;
        unsigned long flags;
@@ -2149,6 +2168,9 @@ out_activate:
        success = 1;
 
 out_running:
+       trace_mark(kernel_sched_wakeup,
+               "pid %d state %ld ## rq %p task %p rq->curr %p",
+               p->pid, p->state, rq, p, rq->curr);
        check_preempt_curr(rq, p);
 
        p->state = TASK_RUNNING;
@@ -2279,6 +2301,9 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
                p->sched_class->task_new(rq, p);
                inc_nr_running(p, rq);
        }
+       trace_mark(kernel_sched_wakeup_new,
+               "pid %d state %ld ## rq %p task %p rq->curr %p",
+               p->pid, p->state, rq, p, rq->curr);
        check_preempt_curr(rq, p);
 #ifdef CONFIG_SMP
        if (p->sched_class->task_wake_up)
@@ -2451,6 +2476,11 @@ context_switch(struct rq *rq, struct task_struct *prev,
        struct mm_struct *mm, *oldmm;
 
        prepare_task_switch(rq, prev, next);
+       trace_mark(kernel_sched_schedule,
+               "prev_pid %d next_pid %d prev_state %ld "
+               "## rq %p prev %p next %p",
+               prev->pid, next->pid, prev->state,
+               rq, prev, next);
        mm = next->mm;
        oldmm = prev->active_mm;
        /*
@@ -4021,26 +4051,44 @@ void scheduler_tick(void)
 #endif
 }
 
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+                               defined(CONFIG_PREEMPT_TRACER))
+
+static inline unsigned long get_parent_ip(unsigned long addr)
+{
+       if (in_lock_functions(addr)) {
+               addr = CALLER_ADDR2;
+               if (in_lock_functions(addr))
+                       addr = CALLER_ADDR3;
+       }
+       return addr;
+}
 
 void __kprobes add_preempt_count(int val)
 {
+#ifdef CONFIG_DEBUG_PREEMPT
        /*
         * Underflow?
         */
        if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
                return;
+#endif
        preempt_count() += val;
+#ifdef CONFIG_DEBUG_PREEMPT
        /*
         * Spinlock count overflowing soon?
         */
        DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
                                PREEMPT_MASK - 10);
+#endif
+       if (preempt_count() == val)
+               trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
 EXPORT_SYMBOL(add_preempt_count);
 
 void __kprobes sub_preempt_count(int val)
 {
+#ifdef CONFIG_DEBUG_PREEMPT
        /*
         * Underflow?
         */
@@ -4052,7 +4100,10 @@ void __kprobes sub_preempt_count(int val)
        if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
                        !(preempt_count() & PREEMPT_MASK)))
                return;
+#endif
 
+       if (preempt_count() == val)
+               trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
        preempt_count() -= val;
 }
 EXPORT_SYMBOL(sub_preempt_count);
@@ -4398,22 +4449,20 @@ do_wait_for_common(struct completion *x, long timeout, int state)
                             signal_pending(current)) ||
                            (state == TASK_KILLABLE &&
                             fatal_signal_pending(current))) {
-                               __remove_wait_queue(&x->wait, &wait);
-                               return -ERESTARTSYS;
+                               timeout = -ERESTARTSYS;
+                               break;
                        }
                        __set_current_state(state);
                        spin_unlock_irq(&x->wait.lock);
                        timeout = schedule_timeout(timeout);
                        spin_lock_irq(&x->wait.lock);
-                       if (!timeout) {
-                               __remove_wait_queue(&x->wait, &wait);
-                               return timeout;
-                       }
-               } while (!x->done);
+               } while (!x->done && timeout);
                __remove_wait_queue(&x->wait, &wait);
+               if (!x->done)
+                       return timeout;
        }
        x->done--;
-       return timeout;
+       return timeout ?: 1;
 }
 
 static long __sched
@@ -5386,7 +5435,7 @@ out_unlock:
        return retval;
 }
 
-static const char stat_nam[] = "RSDTtZX";
+static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
 
 void sched_show_task(struct task_struct *p)
 {
@@ -5889,6 +5938,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
                next = pick_next_task(rq, rq->curr);
                if (!next)
                        break;
+               next->sched_class->put_prev_task(rq, next);
                migrate_dead(dead_cpu, next);
 
        }
@@ -6879,7 +6929,12 @@ static int default_relax_domain_level = -1;
 
 static int __init setup_relax_domain_level(char *str)
 {
-       default_relax_domain_level = simple_strtoul(str, NULL, 0);
+       unsigned long val;
+
+       val = simple_strtoul(str, NULL, 0);
+       if (val < SD_LV_MAX)
+               default_relax_domain_level = val;
+
        return 1;
 }
 __setup("relax_domain_level=", setup_relax_domain_level);
@@ -8498,6 +8553,9 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
        rt_period = (u64)rt_period_us * NSEC_PER_USEC;
        rt_runtime = tg->rt_bandwidth.rt_runtime;
 
+       if (rt_period == 0)
+               return -EINVAL;
+
        return tg_set_bandwidth(tg, rt_period, rt_runtime);
 }