1 files changed, 31 insertions, 10 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2404b59b3097..0d88ce9b9fb8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -264,6 +264,7 @@ struct ftrace_profile {
         unsigned long                   counter;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         unsigned long long              time;
+        unsigned long long              time_squared;
 #endif
 };
 
@@ -366,9 +367,9 @@ static int function_stat_headers(struct seq_file *m)
 {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         seq_printf(m, "  Function                               "
-                   "Hit    Time            Avg\n"
+                   "Hit    Time            Avg             s^2\n"
                       "  --------                               "
-                   "---    ----            ---\n");
+                   "---    ----            ---             ---\n");
 #else
         seq_printf(m, "  Function                               Hit\n"
                       "  --------                               ---\n");
@@ -384,6 +385,7 @@ static int function_stat_show(struct seq_file *m, void *v)
         static DEFINE_MUTEX(mutex);
         static struct trace_seq s;
         unsigned long long avg;
+        unsigned long long stddev;
 #endif
 
         kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
@@ -394,11 +396,25 @@ static int function_stat_show(struct seq_file *m, void *v)
         avg = rec->time;
         do_div(avg, rec->counter);
 
+        /* Sample standard deviation (s^2) */
+        if (rec->counter <= 1)
+                stddev = 0;
+        else {
+                stddev = rec->time_squared - rec->counter * avg * avg;
+                /*
+                 * Divide only 1000 for ns^2 -> us^2 conversion.
+                 * trace_print_graph_duration will divide 1000 again.
+                 */
+                do_div(stddev, (rec->counter - 1) * 1000);
+        }
+
         mutex_lock(&mutex);
         trace_seq_init(&s);
         trace_print_graph_duration(rec->time, &s);
         trace_seq_puts(&s, "    ");
         trace_print_graph_duration(avg, &s);
+        trace_seq_puts(&s, "    ");
+        trace_print_graph_duration(stddev, &s);
         trace_print_seq(m, &s);
         mutex_unlock(&mutex);
 #endif
@@ -650,6 +666,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
         if (!stat->hash || !ftrace_profile_enabled)
                 goto out;
 
+        /* If the calltime was zero'd ignore it */
+        if (!trace->calltime)
+                goto out;
+
         calltime = trace->rettime - trace->calltime;
 
         if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
@@ -668,8 +688,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
         }
 
         rec = ftrace_find_profiled_func(stat, trace->func);
-        if (rec)
+        if (rec) {
                 rec->time += calltime;
+                rec->time_squared += calltime * calltime;
+        }
 
  out:
         local_irq_restore(flags);
@@ -1861,7 +1883,6 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
         struct hlist_head *hhd;
         struct hlist_node *n;
         unsigned long key;
-        int resched;
 
         key = hash_long(ip, FTRACE_HASH_BITS);
 
@@ -1875,12 +1896,12 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
          * period. This syncs the hash iteration and freeing of items
          * on the hash. rcu_read_lock is too dangerous here.
          */
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         hlist_for_each_entry_rcu(entry, n, hhd, node) {
                 if (entry->ip == ip)
                         entry->ops->func(ip, parent_ip, &entry->data);
         }
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_probe_ops __read_mostly =
@@ -3212,8 +3233,8 @@ free:
 }
 
 static void
-ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-                                struct task_struct *next)
+ftrace_graph_probe_sched_switch(void *ignore,
+                        struct task_struct *prev, struct task_struct *next)
 {
         unsigned long long timestamp;
         int index;
@@ -3267,7 +3288,7 @@ static int start_graph_tracing(void)
         } while (ret == -EAGAIN);
 
         if (!ret) {
-                ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+                ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
                 if (ret)
                         pr_info("ftrace_graph: Couldn't activate tracepoint"
                                 " probe to kernel_sched_switch\n");
@@ -3339,11 +3360,11 @@ void unregister_ftrace_graph(void)
                 goto out;
 
         ftrace_graph_active--;
-        unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
         ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
         ftrace_graph_entry = ftrace_graph_entry_stub;
         ftrace_shutdown(FTRACE_STOP_FUNC_RET);
         unregister_pm_notifier(&ftrace_suspend_notifier);
+        unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
  out:
         mutex_unlock(&ftrace_lock);