summaryrefslogtreecommitdiffstats
path: root/kernel/trace/ftrace.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace/ftrace.c')
-rw-r--r--kernel/trace/ftrace.c64
1 files changed, 44 insertions, 20 deletions
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 83783579378f..32837e19e3bd 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -24,9 +24,11 @@
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/sysctl.h>
+#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/hash.h>
+#include <linux/rcupdate.h>
#include <trace/events/sched.h>
@@ -84,22 +86,22 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
-#endif
-
+/*
+ * Traverse the ftrace_list, invoking all entries. The reason that we
+ * can use rcu_dereference_raw() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism. The rcu_dereference_raw() calls are needed to handle
+ * concurrent insertions into the ftrace_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
- struct ftrace_ops *op = ftrace_list;
-
- /* in case someone actually ports this to alpha! */
- read_barrier_depends();
+ struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/
while (op != &ftrace_list_end) {
- /* silly alpha */
- read_barrier_depends();
op->func(ip, parent_ip);
- op = op->next;
+ op = rcu_dereference_raw(op->next); /*see above*/
};
}
@@ -154,8 +156,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
* the ops->next pointer is valid before another CPU sees
* the ops pointer included into the ftrace_list.
*/
- smp_wmb();
- ftrace_list = ops;
+ rcu_assign_pointer(ftrace_list, ops);
if (ftrace_enabled) {
ftrace_func_t func;
@@ -263,6 +264,7 @@ struct ftrace_profile {
unsigned long counter;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
unsigned long long time;
+ unsigned long long time_squared;
#endif
};
@@ -365,9 +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");
@@ -383,6 +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);
@@ -393,11 +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
@@ -649,6 +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)) {
@@ -667,8 +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);
@@ -2276,6 +2299,8 @@ __setup("ftrace_filter=", set_ftrace_filter);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+
static int __init set_graph_function(char *str)
{
strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -3209,8 +3234,7 @@ free:
}
static void
-ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
- struct task_struct *next)
+ftrace_graph_probe_sched_switch(struct task_struct *prev, struct task_struct *next)
{
unsigned long long timestamp;
int index;
@@ -3336,11 +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);
out:
mutex_unlock(&ftrace_lock);
@@ -3351,6 +3375,7 @@ void ftrace_graph_init_task(struct task_struct *t)
{
/* Make sure we do not use the parent ret_stack */
t->ret_stack = NULL;
+ t->curr_ret_stack = -1;
if (ftrace_graph_active) {
struct ftrace_ret_stack *ret_stack;
@@ -3360,7 +3385,6 @@ void ftrace_graph_init_task(struct task_struct *t)
GFP_KERNEL);
if (!ret_stack)
return;
- t->curr_ret_stack = -1;
atomic_set(&t->tracing_graph_pause, 0);
atomic_set(&t->trace_overrun, 0);
t->ftrace_timestamp = 0;
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-18 14:01:04 +0100