tracing: Format non-nanosec times from tsc clock without a decimal point.

With the addition of the "tsc" clock, formatting timestamps to look like
fractional seconds is misleading. Mark clocks as either in nanoseconds or
not, and format non-nanosecond timestamps as decimal integers.

Tested:
$ cd /sys/kernel/debug/tracing/
$ cat trace_clock
[local] global tsc
$ echo sched_switch > set_event
$ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on
$ cat trace
          <idle>-0     [000]  6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120
           sleep-29964 [000]  6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
$ echo 1 > options/latency-format
$ cat trace
  <idle>-0       0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120
   sleep-29964   0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
$ echo tsc > trace_clock
$ cat trace
$ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on
$ echo 0 > options/latency-format
$ cat trace
          <idle>-0     [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120
           sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
echo 1 > options/latency-format
$ cat trace
  <idle>-0       0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120
   sleep-31128   0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...

v2:
Move arch-specific bits out of generic code.
v4:
Fix x86_32 build due to 64-bit division.

Google-Bug-Id: 6980623
Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com

Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: David Sharp <dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 12 insertions, 3 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0d20620c0d27..d943e69569cd 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -484,10 +484,11 @@ static const char *trace_options[] = {
 static struct {
         u64 (*func)(void);
         const char *name;
+        int in_ns;              /* is this clock in nanoseconds? */
 } trace_clocks[] = {
-        { trace_clock_local,    "local" },
-        { trace_clock_global,   "global" },
-        { trace_clock_counter,  "counter" },
+        { trace_clock_local,    "local",        1 },
+        { trace_clock_global,   "global",       1 },
+        { trace_clock_counter,  "counter",      0 },
         ARCH_TRACE_CLOCKS
 };
 
@@ -2478,6 +2479,10 @@ __tracing_open(struct inode *inode, struct file *file)
         if (ring_buffer_overruns(iter->tr->buffer))
                 iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
+        /* Output in nanoseconds only if we are using a clock in nanoseconds. */
+        if (trace_clocks[trace_clock_id].in_ns)
+                iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
         /* stop the trace while dumping */
         tracing_stop();
 
@@ -3339,6 +3344,10 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
         if (trace_flags & TRACE_ITER_LATENCY_FMT)
                 iter->iter_flags |= TRACE_FILE_LAT_FMT;
 
+        /* Output in nanoseconds only if we are using a clock in nanoseconds. */
+        if (trace_clocks[trace_clock_id].in_ns)
+                iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
         iter->cpu_file = cpu_file;
         iter->tr = &global_trace;
         mutex_init(&iter->mutex);