[PATCH v8 06/37] ring-buffer: Redefine the unimplemented RINGBUF_TYPE_TIME_STAMP
From: Tom Zanussi
Date: Thu Dec 21 2017 - 11:14:09 EST
RINGBUF_TYPE_TIME_STAMP is defined but not used, and from what I can
gather was reserved for something like an absolute timestamp feature
for the ring buffer, if not a complete replacement of the current
time_delta scheme.
This code redefines RINGBUF_TYPE_TIME_STAMP to implement absolute time
stamps. Another way to look at it is that it essentially forces
extended time_deltas for all events.
The motivation for doing this is to enable time_deltas that aren't
dependent on previous events in the ring buffer, making it feasible to
use the ring_buffer_event timetamps in a more random-access way, for
purposes other than serial event printing.
To set/reset this mode, use tracing_set_timestamp_abs() from the
previous interface patch.
Signed-off-by: Tom Zanussi <tom.zanussi@xxxxxxxxxxxxxxx>
---
include/linux/ring_buffer.h | 12 ++---
kernel/trace/ring_buffer.c | 104 ++++++++++++++++++++++++++++++++------------
2 files changed, 83 insertions(+), 33 deletions(-)
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 42b626a..b37a5df 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -34,10 +34,12 @@ struct ring_buffer_event {
* array[0] = time delta (28 .. 59)
* size = 8 bytes
*
- * @RINGBUF_TYPE_TIME_STAMP: Sync time stamp with external clock
- * array[0] = tv_nsec
- * array[1..2] = tv_sec
- * size = 16 bytes
+ * @RINGBUF_TYPE_TIME_STAMP: Absolute timestamp
+ * Same format as TIME_EXTEND except that the
+ * value is an absolute timestamp, not a delta
+ * event.time_delta contains bottom 27 bits
+ * array[0] = top (28 .. 59) bits
+ * size = 8 bytes
*
* <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX:
* Data record
@@ -54,12 +56,12 @@ enum ring_buffer_type {
RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28,
RINGBUF_TYPE_PADDING,
RINGBUF_TYPE_TIME_EXTEND,
- /* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
RINGBUF_TYPE_TIME_STAMP,
};
unsigned ring_buffer_event_length(struct ring_buffer_event *event);
void *ring_buffer_event_data(struct ring_buffer_event *event);
+u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event);
/*
* ring_buffer_discard_commit will remove an event that has not
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f57df6f..dd35424 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -41,6 +41,8 @@ int ring_buffer_print_entry_header(struct trace_seq *s)
RINGBUF_TYPE_PADDING);
trace_seq_printf(s, "\ttime_extend : type == %d\n",
RINGBUF_TYPE_TIME_EXTEND);
+ trace_seq_printf(s, "\ttime_stamp : type == %d\n",
+ RINGBUF_TYPE_TIME_STAMP);
trace_seq_printf(s, "\tdata max type_len == %d\n",
RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
@@ -140,12 +142,15 @@ int ring_buffer_print_entry_header(struct trace_seq *s)
enum {
RB_LEN_TIME_EXTEND = 8,
- RB_LEN_TIME_STAMP = 16,
+ RB_LEN_TIME_STAMP = 8,
};
#define skip_time_extend(event) \
((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND))
+#define extended_time(event) \
+ (event->type_len >= RINGBUF_TYPE_TIME_EXTEND)
+
static inline int rb_null_event(struct ring_buffer_event *event)
{
return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
@@ -209,7 +214,7 @@ static void rb_event_set_padding(struct ring_buffer_event *event)
{
unsigned len = 0;
- if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
+ if (extended_time(event)) {
/* time extends include the data event after it */
len = RB_LEN_TIME_EXTEND;
event = skip_time_extend(event);
@@ -231,7 +236,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event)
{
unsigned length;
- if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ if (extended_time(event))
event = skip_time_extend(event);
length = rb_event_length(event);
@@ -248,7 +253,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event)
static __always_inline void *
rb_event_data(struct ring_buffer_event *event)
{
- if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ if (extended_time(event))
event = skip_time_extend(event);
BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
/* If length is in len field, then array[0] has the data */
@@ -275,6 +280,27 @@ void *ring_buffer_event_data(struct ring_buffer_event *event)
#define TS_MASK ((1ULL << TS_SHIFT) - 1)
#define TS_DELTA_TEST (~TS_MASK)
+/**
+ * ring_buffer_event_time_stamp - return the event's extended timestamp
+ * @event: the event to get the timestamp of
+ *
+ * Returns the extended timestamp associated with a data event.
+ * An extended time_stamp is a 64-bit timestamp represented
+ * internally in a special way that makes the best use of space
+ * contained within a ring buffer event. This function decodes
+ * it and maps it to a straight u64 value.
+ */
+u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event)
+{
+ u64 ts;
+
+ ts = event->array[0];
+ ts <<= TS_SHIFT;
+ ts += event->time_delta;
+
+ return ts;
+}
+
/* Flag when events were overwritten */
#define RB_MISSED_EVENTS (1 << 31)
/* Missed count stored at end */
@@ -2213,12 +2239,15 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
/* Slow path, do not inline */
static noinline struct ring_buffer_event *
-rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
+rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
{
- event->type_len = RINGBUF_TYPE_TIME_EXTEND;
+ if (abs)
+ event->type_len = RINGBUF_TYPE_TIME_STAMP;
+ else
+ event->type_len = RINGBUF_TYPE_TIME_EXTEND;
- /* Not the first event on the page? */
- if (rb_event_index(event)) {
+ /* Not the first event on the page, or not delta? */
+ if (abs || rb_event_index(event)) {
event->time_delta = delta & TS_MASK;
event->array[0] = delta >> TS_SHIFT;
} else {
@@ -2261,7 +2290,9 @@ static inline bool rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
* add it to the start of the resevered space.
*/
if (unlikely(info->add_timestamp)) {
- event = rb_add_time_stamp(event, delta);
+ bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer);
+
+ event = rb_add_time_stamp(event, info->delta, abs);
length -= RB_LEN_TIME_EXTEND;
delta = 0;
}
@@ -2449,7 +2480,7 @@ static __always_inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer
static inline void rb_event_discard(struct ring_buffer_event *event)
{
- if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ if (extended_time(event))
event = skip_time_extend(event);
/* array[0] holds the actual length for the discarded event */
@@ -2493,10 +2524,11 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
cpu_buffer->write_stamp =
cpu_buffer->commit_page->page->time_stamp;
else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
- delta = event->array[0];
- delta <<= TS_SHIFT;
- delta += event->time_delta;
+ delta = ring_buffer_event_time_stamp(event);
cpu_buffer->write_stamp += delta;
+ } else if (event->type_len == RINGBUF_TYPE_TIME_STAMP) {
+ delta = ring_buffer_event_time_stamp(event);
+ cpu_buffer->write_stamp = delta;
} else
cpu_buffer->write_stamp += event->time_delta;
}
@@ -2649,7 +2681,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
* If this is the first commit on the page, then it has the same
* timestamp as the page itself.
*/
- if (!tail)
+ if (!tail && !ring_buffer_time_stamp_abs(cpu_buffer->buffer))
info->delta = 0;
/* See if we shot pass the end of this buffer page */
@@ -2726,8 +2758,11 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
/* make sure this diff is calculated here */
barrier();
- /* Did the write stamp get updated already? */
- if (likely(info.ts >= cpu_buffer->write_stamp)) {
+ if (ring_buffer_time_stamp_abs(buffer)) {
+ info.delta = info.ts;
+ rb_handle_timestamp(cpu_buffer, &info);
+ } else /* Did the write stamp get updated already? */
+ if (likely(info.ts >= cpu_buffer->write_stamp)) {
info.delta = diff;
if (unlikely(test_time_stamp(info.delta)))
rb_handle_timestamp(cpu_buffer, &info);
@@ -3409,14 +3444,13 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
return;
case RINGBUF_TYPE_TIME_EXTEND:
- delta = event->array[0];
- delta <<= TS_SHIFT;
- delta += event->time_delta;
+ delta = ring_buffer_event_time_stamp(event);
cpu_buffer->read_stamp += delta;
return;
case RINGBUF_TYPE_TIME_STAMP:
- /* FIXME: not implemented */
+ delta = ring_buffer_event_time_stamp(event);
+ cpu_buffer->read_stamp = delta;
return;
case RINGBUF_TYPE_DATA:
@@ -3440,14 +3474,13 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
return;
case RINGBUF_TYPE_TIME_EXTEND:
- delta = event->array[0];
- delta <<= TS_SHIFT;
- delta += event->time_delta;
+ delta = ring_buffer_event_time_stamp(event);
iter->read_stamp += delta;
return;
case RINGBUF_TYPE_TIME_STAMP:
- /* FIXME: not implemented */
+ delta = ring_buffer_event_time_stamp(event);
+ iter->read_stamp = delta;
return;
case RINGBUF_TYPE_DATA:
@@ -3671,6 +3704,8 @@ static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
struct buffer_page *reader;
int nr_loops = 0;
+ if (ts)
+ *ts = 0;
again:
/*
* We repeat when a time extend is encountered.
@@ -3707,12 +3742,17 @@ static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
goto again;
case RINGBUF_TYPE_TIME_STAMP:
- /* FIXME: not implemented */
+ if (ts) {
+ *ts = ring_buffer_event_time_stamp(event);
+ ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
+ cpu_buffer->cpu, ts);
+ }
+ /* Internal data, OK to advance */
rb_advance_reader(cpu_buffer);
goto again;
case RINGBUF_TYPE_DATA:
- if (ts) {
+ if (ts && !(*ts)) {
*ts = cpu_buffer->read_stamp + event->time_delta;
ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
cpu_buffer->cpu, ts);
@@ -3737,6 +3777,9 @@ static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
struct ring_buffer_event *event;
int nr_loops = 0;
+ if (ts)
+ *ts = 0;
+
cpu_buffer = iter->cpu_buffer;
buffer = cpu_buffer->buffer;
@@ -3789,12 +3832,17 @@ static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
goto again;
case RINGBUF_TYPE_TIME_STAMP:
- /* FIXME: not implemented */
+ if (ts) {
+ *ts = ring_buffer_event_time_stamp(event);
+ ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
+ cpu_buffer->cpu, ts);
+ }
+ /* Internal data, OK to advance */
rb_advance_iter(iter);
goto again;
case RINGBUF_TYPE_DATA:
- if (ts) {
+ if (ts && !(*ts)) {
*ts = iter->read_stamp + event->time_delta;
ring_buffer_normalize_time_stamp(buffer,
cpu_buffer->cpu, ts);
--
1.9.3