tracing: Allow synthetic events to pass around stacktraces

Allow a stacktrace from one event to be displayed by the end event of a
synthetic event. This is very useful when looking for the longest latency
of a sleep or something blocked on I/O.

 # cd /sys/kernel/tracing/
 # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events
 # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace  if prev_state == 1||prev_state == 2' > events/sched/sched_switch/trigger
 # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger

The above creates a "block_lat" synthetic event that take the stacktrace of
when a task schedules out in either the interruptible or uninterruptible
states, and on a new per process max $delta (the time it was scheduled
out), will print the process id and the stacktrace.

  # echo 1 > events/synthetic/block_lat/enable
  # cat trace
 #           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
 #              | |         |   |||||     |         |
    kworker/u16:0-767     [006] d..4.   560.645045: block_lat: pid=767 delta=66 stack=STACK:
 => __schedule
 => schedule
 => pipe_read
 => vfs_read
 => ksys_read
 => do_syscall_64
 => 0x966000aa

           <idle>-0       [003] d..4.   561.132117: block_lat: pid=0 delta=413787 stack=STACK:
 => __schedule
 => schedule
 => schedule_hrtimeout_range_clock
 => do_sys_poll
 => __x64_sys_poll
 => do_syscall_64
 => 0x966000aa

            <...>-153     [006] d..4.   562.068407: block_lat: pid=153 delta=54 stack=STACK:
 => __schedule
 => schedule
 => io_schedule
 => rq_qos_wait
 => wbt_wait
 => __rq_qos_throttle
 => blk_mq_submit_bio
 => submit_bio_noacct_nocheck
 => ext4_bio_write_page
 => mpage_submit_page
 => mpage_process_page_bufs
 => mpage_prepare_extent_to_map
 => ext4_do_writepages
 => ext4_writepages
 => do_writepages
 => __writeback_single_inode

Link: https://lkml.kernel.org/r/20230117152236.010941267@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tom Zanussi <zanussi@kernel.org>
Cc: Ross Zwisler <zwisler@google.com>
Cc: Ching-lin Yu <chinglinyu@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 3 insertions, 4 deletions

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index f8f67e17898a..2c0837ff2299 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -480,10 +480,6 @@ DEFINE_HIST_FIELD_FN(u8);
 #define for_each_hist_key_field(i, hist_data)	\
 	for ((i) = (hist_data)->n_vals; (i) < (hist_data)->n_fields; (i)++)
 
-#define HIST_STACKTRACE_DEPTH	16
-#define HIST_STACKTRACE_SIZE	(HIST_STACKTRACE_DEPTH * sizeof(unsigned long))
-#define HIST_STACKTRACE_SKIP	5
-
 #define HITCOUNT_IDX		0
 #define HIST_KEY_SIZE_MAX	(MAX_FILTER_STR_VAL + HIST_STACKTRACE_SIZE)
 
@@ -3869,6 +3865,9 @@ static int check_synth_field(struct synth_event *event,
 	    && field->is_dynamic)
 		return 0;
 
+	if (strstr(hist_field->type, "long[") && field->is_stack)
+		return 0;
+
 	if (strcmp(field->type, hist_field->type) != 0) {
 		if (field->size != hist_field->size ||
 		    (!field->is_string && field->is_signed != hist_field->is_signed))