tracing/perf: Reimplement TP_perf_assign() logic
The next patch tries to avoid the costly perf_trace_buf_* calls
when possible but there is a problem. We can only do this if
__task == NULL, perf_tp_event(task != NULL) has the additional
code for this case.
Unfortunately, TP_perf_assign/__perf_xxx which changes the default
values of __count/__task variables for perf_trace_buf_submit() is
called "too late", after we already did perf_trace_buf_prepare(),
and the optimization above can't work.
So this patch simply embeds __perf_xxx() into TP_ARGS(), this way
DECLARE_EVENT_CLASS() can use the result of assignments hidden in
"args" right after ftrace_get_offsets_##call() which is mostly
trivial. This allows us to have the fast-path "__task != NULL"
check at the start, see the next patch.
Link: http://lkml.kernel.org/r/20130806160844.GA2739@redhat.com
Tested-by: David Ahern <dsahern@gmail.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 249c024..2e7d994 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -57,7 +57,7 @@
TP_PROTO(struct task_struct *p, int success),
- TP_ARGS(p, success),
+ TP_ARGS(__perf_task(p), success),
TP_STRUCT__entry(
__array( char, comm, TASK_COMM_LEN )
@@ -73,9 +73,6 @@
__entry->prio = p->prio;
__entry->success = success;
__entry->target_cpu = task_cpu(p);
- )
- TP_perf_assign(
- __perf_task(p);
),
TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
@@ -313,7 +310,7 @@
TP_PROTO(struct task_struct *tsk, u64 delay),
- TP_ARGS(tsk, delay),
+ TP_ARGS(__perf_task(tsk), __perf_count(delay)),
TP_STRUCT__entry(
__array( char, comm, TASK_COMM_LEN )
@@ -325,10 +322,6 @@
memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
__entry->pid = tsk->pid;
__entry->delay = delay;
- )
- TP_perf_assign(
- __perf_count(delay);
- __perf_task(tsk);
),
TP_printk("comm=%s pid=%d delay=%Lu [ns]",
@@ -376,7 +369,7 @@
TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
- TP_ARGS(tsk, runtime, vruntime),
+ TP_ARGS(tsk, __perf_count(runtime), vruntime),
TP_STRUCT__entry(
__array( char, comm, TASK_COMM_LEN )
@@ -390,9 +383,6 @@
__entry->pid = tsk->pid;
__entry->runtime = runtime;
__entry->vruntime = vruntime;
- )
- TP_perf_assign(
- __perf_count(runtime);
),
TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",