tracepoint: Optimize using static_call()
Currently the tracepoint site will iterate a vector and issue indirect
calls to however many handlers are registered (ie. the vector is
long).
Using static_call() it is possible to optimize this for the common
case of only having a single handler registered. In this case the
static_call() can directly call this handler. Otherwise, if the vector
is longer than 1, call a function that iterates the whole vector like
the current code.
[peterz: updated to new interface]
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.279421092@infradead.org
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 8e05ed2..e92f3fb8 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -221,6 +221,20 @@ static void *func_remove(struct tracepoint_func **funcs,
return old;
}
+static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs)
+{
+ void *func = tp->iterator;
+
+ /* Synthetic events do not have static call sites */
+ if (!tp->static_call_key)
+ return;
+
+ if (!tp_funcs[1].func)
+ func = tp_funcs[0].func;
+
+ __static_call_update(tp->static_call_key, tp->static_call_tramp, func);
+}
+
/*
* Add the probe function to a tracepoint.
*/
@@ -251,8 +265,9 @@ static int tracepoint_add_func(struct tracepoint *tp,
* include/linux/tracepoint.h using rcu_dereference_sched().
*/
rcu_assign_pointer(tp->funcs, tp_funcs);
- if (!static_key_enabled(&tp->key))
- static_key_slow_inc(&tp->key);
+ tracepoint_update_call(tp, tp_funcs);
+ static_key_enable(&tp->key);
+
release_probes(old);
return 0;
}
@@ -281,9 +296,11 @@ static int tracepoint_remove_func(struct tracepoint *tp,
if (tp->unregfunc && static_key_enabled(&tp->key))
tp->unregfunc();
- if (static_key_enabled(&tp->key))
- static_key_slow_dec(&tp->key);
+ static_key_disable(&tp->key);
+ } else {
+ tracepoint_update_call(tp, tp_funcs);
}
+
rcu_assign_pointer(tp->funcs, tp_funcs);
release_probes(old);
return 0;