summaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
authorSteven Rostedt <srostedt@redhat.com>2012-11-02 17:03:03 -0400
committerSteven Rostedt <rostedt@goodmis.org>2013-01-22 23:37:59 -0500
commit0a016409e42f273415f8225ddf2c58eb2df88034 (patch)
treed18d106e6041e516d8ffa05e2bb62d76306c6afd /kernel/trace
parent9640388b63556b4cfecbb5aaf91a5c99d272f429 (diff)
downloadop-kernel-dev-0a016409e42f273415f8225ddf2c58eb2df88034.zip
op-kernel-dev-0a016409e42f273415f8225ddf2c58eb2df88034.tar.gz
ftrace: Optimize the function tracer list loop
There is lots of places that perform: op = rcu_dereference_raw(ftrace_control_list); while (op != &ftrace_list_end) { Add a helper macro to do this, and also optimize for a single entity. That is, gcc will optimize a loop for either no iterations or more than one iteration. But usually only a single callback is registered to the function tracer, thus the optimized case should be a single pass. to do this we now do: op = rcu_dereference_raw(list); do { [...] } while (likely(op = rcu_dereference_raw((op)->next)) && unlikely((op) != &ftrace_list_end)); An op is always registered (ftrace_list_end when no callbacks is registered), thus when a single callback is registered, the link list looks like: top => callback => ftrace_list_end => NULL. The likely(op = op->next) still must be performed due to the race of removing the callback, where the first op assignment could equal ftrace_list_end. In that case, the op->next would be NULL. But this is unlikely (only happens in a race condition when removing the callback). But it is very likely that the next op would be ftrace_list_end, unless more than one callback has been registered. This tells gcc what the most common case is and makes the fast path with the least amount of branches. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/ftrace.c48
1 files changed, 26 insertions, 22 deletions
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 789cbec..1330969 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -111,6 +111,26 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
#endif
+/*
+ * Traverse the ftrace_global_list, invoking all entries. The reason that we
+ * can use rcu_dereference_raw() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism. The rcu_dereference_raw() calls are needed to handle
+ * concurrent insertions into the ftrace_global_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
+#define do_for_each_ftrace_op(op, list) \
+ op = rcu_dereference_raw(list); \
+ do
+
+/*
+ * Optimized for just a single item in the list (as that is the normal case).
+ */
+#define while_for_each_ftrace_op(op) \
+ while (likely(op = rcu_dereference_raw((op)->next)) && \
+ unlikely((op) != &ftrace_list_end))
+
/**
* ftrace_nr_registered_ops - return number of ops registered
*
@@ -132,15 +152,6 @@ int ftrace_nr_registered_ops(void)
return cnt;
}
-/*
- * Traverse the ftrace_global_list, invoking all entries. The reason that we
- * can use rcu_dereference_raw() is that elements removed from this list
- * are simply leaked, so there is no need to interact with a grace-period
- * mechanism. The rcu_dereference_raw() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
- *
- * Silly Alpha and silly pointer-speculation compiler optimizations!
- */
static void
ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *regs)
@@ -149,11 +160,9 @@ ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
return;
trace_recursion_set(TRACE_GLOBAL_BIT);
- op = rcu_dereference_raw(ftrace_global_list); /*see above*/
- while (op != &ftrace_list_end) {
+ do_for_each_ftrace_op(op, ftrace_global_list) {
op->func(ip, parent_ip, op, regs);
- op = rcu_dereference_raw(op->next); /*see above*/
- };
+ } while_for_each_ftrace_op(op);
trace_recursion_clear(TRACE_GLOBAL_BIT);
}
@@ -4104,14 +4113,11 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
*/
preempt_disable_notrace();
trace_recursion_set(TRACE_CONTROL_BIT);
- op = rcu_dereference_raw(ftrace_control_list);
- while (op != &ftrace_list_end) {
+ do_for_each_ftrace_op(op, ftrace_control_list) {
if (!ftrace_function_local_disabled(op) &&
ftrace_ops_test(op, ip))
op->func(ip, parent_ip, op, regs);
-
- op = rcu_dereference_raw(op->next);
- };
+ } while_for_each_ftrace_op(op);
trace_recursion_clear(TRACE_CONTROL_BIT);
preempt_enable_notrace();
}
@@ -4139,12 +4145,10 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
* they must be freed after a synchronize_sched().
*/
preempt_disable_notrace();
- op = rcu_dereference_raw(ftrace_ops_list);
- while (op != &ftrace_list_end) {
+ do_for_each_ftrace_op(op, ftrace_ops_list) {
if (ftrace_ops_test(op, ip))
op->func(ip, parent_ip, op, regs);
- op = rcu_dereference_raw(op->next);
- };
+ } while_for_each_ftrace_op(op);
preempt_enable_notrace();
trace_recursion_clear(TRACE_INTERNAL_BIT);
}
OpenPOWER on IntegriCloud