Port ftrace to markers

Porting ftrace to the marker infrastructure.

Don't need to chain to the wakeup tracer from the sched tracer, because markers
support multiple probes connected.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
CC: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 244 insertions, 53 deletions

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8845033ab49d..f5de0601b408 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -234,25 +234,10 @@ void update_max_tr_single(struct trace_array *tr,
 
 extern cycle_t ftrace_now(int cpu);
 
-#ifdef CONFIG_SCHED_TRACER
-extern void
-wakeup_sched_switch(struct task_struct *prev, struct task_struct *next);
-extern void
-wakeup_sched_wakeup(struct task_struct *wakee, struct task_struct *curr);
-#else
-static inline void
-wakeup_sched_switch(struct task_struct *prev, struct task_struct *next)
-{
-}
-static inline void
-wakeup_sched_wakeup(struct task_struct *wakee, struct task_struct *curr)
-{
-}
-#endif
-
 #ifdef CONFIG_CONTEXT_SWITCH_TRACER
 typedef void
 (*tracer_switch_func_t)(void *private,
+                        void *__rq,
                         struct task_struct *prev,
                         struct task_struct *next);
 
@@ -262,9 +247,6 @@ struct tracer_switch_ops {
         struct tracer_switch_ops        *next;
 };
 
-extern int register_tracer_switch(struct tracer_switch_ops *ops);
-extern int unregister_tracer_switch(struct tracer_switch_ops *ops);
-
 #endif /* CONFIG_CONTEXT_SWITCH_TRACER */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index a3376478fc2c..d25ffa5eaf2b 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -16,11 +16,14 @@
 
 static struct trace_array       *ctx_trace;
 static int __read_mostly        tracer_enabled;
+static atomic_t                 sched_ref;
 
 static void
-ctx_switch_func(void *__rq, struct task_struct *prev, struct task_struct *next)
+sched_switch_func(void *private, void *__rq, struct task_struct *prev,
+                        struct task_struct *next)
 {
-        struct trace_array *tr = ctx_trace;
+        struct trace_array **ptr = private;
+        struct trace_array *tr = *ptr;
         struct trace_array_cpu *data;
         unsigned long flags;
         long disabled;
@@ -41,10 +44,40 @@ ctx_switch_func(void *__rq, struct task_struct *prev, struct task_struct *next)
         local_irq_restore(flags);
 }
 
+static notrace void
+sched_switch_callback(void *probe_data, void *call_data,
+                      const char *format, va_list *args)
+{
+        struct task_struct *prev;
+        struct task_struct *next;
+        struct rq *__rq;
+
+        if (!atomic_read(&sched_ref))
+                return;
+
+        /* skip prev_pid %d next_pid %d prev_state %ld */
+        (void)va_arg(*args, int);
+        (void)va_arg(*args, int);
+        (void)va_arg(*args, long);
+        __rq = va_arg(*args, typeof(__rq));
+        prev = va_arg(*args, typeof(prev));
+        next = va_arg(*args, typeof(next));
+
+        tracing_record_cmdline(prev);
+
+        /*
+         * If tracer_switch_func only points to the local
+         * switch func, it still needs the ptr passed to it.
+         */
+        sched_switch_func(probe_data, __rq, prev, next);
+}
+
 static void
-wakeup_func(void *__rq, struct task_struct *wakee, struct task_struct *curr)
+wakeup_func(void *private, void *__rq, struct task_struct *wakee, struct
+                        task_struct *curr)
 {
-        struct trace_array *tr = ctx_trace;
+        struct trace_array **ptr = private;
+        struct trace_array *tr = *ptr;
         struct trace_array_cpu *data;
         unsigned long flags;
         long disabled;
@@ -67,35 +100,29 @@ wakeup_func(void *__rq, struct task_struct *wakee, struct task_struct *curr)
         local_irq_restore(flags);
 }
 
-void
-ftrace_ctx_switch(void *__rq, struct task_struct *prev,
-                  struct task_struct *next)
+static notrace void
+wake_up_callback(void *probe_data, void *call_data,
+                 const char *format, va_list *args)
 {
-        if (unlikely(atomic_read(&trace_record_cmdline_enabled)))
-                tracing_record_cmdline(prev);
+        struct task_struct *curr;
+        struct task_struct *task;
+        struct rq *__rq;
 
-        /*
-         * If tracer_switch_func only points to the local
-         * switch func, it still needs the ptr passed to it.
-         */
-        ctx_switch_func(__rq, prev, next);
+        if (likely(!tracer_enabled))
+                return;
 
-        /*
-         * Chain to the wakeup tracer (this is a NOP if disabled):
-         */
-        wakeup_sched_switch(prev, next);
-}
+        /* Skip pid %d state %ld */
+        (void)va_arg(*args, int);
+        (void)va_arg(*args, long);
+        /* now get the meat: "rq %p task %p rq->curr %p" */
+        __rq = va_arg(*args, typeof(__rq));
+        task = va_arg(*args, typeof(task));
+        curr = va_arg(*args, typeof(curr));
 
-void
-ftrace_wake_up_task(void *__rq, struct task_struct *wakee,
-                    struct task_struct *curr)
-{
-        wakeup_func(__rq, wakee, curr);
+        tracing_record_cmdline(task);
+        tracing_record_cmdline(curr);
 
-        /*
-         * Chain to the wakeup tracer (this is a NOP if disabled):
-         */
-        wakeup_sched_wakeup(wakee, curr);
+        wakeup_func(probe_data, __rq, task, curr);
 }
 
 void
@@ -132,15 +159,95 @@ static void sched_switch_reset(struct trace_array *tr)
                 tracing_reset(tr->data[cpu]);
 }
 
+static int tracing_sched_register(void)
+{
+        int ret;
+
+        ret = marker_probe_register("kernel_sched_wakeup",
+                        "pid %d state %ld ## rq %p task %p rq->curr %p",
+                        wake_up_callback,
+                        &ctx_trace);
+        if (ret) {
+                pr_info("wakeup trace: Couldn't add marker"
+                        " probe to kernel_sched_wakeup\n");
+                return ret;
+        }
+
+        ret = marker_probe_register("kernel_sched_wakeup_new",
+                        "pid %d state %ld ## rq %p task %p rq->curr %p",
+                        wake_up_callback,