tracing/filters: add run-time field descriptions to TRACE_EVENT_FORMAT events

This patch adds run-time field descriptions to all the event formats
exported using TRACE_EVENT_FORMAT.  It also hooks up all the tracers
that use them (i.e. the tracers in the 'ftrace subsystem') so they can
also have their output filtered by the event-filtering mechanism.

When I was testing this, there were a couple of things that fooled me
into thinking the filters weren't working, when actually they were -
I'll mention them here so others don't make the same mistakes (and file
bug reports. ;-)

One is that some of the tracers trace multiple events e.g. the
sched_switch tracer uses the context_switch and wakeup events, and if
you don't set filters on all of the traced events, the unfiltered output
from the events without filters on them can make it look like the
filtering as a whole isn't working properly, when actually it is doing
what it was asked to do - it just wasn't asked to do the right thing.

The other is that for the really high-volume tracers e.g. the function
tracer, the volume of filtered events can be so high that it pushes the
unfiltered events out of the ring buffer before they can be read so e.g.
cat'ing the trace file repeatedly shows either no output, or once in
awhile some output but that isn't there the next time you read the
trace, which isn't what you normally expect when reading the trace file.
If you read from the trace_pipe file though, you can catch them before
they disappear.

Changes from v1:

As suggested by Frederic Weisbecker:

- get rid of externs in functions
- added unlikely() to filter_check_discard()

Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 25 insertions, 0 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4865459f609..962e6179994 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -898,6 +898,7 @@ trace_function(struct trace_array *tr,
 	       unsigned long ip, unsigned long parent_ip, unsigned long flags,
 	       int pc)
 {
+	struct ftrace_event_call *call = &event_function;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
@@ -912,6 +913,9 @@ trace_function(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
+
+	filter_check_discard(call, entry, event);
+
 	ring_buffer_unlock_commit(tr->buffer, event);
 }
 
@@ -921,6 +925,7 @@ static int __trace_graph_entry(struct trace_array *tr,
 				unsigned long flags,
 				int pc)
 {
+	struct ftrace_event_call *call = &event_funcgraph_entry;
 	struct ring_buffer_event *event;
 	struct ftrace_graph_ent_entry *entry;
 
@@ -933,6 +938,7 @@ static int __trace_graph_entry(struct trace_array *tr,
 		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
+	filter_check_discard(call, entry, event);
 	ring_buffer_unlock_commit(global_trace.buffer, event);
 
 	return 1;
@@ -943,6 +949,7 @@ static void __trace_graph_return(struct trace_array *tr,
 				unsigned long flags,
 				int pc)
 {
+	struct ftrace_event_call *call = &event_funcgraph_exit;
 	struct ring_buffer_event *event;
 	struct ftrace_graph_ret_entry *entry;
 
@@ -955,6 +962,7 @@ static void __trace_graph_return(struct trace_array *tr,
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ret				= *trace;
+	filter_check_discard(call, entry, event);
 	ring_buffer_unlock_commit(global_trace.buffer, event);
 }
 #endif
@@ -973,6 +981,7 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 				 int skip, int pc)
 {
 #ifdef CONFIG_STACKTRACE
+	struct ftrace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 	struct stack_trace trace;
@@ -990,6 +999,7 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace(&trace);
+	filter_check_discard(call, entry, event);
 	ring_buffer_unlock_commit(tr->buffer, event);
 #endif
 }
@@ -1015,6 +1025,7 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 				   unsigned long flags, int pc)
 {
 #ifdef CONFIG_STACKTRACE
+	struct ftrace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
 	struct stack_trace trace;
@@ -1036,6 +1047,7 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace_user(&trace);
+	filter_check_discard(call, entry, event);
 	ring_buffer_unlock_commit(tr->buffer, event);
 #endif
 }
@@ -1052,6 +1064,7 @@ ftrace_trace_special(void *__tr,
 		     unsigned long arg1, unsigned long arg2, unsigned long arg3,
 		     int pc)
 {
+	struct ftrace_event_call *call = &event_special;
 	struct ring_buffer_event *event;
 	struct trace_array *tr = __tr;
 	struct special_entry *entry;
@@ -1064,6 +1077,7 @@ ftrace_trace_special(void *__tr,
 	entry->arg1			= arg1;
 	entry->arg2			= arg2;
 	entry->arg3			= arg3;
+	filter_check_discard(call, entry, event);
 	trace_buffer_unlock_commit(tr, event, 0, pc);
 }
 
@@ -1080,6 +1094,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 			   struct task_struct *next,
 			   unsigned long flags, int pc)
 {
+	struct ftrace_event_call *call = &event_context_switch;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 
@@ -1095,6 +1110,9 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_prio		= next->prio;
 	entry->next_state		= next->state;
 	entry->next_cpu	= task_cpu(next);
+
+	filter_check_discard(call, entry, event);
+
 	trace_buffer_unlock_commit(tr, event, flags, pc);
 }
 
@@ -1104,6 +1122,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 			   struct task_struct *curr,
 			   unsigned long flags, int pc)
 {
+	struct ftrace_event_call *call = &event_wakeup;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 
@@ -1120,6 +1139,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_state		= wakee->state;
 	entry->next_cpu			= task_cpu(wakee);
 
+	filter_check_discard(call, entry, event);
+
 	ring_buffer_unlock_commit(tr->buffer, event);
 	ftrace_trace_stack(tr, flags, 6, pc);
 	ftrace_trace_userstack(tr, flags, pc);
@@ -1221,6 +1242,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 		(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	static u32 trace_buf[TRACE_BUF_SIZE];
 
+	struct ftrace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
@@ -1260,6 +1282,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
+	filter_check_discard(call, entry, event);
 	ring_buffer_unlock_commit(tr->buffer, event);
 
 out_unlock:
@@ -1279,6 +1302,7 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
 	static char trace_buf[TRACE_BUF_SIZE];
 
+	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
@@ -1314,6 +1338,7 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = 0;
+	filter_check_discard(call, entry, event);
 	ring_buffer_unlock_commit(tr->buffer, event);
 
  out_unlock: