tracing: Merge irqflags + preempt counter.

The state of the interrupts (irqflags) and the preemption counter are
both passed down to tracing_generic_entry_update(). Only one bit of
irqflags is actually required: The on/off state. The complete 32bit
of the preemption counter isn't needed. Just whether of the upper bits
(softirq, hardirq and NMI) are set and the preemption depth is needed.

The irqflags and the preemption counter could be evaluated early and the
information stored in an integer `trace_ctx'.
tracing_generic_entry_update() would use the upper bits as the
TRACE_FLAG_* and the lower 8bit as the disabled-preemption depth
(considering that one must be substracted from the counter in one
special cases).

The actual preemption value is not used except for the tracing record.
The `irqflags' variable is mostly used only for the tracing record. An
exception here is for instance wakeup_tracer_call() or
probe_wakeup_sched_switch() which explicilty disable interrupts and use
that `irqflags' to save (and restore) the IRQ state and to record the
state.

Struct trace_event_buffer has also the `pc' and flags' members which can
be replaced with `trace_ctx' since their actual value is not used
outside of trace recording.

This will reduce tracing_generic_entry_update() to simply assign values
to struct trace_entry. The evaluation of the TRACE_FLAG_* bits is moved
to _tracing_gen_ctx_flags() which replaces preempt_count() and
local_save_flags() invocations.

As an example, ftrace_syscall_enter() may invoke:
- trace_buffer_lock_reserve() -> … -> tracing_generic_entry_update()
- event_trigger_unlock_commit()
  -> ftrace_trace_stack() -> … -> tracing_generic_entry_update()
  -> ftrace_trace_userstack() -> … -> tracing_generic_entry_update()

In this case the TRACE_FLAG_* bits were evaluated three times. By using
the `trace_ctx' they are evaluated once and assigned three times.

A build with all tracers enabled on x86-64 with and without the patch:

    text     data      bss      dec      hex    filename
21970669 17084168  7639260 46694097  2c87ed1 vmlinux.old
21970293 17084168  7639260 46693721  2c87d59 vmlinux.new

text shrank by 379 bytes, data remained constant.

Link: https://lkml.kernel.org/r/20210125194511.3924915-2-bigeasy@linutronix.de

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

1 files changed, 17 insertions, 21 deletions

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e448d2da0b99..8daf3a0758b1 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -589,8 +589,7 @@ struct ring_buffer_event *
 trace_buffer_lock_reserve(struct trace_buffer *buffer,
 			  int type,
 			  unsigned long len,
-			  unsigned long flags,
-			  int pc);
+			  unsigned int trace_ctx);
 
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
@@ -615,11 +614,11 @@ unsigned long trace_total_entries(struct trace_array *tr);
 void trace_function(struct trace_array *tr,
 		    unsigned long ip,
 		    unsigned long parent_ip,
-		    unsigned long flags, int pc);
+		    unsigned int trace_ctx);
 void trace_graph_function(struct trace_array *tr,
 		    unsigned long ip,
 		    unsigned long parent_ip,
-		    unsigned long flags, int pc);
+		    unsigned int trace_ctx);
 void trace_latency_header(struct seq_file *m);
 void trace_default_header(struct seq_file *m);
 void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
@@ -687,11 +686,10 @@ static inline void latency_fsnotify(struct trace_array *tr) { }
 #endif
 
 #ifdef CONFIG_STACKTRACE
-void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
-		   int pc);
+void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip);
 #else
-static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
-				 int skip, int pc)
+static inline void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
+				 int skip)
 {
 }
 #endif /* CONFIG_STACKTRACE */
@@ -831,10 +829,10 @@ extern void graph_trace_open(struct trace_iterator *iter);
 extern void graph_trace_close(struct trace_iterator *iter);
 extern int __trace_graph_entry(struct trace_array *tr,
 			       struct ftrace_graph_ent *trace,
-			       unsigned long flags, int pc);
+			       unsigned int trace_ctx);
 extern void __trace_graph_return(struct trace_array *tr,
 				 struct ftrace_graph_ret *trace,
-				 unsigned long flags, int pc);
+				 unsigned int trace_ctx);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern struct ftrace_hash __rcu *ftrace_graph_hash;
@@ -1297,15 +1295,15 @@ extern int call_filter_check_discard(struct trace_event_call *call, void *rec,
 void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 				     struct trace_buffer *buffer,
 				     struct ring_buffer_event *event,
-				     unsigned long flags, int pc,
+				     unsigned int trcace_ctx,
 				     struct pt_regs *regs);
 
 static inline void trace_buffer_unlock_commit(struct trace_array *tr,
 					      struct trace_buffer *buffer,
 					      struct ring_buffer_event *event,
-					      unsigned long flags, int pc)
+					      unsigned int trace_ctx)
 {
-	trace_buffer_unlock_commit_regs(tr, buffer, event, flags, pc, NULL);
+	trace_buffer_unlock_commit_regs(tr, buffer, event, trace_ctx, NULL);
 }
 
 DECLARE_PER_CPU(struct ring_buffer_event *, trace_buffered_event);
@@ -1366,8 +1364,7 @@ __event_trigger_test_discard(struct trace_event_file *file,
  * @buffer: The ring buffer that the event is being written to
  * @event: The event meta data in the ring buffer
  * @entry: The event itself
- * @irq_flags: The state of the interrupts at the start of the event
- * @pc: The state of the preempt count at the start of the event.
+ * @trace_ctx: The tracing context flags.
  *
  * This is a helper function to handle triggers that require data
  * from the event itself. It also tests the event against filters and
@@ -1377,12 +1374,12 @@ static inline void
 event_trigger_unlock_commit(struct trace_event_file *file,
 			    struct trace_buffer *buffer,
 			    struct ring_buffer_event *event,
-			    void *entry, unsigned long irq_flags, int pc)
+			    void *entry, unsigned int trace_ctx)
 {
 	enum event_trigger_type tt = ETT_NONE;
 
 	if (!__event_trigger_test_discard(file, buffer, event, entry, &tt))
-		trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc);
+		trace_buffer_unlock_commit(file->tr, buffer, event, trace_ctx);
 
 	if (tt)
 		event_triggers_post_call(file, tt);
@@ -1394,8 +1391,7 @@ event_trigger_unlock_commit(struct trace_event_file *file,
  * @buffer: The ring buffer that the event is being written to
  * @event: The event meta data in the ring buffer
  * @entry: The event itself
- * @irq_flags: The state of the interrupts at the start of the event
- * @pc: The state of the preempt count at the start of the event.
+ * @trace_ctx: The tracing context flags.
  *
  * This is a helper function to handle triggers that require data
  * from the event itself. It also tests the event against filters and
@@ -1408,14 +1404,14 @@ static inline void
 event_trigger_unlock_commit_regs(struct trace_event_file *file,
 				 struct trace_buffer *buffer,
 				 struct ring_buffer_event *event,
-				 void *entry, unsigned long irq_flags, int pc,
+				 void *entry, unsigned int trace_ctx,
 				 struct pt_regs *regs)
 {
 	enum event_trigger_type tt = ETT_NONE;
 
 	if (!__event_trigger_test_discard(file, buffer, event, entry, &tt))
 		trace_buffer_unlock_commit_regs(file->tr, buffer, event,
-						irq_flags, pc, regs);
+						trace_ctx, regs);
 
 	if (tt)
 		event_triggers_post_call(file, tt);