perf tools: Reorganize some structs to save space

Using 'pahole --packable' I found some structs that could be reorganized
to eliminate alignment holes, in some cases getting them to be cacheline
multiples.

[acme@doppio linux-2.6-tip]$ codiff perf.old ~/bin/perf
builtin-annotate.c:
  struct perf_session    |   -8
  struct perf_header     |   -8
 2 structs changed

builtin-diff.c:
  struct sample_data         |   -8
 1 struct changed
  diff__process_sample_event |   -8
 1 function changed, 8 bytes removed, diff: -8

builtin-sched.c:
  struct sched_atom      |   -8
 1 struct changed

builtin-timechart.c:
  struct per_pid         |   -8
 1 struct changed
  cmd_timechart          |  -16
 1 function changed, 16 bytes removed, diff: -16

builtin-probe.c:
  struct perf_probe_point |   -8
  struct perf_probe_event |   -8
 2 structs changed
  opt_add_probe_event     |   -3
 1 function changed, 3 bytes removed, diff: -3

util/probe-finder.c:
  struct probe_finder      |   -8
 1 struct changed
  find_kprobe_trace_events |  -16
 1 function changed, 16 bytes removed, diff: -16

/home/acme/bin/perf:
 4 functions changed, 43 bytes removed, diff: -43
[acme@doppio linux-2.6-tip]$

Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-sched.c

@@ -68,10 +68,10 @@ enum sched_event_type {
 
 struct sched_atom {
 	enum sched_event_type	type;
+	int			specific_wait;
 	u64			timestamp;
 	u64			duration;
 	unsigned long		nr;
-	int			specific_wait;
 	sem_t			*wait_sem;
 	struct task_desc	*wakee;
 };

tools/perf/builtin-timechart.c

@@ -77,8 +77,6 @@ struct per_pid {
 
 	struct per_pidcomm *all;
 	struct per_pidcomm *current;
-
-	int painted;
 };
 
 

tools/perf/util/event.h

@@ -68,11 +68,11 @@ struct sample_data {
 	u64 addr;
 	u64 id;
 	u64 stream_id;
-	u32 cpu;
 	u64 period;
-	struct ip_callchain *callchain;
+	u32 cpu;
 	u32 raw_size;
 	void *raw_data;
+	struct ip_callchain *callchain;
 };
 
 #define BUILD_ID_SIZE 20

tools/perf/util/header.h

@@ -47,13 +47,13 @@ int perf_file_header__read(struct perf_file_header *self,
 struct perf_header {
 	int			frozen;
 	int			attrs, size;
+	bool			needs_swap;
 	struct perf_header_attr **attr;
 	s64			attr_offset;
 	u64			data_offset;
 	u64			data_size;
 	u64			event_offset;
 	u64			event_size;
-	bool			needs_swap;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 

tools/perf/util/probe-event.h

@@ -40,9 +40,9 @@ struct perf_probe_point {
 	char		*file;		/* File path */
 	char		*function;	/* Function name */
 	int		line;		/* Line number */
+	bool		retprobe;	/* Return probe flag */
 	char		*lazy_line;	/* Lazy matching pattern */
 	unsigned long	offset;		/* Offset from function entry */
-	bool		retprobe;	/* Return probe flag */
 };
 
 /* Perf probe probing argument field chain */

tools/perf/util/probe-finder.h

@@ -31,13 +31,13 @@ extern int find_line_range(int fd, struct line_range *lr);
 
 struct probe_finder {
 	struct perf_probe_event	*pev;		/* Target probe event */
-	int			ntevs;		/* number of trace events */
 	struct kprobe_trace_event *tevs;	/* Result trace events */
+	int			ntevs;		/* number of trace events */
 
 	/* For function searching */
+	int			lno;		/* Line number */
 	Dwarf_Addr		addr;		/* Address */
 	const char		*fname;		/* Real file name */
-	int			lno;		/* Line number */
 	Dwarf_Die		cu_die;		/* Current CU */
 	struct list_head	lcache;		/* Line cache for lazy match */