perf_counter tools: Make source code headers more coherent

The perf commands had different ways of describing themselves,
introduce a coherent command-file-header format taken from the
Git project.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: John Kacur <jkacur@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/perf_counter/builtin-record.c

 /*
- * perf record: Record the profile of a workload (or a CPU, or a PID) into
- * the perf.data output file - for later analysis via perf report.
+ * builtin-record.c
+ *
+ * Builtin record command: Record the profile of a workload
+ * (or a CPU, or a PID) into the perf.data output file - for
+ * later analysis via perf report.
  */
-#include "perf.h"
 #include "builtin.h"
+
+#include "perf.h"
+
 #include "util/util.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"

Documentation/perf_counter/builtin-report.c

-#include "util/util.h"
+/*
+ * builtin-report.c
+ *
+ * Builtin report command: Analyze the perf.data input file,
+ * look up and read DSOs and symbol information and display
+ * a histogram of results, along various sorting keys.
+ */
 #include "builtin.h"
 
+#include "util/util.h"
+
 #include "util/list.h"
 #include "util/cache.h"
 #include "util/rbtree.h"

Documentation/perf_counter/builtin-stat.c

 /*
- * perf stat:  /usr/bin/time -alike performance counter statistics utility
+ * builtin-stat.c
+ *
+ * Builtin stat command: Give a precise performance counters summary
+ * overview about any workload, CPU or specific PID.
+ *
+ * Sample output:
 
-          It summarizes the counter events of all tasks (and child tasks),
-          covering all CPUs that the command (or workload) executes on.
-          It only counts the per-task events of the workload started,
-          independent of how many other tasks run on those CPUs.
+   $ perf stat ~/hackbench 10
+   Time: 0.104
 
-   Sample output:
+    Performance counter stats for '/home/mingo/hackbench':
 
-   $ perf stat -e 1 -e 3 -e 5 ls -lR /usr/include/ >/dev/null
+       1255.538611  task clock ticks     #      10.143 CPU utilization factor
+             54011  context switches     #       0.043 M/sec
+               385  CPU migrations       #       0.000 M/sec
+             17755  pagefaults           #       0.014 M/sec
+        3808323185  CPU cycles           #    3033.219 M/sec
+        1575111190  instructions         #    1254.530 M/sec
+          17367895  cache references     #      13.833 M/sec
+           7674421  cache misses         #       6.112 M/sec
 
-   Performance counter stats for 'ls':
+    Wall-clock time elapsed:   123.786620 msecs
 
-           163516953 instructions
-                2295 cache-misses
-             2855182 branch-misses
  *
  * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
  *

Documentation/perf_counter/builtin-top.c

 /*
- * kerneltop.c: show top kernel functions - performance counters showcase
-
-   Build with:
-
-     make -C Documentation/perf_counter/
-
-   Sample output:
-
-------------------------------------------------------------------------------
- KernelTop:    2669 irqs/sec  [cache-misses/cache-refs],  (all, cpu: 2)
-------------------------------------------------------------------------------
-
-             weight         RIP          kernel function
-             ______   ________________   _______________
-
-              35.20 - ffffffff804ce74b : skb_copy_and_csum_dev
-              33.00 - ffffffff804cb740 : sock_alloc_send_skb
-              31.26 - ffffffff804ce808 : skb_push
-              22.43 - ffffffff80510004 : tcp_established_options
-              19.00 - ffffffff8027d250 : find_get_page
-              15.76 - ffffffff804e4fc9 : eth_type_trans
-              15.20 - ffffffff804d8baa : dst_release
-              14.86 - ffffffff804cf5d8 : skb_release_head_state
-              14.00 - ffffffff802217d5 : read_hpet
-              12.00 - ffffffff804ffb7f : __ip_local_out
-              11.97 - ffffffff804fc0c8 : ip_local_deliver_finish
-               8.54 - ffffffff805001a3 : ip_queue_xmit
- */
-
- /*
+ * builtin-top.c
+ *
+ * Builtin top command: Display a continuously updated profile of
+ * any workload, CPU or specific PID.
+ *
  * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
  *
  * Improvements and fixes by:
@@ -41,9 +16,10 @@
  *
  * Released under the GPL v2. (and only v2, not any later version)
  */
+#include "builtin.h"
 
 #include "perf.h"
-#include "builtin.h"
+
 #include "util/symbol.h"
 #include "util/util.h"
 #include "util/rbtree.h"

Documentation/perf_counter/perf.c

+/*
+ * perf.c
+ *
+ * Performance analysis utility.
+ *
+ * This is the main hub from which the sub-commands (perf stat,
+ * perf top, perf record, perf report, etc.) are started.
+ */
 #include "builtin.h"
+
 #include "util/exec_cmd.h"
 #include "util/cache.h"
 #include "util/quote.h"