tools/power: turbostat v2 - re-write for efficiency

Measuring large profoundly-idle configurations
requires turbostat to be more lightweight.
Otherwise, the operation of turbostat itself
can interfere with the measurements.

This re-write makes turbostat topology aware.
Hardware is accessed in "topology order".
Redundant hardware accesses are deleted.
Redundant output is deleted.
Also, output is buffered and
local RDTSC use replaces remote MSR access for TSC.

From a feature point of view, the output
looks different since redundant figures are absent.
Also, there are now -c and -p options -- to restrict
output to the 1st thread in each core, and the 1st
thread in each package, respectively.  This is helpful
to reduce output on big systems, where more detail
than the "-s" system summary is desired.
Finally, periodic mode output is now on stdout, not stderr.

Turbostat v2 is also slightly more robust in
handling run-time CPU online/offline events,
as it now checks the actual map of on-line cpus rather
than just the total number of on-line cpus.

Signed-off-by: Len Brown <len.brown@intel.com>

3 files changed, 868 insertions, 539 deletions

diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index fd8e1f1297aa..f85649554191 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,4 +1,5 @@
 turbostat : turbostat.c
+CFLAGS +=       -Wall
 
 clean :
         rm -f turbostat
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index adf175f61496..74e44507dfe9 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -27,7 +27,11 @@ supports an "invariant" TSC, plus the APERF and MPERF MSRs.
 on processors that additionally support C-state residency counters.
 
 .SS Options
-The \fB-s\fP option prints only a 1-line summary for each sample interval.
+The \fB-s\fP option limits output to a 1-line system summary for each interval.
+.PP
+The \fB-c\fP option limits output to the 1st thread in each core.
+.PP
+The \fB-p\fP option limits output to the 1st thread in each package.
 .PP
 The \fB-v\fP option increases verbosity.
 .PP
@@ -65,19 +69,19 @@ Subsequent rows show per-CPU statistics.
 .nf
 [root@x980]# ./turbostat
 cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
-          0.60 1.63 3.38   2.91   0.00  96.49   0.00  76.64
-  0   0   0.59 1.62 3.38   4.51   0.00  94.90   0.00  76.64
-  0   6   1.13 1.64 3.38   3.97   0.00  94.90   0.00  76.64
-  1   2   0.08 1.62 3.38   0.07   0.00  99.85   0.00  76.64
-  1   8   0.03 1.62 3.38   0.12   0.00  99.85   0.00  76.64
-  2   4   0.01 1.62 3.38   0.06   0.00  99.93   0.00  76.64
-  2  10   0.04 1.62 3.38   0.02   0.00  99.93   0.00  76.64
-  8   1   2.85 1.62 3.38  11.71   0.00  85.44   0.00  76.64
-  8   7   1.98 1.62 3.38  12.58   0.00  85.44   0.00  76.64
-  9   3   0.36 1.62 3.38   0.71   0.00  98.93   0.00  76.64
-  9   9   0.09 1.62 3.38   0.98   0.00  98.93   0.00  76.64
- 10   5   0.03 1.62 3.38   0.09   0.00  99.87   0.00  76.64
- 10  11   0.07 1.62 3.38   0.06   0.00  99.87   0.00  76.64
+          0.09 1.62 3.38   1.83   0.32  97.76   1.26  83.61
+  0   0   0.15 1.62 3.38  10.23   0.05  89.56   1.26  83.61
+  0   6   0.05 1.62 3.38  10.34
+  1   2   0.03 1.62 3.38   0.07   0.05  99.86
+  1   8   0.03 1.62 3.38   0.06
+  2   4   0.21 1.62 3.38   0.10   1.49  98.21
+  2  10   0.02 1.62 3.38   0.29
+  8   1   0.04 1.62 3.38   0.04   0.08  99.84
+  8   7   0.01 1.62 3.38   0.06
+  9   3   0.53 1.62 3.38   0.10   0.20  99.17
+  9   9   0.02 1.62 3.38   0.60
+ 10   5   0.01 1.62 3.38   0.02   0.04  99.92
+ 10  11   0.02 1.62 3.38   0.02
 .fi
 .SH SUMMARY EXAMPLE
 The "-s" option prints the column headers just once,
@@ -86,9 +90,10 @@ and then the one line system summary for each sample interval.
 .nf
 [root@x980]# ./turbostat -s
    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
-  0.61 1.89 3.38   5.95   0.00  93.44   0.00  66.33
-  0.52 1.62 3.38   6.83   0.00  92.65   0.00  61.11
-  0.62 1.92 3.38   5.47   0.00  93.91   0.00  67.31
+  0.23 1.67 3.38   2.00   0.30  97.47   1.07  82.12
+  0.10 1.62 3.38   1.87   2.25  95.77  12.02  72.60
+  0.20 1.64 3.38   1.98   0.11  97.72   0.30  83.36
+  0.11 1.70 3.38   1.86   1.81  96.22   9.71  74.90
 .fi
 .SH VERBOSE EXAMPLE
 The "-v" option adds verbosity to the output:
@@ -120,30 +125,28 @@ until ^C while the other CPUs are mostly idle:
 [root@x980 lenb]# ./turbostat cat /dev/zero > /dev/null
 ^C
 cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
-          8.63 3.64 3.38  14.46   0.49  76.42   0.00   0.00
-  0   0   0.34 3.36 3.38  99.66   0.00   0.00   0.00   0.00
-  0   6  99.96 3.64 3.38   0.04   0.00   0.00   0.00   0.00
-  1   2   0.14 3.50 3.38   1.75   2.04  96.07   0.00   0.00
-  1   8   0.38 3.57 3.38   1.51   2.04  96.07   0.00   0.00
-  2   4   0.01 2.65 3.38   0.06   0.00  99.93   0.00   0.00
-  2  10   0.03 2.12 3.38   0.04   0.00  99.93   0.00   0.00
-  8   1   0.91 3.59 3.38  35.27   0.92  62.90   0.00   0.00
-  8   7   1.61 3.63 3.38  34.57   0.92  62.90   0.00   0.00
-  9   3   0.04 3.38 3.38   0.20   0.00  99.76   0.00   0.00
-  9   9   0.04 3.29 3.38   0.20   0.00  99.76   0.00   0.00
- 10   5   0.03 3.08 3.38   0.12   0.00  99.85   0.00   0.00
- 10  11   0.05 3.07 3.38   0.10   0.00  99.85   0.00   0.00
-4.907015 sec
-
+          8.86 3.61 3.38  15.06  31.19  44.89   0.00   0.00
+  0   0   1.46 3.22 3.38  16.84  29.48  52.22   0.00   0.00
+  0   6   0.21 3.06 3.38  18.09
+  1   2   0.53 3.33 3.38   2.80  46.40  50.27
+  1   8   0.89 3.47 3.38   2.44
+  2   4   1.36 3.43 3.38   9.04  23.71  65.89
+  2  10   0.18 2.86 3.38  10.22
+  8   1   0.04 2.87 3.38  99.96   0.01   0.00
+  8   7  99.72 3.63 3.38   0.27
+  9   3   0.31 3.21 3.38   7.64  56.55  35.50
+  9   9   0.08 2.95 3.38   7.88
+ 10   5   1.42 3.43 3.38   2.14  30.99  65.44
+ 10  11   0.16 2.88 3.38   3.40
 .fi
-Above the cycle soaker drives cpu6 up 3.6 Ghz turbo limit
+Above the cycle soaker drives cpu7 up its 3.6 Ghz turbo limit
 while the other processors are generally in various states of idle.
 
-Note that cpu0 is an HT sibling sharing core0
-with cpu6, and thus it is unable to get to an idle state
-deeper than c1 while cpu6 is busy.
+Note that cpu1 and cpu7 are HT siblings within core8.
+As cpu7 is very busy, it prevents its sibling, cpu1,
+from entering a c-state deeper than c1.
 
-Note that turbostat reports average GHz of 3.64, while
+Note that turbostat reports average GHz of 3.63, while
 the arithmetic average of the GHz column above is lower.
 This is a weighted average, where the weight is %c0.  ie. it is the total number of
 un-halted cycles elapsed per time divided by the number of CPUs.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 16de7ad4850f..b815a12159b2 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -67,92 +67,119 @@ double bclk;
 unsigned int show_pkg;
 unsigned int show_core;
 unsigned int show_cpu;
+unsigned int show_pkg_only;
+unsigned int show_core_only;
+char *output_buffer, *outp;
 
 int aperf_mperf_unstable;
 int backwards_count;
 char *progname;
 
-int num_cpus;
-cpu_set_t *cpu_present_set, *cpu_mask;
-size_t cpu_present_setsize, cpu_mask_size;
-
-struct counters {
-        unsigned long long tsc;         /* per thread */
-        unsigned long long aperf;       /* per thread */
-        unsigned long long mperf;       /* per thread */
-        unsigned long long c1;  /* per thread (calculated) */
-        unsigned long long c3;  /* per core */
-        unsigned long long c6;  /* per core */
-        unsigned long long c7;  /* per core */
-        unsigned long long pc2; /* per package */
-        unsigned long long pc3; /* per package */
-        unsigned long long pc6; /* per package */
-        unsigned long long pc7; /* per package */
-        unsigned long long extra_msr;   /* per thread */
-        int pkg;
-        int core;
-        int cpu;
-        struct counters *next;
-};
-
-struct counters *cnt_even;
-struct counters *cnt_odd;
-struct counters *cnt_delta;
-struct counters *cnt_average;
+cpu_set_t *cpu_present_set, *cpu_affinity_set;
+size_t cpu_present_setsize, cpu_affinity_setsize;
+
+struct thread_data {
+        unsigned long long tsc;
+        unsigned long long aperf;
+        unsigned long long mperf;
+        unsigned long long c1;  /* derived */
+        unsigned long long extra_msr;
+        unsigned int cpu_id;
+        unsigned int flags;
+#define CPU_IS_FIRST_THREAD_IN_CORE     0x2
+#define CPU_IS_FIRST_CORE_IN_PACKAGE    0x4
+} *thread_even, *thread_odd;
+
+struct core_data {
+        unsigned long long c3;
+        unsigned long long c6;
+        unsigned long long c7;
+        unsigned int core_id;
+} *core_even, *core_odd;
+
+struct pkg_data {
+        unsigned long long pc2;
+        unsigned long long pc3;
+        unsigned long long pc6;
+        unsigned long long pc