Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/core

15 files changed, 324 insertions, 68 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index b2c63309a65..6f5a498608b 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -24,12 +24,47 @@ OPTIONS
 --input=::
         Input file name. (default: perf.data)
 
+-d::
+--dsos=<dso[,dso...]>::
+        Only consider symbols in these dsos.
+-s::
+--symbol=<symbol>::
+        Symbol to annotate.
+
+-f::
+--force::
+        Don't complain, do it.
+
+-v::
+--verbose::
+        Be more verbose. (Show symbol address, etc)
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname.
+
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel.
+
+-l::
+--print-line::
+        Print matching source lines (may be slow).
+
+-P::
+--full-paths::
+        Don't shorten the displayed pathnames.
+
 --stdio:: Use the stdio interface.
 
 --tui:: Use the TUI interface Use of --tui requires a tty, if one is not
 	present, as when piping to other commands, the stdio interface is
 	used. This interfaces starts by centering on the line with more
-	samples, TAB/UNTAB cycles thru the lines with more samples.
+	samples, TAB/UNTAB cycles through the lines with more samples.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt
index 01b642c0bf8..5eaac6f26d5 100644
--- a/tools/perf/Documentation/perf-buildid-list.txt
+++ b/tools/perf/Documentation/perf-buildid-list.txt
@@ -18,6 +18,9 @@ perf report.
 
 OPTIONS
 -------
+-H::
+--with-hits::
+        Show only DSOs with hits.
 -i::
 --input=::
         Input file name. (default: perf.data)
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 20d97d84ea1..6a9ec2b3531 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -19,6 +19,18 @@ If no parameters are passed it will assume perf.data.old and perf.data.
 
 OPTIONS
 -------
+-M::
+--displacement::
+        Show position displacement relative to baseline.
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel
+
 -d::
 --dsos=::
 	Only consider symbols in these dsos. CSV that understands
@@ -42,7 +54,7 @@ OPTIONS
 --field-separator=::
 
 	Use a special separator character and don't pad with spaces, replacing
-	all occurances of this separator in symbol names (and other output)
+	all occurrences of this separator in symbol names (and other output)
 	with a '.' character, that thus it's the only non valid separator.
 
 -v::
@@ -50,6 +62,11 @@ OPTIONS
 	Be verbose, for instance, show the raw counts in addition to the
 	diff.
 
+-f::
+--force::
+       Don't complain, do it.
+
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index d004e19fe6d..dd84cb2f0a8 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -22,7 +22,7 @@ There are a couple of variants of perf kvm:
   a performance counter profile of guest os in realtime
   of an arbitrary workload.
 
-  'perf kvm record <command>' to record the performance couinter profile
+  'perf kvm record <command>' to record the performance counter profile
   of an arbitrary workload and save it into a perf data file. If both
   --host and --guest are input, the perf data file name is perf.data.kvm.
   If there is  no --host but --guest, the file name is perf.data.guest.
@@ -40,6 +40,12 @@ There are a couple of variants of perf kvm:
 
 OPTIONS
 -------
+-i::
+--input=::
+        Input file name.
+-o::
+--output::
+        Output file name.
 --host=::
         Collect host side performance profile.
 --guest=::
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index b317102138c..921de259ea1 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -24,6 +24,21 @@ and statistics with this 'perf lock' command.
 
   'perf lock report' reports statistical data.
 
+OPTIONS
+-------
+
+-i::
+--input=<file>::
+        Input file name.
+
+-v::
+--verbose::
+        Be more verbose (show symbol address, etc).
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 62de1b7f4e7..4e232327698 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -115,7 +115,7 @@ Each probe argument follows below syntax.
 
 LINE SYNTAX
 -----------
-Line range is descripted by following syntax.
+Line range is described by following syntax.
 
  "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]"
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index a91f9f9e6e5..0ad1bc75ab4 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -39,15 +39,24 @@ OPTIONS
           be passed as follows: '\mem:addr[:[r][w][x]]'.
           If you want to profile read-write accesses in 0x1000, just set
           'mem:0x1000:rw'.
+
+--filter=<filter>::
+        Event filter.
+
 -a::
-        System-wide collection.
+--all-cpus::
+        System-wide collection from all CPUs.
 
 -l::
         Scale counter values.
 
 -p::
 --pid=::
-	Record events on existing pid.
+	Record events on existing process ID.
+
+-t::
+--tid=::
+        Record events on existing thread ID.
 
 -r::
 --realtime=::
@@ -109,8 +118,8 @@ Collect raw sample records from all opened counters (default for tracepoint coun
 
 -C::
 --cpu::
-Collect samples only on the list of cpus provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 In per-thread mode with inheritance mode on (default), samples are captured only when
 the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 12052c9ed0b..59a1f57f2bb 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -20,6 +20,11 @@ OPTIONS
 -i::
 --input=::
         Input file name. (default: perf.data)
+
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
 -d::
 --dsos=::
 	Only consider symbols in these dsos. CSV that understands
@@ -27,6 +32,10 @@ OPTIONS
 -n::
 --show-nr-samples::
 	Show the number of samples for each symbol
+
+--showcpuutilization::
+        Show sample percentage for different cpu modes.
+
 -T::
 --threads::
 	Show per-thread event counters
@@ -39,12 +48,24 @@ OPTIONS
 	Only consider these symbols. CSV that understands
 	file://filename entries.
 
+-U::
+--hide-unresolved::
+        Only display entries resolved to a symbol.
+
 -s::
 --sort=::
 	Sort by key(s): pid, comm, dso, symbol, parent.
 
+-p::
+--parent=<regex>::
+        regex filter to identify parent, see: '--sort parent'
+
+-x::
+--exclude-other::
+        Only display entries with parent-match.
+
 -w::
---field-width=::
+--column-widths=<width[,width...]>::
 	Force each column width to the provided list, for large terminal
 	readability.
 
@@ -52,19 +73,26 @@ OPTIONS
 --field-separator=::
 
 	Use a special separator character and don't pad with spaces, replacing
-	all occurances of this separator in symbol names (and other output)
+	all occurrences of this separator in symbol names (and other output)
 	with a '.' character, that thus it's the only non valid separator.
 
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
 -g [type,min]::
 --call-graph::
-        Display callchains using type and min percent threshold.
+        Display call chains using type and min percent threshold.
 	type can be either:
-	- flat: single column, linear exposure of callchains.
+	- flat: single column, linear exposure of call chains.
 	- graph: use a graph tree, displaying absolute overhead rates.
 	- fractal: like graph, but displays relative rates. Each branch of
 		 the tree is considered as a new profiled object. +
 	Default: fractal,0.5.
 
+--pretty=<key>::
+        Pretty printing style.  key: normal, raw
+
 --stdio:: Use the stdio interface.
 
 --tui:: Use the TUI interface, that is integrated with annotate and allows
@@ -72,6 +100,19 @@ OPTIONS
 	requires a tty, if one is not present, as when piping to other
 	commands, the stdio interface is used.
 
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+
+-m::
+--modules::
+        Load module symbols. WARNING: This should only be used with -k and
+        a LIVE kernel.
+
+-f::
+--force::
+        Don't complain, do it.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 8417644a616..46822d5fde1 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -8,11 +8,11 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
 SYNOPSIS
 --------
 [verse]
-'perf sched' {record|latency|replay|trace}
+'perf sched' {record|latency|map|replay|trace}
 
 DESCRIPTION
 -----------
-There are four variants of perf sched:
+There are five variants of perf sched:
 
   'perf sched record <command>' to record the scheduling events
   of an arbitrary workload.
@@ -30,8 +30,22 @@ There are four variants of perf sched:
   of the workload as it occurred when it was recorded - and can repeat
   it a number of times, measuring its performance.)
 
+  'perf sched map' to print a textual context-switching outline of
+  workload captured via perf sched record.  Columns stand for
+  individual CPUs, and the two-letter shortcuts stand for tasks that
+  are running on a CPU. A '*' denotes the CPU that had the event, and
+  a dot signals an idle CPU.
+
 OPTIONS
 -------
+-i::
+--input=<file>::
+        Input file name. (default: perf.data)
+
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
 -D::
 --dump-raw-trace=::
         Display verbose dump of the sched data.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index f442acc105b..29ad94293cd 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -104,6 +104,13 @@ OPTIONS
         normally don't - this option allows the latter to be run in
         system-wide mode.
 
+-i::
+--input=::
+        Input file name.
+
+-d::
+--debug-mode::
+        Do various checks like samples ordering and lost events.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index c405bcad6ac..b6da7affbbe 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -8,8 +8,8 @@ perf-stat - Run a command and gather performance counter statistics
 SYNOPSIS
 --------
 [verse]
-'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] <command>
-'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] -- <command> [<options>]
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
 
 DESCRIPTION
 -----------
@@ -35,21 +35,33 @@ OPTIONS
         child tasks do not inherit counters
 -p::
 --pid=<pid>::
-        stat events on existing pid
+        stat events on existing process id
+
+-t::
+--tid=<tid>::
+        stat events on existing thread id
+
 
 -a::
-        system-wide collection
+--all-cpus::
+        system-wide collection from all CPUs
 
 -c::
-        scale counter values
+--scale::
+	scale/normalize counter values
+
+-r::
+--repeat=<n>::
+	repeat command and print average + stddev (max: 100)
 
 -B::
+--big-num::
         print large numbers with thousands' separators according to locale
 
 -C::
 --cpu=::
-Count only on the list of cpus provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Count only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 In per-thread mode, this option is ignored. The -a option is still necessary
 to activate system-wide monitoring. Default is to count on all CPUs.
 
@@ -58,6 +70,19 @@ to activate system-wide monitoring. Default is to count on all CPUs.
 Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
 This option is only valid in system-wide mode.
 
+-n::
+--null::
+        null run - don't start any counters
+
+-v::
+--verbose::
+        be more verbose (show counter open errors, etc)
+
+-x SEP::
+--field-separator SEP::
+print counts using a CSV-style output to make it easy to import directly into
+spreadsheets. Columns are separated by the string specified in SEP.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 1c4b5f5b7f7..2c3b462f64b 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command does assorted sanity tests, initially thru linked routines but
+This command does assorted sanity tests, initially through linked routines but
 also will look for a directory with more tests in the form of scripts.
 
 OPTIONS
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 1f9687663f2..f6eb1cdafb7 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command generates and displays a performance counter profile in realtime.
+This command generates and displays a performance counter profile in real time.
 
 
 OPTIONS
@@ -27,8 +27,8 @@ OPTIONS
 
 -C <cpu-list>::
 --cpu=<cpu>::
-Monitor only on the list of cpus provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 Default is to monitor all CPUS.
 
 -d <seconds>::
@@ -50,6 +50,10 @@ Default is to monitor all CPUS.
 --count-filter=<count>::
 	Only display functions with more events than this.
 
+-g::
+--group::
+        Put the counters into a counter group.
+
 -F <freq>::
 --freq=<freq>::
 	Profile at this frequency.
@@ -68,7 +72,11 @@ Default is to monitor all CPUS.
 
 -p <pid>::
 --pid=<pid>::
-	Profile events on existing pid.
+	Profile events on existing Process ID.
+
+-t <tid>::
+--tid=<tid>::
+        Profile events on existing thread ID.
 
 -r <priority>::
 --realtime=<priority>::
@@ -78,6 +86,18 @@ Default is to monitor all CPUS.
 --sym-annotate=<symbol>::
         Annotate this symbol.
 
+-K::
+--hide_kernel_symbols::
+        Hide kernel symbols.
+
+-U::
+--hide_user_symbols::
+        Hide user symbols.
+
+-D::
+--dump-symtab::
+        Dump the symbol table used for profiling.
+
 -v::
 --verbose::
 	Be more verbose (show counter open errors, etc).
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index fca1d440291..221b823bc26 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -173,7 +173,7 @@ static const char * const diff_usage[] = {
 static const struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('m', "displacement", &show_displacement,
+	OPT_BOOLEAN('M', "displacement", &show_displacement,
 		    "Show position displacement relative to baseline"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 970a7f2a083..7ff746da7e6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -52,6 +52,8 @@
 #include <math.h>
 #include <locale.h>
 
+#define DEFAULT_SEPARATOR	" "
+
 static struct perf_event_attr default_attrs[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
@@ -82,8 +84,11 @@ static pid_t			*all_tids			=  NULL;
 static int			thread_num			=  0;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
-static bool			big_num				=  false;
+static bool			big_num				=  true;
+static int			big_num_opt			=  -1;
 static const char		*cpu_list;
+static const char		*csv_sep			= NULL;
+static bool			csv_output			= false;
 
 
 static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
@@ -449,12 +454,18 @@ static void print_noise(int counter, double avg)
 static void nsec_printout(int cpu, int counter, double avg)
 {
 	double msecs = avg / 1e6;
+	char cpustr[16] = { '\0', };
+	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-24s";
 
 	if (no_aggr)
-		fprintf(stderr, "CPU%-4d %18.6f  %-24s",
-			cpumap[cpu], msecs, event_name(counter));
-	else
-		fprintf(stderr, " %18.6f  %-24s", msecs, event_name(counter));
+		sprintf(cpustr, "CPU%*d%s",
+			csv_output ? 0 : -4,
+			cpumap[cpu], csv_sep);
+
+	fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(counter));
+
+	if (csv_output)
+		return;
 
 	if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) {
 		fprintf(stderr, " # %10.3f CPUs ",
@@ -466,18 +477,26 @@ static void abs_printout(int cpu, int counter, double avg)
 {
 	double total, ratio = 0.0;
 	char cpustr[16] = { '\0', };
+	const char *fmt;
+
+	if (csv_output)
+		fmt = "%s%.0f%s%s";
+	else if (big_num)
+		fmt = "%s%'18.0f%s%-24s";
+	else
+		fmt = "%s%18.0f%s%-24s";
 
 	if (no_aggr)
-		sprintf(cpustr, "CPU%-4d", cpumap[cpu]);
+		sprintf(cpustr, "CPU%*d%s",
+			csv_output ? 0 : -4,
+			cpumap[cpu], csv_sep);
 	else
 		cpu = 0;
 
-	if (big_num)
-		fprintf(stderr, "%s %'18.0f  %-24s",
-			cpustr, avg, event_name(counter));
-	else
-		fprintf(stderr, "%s %18.0f  %-24s",
-			cpustr, avg, event_name(counter));
+	fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(counter));
+
+	if (csv_output)
+		return;
 
 	if (MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) {
 		total = avg_stats(&runtime_cycles_stats[cpu]);
@@ -515,8 +534,9 @@ static void print_counter_aggr(int counter)
 	int scaled = event_scaled[counter];
 
 	if (scaled == -1) {
-		fprintf(stderr, " %18s  %-24s\n",
-			"<not counted>", event_name(counter));
+		fprintf(stderr, "%*s%s%-24s\n",
+			csv_output ? 0 : 18,
+			"<not counted>", csv_sep, event_name(counter));
 		return;
 	}
 
@@ -525,6 +545,11 @@ static void print_counter_aggr(int counter)
 	else
 		abs_printout(-1, counter, avg);
 
+	if (csv_output) {
+		fputc('\n', stderr);
+		return;
+	}
+
 	print_noise(counter, avg);
 
 	if (scaled) {
@@ -554,8 +579,12 @@ static void print_counter(int counter)
 		ena = cpu_counts[cpu][counter].ena;
 		run = cpu_counts[cpu][counter].run;
 		if (run == 0 || ena == 0) {
-			fprintf(stderr, "CPU%-4d %18s  %-24s", cpumap[cpu],
-					"<not counted>", event_name(counter));
+			fprintf(stderr, "CPU%*d%s%*s%s%-24s",
+				csv_output ? 0 : -4,
+				cpumap[cpu], csv_sep,
+				csv_output ? 0 : 18,
+				"<not counted>", csv_sep,
+				event_name(counter));
 
 			fprintf(stderr, "\n");
 			continue;
@@ -566,11 +595,13 @@ static void print_counter(int counter)
 		else
 			abs_printout(cpu, counter, val);
 
-		print_noise(counter, 1.0);
+		if (!csv_output) {
+			print_noise(counter, 1.0);
 
-		if (run != ena) {
-			fprintf(stderr, "  (scaled from %.2f%%)",
+			if (run != ena) {
+				fprintf(stderr, "  (scaled from %.2f%%)",
 					100.0 * run / ena);
+			}
 		}
 		fprintf(stderr, "\n");
 	}
@@ -582,21 +613,23 @@ static void print_stat(int argc, const char **argv)
 
 	fflush(stdout);
 
-	fprintf(stderr, "\n");
-	fprintf(stderr, " Performance counter stats for ");
-	if(target_pid == -1 && target_tid == -1) {
-		fprintf(stderr, "\'%s", argv[0]);
-		for (i = 1; i < argc; i++)
-			fprintf(stderr, " %s", argv[i]);
-	} else if (target_pid != -1)
-		fprintf(stderr, "process id \'%d", target_pid);
-	else
-		fprintf(stderr, "thread id \'%d", target_tid);
+	if (!csv_output) {
+		fprintf(stderr, "\n");
+		fprintf(stderr, " Performance counter stats for ");
+		if(target_pid == -1 && target_tid == -1) {
+			fprintf(stderr, "\'%s", argv[0]);
+			for (i = 1; i < argc; i++)
+				fprintf(stderr, " %s", argv[i]);
+		} else if (target_pid != -1)
+			fprintf(stderr, "process id \'%d", target_pid);
+		else
+			fprintf(stderr, "thread id \'%d", target_tid);
 
-	fprintf(stderr, "\'");
-	if (run_count > 1)
-		fprintf(stderr, " (%d runs)", run_count);
-	fprintf(stderr, ":\n\n");
+		fprintf(stderr, "\'");
+		if (run_count > 1)
+			fprintf(stderr, " (%d runs)", run_count);
+		fprintf(stderr, ":\n\n");
+	}
 
 	if (no_aggr) {
 		for (counter = 0; counter < nr_counters; counter++)
@@ -606,15 +639,17 @@ static void print_stat(int argc, const char **argv)
 			print_counter_aggr(counter);
 	}
 
-	fprintf(stderr, "\n");
-	fprintf(stderr, " %18.9f  seconds time elapsed",
-			avg_stats(&walltime_nsecs_stats)/1e9);
-	if (run_count > 1) {
-		fprintf(stderr, "   ( +- %7.3f%% )",
+	if (!csv_output) {
+		fprintf(stderr, "\n");
+		fprintf(stderr, " %18.9f  seconds time elapsed",
+				avg_stats(&walltime_nsecs_stats)/1e9);
+		if (run_count > 1) {
+			fprintf(stderr, "   ( +- %7.3f%% )",
 				100*stddev_stats(&walltime_nsecs_stats) /
 				avg_stats(&walltime_nsecs_stats));
+		}
+		fprintf(stderr, "\n\n");
 	}
-	fprintf(stderr, "\n\n");
 }
 
 static volatile int signr = -1;
@@ -644,6 +679,13 @@ static const char * const stat_usage[] = {
 	NULL
 };
 
+static int stat__set_big_num(const struct option *opt __used,
+			     const char *s __used, int unset)
+{
+	big_num_opt = unset ? 0 : 1;
+	return 0;
+}
+
 static const struct option options[] = {
 	OPT_CALLBACK('e', "event", NULL, "event",
 		     "event selector. use 'perf list' to list available events",
@@ -664,12 +706,15 @@ static const struct option options[] = {
 		    "repeat command and print average + stddev (max: 100)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
-	OPT_BOOLEAN('B', "big-num", &big_num,
-		    "print large numbers with thousands\' separators"),
+	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, 
+			   "print large numbers with thousands\' separators",
+			   stat__set_big_num),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu",
 		    "list of cpus to monitor in system-wide"),
 	OPT_BOOLEAN('A', "no-aggr", &no_aggr,
 		    "disable CPU count aggregation"),
+	OPT_STRING('x', "field-separator", &csv_sep, "separator",
+		   "print counts with custom separator"),
 	OPT_END()
 };
 
@@ -682,6 +727,25 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 
 	argc = parse_options(argc, argv, options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (csv_sep)
+		csv_output = true;
+	else
+		csv_sep = DEFAULT_SEPARATOR;
+
+	/*
+	 * let the spreadsheet do the pretty-printing
+	 */
+	if (csv_output) {
+		/* User explicitely passed -B? */
+		if (big_num_opt == 1) {
+			fprintf(stderr, "-B option not supported with -x\n");
+			usage_with_options(stat_usage, options);
+		} else /* Nope, so disable big number formatting */
+			big_num = false;
+	} else if (big_num_opt == 0) /* User passed --no-big-num */
+		big_num = false;
+
 	if (!argc && target_pid == -1 && target_tid == -1)
 		usage_with_options(stat_usage, options);
 	if (run_count <= 0)