11 files changed, 795 insertions, 0 deletions

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
new file mode 100644
index 000000000000..ae525ac5a2ce
--- /dev/null
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -0,0 +1,120 @@
+perf-bench(1)
+============
+
+NAME
+----
+perf-bench - General framework for benchmark suites
+
+SYNOPSIS
+--------
+[verse]
+'perf bench' [<common options>] <subsystem> <suite> [<options>]
+
+DESCRIPTION
+-----------
+This 'perf bench' command is general framework for benchmark suites.
+
+COMMON OPTIONS
+--------------
+-f::
+--format=::
+Specify format style.
+Current available format styles are,
+
+'default'::
+Default style. This is mainly for human reading.
+---------------------
+% perf bench sched pipe                      # with no style specify
+(executing 1000000 pipe operations between two tasks)
+        Total time:5.855 sec
+                5.855061 usecs/op
+		170792 ops/sec
+---------------------
+
+'simple'::
+This simple style is friendly for automated
+processing by scripts.
+---------------------
+% perf bench --format=simple sched pipe      # specified simple
+5.988
+---------------------
+
+SUBSYSTEM
+---------
+
+'sched'::
+	Scheduler and IPC mechanisms.
+
+SUITES FOR 'sched'
+~~~~~~~~~~~~~~~~~~
+*messaging*::
+Suite for evaluating performance of scheduler and IPC mechanisms.
+Based on hackbench by Rusty Russell.
+
+Options of *pipe*
+^^^^^^^^^^^^^^^^^
+-p::
+--pipe::
+Use pipe() instead of socketpair()
+
+-t::
+--thread::
+Be multi thread instead of multi process
+
+-g::
+--group=::
+Specify number of groups
+
+-l::
+--loop=::
+Specify number of loops
+
+Example of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
+
+---------------------
+% perf bench sched messaging                 # run with default
+options (20 sender and receiver processes per group)
+(10 groups == 400 processes run)
+
+      Total time:0.308 sec
+
+% perf bench sched messaging -t -g 20        # be multi-thread,with 20 groups
+(20 sender and receiver threads per group)
+(20 groups == 800 threads run)
+
+      Total time:0.582 sec
+---------------------
+
+*pipe*::
+Suite for pipe() system call.
+Based on pipe-test-1m.c by Ingo Molnar.
+
+Options of *pipe*
+^^^^^^^^^^^^^^^^^
+-l::
+--loop=::
+Specify number of loops.
+
+Example of *pipe*
+^^^^^^^^^^^^^^^^^
+
+---------------------
+% perf bench sched pipe
+(executing 1000000 pipe operations between two tasks)
+
+        Total time:8.091 sec
+                8.091833 usecs/op
+                123581 ops/sec
+
+% perf bench sched pipe -l 1000              # loop 1000
+(executing 1000 pipe operations between two tasks)
+
+        Total time:0.016 sec
+                16.948000 usecs/op
+                59004 ops/sec
+---------------------
+
+SEE ALSO
+--------
+linkperf:perf[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index e6d42728a33a..f7cd89622cf4 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -421,6 +421,13 @@ LIB_OBJS += util/hist.o
 LIB_OBJS += util/data_map.o
 
 BUILTIN_OBJS += builtin-annotate.o
+
+BUILTIN_OBJS += builtin-bench.o
+
+# Benchmark modules
+BUILTIN_OBJS += bench/sched-messaging.o
+BUILTIN_OBJS += bench/sched-pipe.o
+
 BUILTIN_OBJS += builtin-help.o
 BUILTIN_OBJS += builtin-sched.o
 BUILTIN_OBJS += builtin-list.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
new file mode 100644
index 000000000000..9fbd8d745fa1
--- /dev/null
+++ b/tools/perf/bench/bench.h
@@ -0,0 +1,16 @@
+#ifndef BENCH_H
+#define BENCH_H
+
+extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
+extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
+
+#define BENCH_FORMAT_DEFAULT_STR	"default"
+#define BENCH_FORMAT_DEFAULT		0
+#define BENCH_FORMAT_SIMPLE_STR		"simple"
+#define BENCH_FORMAT_SIMPLE		1
+
+#define BENCH_FORMAT_UNKNOWN		-1
+
+extern int bench_format;
+
+#endif
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
new file mode 100644
index 000000000000..605a2a959aa8
--- /dev/null
+++ b/tools/perf/bench/sched-messaging.c
@@ -0,0 +1,336 @@
+/*
+ *
+ * builtin-bench-messaging.c
+ *
+ * messaging: Benchmark for scheduler and IPC mechanisms
+ *
+ * Based on hackbench by Rusty Russell <rusty@rustcorp.com.au>
+ * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
+ *
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+#include "../builtin.h"
+#include "bench.h"
+
+/* Test groups of 20 processes spraying to 20 receivers */
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/wait.h>
+#include <sys/time.h>
+#include <sys/poll.h>
+#include <limits.h>
+
+#define DATASIZE 100
+
+static int use_pipes = 0;
+static unsigned int loops = 100;
+static unsigned int thread_mode = 0;
+static unsigned int num_groups = 10;
+
+struct sender_context {
+	unsigned int num_fds;
+	int ready_out;
+	int wakefd;
+	int out_fds[0];
+};
+
+struct receiver_context {
+	unsigned int num_packets;
+	int in_fds[2];
+	int ready_out;
+	int wakefd;
+};
+
+static void barf(const char *msg)
+{
+	fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno));
+	exit(1);
+}
+
+static void fdpair(int fds[2])
+{
+	if (use_pipes) {
+		if (pipe(fds) == 0)
+			return;
+	} else {
+		if (socketpair(AF_UNIX, SOCK_STREAM, 0, fds) == 0)
+			return;
+	}
+
+	barf(use_pipes ? "pipe()" : "socketpair()");
+}
+
+/* Block until we're ready to go */
+static void ready(int ready_out, int wakefd)
+{
+	char dummy;
+	struct pollfd pollfd = { .fd = wakefd, .events = POLLIN };
+
+	/* Tell them we're ready. */
+	if (write(ready_out, &dummy, 1) != 1)
+		barf("CLIENT: ready write");
+
+	/* Wait for "GO" signal */
+	if (poll(&pollfd, 1, -1) != 1)
+		barf("poll");
+}
+
+/* Sender sprays loops messages down each file descriptor */
+static void *sender(struct sender_context *ctx)
+{
+	char data[DATASIZE];
+	unsigned int i, j;
+
+	ready(ctx->ready_out, ctx->wakefd);
+
+	/* Now pump to every receiver. */
+	for (i = 0; i < loops; i++) {
+		for (j = 0; j < ctx->num_fds; j++) {
+			int ret, done = 0;
+
+again:
+			ret = write(ctx->out_fds[j], data + done,
+				    sizeof(data)-done);
+			if (ret < 0)
+				barf("SENDER: write");
+			done += ret;
+			if (done < DATASIZE)
+				goto again;
+		}
+	}
+
+	return NULL;
+}
+
+
+/* One receiver per fd */
+static void *receiver(struct receiver_context* ctx)
+{
+	unsigned int i;
+
+	if (!thread_mode)
+		close(ctx->in_fds[1]);
+
+	/* Wait for start... */
+	ready(ctx->ready_out, ctx->wakefd);
+
+	/* Receive them all */
+	for (i = 0; i < ctx->num_packets; i++) {
+		char data[DATASIZE];
+		int ret, done = 0;
+
+again:
+		ret = read(ctx->in_fds[0], data + done, DATASIZE - done);
+		if (ret < 0)
+			barf("SERVER: read");
+		done += ret;
+		if (done < DATASIZE)
+			goto again;
+	}
+
+	return NULL;
+}
+
+static pthread_t create_worker(void *ctx, void *(*func)(void *))
+{
+	pthread_attr_t attr;
+	pthread_t childid;
+	int err;
+
+	if (!thread_mode) {
+		/* process mode */
+		/* Fork the receiver. */
+		switch (fork()) {
+		case -1:
+			barf("fork()");
+			break;
+		case 0:
+			(*func) (ctx);
+			exit(0);
+			break;
+		default:
+			break;
+		}
+
+		return (pthread_t)0;
+	}
+
+	if (pthread_attr_init(&attr) != 0)
+		barf("pthread_attr_init:");
+
+#ifndef __ia64__
+	if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0)
+		barf("pthread_attr_setstacksize");
+#endif
+
+	err = pthread_create(&childid, &attr, func, ctx);
+	if (err != 0) {
+		fprintf(stderr, "pthread_create failed: %s (%d)\n",
+			strerror(err), err);
+		exit(-1);
+	}
+	return childid;
+}
+
+static void reap_worker(pthread_t id)
+{
+	int proc_status;
+	void *thread_status;
+
+	if (!thread_mode) {
+		/* process mode */
+		wait(&proc_status);
+		if (!WIFEXITED(proc_status))
+			exit(1);
+	} else {
+		pthread_join(id, &thread_status);
+	}
+}
+
+/* One group of senders and receivers */
+static unsigned int group(pthread_t *pth,
+		unsigned int num_fds,
+		int ready_out,
+		int wakefd)
+{
+	unsigned int i;
+	struct sender_context *snd_ctx = malloc(sizeof(struct sender_context)
+			+ num_fds * sizeof(int));
+
+	if (!snd_ctx)
+		barf("malloc()");
+
+	for (i = 0; i < num_fds; i++) {
+		int fds[2];
+		struct receiver_context *ctx = malloc(sizeof(*ctx));
+
+		if (!ctx)
+			barf("malloc()");
+
+
+		/* Create the pipe between client and server */
+		fdpair(fds);
+
+		ctx->num_packets = num_fds * loops;
+		ctx->in_fds[0] = fds[0];
+		ctx->in_fds[1] = fds[1];
+		ctx->ready_out = ready_out;
+		ctx->wakefd = wakefd;
+
+		pth[i] = create_worker(ctx, (void *)receiver);
+
+		snd_ctx->out_fds[i] = fds[1];
+		if (!thread_mode)
+			close(fds[0]);
+	}
+
+	/* Now we have all the fds, fork the senders */
+	for (i = 0; i < num_fds; i++) {
+		snd_ctx->ready_out = ready_out;
+		snd_ctx->wakefd = wakefd;
+		snd_ctx->num_fds = num_fds;
+
+		pth[num_fds+i] = create_worker(snd_ctx, (void *)sender);
+	}
+
+	/* Close the fds we have left */
+	if (!thread_mode)
+		for (i = 0; i < num_fds; i++)
+			close(snd_ctx->out_fds[i]);
+
+	/* Return number of children to reap */
+	return num_fds * 2;
+}
+
+static const struct option options[] = {
+	OPT_BOOLEAN('p', "pipe", &use_pipes,
+		    "Use pipe() instead of socketpair()"),
+	OPT_BOOLEAN('t', "thread", &thread_mode,
+		    "Be multi thread instead of multi process"),
+	OPT_INTEGER('g', "group", &num_groups,
+		    "Specify number of groups"),
+	OPT_INTEGER('l', "loop", &loops,
+		    "Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_sched_message_usage[] = {
+	"perf bench sched messaging <options>",
+	NULL
+};
+
+int bench_sched_messaging(int argc, const char **argv,
+		    const char *prefix __used)
+{
+	unsigned int i, total_children;
+	struct timeval start, stop, diff;
+	unsigned int num_fds = 20;
+	int readyfds[2], wakefds[2];
+	char dummy;
+	pthread_t *pth_tab;
+
+	argc = parse_options(argc, argv, options,
+			     bench_sched_message_usage, 0);
+
+	pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t));
+	if (!pth_tab)
+		barf("main:malloc()");
+
+	fdpair(readyfds);
+	fdpair(wakefds);
+
+	total_children = 0;
+	for (i = 0; i < num_groups; i++)
+		total_children += group(pth_tab+total_children, num_fds,
+					readyfds[1], wakefds[0]);
+
+	/* Wait for everyone to be ready */
+	for (i = 0; i < total_children; i++)
+		if (read(readyfds[0], &dummy, 1) != 1)
+			barf("Reading for readyfds");
+
+	gettimeofday(&start, NULL);
+
+	/* Kick them off */
+	if (write(wakefds[1], &dummy, 1) != 1)
+		barf("Writing to start them");
+
+	/* Reap them all */
+	for (i = 0; i < total_children; i++)
+		reap_worker(pth_tab[i]);
+
+	gettimeofday(&stop, NULL);
+
+	timersub(&stop, &start, &diff);
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		printf("# %d sender and receiver %s per group\n",
+		       num_fds, thread_mode ? "threads" : "processes");
+		printf("# %d groups == %d %s run\n\n",
+		       num_groups, num_groups * 2 * num_fds,
+		       thread_mode ? "threads" : "processes");
+		printf(" %14s: %lu.%03lu [sec]\n", "Total time",
+		       diff.tv_sec, diff.tv_usec/1000);
+		break;
+	case BENCH_FORMAT_SIMPLE:
+		printf("%lu.%03lu\n", diff.tv_sec, diff.tv_usec/1000);
+		break;
+	default:
+		/* reaching here is something disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+		break;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
new file mode 100644
index 000000000000..238185f97977
--- /dev/null
+++ b/tools/perf/bench/sched-pipe.c
@@ -0,0 +1,124 @@
+/*
+ *
+ * builtin-bench-pipe.c
+ *
+ * pipe: Benchmark for pipe()
+ *
+ * Based on pipe-test-1m.c by Ingo Molnar <mingo@redhat.com>
+ *  http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c
+ * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
+ *
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+#include "../builtin.h"
+#include "bench.h"
+
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/wait.h>
+#include <linux/unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+#include <sys/time.h>
+#include <sys/types.h>
+
+#define LOOPS_DEFAULT 1000000
+static int loops = LOOPS_DEFAULT;
+
+static const struct option options[] = {
+	OPT_INTEGER('l', "loop", &loops,
+		    "Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_sched_pipe_usage[] = {
+	"perf bench sched pipe <options>",
+	NULL
+};
+
+int bench_sched_pipe(int argc, const char **argv,
+		     const char *prefix __used)
+{
+	int pipe_1[2], pipe_2[2];
+	int m = 0, i;
+	struct timeval start, stop, diff;
+	unsigned long long result_usec = 0;
+
+	/*
+	 * why does "ret" exist?
+	 * discarding returned value of read(), write()
+	 * causes error in building environment for perf
+	 */
+	int ret, wait_stat;
+	pid_t pid, retpid;
+
+	argc = parse_options(argc, argv, options,
+			     bench_sched_pipe_usage, 0);
+
+	assert(!pipe(pipe_1));
+	assert(!pipe(pipe_2));
+
+	pid = fork();
+	assert(pid >= 0);
+
+	gettimeofday(&start, NULL);
+
+	if (!pid) {
+		for (i = 0; i < loops; i++) {
+			ret = read(pipe_1[0], &m, sizeof(int));
+			ret = write(pipe_2[1], &m, sizeof(int));
+		}
+	} else {
+		for (i = 0; i < loops; i++) {
+			ret = write(pipe_1[1], &m, sizeof(int));
+			ret = read(pipe_2[0], &m, sizeof(int));
+		}
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
+	if (pid) {
+		retpid = waitpid(pid, &wait_stat, 0);
+		assert((retpid == pid) && WIFEXITED(wait_stat));
+		return 0;
+	}
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		printf("# Extecuted %d pipe operations between two tasks\n\n",
+			loops);
+
+		result_usec = diff.tv_sec * 1000000;
+		result_usec += diff.tv_usec;
+
+		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
+		       diff.tv_sec, diff.tv_usec/1000);
+
+		printf(" %14lf usecs/op\n",
+		       (double)result_usec / (double)loops);
+		printf(" %14d ops/sec\n",
+		       (int)((double)loops /
+			     ((double)result_usec / (double)1000000)));
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%lu.%03lu\n",
+		       diff.tv_sec, diff.tv_usec / 1000);
+		break;
+
+	default:
+		/* reaching here is something disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+		break;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
new file mode 100644
index 000000000000..90c39baae0de
--- /dev/null
+++ b/tools/perf/builtin-bench.c
@@ -0,0 +1,183 @@
+/*
+ *
+ * builtin-bench.c
+ *
+ * General benchmarking subsystem provided by perf
+ *
+ * Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
+ *
+ */
+
+/*
+ *
+ * Available subsystem list:
+ *  sched ... scheduler and IPC mechanism
+ *
+ */
+
+#include "perf.h"
+#include "util/util.h"
+#include "util/parse-options.h"
+#include "builtin.h"
+#include "bench/bench.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+struct bench_suite {
+	const char *name;
+	const char *summary;
+	int (*fn)(int, const char **, const char *);
+};
+
+static struct bench_suite sched_suites[] = {
+	{ "messaging",
+	  "Benchmark for scheduler and IPC mechanisms",
+	  bench_sched_messaging },
+	{ "pipe",
+	  "Flood of communication over pipe() between two processes",
+	  bench_sched_pipe      },
+	{ NULL,
+	  NULL,
+	  NULL                  }
+};
+
+struct bench_subsys {
+	const char *name;
+	const char *summary;
+	struct bench_suite *suites;
+};
+
+static struct bench_subsys subsystems[] = {
+	{ "sched",
+	  "scheduler and IPC mechanism",
+	  sched_suites },
+	{ NULL,
+	  NULL,
+	  NULL         }
+};
+
+static void dump_suites(int subsys_index)
+{
+	int i;
+
+	printf("List of available suites for %s...\n\n",
+	       subsystems[subsys_index].name);
+
+	for (i = 0; subsystems[subsys_index].suites[i].name; i++)
+		printf("\t%s: %s\n",
+		       subsystems[subsys_index].suites[i].name,
+		       subsystems[subsys_index].suites[i].summary);
+
+	printf("\n");
+	return;
+}
+
+static char *bench_format_str;
+int bench_format = BENCH_FORMAT_DEFAULT;
+
+static const struct option bench_options[] = {
+	OPT_STRING('f', "format", &bench_format_str, "default",
+		    "Specify format style"),
+	OPT_END()
+};
+
+static const char * const bench_usage[] = {
+	"perf bench [<common options>] <subsystem> <suite> [<options>]",
+	NULL
+};
+
+static void print_usage(void)
+{
+	int i;
+
+	printf("Usage: \n");
+	for (i = 0; bench_usage[i]; i++)
+		printf("\t%s\n", bench_usage[i]);
+	printf("\n");
+
+	printf("List of available subsystems...\n\n");
+
+	for (i = 0; subsystems[i].name; i++)
+		printf("\t%s: %s\n",
+		       subsystems[i].name, subsystems[i].summary);
+	printf("\n");
+}
+
+static int bench_str2int(char *str)
+{
+	if (!str)
+		return BENCH_FORMAT_DEFAULT;
+
+	if (!strcmp(str, BENCH_FORMAT_DEFAULT_STR))
+		return BENCH_FORMAT_DEFAULT;
+	else if (!strcmp(str, BENCH_FORMAT_SIMPLE_STR))
+		return BENCH_FORMAT_SIMPLE;
+
+	return BENCH_FORMAT_UNKNOWN;
+}
+
+int cmd_bench(int argc, const char **argv, const char *prefix __used)
+{
+	int i, j, status = 0;
+
+	if (argc < 2) {
+		/* No subsystem specified. */
+		print_usage();
+		goto end;
+	}
+
+	argc = parse_options(argc, argv, bench_options, bench_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	bench_format = bench_str2int(bench_format_str);
+	if (bench_format == BENCH_FORMAT_UNKNOWN) {
+		printf("Unknown format descriptor:%s\n", bench_format_str);
+		goto end;
+	}
+
+	if (argc < 1) {
+		print_usage();
+		goto end;
+	}
+
+	for (i = 0; subsystems[i].name; i++) {
+		if (strcmp(subsystems[i].name, argv[0]))
+			continue;
+
+		if (argc < 2) {
+			/* No suite specified. */
+			dump_suites(i);
+			goto end;
+		}
+
+		for (j = 0; subsystems[i].suites[j].name; j++) {
+			if (strcmp(subsystems[i].suites[j].name, argv[1]))
+				continue;
+
+			if (bench_format == BENCH_FORMAT_DEFAULT)
+				printf("# Running %s/%s benchmark...\n",
+				       subsystems[i].name,
+				       subsystems[i].suites[j].name);
+			status = subsystems[i].suites[j].fn(argc - 1,
+							    argv + 1, prefix);
+			goto end;
+		}
+
+		if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) {
+			dump_suites(i);
+			goto end;
+		}
+
+		printf("Unknown suite:%s for %s\n", argv[1], argv[0]);
+		status = 1;
+		goto end;
+	}
+
+	printf("Unknown subsystem:%s\n", argv[0]);
+	status = 1;
+
+end:
+	return status;
+}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index e11d8d231c3b..f0cd5b139b7c 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -15,6 +15,7 @@ extern int read_line_with_nul(char *buf, int size, FILE *file);
 extern int check_pager_config(const char *cmd);
 
 extern int cmd_annotate(int argc, const char **argv, const char *prefix);
+extern int cmd_bench(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
 extern int cmd_sched(int argc, const char **argv, const char *prefix);
 extern int cmd_list(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 00326e230d87..981c40b9a5e2 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -3,6 +3,7 @@
 # command name			category [deprecated] [common]
 #
 perf-annotate			mainporcelain common
+perf-bench			mainporcelain common
 perf-list			mainporcelain common
 perf-sched			mainporcelain common
 perf-record			mainporcelain common
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index fdd42a824c98..f000c30877ac 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -137,6 +137,8 @@ enum sw_event_ids {
 	PERF_COUNT_SW_CPU_MIGRATIONS	= 4,
 	PERF_COUNT_SW_PAGE_FAULTS_MIN	= 5,
 	PERF_COUNT_SW_PAGE_FAULTS_MAJ	= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS	= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS	= 8,
 };
 
 Counters of the type PERF_TYPE_TRACEPOINT are available when the ftrace event
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 601f403fbdac..8936786b42ea 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -289,6 +289,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "list", cmd_list, 0 },
 		{ "record", cmd_record, 0 },
 		{ "report", cmd_report, 0 },
+		{ "bench", cmd_bench, 0 },
 		{ "stat", cmd_stat, 0 },
 		{ "timechart", cmd_timechart, 0 },
 		{ "top", cmd_top, 0 },
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 097938a96d74..0faf4f2bb5ca 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -48,6 +48,8 @@ static struct event_symbol event_symbols[] = {
   { CSW(PAGE_FAULTS_MAJ),	"major-faults",		""		},
   { CSW(CONTEXT_SWITCHES),	"context-switches",	"cs"		},
   { CSW(CPU_MIGRATIONS),	"cpu-migrations",	"migrations"	},
+  { CSW(ALIGNMENT_FAULTS),	"alignment-faults",	""		},
+  { CSW(EMULATION_FAULTS),	"emulation-faults",	""		},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -76,6 +78,8 @@ static const char *sw_event_names[] = {
 	"CPU-migrations",
 	"minor-faults",
 	"major-faults",
+	"alignment-faults",
+	"emulation-faults",
 };
 
 #define MAX_ALIASES 8