25 files changed, 471 insertions, 201 deletions

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index a3dbadb26ef5..f3c716a4cad3 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This 'perf bench' command is general framework for benchmark suites.
+This 'perf bench' command is a general framework for benchmark suites.
 
 COMMON OPTIONS
 --------------
@@ -45,14 +45,20 @@ SUBSYSTEM
 'sched'::
         Scheduler and IPC mechanisms.
 
+'mem'::
+        Memory access performance.
+
+'all'::
+        All benchmark subsystems.
+
 SUITES FOR 'sched'
 ~~~~~~~~~~~~~~~~~~
 *messaging*::
 Suite for evaluating performance of scheduler and IPC mechanisms.
 Based on hackbench by Rusty Russell.
 
-Options of *pipe*
-^^^^^^^^^^^^^^^^^
+Options of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
 -p::
 --pipe::
 Use pipe() instead of socketpair()
@@ -115,6 +121,72 @@ Example of *pipe*
                 59004 ops/sec
 ---------------------
 
+SUITES FOR 'mem'
+~~~~~~~~~~~~~~~~
+*memcpy*::
+Suite for evaluating performance of simple memory copy in various ways.
+
+Options of *memcpy*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to copy (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to copy (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
+
+-i::
+--iterations::
+Repeat memcpy invocation this number of times.
+
+-c::
+--clock::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memcpy.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memcpy.
+
+*memset*::
+Suite for evaluating performance of simple memory set in various ways.
+
+Options of *memset*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to set (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to set (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
+
+-i::
+--iterations::
+Repeat memset invocation this number of times.
+
+-c::
+--clock::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memset.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memset.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index d698c118a602..75d74e5db8d5 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -155,7 +155,7 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)/util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 71557225bf92..d990365cafa0 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -32,13 +32,13 @@ static bool		no_prefault;
 static const struct option options[] = {
         OPT_STRING('l', "length", &length_str, "1MB",
                     "Specify length of memory to copy. "
-                    "available unit: B, MB, GB (upper and lower)"),
+                    "Available units: B, KB, MB, GB and TB (upper and lower)"),
         OPT_STRING('r', "routine", &routine, "default",
                     "Specify routine to copy"),
         OPT_INTEGER('i', "iterations", &iterations,
                     "repeat memcpy() invocation this number of times"),
         OPT_BOOLEAN('c', "clock", &use_clock,
-                    "Use CPU clock for measuring"),
+                    "Use cycles event instead of gettimeofday() for measuring"),
         OPT_BOOLEAN('o', "only-prefault", &only_prefault,
                     "Show only the result with page faults before memcpy()"),
         OPT_BOOLEAN('n', "no-prefault", &no_prefault,
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index e9079185bd72..bf0d5f552017 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -31,14 +31,14 @@ static bool		no_prefault;
 
 static const struct option options[] = {