perf bench: Also allow measuring memset()

This simply clones the respective memcpy() implementation.

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/4F16D743020000780006D735@nat28.tlf.novell.com
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 322 insertions, 0 deletions

diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index f7781c6267c0..a09bece6dad2 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -4,6 +4,7 @@
 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);
 extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used);
+extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR        "default"
 #define BENCH_FORMAT_DEFAULT            0
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
new file mode 100644
index 000000000000..a040fa77665b
--- /dev/null
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#define MEMSET_FN(fn, name, desc)               \
+        extern void *fn(void *, int, size_t);
+
+#include "mem-memset-x86-64-asm-def.h"
+
+#undef MEMSET_FN
+
+#endif
+
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
new file mode 100644
index 000000000000..a71dff97c1f5
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -0,0 +1,12 @@
+
+MEMSET_FN(__memset,
+        "x86-64-unrolled",
+        "unrolled memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c,
+        "x86-64-stosq",
+        "movsq-based memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c_e,
+        "x86-64-stosb",
+        "movsb-based memset() in arch/x86/lib/memset_64.S")
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
new file mode 100644
index 000000000000..cb9217063776
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -0,0 +1,6 @@
+#define memset MEMSET /* don't hide glibc's memset() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemset_c globl memset_c; memset_c
+#define Lmemset_c_e globl memset_c_e; memset_c_e
+#include "../../../arch/x86/lib/memset_64.S"
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
new file mode 100644
index 000000000000..9c0c6f0cba9b
--- /dev/null
+++ b/tools/perf/bench/mem-memset.c
@@ -0,0 +1,291 @@
+/*
+ * mem-memset.c
+ *
+ * memset: Simple memory set in various ways
+ *
+ * Trivial clone of mem-memcpy.c.
+ */
+#include <ctype.h>
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "mem-memset-arch.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/time.h>
+#include <errno.h>
+
+#define K 1024
+
+static const char       *length_str     = "1MB";
+static const char       *routine        = "default";
+static bool             use_clock;
+static int              clock_fd;
+static bool             only_prefault;
+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)"),
+        OPT_STRING('r', "routine", &routine, "default",
+                    "Specify routine to copy"),
+        OPT_BOOLEAN('c', "clock", &use_clock,
+                    "Use CPU clock for measuring"),
+        OPT_BOOLEAN('o', "only-prefault", &only_prefault,
+                    "Show only the result with page faults before memset()"),
+        OPT_BOOLEAN('n', "no-prefault", &no_prefault,
+                    "Show only the result without page faults before memset()"),
+        OPT_END()
+};
+
+typedef void *(*memset_t)(void *, int, size_t);
+
+struct routine {
+        const char *name;
+        const char *desc;
+        memset_t fn;
+};
+
+static const struct routine routines[] = {
+        { "default",
+          "Default memset() provided by glibc",
+          memset },
+#ifdef ARCH_X86_64
+
+#define MEMSET_FN(fn, name, desc) { name, desc, fn },
+#include "mem-memset-x86-64-asm-def.h"
+#undef MEMSET_FN
+
+#endif
+
+        { NULL,
+          NULL,
+          NULL   }
+};
+
+static const char * const bench_mem_memset_usage[] = {
+        "perf bench mem memset <options>",
+        NULL
+};
+
+static struct perf_event_attr clock_attr = {
+        .type           = PERF_TYPE_HARDWARE,
+        .config         = PERF_COUNT_HW_CPU_CYCLES
+};
+
+static void init_clock(void)
+{
+        clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+
+        if (clock_fd < 0 && errno == ENOSYS)
+                die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+        else
+                BUG_ON(clock_fd < 0);
+}
+
+static u64 get_clock(void)
+{
+        int ret;
+        u64 clk;
+
+        ret = read(clock_fd, &clk, sizeof(u64));
+        BUG_ON(ret != sizeof(u64));
+
+        return clk;
+}
+
+static double timeval2double(struct timeval *ts)
+{
+        return (double)ts->tv_sec +
+                (double)ts->tv_usec / (double)1000000;
+}
+
+static void alloc_mem(void **dst, size_t length)
+{
+        *dst = zalloc(length);
+        if (!dst)
+                die("memory allocation failed - maybe length is too large?\n");
+}
+
+static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
+{
+        u64 clock_start = 0ULL, clock_end = 0ULL;
+        void *dst = NULL;
+
+        alloc_mem(&dst, len);
+
+        if (prefault)
+                fn(dst, -1, len);
+
+        clock_start = get_clock();
+        fn(dst, 0, len);
+        clock_end = get_clock();
+
+        free(dst);
+        return clock_end - clock_start;
+}
+
+static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
+{
+        struct timeval tv_start, tv_end, tv_diff;
+        void *dst = NULL;
+
+        alloc_mem(&dst, len);
+