6 files changed, 113 insertions, 48 deletions

diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
index a72e36cb5394..57b4ed871459 100644
--- a/tools/perf/bench/mem-memcpy-arch.h
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -1,5 +1,5 @@
 
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMCPY_FN(fn, name, desc)               \
         extern void *fn(void *, const void *, size_t);
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 8cdca43016b2..5ce71d3b72cf 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -58,7 +58,7 @@ struct routine routines[] = {
         { "default",
           "Default memcpy() provided by glibc",
           memcpy },
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMCPY_FN(fn, name, desc) { name, desc, fn },
 #include "mem-memcpy-x86-64-asm-def.h"
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
index a040fa77665b..633800cb0dcb 100644
--- a/tools/perf/bench/mem-memset-arch.h
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -1,5 +1,5 @@
 
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMSET_FN(fn, name, desc)               \
         extern void *fn(void *, int, size_t);
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index 4a2f12081964..9af79d2b18e5 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -58,7 +58,7 @@ static const struct routine routines[] = {
         { "default",
           "Default memset() provided by glibc",
           memset },
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMSET_FN(fn, name, desc) { name, desc, fn },
 #include "mem-memset-x86-64-asm-def.h"
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 30d1c3225b46..d4c83c60b9b2 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -429,14 +429,14 @@ static int parse_cpu_list(const char *arg)
         return 0;
 }
 
-static void parse_setup_cpu_list(void)
+static int parse_setup_cpu_list(void)
 {
         struct thread_data *td;
         char *str0, *str;
         int t;
 
         if (!g->p.cpu_list_str)
-                return;
+                return 0;
 
         dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
 
@@ -500,8 +500,12 @@ static void parse_setup_cpu_list(void)
 
                 dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul);
 
-                BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus);
-                BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus);
+                if (bind_cpu_0 >= g->p.nr_cpus || bind_cpu_1 >= g->p.nr_cpus) {
+                        printf("\nTest not applicable, system has only %d CPUs.\n", g->p.nr_cpus);
+                        return -1;
+                }
+
+                BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0);
                 BUG_ON(bind_cpu_0 > bind_cpu_1);
 
                 for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
@@ -541,6 +545,7 @@ out:
                 printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
 
         free(str0);
+        return 0;
 }
 
 static int parse_cpus_opt(const struct option *opt __maybe_unused,
@@ -561,14 +566,14 @@ static int parse_node_list(const char *arg)
         return 0;
 }
 
-static void parse_setup_node_list(void)
+static int parse_setup_node_list(void)
 {
         struct thread_data *td;
         char *str0, *str;
         int t;
 
         if (!g->p.node_list_str)
-                return;
+                return 0;
 
         dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
 
@@ -619,8 +624,12 @@ static void parse_setup_node_list(void)
 
                 dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step);
 
-                BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes);
-                BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes);
+                if (bind_node_0 >= g->p.nr_nodes || bind_node_1 >= g->p.nr_nodes) {
+                        printf("\nTest not applicable, system has only %d nodes.\n", g->p.nr_nodes);
+                        return -1;
+                }
+
+                BUG_ON(bind_node_0 < 0 || bind_node_1 < 0);
                 BUG_ON(bind_node_0 > bind_node_1);
 
                 for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) {
@@ -651,6 +660,7 @@ out:
                 printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
 
         free(str0);
+        return 0;
 }
 
 static int parse_nodes_opt(const struct option *opt __maybe_unused,
@@ -1110,7 +1120,7 @@ static void *worker_thread(void *__tdata)
                 /* Check whether our max runtime timed out: */
                 if (g->p.nr_secs) {
                         timersub(&stop, &start0, &diff);
-                        if (diff.tv_sec >= g->p.nr_secs) {
+                        if ((u32)diff.tv_sec >= g->p.nr_secs) {
                                 g->stop_work = true;
                                 break;
                         }
@@ -1157,7 +1167,7 @@ static void *worker_thread(void *__tdata)
                         runtime_ns_max += diff.tv_usec * 1000;
 
                         if (details >= 0) {
-                                printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n",
+                                printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016"PRIx64"]\n",
                                         process_nr, thread_nr, runtime_ns_max / bytes_done, val);
                         }
                         fflush(stdout);
@@ -1356,8 +1366,8 @@ static int init(void)
         init_thread_data();
 
         tprintf("#\n");
-        parse_setup_cpu_list();
-        parse_setup_node_list();
+        if (parse_setup_cpu_list() || parse_setup_node_list())
+                return -1;
         tprintf("#\n");
 
         print_summary();
@@ -1600,7 +1610,6 @@ static int run_bench_numa(const char *name, const char **argv)
         return 0;
 
 err:
-        usage_with_options(numa_usage, options);
         return -1;
 }
 
@@ -1701,8 +1710,7 @@ static int bench_all(void)
         BUG_ON(ret < 0);
 
         for (i = 0; i < nr; i++) {
-                if (run_bench_numa(tests[i][0], tests[i] + 1))
-                        return -1;
+                run_bench_numa(tests[i][0], tests[i] + 1);
         }
 
         printf("\n");
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 69cfba8d4c6c..07a8d7646a15 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -7,9 +7,7 @@
  * 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"
@@ -28,12 +26,24 @@
 #include <sys/time.h>
 #include <sys/types.h>
 
+#include <pthread.h>
+
+struct thread_data {
+        int                     nr;
+        int                     pipe_read;
+        int                     pipe_write;
+        pthread_t               pthread;
+};
+
 #define LOOPS_DEFAULT 1000000
-static int loops = LOOPS_DEFAULT;
+static  int                     loops = LOOPS_DEFAULT;
+
+/* Use processes by default: */
+static bool                     threaded;
 
 static const struct option options[] = {
-        OPT_INTEGER('l', "loop", &loops,
-                    "Specify number of loops"),
+        OPT_INTEGER('l', "loop",        &loops,         "Specify number of loops"),
+        OPT_BOOLEAN('T', "threaded",    &threaded,      "Specify threads/process based task setup"),
         OPT_END()
 };
 
@@ -42,13 +52,37 @@ static const char * const bench_sched_pipe_usage[] = {
         NULL
 };
 
-int bench_sched_pipe(int argc, const char **argv,
-                     const char *prefix __maybe_unused)
+static void *worker_thread(void *__tdata)
 {
-        int pipe_1[2], pipe_2[2];
+        struct thread_data *td = __tdata;
         int m = 0, i;
+        int ret;
+
+        for (i = 0; i < loops; i++) {
+                if (!td->nr) {
+                        ret = read(td->pipe_read, &m, sizeof(int));
+                        BUG_ON(ret != sizeof(int));
+                        ret = write(td->pipe_write, &m, sizeof(int));
+                        BUG_ON(ret != sizeof(int));
+                } else {
+                        ret = write(td->pipe_write, &m, sizeof(int));
+                        BUG_ON(ret != sizeof(int));
+                        ret = read(td->pipe_read, &m, sizeof(int));
+                        BUG_ON(ret != sizeof(int));
+                }
+        }
+
+        return NULL;
+}
+
+int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+        struct thread_data threads[2], *td;
+        int pipe_1[2], pipe_2[2];
         struct timeval start, stop, diff;
         unsigned long long result_usec = 0;
+        int nr_threads = 2;
+        int t;
 
         /*
          * why does "ret" exist?
@@ -58,43 +92,66 @@ int bench_sched_pipe(int argc, const char **argv,
         int __maybe_unused ret, wait_stat;
         pid_t pid, retpid __maybe_unused;
 
-        argc = parse_options(argc, argv, options,
-                             bench_sched_pipe_usage, 0);
+        argc = parse_options(argc, argv, options, bench_sched_pipe_usage, 0);
 
         BUG_ON(pipe(pipe_1));
         BUG_ON(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));
+        for (t = 0; t < nr_threads; t++) {
+                td = threads + t;
+
+                td->nr = t;
+
+                if (t == 0) {
+                        td->pipe_read = pipe_1[0];
+                        td->pipe_write = pipe_2[1];
+                } else {
+                        td->pipe_write = pipe_1[1];
+                        td->pipe_read = pipe_2[0];
                 }
         }
 
-        gettimeofday(&stop, NULL);
-        timersub(&stop, &start, &diff);
 
-        if (pid) {
+        if (threaded) {
+
+                for (t = 0; t < nr_threads; t++) {
+                        td = threads + t;
+
+                        ret = pthread_create(&td->pthread, NULL, worker_thread, td);
+                        BUG_ON(ret);
+                }
+
+                for (t = 0; t < nr_threads; t++) {
+                        td = threads + t;
+
+                        ret = pthread_join(td->pthread, NULL);
+                        BUG_ON(ret);
+                }
+
+        } else {
+                pid = fork();
+                assert(pid >= 0);
+
+                if (!pid) {
+                        worker_thread(threads + 0);
+                        exit(0);
+                } else {
+                        worker_thread(threads + 1);
+                }
+
                 retpid = waitpid(pid, &wait_stat, 0);
                 assert((retpid == pid) && WIFEXITED(wait_stat));
-        } else {
-                exit(0);
         }
 
+        gettimeofday(&stop, NULL);
+        timersub(&stop, &start, &diff);
+
         switch (bench_format) {
         case BENCH_FORMAT_DEFAULT:
-                printf("# Executed %d pipe operations between two tasks\n\n",
-                        loops);
+                printf("# Executed %d pipe operations between two %s\n\n",
+                        loops, threaded ? "threads" : "processes");
 
                 result_usec = diff.tv_sec * 1000000;
                 result_usec += diff.tv_usec;