Merge remote-tracking branch 'remotes/thuth-gitlab/tags/pull-request-2021-03-12' into staging

* Move unit and bench tests into separate directories
* Clean-up and improve gitlab-ci jobs
* Drop the non-working "check-speed" makefile target
* Minor documentation updates

# gpg: Signature made Fri 12 Mar 2021 17:18:45 GMT
# gpg:                using RSA key 27B88847EEE0250118F3EAB92ED9D774FE702DB5
# gpg:                issuer "thuth@redhat.com"
# gpg: Good signature from "Thomas Huth <th.huth@gmx.de>" [full]
# gpg:                 aka "Thomas Huth <thuth@redhat.com>" [full]
# gpg:                 aka "Thomas Huth <huth@tuxfamily.org>" [full]
# gpg:                 aka "Thomas Huth <th.huth@posteo.de>" [unknown]
# Primary key fingerprint: 27B8 8847 EEE0 2501 18F3  EAB9 2ED9 D774 FE70 2DB5

* remotes/thuth-gitlab/tags/pull-request-2021-03-12:
  README: Add Documentation blurb
  MAINTAINERS: Merge the Gitlab-CI section into the generic CI section
  tests: remove "make check-speed" in favor of "make bench"
  gitlab-ci.yml: Merge check-crypto-old jobs into the build-crypto-old jobs
  gitlab-ci.yml: Merge one of the coroutine jobs with the tcg-disabled job
  gitlab-ci.yml: Add some missing dependencies to the jobs
  gitlab-ci.yml: Move build-tools-and-docs-debian to a better place
  tests: Move benchmarks into a separate folder
  tests: Move unit tests into a separate directory

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 169 insertions, 0 deletions

diff --git a/tests/bench/atomic64-bench.c b/tests/bench/atomic64-bench.c
new file mode 100644
index 0000000000..e474753d34
--- /dev/null
+++ b/tests/bench/atomic64-bench.c
@@ -0,0 +1,169 @@
+/*
+ * Copyright (C) 2018, Emilio G. Cota <cota@braap.org>
+ *
+ * License: GNU GPL, version 2 or later.
+ *   See the COPYING file in the top-level directory.
+ */
+#include "qemu/osdep.h"
+#include "qemu/thread.h"
+#include "qemu/host-utils.h"
+#include "qemu/processor.h"
+
+struct thread_info {
+    uint64_t r;
+    uint64_t accesses;
+} QEMU_ALIGNED(64);
+
+struct count {
+    int64_t i64;
+} QEMU_ALIGNED(64);
+
+static QemuThread *threads;
+static struct thread_info *th_info;
+static unsigned int n_threads = 1;
+static unsigned int n_ready_threads;
+static struct count *counts;
+static unsigned int duration = 1;
+static unsigned int range = 1024;
+static bool test_start;
+static bool test_stop;
+
+static const char commands_string[] =
+    " -d = duration in seconds\n"
+    " -n = number of threads\n"
+    " -r = range (will be rounded up to pow2)";
+
+static void usage_complete(char *argv[])
+{
+    fprintf(stderr, "Usage: %s [options]\n", argv[0]);
+    fprintf(stderr, "options:\n%s\n", commands_string);
+}
+
+/*
+ * From: https://en.wikipedia.org/wiki/Xorshift
+ * This is faster than rand_r(), and gives us a wider range (RAND_MAX is only
+ * guaranteed to be >= INT_MAX).
+ */
+static uint64_t xorshift64star(uint64_t x)
+{
+    x ^= x >> 12; /* a */
+    x ^= x << 25; /* b */
+    x ^= x >> 27; /* c */
+    return x * UINT64_C(2685821657736338717);
+}
+
+static void *thread_func(void *arg)
+{
+    struct thread_info *info = arg;
+
+    qatomic_inc(&n_ready_threads);
+    while (!qatomic_read(&test_start)) {
+        cpu_relax();
+    }
+
+    while (!qatomic_read(&test_stop)) {
+        unsigned int index;
+
+        info->r = xorshift64star(info->r);
+        index = info->r & (range - 1);
+        qatomic_read_i64(&counts[index].i64);
+        info->accesses++;
+    }
+    return NULL;
+}
+
+static void run_test(void)
+{
+    unsigned int i;
+
+    while (qatomic_read(&n_ready_threads) != n_threads) {
+        cpu_relax();
+    }
+
+    qatomic_set(&test_start, true);
+    g_usleep(duration * G_USEC_PER_SEC);
+    qatomic_set(&test_stop, true);
+
+    for (i = 0; i < n_threads; i++) {
+        qemu_thread_join(&threads[i]);
+    }
+}
+
+static void create_threads(void)
+{
+    unsigned int i;
+
+    threads = g_new(QemuThread, n_threads);
+    th_info = g_new(struct thread_info, n_threads);
+    counts = g_malloc0_n(range, sizeof(*counts));
+
+    for (i = 0; i < n_threads; i++) {
+        struct thread_info *info = &th_info[i];
+
+        info->r = (i + 1) ^ time(NULL);
+        info->accesses = 0;
+        qemu_thread_create(&threads[i], NULL, thread_func, info,
+                           QEMU_THREAD_JOINABLE);
+    }
+}
+
+static void pr_params(void)
+{
+    printf("Parameters:\n");
+    printf(" # of threads:      %u\n", n_threads);
+    printf(" duration:          %u\n", duration);
+    printf(" ops' range:        %u\n", range);
+}
+
+static void pr_stats(void)
+{
+    unsigned long long val = 0;
+    double tx;
+    int i;
+
+    for (i = 0; i < n_threads; i++) {
+        val += th_info[i].accesses;
+    }
+    tx = val / duration / 1e6;
+
+    printf("Results:\n");
+    printf("Duration:            %u s\n", duration);
+    printf(" Throughput:         %.2f Mops/s\n", tx);
+    printf(" Throughput/thread:  %.2f Mops/s/thread\n", tx / n_threads);
+}
+
+static void parse_args(int argc, char *argv[])
+{
+    int c;
+
+    for (;;) {
+        c = getopt(argc, argv, "hd:n:r:");
+        if (c < 0) {
+            break;
+        }
+        switch (c) {
+        case 'h':
+            usage_complete(argv);
+            exit(0);
+        case 'd':
+            duration = atoi(optarg);
+            break;
+        case 'n':
+            n_threads = atoi(optarg);
+            break;
+        case 'r':
+            range = pow2ceil(atoi(optarg));
+            break;
+        }
+    }
+}
+
+int main(int argc, char *argv[])
+{
+    parse_args(argc, argv);
+    pr_params();
+    create_threads();
+    run_test();
+    pr_stats();
+    return 0;
+}