10 files changed, 188 insertions, 125 deletions

diff --git a/tests/plugin/bb.c b/tests/plugin/bb.c
index f30bea0..df19fd3 100644
--- a/tests/plugin/bb.c
+++ b/tests/plugin/bb.c
@@ -22,9 +22,9 @@ static bool do_inline;
 
 static void plugin_exit(qemu_plugin_id_t id, void *p)
 {
-    g_autofree gchar *out;
-    out = g_strdup_printf("bb's: %" PRIu64", insns: %" PRIu64 "\n",
-                          bb_count, insn_count);
+    g_autofree gchar *out = g_strdup_printf(
+        "bb's: %" PRIu64", insns: %" PRIu64 "\n",
+        bb_count, insn_count);
     qemu_plugin_outs(out);
 }
 
diff --git a/tests/plugin/howvec.c b/tests/plugin/howvec.c
index 4ca555e..3b9a693 100644
--- a/tests/plugin/howvec.c
+++ b/tests/plugin/howvec.c
@@ -163,6 +163,13 @@ static gint cmp_exec_count(gconstpointer a, gconstpointer b)
     return ea->count > eb->count ? -1 : 1;
 }
 
+static void free_record(gpointer data)
+{
+    InsnExecCount *rec = (InsnExecCount *) data;
+    g_free(rec->insn);
+    g_free(rec);
+}
+
 static void plugin_exit(qemu_plugin_id_t id, void *p)
 {
     g_autoptr(GString) report = g_string_new("Instruction Classes:\n");
@@ -195,30 +202,31 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
 
     counts = g_hash_table_get_values(insns);
     if (counts && g_list_next(counts)) {
-        GList *it;
-
         g_string_append_printf(report,"Individual Instructions:\n");
+        counts = g_list_sort(counts, cmp_exec_count);
 
-        it = g_list_sort(counts, cmp_exec_count);
-
-        for (i = 0; i < limit && it->next; i++, it = it->next) {
-            InsnExecCount *rec = (InsnExecCount *) it->data;
-            g_string_append_printf(report, "Instr: %-24s\t(%ld hits)\t(op=%#08x/%s)\n",
+        for (i = 0; i < limit && g_list_next(counts);
+             i++, counts = g_list_next(counts)) {
+            InsnExecCount *rec = (InsnExecCount *) counts->data;
+            g_string_append_printf(report,
+                                   "Instr: %-24s\t(%ld hits)\t(op=%#08x/%s)\n",
                                    rec->insn,
                                    rec->count,
                                    rec->opcode,
                                    rec->class ?
                                    rec->class->class : "un-categorised");
         }
-        g_list_free(it);
+        g_list_free(counts);
     }
 
+    g_hash_table_destroy(insns);
+
     qemu_plugin_outs(report->str);
 }
 
 static void plugin_init(void)
 {
-    insns = g_hash_table_new(NULL, g_direct_equal);
+    insns = g_hash_table_new_full(NULL, g_direct_equal, NULL, &free_record);
 }
 
 static void vcpu_insn_exec_before(unsigned int cpu_index, void *udata)
diff --git a/tests/plugin/insn.c b/tests/plugin/insn.c
index 0a8f5a0..a9a6e41 100644
--- a/tests/plugin/insn.c
+++ b/tests/plugin/insn.c
@@ -44,8 +44,7 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
 
 static void plugin_exit(qemu_plugin_id_t id, void *p)
 {
-    g_autofree gchar *out;
-    out = g_strdup_printf("insns: %" PRIu64 "\n", insn_count);
+    g_autofree gchar *out = g_strdup_printf("insns: %" PRIu64 "\n", insn_count);
     qemu_plugin_outs(out);
 }
 
diff --git a/tests/qemu-iotests/214 b/tests/qemu-iotests/214
index 3500e0c..af677d9 100755
--- a/tests/qemu-iotests/214
+++ b/tests/qemu-iotests/214
@@ -125,9 +125,9 @@ $QEMU_IO -c "write -P 0xcc $offset $data_size" "json:{\
 sizeB=$($QEMU_IMG info --output=json "$TEST_IMG" |
         sed -n '/"actual-size":/ s/[^0-9]//gp')
 
-if [ $sizeA -le $sizeB ]
+if [ $sizeA -lt $sizeB ]
 then
-    echo "Compression ERROR"
+    echo "Compression ERROR ($sizeA < $sizeB)"
 fi
 
 $QEMU_IMG check --output=json "$TEST_IMG" |
diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c
index 17dd807..2f9b7f6 100644
--- a/tests/qtest/numa-test.c
+++ b/tests/qtest/numa-test.c
@@ -14,67 +14,60 @@
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qlist.h"
 
-static char *make_cli(const char *generic_cli, const char *test_cli)
+static char *make_cli(const GString *generic_cli, const char *test_cli)
 {
-    return g_strdup_printf("%s %s", generic_cli ? generic_cli : "", test_cli);
+    return g_strdup_printf("%s %s", generic_cli->str, test_cli);
 }
 
 static void test_mon_explicit(const void *data)
 {
-    char *s;
-    char *cli;
     QTestState *qts;
+    g_autofree char *s = NULL;
+    g_autofree char *cli = NULL;
 
-    cli = make_cli(data, "-smp 8 "
-                   "-numa node,nodeid=0,cpus=0-3 "
-                   "-numa node,nodeid=1,cpus=4-7 ");
+    cli = make_cli(data, "-smp 8 -numa node,nodeid=0,memdev=ram,cpus=0-3 "
+                         "-numa node,nodeid=1,cpus=4-7");
     qts = qtest_init(cli);
 
     s = qtest_hmp(qts, "info numa");
     g_assert(strstr(s, "node 0 cpus: 0 1 2 3"));
     g_assert(strstr(s, "node 1 cpus: 4 5 6 7"));
-    g_free(s);
 
     qtest_quit(qts);
-    g_free(cli);
 }
 
-static void test_mon_default(const void *data)
+static void test_def_cpu_split(const void *data)
 {
-    char *s;
-    char *cli;
     QTestState *qts;
+    g_autofree char *s = NULL;
+    g_autofree char *cli = NULL;
 
-    cli = make_cli(data, "-smp 8 -numa node -numa node");
+    cli = make_cli(data, "-smp 8 -numa node,memdev=ram -numa node");
     qts = qtest_init(cli);
 
     s = qtest_hmp(qts, "info numa");
     g_assert(strstr(s, "node 0 cpus: 0 2 4 6"));
     g_assert(strstr(s, "node 1 cpus: 1 3 5 7"));
-    g_free(s);
 
     qtest_quit(qts);
-    g_free(cli);
 }
 
 static void test_mon_partial(const void *data)
 {
-    char *s;
-    char *cli;
     QTestState *qts;
+    g_autofree char *s = NULL;
+    g_autofree char *cli = NULL;
 
     cli = make_cli(data, "-smp 8 "
-                   "-numa node,nodeid=0,cpus=0-1 "
+                   "-numa node,nodeid=0,memdev=ram,cpus=0-1 "
                    "-numa node,nodeid=1,cpus=4-5 ");
     qts = qtest_init(cli);
 
     s = qtest_hmp(qts, "info numa");
     g_assert(strstr(s, "node 0 cpus: 0 1 2 3 6 7"));
     g_assert(strstr(s, "node 1 cpus: 4 5"));
-    g_free(s);
 
     qtest_quit(qts);
-    g_free(cli);
 }
 
 static QList *get_cpus(QTestState *qts, QDict **resp)
@@ -87,13 +80,14 @@ static QList *get_cpus(QTestState *qts, QDict **resp)
 
 static void test_query_cpus(const void *data)
 {
-    char *cli;
     QDict *resp;
     QList *cpus;
     QObject *e;
     QTestState *qts;
+    g_autofree char *cli = NULL;
 
-    cli = make_cli(data, "-smp 8 -numa node,cpus=0-3 -numa node,cpus=4-7");
+    cli = make_cli(data, "-smp 8 -numa node,memdev=ram,cpus=0-3 "
+                         "-numa node,cpus=4-7");
     qts = qtest_init(cli);
     cpus = get_cpus(qts, &resp);
     g_assert(cpus);
@@ -120,19 +114,18 @@ static void test_query_cpus(const void *data)
 
     qobject_unref(resp);
     qtest_quit(qts);
-    g_free(cli);
 }
 
 static void pc_numa_cpu(const void *data)
 {
-    char *cli;
     QDict *resp;
     QList *cpus;
     QObject *e;
     QTestState *qts;
+    g_autofree char *cli = NULL;
 
     cli = make_cli(data, "-cpu pentium -smp 8,sockets=2,cores=2,threads=2 "
-        "-numa node,nodeid=0 -numa node,nodeid=1 "
+        "-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 "
         "-numa cpu,node-id=1,socket-id=0 "
         "-numa cpu,node-id=0,socket-id=1,core-id=0 "
         "-numa cpu,node-id=0,socket-id=1,core-id=1,thread-id=0 "
@@ -174,19 +167,18 @@ static void pc_numa_cpu(const void *data)
 
     qobject_unref(resp);
     qtest_quit(qts);
-    g_free(cli);
 }
 
 static void spapr_numa_cpu(const void *data)
 {
-    char *cli;
     QDict *resp;
     QList *cpus;
     QObject *e;
     QTestState *qts;
+    g_autofree char *cli = NULL;
 
     cli = make_cli(data, "-smp 4,cores=4 "
-        "-numa node,nodeid=0 -numa node,nodeid=1 "
+        "-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 "
         "-numa cpu,node-id=0,core-id=0 "
         "-numa cpu,node-id=0,core-id=1 "
         "-numa cpu,node-id=0,core-id=2 "
@@ -220,19 +212,18 @@ static void spapr_numa_cpu(const void *data)
 
     qobject_unref(resp);
     qtest_quit(qts);
-    g_free(cli);
 }
 
 static void aarch64_numa_cpu(const void *data)
 {
-    char *cli;
     QDict *resp;
     QList *cpus;
     QObject *e;
     QTestState *qts;
+    g_autofree char *cli = NULL;
 
     cli = make_cli(data, "-smp 2 "
-        "-numa node,nodeid=0 -numa node,nodeid=1 "
+        "-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 "
         "-numa cpu,node-id=1,thread-id=0 "
         "-numa cpu,node-id=0,thread-id=1");
     qts = qtest_init(cli);
@@ -264,7 +255,6 @@ static void aarch64_numa_cpu(const void *data)
 
     qobject_unref(resp);
     qtest_quit(qts);
-    g_free(cli);
 }
 
 static void pc_dynamic_cpu_cfg(const void *data)
@@ -273,13 +263,14 @@ static void pc_dynamic_cpu_cfg(const void *data)
     QDict *resp;
     QList *cpus;
     QTestState *qs;
+    g_autofree char *cli = NULL;
 
-    qs = qtest_initf("%s -nodefaults --preconfig -smp 2",
-                     data ? (char *)data : "");
+    cli = make_cli(data, "-nodefaults --preconfig -smp 2");
+    qs = qtest_init(cli);
 
     /* create 2 numa nodes */
     g_assert(!qmp_rsp_is_err(qtest_qmp(qs, "{ 'execute': 'set-numa-node',"
-        " 'arguments': { 'type': 'node', 'nodeid': 0 } }")));
+        " 'arguments': { 'type': 'node', 'nodeid': 0, 'memdev': 'ram' } }")));
     g_assert(!qmp_rsp_is_err(qtest_qmp(qs, "{ 'execute': 'set-numa-node',"
         " 'arguments': { 'type': 'node', 'nodeid': 1 } }")));
 
@@ -329,16 +320,19 @@ static void pc_dynamic_cpu_cfg(const void *data)
 
 static void pc_hmat_build_cfg(const void *data)
 {
-    QTestState *qs = qtest_initf("%s -nodefaults --preconfig -machine hmat=on "
-                     "-smp 2,sockets=2 "
-                     "-m 128M,slots=2,maxmem=1G "
-                     "-object memory-backend-ram,size=64M,id=m0 "
-                     "-object memory-backend-ram,size=64M,id=m1 "
-                     "-numa node,nodeid=0,memdev=m0 "
-                     "-numa node,nodeid=1,memdev=m1,initiator=0 "
-                     "-numa cpu,node-id=0,socket-id=0 "
-                     "-numa cpu,node-id=0,socket-id=1",
-                     data ? (char *)data : "");
+    QTestState *qs;
+    g_autofree char *cli = NULL;
+
+    cli = make_cli(data, "-nodefaults --preconfig -machine hmat=on "
+                         "-smp 2,sockets=2 "
+                         "-m 128M,slots=2,maxmem=1G "
+                         "-object memory-backend-ram,size=64M,id=m0 "
+                         "-object memory-backend-ram,size=64M,id=m1 "
+                         "-numa node,nodeid=0,memdev=m0 "
+                         "-numa node,nodeid=1,memdev=m1,initiator=0 "
+                         "-numa cpu,node-id=0,socket-id=0 "
+                         "-numa cpu,node-id=0,socket-id=1");
+    qs = qtest_init(cli);
 
     /* Fail: Initiator should be less than the number of nodes */
     g_assert_true(qmp_rsp_is_err(qtest_qmp(qs, "{ 'execute': 'set-numa-node',"
@@ -455,13 +449,16 @@ static void pc_hmat_build_cfg(const void *data)
 
 static void pc_hmat_off_cfg(const void *data)
 {
-    QTestState *qs = qtest_initf("%s -nodefaults --preconfig "
-                     "-smp 2,sockets=2 "
-                     "-m 128M,slots=2,maxmem=1G "
-                     "-object memory-backend-ram,size=64M,id=m0 "
-                     "-object memory-backend-ram,size=64M,id=m1 "
-                     "-numa node,nodeid=0,memdev=m0",
-                     data ? (char *)data : "");
+    QTestState *qs;
+    g_autofree char *cli = NULL;
+
+    cli = make_cli(data, "-nodefaults --preconfig "
+                         "-smp 2,sockets=2 "
+                         "-m 128M,slots=2,maxmem=1G "
+                         "-object memory-backend-ram,size=64M,id=m0 "
+                         "-object memory-backend-ram,size=64M,id=m1 "
+                         "-numa node,nodeid=0,memdev=m0");
+    qs = qtest_init(cli);
 
     /*
      * Fail: Enable HMAT with -machine hmat=on
@@ -491,16 +488,19 @@ static void pc_hmat_off_cfg(const void *data)
 
 static void pc_hmat_erange_cfg(const void *data)
 {
-    QTestState *qs = qtest_initf("%s -nodefaults --preconfig -machine hmat=on "
-                     "-smp 2,sockets=2 "
-                     "-m 128M,slots=2,maxmem=1G "
-                     "-object memory-backend-ram,size=64M,id=m0 "
-                     "-object memory-backend-ram,size=64M,id=m1 "
-                     "-numa node,nodeid=0,memdev=m0 "
-                     "-numa node,nodeid=1,memdev=m1,initiator=0 "
-                     "-numa cpu,node-id=0,socket-id=0 "
-                     "-numa cpu,node-id=0,socket-id=1",
-                     data ? (char *)data : "");
+    QTestState *qs;
+    g_autofree char *cli = NULL;
+
+    cli = make_cli(data, "-nodefaults --preconfig -machine hmat=on "
+                         "-smp 2,sockets=2 "
+                         "-m 128M,slots=2,maxmem=1G "
+                         "-object memory-backend-ram,size=64M,id=m0 "
+                         "-object memory-backend-ram,size=64M,id=m1 "
+                         "-numa node,nodeid=0,memdev=m0 "
+                         "-numa node,nodeid=1,memdev=m1,initiator=0 "
+                         "-numa cpu,node-id=0,socket-id=0 "
+                         "-numa cpu,node-id=0,socket-id=1");
+    qs = qtest_init(cli);
 
     /* Can't store the compressed latency */
     g_assert_false(qmp_rsp_is_err(qtest_qmp(qs, "{ 'execute': 'set-numa-node',"
@@ -539,16 +539,22 @@ static void pc_hmat_erange_cfg(const void *data)
 
 int main(int argc, char **argv)
 {
-    const char *args = NULL;
+    g_autoptr(GString) args = g_string_new(NULL);
     const char *arch = qtest_get_arch();
 
-    if (strcmp(arch, "aarch64") == 0) {
-        args = "-machine virt";
+    if (g_str_equal(arch, "ppc64")) {
+        g_string_append(args, " -object memory-backend-ram,id=ram,size=512M");
+    } else {
+        g_string_append(args, " -object memory-backend-ram,id=ram,size=128M");
+    }
+
+    if (g_str_equal(arch, "aarch64")) {
+        g_string_append(args, " -machine virt");
     }
 
     g_test_init(&argc, &argv, NULL);
 
-    qtest_add_data_func("/numa/mon/default", args, test_mon_default);
+    qtest_add_data_func("/numa/mon/cpus/default", args, test_def_cpu_split);
     qtest_add_data_func("/numa/mon/cpus/explicit", args, test_mon_explicit);
     qtest_add_data_func("/numa/mon/cpus/partial", args, test_mon_partial);
     qtest_add_data_func("/numa/qmp/cpus/query-cpus", args, test_query_cpus);
diff --git a/tests/rcutorture.c b/tests/rcutorture.c
index 49311c8..732f03a 100644
--- a/tests/rcutorture.c
+++ b/tests/rcutorture.c
@@ -65,8 +65,6 @@
 #include "qemu/rcu.h"
 #include "qemu/thread.h"
 
-long long n_reads = 0LL;
-long n_updates = 0L;
 int nthreadsrunning;
 
 #define GOFLAG_INIT 0
@@ -78,11 +76,20 @@ static volatile int goflag = GOFLAG_INIT;
 #define RCU_READ_RUN 1000
 
 #define NR_THREADS 100
-static QemuMutex counts_mutex;
 static QemuThread threads[NR_THREADS];
 static struct rcu_reader_data *data[NR_THREADS];
 static int n_threads;
 
+/*
+ * Statistical counts
+ *
+ * These are the sum of local counters at the end of a run.
+ * Updates are protected by a mutex.
+ */
+static QemuMutex counts_mutex;
+long long n_reads = 0LL;
+long n_updates = 0L;
+
 static void create_thread(void *(*func)(void *))
 {
     if (n_threads >= NR_THREADS) {
@@ -223,15 +230,15 @@ static void uperftest(int nupdaters, int duration)
 #define RCU_STRESS_PIPE_LEN 10
 
 struct rcu_stress {
-    int pipe_count;
+    int age;  /* how many update cycles while not rcu_stress_current */
     int mbtest;
 };
 
 struct rcu_stress rcu_stress_array[RCU_STRESS_PIPE_LEN] = { { 0 } };
 struct rcu_stress *rcu_stress_current;
-int rcu_stress_idx;
-
 int n_mberror;
+
+/* Updates protected by counts_mutex */
 long long rcu_stress_count[RCU_STRESS_PIPE_LEN + 1];
 
 
@@ -253,7 +260,7 @@ static void *rcu_read_stress_test(void *arg)
     while (goflag == GOFLAG_RUN) {
         rcu_read_lock();
         p = atomic_rcu_read(&rcu_stress_current);
-        if (p->mbtest == 0) {
+        if (atomic_read(&p->mbtest) == 0) {
             n_mberror++;
         }
         rcu_read_lock();
@@ -261,7 +268,7 @@ static void *rcu_read_stress_test(void *arg)
             garbage++;
         }
         rcu_read_unlock();
-        pc = p->pipe_count;
+        pc = atomic_read(&p->age);
         rcu_read_unlock();
         if ((pc > RCU_STRESS_PIPE_LEN) || (pc < 0)) {
             pc = RCU_STRESS_PIPE_LEN;
@@ -280,32 +287,52 @@ static void *rcu_read_stress_test(void *arg)
     return NULL;
 }
 
+/*
+ * Stress Test Updater
+ *
+ * The updater cycles around updating rcu_stress_current to point at
+ * one of the rcu_stress_array_entries and resets it's age. It
+ * then increments the age of all the other entries. The age
+ * will be read under an rcu_read_lock() and distribution of values
+ * calculated. The final result gives an indication of how many
+ * previously current rcu_stress entries are in flight until the RCU
+ * cycle complete.
+ */
 static void *rcu_update_stress_test(void *arg)
 {
-    int i;
-    struct rcu_stress *p;
+    int i, rcu_stress_idx = 0;
+    struct rcu_stress *cp = atomic_read(&rcu_stress_current);
 
     rcu_register_thread();
-
     *(struct rcu_reader_data **)arg = &rcu_reader;
+
     while (goflag == GOFLAG_INIT) {
         g_usleep(1000);
     }
+
     while (goflag == GOFLAG_RUN) {
-        i = rcu_stress_idx + 1;
-        if (i >= RCU_STRESS_PIPE_LEN) {
-            i = 0;
+        struct rcu_stress *p;
+        rcu_stress_idx++;
+        if (rcu_stress_idx >= RCU_STRESS_PIPE_LEN) {
+            rcu_stress_idx = 0;
         }
-        p = &rcu_stress_array[i];
-        p->mbtest = 0;
+        p = &rcu_stress_array[rcu_stress_idx];
+        /* catching up with ourselves would be a bug */
+        assert(p != cp);
+        atomic_set(&p->mbtest, 0);
         smp_mb();
-        p->pipe_count = 0;
-        p->mbtest = 1;
+        atomic_set(&p->age, 0);
+        atomic_set(&p->mbtest, 1);
         atomic_rcu_set(&rcu_stress_current, p);
-        rcu_stress_idx = i;
+        cp = p;
+        /*
+         * New RCU structure is now live, update pipe counts on old
+         * ones.
+         */
         for (i = 0; i < RCU_STRESS_PIPE_LEN; i++) {
             if (i != rcu_stress_idx) {
-                rcu_stress_array[i].pipe_count++;
+                atomic_set(&rcu_stress_array[i].age,
+                           rcu_stress_array[i].age + 1);
             }
         }
         synchronize_rcu();
@@ -338,7 +365,7 @@ static void stresstest(int nreaders, int duration)
     int i;
 
     rcu_stress_current = &rcu_stress_array[0];
-    rcu_stress_current->pipe_count = 0;
+    rcu_stress_current->age = 0;
     rcu_stress_current->mbtest = 1;
     for (i = 0; i < nreaders; i++) {
         create_thread(rcu_read_stress_test);
@@ -368,7 +395,7 @@ static void gtest_stress(int nreaders, int duration)
     int i;
 
     rcu_stress_current = &rcu_stress_array[0];
-    rcu_stress_current->pipe_count = 0;
+    rcu_stress_current->age = 0;
     rcu_stress_current->mbtest = 1;
     for (i = 0; i < nreaders; i++) {
         create_thread(rcu_read_stress_test);
@@ -413,7 +440,8 @@ static void gtest_stress_10_5(void)
 
 static void usage(int argc, char *argv[])
 {
-    fprintf(stderr, "Usage: %s [nreaders [ perf | stress ] ]\n", argv[0]);
+    fprintf(stderr, "Usage: %s [nreaders [ [r|u]perf | stress [duration]]\n",
+            argv[0]);
     exit(-1);
 }
 
diff --git a/tests/tcg/Makefile.target b/tests/tcg/Makefile.target
index 3c7421a..b3cff3c 100644
--- a/tests/tcg/Makefile.target
+++ b/tests/tcg/Makefile.target
@@ -79,7 +79,7 @@ QEMU_OPTS=
 
 # If TCG debugging is enabled things are a lot slower
 ifeq ($(CONFIG_DEBUG_TCG),y)
-TIMEOUT=45
+TIMEOUT=60
 else
 TIMEOUT=15
 endif
@@ -137,7 +137,7 @@ PLUGINS=$(notdir $(wildcard $(PLUGIN_DIR)/*.so))
 $(foreach p,$(PLUGINS), \
 	$(foreach t,$(TESTS),\
 		$(eval run-plugin-$(t)-with-$(p): $t $p) \
-		$(eval run-plugin-$(t)-with-$(p): TIMEOUT=30) \
+		$(eval run-plugin-$(t)-with-$(p): TIMEOUT=60) \
 		$(eval RUN_TESTS+=run-plugin-$(t)-with-$(p))))
 endif
 
diff --git a/tests/tcg/aarch64/Makefile.softmmu-target b/tests/tcg/aarch64/Makefile.softmmu-target
index d2299b9..71f72cf 100644
--- a/tests/tcg/aarch64/Makefile.softmmu-target
+++ b/tests/tcg/aarch64/Makefile.softmmu-target
@@ -70,4 +70,6 @@ pauth-3:
 	$(call skip-test, "BUILD of $@", "missing compiler support")
 run-pauth-3:
 	$(call skip-test, "RUN of pauth-3", "not built")
+run-plugin-pauth-3-with-%:
+	$(call skip-test, "RUN of pauth-3 ($*)", "not built")
 endif
diff --git a/tests/tcg/aarch64/pauth-4.c b/tests/tcg/aarch64/pauth-4.c
index 1040e92..24a639e 100644
--- a/tests/tcg/aarch64/pauth-4.c
+++ b/tests/tcg/aarch64/pauth-4.c
@@ -1,25 +1,45 @@
 #include <stdint.h>
 #include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#define TESTS 1000
 
 int main()
 {
-  uintptr_t x, y;
+    int i, count = 0;
+    float perc;
+    void *base = malloc(TESTS);
+
+    for (i = 0; i < TESTS; i++) {
+        uintptr_t in, x, y;
+
+        in = i + (uintptr_t) base;
+
+        asm("mov %0, %[in]\n\t"
+            "pacia %0, sp\n\t"        /* sigill if pauth not supported */
+            "eor %0, %0, #4\n\t"      /* corrupt single bit */
+            "mov %1, %0\n\t"
+            "autia %1, sp\n\t"        /* validate corrupted pointer */
+            "xpaci %0\n\t"            /* strip pac from corrupted pointer */
+            : /* out */ "=r"(x), "=r"(y)
+            : /* in */ [in] "r" (in)
+            : /* clobbers */);
 
-  asm("mov %0, lr\n\t"
-      "pacia %0, sp\n\t"        /* sigill if pauth not supported */
-      "eor %0, %0, #4\n\t"      /* corrupt single bit */
-      "mov %1, %0\n\t"
-      "autia %1, sp\n\t"        /* validate corrupted pointer */
-      "xpaci %0\n\t"            /* strip pac from corrupted pointer */
-      : "=r"(x), "=r"(y));
+        /*
+         * Once stripped, the corrupted pointer is of the form 0x0000...wxyz.
+         * We expect the autia to indicate failure, producing a pointer of the
+         * form 0x000e....wxyz.  Use xpaci and != for the test, rather than
+         * extracting explicit bits from the top, because the location of the
+         * error code "e" depends on the configuration of virtual memory.
+         */
+        if (x != y) {
+            count++;
+        }
 
-  /*
-   * Once stripped, the corrupted pointer is of the form 0x0000...wxyz.
-   * We expect the autia to indicate failure, producing a pointer of the
-   * form 0x000e....wxyz.  Use xpaci and != for the test, rather than
-   * extracting explicit bits from the top, because the location of the
-   * error code "e" depends on the configuration of virtual memory.
-   */
-  assert(x != y);
-  return 0;
+    }
+    perc = (float) count / (float) TESTS;
+    printf("Checks Passed: %0.2f%%", perc * 100.0);
+    assert(perc > 0.95);
+    return 0;
 }
diff --git a/tests/tcg/configure.sh b/tests/tcg/configure.sh
index 9eb6ba3..eaaaff6 100755
--- a/tests/tcg/configure.sh
+++ b/tests/tcg/configure.sh
@@ -228,7 +228,7 @@ for target in $target_list; do
                 echo "CROSS_CC_HAS_SVE=y" >> $config_target_mak
             fi
             if do_compiler "$target_compiler" $target_compiler_cflags \
-               -march=-march=armv8.3-a -o $TMPE $TMPC; then
+               -march=armv8.3-a -o $TMPE $TMPC; then
                 echo "CROSS_CC_HAS_ARMV8_3=y" >> $config_target_mak
             fi
         ;;