Merge remote-tracking branch 'remotes/stsquad/tags/pull-tcg-plugins-281019-4' into staging

TCG Plugins initial implementation

  - use --enable-plugins @ configure
  - low impact introspection (-plugin empty.so to measure overhead)
  - plugins cannot alter guest state
  - example plugins included in source tree (tests/plugins)
  - -d plugin to enable plugin output in logs
  - check-tcg runs extra tests when plugins enabled
  - documentation in docs/devel/plugins.rst

# gpg: Signature made Mon 28 Oct 2019 15:13:23 GMT
# gpg:                using RSA key 6685AE99E75167BCAFC8DF35FBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <alex.bennee@linaro.org>" [full]
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* remotes/stsquad/tags/pull-tcg-plugins-281019-4: (57 commits)
  travis.yml: enable linux-gcc-debug-tcg cache
  MAINTAINERS: add me for the TCG plugins code
  scripts/checkpatch.pl: don't complain about (foo, /* empty */)
  .travis.yml: add --enable-plugins tests
  include/exec: wrap cpu_ldst.h in CONFIG_TCG
  accel/stubs: reduce headers from tcg-stub
  tests/plugin: add hotpages to analyse memory access patterns
  tests/plugin: add instruction execution breakdown
  tests/plugin: add a hotblocks plugin
  tests/tcg: enable plugin testing
  tests/tcg: drop test-i386-fprem from TESTS when not SLOW
  tests/tcg: move "virtual" tests to EXTRA_TESTS
  tests/tcg: set QEMU_OPTS for all cris runs
  tests/tcg/Makefile.target: fix path to config-host.mak
  tests/plugin: add sample plugins
  linux-user: support -plugin option
  vl: support -plugin option
  plugin: add qemu_plugin_outs helper
  plugin: add qemu_plugin_insn_disas helper
  plugin: expand the plugin_init function to include an info block
  ...

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

16 files changed, 1041 insertions, 10 deletions

diff --git a/tests/Makefile.include b/tests/Makefile.include
index 34ec03391c..c79402ab75 100644
--- a/tests/Makefile.include
+++ b/tests/Makefile.include
@@ -1066,6 +1066,15 @@ check-softfloat:
 		"SKIPPED for non-TCG builds")
 endif
 
+# Plugins
+ifeq ($(CONFIG_PLUGIN),y)
+.PHONY: plugins
+plugins:
+	$(call quiet-command,\
+		$(MAKE) $(SUBDIR_MAKEFLAGS) -C tests/plugin V="$(V)", \
+		"BUILD", "plugins")
+endif
+
 # Per guest TCG tests
 
 BUILD_TCG_TARGET_RULES=$(patsubst %,build-tcg-tests-%, $(TARGET_DIRS))
@@ -1076,7 +1085,7 @@ RUN_TCG_TARGET_RULES=$(patsubst %,run-tcg-tests-%, $(TARGET_DIRS))
 $(foreach PROBE_TARGET,$(TARGET_DIRS), 				\
 	$(eval -include $(SRC_PATH)/tests/tcg/Makefile.prereqs))
 
-build-tcg-tests-%:
+build-tcg-tests-%: $(if $(CONFIG_PLUGIN),plugins)
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) \
 		-f $(SRC_PATH)/tests/tcg/Makefile.qemu \
 		SRC_PATH=$(SRC_PATH) \
diff --git a/tests/plugin/Makefile b/tests/plugin/Makefile
new file mode 100644
index 0000000000..75467b6db8
--- /dev/null
+++ b/tests/plugin/Makefile
@@ -0,0 +1,31 @@
+BUILD_DIR := $(CURDIR)/../..
+
+include $(BUILD_DIR)/config-host.mak
+include $(SRC_PATH)/rules.mak
+
+$(call set-vpath, $(SRC_PATH)/tests/plugin)
+
+NAMES :=
+NAMES += bb
+NAMES += empty
+NAMES += insn
+NAMES += mem
+NAMES += hotblocks
+NAMES += howvec
+NAMES += hotpages
+
+SONAMES := $(addsuffix .so,$(addprefix lib,$(NAMES)))
+
+QEMU_CFLAGS += -fPIC
+QEMU_CFLAGS += -I$(SRC_PATH)/include/qemu
+
+all: $(SONAMES)
+
+lib%.so: %.o
+	$(CC) -shared -Wl,-soname,$@ -o $@ $^ $(LDLIBS)
+
+clean:
+	rm -f *.o *.so *.d
+	rm -Rf .libs
+
+.PHONY: all clean
diff --git a/tests/plugin/bb.c b/tests/plugin/bb.c
new file mode 100644
index 0000000000..45e1de5bd6
--- /dev/null
+++ b/tests/plugin/bb.c
@@ -0,0 +1,64 @@
+/*
+ * 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 <inttypes.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <glib.h>
+
+#include <qemu-plugin.h>
+
+static uint64_t bb_count;
+static uint64_t insn_count;
+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);
+    qemu_plugin_outs(out);
+}
+
+static void vcpu_tb_exec(unsigned int cpu_index, void *udata)
+{
+    unsigned long n_insns = (unsigned long)udata;
+
+    insn_count += n_insns;
+    bb_count++;
+}
+
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{
+    unsigned long n_insns = qemu_plugin_tb_n_insns(tb);
+
+    if (do_inline) {
+        qemu_plugin_register_vcpu_tb_exec_inline(tb, QEMU_PLUGIN_INLINE_ADD_U64,
+                                                 &bb_count, 1);
+        qemu_plugin_register_vcpu_tb_exec_inline(tb, QEMU_PLUGIN_INLINE_ADD_U64,
+                                                 &insn_count, n_insns);
+    } else {
+        qemu_plugin_register_vcpu_tb_exec_cb(tb, vcpu_tb_exec,
+                                             QEMU_PLUGIN_CB_NO_REGS,
+                                             (void *)n_insns);
+    }
+}
+
+QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
+                                           const qemu_info_t *info,
+                                           int argc, char **argv)
+{
+    if (argc && strcmp(argv[0], "inline") == 0) {
+        do_inline = true;
+    }
+
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
+    return 0;
+}
diff --git a/tests/plugin/empty.c b/tests/plugin/empty.c
new file mode 100644
index 0000000000..3f60f69027
--- /dev/null
+++ b/tests/plugin/empty.c
@@ -0,0 +1,30 @@
+/*
+ * 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 <inttypes.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+
+#include <qemu-plugin.h>
+
+/*
+ * Empty TB translation callback.
+ * This allows us to measure the overhead of injecting and then
+ * removing empty instrumentation.
+ */
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{ }
+
+QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
+                                           const qemu_info_t *info,
+                                           int argc, char **argv)
+{
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    return 0;
+}
diff --git a/tests/plugin/hotblocks.c b/tests/plugin/hotblocks.c
new file mode 100644
index 0000000000..1bd183849a
--- /dev/null
+++ b/tests/plugin/hotblocks.c
@@ -0,0 +1,143 @@
+/*
+ * Copyright (C) 2019, Alex Bennée <alex.bennee@linaro.org>
+ *
+ * License: GNU GPL, version 2 or later.
+ *   See the COPYING file in the top-level directory.
+ */
+#include <inttypes.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <glib.h>
+
+#include <qemu-plugin.h>
+
+static bool do_inline;
+
+/* Plugins need to take care of their own locking */
+static GMutex lock;
+static GHashTable *hotblocks;
+static guint64 limit = 20;
+
+/*
+ * Counting Structure
+ *
+ * The internals of the TCG are not exposed to plugins so we can only
+ * get the starting PC for each block. We cheat this slightly by
+ * xor'ing the number of instructions to the hash to help
+ * differentiate.
+ */
+typedef struct {
+    uint64_t start_addr;
+    uint64_t exec_count;
+    int      trans_count;
+    unsigned long insns;
+} ExecCount;
+
+static gint cmp_exec_count(gconstpointer a, gconstpointer b)
+{
+    ExecCount *ea = (ExecCount *) a;
+    ExecCount *eb = (ExecCount *) b;
+    return ea->exec_count > eb->exec_count ? -1 : 1;
+}
+
+static void plugin_exit(qemu_plugin_id_t id, void *p)
+{
+    g_autoptr(GString) report = g_string_new("collected ");
+    GList *counts, *it;
+    int i;
+
+    g_mutex_lock(&lock);
+    g_string_append_printf(report, "%d entries in the hash table\n",
+                           g_hash_table_size(hotblocks));
+    counts = g_hash_table_get_values(hotblocks);
+    it = g_list_sort(counts, cmp_exec_count);
+
+    if (it) {
+        g_string_append_printf(report, "pc, tcount, icount, ecount\n");
+
+        for (i = 0; i < limit && it->next; i++, it = it->next) {
+            ExecCount *rec = (ExecCount *) it->data;
+            g_string_append_printf(report, "%#016"PRIx64", %d, %ld, %"PRId64"\n",
+                                   rec->start_addr, rec->trans_count,
+                                   rec->insns, rec->exec_count);
+        }
+
+        g_list_free(it);
+        g_mutex_unlock(&lock);
+    }
+
+    qemu_plugin_outs(report->str);
+}
+
+static void plugin_init(void)
+{
+    hotblocks = g_hash_table_new(NULL, g_direct_equal);
+}
+
+static void vcpu_tb_exec(unsigned int cpu_index, void *udata)
+{
+    ExecCount *cnt;
+    uint64_t hash = (uint64_t) udata;
+
+    g_mutex_lock(&lock);
+    cnt = (ExecCount *) g_hash_table_lookup(hotblocks, (gconstpointer) hash);
+    /* should always succeed */
+    g_assert(cnt);
+    cnt->exec_count++;
+    g_mutex_unlock(&lock);
+}
+
+/*
+ * When do_inline we ask the plugin to increment the counter for us.
+ * Otherwise a helper is inserted which calls the vcpu_tb_exec
+ * callback.
+ */
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{
+    ExecCount *cnt;
+    uint64_t pc = qemu_plugin_tb_vaddr(tb);
+    unsigned long insns = qemu_plugin_tb_n_insns(tb);
+    uint64_t hash = pc ^ insns;
+
+    g_mutex_lock(&lock);
+    cnt = (ExecCount *) g_hash_table_lookup(hotblocks, (gconstpointer) hash);
+    if (cnt) {
+        cnt->trans_count++;
+    } else {
+        cnt = g_new0(ExecCount, 1);
+        cnt->start_addr = pc;
+        cnt->trans_count = 1;
+        cnt->insns = insns;
+        g_hash_table_insert(hotblocks, (gpointer) hash, (gpointer) cnt);
+    }
+
+    g_mutex_unlock(&lock);
+
+    if (do_inline) {
+        qemu_plugin_register_vcpu_tb_exec_inline(tb, QEMU_PLUGIN_INLINE_ADD_U64,
+                                                 &cnt->exec_count, 1);
+    } else {
+        qemu_plugin_register_vcpu_tb_exec_cb(tb, vcpu_tb_exec,
+                                             QEMU_PLUGIN_CB_NO_REGS,
+                                             (void *)hash);
+    }
+}
+
+QEMU_PLUGIN_EXPORT
+int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info,
+                        int argc, char **argv)
+{
+    if (argc && strcmp(argv[0], "inline") == 0) {
+        do_inline = true;
+    }
+
+    plugin_init();
+
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
+    return 0;
+}
diff --git a/tests/plugin/hotpages.c b/tests/plugin/hotpages.c
new file mode 100644
index 0000000000..77df07a3cc
--- /dev/null
+++ b/tests/plugin/hotpages.c
@@ -0,0 +1,191 @@
+/*
+ * Copyright (C) 2019, Alex Bennée <alex.bennee@linaro.org>
+ *
+ * Hot Pages - show which pages saw the most memory accesses.
+ *
+ * License: GNU GPL, version 2 or later.
+ *   See the COPYING file in the top-level directory.
+ */
+
+#include <inttypes.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <glib.h>
+
+#include <qemu-plugin.h>
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+static uint64_t page_size = 4096;
+static uint64_t page_mask;
+static int limit = 50;
+static enum qemu_plugin_mem_rw rw = QEMU_PLUGIN_MEM_RW;
+static bool track_io;
+
+enum sort_type {
+    SORT_RW = 0,
+    SORT_R,
+    SORT_W,
+    SORT_A
+};
+
+static int sort_by = SORT_RW;
+
+typedef struct {
+    uint64_t page_address;
+    int cpu_read;
+    int cpu_write;
+    uint64_t reads;
+    uint64_t writes;
+} PageCounters;
+
+static GMutex lock;
+static GHashTable *pages;
+
+static gint cmp_access_count(gconstpointer a, gconstpointer b)
+{
+    PageCounters *ea = (PageCounters *) a;
+    PageCounters *eb = (PageCounters *) b;
+    int r;
+    switch (sort_by) {
+    case SORT_RW:
+        r = (ea->reads + ea->writes) > (eb->reads + eb->writes) ? -1 : 1;
+        break;
+    case SORT_R:
+        r = ea->reads > eb->reads ? -1 : 1;
+        break;
+    case SORT_W:
+        r = ea->writes > eb->writes ? -1 : 1;
+        break;
+    case SORT_A:
+        r = ea->page_address > eb->page_address ? -1 : 1;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+    return r;
+}
+
+
+static void plugin_exit(qemu_plugin_id_t id, void *p)
+{
+    g_autoptr(GString) report = g_string_new("Addr, RCPUs, Reads, WCPUs, Writes\n");
+    int i;
+    GList *counts;
+
+    counts = g_hash_table_get_values(pages);
+    if (counts && g_list_next(counts)) {
+        GList *it;
+
+        it = g_list_sort(counts, cmp_access_count);
+
+        for (i = 0; i < limit && it->next; i++, it = it->next) {
+            PageCounters *rec = (PageCounters *) it->data;
+            g_string_append_printf(report,
+                                   "%#016"PRIx64", 0x%04x, %"PRId64
+                                   ", 0x%04x, %"PRId64"\n",
+                                   rec->page_address,
+                                   rec->cpu_read, rec->reads,
+                                   rec->cpu_write, rec->writes);
+        }
+        g_list_free(it);
+    }
+
+    qemu_plugin_outs(report->str);
+}
+
+static void plugin_init(void)
+{
+    page_mask = (page_size - 1);
+    pages = g_hash_table_new(NULL, g_direct_equal);
+}
+
+static void vcpu_haddr(unsigned int cpu_index, qemu_plugin_meminfo_t meminfo,
+                       uint64_t vaddr, void *udata)
+{
+    struct qemu_plugin_hwaddr *hwaddr = qemu_plugin_get_hwaddr(meminfo, vaddr);
+    uint64_t page;
+    PageCounters *count;
+
+    /* We only get a hwaddr for system emulation */
+    if (track_io) {
+        if (hwaddr && qemu_plugin_hwaddr_is_io(hwaddr)) {
+            page = vaddr;
+        } else {
+            return;
+        }
+    } else {
+        if (hwaddr && !qemu_plugin_hwaddr_is_io(hwaddr)) {
+            page = (uint64_t) qemu_plugin_hwaddr_device_offset(hwaddr);
+        } else {
+            page = vaddr;
+        }
+    }
+    page &= ~page_mask;
+
+    g_mutex_lock(&lock);
+    count = (PageCounters *) g_hash_table_lookup(pages, GUINT_TO_POINTER(page));
+
+    if (!count) {
+        count = g_new0(PageCounters, 1);
+        count->page_address = page;
+        g_hash_table_insert(pages, GUINT_TO_POINTER(page), (gpointer) count);
+    }
+    if (qemu_plugin_mem_is_store(meminfo)) {
+        count->writes++;
+        count->cpu_write |= (1 << cpu_index);
+    } else {
+        count->reads++;
+        count->cpu_read |= (1 << cpu_index);
+    }
+
+    g_mutex_unlock(&lock);
+}
+
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{
+    size_t n = qemu_plugin_tb_n_insns(tb);
+    size_t i;
+
+    for (i = 0; i < n; i++) {
+        struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i);
+        qemu_plugin_register_vcpu_mem_cb(insn, vcpu_haddr,
+                                         QEMU_PLUGIN_CB_NO_REGS,
+                                         rw, NULL);
+    }
+}
+
+QEMU_PLUGIN_EXPORT
+int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info,
+                        int argc, char **argv)
+{
+    int i;
+
+    for (i = 0; i < argc; i++) {
+        char *opt = argv[i];
+        if (g_strcmp0(opt, "reads") == 0) {
+            sort_by = SORT_R;
+        } else if (g_strcmp0(opt, "writes") == 0) {
+            sort_by = SORT_W;
+        } else if (g_strcmp0(opt, "address") == 0) {
+            sort_by = SORT_A;
+        } else if (g_strcmp0(opt, "io") == 0) {
+            track_io = true;
+        } else if (g_str_has_prefix(opt, "pagesize=")) {
+            page_size = g_ascii_strtoull(opt + 9, NULL, 10);
+        } else {
+            fprintf(stderr, "option parsing failed: %s\n", opt);
+            return -1;
+        }
+    }
+
+    plugin_init();
+
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
+    return 0;
+}
diff --git a/tests/plugin/howvec.c b/tests/plugin/howvec.c
new file mode 100644
index 0000000000..58fa675e34
--- /dev/null
+++ b/tests/plugin/howvec.c
@@ -0,0 +1,352 @@
+/*
+ * Copyright (C) 2019, Alex Bennée <alex.bennee@linaro.org>
+ *
+ * How vectorised is this code?
+ *
+ * Attempt to measure the amount of vectorisation that has been done
+ * on some code by counting classes of instruction.
+ *
+ * License: GNU GPL, version 2 or later.
+ *   See the COPYING file in the top-level directory.
+ */
+#include <inttypes.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <glib.h>
+
+#include <qemu-plugin.h>
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+typedef enum {
+    COUNT_CLASS,
+    COUNT_INDIVIDUAL,
+    COUNT_NONE
+} CountType;
+
+static int limit = 50;
+static bool do_inline;
+static bool verbose;
+
+static GMutex lock;
+static GHashTable *insns;
+
+typedef struct {
+    const char *class;
+    const char *opt;
+    uint32_t mask;
+    uint32_t pattern;
+    CountType what;
+    uint64_t count;
+} InsnClassExecCount;
+
+typedef struct {
+    char *insn;
+    uint32_t opcode;
+    uint64_t count;
+    InsnClassExecCount *class;
+} InsnExecCount;
+
+/*
+ * Matchers for classes of instructions, order is important.
+ *
+ * Your most precise match must be before looser matches. If no match
+ * is found in the table we can create an individual entry.
+ *
+ * 31..28 27..24 23..20 19..16 15..12 11..8 7..4 3..0
+ */
+static InsnClassExecCount aarch64_insn_classes[] = {
+    /* "Reserved"" */
+    { "  UDEF",              "udef",   0xffff0000, 0x00000000, COUNT_NONE},
+    { "  SVE",               "sve",    0x1e000000, 0x04000000, COUNT_CLASS},
+    { "Reserved",            "res",    0x1e000000, 0x00000000, COUNT_CLASS},
+    /* Data Processing Immediate */
+    { "  PCrel addr",        "pcrel",  0x1f000000, 0x10000000, COUNT_CLASS},
+    { "  Add/Sub (imm,tags)","asit",   0x1f800000, 0x11800000, COUNT_CLASS},
+    { "  Add/Sub (imm)",     "asi",    0x1f000000, 0x11000000, COUNT_CLASS},
+    { "  Logical (imm)",     "logi",   0x1f800000, 0x12000000, COUNT_CLASS},
+    { "  Move Wide (imm)",   "movwi",  0x1f800000, 0x12800000, COUNT_CLASS},
+    { "  Bitfield",          "bitf",   0x1f800000, 0x13000000, COUNT_CLASS},
+    { "  Extract",           "extr",   0x1f800000, 0x13800000, COUNT_CLASS},
+    { "Data Proc Imm",       "dpri",   0x1c000000, 0x10000000, COUNT_CLASS},
+    /* Branches */
+    { "  Cond Branch (imm)", "cndb",   0xfe000000, 0x54000000, COUNT_CLASS},
+    { "  Exception Gen",     "excp",   0xff000000, 0xd4000000, COUNT_CLASS},
+    { "    NOP",             "nop",    0xffffffff, 0xd503201f, COUNT_NONE},
+    { "  Hints",             "hint",   0xfffff000, 0xd5032000, COUNT_CLASS},
+    { "  Barriers",          "barr",   0xfffff000, 0xd5033000, COUNT_CLASS},
+    { "  PSTATE",            "psta",   0xfff8f000, 0xd5004000, COUNT_CLASS},
+    { "  System Insn",       "sins",   0xffd80000, 0xd5080000, COUNT_CLASS},
+    { "  System Reg",        "sreg",   0xffd00000, 0xd5100000, COUNT_CLASS},
+    { "  Branch (reg)",      "breg",   0xfe000000, 0xd6000000, COUNT_CLASS},
+    { "  Branch (imm)",      "bimm",   0x7c000000, 0x14000000, COUNT_CLASS},
+    { "  Cmp & Branch",      "cmpb",   0x7e000000, 0x34000000, COUNT_CLASS},
+    { "  Tst & Branch",      "tstb",   0x7e000000, 0x36000000, COUNT_CLASS},
+    { "Branches",            "branch", 0x1c000000, 0x14000000, COUNT_CLASS},
+    /* Loads and Stores */
+    { "  AdvSimd ldstmult",  "advlsm", 0xbfbf0000, 0x0c000000, COUNT_CLASS},
+    { "  AdvSimd ldstmult++","advlsmp",0xbfb00000, 0x0c800000, COUNT_CLASS},
+    { "  AdvSimd ldst",      "advlss", 0xbf9f0000, 0x0d000000, COUNT_CLASS},
+    { "  AdvSimd ldst++",    "advlssp",0xbf800000, 0x0d800000, COUNT_CLASS},
+    { "  ldst excl",         "ldstx",  0x3f000000, 0x08000000, COUNT_CLASS},
+    { "    Prefetch",        "prfm",   0xff000000, 0xd8000000, COUNT_CLASS},
+    { "  Load Reg (lit)",    "ldlit",  0x1b000000, 0x18000000, COUNT_CLASS},
+    { "  ldst noalloc pair", "ldstnap",0x3b800000, 0x28000000, COUNT_CLASS},
+    { "  ldst pair",         "ldstp",  0x38000000, 0x28000000, COUNT_CLASS},
+    { "  ldst reg",          "ldstr",  0x3b200000, 0x38000000, COUNT_CLASS},
+    { "  Atomic ldst",       "atomic", 0x3b200c00, 0x38200000, COUNT_CLASS},
+    { "  ldst reg (reg off)","ldstro", 0x3b200b00, 0x38200800, COUNT_CLASS},
+    { "  ldst reg (pac)",    "ldstpa", 0x3b200200, 0x38200800, COUNT_CLASS},
+    { "  ldst reg (imm)",    "ldsti",  0x3b000000, 0x39000000, COUNT_CLASS},
+    { "Loads & Stores",      "ldst",   0x0a000000, 0x08000000, COUNT_CLASS},
+    /* Data Processing Register */
+    { "Data Proc Reg",       "dprr",   0x0e000000, 0x0a000000, COUNT_CLASS},
+    /* Scalar FP */
+    { "Scalar FP ",          "fpsimd", 0x0e000000, 0x0e000000, COUNT_CLASS},
+    /* Unclassified */
+    { "Unclassified",        "unclas", 0x00000000, 0x00000000, COUNT_CLASS},
+};
+
+static InsnClassExecCount sparc32_insn_classes[] = {
+    { "Call",                "call",   0xc0000000, 0x40000000, COUNT_CLASS},
+    { "Branch ICond",        "bcc",    0xc1c00000, 0x00800000, COUNT_CLASS},
+    { "Branch Fcond",        "fbcc",   0xc1c00000, 0x01800000, COUNT_CLASS},
+    { "SetHi",               "sethi",  0xc1c00000, 0x01000000, COUNT_CLASS},
+    { "FPU ALU",             "fpu",    0xc1f00000, 0x81a00000, COUNT_CLASS},
+    { "ALU",                 "alu",    0xc0000000, 0x80000000, COUNT_CLASS},
+    { "Load/Store",          "ldst",   0xc0000000, 0xc0000000, COUNT_CLASS},
+    /* Unclassified */
+    { "Unclassified",        "unclas", 0x00000000, 0x00000000, COUNT_INDIVIDUAL},
+};
+
+static InsnClassExecCount sparc64_insn_classes[] = {
+    { "SetHi & Branches",     "op0",   0xc0000000, 0x00000000, COUNT_CLASS},
+    { "Call",                 "op1",   0xc0000000, 0x40000000, COUNT_CLASS},
+    { "Arith/Logical/Move",   "op2",   0xc0000000, 0x80000000, COUNT_CLASS},
+    { "Arith/Logical/Move",   "op3",   0xc0000000, 0xc0000000, COUNT_CLASS},
+    /* Unclassified */
+    { "Unclassified",        "unclas", 0x00000000, 0x00000000, COUNT_INDIVIDUAL},
+};
+
+/* Default matcher for currently unclassified architectures */
+static InsnClassExecCount default_insn_classes[] = {
+    { "Unclassified",        "unclas", 0x00000000, 0x00000000, COUNT_INDIVIDUAL},
+};
+
+typedef struct {
+    const char *qemu_target;
+    InsnClassExecCount *table;
+    int table_sz;
+} ClassSelector;
+
+static ClassSelector class_tables[] =
+{
+    { "aarch64", aarch64_insn_classes, ARRAY_SIZE(aarch64_insn_classes) },
+    { "sparc",   sparc32_insn_classes, ARRAY_SIZE(sparc32_insn_classes) },
+    { "sparc64", sparc64_insn_classes, ARRAY_SIZE(sparc64_insn_classes) },
+    { NULL, default_insn_classes, ARRAY_SIZE(default_insn_classes) },
+};
+
+static InsnClassExecCount *class_table;
+static int class_table_sz;
+
+static gint cmp_exec_count(gconstpointer a, gconstpointer b)
+{
+    InsnExecCount *ea = (InsnExecCount *) a;
+    InsnExecCount *eb = (InsnExecCount *) b;
+    return ea->count > eb->count ? -1 : 1;
+}
+
+static void plugin_exit(qemu_plugin_id_t id, void *p)
+{
+    g_autoptr(GString) report = g_string_new("Instruction Classes:\n");
+    int i;
+    GList *counts;
+    InsnClassExecCount *class = NULL;
+
+    for (i = 0; i < class_table_sz; i++) {
+        class = &class_table[i];
+        switch (class->what) {
+        case COUNT_CLASS:
+            if (class->count || verbose) {
+                g_string_append_printf(report, "Class: %-24s\t(%ld hits)\n",
+                                       class->class,
+                                       class->count);
+            }
+            break;
+        case COUNT_INDIVIDUAL:
+            g_string_append_printf(report, "Class: %-24s\tcounted individually\n",
+                                   class->class);
+            break;
+        case COUNT_NONE:
+            g_string_append_printf(report, "Class: %-24s\tnot counted\n",
+                                   class->class);
+            break;
+        default:
+            break;
+        }
+    }
+
+    counts = g_hash_table_get_values(insns);
+    if (counts && g_list_next(counts)) {
+        GList *it;
+
+        g_string_append_printf(report,"Individual Instructions:\n");
+
+        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",
+                                   rec->insn,
+                                   rec->count,
+                                   rec->opcode,
+                                   rec->class ?
+                                   rec->class->class : "un-categorised");
+        }
+        g_list_free(it);
+    }
+
+    qemu_plugin_outs(report->str);
+}
+
+static void plugin_init(void)
+{
+    insns = g_hash_table_new(NULL, g_direct_equal);
+}
+
+static void vcpu_insn_exec_before(unsigned int cpu_index, void *udata)
+{
+    uint64_t *count = (uint64_t *) udata;
+    (*count)++;
+}
+
+static uint64_t * find_counter(struct qemu_plugin_insn *insn)
+{
+    int i;
+    uint64_t *cnt = NULL;
+    uint32_t opcode;
+    InsnClassExecCount *class = NULL;
+
+    /*
+     * We only match the first 32 bits of the instruction which is
+     * fine for most RISCs but a bit limiting for CISC architectures.
+     * They would probably benefit from a more tailored plugin.
+     * However we can fall back to individual instruction counting.
+     */
+    opcode = *((uint32_t *)qemu_plugin_insn_data(insn));
+
+    for (i = 0; !cnt && i < class_table_sz; i++) {
+        class = &class_table[i];
+        uint32_t masked_bits = opcode & class->mask;
+        if (masked_bits == class->pattern) {
+            break;
+        }
+    }
+
+    g_assert(class);
+
+    switch (class->what) {
+    case COUNT_NONE:
+        return NULL;
+    case COUNT_CLASS:
+        return &class->count;
+    case COUNT_INDIVIDUAL:
+    {
+        InsnExecCount *icount;
+
+        g_mutex_lock(&lock);
+        icount = (InsnExecCount *) g_hash_table_lookup(insns,
+                                                       GUINT_TO_POINTER(opcode));
+
+        if (!icount) {
+            icount = g_new0(InsnExecCount, 1);
+            icount->opcode = opcode;
+            icount->insn = qemu_plugin_insn_disas(insn);
+            icount->class = class;
+
+            g_hash_table_insert(insns, GUINT_TO_POINTER(opcode),
+                                (gpointer) icount);
+        }
+        g_mutex_unlock(&lock);
+
+        return &icount->count;
+    }
+    default:
+        g_assert_not_reached();
+    }
+
+    return NULL;
+}
+
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{
+    size_t n = qemu_plugin_tb_n_insns(tb);
+    size_t i;
+
+    for (i = 0; i < n; i++) {
+        uint64_t *cnt;
+        struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i);
+        cnt = find_counter(insn);
+
+        if (cnt) {
+            if (do_inline) {
+                qemu_plugin_register_vcpu_insn_exec_inline(
+                    insn, QEMU_PLUGIN_INLINE_ADD_U64, cnt, 1);
+            } else {
+                qemu_plugin_register_vcpu_insn_exec_cb(
+                    insn, vcpu_insn_exec_before, QEMU_PLUGIN_CB_NO_REGS, cnt);
+            }
+        }
+    }
+}
+
+QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
+                                           const qemu_info_t *info,
+                                           int argc, char **argv)
+{
+    int i;
+
+    /* Select a class table appropriate to the guest architecture */
+    for (i = 0; i < ARRAY_SIZE(class_tables); i++) {
+        ClassSelector *entry = &class_tables[i];
+        if (!entry->qemu_target ||
+            strcmp(entry->qemu_target, info->target_name) == 0) {
+            class_table = entry->table;
+            class_table_sz = entry->table_sz;
+            break;
+        }
+    }
+
+    for (i = 0; i < argc; i++) {
+        char *p = argv[i];
+        if (strcmp(p, "inline") == 0) {
+            do_inline = true;
+        } else if (strcmp(p, "verbose") == 0) {
+            verbose = true;
+        } else {
+            int j;
+            CountType type = COUNT_INDIVIDUAL;
+            if (*p == '!') {
+                type = COUNT_NONE;
+                p++;
+            }
+            for (j = 0; j < class_table_sz; j++) {
+                if (strcmp(p, class_table[j].opt) == 0) {
+                    class_table[j].what = type;
+                    break;
+                }
+            }
+        }
+    }
+
+    plugin_init();
+
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
+    return 0;
+}
diff --git a/tests/plugin/insn.c b/tests/plugin/insn.c
new file mode 100644
index 0000000000..e5fd07fb64
--- /dev/null
+++ b/tests/plugin/insn.c
@@ -0,0 +1,61 @@
+/*
+ * 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 <inttypes.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <glib.h>
+
+#include <qemu-plugin.h>
+
+static uint64_t insn_count;
+static bool do_inline;
+
+static void vcpu_insn_exec_before(unsigned int cpu_index, void *udata)
+{
+    insn_count++;
+}
+
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{
+    size_t n = qemu_plugin_tb_n_insns(tb);
+    size_t i;
+
+    for (i = 0; i < n; i++) {
+        struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i);
+
+        if (do_inline) {
+            qemu_plugin_register_vcpu_insn_exec_inline(
+                insn, QEMU_PLUGIN_INLINE_ADD_U64, &insn_count, 1);
+        } else {
+            qemu_plugin_register_vcpu_insn_exec_cb(
+                insn, vcpu_insn_exec_before, QEMU_PLUGIN_CB_NO_REGS, NULL);
+        }
+    }
+}
+
+static void plugin_exit(qemu_plugin_id_t id, void *p)
+{
+    g_autofree gchar *out;
+    out = g_strdup_printf("insns: %" PRIu64 "\n", insn_count);
+    qemu_plugin_outs(out);
+}
+
+QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
+                                           const qemu_info_t *info,
+                                           int argc, char **argv)
+{
+    if (argc && !strcmp(argv[0], "inline")) {
+        do_inline = true;
+    }
+
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
+    return 0;
+}
diff --git a/tests/plugin/mem.c b/tests/plugin/mem.c
new file mode 100644
index 0000000000..d967388989
--- /dev/null
+++ b/tests/plugin/mem.c
@@ -0,0 +1,97 @@
+/*
+ * 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 <inttypes.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <glib.h>
+
+#include <qemu-plugin.h>
+
+static uint64_t mem_count;
+static uint64_t io_count;
+static bool do_inline;
+static bool do_haddr;
+static enum qemu_plugin_mem_rw rw = QEMU_PLUGIN_MEM_RW;
+
+static void plugin_exit(qemu_plugin_id_t id, void *p)
+{
+    g_autoptr(GString) out = g_string_new("");
+
+    g_string_printf(out, "mem accesses: %" PRIu64 "\n", mem_count);
+    if (do_haddr) {
+        g_string_append_printf(out, "io accesses: %" PRIu64 "\n", mem_count);
+    }
+    qemu_plugin_outs(out->str);
+}
+
+static void vcpu_mem(unsigned int cpu_index, qemu_plugin_meminfo_t meminfo,
+                     uint64_t vaddr, void *udata)
+{
+    if (do_haddr) {
+        struct qemu_plugin_hwaddr *hwaddr;
+        hwaddr = qemu_plugin_get_hwaddr(meminfo, vaddr);
+        if (qemu_plugin_hwaddr_is_io(hwaddr)) {
+            io_count++;
+        } else {
+            mem_count++;
+        }
+    } else {
+        mem_count++;
+    }
+}
+
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{
+    size_t n = qemu_plugin_tb_n_insns(tb);
+    size_t i;
+
+    for (i = 0; i < n; i++) {
+        struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i);
+
+        if (do_inline) {
+            qemu_plugin_register_vcpu_mem_inline(insn, rw,
+                                                 QEMU_PLUGIN_INLINE_ADD_U64,
+                                                 &mem_count, 1);
+        } else {
+            qemu_plugin_register_vcpu_mem_cb(insn, vcpu_mem,
+                                             QEMU_PLUGIN_CB_NO_REGS,
+                                             rw, NULL);
+        }
+    }
+}
+
+QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
+                                           const qemu_info_t *info,
+                                           int argc, char **argv)
+{
+    if (argc) {
+        if (argc >= 3) {
+            if (!strcmp(argv[2], "haddr")) {
+                do_haddr = true;
+            }
+        }
+        if (argc >= 2) {
+            const char *str = argv[1];
+
+            if (!strcmp(str, "r")) {
+                rw = QEMU_PLUGIN_MEM_R;
+            } else if (!strcmp(str, "w")) {
+                rw = QEMU_PLUGIN_MEM_W;
+            }
+        }
+        if (!strcmp(argv[0], "inline")) {
+            do_inline = true;
+        }
+    }
+
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
+    return 0;
+}
diff --git a/tests/tcg/Makefile.target b/tests/tcg/Makefile.target
index 5a9a6faba4..3c7421a356 100644
--- a/tests/tcg/Makefile.target
+++ b/tests/tcg/Makefile.target
@@ -30,7 +30,7 @@
 #
 
 all:
--include ../../config-host.mak
+-include ../../../config-host.mak
 -include ../config-$(TARGET).mak
 
 # for including , in command strings
@@ -66,6 +66,8 @@ conditional-diff-out = 							\
 
 # Tests we are building
 TESTS=
+# additional tests which may re-use existing binaries
+EXTRA_TESTS=
 
 # Start with a blank slate, the build targets get to add stuff first
 CFLAGS=
@@ -109,7 +111,7 @@ else
 
 endif
 
-all: $(TESTS)
+all: $(TESTS) $(EXTRA_TESTS)
 
 #
 # Test Runners
@@ -121,11 +123,39 @@ all: $(TESTS)
 #
 
 RUN_TESTS=$(patsubst %,run-%, $(TESTS))
+
+# If plugins exist also include those in the tests
+ifeq ($(CONFIG_PLUGIN),y)
+PLUGIN_DIR=../../plugin
+VPATH+=$(PLUGIN_DIR)
+PLUGINS=$(notdir $(wildcard $(PLUGIN_DIR)/*.so))
+
+# We need to ensure expand the run-plugin-TEST-with-PLUGIN
+# pre-requistes manually here as we can't use stems to handle it. We
+# also add some special helpers the run-plugin- rules can use bellow.
+
+$(foreach p,$(PLUGINS), \
+	$(foreach t,$(TESTS),\
+		$(eval run-plugin-$(t)-with-$(p): $t $p) \
+		$(eval run-plugin-$(t)-with-$(p): TIMEOUT=30) \
+		$(eval RUN_TESTS+=run-plugin-$(t)-with-$(p))))
+endif
+
+strip-plugin = $(wordlist 1, 1, $(subst -with-, ,$1))
+extract-plugin = $(wordlist 2, 2, $(subst -with-, ,$1))
+
 RUN_TESTS+=$(EXTRA_RUNS)
 
 ifdef CONFIG_USER_ONLY
 run-%: %
 	$(call run-test, $<, $(QEMU) $(QEMU_OPTS) $<, "$< on $(TARGET_NAME)")
+
+run-plugin-%:
+	$(call run-test, $@, $(QEMU) $(QEMU_OPTS) \
+		-plugin $(PLUGIN_DIR)/$(call extract-plugin,$@) \
+		-d plugin -D $*.pout \
+		 $(call strip-plugin,$<), \
+	"$* on $(TARGET_NAME)")
 else
 run-%: %
 	$(call run-test, $<, \
@@ -133,6 +163,15 @@ run-%: %
 		  -chardev file$(COMMA)path=$<.out$(COMMA)id=output \
 	   	  $(QEMU_OPTS) $<, \
 	  "$< on $(TARGET_NAME)")
+
+run-plugin-%:
+	$(call run-test, $@, \
+	  $(QEMU) -monitor none -display none \
+		  -chardev file$(COMMA)path=$@.out$(COMMA)id=output \
+	   	  -plugin $(PLUGIN_DIR)/$(call extract-plugin,$@) \
+	    	  -d plugin -D $*.pout \
+	   	  $(QEMU_OPTS) $(call strip-plugin,$<), \
+	  "$* on $(TARGET_NAME)")
 endif
 
 gdb-%: %
diff --git a/tests/tcg/aarch64/Makefile.softmmu-target b/tests/tcg/aarch64/Makefile.softmmu-target
index b4b3957963..950dbb4bac 100644
--- a/tests/tcg/aarch64/Makefile.softmmu-target
+++ b/tests/tcg/aarch64/Makefile.softmmu-target
@@ -52,4 +52,4 @@ run-memory-replay: memory-replay run-memory-record
 	   	  $(QEMU_OPTS) memory, \
 	  "$< on $(TARGET_NAME)")
 
-TESTS+=memory-record memory-replay
+EXTRA_TESTS+=memory-record memory-replay
diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target
index 509f1afa93..96d2321045 100644
--- a/tests/tcg/aarch64/Makefile.target
+++ b/tests/tcg/aarch64/Makefile.target
@@ -26,4 +26,10 @@ AARCH64_TESTS += semihosting
 run-semihosting: semihosting
 	$(call run-test,$<,$(QEMU) $< 2> $<.err, "$< on $(TARGET_NAME)")
 
+run-plugin-semihosting-with-%:
+	$(call run-test, $@, $(QEMU) $(QEMU_OPTS) \
+		-plugin $(PLUGIN_DIR)/$(call extract-plugin,$@) \
+		 $(call strip-plugin,$<) 2> $<.err, \
+		"$< on $(TARGET_NAME) with $*")
+
 TESTS += $(AARCH64_TESTS)
diff --git a/tests/tcg/arm/Makefile.softmmu-target b/tests/tcg/arm/Makefile.softmmu-target
index 231e9a57b4..3fe237ba39 100644
--- a/tests/tcg/arm/Makefile.softmmu-target
+++ b/tests/tcg/arm/Makefile.softmmu-target
@@ -23,3 +23,4 @@ LDFLAGS+=-nostdlib -N -static
 test-armv6m-undef: EXTRA_CFLAGS+=-mcpu=cortex-m0
 
 run-test-armv6m-undef: QEMU_OPTS+=-semihosting -M microbit -kernel
+run-plugin-test-armv6m-undef-%: QEMU_OPTS+=-semihosting -M microbit -kernel
diff --git a/tests/tcg/arm/Makefile.target b/tests/tcg/arm/Makefile.target
index 3ddff85240..0765f37ff0 100644
--- a/tests/tcg/arm/Makefile.target
+++ b/tests/tcg/arm/Makefile.target
@@ -34,6 +34,12 @@ ARM_TESTS += semihosting
 run-semihosting: semihosting
 	$(call run-test,$<,$(QEMU) $< 2> $<.err, "$< on $(TARGET_NAME)")
 
+run-plugin-semihosting-with-%:
+	$(call run-test, $@, $(QEMU) $(QEMU_OPTS) \
+		-plugin $(PLUGIN_DIR)/$(call extract-plugin,$@) \
+		 $(call strip-plugin,$<) 2> $<.err, \
+		"$< on $(TARGET_NAME) with $*")
+
 TESTS += $(ARM_TESTS)
 
 # On ARM Linux only supports 4k pages
diff --git a/tests/tcg/cris/Makefile.target b/tests/tcg/cris/Makefile.target
index c1173ead42..24c7f2e761 100644
--- a/tests/tcg/cris/Makefile.target
+++ b/tests/tcg/cris/Makefile.target
@@ -47,7 +47,7 @@ CRT_FILES = crt.o sys.o
 	$(CC) $(ASFLAGS) $< -o $@ $(LDFLAGS) $(NOSTDFLAGS) $(CRT_FILES)
 
 # The default CPU breaks (possibly as it's max?) so force crisv17
-$(CRIS_RUNS): QEMU_OPTS=-cpu crisv17
+QEMU_OPTS=-cpu crisv17
 
 # Additional runners to run under GNU SIM
 CRIS_RUNS_ON_SIM=$(patsubst %, %-on-sim, $(CRIS_RUNS))
diff --git a/tests/tcg/i386/Makefile.target b/tests/tcg/i386/Makefile.target
index 08c5736a4d..43ee2e181e 100644
--- a/tests/tcg/i386/Makefile.target
+++ b/tests/tcg/i386/Makefile.target
@@ -7,10 +7,8 @@ VPATH 		+= $(I386_SRC)
 
 I386_SRCS=$(notdir $(wildcard $(I386_SRC)/*.c))
 ALL_X86_TESTS=$(I386_SRCS:.c=)
-I386_TESTS:=$(filter-out test-i386-ssse3, $(ALL_X86_TESTS))
+SKIP_I386_TESTS=test-i386-ssse3
 X86_64_TESTS:=$(filter test-i386-ssse3, $(ALL_X86_TESTS))
-# Update TESTS
-TESTS=$(MULTIARCH_TESTS) $(I386_TESTS)
 
 #
 # hello-i386 is a barebones app
@@ -36,9 +34,12 @@ run-test-i386-fprem: test-i386-fprem test-i386-fprem.ref
 	$(call run-test,test-i386-fprem, $(QEMU) $<,"$< on $(TARGET_NAME)")
 	$(call diff-out,test-i386-fprem, test-i386-fprem.ref)
 else
-run-test-i386-fprem: test-i386-fprem
-	$(call skip-test, $<, "SLOW")
+SKIP_I386_TESTS+=test-i386-fprem
 endif
 
+# Update TESTS
+I386_TESTS:=$(filter-out $(SKIP_I386_TESTS), $(ALL_X86_TESTS))
+TESTS=$(MULTIARCH_TESTS) $(I386_TESTS)
+
 # On i386 and x86_64 Linux only supports 4k pages (large pages are a different hack)
 EXTRA_RUNS+=run-test-mmap-4096