Series comparison

When running with a single vcpu, we can return a constant instead of a
load when accessing cpu_index.
A side effect is that all tcg operations using it are optimized, most
notably scoreboard access.
When running a simple loop in user-mode, the speedup is around 20%.

Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
---
 accel/tcg/plugin-gen.c |  7 +++++++
 plugins/core.c         | 13 +++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/plugin-gen.c
+++ b/accel/tcg/plugin-gen.c
@@ -XXX,XX +XXX,XX @@ static void gen_disable_mem_helper(void)
 
 static TCGv_i32 gen_cpu_index(void)
 {
+    /*
+     * Optimize when we run with a single vcpu. All values using cpu_index,
+     * including scoreboard index, will be optimized out.
+     */
+    if (qemu_plugin_num_vcpus() == 1) {
+        return tcg_constant_i32(0);
+    }
     TCGv_i32 cpu_index = tcg_temp_ebb_new_i32();
     tcg_gen_ld_i32(cpu_index, tcg_env,
                    -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index));
diff --git a/plugins/core.c b/plugins/core.c
index XXXXXXX..XXXXXXX 100644
--- a/plugins/core.c
+++ b/plugins/core.c
@@ -XXX,XX +XXX,XX @@ static void qemu_plugin_vcpu_init__async(CPUState *cpu, run_on_cpu_data unused)
 
     assert(cpu->cpu_index != UNASSIGNED_CPU_INDEX);
     qemu_rec_mutex_lock(&plugin.lock);
+
+    /*
+     * We want to flush tb when a second cpu appear.
+     * When generating plugin code, we optimize cpu_index for num_vcpus == 1.
+     */
+    if (plugin.num_vcpus == 1) {
+        qemu_rec_mutex_unlock(&plugin.lock);
+        start_exclusive();
+        qemu_rec_mutex_lock(&plugin.lock);
+        tb_flush(cpu);
+        end_exclusive();
+    }
+
     plugin.num_vcpus = MAX(plugin.num_vcpus, cpu->cpu_index + 1);
     plugin_cpu_update__locked(&cpu->cpu_index, NULL, NULL);
     success = g_hash_table_insert(plugin.cpu_ht, &cpu->cpu_index,
-- 
2.39.5

Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>

---

v2:
- no need to do a flush, as user-mode already does it when spawning a
  second cpu (to honor CF_PARALLEL flags).
- change condition detection to use CF_PARALLEL instead
---
 accel/tcg/plugin-gen.c | 9 +++++++++
 1 file changed, 9 insertions(+)