cpu: cache CPUClass in CPUState for hot code paths

The class cast checkers are quite expensive and always on (unlike the
dynamic case who's checks are gated by CONFIG_QOM_CAST_DEBUG). To
avoid the overhead of repeatedly checking something which should never
change we cache the CPUClass reference for use in the hot code paths.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220811151413.3350684-3-alex.bennee@linaro.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Message-Id: <20220923084803.498337-3-clg@kaod.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

diff --git a/cpu.c b/cpu.c
index 584ac78baf969ae6cd6afa6ca9a9fec902ede242..14365e36f3a1ddc5f6f167b648069ac95eaad7b9 100644 (file)
--- a/cpu.c
+++ b/cpu.c
@@ -131,9 +131,8 @@ const VMStateDescription vmstate_cpu_common = {
 
 void cpu_exec_realizefn(CPUState *cpu, Error **errp)
 {
-#ifndef CONFIG_USER_ONLY
-    CPUClass *cc = CPU_GET_CLASS(cpu);
-#endif
+    /* cache the cpu class for the hotpath */
+    cpu->cc = CPU_GET_CLASS(cpu);
 
     cpu_list_add(cpu);
     if (!accel_cpu_realizefn(cpu, errp)) {
@@ -151,8 +150,8 @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp)
     if (qdev_get_vmsd(DEVICE(cpu)) == NULL) {
         vmstate_register(NULL, cpu->cpu_index, &vmstate_cpu_common, cpu);
     }
-    if (cc->sysemu_ops->legacy_vmsd != NULL) {
-        vmstate_register(NULL, cpu->cpu_index, cc->sysemu_ops->legacy_vmsd, cpu);
+    if (cpu->cc->sysemu_ops->legacy_vmsd != NULL) {
+        vmstate_register(NULL, cpu->cpu_index, cpu->cc->sysemu_ops->legacy_vmsd, cpu);
     }
 #endif /* CONFIG_USER_ONLY */
 }

diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index 500503da1316dffe04b7fc1849fe8c1920b3c2d4..1a7e1a93804acf28447999607882720a4472ee37 100644 (file)
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -51,6 +51,13 @@ typedef int (*WriteCoreDumpFunction)(const void *buf, size_t size,
  */
 #define CPU(obj) ((CPUState *)(obj))
 
+/*
+ * The class checkers bring in CPU_GET_CLASS() which is potentially
+ * expensive given the eventual call to
+ * object_class_dynamic_cast_assert(). Because of this the CPUState
+ * has a cached value for the class in cs->cc which is set up in
+ * cpu_exec_realizefn() for use in hot code paths.
+ */
 typedef struct CPUClass CPUClass;
 DECLARE_CLASS_CHECKERS(CPUClass, CPU,
                        TYPE_CPU)
@@ -317,6 +324,8 @@ struct qemu_work_item;
 struct CPUState {
     /*< private >*/
     DeviceState parent_obj;
+    /* cache to avoid expensive CPU_GET_CLASS */
+    CPUClass *cc;
     /*< public >*/
 
     int nr_cores;