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>

1 files changed, 9 insertions, 0 deletions

diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index 500503da13..1a7e1a9380 100644
--- 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;