jni: Do not create a managed frame for @CriticalNative.
Omit managed frame for @CriticalNative methods, do not check
for exceptions and and make a tail call when possible.
Pass the method pointer in a hidden argument to prepare for
implementing late binding for @CriticalNative methods.
This changes only the JNI compiler, Generic JNI shall be
updated in a separate change.
Performance improvements reported by Golem (art-opt-cc):
x86 x86-64 arm arm64
NativeDowncallStaticCritical6 +17% +50% +88% +139%
NativeDowncallStaticCritical +37% +32% +103% +216%
Test: m test-art-host-gtest
Test: testrunner.py --host --optimizing
Test: aosp_taimen-userdebug boots.
Test: run-gtests.sh
Test: testrunner.py --target --optimizing
Bug: 112189621
Change-Id: I5758c8f478627f2eee8f615b4537a907c211b9f8
diff --git a/compiler/utils/jni_macro_assembler.h b/compiler/utils/jni_macro_assembler.h
index e6130cf..bbe0f73 100644
--- a/compiler/utils/jni_macro_assembler.h
+++ b/compiler/utils/jni_macro_assembler.h
@@ -197,6 +197,9 @@
virtual void VerifyObject(ManagedRegister src, bool could_be_null) = 0;
virtual void VerifyObject(FrameOffset src, bool could_be_null) = 0;
+ // Jump to address held at [base+offset] (used for tail calls).
+ virtual void Jump(ManagedRegister base, Offset offset, ManagedRegister scratch) = 0;
+
// Call to address held at [base+offset]
virtual void Call(ManagedRegister base, Offset offset, ManagedRegister scratch) = 0;
virtual void Call(FrameOffset base, Offset offset, ManagedRegister scratch) = 0;