Fix performance issues related to chaining and unchaining.

1) Patching requests for predicted chaining cells (used by virtual/interface
methods) are now batched in a queue and processed when the VM is paused for GC.

2) When the code cache is full the reset operation is also conducted at the
end of GC pauses so this totally eliminates the need for the compiler thread
to issue suspend-all requests. This is a very rare event and when happening it
takes less than 5ms to finish.

3) Change the initial value of the branch in a predicted chaining cell from 0
(ie lsl r0, r0, #0) to 0xe7fe (ie branch to self) so that initializing a
predicted chaining cell doesn't need to suspend all threads. Together with 1)
seeing 20% speedup on some benchmarks.

4) Add TestCompability.c where defining "TEST_VM_IN_ECLAIR := true" in
buildspec.mk will activate dummy symbols needed to run libdvm.so in older
releases.

Bug: 2397689
Bug: 2396513
Bug: 2331313

1 files changed, 1 insertions, 5 deletions

diff --git a/vm/compiler/codegen/arm/CodegenDriver.c b/vm/compiler/codegen/arm/CodegenDriver.c
index 5be07aa3d..b0e16b82f 100644
--- a/vm/compiler/codegen/arm/CodegenDriver.c
+++ b/vm/compiler/codegen/arm/CodegenDriver.c
@@ -4121,8 +4121,7 @@ bool dvmCompilerDoWork(CompilerWorkOrder *work)
 {
     bool res;
 
-    if (gDvmJit.codeCacheFull &&
-        (work->kind != kWorkOrderICPatch)) {
+    if (gDvmJit.codeCacheFull) {
         return false;
     }
 
@@ -4142,9 +4141,6 @@ bool dvmCompilerDoWork(CompilerWorkOrder *work)
             gDvmJit.printMe = oldPrintMe;;
             break;
         }
-        case kWorkOrderICPatch:
-            res = dvmJitPatchInlineCache((void *) work->pc, work->info);
-            break;
         default:
             res = false;
             dvmAbort();