With the new EH enabled, one exception handling performance test has
regressed while all other improved dramatically. I have investigated the
test case and it turned out that the regression is due to the way we
unwind during second pass when we have an exception that occured in a
catch or finally funclet call chain and escaped it.
What we do is that we unwind stack until we reach the parent stack frame
of the catch / finally and then continue searching for handlers.
The NativeAOT that the new EH is based on doesn't unwind stack though,
it just moves the current stack frame iterator to the position of the
previous exception's stack frame iterator by copying its state.
I have applied the same mechanism to the new EH in coreclr and it
improved the performance of that test 3-4 times on my machine.