C2: LoopStripMining doesn't strip as expected

During work on JDK-8219584, I noticed that we still get safepoint timeouts when running the simple loop below with -XX:+UseCountedLoopSafepoints -XX:LoopStripMiningIter=1000.
OptoAssembly shows that LoopStripMining has stripped the loop, but uses the same loop exit condition for both, the inner and outer loop:
03b cmpl R11, #2147483647
04e cmpl R11, #2147483647
So the inner loop runs through the full int range without safepoint check leading to a timeout.


TestLoop.java:
public class TestLoop{

  public static int test_loop(int x) {
      int sum = 0;
      if (x != 0) {
          for (int y = 1; y < Integer.MAX_VALUE; ++y) {
              if (y % x == 0) ++sum;
          }
      }
      return sum;
  }

  public static void main(String args[]) {
    int sum = test_loop(3);
    System.out.println("sum: " + sum);
  }
}

Full command line:
jdk-jdk-fastdebug/images/jdk/bin/java -XX:+UnlockDiagnosticVMOptions -XX:+SafepointTimeout -XX:+SafepointALot -XX:+AbortVMOnSafepointTimeout -XX:SafepointTimeoutDelay=500 -XX:GuaranteedSafepointInterval=500 -XX:+PrintOptoAssembly -XX:-TieredCompilation -XX:+UseCountedLoopSafepoints -XX:LoopStripMiningIter=1000 -XX:LoopUnrollLimit=0 -XX:CompileCommand=compileonly,TestLoop::test_loop -Xcomp TestLoop

Full OptoAssembly:
000 B1: # B8 B2 <- BLOCK HEAD IS JUNK Freq: 1
000 # stack bang (136 bytes)
        pushq rbp # Save rbp
        subq rsp, #16 # Create frame

00c testl RSI, RSI
00e je,s B8 P=0,100000 C=-1,000000
00e
010 B2: # B3 <- B1 Freq: 0,9
010 # TLS is in R15
010 xorl R8, R8 # int
013 movl R11, #1 # int
        nop # 7 bytes pad for loops and calls

020 B3: # B7 B4 <- B2 B5 B4 Loop: B3-B4 inner strip mined Freq: 90
020 movl RAX, R11 # spill
023 cmpl rax, 0x80000000 # irem
        jne,s normal
        xorl rdx, rdx
        cmpl RSI, -1
        je,s done
normal: cdql
        idivl RSI
done:
034 testl RDX, RDX
036 je,s B7 P=0,100000 C=-1,000000
036
038 B4: # B3 B5 <- B7 B3 Freq: 90
038 incl R11 # int
03b cmpl R11, #2147483647
042 jl,s B3 # loop end P=0,900000 C=-1,000000
042
044 B5: # B3 B6 <- B4 Freq: 9
044 movq R10, [R15 + #296 (32-bit)] # ptr
04b testl rax, [R10] # Safepoint: poll for GC # TestLoop::test_loop @ bci:26 L[0]=RSI L[1]=R8 L[2]=R11
        # OopMap{off=75}
04e cmpl R11, #2147483647
055 jl,s B3 P=0,900000 C=-1,000000
055
057 B6: # N1 <- B5 B8 Freq: 1
057 movl RAX, R8 # spill
05a addq rsp, 16 # Destroy frame
        popq rbp
        movq rscratch1, poll_offset[r15_thread] #polling_page_address
        testl rax, [rscratch1] # Safepoint: poll for GC

069 ret
069
06a B7: # B4 <- B3 Freq: 9
06a incl R8 # int
06d jmp,s B4
06d
06f B8: # B6 <- B1 Freq: 0,1
06f xorl R8, R8 # int
072 jmp,s B6