Speed up the tail duplication pass on the testcase below from 68.2s to 1.23s:

#define CL0(a) case a: f(); goto c;
 #define CL1(a) CL0(a##0) CL0(a##1) CL0(a##2) CL0(a##3) CL0(a##4) CL0(a##5) \
 CL0(a##6) CL0(a##7) CL0(a##8) CL0(a##9)
 #define CL2(a) CL1(a##0) CL1(a##1) CL1(a##2) CL1(a##3) CL1(a##4) CL1(a##5) \
 CL1(a##6) CL1(a##7) CL1(a##8) CL1(a##9)
 #define CL3(a) CL2(a##0) CL2(a##1) CL2(a##2) CL2(a##3) CL2(a##4) CL2(a##5) \
 CL2(a##6) CL2(a##7) CL2(a##8) CL2(a##9)
 #define CL4(a) CL3(a##0) CL3(a##1) CL3(a##2) CL3(a##3) CL3(a##4) CL3(a##5) \
 CL3(a##6) CL3(a##7) CL3(a##8) CL3(a##9)

 void f();

 void a() {
     int b;
  c: switch (b) {
         CL4(1)
     }
 }

This comes from GCC PR 15524

llvm-svn: 17390