AMDGPU/GlobalISel: Set insert point after waterfall loop

[arsenm]

Summary

The current users of the waterfall loop utility functions do not make
use of the restored original insert point. The insertion is either
done, or they set the insert point somewhere else. A future change
will want to insert instructions after the waterfall loop, but
figuring out the point after the loop is more difficult than ensuring
the insert point is there after the loop.

[kerbowa]

LGTM

[arsenm]

3d8f1b2d22be79aab3d246fa5bc9c24b911b0bd2

llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp

BuildMI(MBB, MBB.end(), DL, TII->get(MovTermOpc), SaveExecReg)
     .addReg(ExecReg);
 
   // Restore the EXEC mask after the loop.
   B.setMBB(*RestoreExecBB);
   B.buildInstr(MovTermOpc)
     .addDef(ExecReg)
     .addReg(SaveExecReg);
 
-  // Restore the insert point before the original instruction.
-  B.setInsertPt(MBB, MBB.end());
+  // Set the insert point after the original instruction, so any new
+  // instructions will be in the remainder.
+  B.setInsertPt(*RemainderBB, RemainderBB->begin());
 
   return true;
 }
 
 // Return any unique registers used by \p MI at \p OpIndices that need to be
 // handled in a waterfall loop. Returns these registers in \p
 // SGPROperandRegs. Returns true if there are any operansd to handle and a
 // waterfall loop is necessary.