[SelectionDAGBuilder] Look for appropriate INLINEASM_BR instruction to verify (#152591)

Partially fix #149023.
The original code `MRI.def_begin(Reg)->getParent()` may return the
incorrect MI, as the physical register `Reg` may have multiple
definitions.
This patch selects the correct MI to verify by comparing the MBB of each
definition.

New testcase hangs with -O1/2/3 enabled. The BranchFolding may be to
blame.

Author: XChy

llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

@@ -12744,17 +12744,22 @@ static Register FollowCopyChain(MachineRegisterInfo &MRI, Register Reg) {
   assert(MI->getOpcode() == TargetOpcode::COPY &&
          "start of copy chain MUST be COPY");
   Reg = MI->getOperand(1).getReg();
+
+  // If the copied register in the first copy must be virtual.
+  assert(Reg.isVirtual() && "expected COPY of virtual register");
   MI = MRI.def_begin(Reg)->getParent();
+
   // There may be an optional second copy.
   if (MI->getOpcode() == TargetOpcode::COPY) {
     assert(Reg.isVirtual() && "expected COPY of virtual register");
     Reg = MI->getOperand(1).getReg();
     assert(Reg.isPhysical() && "expected COPY of physical register");
-    MI = MRI.def_begin(Reg)->getParent();
+  } else {
+    // The start of the chain must be an INLINEASM_BR.
+    assert(MI->getOpcode() == TargetOpcode::INLINEASM_BR &&
+           "end of copy chain MUST be INLINEASM_BR");
   }
-  // The start of the chain must be an INLINEASM_BR.
-  assert(MI->getOpcode() == TargetOpcode::INLINEASM_BR &&
-         "end of copy chain MUST be INLINEASM_BR");
+
   return Reg;
 }
 

llvm/test/CodeGen/X86/callbr-asm-loop.ll

@@ -0,0 +1,47 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+
+; RUN: llc -O0 -mtriple=i686-- < %s | FileCheck %s
+
+; Test that causes multiple defs of %eax.
+; FIXME: The testcase hangs with -O1/2/3 enabled.
+define i32 @loop1() nounwind {
+; CHECK-LABEL: loop1:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushl %esi
+; CHECK-NEXT:    jmp .LBB0_1
+; CHECK-NEXT:  .LBB0_1: # %tailrecurse
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movl $1, %edx
+; CHECK-NEXT:    #APP
+; CHECK-NEXT:    #NO_APP
+; CHECK-NEXT:    movl %eax, %ecx
+; CHECK-NEXT:    movl %edx, %esi
+; CHECK-NEXT:    jmp .LBB0_3
+; CHECK-NEXT:  .LBB0_2: # Inline asm indirect target
+; CHECK-NEXT:    # %tailrecurse.tailrecurse.backedge_crit_edge
+; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:    # Label of block must be emitted
+; CHECK-NEXT:  .LBB0_3: # %tailrecurse.backedge
+; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:    jmp .LBB0_1
+; CHECK-NEXT:  .LBB0_4: # Inline asm indirect target
+; CHECK-NEXT:    # %lab2.split
+; CHECK-NEXT:    # Label of block must be emitted
+; CHECK-NEXT:    movl %edx, %eax
+; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:    retl
+entry:
+  br label %tailrecurse
+
+tailrecurse:
+  %0 = callbr { i32, i32 } asm "", "={ax},={dx},0,1,!i,!i"(i32 0, i32 1) #1
+          to label %tailrecurse.backedge [label %tailrecurse.backedge, label %lab2.split]
+
+tailrecurse.backedge:
+  br label %tailrecurse
+
+lab2.split:
+  %asmresult5 = extractvalue { i32, i32 } %0, 1
+  ret i32 %asmresult5
+}