diff --git a/llvm/lib/CodeGen/TailDuplicator.cpp b/llvm/lib/CodeGen/TailDuplicator.cpp
--- a/llvm/lib/CodeGen/TailDuplicator.cpp
+++ b/llvm/lib/CodeGen/TailDuplicator.cpp
@@ -550,6 +550,14 @@
   }
 }
 
+static bool hasMultipSuccsAsLatch(const MachineBasicBlock *A) {
+  const SmallPtrSet<const MachineBasicBlock *, 8> Preds(A->pred_begin(),
+                                                        A->pred_end());
+  return llvm::count_if(A->successors(), [&](const MachineBasicBlock *SuccBB) {
+           return Preds.count(SuccBB);
+         }) > 2;
+}
+
 /// Determine if it is profitable to duplicate this block.
 bool TailDuplicator::shouldTailDuplicate(bool IsSimple,
                                          MachineBasicBlock &TailBB) {
@@ -563,6 +571,10 @@
   if (TailBB.isSuccessor(&TailBB))
     return false;
 
+  // Don't tail-duplicate loop header with multiple successors as its latches.
+  if (hasMultipSuccsAsLatch(&TailBB))
+    return false;
+
   // Set the limit on the cost to duplicate. When optimizing for size,
   // duplicate only one, because one branch instruction can be eliminated to
   // compensate for the duplication.
diff --git a/llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll b/llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll
--- a/llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll
+++ b/llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll
@@ -6,71 +6,43 @@
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    .cfi_offset %rbx, -16
-; CHECK-NEXT:    movq %rdi, %rax
+; CHECK-NEXT:    movq %rdi, %rsi
 ; CHECK-NEXT:    movl $6, %ebx
-; CHECK-NEXT:    movl %ebx, %ecx
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:  .LBB0_1: # %for.cond.cleanup
-; CHECK-NEXT:    movl $530, %edi # imm = 0x212
-; CHECK-NEXT:    movq %rax, %rsi
-; CHECK-NEXT:    popq %rbx
-; CHECK-NEXT:    .cfi_def_cfa_offset 8
-; CHECK-NEXT:    jmp ccc@PLT # TAILCALL
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    movl %ebx, %eax
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rax,8)
 ; CHECK-NEXT:  .LBB0_2: # %sw.bb1
-; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    movl $531, %edi # imm = 0x213
-; CHECK-NEXT:    movq %rax, %rsi
+; CHECK-NEXT:  .LBB0_3: # %for.body
 ; CHECK-NEXT:    callq ccc@PLT
+; CHECK-NEXT:  .LBB0_4: # %for.body
+; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    movl %ebx, %ecx
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
-; CHECK-NEXT:  .LBB0_3: # %sw.bb3
-; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    movl %ebx, %eax
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rax,8)
+; CHECK-NEXT:  .LBB0_5: # %sw.bb3
 ; CHECK-NEXT:    movl $532, %edi # imm = 0x214
-; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    callq bbb@PLT
-; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    movl %ebx, %ecx
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
-; CHECK-NEXT:  .LBB0_4: # %sw.bb5
-; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    jmp .LBB0_4
+; CHECK-NEXT:  .LBB0_7: # %sw.bb5
 ; CHECK-NEXT:    movl $533, %edi # imm = 0x215
-; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    callq bbb@PLT
-; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    movl %ebx, %ecx
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
-; CHECK-NEXT:  .LBB0_5: # %sw.bb7
-; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    jmp .LBB0_4
+; CHECK-NEXT:  .LBB0_8: # %sw.bb7
 ; CHECK-NEXT:    movl $535, %edi # imm = 0x217
-; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    callq bbb@PLT
-; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    movl %ebx, %ecx
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
-; CHECK-NEXT:  .LBB0_6: # %sw.bb9
-; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    jmp .LBB0_4
+; CHECK-NEXT:  .LBB0_9: # %sw.bb9
 ; CHECK-NEXT:    movl $536, %edi # imm = 0x218
-; CHECK-NEXT:    movq %rax, %rsi
-; CHECK-NEXT:    callq ccc@PLT
-; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    movl %ebx, %ecx
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
-; CHECK-NEXT:  .LBB0_7: # %sw.bb11
-; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    jmp .LBB0_3
+; CHECK-NEXT:  .LBB0_10: # %sw.bb11
 ; CHECK-NEXT:    movl $658, %edi # imm = 0x292
-; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    callq bbb@PLT
-; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    movl %ebx, %ecx
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
+; CHECK-NEXT:    jmp .LBB0_4
+; CHECK-NEXT:  .LBB0_11: # %for.cond.cleanup
+; CHECK-NEXT:    movl $530, %edi # imm = 0x212
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    jmp ccc@PLT # TAILCALL
 entry:
   br label %for.body