Index: llvm/test/Transforms/SimplifyCFG/preserve-llvm-loop-metadata.ll
===================================================================
--- llvm/test/Transforms/SimplifyCFG/preserve-llvm-loop-metadata.ll
+++ llvm/test/Transforms/SimplifyCFG/preserve-llvm-loop-metadata.ll
@@ -48,7 +48,69 @@
   ret void
 }
 
+; The test case is constructed based on the following C++ code,
+; as a simplified test case to show why `llvm.loop.unroll.enable`
+; could be dropped.
+;
+; While the C++ code itself might have the inner-loop unrolled (e.g., with -O3),
+; the loss of inner-loop unroll metadata is a bug.
+; Under some optimization pipelines (e.g., FullLoopUnroll pass is skipped in ThinLTO prelink stage),
+; and in real-world C++ code (e.g., with larger loop body), failing to
+; preserve loop unroll metadata could cause missed loop unroll.
+;
+; constexpr int kUnroll = 5;
+; int sum(int a, int b, int step, const int remainder, int* input) {
+;    int i = a, j = b;
+;    int sum = 0;
+;    while(j - i > remainder) {
+;        i += step;
+;        #pragma unroll
+;        for (int k = 0; k < kUnroll; k++) {
+;           asm volatile ("add %w0, %w1\n" : "=r"(sum) : "r"(input[k + i]):"cc");
+;        }
+;    }
+;    return sum;
+; }
+define i32 @test2(i32 %a, i32 %b, i32 %step, i32 %remainder, i32* %input) {
+entry:
+  br label %while.cond
+
+while.cond.loopexit:                              ; preds = %for.body
+  br label %while.cond, !llvm.loop !2
+
+while.cond:                                       ; preds = %while.cond.loopexit, %entry
+  %i.0 = phi i32 [ %a, %entry ], [ %add, %while.cond.loopexit ]
+  %sum.0 = phi i32 [ 0, %entry ], [ %1, %while.cond.loopexit ]
+  %sub = sub nsw i32 %b, %i.0
+  %cmp = icmp sgt i32 %sub, %remainder
+  br i1 %cmp, label %while.body, label %while.end
+
+while.body:                                       ; preds = %while.cond
+  %add = add nsw i32 %i.0, %step
+  br label %for.body
+
+for.body:                                         ; preds = %while.body, %for.body
+  %k.07 = phi i32 [ 0, %while.body ], [ %inc, %for.body ]
+  %add2 = add nsw i32 %k.07, %add
+  %idxprom = sext i32 %add2 to i64
+  %arrayidx = getelementptr inbounds i32, i32* %input, i64 %idxprom
+  %0 = load i32, i32* %arrayidx, align 4
+  %1 = tail call i32 asm sideeffect "add ${0:w}, ${1:w}\0A", "=r,r,~{cc}"(i32 %0)
+  %inc = add nuw nsw i32 %k.07, 1
+  %cmp1 = icmp ult i32 %inc, 5
+  br i1 %cmp1, label %for.body, label %while.cond.loopexit, !llvm.loop !4
+
+while.end:                                        ; preds = %while.cond
+  %sum.0.lcssa = phi i32 [ %sum.0, %while.cond ]
+  ret i32 %sum.0.lcssa
+}
+
 !0 = distinct !{!0, !1}
 !1 = !{!"llvm.loop.distribute.enable", i1 true}
+!2 = distinct !{!2, !3}
+!3 = !{!"llvm.loop.mustprogress"}
+!4 = distinct !{!4, !3, !5}
+!5 = !{!"llvm.loop.unroll.enable"}
 ; CHECK: !0 = distinct !{!0, !1}
 ; CHECK: !1 = !{!"llvm.loop.distribute.enable", i1 true}
+; CHECK-NOT: !{!"llvm.loop.unroll.enable"}