[MLIR][CF] Avoid collapsing blocks which participate in cycles (#159743)

Previously, collapseBranch did not return failure for successor blocks
which were part of a cycle. mlir-opt --canonicalize would run indefinitely
for any N-block cycle which is kicked off with an unconditional jump. The
simplifyPassThroughBr transform would continue alternating which block was
targeted in ^bb0, resulting in an infinite loop.

collapseBranch will not result in any useful transformation on blocks which
participate in cycles, since the block is aliased by a different block. To
avoid this, we can check for cycles in collapseBranch and abort when one is
detected. Simplification of the cycle is left for other transforms.

Author: benwu25

mlir/lib/Dialect/ControlFlow/IR/ControlFlowOps.cpp

@@ -122,6 +122,16 @@ static LogicalResult collapseBranch(Block *&successor,
   Block *successorDest = successorBranch.getDest();
   if (successorDest == successor)
     return failure();
+  // Don't try to collapse branches which participate in a cycle.
+  BranchOp nextBranch = dyn_cast<BranchOp>(successorDest->getTerminator());
+  while (nextBranch) {
+    Block *nextBranchDest = nextBranch.getDest();
+    if (!nextBranchDest)
+      break;
+    else if (nextBranchDest == successor)
+      return failure();
+    nextBranch = dyn_cast<BranchOp>(nextBranchDest->getTerminator());
+  }
 
   // Update the operands to the successor. If the branch parent has no
   // arguments, we can use the branch operands directly.

mlir/test/Transforms/control-flow-cycles.mlir

@@ -0,0 +1,81 @@
+// RUN: mlir-opt --canonicalize %s | FileCheck %s
+
+// Test that control-flow cycles are not simplified infinitely.
+
+// CHECK-LABEL: @cycle_2_blocks
+// CHECK-NEXT: cf.br ^bb1
+// CHECK-NEXT: ^bb1:
+// CHECK-NEXT: cf.br ^bb1
+func.func @cycle_2_blocks() {
+  cf.br ^bb1
+  ^bb1:
+    cf.br ^bb2
+  ^bb2:
+    cf.br ^bb1
+}
+
+// CHECK-LABEL: @no_cycle_2_blocks
+// CHECK-NEXT: %c1_i32 = arith.constant 1 : i32
+// CHECK-NEXT: return %c1_i32 : i32
+func.func @no_cycle_2_blocks() -> i32 {
+  cf.br ^bb1
+  ^bb1:
+    cf.br ^bb2
+  ^bb2:
+    cf.br ^bb3
+  ^bb3:
+    %ret = arith.constant 1 : i32
+    return %ret : i32
+}
+
+// CHECK-LABEL: @cycle_4_blocks
+// CHECK-NEXT: cf.br ^bb1
+// CHECK-NEXT: ^bb1:
+// CHECK-NEXT: cf.br ^bb1
+func.func @cycle_4_blocks() {
+  cf.br ^bb1
+  ^bb1:
+    cf.br ^bb2
+  ^bb2:
+    cf.br ^bb3
+  ^bb3:
+    cf.br ^bb4
+  ^bb4:
+    cf.br ^bb1
+}
+
+// CHECK-LABEL: @no_cycle_4_blocks
+// CHECK-NEXT: %c1_i32 = arith.constant 1 : i32
+// CHECK-NEXT: return %c1_i32 : i32
+func.func @no_cycle_4_blocks() -> i32 {
+  cf.br ^bb1
+  ^bb1:
+    cf.br ^bb2
+  ^bb2:
+    cf.br ^bb3
+  ^bb3:
+    cf.br ^bb4
+  ^bb4:
+    cf.br ^bb5
+  ^bb5:
+    %ret = arith.constant 1 : i32
+    return %ret : i32
+}
+
+// CHECK-LABEL: @delayed_3_cycle
+// CHECK-NEXT: cf.br ^bb1
+// CHECK-NEXT: ^bb1:
+// CHECK-NEXT: cf.br ^bb1
+func.func @delayed_3_cycle() {
+  cf.br ^bb1
+  ^bb1:
+    cf.br ^bb2
+  ^bb2:
+    cf.br ^bb3
+  ^bb3:
+    cf.br ^bb4
+  ^bb4:
+    cf.br ^bb5
+  ^bb5:
+    cf.br ^bb3
+}