[WebAssembly] remove instruction after builtin trap (#90207)

`llvm.trap` will be convert as `unreachable` which is terminator.
Instruction after terminator will cause validation failed.
This PR introduces a pass to clean instruction after terminator.
Fixes: #68770.

Author: HerrCai0907

llvm/lib/Target/WebAssembly/CMakeLists.txt

@@ -19,6 +19,7 @@ add_llvm_target(WebAssemblyCodeGen
   WebAssemblyArgumentMove.cpp
   WebAssemblyAsmPrinter.cpp
   WebAssemblyCFGStackify.cpp
+  WebAssemblyCleanCodeAfterTrap.cpp
   WebAssemblyCFGSort.cpp
   WebAssemblyDebugFixup.cpp
   WebAssemblyDebugValueManager.cpp

llvm/lib/Target/WebAssembly/WebAssembly.h

@@ -37,6 +37,7 @@ FunctionPass *createWebAssemblyISelDag(WebAssemblyTargetMachine &TM,
                                        CodeGenOptLevel OptLevel);
 FunctionPass *createWebAssemblyArgumentMove();
 FunctionPass *createWebAssemblySetP2AlignOperands();
+FunctionPass *createWebAssemblyCleanCodeAfterTrap();
 
 // Late passes.
 FunctionPass *createWebAssemblyReplacePhysRegs();
@@ -63,6 +64,7 @@ void initializeOptimizeReturnedPass(PassRegistry &);
 void initializeWebAssemblyRefTypeMem2LocalPass(PassRegistry &);
 void initializeWebAssemblyAddMissingPrototypesPass(PassRegistry &);
 void initializeWebAssemblyArgumentMovePass(PassRegistry &);
+void initializeWebAssemblyCleanCodeAfterTrapPass(PassRegistry &);
 void initializeWebAssemblyCFGSortPass(PassRegistry &);
 void initializeWebAssemblyCFGStackifyPass(PassRegistry &);
 void initializeWebAssemblyDAGToDAGISelPass(PassRegistry &);

llvm/lib/Target/WebAssembly/WebAssemblyCleanCodeAfterTrap.cpp

@@ -0,0 +1,80 @@
+//===-- WebAssemblyCleanCodeAfterTrap.cpp - Clean Code After Trap ---------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// This file remove instruction after trap.
+/// ``llvm.trap`` will be convert as ``unreachable`` which is terminator.
+/// Instruction after terminator will cause validation failed.
+///
+//===----------------------------------------------------------------------===//
+
+#include "WebAssembly.h"
+#include "WebAssemblyUtilities.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/MC/MCInstrDesc.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/raw_ostream.h"
+using namespace llvm;
+
+#define DEBUG_TYPE "wasm-clean-code-after-trap"
+
+namespace {
+class WebAssemblyCleanCodeAfterTrap final : public MachineFunctionPass {
+public:
+  static char ID; // Pass identification, replacement for typeid
+  WebAssemblyCleanCodeAfterTrap() : MachineFunctionPass(ID) {}
+
+  StringRef getPassName() const override {
+    return "WebAssembly Clean Code After Trap";
+  }
+
+  bool runOnMachineFunction(MachineFunction &MF) override;
+};
+} // end anonymous namespace
+
+char WebAssemblyCleanCodeAfterTrap::ID = 0;
+INITIALIZE_PASS(WebAssemblyCleanCodeAfterTrap, DEBUG_TYPE,
+                "WebAssembly Clean Code After Trap", false, false)
+
+FunctionPass *llvm::createWebAssemblyCleanCodeAfterTrap() {
+  return new WebAssemblyCleanCodeAfterTrap();
+}
+
+bool WebAssemblyCleanCodeAfterTrap::runOnMachineFunction(MachineFunction &MF) {
+  LLVM_DEBUG({
+    dbgs() << "********** CleanCodeAfterTrap **********\n"
+           << "********** Function: " << MF.getName() << '\n';
+  });
+
+  bool Changed = false;
+
+  for (MachineBasicBlock &BB : MF) {
+    bool HasTerminator = false;
+    llvm::SmallVector<MachineInstr *> RemoveMI{};
+    for (MachineInstr &MI : BB) {
+      if (HasTerminator)
+        RemoveMI.push_back(&MI);
+      if (MI.hasProperty(MCID::Trap) && MI.isTerminator())
+        HasTerminator = true;
+    }
+    if (!RemoveMI.empty()) {
+      Changed = true;
+      LLVM_DEBUG({
+        for (MachineInstr *MI : RemoveMI) {
+          llvm::dbgs() << "* remove ";
+          MI->print(llvm::dbgs());
+        }
+      });
+      for (MachineInstr *MI : RemoveMI)
+        MI->eraseFromParent();
+    }
+  }
+  return Changed;
+}

llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp

@@ -512,6 +512,10 @@ bool WebAssemblyPassConfig::addInstSelector() {
   // Eliminate range checks and add default targets to br_table instructions.
   addPass(createWebAssemblyFixBrTableDefaults());
 
+  // unreachable is terminator, non-terminator instruction after it is not
+  // allowed.
+  addPass(createWebAssemblyCleanCodeAfterTrap());
+
   return false;
 }
 

llvm/test/CodeGen/WebAssembly/unreachable.ll

@@ -30,7 +30,6 @@ define void @trap_ret_void() {
 ; CHECK:         .functype trap_ret_void () -> ()
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    unreachable
-; CHECK-NEXT:    # fallthrough-return
 ; CHECK-NEXT:    end_function
   call void @llvm.trap()
   ret void
@@ -54,7 +53,6 @@ define void @trap_unreacheable() {
 ; CHECK:         .functype trap_unreacheable () -> ()
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    unreachable
-; CHECK-NEXT:    unreachable
 ; CHECK-NEXT:    end_function
   call void @llvm.trap()
   unreachable
@@ -94,3 +92,12 @@ define i32 @missing_ret_noreturn_unreachable() {
   call void @ext_never_return()
   unreachable
 }
+
+define i32 @no_crash_for_other_instruction_after_trap(ptr %p, i32 %b) {
+; CHECK-LABEL: no_crash_for_other_instruction_after_trap:
+; CHECK:      unreachable
+; CHECK-NEXT: end_function
+  %a = load i32, ptr %p
+  call void @llvm.trap()
+  ret i32 %a
+}

llvm/test/MC/WebAssembly/global-ctor-dtor.ll

@@ -80,29 +80,29 @@ declare void @func3()
 ; CHECK-NEXT:         Offset:          0x1D
 ; CHECK-NEXT:       - Type:            R_WASM_FUNCTION_INDEX_LEB
 ; CHECK-NEXT:         Index:           6
-; CHECK-NEXT:         Offset:          0x2C
+; CHECK-NEXT:         Offset:          0x2B
 ; CHECK-NEXT:       - Type:            R_WASM_TABLE_INDEX_SLEB
 ; CHECK-NEXT:         Index:           5
-; CHECK-NEXT:         Offset:          0x37
+; CHECK-NEXT:         Offset:          0x36
 ; CHECK-NEXT:       - Type:            R_WASM_MEMORY_ADDR_SLEB
 ; CHECK-NEXT:         Index:           3
-; CHECK-NEXT:         Offset:          0x3F
+; CHECK-NEXT:         Offset:          0x3E
 ; CHECK-NEXT:       - Type:            R_WASM_FUNCTION_INDEX_LEB
 ; CHECK-NEXT:         Index:           4
-; CHECK-NEXT:         Offset:          0x45
+; CHECK-NEXT:         Offset:          0x44
 ; CHECK-NEXT:     Functions:
 ; CHECK-NEXT:       - Index:           5
 ; CHECK-NEXT:         Locals:
 ; CHECK-NEXT:         Body:            1080808080000B
 ; CHECK-NEXT:       - Index:           6
 ; CHECK-NEXT:         Locals:
-; CHECK-NEXT:         Body:            02404181808080004100418080808000108180808000450D0000000B0B
+; CHECK-NEXT:         Body:            02404181808080004100418080808000108180808000450D00000B0B
 ; CHECK-NEXT:       - Index:           7
 ; CHECK-NEXT:         Locals:
 ; CHECK-NEXT:         Body:            1082808080000B
 ; CHECK-NEXT:       - Index:           8
 ; CHECK-NEXT:         Locals:
-; CHECK-NEXT:         Body:            02404182808080004100418080808000108180808000450D0000000B0B
+; CHECK-NEXT:         Body:            02404182808080004100418080808000108180808000450D00000B0B
 ; CHECK-NEXT:   - Type:            DATA
 ; CHECK-NEXT:     Segments:
 ; CHECK-NEXT:       - SectionOffset:   6