Add wasm unreachable peephole optimisation

Author: majaha

lld/test/wasm/init-fini.ll

@@ -77,7 +77,7 @@ entry:
 ; CHECK-NEXT:         Body:            10031004100A100F1012100F10141003100C100F10161001100E0B
 ; CHECK:            - Index:           22
 ; CHECK-NEXT:         Locals:
-; CHECK-NEXT:         Body:            02404186808080004100418088808000108780808000450D0000000B0B
+; CHECK-NEXT:         Body:            02404186808080004100418088808000108780808000450D00000B0B
 ; CHECK-NEXT:   - Type:            CUSTOM
 ; CHECK-NEXT:     Name:            name
 ; CHECK-NEXT:     FunctionNames:

llvm/lib/Target/WebAssembly/WebAssemblyDebugFixup.cpp

@@ -122,9 +122,22 @@ bool WebAssemblyDebugFixup::runOnMachineFunction(MachineFunction &MF) {
           // it will be culled later.
         }
       } else {
+
+        // WebAssembly Peephole optimisation can remove instructions around wasm
+        // unreachable. This is valid for wasm, as unreachable is operand stack
+        // polymorphic. But this is not modeled in llvm at the moment, and so
+        // the stack may not seem to pop all that it pushes. Clear the stack so
+        // we don't violate the assert(Stack.empty()) later on.
+        if (MI.getOpcode() == WebAssembly::UNREACHABLE) {
+          Stack.clear();
+          break;
+        }
+
         // Track stack depth.
         for (MachineOperand &MO : reverse(MI.explicit_uses())) {
           if (MO.isReg() && MFI.isVRegStackified(MO.getReg())) {
+            assert(Stack.size() != 0 &&
+                   "WebAssemblyDebugFixup: Pop: Operand stack empty!");
             auto Prev = Stack.back();
             Stack.pop_back();
             assert(Prev.Reg == MO.getReg() &&

llvm/lib/Target/WebAssembly/WebAssemblyPeephole.cpp

@@ -20,6 +20,7 @@
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include <iterator>
 using namespace llvm;
 
 #define DEBUG_TYPE "wasm-peephole"
@@ -109,6 +110,53 @@ static bool maybeRewriteToFallthrough(MachineInstr &MI, MachineBasicBlock &MBB,
   return true;
 }
 
+static bool eraseDeadCodeAroundUnreachable(MachineInstr &UnreachbleMI,
+                                           MachineBasicBlock &MBB) {
+  SmallVector<MachineInstr *, 16> ToDelete;
+
+  // Because wasm unreachable is stack polymorphic and unconditionally ends
+  // control, all instructions after it can be removed until the end of this
+  // block. We remove the common case of double unreachable.
+  auto ForwardsIterator = UnreachbleMI.getIterator();
+  for (ForwardsIterator++; !ForwardsIterator.isEnd(); ForwardsIterator++) {
+    MachineInstr &MI = *ForwardsIterator;
+    if (MI.getOpcode() == WebAssembly::UNREACHABLE) {
+      ToDelete.push_back(&MI);
+    } else {
+      break;
+    }
+  }
+
+  // For the same reasons as above, previous instructions that only affect
+  // local function state can be removed (e.g. local.set, drop, various reads).
+  // We remove the common case of "drop unreachable".
+  auto BackwardsIterator = UnreachbleMI.getReverseIterator();
+  for (BackwardsIterator++; !BackwardsIterator.isEnd(); BackwardsIterator++) {
+    MachineInstr &MI = *BackwardsIterator;
+    switch (MI.getOpcode()) {
+    case WebAssembly::DROP_I32:
+    case WebAssembly::DROP_I64:
+    case WebAssembly::DROP_F32:
+    case WebAssembly::DROP_F64:
+    case WebAssembly::DROP_EXTERNREF:
+    case WebAssembly::DROP_FUNCREF:
+    case WebAssembly::DROP_V128:
+      ToDelete.push_back(&MI);
+      continue;
+    default:
+      goto exit_loop;
+    }
+  }
+exit_loop:;
+
+  bool Changed = false;
+  for (MachineInstr *MI : ToDelete) {
+    MI->eraseFromParent();
+    Changed = true;
+  }
+  return Changed;
+}
+
 bool WebAssemblyPeephole::runOnMachineFunction(MachineFunction &MF) {
   LLVM_DEBUG({
     dbgs() << "********** Peephole **********\n"
@@ -159,6 +207,9 @@ bool WebAssemblyPeephole::runOnMachineFunction(MachineFunction &MF) {
       case WebAssembly::RETURN:
         Changed |= maybeRewriteToFallthrough(MI, MBB, MF, MFI, MRI, TII);
         break;
+      case WebAssembly::UNREACHABLE:
+        Changed |= eraseDeadCodeAroundUnreachable(MI, MBB);
+        break;
       }
 
   return Changed;

llvm/test/CodeGen/WebAssembly/unreachable.ll

@@ -41,7 +41,6 @@ define void @trap_unreach() {
 ; CHECK:         .functype trap_unreach () -> ()
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    unreachable
-; CHECK-NEXT:    unreachable
 ; CHECK-NEXT:    end_function
   call void @llvm.trap()
   unreachable
@@ -99,7 +98,6 @@ define i32 @i32_sig_match_unreach() {
 ; CHECK:         .functype i32_sig_match_unreach () -> (i32)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    call ext_func_i32
-; CHECK-NEXT:    drop
 ; CHECK-NEXT:    unreachable
 ; CHECK-NEXT:    end_function
   call i32 @ext_func_i32()

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