[WebAssembly] Add asm.js-style setjmp/longjmp handling for wasm (reland r280302)

[aheejin]

Summary

This patch adds asm.js-style setjmp/longjmp handling support for WebAssembly. It also uses JavaScript's try and catch mechanism.

[aheejin]

The reason for the test failure in the previous commit was this part:
In lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp

if (!EnableEmException) {
  addPass(createLowerInvokePass());
  addPass(createCFGSimplificationPass());
}

Actually, if EH is not supported, LowerInvoke pass runs anyway at later point because TargetPassConfig::addPassesToHandleExceptions adds createLowerInvokePass() to the list of passes. But this runs after all our custom IR passes run, and SjLj handling expects all the invoke instructions to be lowered before processing. So that's the reason I added these two passes when EH is not enabled.(LowerInvoke for lowering invokes to calls, and CFGSimplify for removing orphan landingpad blocks.)

But the problem is even if neither EH nor SjLj is enabled, this runs CFGSimplify all the time, causing several WebAssembly tests to break. I changed this part as follows:

if (!EnableEmException && EnableEmSjLj) {
  addPass(createLowerInvokePass());
  addPass(createCFGSimplificationPass());
}

This way, CFGSimplify only runs when SjLj is enabled.
Confirmed that all tests run.

[dschuff]

Oh, I had forgotten there's a dedicated target hook for inserting EH handling passes. So probably what we should do is override TargetPassConfig::addPassesToHandleExceptions() and put this pass there instead of in addIRPasses(). Also the default EH-handling pass seems to run only createUnreachableBlockEliminationPass() rather than full CFG simplification. Maybe we should do that instead too? Then it wouldn't interfere with the other tests, and be more consistent with other targets.

[aheejin]

Then should I also add SjLj to that addPassesToHandleException? Currently SjLj does not expect any invokes to exist in the module.
I guess we have to, because anyway EH and SjLj are in the same pass.

[dschuff]

Yeah, I think it would be OK to keep them in the same pass, and just move it. We'll want to put some comments to make it clear that it also handles setjmp/longjmp using JS exceptions. That part is somewhat unique.

So then I guess the logic in addPassesToHandleExceptions would be something like

if (!EnableEmException) {
  addPass(createLowerInvokePass());
  addPass(createUnreachableBlockEliminationPass());
}

// Handle exceptions and setjmp/longjmp if enabled.
if (EnableEmException || EnableEmSjLj)
  addPass(createWebAssemblyLowerEmscriptenEHSjLj(EnableEmException,
                                                 EnableEmSjLj))

[aheejin]

In that case, because addPassesToHandleExceptions always runs, createUnreachableBlockEliminationPass() will always run even if neither EH nor SjLj is enabled. And I think this may affect other tests in case there are unreachable blocks in other tests. Shouldn't it be

if (!EnableEmException && EnableEmSjLj) {
  addPass(createLowerInvokePass());
  addPass(createCFGSimplificationPass());
}

As I did in this patch?

[aheejin]

Oh, TargetPassConfig::addPassesToHandleExceptions() is not virtual, so it can't be overriden anyway.

[dschuff]

Before this patch, lowerInvoke and UnreachableBlockElimination are always run anyway as the the standard EH passes. So having UBE run unconditionally shouldn't break anything existing.

Hm, that's unfortunate about addPassesToHandleExceptions not being virtual. Maybe we could change that. For now maybe we can go with what you had in the original CL, except with UnreachableBlockElimination instead of CFGSimplify (and add a comment that we need to run it before setjmp/longjmp handing). Then it would run again in addPassesToHandleExceptions which would be redundant when this pass is turned on, but not harmful.

[aheejin]

Address comments

[dschuff]

(tip: you don't have to manually close the code reviews. They will automatically close when a commit lands that references the review.)

[aheejin]

I didn't manually close this one. This one was automatically closed when I committed the revision.

lib/Target/WebAssembly/WebAssemblyLowerEmscriptenEHSjLj.cpp

 //=== WebAssemblyLowerEmscriptenEHSjLj.cpp - Lower exceptions for Emscripten =//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 ///
 /// \file
-/// \brief This file lowers exception-related instructions in order to use
-/// Emscripten's JavaScript try and catch mechanism to handle exceptions.
+/// \brief This file lowers exception-related instructions and setjmp/longjmp
+/// function calls in order to use Emscripten's JavaScript try and catch
+/// mechanism.
 ///
-/// To handle exceptions, this scheme relies on JavaScript's try and catch
-/// syntax and relevant exception-related libraries implemented in JavaScript
-/// glue code that will be produced by Emscripten. This is similar to the
-/// current Emscripten asm.js exception handling in fastcomp.
-/// For fastcomp's EH scheme, see these files in fastcomp LLVM branch:
+/// To handle exceptions and setjmp/longjmps, this scheme relies on JavaScript's
+/// try and catch syntax and relevant exception-related libraries implemented
+/// in JavaScript glue code that will be produced by Emscripten. This is similar
+/// to the current Emscripten asm.js exception handling in fastcomp. For
+/// fastcomp's EH / SjLj scheme, see these files in fastcomp LLVM branch:
 /// (Location: https://github.com/kripken/emscripten-fastcomp)
 /// lib/Target/JSBackend/NaCl/LowerEmExceptionsPass.cpp
+/// lib/Target/JSBackend/NaCl/LowerEmSetjmp.cpp
 /// lib/Target/JSBackend/JSBackend.cpp
 /// lib/Target/JSBackend/CallHandlers.h
 ///
-/// This pass does following things:
+/// * Exception handling
+/// This pass lowers invokes and landingpads into library functions in JS glue
+/// code. Invokes are lowered into function wrappers called invoke wrappers that
+/// exist in JS side, which wraps the original function call with JS try-catch.
+/// If an exception occurred, cxa_throw() function in JS side sets some
+/// variables (see below) so we can check whether an exception occurred from
+/// wasm code and handle it appropriately.
 ///
-/// 1) Create three global variables: __THREW__, __threwValue, and tempRet0.
-///    tempRet0 will be set within __cxa_find_matching_catch() function in
+/// * Setjmp-longjmp handling
+/// This pass lowers setjmp to a reasonably-performant approach for emscripten.
+/// The idea is that each block with a setjmp is broken up into two parts: the
+/// part containing setjmp and the part right after the setjmp. The latter part
+/// is either reached from the setjmp, or later from a longjmp. To handle the
+/// longjmp, all calls that might longjmp are also called using invoke wrappers
+/// and thus JS / try-catch. JS longjmp() function also sets some variables so
+/// we can check / whether a longjmp occurred from wasm code. Each block with a
+/// function call that might longjmp is also split up after the longjmp call.
+/// After the longjmp call, we check whether a longjmp occurred, and if it did,
+/// which setjmp it corresponds to, and jump to the right post-setjmp block.
+/// We assume setjmp-longjmp handling always run after EH handling, which means
+/// we don't expect any exception-related instructions when SjLj runs.
+/// FIXME Currently this scheme does not support indirect call of setjmp,
+/// because of the limitation of the scheme itself. fastcomp does not support it
+/// either.
+///
+/// In detail, this pass does following things:
+///
+/// 1) Create three global variables: __THREW__, __threwValue, and __tempRet0.
+///    __tempRet0 will be set within __cxa_find_matching_catch() function in
 ///    JS library, and __THREW__ and __threwValue will be set in invoke wrappers
-///    in JS glue code. For what invoke wrappers are, refer to 3).
+///    in JS glue code. For what invoke wrappers are, refer to 3). These
+///    variables are used for both exceptions and setjmp/longjmps.
+///    __THREW__ indicates whether an exception or a longjmp occurred or not. 0
+///    means nothing occurred, 1 means an exception occurred, and other numbers
+///    mean a longjmp occurred. In the case of longjmp, threwValue variable
+///    indicates the corresponding setjmp buffer the longjmp corresponds to.
+///    In exception handling, __tempRet0 indicates the type of an exception
+///    caught, and in setjmp/longjmp, it means the second argument to longjmp
+///    function.
+///
+/// * Exception handling
 ///
 /// 2) Create setThrew and setTempRet0 functions.
 ///    The global variables created in 1) will exist in wasm address space,
 ///    but their values should be set in JS code, so we provide these functions
 ///    as interfaces to JS glue code. These functions are equivalent to the
 ///    following JS functions, which actually exist in asm.js version of JS
 ///    library.
 ///
 ///    function setThrew(threw, value) {
 ///      if (__THREW__ == 0) {
 ///        __THREW__ = threw;
 ///        __threwValue = value;
 ///      }
 ///    }
 ///
 ///    function setTempRet0(value) {
-///      tempRet0 = value;
+///      __tempRet0 = value;
 ///    }
 ///
 /// 3) Lower
 ///      invoke @func(arg1, arg2) to label %invoke.cont unwind label %lpad
 ///    into
 ///      __THREW__ = 0;
 ///      call @invoke_SIG(func, arg1, arg2)
 ///      %__THREW__.val = __THREW__;

 ///    If an exception is thrown, __THREW__ will be set to true in a wrapper,
 ///    so we can jump to the right BB based on this value.
 ///
 /// 4) Lower
 ///      %val = landingpad catch c1 catch c2 catch c3 ...
 ///      ... use %val ...
 ///    into
 ///      %fmc = call @__cxa_find_matching_catch_N(c1, c2, c3, ...)
-///      %val = {%fmc, tempRet0}
+///      %val = {%fmc, __tempRet0}
 ///      ... use %val ...
 ///    Here N is a number calculated based on the number of clauses.
-///    Global variable tempRet0 is set within __cxa_find_matching_catch() in
+///    Global variable __tempRet0 is set within __cxa_find_matching_catch() in
 ///    JS glue code.
 ///
 /// 5) Lower
 ///      resume {%a, %b}
 ///    into
 ///      call @__resumeException(%a)
 ///    where __resumeException() is a function in JS glue code.
 ///
 /// 6) Lower
 ///      call @llvm.eh.typeid.for(type) (intrinsic)
 ///    into
 ///      call @llvm_eh_typeid_for(type)
 ///    llvm_eh_typeid_for function will be generated in JS glue code.
 ///
+/// * Setjmp / Longjmp handling
+///
+/// 7) In the function entry that calls setjmp, initialize setjmpTable and
+///    sejmpTableSize as follows:
+///      setjmpTableSize = 4;
+///      setjmpTable = (int *) malloc(40);
+///      setjmpTable[0] = 0;
+///    setjmpTable and setjmpTableSize are used in saveSetjmp() function in JS
+///    code.
+///
+/// 8) Lower
+///      setjmp(buf)
+///    into
+///      setjmpTable = saveSetjmp(buf, label, setjmpTable, setjmpTableSize);
+///      setjmpTableSize = __tempRet0;
+///    For each dynamic setjmp call, setjmpTable stores its ID (a number which
+///    is incrementally assigned from 0) and its label (a unique number that
+///    represents each callsite of setjmp). When we need more entries in
+///    setjmpTable, it is reallocated in saveSetjmp() in JS code and it will
+///    return the new table address, and assign the new table size in
+///    __tempRet0. saveSetjmp also stores the setjmp's ID into the buffer buf.
+///    A BB with setjmp is split into two after setjmp call in order to make the
+///    post-setjmp BB the possible destination of longjmp BB.
+///
+/// 9) Lower
+///      longjmp(buf, value)
+///    into
+///      emscripten_longjmp_jmpbuf(buf, value)
+///    emscripten_longjmp_jmpbuf will be lowered to emscripten_longjmp later.
+///
+/// 10) Lower every call that might longjmp into
+///      __THREW__ = 0;
+///      call @invoke_SIG(func, arg1, arg2)
+///      %__THREW__.val = __THREW__;
+///      __THREW__ = 0;
+///      if (%__THREW__.val != 0 & threwValue != 0) {
+///        %label = testSetjmp(mem[%__THREW__.val], setjmpTable,
+///                            setjmpTableSize);
+///        if (%label == 0)
+///          emscripten_longjmp(%__THREW__.val, threwValue);
+///        __tempRet0 = threwValue;
+///      } else {
+///        %label = -1;
+///      }
+///      longjmp_result = __tempRet0;
+///      switch label {
+///        label 1: post-setjmp BB 1
+///        label 2: post-setjmp BB 2
+///        ...
+///        default: splited next BB
+///      }
+///     testSetjmp examines setjmpTable to see if there is a matching setjmp
+///     call. After calling an invoke wrapper, if a longjmp occurred, __THREW__
+///     will be the address of matching jmp_buf buffer and threwValue be the
+///     second argument to longjmp. mem[__THREW__.val] is a setjmp ID that is
+///     stored in saveSetjmp. testSetjmp returns a setjmp label, a unique ID to
+///     each setjmp callsite. Label 0 means this longjmp buffer does not
+///     correspond to one of the setjmp callsites in this function, so in this
+///     case we just chain the longjmp to the caller. (Here we call
+///     emscripten_longjmp, which is different from emscripten_longjmp_jmpbuf.
+///     emscripten_longjmp_jmpbuf takes jmp_buf as its first argument, while
+///     emscripten_longjmp takes an int. Both of them will eventually be lowered
+///     to emscripten_longjmp in s2wasm, but here we need two signatures - we
+///     can't translate an int value to a jmp_buf.)
+///     Label -1 means no longjmp occurred. Otherwise we jump to the right
+///     post-setjmp BB based on the label.
+///
 ///===----------------------------------------------------------------------===//
 
 #include "WebAssembly.h"
 #include "llvm/IR/CallSite.h"
+#include "llvm/IR/Dominators.h"
 #include "llvm/IR/IRBuilder.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Support/raw_ostream.h"
-#include <set>
+#include "llvm/Transforms/Utils/BasicBlockUtils.h"
+#include "llvm/Transforms/Utils/SSAUpdater.h"
 
 using namespace llvm;
 
 #define DEBUG_TYPE "wasm-lower-em-ehsjlj"
 
 static cl::list<std::string>
     EHWhitelist("emscripten-cxx-exceptions-whitelist",
                 cl::desc("The list of function names in which Emscripten-style "
                          "exception handling is enabled (see emscripten "
                          "EMSCRIPTEN_CATCHING_WHITELIST options)"),
                 cl::CommaSeparated);
 
 namespace {
 class WebAssemblyLowerEmscriptenEHSjLj final : public ModulePass {
   static const char *ThrewGVName;
   static const char *ThrewValueGVName;
   static const char *TempRet0GVName;
   static const char *ResumeFName;
   static const char *EHTypeIDFName;
   static const char *SetThrewFName;
   static const char *SetTempRet0FName;
+  static const char *EmLongjmpFName;
+  static const char *EmLongjmpJmpbufFName;
+  static const char *SaveSetjmpFName;
+  static const char *TestSetjmpFName;
   static const char *FindMatchingCatchPrefix;
   static const char *InvokePrefix;
 
-  bool DoEH;   // Enable exception handling
-  bool DoSjLj; // Enable setjmp/longjmp handling
+  bool EnableEH;   // Enable exception handling
+  bool EnableSjLj; // Enable setjmp/longjmp handling
 
   GlobalVariable *ThrewGV;
   GlobalVariable *ThrewValueGV;
   GlobalVariable *TempRet0GV;
   Function *ResumeF;
   Function *EHTypeIDF;
+  Function *EmLongjmpF;
+  Function *EmLongjmpJmpbufF;
+  Function *SaveSetjmpF;
+  Function *TestSetjmpF;
+
   // __cxa_find_matching_catch_N functions.
   // Indexed by the number of clauses in an original landingpad instruction.
   DenseMap<int, Function *> FindMatchingCatches;
   // Map of <function signature string, invoke_ wrappers>
   StringMap<Function *> InvokeWrappers;
   // Set of whitelisted function names for exception handling
   std::set<std::string> EHWhitelistSet;
 
   const char *getPassName() const override {
     return "WebAssembly Lower Emscripten Exceptions";
   }
 
   bool runEHOnFunction(Function &F);
   bool runSjLjOnFunction(Function &F);
-  // Returns __cxa_find_matching_catch_N function, where N = NumClauses + 2.
-  // This is because a landingpad instruction contains two more arguments,
-  // a personality function and a cleanup bit, and __cxa_find_matching_catch_N
-  // functions are named after the number of arguments in the original
-  // landingpad instruction.
   Function *getFindMatchingCatch(Module &M, unsigned NumClauses);
 
-  Function *getInvokeWrapper(Module &M, InvokeInst *II);
+  template <typename CallOrInvoke> Value *wrapInvoke(CallOrInvoke *CI);
+  void wrapTestSetjmp(BasicBlock *BB, Instruction *InsertPt, Value *Threw,
+                      Value *SetjmpTable, Value *SetjmpTableSize, Value *&Label,
+                      Value *&LongjmpResult, BasicBlock *&EndBB);
+  template <typename CallOrInvoke> Function *getInvokeWrapper(CallOrInvoke *CI);
+
   bool areAllExceptionsAllowed() const { return EHWhitelistSet.empty(); }
+  bool canLongjmp(Module &M, const Value *Callee) const;
+
+  void createSetThrewFunction(Module &M);
+  void createSetTempRet0Function(Module &M);
+
+  void rebuildSSA(Function &F);
 
 public:
   static char ID;
 
-  WebAssemblyLowerEmscriptenEHSjLj(bool DoEH = true, bool DoSjLj = true)
-      : ModulePass(ID), DoEH(DoEH), DoSjLj(DoSjLj), ThrewGV(nullptr),
-        ThrewValueGV(nullptr), TempRet0GV(nullptr), ResumeF(nullptr),
-        EHTypeIDF(nullptr) {
+  WebAssemblyLowerEmscriptenEHSjLj(bool EnableEH = true, bool EnableSjLj = true)
+      : ModulePass(ID), EnableEH(EnableEH), EnableSjLj(EnableSjLj),
+        ThrewGV(nullptr), ThrewValueGV(nullptr), TempRet0GV(nullptr),
+        ResumeF(nullptr), EHTypeIDF(nullptr), EmLongjmpF(nullptr),
+        EmLongjmpJmpbufF(nullptr), SaveSetjmpF(nullptr), TestSetjmpF(nullptr) {
     EHWhitelistSet.insert(EHWhitelist.begin(), EHWhitelist.end());
   }
   bool runOnModule(Module &M) override;
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addRequired<DominatorTreeWrapperPass>();
+  }
 };
 } // End anonymous namespace
 
 const char *WebAssemblyLowerEmscriptenEHSjLj::ThrewGVName = "__THREW__";
 const char *WebAssemblyLowerEmscriptenEHSjLj::ThrewValueGVName = "__threwValue";
 const char *WebAssemblyLowerEmscriptenEHSjLj::TempRet0GVName = "__tempRet0";
 const char *WebAssemblyLowerEmscriptenEHSjLj::ResumeFName = "__resumeException";
 const char *WebAssemblyLowerEmscriptenEHSjLj::EHTypeIDFName =
     "llvm_eh_typeid_for";
 const char *WebAssemblyLowerEmscriptenEHSjLj::SetThrewFName = "setThrew";
 const char *WebAssemblyLowerEmscriptenEHSjLj::SetTempRet0FName = "setTempRet0";
+const char *WebAssemblyLowerEmscriptenEHSjLj::EmLongjmpFName =
+    "emscripten_longjmp";
+const char *WebAssemblyLowerEmscriptenEHSjLj::EmLongjmpJmpbufFName =
+    "emscripten_longjmp_jmpbuf";
+const char *WebAssemblyLowerEmscriptenEHSjLj::SaveSetjmpFName = "saveSetjmp";
+const char *WebAssemblyLowerEmscriptenEHSjLj::TestSetjmpFName = "testSetjmp";
 const char *WebAssemblyLowerEmscriptenEHSjLj::FindMatchingCatchPrefix =
     "__cxa_find_matching_catch_";
 const char *WebAssemblyLowerEmscriptenEHSjLj::InvokePrefix = "__invoke_";
 
 char WebAssemblyLowerEmscriptenEHSjLj::ID = 0;
 INITIALIZE_PASS(WebAssemblyLowerEmscriptenEHSjLj, DEBUG_TYPE,
                 "WebAssembly Lower Emscripten Exceptions / Setjmp / Longjmp",
                 false, false)
 
-ModulePass *llvm::createWebAssemblyLowerEmscriptenEHSjLj(bool DoEH,
-                                                         bool DoSjLj) {
-  return new WebAssemblyLowerEmscriptenEHSjLj(DoEH, DoSjLj);
+ModulePass *llvm::createWebAssemblyLowerEmscriptenEHSjLj(bool EnableEH,
+                                                         bool EnableSjLj) {
+  return new WebAssemblyLowerEmscriptenEHSjLj(EnableEH, EnableSjLj);
 }
 
 static bool canThrow(const Value *V) {
   if (const auto *F = dyn_cast<const Function>(V)) {
     // Intrinsics cannot throw
     if (F->isIntrinsic())
       return false;
     StringRef Name = F->getName();
     // leave setjmp and longjmp (mostly) alone, we process them properly later
     if (Name == "setjmp" || Name == "longjmp")
       return false;
-    return true;
+    return !F->doesNotThrow();
   }
   // not a function, so an indirect call - can throw, we can't tell
   return true;
 }
 
 // Returns an available name for a global value.
 // If the proposed name already exists in the module, adds '_' at the end of
 // the name until the name is available.
static std::string getSignature(FunctionType *FTy) {
   Sig = OS.str();
   Sig.erase(remove_if(Sig, isspace), Sig.end());
   // When s2wasm parses .s file, a comma means the end of an argument. So a
   // mangled function name can contain any character but a comma.
   std::replace(Sig.begin(), Sig.end(), ',', '.');
   return Sig;
 }
 
+// Returns __cxa_find_matching_catch_N function, where N = NumClauses + 2.
+// This is because a landingpad instruction contains two more arguments, a
+// personality function and a cleanup bit, and __cxa_find_matching_catch_N
+// functions are named after the number of arguments in the original landingpad
+// instruction.
 Function *
 WebAssemblyLowerEmscriptenEHSjLj::getFindMatchingCatch(Module &M,
                                                        unsigned NumClauses) {
   if (FindMatchingCatches.count(NumClauses))
     return FindMatchingCatches[NumClauses];
   PointerType *Int8PtrTy = Type::getInt8PtrTy(M.getContext());
   SmallVector<Type *, 16> Args(NumClauses, Int8PtrTy);
   FunctionType *FTy = FunctionType::get(Int8PtrTy, Args, false);
   Function *F =
       Function::Create(FTy, GlobalValue::ExternalLinkage,
                        FindMatchingCatchPrefix + Twine(NumClauses + 2), &M);
   FindMatchingCatches[NumClauses] = F;
   return F;
 }
 
-Function *WebAssemblyLowerEmscriptenEHSjLj::getInvokeWrapper(Module &M,
-                                                             InvokeInst *II) {
+// Generate invoke wrapper seqence with preamble and postamble
+// Preamble:
+// __THREW__ = 0;
+// Postamble:
+// %__THREW__.val = __THREW__; __THREW__ = 0;
+// Returns %__THREW__.val, which indicates whether an exception is thrown (or
+// whether longjmp occurred), for future use.
+template <typename CallOrInvoke>
+Value *WebAssemblyLowerEmscriptenEHSjLj::wrapInvoke(CallOrInvoke *CI) {
+  LLVMContext &C = CI->getModule()->getContext();
+
+  // If we are calling a function that is noreturn, we must remove that
+  // attribute. The code we insert here does expect it to return, after we
+  // catch the exception.
+  if (CI->doesNotReturn()) {
+    if (auto *F = dyn_cast<Function>(CI->getCalledValue()))
+      F->removeFnAttr(Attribute::NoReturn);
+    CI->removeAttribute(AttributeSet::FunctionIndex, Attribute::NoReturn);
+  }
+
+  IRBuilder<> IRB(C);
+  IRB.SetInsertPoint(CI);
+
+  // Pre-invoke
+  // __THREW__ = 0;
+  IRB.CreateStore(IRB.getInt32(0), ThrewGV);
+
+  // Invoke function wrapper in JavaScript
+  SmallVector<Value *, 16> Args;
+  // Put the pointer to the callee as first argument, so it can be called
+  // within the invoke wrapper later
+  Args.push_back(CI->getCalledValue());
+  Args.append(CI->arg_begin(), CI->arg_end());
+  CallInst *NewCall = IRB.CreateCall(getInvokeWrapper(CI), Args);
+  NewCall->takeName(CI);
+  NewCall->setCallingConv(CI->getCallingConv());
+  NewCall->setDebugLoc(CI->getDebugLoc());
+
+  // Because we added the pointer to the callee as first argument, all
+  // argument attribute indices have to be incremented by one.
+  SmallVector<AttributeSet, 8> AttributesVec;
+  const AttributeSet &InvokePAL = CI->getAttributes();
+  CallSite::arg_iterator AI = CI->arg_begin();
+  unsigned i = 1; // Argument attribute index starts from 1
+  for (unsigned e = CI->getNumArgOperands(); i <= e; ++AI, ++i) {
+    if (InvokePAL.hasAttributes(i)) {
+      AttrBuilder B(InvokePAL, i);
+      AttributesVec.push_back(AttributeSet::get(C, i + 1, B));
+    }
+  }
+  // Add any return attributes.
+  if (InvokePAL.hasAttributes(AttributeSet::ReturnIndex))
+    AttributesVec.push_back(AttributeSet::get(C, InvokePAL.getRetAttributes()));
+  // Add any function attributes.
+  if (InvokePAL.hasAttributes(AttributeSet::FunctionIndex))
+    AttributesVec.push_back(AttributeSet::get(C, InvokePAL.getFnAttributes()));
+  // Reconstruct the AttributesList based on the vector we constructed.
+  AttributeSet NewCallPAL = AttributeSet::get(C, AttributesVec);
+  NewCall->setAttributes(NewCallPAL);
+
+  CI->replaceAllUsesWith(NewCall);
+
+  // Post-invoke
+  // %__THREW__.val = __THREW__; __THREW__ = 0;
+  Value *Threw = IRB.CreateLoad(ThrewGV, ThrewGV->getName() + ".val");
+  IRB.CreateStore(IRB.getInt32(0), ThrewGV);
+  return Threw;
+}
+
+// Get matching invoke wrapper based on callee signature
+template <typename CallOrInvoke>
+Function *WebAssemblyLowerEmscriptenEHSjLj::getInvokeWrapper(CallOrInvoke *CI) {
+  Module *M = CI->getModule();
   SmallVector<Type *, 16> ArgTys;
-  Value *Callee = II->getCalledValue();
+  Value *Callee = CI->getCalledValue();
   FunctionType *CalleeFTy;
   if (auto *F = dyn_cast<Function>(Callee))
     CalleeFTy = F->getFunctionType();
   else {
-    auto *CalleeTy = dyn_cast<PointerType>(Callee->getType())->getElementType();
+    auto *CalleeTy = cast<PointerType>(Callee->getType())->getElementType();
     CalleeFTy = dyn_cast<FunctionType>(CalleeTy);
   }
 
   std::string Sig = getSignature(CalleeFTy);
   if (InvokeWrappers.find(Sig) != InvokeWrappers.end())
     return InvokeWrappers[Sig];
 
   // Put the pointer to the callee as first argument
   ArgTys.push_back(PointerType::getUnqual(CalleeFTy));
   // Add argument types
   ArgTys.append(CalleeFTy->param_begin(), CalleeFTy->param_end());
 
   FunctionType *FTy = FunctionType::get(CalleeFTy->getReturnType(), ArgTys,
                                         CalleeFTy->isVarArg());
   Function *F = Function::Create(FTy, GlobalValue::ExternalLinkage,
-                                 InvokePrefix + Sig, &M);
+                                 InvokePrefix + Sig, M);
   InvokeWrappers[Sig] = F;
   return F;
 }
 
-bool WebAssemblyLowerEmscriptenEHSjLj::runOnModule(Module &M) {
-  LLVMContext &C = M.getContext();
-  IRBuilder<> IRB(C);
-  IntegerType *Int1Ty = IRB.getInt1Ty();
-  PointerType *Int8PtrTy = IRB.getInt8PtrTy();
-  IntegerType *Int32Ty = IRB.getInt32Ty();
-  Type *VoidTy = IRB.getVoidTy();
+bool WebAssemblyLowerEmscriptenEHSjLj::canLongjmp(Module &M,
+                                                  const Value *Callee) const {
+  if (auto *CalleeF = dyn_cast<Function>(Callee))
+    if (CalleeF->isIntrinsic())
+      return false;
 
-  // Create global variables __THREW__, threwValue, and tempRet0, which are
-  // used in common for both exception handling and setjmp/longjmp handling
-  ThrewGV =
-      new GlobalVariable(M, Int1Ty, false, GlobalValue::ExternalLinkage,
-                         IRB.getFalse(), createGlobalValueName(M, ThrewGVName));
-  ThrewValueGV = new GlobalVariable(
-      M, Int32Ty, false, GlobalValue::ExternalLinkage, IRB.getInt32(0),
-      createGlobalValueName(M, ThrewValueGVName));
-  TempRet0GV = new GlobalVariable(M, Int32Ty, false,
-                                  GlobalValue::ExternalLinkage, IRB.getInt32(0),
-                                  createGlobalValueName(M, TempRet0GVName));
+  // The reason we include malloc/free here is to exclude the malloc/free
+  // calls generated in setjmp prep / cleanup routines.
+  Function *SetjmpF = M.getFunction("setjmp");
+  Function *MallocF = M.getFunction("malloc");
+  Function *FreeF = M.getFunction("free");
+  if (Callee == SetjmpF || Callee == MallocF || Callee == FreeF)
+    return false;
 
-  bool Changed = false;
+  // There are functions in JS glue code
+  if (Callee == ResumeF || Callee == EHTypeIDF || Callee == SaveSetjmpF ||
+      Callee == TestSetjmpF)
+    return false;
 
-  // Exception handling
-  if (DoEH) {
-    // Register __resumeException function
-    FunctionType *ResumeFTy = FunctionType::get(VoidTy, Int8PtrTy, false);
-    ResumeF = Function::Create(ResumeFTy, GlobalValue::ExternalLinkage,
-                               ResumeFName, &M);
+  // __cxa_find_matching_catch_N functions cannot longjmp
+  if (Callee->getName().startswith(FindMatchingCatchPrefix))
+    return false;
 
-    // Register llvm_eh_typeid_for function
-    FunctionType *EHTypeIDTy = FunctionType::get(Int32Ty, Int8PtrTy, false);
-    EHTypeIDF = Function::Create(EHTypeIDTy, GlobalValue::ExternalLinkage,
-                                 EHTypeIDFName, &M);
+  // Exception-catching related functions
+  Function *BeginCatchF = M.getFunction("__cxa_begin_catch");
+  Function *EndCatchF = M.getFunction("__cxa_end_catch");
+  Function *AllocExceptionF = M.getFunction("__cxa_allocate_exception");
+  Function *ThrowF = M.getFunction("__cxa_throw");
+  Function *TerminateF = M.getFunction("__clang_call_terminate");
+  if (Callee == BeginCatchF || Callee == EndCatchF ||
+      Callee == AllocExceptionF || Callee == ThrowF || Callee == TerminateF)
+    return false;
 
-    for (Function &F : M) {
-      if (F.isDeclaration())
-        continue;
-      Changed |= runEHOnFunction(F);
-    }
-  }
+  // Otherwise we don't know
+  return true;
 
-  // TODO: Run CFGSimplify like the emscripten JSBackend?
+// Generate testSetjmp function call seqence with preamble and postamble.
+// The code this generates is equivalent to the following JavaScript code:
+// if (%__THREW__.val != 0 & threwValue != 0) {
+//   %label = _testSetjmp(mem[%__THREW__.val], setjmpTable, setjmpTableSize);
+//   if (%label == 0)
+//     emscripten_longjmp(%__THREW__.val, threwValue);
+//   __tempRet0 = threwValue;
+// } else {
+//   %label = -1;
+// }
+// %longjmp_result = __tempRet0;
+//
+// As output parameters. returns %label, %longjmp_result, and the BB the last
+// instruction (%longjmp_result = ...) is in.
+void WebAssemblyLowerEmscriptenEHSjLj::wrapTestSetjmp(
+    BasicBlock *BB, Instruction *InsertPt, Value *Threw, Value *SetjmpTable,
+    Value *SetjmpTableSize, Value *&Label, Value *&LongjmpResult,
+    BasicBlock *&EndBB) {
+  Function *F = BB->getParent();
+  LLVMContext &C = BB->getModule()->getContext();
+  IRBuilder<> IRB(C);
+  IRB.SetInsertPoint(InsertPt);
 
-  // Setjmp/longjmp handling
-  if (DoSjLj) {
-    for (Function &F : M) {
-      if (F.isDeclaration())
-        continue;
-      Changed |= runSjLjOnFunction(F);
-    }
-  }
+  // if (%__THREW__.val != 0 & threwValue != 0)
+  IRB.SetInsertPoint(BB);
+  BasicBlock *ThenBB1 = BasicBlock::Create(C, "if.then1", F);
+  BasicBlock *ElseBB1 = BasicBlock::Create(C, "if.else1", F);
+  BasicBlock *EndBB1 = BasicBlock::Create(C, "if.end", F);
+  Value *ThrewCmp = IRB.CreateICmpNE(Threw, IRB.getInt32(0));
+  Value *ThrewValue =
+      IRB.CreateLoad(ThrewValueGV, ThrewValueGV->getName() + ".val");
+  Value *ThrewValueCmp = IRB.CreateICmpNE(ThrewValue, IRB.getInt32(0));
+  Value *Cmp1 = IRB.CreateAnd(ThrewCmp, ThrewValueCmp, "cmp1");
+  IRB.CreateCondBr(Cmp1, ThenBB1, ElseBB1);
+
+  // %label = _testSetjmp(mem[%__THREW__.val], _setjmpTable, _setjmpTableSize);
+  // if (%label == 0)
+  IRB.SetInsertPoint(ThenBB1);
+  BasicBlock *ThenBB2 = BasicBlock::Create(C, "if.then2", F);
+  BasicBlock *EndBB2 = BasicBlock::Create(C, "if.end2", F);
+  Value *ThrewInt = IRB.CreateIntToPtr(Threw, Type::getInt32PtrTy(C),
+                                       Threw->getName() + ".i32p");
+  Value *LoadedThrew =
+      IRB.CreateLoad(ThrewInt, ThrewInt->getName() + ".loaded");
+  Value *ThenLabel = IRB.CreateCall(
+      TestSetjmpF, {LoadedThrew, SetjmpTable, SetjmpTableSize}, "label");
+  Value *Cmp2 = IRB.CreateICmpEQ(ThenLabel, IRB.getInt32(0));
+  IRB.CreateCondBr(Cmp2, ThenBB2, EndBB2);
+
+  // emscripten_longjmp(%__THREW__.val, threwValue);
+  IRB.SetInsertPoint(ThenBB2);
+  IRB.CreateCall(EmLongjmpF, {Threw, ThrewValue});
+  IRB.CreateUnreachable();
+
+  // __tempRet0 = threwValue;
+  IRB.SetInsertPoint(EndBB2);
+  IRB.CreateStore(ThrewValue, TempRet0GV);
+  IRB.CreateBr(EndBB1);
+
+  IRB.SetInsertPoint(ElseBB1);
+  IRB.CreateBr(EndBB1);
+
+  // longjmp_result = __tempRet0;
+  IRB.SetInsertPoint(EndBB1);
+  PHINode *LabelPHI = IRB.CreatePHI(IRB.getInt32Ty(), 2, "label");
+  LabelPHI->addIncoming(ThenLabel, EndBB2);
+
+  LabelPHI->addIncoming(IRB.getInt32(-1), ElseBB1);
+
+  // Output parameter assignment
+  Label = LabelPHI;
+  EndBB = EndBB1;
+  LongjmpResult = IRB.CreateLoad(TempRet0GV, "longjmp_result");
 
-  if (!Changed)
-    return false;
+// Create setThrew function
+// function setThrew(threw, value) {
+//   if (__THREW__ == 0) {
+//     __THREW__ = threw;
+//     __threwValue = value;
+//   }
+// }
+void WebAssemblyLowerEmscriptenEHSjLj::createSetThrewFunction(Module &M) {
+  LLVMContext &C = M.getContext();
+  IRBuilder<> IRB(C);
 
-  // If we have made any changes while doing exception handling or
-  // setjmp/longjmp handling, we have to create these functions for JavaScript
-  // to call.
   assert(!M.getNamedGlobal(SetThrewFName) && "setThrew already exists");
-  assert(!M.getNamedGlobal(SetTempRet0FName) && "setTempRet0 already exists");
-
-  // Create setThrew function
-  SmallVector<Type *, 2> Params = {Int1Ty, Int32Ty};
-  FunctionType *FTy = FunctionType::get(VoidTy, Params, false);
+  Type *Params[] = {IRB.getInt32Ty(), IRB.getInt32Ty()};
+  FunctionType *FTy = FunctionType::get(IRB.getVoidTy(), Params, false);
   Function *F =
       Function::Create(FTy, GlobalValue::ExternalLinkage, SetThrewFName, &M);
   Argument *Arg1 = &*(F->arg_begin());
   Argument *Arg2 = &*(++F->arg_begin());
   Arg1->setName("threw");
   Arg2->setName("value");
   BasicBlock *EntryBB = BasicBlock::Create(C, "entry", F);
   BasicBlock *ThenBB = BasicBlock::Create(C, "if.then", F);
   BasicBlock *EndBB = BasicBlock::Create(C, "if.end", F);
 
   IRB.SetInsertPoint(EntryBB);
   Value *Threw = IRB.CreateLoad(ThrewGV, ThrewGV->getName() + ".val");
-  Value *Cmp = IRB.CreateICmpEQ(Threw, IRB.getFalse(), "cmp");
+  Value *Cmp = IRB.CreateICmpEQ(Threw, IRB.getInt32(0), "cmp");
   IRB.CreateCondBr(Cmp, ThenBB, EndBB);
 
   IRB.SetInsertPoint(ThenBB);
   IRB.CreateStore(Arg1, ThrewGV);
   IRB.CreateStore(Arg2, ThrewValueGV);
   IRB.CreateBr(EndBB);
 
   IRB.SetInsertPoint(EndBB);
   IRB.CreateRetVoid();
+}
 
-  // Create setTempRet0 function
-  Params = {Int32Ty};
-  FTy = FunctionType::get(VoidTy, Params, false);
-  F = Function::Create(FTy, GlobalValue::ExternalLinkage, SetTempRet0FName, &M);
+// function setTempRet0(value) {
+//   __tempRet0 = value;
+// }
+void WebAssemblyLowerEmscriptenEHSjLj::createSetTempRet0Function(Module &M) {
+  LLVMContext &C = M.getContext();
+  IRBuilder<> IRB(C);
+
+  assert(!M.getNamedGlobal(SetTempRet0FName) && "setTempRet0 already exists");
+  Type *Params[] = {IRB.getInt32Ty()};
+  FunctionType *FTy = FunctionType::get(IRB.getVoidTy(), Params, false);
+  Function *F =
+      Function::Create(FTy, GlobalValue::ExternalLinkage, SetTempRet0FName, &M);
   F->arg_begin()->setName("value");
-  EntryBB = BasicBlock::Create(C, "entry", F);
+  BasicBlock *EntryBB = BasicBlock::Create(C, "entry", F);
   IRB.SetInsertPoint(EntryBB);
   IRB.CreateStore(&*F->arg_begin(), TempRet0GV);
   IRB.CreateRetVoid();
+}
+
+void WebAssemblyLowerEmscriptenEHSjLj::rebuildSSA(Function &F) {
+  DominatorTree &DT = getAnalysis<DominatorTreeWrapperPass>(F).getDomTree();
+  DT.recalculate(F); // CFG has been changed
+  SSAUpdater SSA;
+  for (BasicBlock &BB : F) {
+    for (Instruction &I : BB) {
+      for (auto UI = I.use_begin(), UE = I.use_end(); UI != UE;) {
+        Use &U = *UI;
+        ++UI;
+        SSA.Initialize(I.getType(), I.getName());
+        SSA.AddAvailableValue(&BB, &I);
+        Instruction *User = cast<Instruction>(U.getUser());
+        if (User->getParent() == &BB)
+          continue;
+
+        if (PHINode *UserPN = dyn_cast<PHINode>(User))
+          if (UserPN->getIncomingBlock(U) == &BB)
+            continue;
+
+        if (DT.dominates(&I, User))
+          continue;
+        SSA.RewriteUseAfterInsertions(U);
+      }
+    }
+  }
+}
+
+bool WebAssemblyLowerEmscriptenEHSjLj::runOnModule(Module &M) {
+  LLVMContext &C = M.getContext();
+  IRBuilder<> IRB(C);
+
+  Function *SetjmpF = M.getFunction("setjmp");
+  Function *LongjmpF = M.getFunction("longjmp");
+  bool SetjmpUsed = SetjmpF && !SetjmpF->use_empty();
+  bool LongjmpUsed = LongjmpF && !LongjmpF->use_empty();
+  bool DoSjLj = EnableSjLj && (SetjmpUsed || LongjmpUsed);
+
+  // Create global variables __THREW__, threwValue, and __tempRet0, which are
+  // used in common for both exception handling and setjmp/longjmp handling
+  ThrewGV = new GlobalVariable(M, IRB.getInt32Ty(), false,
+                               GlobalValue::ExternalLinkage, IRB.getInt32(0),
+                               createGlobalValueName(M, ThrewGVName));
+  ThrewValueGV = new GlobalVariable(
+      M, IRB.getInt32Ty(), false, GlobalValue::ExternalLinkage, IRB.getInt32(0),
+      createGlobalValueName(M, ThrewValueGVName));
+  TempRet0GV = new GlobalVariable(M, IRB.getInt32Ty(), false,
+                                  GlobalValue::ExternalLinkage, IRB.getInt32(0),
+                                  createGlobalValueName(M, TempRet0GVName));
+
+  bool Changed = false;
+
+  // Exception handling
+  if (EnableEH) {
+    // Register __resumeException function
+    FunctionType *ResumeFTy =
+        FunctionType::get(IRB.getVoidTy(), IRB.getInt8PtrTy(), false);
+    ResumeF = Function::Create(ResumeFTy, GlobalValue::ExternalLinkage,
+                               ResumeFName, &M);
+
+    // Register llvm_eh_typeid_for function
+    FunctionType *EHTypeIDTy =
+        FunctionType::get(IRB.getInt32Ty(), IRB.getInt8PtrTy(), false);
+    EHTypeIDF = Function::Create(EHTypeIDTy, GlobalValue::ExternalLinkage,
+                                 EHTypeIDFName, &M);
+
+    for (Function &F : M) {
+      if (F.isDeclaration())
+        continue;
+      Changed |= runEHOnFunction(F);
+    }
+  }
+
+  // Setjmp/longjmp handling
+  if (DoSjLj) {
+    Changed = true; // We have setjmp or longjmp somewhere
+
+    Function *MallocF = M.getFunction("malloc");
+    Function *FreeF = M.getFunction("free");
+    if (!MallocF || !FreeF)
+      report_fatal_error(
+          "malloc and free must be linked into the module if setjmp is used");
+
+    // Register saveSetjmp function
+    FunctionType *SetjmpFTy = SetjmpF->getFunctionType();
+    SmallVector<Type *, 4> Params = {SetjmpFTy->getParamType(0),
+                                     IRB.getInt32Ty(), Type::getInt32PtrTy(C),
+                                     IRB.getInt32Ty()};
+    FunctionType *FTy =
+        FunctionType::get(Type::getInt32PtrTy(C), Params, false);
+    SaveSetjmpF = Function::Create(FTy, GlobalValue::ExternalLinkage,
+                                   SaveSetjmpFName, &M);
+
+    // Register testSetjmp function
+    Params = {IRB.getInt32Ty(), Type::getInt32PtrTy(C), IRB.getInt32Ty()};
+    FTy = FunctionType::get(IRB.getInt32Ty(), Params, false);
+    TestSetjmpF = Function::Create(FTy, GlobalValue::ExternalLinkage,
+                                   TestSetjmpFName, &M);
+
+    if (LongjmpF) {
+      // Replace all uses of longjmp with emscripten_longjmp_jmpbuf, which is
+      // defined in JS code
+      EmLongjmpJmpbufF = Function::Create(LongjmpF->getFunctionType(),
+                                          GlobalValue::ExternalLinkage,
+                                          EmLongjmpJmpbufFName, &M);
+
+      LongjmpF->replaceAllUsesWith(EmLongjmpJmpbufF);
+    }
+    FTy = FunctionType::get(IRB.getVoidTy(),
+                            {IRB.getInt32Ty(), IRB.getInt32Ty()}, false);
+    EmLongjmpF =
+        Function::Create(FTy, GlobalValue::ExternalLinkage, EmLongjmpFName, &M);
+
+    // Only traverse functions that uses setjmp in order not to insert
+    // unnecessary prep / cleanup code in every function
+    SmallPtrSet<Function *, 8> SetjmpUsers;
+    for (User *U : SetjmpF->users()) {
+      auto *UI = cast<Instruction>(U);
+      SetjmpUsers.insert(UI->getFunction());
+    }
+    for (Function *F : SetjmpUsers)
+      runSjLjOnFunction(*F);
+  }
+
+  if (!Changed) {
+    // Delete unused global variables and functions
+    ThrewGV->eraseFromParent();
+    ThrewValueGV->eraseFromParent();
+    TempRet0GV->eraseFromParent();
+    if (ResumeF)
+      ResumeF->eraseFromParent();
+    if (EHTypeIDF)
+      EHTypeIDF->eraseFromParent();
+    if (EmLongjmpF)
+      EmLongjmpF->eraseFromParent();
+    if (SaveSetjmpF)
+      SaveSetjmpF->eraseFromParent();
+    if (TestSetjmpF)
+      TestSetjmpF->eraseFromParent();
+    return false;
+  }
+
+  // If we have made any changes while doing exception handling or
+  // setjmp/longjmp handling, we have to create these functions for JavaScript
+  // to call.
+  createSetThrewFunction(M);
+  createSetTempRet0Function(M);
 
   return true;
 }
 
 bool WebAssemblyLowerEmscriptenEHSjLj::runEHOnFunction(Function &F) {
   Module &M = *F.getParent();
   LLVMContext &C = F.getContext();
   IRBuilder<> IRB(C);
   bool Changed = false;
   SmallVector<Instruction *, 64> ToErase;
   SmallPtrSet<LandingPadInst *, 32> LandingPads;
   bool AllowExceptions =
       areAllExceptionsAllowed() || EHWhitelistSet.count(F.getName());
 
   for (BasicBlock &BB : F) {
     auto *II = dyn_cast<InvokeInst>(BB.getTerminator());
     if (!II)
       continue;
     Changed = true;
     LandingPads.insert(II->getLandingPadInst());
     IRB.SetInsertPoint(II);
 
     bool NeedInvoke = AllowExceptions && canThrow(II->getCalledValue());
     if (NeedInvoke) {
-      // If we are calling a function that is noreturn, we must remove that
-      // attribute. The code we insert here does expect it to return, after we
-      // catch the exception.
-      if (II->doesNotReturn()) {
-        if (auto *F = dyn_cast<Function>(II->getCalledValue()))
-          F->removeFnAttr(Attribute::NoReturn);
-        AttributeSet NewAttrs = II->getAttributes();
-        NewAttrs.removeAttribute(C, AttributeSet::FunctionIndex,
-                                 Attribute::NoReturn);
-        II->setAttributes(NewAttrs);
-      }
-
-      // Pre-invoke
-      // __THREW__ = 0;
-      IRB.CreateStore(IRB.getFalse(), ThrewGV);
-
-      // Invoke function wrapper in JavaScript
-      SmallVector<Value *, 16> CallArgs;
-      // Put the pointer to the callee as first argument, so it can be called
-      // within the invoke wrapper later
-      CallArgs.push_back(II->getCalledValue());
-      CallArgs.append(II->arg_begin(), II->arg_end());
-      CallInst *NewCall = IRB.CreateCall(getInvokeWrapper(M, II), CallArgs);
-      NewCall->takeName(II);
-      NewCall->setCallingConv(II->getCallingConv());
-      NewCall->setDebugLoc(II->getDebugLoc());
-
-      // Because we added the pointer to the callee as first argument, all
-      // argument attribute indices have to be incremented by one.
-      SmallVector<AttributeSet, 8> AttributesVec;
-      const AttributeSet &InvokePAL = II->getAttributes();
-      CallSite::arg_iterator AI = II->arg_begin();
-      unsigned i = 1; // Argument attribute index starts from 1
-      for (unsigned e = II->getNumArgOperands(); i <= e; ++AI, ++i) {
-        if (InvokePAL.hasAttributes(i)) {
-          AttrBuilder B(InvokePAL, i);
-          AttributesVec.push_back(AttributeSet::get(C, i + 1, B));
-        }
-      }
-      // Add any return attributes.
-      if (InvokePAL.hasAttributes(AttributeSet::ReturnIndex))
-        AttributesVec.push_back(
-            AttributeSet::get(C, InvokePAL.getRetAttributes()));
-      // Add any function attributes.
-      if (InvokePAL.hasAttributes(AttributeSet::FunctionIndex))
-        AttributesVec.push_back(
-            AttributeSet::get(C, InvokePAL.getFnAttributes()));
-      // Reconstruct the AttributesList based on the vector we constructed.
-      AttributeSet NewCallPAL = AttributeSet::get(C, AttributesVec);
-      NewCall->setAttributes(NewCallPAL);
-
-      II->replaceAllUsesWith(NewCall);
+      // Wrap invoke with invoke wrapper and generate preamble/postamble
+      Value *Threw = wrapInvoke(II);
       ToErase.push_back(II);
 
-      // Post-invoke
-      // %__THREW__.val = __THREW__; __THREW__ = 0;
-      Value *Threw = IRB.CreateLoad(ThrewGV, ThrewGV->getName() + ".val");
-      IRB.CreateStore(IRB.getFalse(), ThrewGV);
-
       // Insert a branch based on __THREW__ variable
-      IRB.CreateCondBr(Threw, II->getUnwindDest(), II->getNormalDest());
+      Value *Cmp = IRB.CreateICmpEQ(Threw, IRB.getInt32(1), "cmp");
+      IRB.CreateCondBr(Cmp, II->getUnwindDest(), II->getNormalDest());
 
     } else {
       // This can't throw, and we don't need this invoke, just replace it with a
       // call+branch
-      SmallVector<Value *, 16> CallArgs(II->arg_begin(), II->arg_end());
-      CallInst *NewCall = IRB.CreateCall(II->getCalledValue(), CallArgs);
+      SmallVector<Value *, 16> Args(II->arg_begin(), II->arg_end());
+      CallInst *NewCall = IRB.CreateCall(II->getCalledValue(), Args);
       NewCall->takeName(II);
       NewCall->setCallingConv(II->getCallingConv());
       NewCall->setDebugLoc(II->getDebugLoc());
       NewCall->setAttributes(II->getAttributes());
       II->replaceAllUsesWith(NewCall);
       ToErase.push_back(II);
 
       IRB.CreateBr(II->getNormalDest());
for (Instruction &I : BB) {
       auto *RI = dyn_cast<ResumeInst>(&I);
       if (!RI)
         continue;
 
       // Split the input into legal values
       Value *Input = RI->getValue();
       IRB.SetInsertPoint(RI);
       Value *Low = IRB.CreateExtractValue(Input, 0, "low");
-
       // Create a call to __resumeException function
-      Value *Args[] = {Low};
-      IRB.CreateCall(ResumeF, Args);
-
+      IRB.CreateCall(ResumeF, {Low});
       // Add a terminator to the block
       IRB.CreateUnreachable();
       ToErase.push_back(RI);
     }
   }
 
   // Process llvm.eh.typeid.for intrinsics
   for (BasicBlock &BB : F) {
for (LandingPadInst *LPI : LandingPads) {
     IRB.SetInsertPoint(LPI);
     SmallVector<Value *, 16> FMCArgs;
     for (unsigned i = 0, e = LPI->getNumClauses(); i < e; ++i) {
       Constant *Clause = LPI->getClause(i);
       // As a temporary workaround for the lack of aggregate varargs support
       // in the interface between JS and wasm, break out filter operands into
       // their component elements.
       if (LPI->isFilter(i)) {
-        ArrayType *ATy = cast<ArrayType>(Clause->getType());
+        auto *ATy = cast<ArrayType>(Clause->getType());
         for (unsigned j = 0, e = ATy->getNumElements(); j < e; ++j) {
           Value *EV = IRB.CreateExtractValue(Clause, makeArrayRef(j), "filter");
           FMCArgs.push_back(EV);
         }
       } else
         FMCArgs.push_back(Clause);
     }
 
     // Create a call to __cxa_find_matching_catch_N function
     Function *FMCF = getFindMatchingCatch(M, FMCArgs.size());
     CallInst *FMCI = IRB.CreateCall(FMCF, FMCArgs, "fmc");
     Value *Undef = UndefValue::get(LPI->getType());
     Value *Pair0 = IRB.CreateInsertValue(Undef, FMCI, 0, "pair0");
-    Value *TempRet0 = IRB.CreateLoad(TempRet0GV, TempRet0GV->getName() + "val");
+    Value *TempRet0 =
+        IRB.CreateLoad(TempRet0GV, TempRet0GV->getName() + ".val");
     Value *Pair1 = IRB.CreateInsertValue(Pair0, TempRet0, 1, "pair1");
 
     LPI->replaceAllUsesWith(Pair1);
     ToErase.push_back(LPI);
   }
 
   // Erase everything we no longer need in this function
   for (Instruction *I : ToErase)
     I->eraseFromParent();
 
   return Changed;
 }
 
 bool WebAssemblyLowerEmscriptenEHSjLj::runSjLjOnFunction(Function &F) {
-  // TODO
-  return false;
+  Module &M = *F.getParent();
+  LLVMContext &C = F.getContext();
+  IRBuilder<> IRB(C);
+  SmallVector<Instruction *, 64> ToErase;
+  // Vector of %setjmpTable values
+  std::vector<Instruction *> SetjmpTableInsts;
+  // Vector of %setjmpTableSize values
+  std::vector<Instruction *> SetjmpTableSizeInsts;
+
+  // Setjmp preparation
+
+  // This instruction effectively means %setjmpTableSize = 4.
+  // We create this as an instruction intentionally, and we don't want to fold
+  // this instruction to a constant 4, because this value will be used in
+  // SSAUpdater.AddAvailableValue(...) later.
+  BasicBlock &EntryBB = F.getEntryBlock();
+  BinaryOperator *SetjmpTableSize = BinaryOperator::Create(
+      Instruction::Add, IRB.getInt32(4), IRB.getInt32(0), "setjmpTableSize",
+      &*EntryBB.getFirstInsertionPt());
+  // setjmpTable = (int *) malloc(40);
+  Instruction *SetjmpTable = CallInst::CreateMalloc(
+      SetjmpTableSize, IRB.getInt32Ty(), IRB.getInt32Ty(), IRB.getInt32(40),
+      nullptr, nullptr, "setjmpTable");
+  // setjmpTable[0] = 0;
+  IRB.SetInsertPoint(SetjmpTableSize);
+  IRB.CreateStore(IRB.getInt32(0), SetjmpTable);
+  SetjmpTableInsts.push_back(SetjmpTable);
+  SetjmpTableSizeInsts.push_back(SetjmpTableSize);
+
+  // Setjmp transformation
+  std::vector<PHINode *> SetjmpRetPHIs;
+  Function *SetjmpF = M.getFunction("setjmp");
+  for (User *U : SetjmpF->users()) {
+    auto *CI = dyn_cast<CallInst>(U);
+    if (!CI)
+      report_fatal_error("Does not support indirect calls to setjmp");
+
+    BasicBlock *BB = CI->getParent();
+    if (BB->getParent() != &F) // in other function
+      continue;
+
+    // The tail is everything right after the call, and will be reached once
+    // when setjmp is called, and later when longjmp returns to the setjmp
+    BasicBlock *Tail = SplitBlock(BB, CI->getNextNode());
+    // Add a phi to the tail, which will be the output of setjmp, which
+    // indicates if this is the first call or a longjmp back. The phi directly
+    // uses the right value based on where we arrive from
+    IRB.SetInsertPoint(Tail->getFirstNonPHI());
+    PHINode *SetjmpRet = IRB.CreatePHI(IRB.getInt32Ty(), 2, "setjmp.ret");
+
+    // setjmp initial call returns 0
+    SetjmpRet->addIncoming(IRB.getInt32(0), BB);
+    // The proper output is now this, not the setjmp call itself
+    CI->replaceAllUsesWith(SetjmpRet);
+    // longjmp returns to the setjmp will add themselves to this phi
+    SetjmpRetPHIs.push_back(SetjmpRet);
+
+    // Fix call target
+    // Our index in the function is our place in the array + 1 to avoid index
+    // 0, because index 0 means the longjmp is not ours to handle.
+    IRB.SetInsertPoint(CI);
+    Value *Args[] = {CI->getArgOperand(0), IRB.getInt32(SetjmpRetPHIs.size()),
+                     SetjmpTable, SetjmpTableSize};
+    Instruction *NewSetjmpTable =
+        IRB.CreateCall(SaveSetjmpF, Args, "setjmpTable");
+    Instruction *NewSetjmpTableSize =
+        IRB.CreateLoad(TempRet0GV, "setjmpTableSize");
+    SetjmpTableInsts.push_back(NewSetjmpTable);
+    SetjmpTableSizeInsts.push_back(NewSetjmpTableSize);
+    ToErase.push_back(CI);
+  }
+
+  // Update each call that can longjmp so it can return to a setjmp where
+  // relevant.
+
+  // Because we are creating new BBs while processing and don't want to make
+  // all these newly created BBs candidates again for longjmp processing, we
+  // first make the vector of candidate BBs.
+  std::vector<BasicBlock *> BBs;
+  for (BasicBlock &BB : F)
+    BBs.push_back(&BB);
+
+  // BBs.size() will change within the loop, so we query it every time
+  for (unsigned i = 0; i < BBs.size(); i++) {
+    BasicBlock *BB = BBs[i];
+    for (Instruction &I : *BB) {
+      assert(!isa<InvokeInst>(&I));
+      auto *CI = dyn_cast<CallInst>(&I);
+      if (!CI)
+        continue;
+
+      const Value *Callee = CI->getCalledValue();
+      if (!canLongjmp(M, Callee))
+        continue;
+
+      Value *Threw = nullptr;
+      BasicBlock *Tail;
+      if (Callee->getName().startswith(InvokePrefix)) {
+        // If invoke wrapper has already been generated for this call in
+        // previous EH phase, search for the load instruction
+        // %__THREW__.val = __THREW__;
+        // in postamble after the invoke wrapper call
+        LoadInst *ThrewLI = nullptr;
+        StoreInst *ThrewResetSI = nullptr;
+        for (auto I = std::next(BasicBlock::iterator(CI)), IE = BB->end();
+             I != IE; ++I) {
+          if (auto *LI = dyn_cast<LoadInst>(I))
+            if (auto *GV = dyn_cast<GlobalVariable>(LI->getPointerOperand()))
+              if (GV == ThrewGV) {
+                Threw = ThrewLI = LI;
+                break;
+              }
+        }
+        // Search for the store instruction after the load above
+        // __THREW__ = 0;
+        for (auto I = std::next(BasicBlock::iterator(ThrewLI)), IE = BB->end();
+             I != IE; ++I) {
+          if (auto *SI = dyn_cast<StoreInst>(I))
+            if (auto *GV = dyn_cast<GlobalVariable>(SI->getPointerOperand()))
+              if (GV == ThrewGV && SI->getValueOperand() == IRB.getInt32(0)) {
+                ThrewResetSI = SI;
+                break;
+              }
+        }
+        assert(Threw && ThrewLI && "Cannot find __THREW__ load after invoke");
+        assert(ThrewResetSI && "Cannot find __THREW__ store after invoke");
+        Tail = SplitBlock(BB, ThrewResetSI->getNextNode());
+
+      } else {
+        // Wrap call with invoke wrapper and generate preamble/postamble
+        Threw = wrapInvoke(CI);
+        ToErase.push_back(CI);
+        Tail = SplitBlock(BB, CI->getNextNode());
+      }
+
+      // We need to replace the terminator in Tail - SplitBlock makes BB go
+      // straight to Tail, we need to check if a longjmp occurred, and go to the
+      // right setjmp-tail if so
+      ToErase.push_back(BB->getTerminator());
+
+      // Generate a function call to testSetjmp function and preamble/postamble
+      // code to figure out (1) whether longjmp occurred (2) if longjmp
+      // occurred, which setjmp it corresponds to
+      Value *Label = nullptr;
+      Value *LongjmpResult = nullptr;
+      BasicBlock *EndBB = nullptr;
+      wrapTestSetjmp(BB, CI, Threw, SetjmpTable, SetjmpTableSize, Label,
+                     LongjmpResult, EndBB);
+      assert(Label && LongjmpResult && EndBB);
+
+      // Create switch instruction
+      IRB.SetInsertPoint(EndBB);
+      SwitchInst *SI = IRB.CreateSwitch(Label, Tail, SetjmpRetPHIs.size());
+      // -1 means no longjmp happened, continue normally (will hit the default
+      // switch case). 0 means a longjmp that is not ours to handle, needs a
+      // rethrow. Otherwise the index is the same as the index in P+1 (to avoid
+      // 0).
+      for (unsigned i = 0; i < SetjmpRetPHIs.size(); i++) {
+        SI->addCase(IRB.getInt32(i + 1), SetjmpRetPHIs[i]->getParent());
+        SetjmpRetPHIs[i]->addIncoming(LongjmpResult, EndBB);
+      }
+
+      // We are splitting the block here, and must continue to find other calls
+      // in the block - which is now split. so continue to traverse in the Tail
+      BBs.push_back(Tail);
+    }
+  }
+
+  // Erase everything we no longer need in this function
+  for (Instruction *I : ToErase)
+    I->eraseFromParent();
+
+  // Free setjmpTable buffer before each return instruction
+  for (BasicBlock &BB : F) {
+    TerminatorInst *TI = BB.getTerminator();
+    if (isa<ReturnInst>(TI))
+      CallInst::CreateFree(SetjmpTable, TI);
+  }
+
+  // Every call to saveSetjmp can change setjmpTable and setjmpTableSize
+  // (when buffer reallocation occurs)
+  // entry:
+  //   setjmpTableSize = 4;
+  //   setjmpTable = (int *) malloc(40);
+  //   setjmpTable[0] = 0;
+  // ...
+  // somebb:
+  //   setjmpTable = saveSetjmp(buf, label, setjmpTable, setjmpTableSize);
+  //   setjmpTableSize = __tempRet0;
+  // So we need to make sure the SSA for these variables is valid so that every
+  // saveSetjmp and testSetjmp calls have the correct arguments.
+  SSAUpdater SetjmpTableSSA;
+  SSAUpdater SetjmpTableSizeSSA;
+  SetjmpTableSSA.Initialize(Type::getInt32PtrTy(C), "setjmpTable");
+  SetjmpTableSizeSSA.Initialize(Type::getInt32Ty(C), "setjmpTableSize");
+  for (Instruction *I : SetjmpTableInsts)
+    SetjmpTableSSA.AddAvailableValue(I->getParent(), I);
+  for (Instruction *I : SetjmpTableSizeInsts)
+    SetjmpTableSizeSSA.AddAvailableValue(I->getParent(), I);
+
+  for (auto UI = SetjmpTable->use_begin(), UE = SetjmpTable->use_end();
+       UI != UE;) {
+    // Grab the use before incrementing the iterator.
+    Use &U = *UI;
+    // Increment the iterator before removing the use from the list.
+    ++UI;
+    if (Instruction *I = dyn_cast<Instruction>(U.getUser()))
+      if (I->getParent() != &EntryBB)
+        SetjmpTableSSA.RewriteUse(U);
+  }
+  for (auto UI = SetjmpTableSize->use_begin(), UE = SetjmpTableSize->use_end();
+       UI != UE;) {
+    Use &U = *UI;
+    ++UI;
+    if (Instruction *I = dyn_cast<Instruction>(U.getUser()))
+      if (I->getParent() != &EntryBB)
+        SetjmpTableSizeSSA.RewriteUse(U);
+  }
+
+  // Finally, our modifications to the cfg can break dominance of SSA variables.
+  // For example, in this code,
+  // if (x()) { .. setjmp() .. }
+  // if (y()) { .. longjmp() .. }
+  // We must split the longjmp block, and it can jump into the block splitted
+  // from setjmp one. But that means that when we split the setjmp block, it's
+  // first part no longer dominates its second part - there is a theoretically
+  // possible control flow path where x() is false, then y() is true and we
+  // reach the second part of the setjmp block, without ever reaching the first
+  // part. So, we rebuild SSA form here.
+  rebuildSSA(F);
+  return true;
 }

lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp

else
     // Expand some atomic operations. WebAssemblyTargetLowering has hooks which
     // control specifically what gets lowered.
     addPass(createAtomicExpandPass(TM));
 
   // Optimize "returned" function attributes.
   if (getOptLevel() != CodeGenOpt::None)
     addPass(createWebAssemblyOptimizeReturned());
 
-  // Handle exceptions.
+  // If exception handling is not enabled and setjmp/longjmp handling is
+  // enabled, we lower invokes into calls and delete unreachable landingpad
+  // blocks. Lowering invokes when there is no EH support is done in
+  // TargetPassConfig::addPassesToHandleExceptions, but this runs after this
+  // function and SjLj handling expects all invokes to be lowered before.
+  if (!EnableEmException) {
+    addPass(createLowerInvokePass());
+    // The lower invoke pass may create unreachable code. Remove it in order not
+    // to process dead blocks in setjmp/longjmp handling.
+    addPass(createUnreachableBlockEliminationPass());
+  }
+
+  // Handle exceptions and setjmp/longjmp if enabled.
   if (EnableEmException || EnableEmSjLj)
     addPass(createWebAssemblyLowerEmscriptenEHSjLj(EnableEmException,
                                                    EnableEmSjLj));
 
   TargetPassConfig::addIRPasses();
 }
 
 bool WebAssemblyPassConfig::addInstSelector() {

test/CodeGen/WebAssembly/lower-em-ehsjlj-options.ll

+; RUN: llc < %s -enable-emscripten-cxx-exceptions | FileCheck %s --check-prefix=EH
+; RUN: llc < %s -enable-emscripten-sjlj | FileCheck %s --check-prefix=SJLJ
+; RUN: llc < %s | FileCheck %s --check-prefix=NONE
+
+target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
+target triple = "wasm32-unknown-unknown"
+
+%struct.__jmp_buf_tag = type { [6 x i32], i32, [32 x i32] }
+
+define hidden void @exception() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+; EH-LABEL:   type exception,@function
+; NONE-LABEL: type exception,@function
+entry:
+  invoke void @foo()
+          to label %try.cont unwind label %lpad
+; EH:   call __invoke_void@FUNCTION
+; NONE: call foo@FUNCTION
+
+lpad:                                             ; preds = %entry
+  %0 = landingpad { i8*, i32 }
+          catch i8* null
+  %1 = extractvalue { i8*, i32 } %0, 0
+  %2 = extractvalue { i8*, i32 } %0, 1
+  %3 = call i8* @__cxa_begin_catch(i8* %1) #2
+  call void @__cxa_end_catch()
+  br label %try.cont
+
+try.cont:                                         ; preds = %entry, %lpad
+  ret void
+}
+
+define hidden void @setjmp_longjmp() {
+; SJLJ-LABEL: type setjmp_longjmp,@function
+; NONE-LABEL: type setjmp_longjmp,@function
+entry:
+  %buf = alloca [1 x %struct.__jmp_buf_tag], align 16
+  %arraydecay = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  %call = call i32 @setjmp(%struct.__jmp_buf_tag* %arraydecay) #0
+  %arraydecay1 = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  call void @longjmp(%struct.__jmp_buf_tag* %arraydecay1, i32 1) #1
+  unreachable
+; SJLJ: i32.call ${{[a-zA-Z0-9]+}}=, saveSetjmp@FUNCTION
+; SJLJ: i32.call ${{[a-zA-Z0-9]+}}=, testSetjmp@FUNCTION
+; NONE: i32.call ${{[a-zA-Z0-9]+}}=, setjmp@FUNCTION
+; NONE: call longjmp@FUNCTION
+}
+
+declare void @foo()
+declare i32 @__gxx_personality_v0(...)
+declare i8* @__cxa_begin_catch(i8*)
+declare void @__cxa_end_catch()
+; Function Attrs: returns_twice
+declare i32 @setjmp(%struct.__jmp_buf_tag*) #0
+; Function Attrs: noreturn
+declare void @longjmp(%struct.__jmp_buf_tag*, i32) #1
+declare i8* @malloc(i32)
+declare void @free(i8*)
+
+attributes #0 = { returns_twice }
+attributes #1 = { noreturn }
+attributes #2 = { nounwind }

test/CodeGen/WebAssembly/lower-em-exceptions-whitelist.ll

 ; RUN: opt < %s -wasm-lower-em-ehsjlj -emscripten-cxx-exceptions-whitelist=do_catch -S | FileCheck %s
 
+target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
+target triple = "wasm32-unknown-unknown"
+
 define void @dont_catch() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
 ; CHECK-LABEL: @dont_catch(
 entry:
   invoke void @foo()
           to label %invoke.cont unwind label %lpad
 ; CHECK: entry:
 ; CHECK-NEXT: call void @foo()
 ; CHECK-NEXT: br label %invoke.cont

 }
 
 define void @do_catch() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
 ; CHECK-LABEL: @do_catch(
 entry:
   invoke void @foo()
           to label %invoke.cont unwind label %lpad
 ; CHECK: entry:
-; CHECK-NEXT: store i1 false, i1*
+; CHECK-NEXT: store i32 0, i32*
 ; CHECK-NEXT: call void @__invoke_void(void ()* @foo)
 
 invoke.cont:                                      ; preds = %entry
   br label %try.cont
 
 lpad:                                             ; preds = %entry
   %0 = landingpad { i8*, i32 }
           catch i8* null

test/CodeGen/WebAssembly/lower-em-exceptions.ll

 ; RUN: opt < %s -wasm-lower-em-ehsjlj -S | FileCheck %s
 
+target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
+target triple = "wasm32-unknown-unknown"
+
 @_ZTIi = external constant i8*
 @_ZTIc = external constant i8*
-; CHECK: @[[__THREW__:__THREW__.*]] = global i1 false
-; CHECK: @[[THREWVALUE:__threwValue.*]] = global i32 0
-; CHECK: @[[TEMPRET0:__tempRet0.*]] = global i32 0
+; CHECK-DAG: @[[__THREW__:__THREW__.*]] = global i32 0
+; CHECK-DAG: @[[THREWVALUE:__threwValue.*]] = global i32 0
+; CHECK-DAG: @[[TEMPRET0:__tempRet0.*]] = global i32 0
 
 ; Test invoke instruction with clauses (try-catch block)
 define void @clause() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
 ; CHECK-LABEL: @clause(
 entry:
   invoke void @foo(i32 3)
           to label %invoke.cont unwind label %lpad
 ; CHECK: entry:
-; CHECK-NEXT: store i1 false, i1* @[[__THREW__]]
+; CHECK-NEXT: store i32 0, i32* @[[__THREW__]]
 ; CHECK-NEXT: call void @__invoke_void_i32(void (i32)* @foo, i32 3)
-; CHECK-NEXT: %[[__THREW__VAL:.*]] = load i1, i1* @[[__THREW__]]
-; CHECK-NEXT: store i1 false, i1* @[[__THREW__]]
-; CHECK-NEXT: br i1 %[[__THREW__VAL]], label %lpad, label %invoke.cont
+; CHECK-NEXT: %[[__THREW__VAL:.*]] = load i32, i32* @[[__THREW__]]
+; CHECK-NEXT: store i32 0, i32* @[[__THREW__]]
+; CHECK-NEXT: %cmp = icmp eq i32 %[[__THREW__VAL]], 1
+; CHECK-NEXT: br i1 %cmp, label %lpad, label %invoke.cont
 
 invoke.cont:                                      ; preds = %entry
   br label %try.cont
 
 lpad:                                             ; preds = %entry
   %0 = landingpad { i8*, i32 }
           catch i8* bitcast (i8** @_ZTIi to i8*)
           catch i8* null

 
 ; Test invoke instruction with filters (functions with throw(...) declaration)
 define void @filter() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
 ; CHECK-LABEL: @filter(
 entry:
   invoke void @foo(i32 3)
           to label %invoke.cont unwind label %lpad
 ; CHECK: entry:
-; CHECK-NEXT: store i1 false, i1* @[[__THREW__]]
+; CHECK-NEXT: store i32 0, i32* @[[__THREW__]]
 ; CHECK-NEXT: call void @__invoke_void_i32(void (i32)* @foo, i32 3)
-; CHECK-NEXT: %[[__THREW__VAL:.*]] = load i1, i1* @[[__THREW__]]
-; CHECK-NEXT: store i1 false, i1* @[[__THREW__]]
-; CHECK-NEXT: br i1 %[[__THREW__VAL]], label %lpad, label %invoke.cont
+; CHECK-NEXT: %[[__THREW__VAL:.*]] = load i32, i32* @[[__THREW__]]
+; CHECK-NEXT: store i32 0, i32* @[[__THREW__]]
+; CHECK-NEXT: %cmp = icmp eq i32 %[[__THREW__VAL]], 1
+; CHECK-NEXT: br i1 %cmp, label %lpad, label %invoke.cont
 
 invoke.cont:                                      ; preds = %entry
   ret void
 
 lpad:                                             ; preds = %entry
   %0 = landingpad { i8*, i32 }
           filter [2 x i8*] [i8* bitcast (i8** @_ZTIi to i8*), i8* bitcast (i8** @_ZTIc to i8*)]
   %1 = extractvalue { i8*, i32 } %0, 0

 
 ; Test if argument attributes indices in newly created call instructions are correct
 define void @arg_attributes() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
 ; CHECK-LABEL: @arg_attributes(
 entry:
   %0 = invoke noalias i8* @bar(i8 signext 1, i8 zeroext 2)
           to label %invoke.cont unwind label %lpad
 ; CHECK: entry:
-; CHECK-NEXT: store i1 false, i1* @[[__THREW__]]
+; CHECK-NEXT: store i32 0, i32* @[[__THREW__]]
 ; CHECK-NEXT: %0 = call noalias i8* @"__invoke_i8*_i8_i8"(i8* (i8, i8)* @bar, i8 signext 1, i8 zeroext 2)
 
 invoke.cont:                                      ; preds = %entry
   br label %try.cont
 
 lpad:                                             ; preds = %entry
   %1 = landingpad { i8*, i32 }
           catch i8* bitcast (i8** @_ZTIi to i8*)

 declare i8* @bar(i8, i8)
 
 declare i32 @__gxx_personality_v0(...)
 declare i32 @llvm.eh.typeid.for(i8*)
 declare i8* @__cxa_begin_catch(i8*)
 declare void @__cxa_end_catch()
 declare void @__cxa_call_unexpected(i8*)
 
-; JS glue functions and invoke wrappers registration
-; CHECK: declare void @__resumeException(i8*)
-; CHECK: declare void @__invoke_void_i32(void (i32)*, i32)
-; CHECK: declare i8* @__cxa_find_matching_catch_4(i8*, i8*)
+; JS glue functions and invoke wrappers declaration
+; CHECK-DAG: declare void @__resumeException(i8*)
+; CHECK-DAG: declare void @__invoke_void_i32(void (i32)*, i32)
+; CHECK-DAG: declare i8* @__cxa_find_matching_catch_4(i8*, i8*)
 
 ; setThrew function creation
-; CHECK-LABEL: define void @setThrew(i1 %threw, i32 %value) {
+; CHECK-LABEL: define void @setThrew(i32 %threw, i32 %value) {
 ; CHECK: entry:
-; CHECK-NEXT: %[[__THREW__]].val = load i1, i1* @[[__THREW__]]
-; CHECK-NEXT: %cmp = icmp eq i1 %[[__THREW__]].val, false
+; CHECK-NEXT: %[[__THREW__]].val = load i32, i32* @[[__THREW__]]
+; CHECK-NEXT: %cmp = icmp eq i32 %[[__THREW__]].val, 0
 ; CHECK-NEXT: br i1 %cmp, label %if.then, label %if.end
 ; CHECK: if.then:
-; CHECK-NEXT: store i1 %threw, i1* @[[__THREW__]]
+; CHECK-NEXT: store i32 %threw, i32* @[[__THREW__]]
 ; CHECK-NEXT: store i32 %value, i32* @[[THREWVALUE]]
 ; CHECK-NEXT: br label %if.end
 ; CHECK: if.end:
 ; CHECK-NEXT: ret void
 ; CHECK: }
 
 ; setTempRet0 function creation
 ; CHECK-LABEL: define void @setTempRet0(i32 %value) {
 ; CHECK: entry:
 ; CHECK-NEXT: store i32 %value, i32* @[[TEMPRET0]]
 ; CHECK-NEXT: ret void
 ; CHECK: }

test/CodeGen/WebAssembly/lower-em-sjlj.ll

+; RUN: opt < %s -wasm-lower-em-ehsjlj -S | FileCheck %s
+
+target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
+target triple = "wasm32-unknown-unknown"
+
+%struct.__jmp_buf_tag = type { [6 x i32], i32, [32 x i32] }
+
+@global_var = hidden global i32 0, align 4
+; CHECK-DAG: @[[__THREW__:__THREW__.*]] = global i32 0
+; CHECK-DAG: @[[THREWVALUE:__threwValue.*]] = global i32 0
+; CHECK-DAG: @[[TEMPRET0:__tempRet0.*]] = global i32 0
+
+; Test a simple setjmp - longjmp sequence
+define hidden void @setjmp_longjmp() {
+; CHECK-LABEL: @setjmp_longjmp
+entry:
+  %buf = alloca [1 x %struct.__jmp_buf_tag], align 16
+  %arraydecay = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  %call = call i32 @setjmp(%struct.__jmp_buf_tag* %arraydecay) #0
+  %arraydecay1 = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  call void @longjmp(%struct.__jmp_buf_tag* %arraydecay1, i32 1) #1
+  unreachable
+; CHECK: entry:
+; CHECK-NEXT: %[[MALLOCCALL:.*]] = tail call i8* @malloc(i32 40)
+; CHECK-NEXT: %[[SETJMP_TABLE:.*]] = bitcast i8* %[[MALLOCCALL]] to i32*
+; CHECK-NEXT: store i32 0, i32* %[[SETJMP_TABLE]]
+; CHECK-NEXT: %[[SETJMP_TABLE_SIZE:.*]] = add i32 4, 0
+; CHECK-NEXT: %[[BUF:.*]] = alloca [1 x %struct.__jmp_buf_tag]
+; CHECK-NEXT: %[[ARRAYDECAY:.*]] = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %[[BUF]], i32 0, i32 0
+; CHECK-NEXT: %[[SETJMP_TABLE1:.*]] = call i32* @saveSetjmp(%struct.__jmp_buf_tag* %[[ARRAYDECAY]], i32 1, i32* %[[SETJMP_TABLE]], i32 %[[SETJMP_TABLE_SIZE]])
+; CHECK-NEXT: %[[SETJMP_TABLE_SIZE1:.*]] = load i32, i32* @[[TEMPRET0]]
+; CHECK-NEXT: br label %entry.split
+
+; CHECK: entry.split:
+; CHECK-NEXT: phi i32 [ 0, %entry ], [ %[[LONGJMP_RESULT:.*]], %if.end ]
+; CHECK-NEXT: %[[ARRAYDECAY1:.*]] = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %[[BUF]], i32 0, i32 0
+; CHECK-NEXT: store i32 0, i32* @[[__THREW__]]
+; CHECK-NEXT: call void @"__invoke_void_%struct.__jmp_buf_tag*_i32"(void (%struct.__jmp_buf_tag*, i32)* @emscripten_longjmp_jmpbuf, %struct.__jmp_buf_tag* %[[ARRAYDECAY1]], i32 1)
+; CHECK-NEXT: %[[__THREW__VAL:.*]] = load i32, i32* @[[__THREW__]]
+; CHECK-NEXT: store i32 0, i32* @[[__THREW__]]
+; CHECK-NEXT: %[[CMP0:.*]] = icmp ne i32 %__THREW__.val, 0
+; CHECK-NEXT: %[[THREWVALUE_VAL:.*]] = load i32, i32* @[[THREWVALUE]]
+; CHECK-NEXT: %[[CMP1:.*]] = icmp ne i32 %[[THREWVALUE_VAL]], 0
+; CHECK-NEXT: %[[CMP:.*]] = and i1 %[[CMP0]], %[[CMP1]]
+; CHECK-NEXT: br i1 %[[CMP]], label %if.then1, label %if.else1
+
+; CHECK: entry.split.split:
+; CHECK-NEXT: unreachable
+
+; CHECK: if.then1:
+; CHECK-NEXT: %[[__THREW__VAL_I32P:.*]] = inttoptr i32 %[[__THREW__VAL]] to i32*
+; CHECK-NEXT: %[[__THREW__VAL_I32P_LOADED:.*]] = load i32, i32* %[[__THREW__VAL_I32P]]
+; CHECK-NEXT: %[[LABEL:.*]] = call i32 @testSetjmp(i32 %[[__THREW__VAL_I32P_LOADED]], i32* %[[SETJMP_TABLE1]], i32 %[[SETJMP_TABLE_SIZE1]])
+; CHECK-NEXT: %[[CMP:.*]] = icmp eq i32 %[[LABEL]], 0
+; CHECK-NEXT: br i1 %[[CMP]], label %if.then2, label %if.end2
+
+; CHECK: if.else1:
+; CHECK-NEXT: br label %if.end
+
+; CHECK: if.end:
+; CHECK-NEXT: %[[LABEL_PHI:.*]] = phi i32 [ %[[LABEL:.*]], %if.end2 ], [ -1, %if.else1 ]
+; CHECK-NEXT: %[[LONGJMP_RESULT]] = load i32, i32* @[[TEMPRET0]]
+; CHECK-NEXT: switch i32 %[[LABEL_PHI]], label %entry.split.split [
+; CHECK-NEXT:   i32 1, label %entry.split
+; CHECK-NEXT: ]
+
+; CHECK: if.then2:
+; CHECK-NEXT: call void @emscripten_longjmp(i32 %[[__THREW__VAL]], i32 %[[THREWVALUE_VAL]])
+; CHECK-NEXT: unreachable
+
+; CHECK: if.end2:
+; CHECK-NEXT: store i32 %[[THREWVALUE_VAL]], i32* @[[TEMPRET0]]
+; CHECK-NEXT: br label %if.end
+}
+
+; Test a case of a function call (which is not longjmp) after a setjmp
+define hidden void @setjmp_other() {
+; CHECK-LABEL: @setjmp_other
+entry:
+  %buf = alloca [1 x %struct.__jmp_buf_tag], align 16
+  %arraydecay = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  %call = call i32 @setjmp(%struct.__jmp_buf_tag* %arraydecay) #0
+  call void @foo()
+  ret void
+; CHECK: entry:
+; CHECK: %[[SETJMP_TABLE:.*]] = call i32* @saveSetjmp(
+
+; CHECK: entry.split:
+; CHECK: call void @__invoke_void(void ()* @foo)
+
+; CHECK: entry.split.split:
+; CHECK-NEXT: %[[BUF:.*]] = bitcast i32* %[[SETJMP_TABLE]] to i8*
+; CHECK-NEXT: tail call void @free(i8* %[[BUF]])
+; CHECK-NEXT: ret void
+}
+
+; Test a case when a function call is within try-catch, after a setjmp
+define hidden void @exception_and_longjmp() #3 personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+; CHECK-LABEL: @exception_and_longjmp
+entry:
+  %buf = alloca [1 x %struct.__jmp_buf_tag], align 16
+  %arraydecay = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  %call = call i32 @setjmp(%struct.__jmp_buf_tag* %arraydecay) #0
+  invoke void @foo()
+          to label %try.cont unwind label %lpad
+
+; CHECK: entry.split:
+; CHECK: store i32 0, i32* @[[__THREW__]]
+; CHECK-NEXT: call void @__invoke_void(void ()* @foo)
+; CHECK-NEXT: %[[__THREW__VAL:.*]] = load i32, i32* @[[__THREW__]]
+; CHECK-NEXT: store i32 0, i32* @[[__THREW__]]
+; CHECK-NEXT: %[[CMP0:.*]] = icmp ne i32 %[[__THREW__VAL]], 0
+; CHECK-NEXT: %[[THREWVALUE_VAL:.*]] = load i32, i32* @[[THREWVALUE]]
+; CHECK-NEXT: %[[CMP1:.*]] = icmp ne i32 %[[THREWVALUE_VAL]], 0
+; CHECK-NEXT: %[[CMP:.*]] = and i1 %[[CMP0]], %[[CMP1]]
+; CHECK-NEXT: br i1 %[[CMP]], label %if.then1, label %if.else1
+
+; CHECK: entry.split.split:
+; CHECK-NEXT: %[[CMP:.*]] = icmp eq i32 %[[__THREW__VAL]], 1
+; CHECK-NEXT: br i1 %[[CMP]], label %lpad, label %try.cont
+
+lpad:                                             ; preds = %entry
+  %0 = landingpad { i8*, i32 }
+          catch i8* null
+  %1 = extractvalue { i8*, i32 } %0, 0
+  %2 = extractvalue { i8*, i32 } %0, 1
+  %3 = call i8* @__cxa_begin_catch(i8* %1) #2
+  call void @__cxa_end_catch()
+  br label %try.cont
+
+try.cont:                                         ; preds = %entry, %lpad
+  ret void
+}
+
+; Test SSA validity
+define hidden void @ssa(i32 %n) {
+; CHECK-LABEL: @ssa
+entry:
+  %buf = alloca [1 x %struct.__jmp_buf_tag], align 16
+  %cmp = icmp sgt i32 %n, 5
+  br i1 %cmp, label %if.then, label %if.end
+; CHECK: entry:
+; CHECK: %[[SETJMP_TABLE0:.*]] = bitcast i8*
+; CHECK: %[[SETJMP_TABLE_SIZE0:.*]] = add i32 4, 0
+
+if.then:                                          ; preds = %entry
+  %0 = load i32, i32* @global_var, align 4
+  %arraydecay = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  %call = call i32 @setjmp(%struct.__jmp_buf_tag* %arraydecay) #0
+  store i32 %0, i32* @global_var, align 4
+  br label %if.end
+; CHECK: if.then:
+; CHECK: %[[VAR0:.*]] = load i32, i32* @global_var, align 4
+; CHECK: %[[SETJMP_TABLE1:.*]] = call i32* @saveSetjmp(
+; CHECK-NEXT: %[[SETJMP_TABLE_SIZE1:.*]] = load i32, i32* @[[TEMPRET0]]
+
+; CHECK: if.then.split:
+; CHECK: %[[VAR1:.*]] = phi i32 [ %[[VAR0]], %if.then ], [ %[[VAR2:.*]], %if.end3 ]
+; CHECK: %[[SETJMP_TABLE_SIZE2:.*]] = phi i32 [ %[[SETJMP_TABLE_SIZE1]], %if.then ], [ %[[SETJMP_TABLE_SIZE3:.*]], %if.end3 ]
+; CHECK: %[[SETJMP_TABLE2:.*]] = phi i32* [ %[[SETJMP_TABLE1]], %if.then ], [ %[[SETJMP_TABLE3:.*]], %if.end3 ]
+; CHECK: store i32 %[[VAR1]], i32* @global_var, align 4
+
+if.end:                                           ; preds = %if.then, %entry
+  %arraydecay1 = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  call void @longjmp(%struct.__jmp_buf_tag* %arraydecay1, i32 5) #1
+  unreachable
+; CHECK: if.end:
+; CHECK: %[[VAR2]] = phi i32 [ %[[VAR1]], %if.then.split ], [ undef, %entry ]
+; CHECK: %[[SETJMP_TABLE_SIZE3]] = phi i32 [ %[[SETJMP_TABLE_SIZE2]], %if.then.split ], [ %[[SETJMP_TABLE_SIZE0]], %entry ]
+; CHECK: %[[SETJMP_TABLE3]] = phi i32* [ %[[SETJMP_TABLE2]], %if.then.split ], [ %[[SETJMP_TABLE0]], %entry ]
+}
+
+; Test a case when a function only calls other functions that are neither setjmp nor longjmp
+define hidden void @only_other_func() {
+entry:
+  call void @foo()
+  ret void
+; CHECK: call void @foo()
+}
+
+; Test a case when a function only calls longjmp and not setjmp
+define hidden void @only_longjmp() {
+entry:
+  %buf = alloca [1 x %struct.__jmp_buf_tag], align 16
+  %arraydecay = getelementptr inbounds [1 x %struct.__jmp_buf_tag], [1 x %struct.__jmp_buf_tag]* %buf, i32 0, i32 0
+  call void @longjmp(%struct.__jmp_buf_tag* %arraydecay, i32 5) #1
+  unreachable
+; CHECK: %[[ARRAYDECAY:.*]] = getelementptr inbounds
+; CHECK-NEXT: call void @emscripten_longjmp_jmpbuf(%struct.__jmp_buf_tag* %[[ARRAYDECAY]], i32 5) #1
+}
+
+declare void @foo()
+; Function Attrs: returns_twice
+declare i32 @setjmp(%struct.__jmp_buf_tag*) #0
+; Function Attrs: noreturn
+declare void @longjmp(%struct.__jmp_buf_tag*, i32) #1
+declare i32 @__gxx_personality_v0(...)
+declare i8* @__cxa_begin_catch(i8*)
+declare void @__cxa_end_catch()
+declare i8* @malloc(i32)
+declare void @free(i8*)
+
+; JS glue functions and invoke wrappers declaration
+; CHECK-DAG: declare i32* @saveSetjmp(%struct.__jmp_buf_tag*, i32, i32*, i32)
+; CHECK-DAG: declare i32 @testSetjmp(i32, i32*, i32)
+; CHECK-DAG: declare void @emscripten_longjmp_jmpbuf(%struct.__jmp_buf_tag*, i32)
+; CHECK-DAG: declare void @emscripten_longjmp(i32, i32)
+; CHECK-DAG: declare void @__invoke_void(void ()*)
+; CHECK-DAG: declare void @"__invoke_void_%struct.__jmp_buf_tag*_i32"(void (%struct.__jmp_buf_tag*, i32)*, %struct.__jmp_buf_tag*, i32)
+
+attributes #0 = { returns_twice }
+attributes #1 = { noreturn }
+attributes #2 = { nounwind }