Conditionalize use of POSIX features missing on WASI/WebAssembly.

whitequark · whitequark · commit 69bd8547e9cc · 2024-07-14T14:02:51.000+01:00
This patch makes it possible to build LLVM, Clang, and LLD for
WASI/WebAssembly. This patch introduces conditionals of the form
`defined(__wasi__)` or `defined(__wasm__)` wherever necessary to detect
the use of the WASI platform. In addition, it introduces a `HAVE_SETJMP`
feature test macro because the WASI platform can have or lack support
for this feature depending on compiler options.
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
@@ -1578,7 +1578,7 @@ bool Driver::getCrashDiagnosticFile(StringRef ReproCrashFilename,
     CrashDiagDir = "/";
   path::append(CrashDiagDir, "Library/Logs/DiagnosticReports");
   int PID =
-#if LLVM_ON_UNIX
+#if LLVM_ON_UNIX && !defined(__wasi__)
       getpid();
 #else
       0;
diff --git a/lld/Common/Filesystem.cpp b/lld/Common/Filesystem.cpp
@@ -45,8 +45,11 @@ void lld::unlinkAsync(StringRef path) {
   if (!sys::fs::exists(path) || !sys::fs::is_regular_file(path))
     return;
 
+// If threads are disabled, remove the file synchronously.
+#if !LLVM_ENABLE_THREADS
+  sys::fs::remove(path);
 // Removing a file is async on windows.
-#if defined(_WIN32)
+#elif defined(_WIN32)
   // On Windows co-operative programs can be expected to open LLD's
   // output in FILE_SHARE_DELETE mode. This allows us to delete the
   // file (by moving it to a temporary filename and then deleting
diff --git a/llvm/cmake/config-ix.cmake b/llvm/cmake/config-ix.cmake
@@ -300,6 +300,7 @@ check_symbol_exists(getrlimit "sys/types.h;sys/time.h;sys/resource.h" HAVE_GETRL
 check_symbol_exists(posix_spawn spawn.h HAVE_POSIX_SPAWN)
 check_symbol_exists(pread unistd.h HAVE_PREAD)
 check_symbol_exists(sbrk unistd.h HAVE_SBRK)
+check_symbol_exists(setjmp setjmp.h HAVE_SETJMP)
 check_symbol_exists(strerror_r string.h HAVE_STRERROR_R)
 check_symbol_exists(strerror_s string.h HAVE_DECL_STRERROR_S)
 check_symbol_exists(setenv stdlib.h HAVE_SETENV)
diff --git a/llvm/cmake/modules/HandleLLVMOptions.cmake b/llvm/cmake/modules/HandleLLVMOptions.cmake
@@ -217,6 +217,10 @@ elseif(FUCHSIA OR UNIX)
   else()
     set(LLVM_HAVE_LINK_VERSION_SCRIPT 1)
   endif()
+elseif(WASI)
+  set(LLVM_ON_WIN32 0)
+  set(LLVM_ON_UNIX 1)
+  set(LLVM_HAVE_LINK_VERSION_SCRIPT 0)
 elseif(CMAKE_SYSTEM_NAME STREQUAL "Generic")
   set(LLVM_ON_WIN32 0)
   set(LLVM_ON_UNIX 0)
diff --git a/llvm/include/llvm/ADT/bit.h b/llvm/include/llvm/ADT/bit.h
@@ -29,7 +29,7 @@
 
 #if defined(__linux__) || defined(__GNU__) || defined(__HAIKU__) ||            \
     defined(__Fuchsia__) || defined(__EMSCRIPTEN__) || defined(__NetBSD__) ||  \
-    defined(__OpenBSD__) || defined(__DragonFly__)
+    defined(__OpenBSD__) || defined(__DragonFly__) || defined(__wasm__)
 #include <endian.h>
 #elif defined(_AIX)
 #include <sys/machine.h>
diff --git a/llvm/include/llvm/Config/config.h.cmake b/llvm/include/llvm/Config/config.h.cmake
@@ -164,6 +164,10 @@
 /* Define to 1 if you have the `sbrk' function. */
 #cmakedefine HAVE_SBRK ${HAVE_SBRK}
 
+/* Define to 1 if you have the `setjmp' function. */
+/* This function is expected to be present everywhere except for a subset of WebAssembly builds. */
+#cmakedefine HAVE_SETJMP ${HAVE_SETJMP}
+
 /* Define to 1 if you have the `setenv' function. */
 #cmakedefine HAVE_SETENV ${HAVE_SETENV}
 
diff --git a/llvm/lib/ExecutionEngine/Interpreter/ExternalFunctions.cpp b/llvm/lib/ExecutionEngine/Interpreter/ExternalFunctions.cpp
@@ -34,7 +34,9 @@
 #include "llvm/Support/raw_ostream.h"
 #include <cassert>
 #include <cmath>
+#if !defined(__wasi__)
 #include <csignal>
+#endif
 #include <cstdint>
 #include <cstdio>
 #include <cstring>
@@ -340,7 +342,11 @@ static GenericValue lle_X_exit(FunctionType *FT, ArrayRef<GenericValue> Args) {
 static GenericValue lle_X_abort(FunctionType *FT, ArrayRef<GenericValue> Args) {
   //FIXME: should we report or raise here?
   //report_fatal_error("Interpreted program raised SIGABRT");
+#if defined(__wasi__)
+  abort();
+#else
   raise (SIGABRT);
+#endif
   return GenericValue();
 }
 
diff --git a/llvm/lib/Support/CrashRecoveryContext.cpp b/llvm/lib/Support/CrashRecoveryContext.cpp
@@ -13,8 +13,17 @@
 #include "llvm/Support/Signals.h"
 #include "llvm/Support/thread.h"
 #include <cassert>
+#if !defined(__wasi__)
+#include <csignal>
+#endif
+#if LLVM_ENABLE_THREADS
 #include <mutex>
+#endif
+#if HAVE_SETJMP
+// We can rely on setjmp to exist everywhere except for a subset of WebAssembly
+// builds.
 #include <setjmp.h>
+#endif
 
 using namespace llvm;
 
@@ -31,7 +40,9 @@ struct CrashRecoveryContextImpl {
   const CrashRecoveryContextImpl *Next;
 
   CrashRecoveryContext *CRC;
+#ifdef HAVE_SETJMP
   ::jmp_buf JumpBuffer;
+#endif
   volatile unsigned Failed : 1;
   unsigned SwitchedThread : 1;
   unsigned ValidJumpBuffer : 1;
@@ -50,7 +61,7 @@ struct CrashRecoveryContextImpl {
   /// Called when the separate crash-recovery thread was finished, to
   /// indicate that we don't need to clear the thread-local CurrentContext.
   void setSwitchedThread() {
-#if defined(LLVM_ENABLE_THREADS) && LLVM_ENABLE_THREADS != 0
+#if LLVM_ENABLE_THREADS
     SwitchedThread = true;
 #endif
   }
@@ -72,19 +83,23 @@ struct CrashRecoveryContextImpl {
 
     CRC->RetCode = RetCode;
 
+#if HAVE_SETJMP
     // Jump back to the RunSafely we were called under.
     if (ValidJumpBuffer)
       longjmp(JumpBuffer, 1);
+#endif
 
     // Otherwise let the caller decide of the outcome of the crash. Currently
     // this occurs when using SEH on Windows with MSVC or clang-cl.
   }
 };
 
-std::mutex &getCrashRecoveryContextMutex() {
+#if LLVM_ENABLE_THREADS
+static std::mutex &getCrashRecoveryContextMutex() {
   static std::mutex CrashRecoveryContextMutex;
   return CrashRecoveryContextMutex;
 }
+#endif
 
 static bool gCrashRecoveryEnabled = false;
 
@@ -138,7 +153,9 @@ CrashRecoveryContext *CrashRecoveryContext::GetCurrent() {
 }
 
 void CrashRecoveryContext::Enable() {
+#if LLVM_ENABLE_THREADS
   std::lock_guard<std::mutex> L(getCrashRecoveryContextMutex());
+#endif
   // FIXME: Shouldn't this be a refcount or something?
   if (gCrashRecoveryEnabled)
     return;
@@ -147,7 +164,9 @@ void CrashRecoveryContext::Enable() {
 }
 
 void CrashRecoveryContext::Disable() {
+#if LLVM_ENABLE_THREADS
   std::lock_guard<std::mutex> L(getCrashRecoveryContextMutex());
+#endif
   if (!gCrashRecoveryEnabled)
     return;
   gCrashRecoveryEnabled = false;
@@ -329,7 +348,16 @@ static void uninstallExceptionOrSignalHandlers() {
   }
 }
 
-#else // !_WIN32
+#elif defined(__wasi__)
+
+// WASI implementation.
+//
+// WASI traps are always fatal, and recovery is not possible. Do nothing.
+
+static void installExceptionOrSignalHandlers() {}
+static void uninstallExceptionOrSignalHandlers() {}
+
+#else // !_WIN32 && !__wasi__
 
 // Generic POSIX implementation.
 //
@@ -417,10 +445,12 @@ bool CrashRecoveryContext::RunSafely(function_ref<void()> Fn) {
     CrashRecoveryContextImpl *CRCI = new CrashRecoveryContextImpl(this);
     Impl = CRCI;
 
+#if HAVE_SETJMP
     CRCI->ValidJumpBuffer = true;
     if (setjmp(CRCI->JumpBuffer) != 0) {
       return false;
     }
+#endif
   }
 
   Fn();
@@ -467,7 +497,9 @@ bool CrashRecoveryContext::isCrash(int RetCode) {
 bool CrashRecoveryContext::throwIfCrash(int RetCode) {
   if (!isCrash(RetCode))
     return false;
-#if defined(_WIN32)
+#if defined(__wasi__)
+  abort();
+#elif defined(_WIN32)
   ::RaiseException(RetCode, 0, 0, NULL);
 #else
   llvm::sys::unregisterHandlers();
diff --git a/llvm/lib/Support/InitLLVM.cpp b/llvm/lib/Support/InitLLVM.cpp
@@ -47,6 +47,7 @@ InitLLVM::InitLLVM(int &Argc, const char **&Argv,
   // Bring stdin/stdout/stderr into a known state.
   sys::AddSignalHandler(CleanupStdHandles, nullptr);
 #endif
+#if !defined(__wasi__)
   if (InstallPipeSignalExitHandler)
     // The pipe signal handler must be installed before any other handlers are
     // registered. This is because the Unix \ref RegisterHandlers function does
@@ -59,6 +60,7 @@ InitLLVM::InitLLVM(int &Argc, const char **&Argv,
   StackPrinter.emplace(Argc, Argv);
   sys::PrintStackTraceOnErrorSignal(Argv[0]);
   install_out_of_memory_new_handler();
+#endif
 
 #ifdef __MVS__
 
diff --git a/llvm/lib/Support/LockFileManager.cpp b/llvm/lib/Support/LockFileManager.cpp
@@ -94,7 +94,7 @@ static std::error_code getHostID(SmallVectorImpl<char> &HostID) {
   StringRef UUIDRef(UUIDStr);
   HostID.append(UUIDRef.begin(), UUIDRef.end());
 
-#elif LLVM_ON_UNIX
+#elif !defined(__wasi__)
   char HostName[256];
   HostName[255] = 0;
   HostName[0] = 0;
@@ -111,7 +111,7 @@ static std::error_code getHostID(SmallVectorImpl<char> &HostID) {
 }
 
 bool LockFileManager::processStillExecuting(StringRef HostID, int PID) {
-#if LLVM_ON_UNIX && !defined(__ANDROID__)
+#if LLVM_ON_UNIX && !defined(__ANDROID__) && !defined(__wasi__)
   SmallString<256> StoredHostID;
   if (getHostID(StoredHostID))
     return true; // Conservatively assume it's executing on error.
diff --git a/llvm/lib/Support/Signals.cpp b/llvm/lib/Support/Signals.cpp
@@ -273,9 +273,19 @@ static bool printMarkupStackTrace(StringRef Argv0, void **StackTrace, int Depth,
 }
 
 // Include the platform-specific parts of this class.
-#ifdef LLVM_ON_UNIX
+#if defined(__wasi__)
+// WASI does not have signals.
+void llvm::sys::AddSignalHandler(sys::SignalHandlerCallback FnPtr,
+                                 void *Cookie) {}
+void llvm::sys::RunInterruptHandlers() {}
+void sys::CleanupOnSignal(uintptr_t Context) {}
+bool llvm::sys::RemoveFileOnSignal(StringRef Filename, std::string *ErrMsg) {
+  return false;
+}
+void llvm::sys::DontRemoveFileOnSignal(StringRef Filename) {}
+void llvm::sys::DisableSystemDialogsOnCrash() {}
+#elif defined(LLVM_ON_UNIX)
 #include "Unix/Signals.inc"
-#endif
-#ifdef _WIN32
+#elif defined(_WIN32)
 #include "Windows/Signals.inc"
 #endif
diff --git a/llvm/lib/Support/Unix/Memory.inc b/llvm/lib/Support/Unix/Memory.inc
@@ -163,6 +163,11 @@ std::error_code Memory::releaseMappedMemory(MemoryBlock &M) {
 
 std::error_code Memory::protectMappedMemory(const MemoryBlock &M,
                                             unsigned Flags) {
+#if defined(__wasi__)
+  // Wasm does not allow making memory read-only or executable.
+  return std::error_code(ENOSYS, std::generic_category());
+#endif
+
   static const Align PageSize = Align(Process::getPageSizeEstimate());
   if (M.Address == nullptr || M.AllocatedSize == 0)
     return std::error_code();
diff --git a/llvm/lib/Support/Unix/Path.inc b/llvm/lib/Support/Unix/Path.inc
diff --git a/llvm/lib/Support/Unix/Process.inc b/llvm/lib/Support/Unix/Process.inc
diff --git a/llvm/lib/Support/Unix/Program.inc b/llvm/lib/Support/Unix/Program.inc
diff --git a/llvm/lib/Support/Unix/Unix.h b/llvm/lib/Support/Unix/Unix.h
diff --git a/llvm/lib/Support/Unix/Watchdog.inc b/llvm/lib/Support/Unix/Watchdog.inc
diff --git a/llvm/lib/Support/raw_socket_stream.cpp b/llvm/lib/Support/raw_socket_stream.cpp
