Conditionalize use of POSIX features missing on WASI/WebAssembly.

This patch is the first in a series that makes it possible to build
LLVM, Clang, and LLD for WASI/WebAssembly. This patch does not introduce
conditionals of the form `defined(__wasi__)` or `defined(__wasm__)`;
instead it detects these APIs like any other platform features. While
some features are never present in WASI and the feature check is
functionally identical to a platform check, some may be conditionally
present if emulation is turned on, e.g. `getpid`.

The complete list of feature tests introduced is:
* `HAVE_ALARM`: WebAssembly does not support delivery of asynchronous
  signals.
* `HAVE_GETHOSTNAME`: WASI does not provide `gethostname`.
* `HAVE_GETPID`: WASI does not have process IDs. However, it ships
  with a polyfill (`-D_WASI_EMULATED_GETPID`). The final behavior is
  the same either way.
* `HAVE_FCHOWN`: WASI likely will never support UNIX ownership model.
* `HAVE_FLOCK`: WASI likely will never support POSIX advisory locking.
* `HAVE_PWD_H`: WASI likely will never support UNIX password databases.
* `HAVE_RAISE`: WASI does not support delivery of asynchronous signals.
  However, it ships with a polyfill (`-D_WASI_EMULATED_SIGNAL`).
  This polyfill implements `raise` but not `sigaction` (only `signal`)
  and as a result it is not currently useful for LLVM. If `sigaction`
  is implemented in wasi-libc then `raise(SIGABRT);` would be able to
  invoke the handler.
* `HAVE_SETJMP`: WebAssembly implements SjLj using exception handling.
  Exception handling has not been stabilized in Wasm yet. In addition,
  it significantly increases deployment complexity. Building with
  `-mllvm -wasm-enable-sjlj` enables the use of SjLj.
* `HAVE_SOCKET`: WASIp1 does not provide the Berkeley socket API.
  WASIp2 does provide it. It will likely remain desirable to target
  WASIp1 for a long time.
* `HAVE_SYS_WAIT_H`: WASI does not have subprocess management.
* `HAVE_UMASK`: WASI likely will never support UNIX permission model,
  but `umask` might eventually be added in a polyfill.

Of these, only `HAVE_FLOCK` requires a custom compile test:

    #include <sys/file.h>
    struct flock lk;
    int main(void) { return 0; }

clang/lib/Driver/Driver.cpp

@@ -99,8 +99,8 @@
 #include <optional>
 #include <set>
 #include <utility>
-#if LLVM_ON_UNIX
-#include <unistd.h> // getpid
+#if HAVE_GETPID
+#include <unistd.h>
 #endif
 
 using namespace clang::driver;
@@ -1577,7 +1577,7 @@ bool Driver::getCrashDiagnosticFile(StringRef ReproCrashFilename,
     CrashDiagDir = "/";
   path::append(CrashDiagDir, "Library/Logs/DiagnosticReports");
   int PID =
-#if LLVM_ON_UNIX
+#if HAVE_GETPID
       getpid();
 #else
       0;

llvm/cmake/config-ix.cmake

@@ -49,6 +49,7 @@ check_include_file(malloc/malloc.h HAVE_MALLOC_MALLOC_H)
 if( NOT PURE_WINDOWS )
   check_include_file(pthread.h HAVE_PTHREAD_H)
 endif()
+check_include_file(pwd.h HAVE_PWD_H)
 check_include_file(signal.h HAVE_SIGNAL_H)
 check_include_file(sys/ioctl.h HAVE_SYS_IOCTL_H)
 check_include_file(sys/mman.h HAVE_SYS_MMAN_H)
@@ -57,6 +58,7 @@ check_include_file(sys/resource.h HAVE_SYS_RESOURCE_H)
 check_include_file(sys/stat.h HAVE_SYS_STAT_H)
 check_include_file(sys/time.h HAVE_SYS_TIME_H)
 check_include_file(sys/types.h HAVE_SYS_TYPES_H)
+check_include_file(sys/wait.h HAVE_SYS_WAIT_H)
 check_include_file(sysexits.h HAVE_SYSEXITS_H)
 check_include_file(termios.h HAVE_TERMIOS_H)
 check_include_file(unistd.h HAVE_UNISTD_H)
@@ -276,11 +278,15 @@ check_symbol_exists(__deregister_frame "${CMAKE_CURRENT_LIST_DIR}/unwind.h" HAVE
 check_symbol_exists(__unw_add_dynamic_fde "${CMAKE_CURRENT_LIST_DIR}/unwind.h" HAVE_UNW_ADD_DYNAMIC_FDE)
 
 check_symbol_exists(_Unwind_Backtrace "unwind.h" HAVE__UNWIND_BACKTRACE)
+check_symbol_exists(alarm unistd.h HAVE_ALARM)
+check_symbol_exists(gethostname unistd.h HAVE_GETHOSTNAME)
 check_symbol_exists(getpagesize unistd.h HAVE_GETPAGESIZE)
+check_symbol_exists(getpid unistd.h HAVE_GETPID)
 check_symbol_exists(sysconf unistd.h HAVE_SYSCONF)
 check_symbol_exists(getrusage sys/resource.h HAVE_GETRUSAGE)
 check_symbol_exists(setrlimit sys/resource.h HAVE_SETRLIMIT)
 check_symbol_exists(isatty unistd.h HAVE_ISATTY)
+check_symbol_exists(fchown unistd.h HAVE_FCHOWN)
 check_symbol_exists(futimens sys/stat.h HAVE_FUTIMENS)
 check_symbol_exists(futimes sys/time.h HAVE_FUTIMES)
 # AddressSanitizer conflicts with lib/Support/Unix/Signals.inc
@@ -298,10 +304,14 @@ check_symbol_exists(malloc_zone_statistics malloc/malloc.h
 check_symbol_exists(getrlimit "sys/types.h;sys/time.h;sys/resource.h" HAVE_GETRLIMIT)
 check_symbol_exists(posix_spawn spawn.h HAVE_POSIX_SPAWN)
 check_symbol_exists(pread unistd.h HAVE_PREAD)
+check_symbol_exists(raise signal.h HAVE_RAISE)
 check_symbol_exists(sbrk unistd.h HAVE_SBRK)
+check_symbol_exists(setjmp setjmp.h HAVE_SETJMP)
+check_symbol_exists(socket sys/socket.h HAVE_SOCKET)
 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)
+check_symbol_exists(umask sys/stat.h HAVE_UMASK)
 if( PURE_WINDOWS )
   check_symbol_exists(_chsize_s io.h HAVE__CHSIZE_S)
 
@@ -327,6 +337,12 @@ if( PURE_WINDOWS )
   check_function_exists(__cmpdi2 HAVE___CMPDI2)
 endif()
 
+check_c_source_compiles("
+        #include <sys/file.h>
+        struct flock lk;
+        int main(void) { return 0; }"
+        HAVE_FLOCK)
+
 CHECK_STRUCT_HAS_MEMBER("struct stat" st_mtimespec.tv_nsec
     "sys/types.h;sys/stat.h" HAVE_STRUCT_STAT_ST_MTIMESPEC_TV_NSEC)
 if (UNIX AND ${CMAKE_SYSTEM_NAME} MATCHES "AIX")

llvm/include/llvm/Config/config.h.cmake

@@ -23,6 +23,9 @@
    backslashes. */
 #cmakedefine01 LLVM_WINDOWS_PREFER_FORWARD_SLASH
 
+/* Define to 1 if you have the `alarm' function. */
+#cmakedefine HAVE_ALARM ${HAVE_ALARM}
+
 /* Define to 1 if you have the `backtrace' function. */
 #cmakedefine HAVE_BACKTRACE ${HAVE_BACKTRACE}
 
@@ -71,6 +74,12 @@
 /* Define to 1 if you have the <errno.h> header file. */
 #cmakedefine HAVE_ERRNO_H ${HAVE_ERRNO_H}
 
+/* Define to 1 if you have the `flock' structure. */
+#cmakedefine HAVE_FLOCK ${HAVE_FLOCK}
+
+/* Define to 1 if you have the `fchown' function. */
+#cmakedefine HAVE_FCHOWN ${HAVE_FCHOWN}
+
 /* Define to 1 if you have the <fcntl.h> header file. */
 #cmakedefine HAVE_FCNTL_H ${HAVE_FCNTL_H}
 
@@ -92,9 +101,15 @@
 /* Define to 1 if you have the `futimes' function. */
 #cmakedefine HAVE_FUTIMES ${HAVE_FUTIMES}
 
+/* Define to 1 if you have the `gethostname' function. */
+#cmakedefine HAVE_GETHOSTNAME ${HAVE_GETHOSTNAME}
+
 /* Define to 1 if you have the `getpagesize' function. */
 #cmakedefine HAVE_GETPAGESIZE ${HAVE_GETPAGESIZE}
 
+/* Define to 1 if you have the `getpid' function. */
+#cmakedefine HAVE_GETPID ${HAVE_GETPID}
+
 /* Define to 1 if you have the `getrlimit' function. */
 #cmakedefine HAVE_GETRLIMIT ${HAVE_GETRLIMIT}
 
@@ -161,9 +176,21 @@
 /* Have pthread_rwlock_init */
 #cmakedefine HAVE_PTHREAD_RWLOCK_INIT ${HAVE_PTHREAD_RWLOCK_INIT}
 
+/* Define to 1 if you have the <pwd.h> header file. */
+#cmakedefine HAVE_PWD_H ${HAVE_PWD_H}
+
+/* Define to 1 if you have the `raise' function. */
+#cmakedefine HAVE_RAISE ${HAVE_RAISE}
+
 /* Define to 1 if you have the `sbrk' function. */
 #cmakedefine HAVE_SBRK ${HAVE_SBRK}
 
+/* Define to 1 if you have the `setjmp' function. */
+#cmakedefine HAVE_SETJMP ${HAVE_SETJMP}
+
+/* Define to 1 if you have the `socket' function. */
+#cmakedefine HAVE_SOCKET ${HAVE_SOCKET}
+
 /* Define to 1 if you have the `setenv' function. */
 #cmakedefine HAVE_SETENV ${HAVE_SETENV}
 
@@ -209,12 +236,18 @@
 /* Define to 1 if you have the <sys/types.h> header file. */
 #cmakedefine HAVE_SYS_TYPES_H ${HAVE_SYS_TYPES_H}
 
+/* Define to 1 if you have the <sys/wait.h> header file. */
+#cmakedefine HAVE_SYS_WAIT_H ${HAVE_SYS_WAIT_H}
+
 /* Define if the setupterm() function is supported this platform. */
 #cmakedefine LLVM_ENABLE_TERMINFO ${LLVM_ENABLE_TERMINFO}
 
 /* Define to 1 if you have the <termios.h> header file. */
 #cmakedefine HAVE_TERMIOS_H ${HAVE_TERMIOS_H}
 
+/* Define to 1 if you have the `umask' function. */
+#cmakedefine HAVE_UMASK ${HAVE_UMASK}
+
 /* Define to 1 if you have the <unistd.h> header file. */
 #cmakedefine HAVE_UNISTD_H ${HAVE_UNISTD_H}
 

llvm/lib/ExecutionEngine/Interpreter/ExternalFunctions.cpp

@@ -34,7 +34,9 @@
 #include "llvm/Support/raw_ostream.h"
 #include <cassert>
 #include <cmath>
+#if HAVE_RAISE
 #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 HAVE_RAISE
   raise (SIGABRT);
+#else
+  abort();
+#endif
   return GenericValue();
 }
 

llvm/lib/Support/CrashRecoveryContext.cpp

@@ -13,8 +13,13 @@
 #include "llvm/Support/Signals.h"
 #include "llvm/Support/thread.h"
 #include <cassert>
+#if HAVE_RAISE
+#include <csignal>
+#endif
 #include <mutex>
+#if HAVE_SETJMP
 #include <setjmp.h>
+#endif
 
 using namespace llvm;
 
@@ -31,7 +36,9 @@ struct CrashRecoveryContextImpl {
   const CrashRecoveryContextImpl *Next;
 
   CrashRecoveryContext *CRC;
+#ifdef HAVE_SETJMP
   ::jmp_buf JumpBuffer;
+#endif
   volatile unsigned Failed : 1;
   unsigned SwitchedThread : 1;
   unsigned ValidJumpBuffer : 1;
@@ -72,9 +79,11 @@ 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.
@@ -417,10 +426,12 @@ 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();
@@ -469,9 +480,11 @@ bool CrashRecoveryContext::throwIfCrash(int RetCode) {
     return false;
 #if defined(_WIN32)
   ::RaiseException(RetCode, 0, 0, NULL);
-#else
+#elif HAVE_RAISE
   llvm::sys::unregisterHandlers();
   raise(RetCode - 128);
+#else
+  abort();
 #endif
   return true;
 }

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 HAVE_GETHOSTNAME
   char HostName[256];
   HostName[255] = 0;
   HostName[0] = 0;

llvm/lib/Support/Unix/Path.inc

@@ -32,7 +32,9 @@
 #endif
 
 #include <dirent.h>
+#ifdef HAVE_PWD_H
 #include <pwd.h>
+#endif
 #include <sys/file.h>
 
 #ifdef __APPLE__
@@ -673,6 +675,11 @@ static void expandTildeExpr(SmallVectorImpl<char> &Path) {
     return;
   }
 
+#if !defined(HAVE_PWD_H)
+  // No access to password database, return back the original path.
+  (void)Remainder;
+  return;
+#else
   // This is a string of the form ~username/, look up this user's entry in the
   // password database.
   std::unique_ptr<char[]> Buf;
@@ -694,6 +701,7 @@ static void expandTildeExpr(SmallVectorImpl<char> &Path) {
   Path.clear();
   Path.append(Entry->pw_dir, Entry->pw_dir + strlen(Entry->pw_dir));
   llvm::sys::path::append(Path, Storage);
+#endif
 }
 
 void expand_tilde(const Twine &path, SmallVectorImpl<char> &dest) {
@@ -770,11 +778,15 @@ std::error_code status(int FD, file_status &Result) {
 }
 
 unsigned getUmask() {
+#if HAVE_UMASK
   // Chose arbitary new mask and reset the umask to the old mask.
   // umask(2) never fails so ignore the return of the second call.
   unsigned Mask = ::umask(0);
   (void)::umask(Mask);
   return Mask;
+#else
+  return 0022;
+#endif
 }
 
 std::error_code setPermissions(const Twine &Path, perms Permissions) {
@@ -1224,6 +1236,7 @@ Expected<size_t> readNativeFileSlice(file_t FD, MutableArrayRef<char> Buf,
 }
 
 std::error_code tryLockFile(int FD, std::chrono::milliseconds Timeout) {
+#if HAVE_FLOCK
   auto Start = std::chrono::steady_clock::now();
   auto End = Start + Timeout;
   do {
@@ -1241,9 +1254,13 @@ std::error_code tryLockFile(int FD, std::chrono::milliseconds Timeout) {
     usleep(1000);
   } while (std::chrono::steady_clock::now() < End);
   return make_error_code(errc::no_lock_available);
+#else
+  return std::error_code(ENOSYS, std::generic_category());
+#endif
 }
 
 std::error_code lockFile(int FD) {
+#if HAVE_FLOCK
   struct flock Lock;
   memset(&Lock, 0, sizeof(Lock));
   Lock.l_type = F_WRLCK;
@@ -1253,9 +1270,13 @@ std::error_code lockFile(int FD) {
   if (::fcntl(FD, F_SETLKW, &Lock) != -1)
     return std::error_code();
   return errnoAsErrorCode();
+#else
+  return std::error_code(ENOSYS, std::generic_category());
+#endif
 }
 
 std::error_code unlockFile(int FD) {
+#if HAVE_FLOCK
   struct flock Lock;
   Lock.l_type = F_UNLCK;
   Lock.l_whence = SEEK_SET;
@@ -1264,6 +1285,9 @@ std::error_code unlockFile(int FD) {
   if (::fcntl(FD, F_SETLK, &Lock) != -1)
     return std::error_code();
   return errnoAsErrorCode();
+#else
+  return std::error_code(ENOSYS, std::generic_category());
+#endif
 }
 
 std::error_code closeFile(file_t &F) {
@@ -1335,11 +1359,15 @@ std::error_code real_path(const Twine &path, SmallVectorImpl<char> &dest,
 }
 
 std::error_code changeFileOwnership(int FD, uint32_t Owner, uint32_t Group) {
+#if HAVE_FCHOWN
   auto FChown = [&]() { return ::fchown(FD, Owner, Group); };
   // Retry if fchown call fails due to interruption.
   if ((sys::RetryAfterSignal(-1, FChown)) < 0)
     return errnoAsErrorCode();
   return std::error_code();
+#else
+  return std::error_code(ENOSYS, std::generic_category());
+#endif
 }
 
 } // end namespace fs
@@ -1349,6 +1377,7 @@ namespace path {
 bool home_directory(SmallVectorImpl<char> &result) {
   std::unique_ptr<char[]> Buf;
   char *RequestedDir = getenv("HOME");
+#if HAVE_PWD_H
   if (!RequestedDir) {
     long BufSize = sysconf(_SC_GETPW_R_SIZE_MAX);
     if (BufSize <= 0)
@@ -1360,6 +1389,7 @@ bool home_directory(SmallVectorImpl<char> &result) {
     if (pw && pw->pw_dir)
       RequestedDir = pw->pw_dir;
   }
+#endif
   if (!RequestedDir)
     return false;
 

llvm/lib/Support/Unix/Process.inc

@@ -72,7 +72,11 @@ getRUsageTimes() {
 Process::Pid Process::getProcessId() {
   static_assert(sizeof(Pid) >= sizeof(pid_t),
                 "Process::Pid should be big enough to store pid_t");
+#if HAVE_GETPID
   return Pid(::getpid());
+#else
+  return Pid(0);
+#endif
 }
 
 // On Cygwin, getpagesize() returns 64k(AllocationGranularity) and

llvm/lib/Support/Unix/Unix.h

@@ -30,7 +30,10 @@
 #include <cstring>
 #include <string>
 #include <sys/types.h>
+
+#ifdef HAVE_SYS_WAIT_H
 #include <sys/wait.h>
+#endif
 
 #ifdef HAVE_UNISTD_H
 #include <unistd.h>