[Tarantool-patches] [PATCH luajit 08/19] Windows: Add UWP support, part 1.

[Sergey Kaplun via Tarantool-patches <tarantool-patches@dev.tarantool.org>]

From: Mike Pall <mike>

Contributed by Ben Pye.

(cherry-picked from commit c3c54ce1aef782823936808a75460e6b53aada2c)

This patch adds partial support for the Universal Windows Platform [1]
in LuaJIT.
This includes:
* `LJ_TARGET_UWP` is introduced to mark that target is Universal Windows
  Platform.
* `LJ_WIN_VALLOC()` macro is introduced to use instead of
  `VirtualAlloc()` [2] (`VirtualAllocFromApp()` [3] for UWP)
* `LJ_WIN_VPROTECT()` macro is introduced to use instead of
  `VirtualProtect()` [4] (`VirtualProtectFromApp()` [5] for UWP)
* `LJ_WIN_LOADLIBA()` macro is introduced to use instead of
  `LoadLibraryExA()` [6] (custom implementation using
  `LoadPackagedLibrary()` [7] for UWP).

Note that the following features are not implemented for UWP:
* `io.popen()`.
* LuaJIT profiler's (`jit.p`) timer for Windows has not very high
  resolution since `timeBeginPeriod()` [8] and `timeEndPeriod()` [9] are
  not used, because the <winmm.dll> library isn't loaded.

[1]: https://learn.microsoft.com/en-us/windows/uwp/get-started/universal-application-platform-guide
[2]: https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-virtualalloc
[3]: https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-virtualallocfromapp
[4]: https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-virtualprotect
[5]: https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-virtualprotectfromapp
[6]: https://learn.microsoft.com/en-us/windows/win32/api/libloaderapi/nf-libloaderapi-loadlibraryexa
[7]: https://learn.microsoft.com/en-us/windows/win32/api/winbase/nf-winbase-loadpackagedlibrary
[8]: https://learn.microsoft.com/en-us/windows/win32/api/timeapi/nf-timeapi-timebeginperiod
[9]: https://learn.microsoft.com/en-us/windows/win32/api/timeapi/nf-timeapi-timeendperiod

Sergey Kaplun:
* added the description for the feature

Part of tarantool/tarantool#8825
---
 doc/ext_ffi_api.html   |  2 ++
 src/lib_ffi.c          |  3 +++
 src/lib_io.c           |  4 ++--
 src/lib_package.c      | 24 +++++++++++++++++++++++-
 src/lj_alloc.c         |  6 +++---
 src/lj_arch.h          | 19 +++++++++++++++++++
 src/lj_ccallback.c     |  4 ++--
 src/lj_clib.c          | 20 ++++++++++++++++----
 src/lj_mcode.c         |  8 ++++----
 src/lj_profile_timer.c |  8 ++++----
 10 files changed, 78 insertions(+), 20 deletions(-)

diff --git a/doc/ext_ffi_api.html b/doc/ext_ffi_api.html
index 91af2e1d..c72191d1 100644
--- a/doc/ext_ffi_api.html
+++ b/doc/ext_ffi_api.html
@@ -469,6 +469,8 @@ otherwise. The following parameters are currently defined:
 <tr class="odd">
 <td class="abiparam">win</td><td class="abidesc">Windows variant of the standard ABI</td></tr>
 <tr class="even">
+<td class="abiparam">uwp</td><td class="abidesc">Universal Windows Platform</td></tr>
+<tr class="odd">
 <td class="abiparam">gc64</td><td class="abidesc">64 bit GC references</td></tr>
 </table>
 
diff --git a/src/lib_ffi.c b/src/lib_ffi.c
index 136e98e8..d1fe1a14 100644
--- a/src/lib_ffi.c
+++ b/src/lib_ffi.c
@@ -746,6 +746,9 @@ LJLIB_CF(ffi_abi)	LJLIB_REC(.)
 #endif
 #if LJ_ABI_WIN
   case H_(4ab624a8,4ab624a8): b = 1; break;  /* win */
+#endif
+#if LJ_TARGET_UWP
+  case H_(a40f0bcb,a40f0bcb): b = 1; break;  /* uwp */
 #endif
   case H_(3af93066,1f001464): b = 1; break;  /* le/be */
 #if LJ_GC64
diff --git a/src/lib_io.c b/src/lib_io.c
index f0108227..db995ae6 100644
--- a/src/lib_io.c
+++ b/src/lib_io.c
@@ -99,7 +99,7 @@ static int io_file_close(lua_State *L, IOFileUD *iof)
     int stat = -1;
 #if LJ_TARGET_POSIX
     stat = pclose(iof->fp);
-#elif LJ_TARGET_WINDOWS && !LJ_TARGET_XBOXONE
+#elif LJ_TARGET_WINDOWS && !LJ_TARGET_XBOXONE && !LJ_TARGET_UWP
     stat = _pclose(iof->fp);
 #else
     lua_assert(0);
@@ -414,7 +414,7 @@ LJLIB_CF(io_open)
 
 LJLIB_CF(io_popen)
 {
-#if LJ_TARGET_POSIX || (LJ_TARGET_WINDOWS && !LJ_TARGET_XBOXONE)
+#if LJ_TARGET_POSIX || (LJ_TARGET_WINDOWS && !LJ_TARGET_XBOXONE && !LJ_TARGET_UWP)
   const char *fname = strdata(lj_lib_checkstr(L, 1));
   GCstr *s = lj_lib_optstr(L, 2);
   const char *mode = s ? strdata(s) : "r";
diff --git a/src/lib_package.c b/src/lib_package.c
index 67959a10..b49f0209 100644
--- a/src/lib_package.c
+++ b/src/lib_package.c
@@ -76,6 +76,20 @@ static const char *ll_bcsym(void *lib, const char *sym)
 BOOL WINAPI GetModuleHandleExA(DWORD, LPCSTR, HMODULE*);
 #endif
 
+#if LJ_TARGET_UWP
+void *LJ_WIN_LOADLIBA(const char *path)
+{
+  DWORD err = GetLastError();
+  wchar_t wpath[256];
+  HANDLE lib = NULL;
+  if (MultiByteToWideChar(CP_ACP, 0, path, -1, wpath, 256) > 0) {
+    lib = LoadPackagedLibrary(wpath, 0);
+  }
+  SetLastError(err);
+  return lib;
+}
+#endif
+
 #undef setprogdir
 
 static void setprogdir(lua_State *L)
@@ -119,7 +133,7 @@ static void ll_unloadlib(void *lib)
 
 static void *ll_load(lua_State *L, const char *path, int gl)
 {
-  HINSTANCE lib = LoadLibraryExA(path, NULL, 0);
+  HINSTANCE lib = LJ_WIN_LOADLIBA(path);
   if (lib == NULL) pusherror(L);
   UNUSED(gl);
   return lib;
@@ -132,17 +146,25 @@ static lua_CFunction ll_sym(lua_State *L, void *lib, const char *sym)
   return f;
 }
 
+#if LJ_TARGET_UWP
+EXTERN_C IMAGE_DOS_HEADER __ImageBase;
+#endif
+
 static const char *ll_bcsym(void *lib, const char *sym)
 {
   if (lib) {
     return (const char *)GetProcAddress((HINSTANCE)lib, sym);
   } else {
+#if LJ_TARGET_UWP
+    return (const char *)GetProcAddress((HINSTANCE)&__ImageBase, sym);
+#else
     HINSTANCE h = GetModuleHandleA(NULL);
     const char *p = (const char *)GetProcAddress(h, sym);
     if (p == NULL && GetModuleHandleExA(GET_MODULE_HANDLE_EX_FLAG_FROM_ADDRESS|GET_MODULE_HANDLE_EX_FLAG_UNCHANGED_REFCOUNT,
 					(const char *)ll_bcsym, &h))
       p = (const char *)GetProcAddress(h, sym);
     return p;
+#endif
   }
 }
 
diff --git a/src/lj_alloc.c b/src/lj_alloc.c
index f7039b5b..9e2fb1f6 100644
--- a/src/lj_alloc.c
+++ b/src/lj_alloc.c
@@ -167,7 +167,7 @@ static void *DIRECT_MMAP(size_t size)
 static void *CALL_MMAP(size_t size)
 {
   DWORD olderr = GetLastError();
-  void *ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE);
+  void *ptr = LJ_WIN_VALLOC(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE);
   SetLastError(olderr);
   return ptr ? ptr : MFAIL;
 }
@@ -176,8 +176,8 @@ static void *CALL_MMAP(size_t size)
 static void *DIRECT_MMAP(size_t size)
 {
   DWORD olderr = GetLastError();
-  void *ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN,
-			   PAGE_READWRITE);
+  void *ptr = LJ_WIN_VALLOC(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN,
+			    PAGE_READWRITE);
   SetLastError(olderr);
   return ptr ? ptr : MFAIL;
 }
diff --git a/src/lj_arch.h b/src/lj_arch.h
index 7397492e..0351e046 100644
--- a/src/lj_arch.h
+++ b/src/lj_arch.h
@@ -141,6 +141,13 @@
 #define LJ_TARGET_GC64		1
 #endif
 
+#ifdef _UWP
+#define LJ_TARGET_UWP		1
+#if LUAJIT_TARGET == LUAJIT_ARCH_X64
+#define LJ_TARGET_GC64		1
+#endif
+#endif
+
 #define LJ_NUMMODE_SINGLE	0	/* Single-number mode only. */
 #define LJ_NUMMODE_SINGLE_DUAL	1	/* Default to single-number mode. */
 #define LJ_NUMMODE_DUAL		2	/* Dual-number mode only. */
@@ -586,6 +593,18 @@
 #define LJ_ABI_WIN		0
 #endif
 
+#if LJ_TARGET_WINDOWS
+#if LJ_TARGET_UWP
+#define LJ_WIN_VALLOC	VirtualAllocFromApp
+#define LJ_WIN_VPROTECT	VirtualProtectFromApp
+extern void *LJ_WIN_LOADLIBA(const char *path);
+#else
+#define LJ_WIN_VALLOC	VirtualAlloc
+#define LJ_WIN_VPROTECT	VirtualProtect
+#define LJ_WIN_LOADLIBA(path)	LoadLibraryExA((path), NULL, 0)
+#endif
+#endif
+
 #if defined(LUAJIT_NO_UNWIND) || __GNU_COMPACT_EH__ || defined(__symbian__) || LJ_TARGET_IOS || LJ_TARGET_PS3 || LJ_TARGET_PS4
 #define LJ_NO_UNWIND		1
 #endif
diff --git a/src/lj_ccallback.c b/src/lj_ccallback.c
index c33190d7..37edd00f 100644
--- a/src/lj_ccallback.c
+++ b/src/lj_ccallback.c
@@ -267,7 +267,7 @@ static void callback_mcode_new(CTState *cts)
   if (CALLBACK_MAX_SLOT == 0)
     lj_err_caller(cts->L, LJ_ERR_FFI_CBACKOV);
 #if LJ_TARGET_WINDOWS
-  p = VirtualAlloc(NULL, sz, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE);
+  p = LJ_WIN_VALLOC(NULL, sz, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE);
   if (!p)
     lj_err_caller(cts->L, LJ_ERR_FFI_CBACKOV);
 #elif LJ_TARGET_POSIX
@@ -285,7 +285,7 @@ static void callback_mcode_new(CTState *cts)
 #if LJ_TARGET_WINDOWS
   {
     DWORD oprot;
-    VirtualProtect(p, sz, PAGE_EXECUTE_READ, &oprot);
+    LJ_WIN_VPROTECT(p, sz, PAGE_EXECUTE_READ, &oprot);
   }
 #elif LJ_TARGET_POSIX
   mprotect(p, sz, (PROT_READ|PROT_EXEC));
diff --git a/src/lj_clib.c b/src/lj_clib.c
index c06c0915..a8672052 100644
--- a/src/lj_clib.c
+++ b/src/lj_clib.c
@@ -158,11 +158,13 @@ BOOL WINAPI GetModuleHandleExA(DWORD, LPCSTR, HMODULE*);
 /* Default libraries. */
 enum {
   CLIB_HANDLE_EXE,
+#if !LJ_TARGET_UWP
   CLIB_HANDLE_DLL,
   CLIB_HANDLE_CRT,
   CLIB_HANDLE_KERNEL32,
   CLIB_HANDLE_USER32,
   CLIB_HANDLE_GDI32,
+#endif
   CLIB_HANDLE_MAX
 };
 
@@ -208,7 +210,7 @@ static const char *clib_extname(lua_State *L, const char *name)
 static void *clib_loadlib(lua_State *L, const char *name, int global)
 {
   DWORD oldwerr = GetLastError();
-  void *h = (void *)LoadLibraryExA(clib_extname(L, name), NULL, 0);
+  void *h = LJ_WIN_LOADLIBA(clib_extname(L, name));
   if (!h) clib_error(L, "cannot load module " LUA_QS ": %s", name);
   SetLastError(oldwerr);
   UNUSED(global);
@@ -218,6 +220,7 @@ static void *clib_loadlib(lua_State *L, const char *name, int global)
 static void clib_unloadlib(CLibrary *cl)
 {
   if (cl->handle == CLIB_DEFHANDLE) {
+#if !LJ_TARGET_UWP
     MSize i;
     for (i = CLIB_HANDLE_KERNEL32; i < CLIB_HANDLE_MAX; i++) {
       void *h = clib_def_handle[i];
@@ -226,11 +229,16 @@ static void clib_unloadlib(CLibrary *cl)
 	FreeLibrary((HINSTANCE)h);
       }
     }
+#endif
   } else if (cl->handle) {
     FreeLibrary((HINSTANCE)cl->handle);
   }
 }
 
+#if LJ_TARGET_UWP
+EXTERN_C IMAGE_DOS_HEADER __ImageBase;
+#endif
+
 static void *clib_getsym(CLibrary *cl, const char *name)
 {
   void *p = NULL;
@@ -239,6 +247,9 @@ static void *clib_getsym(CLibrary *cl, const char *name)
     for (i = 0; i < CLIB_HANDLE_MAX; i++) {
       HINSTANCE h = (HINSTANCE)clib_def_handle[i];
       if (!(void *)h) {  /* Resolve default library handles (once). */
+#if LJ_TARGET_UWP
+	h = (HINSTANCE)&__ImageBase;
+#else
 	switch (i) {
 	case CLIB_HANDLE_EXE: GetModuleHandleExA(GET_MODULE_HANDLE_EX_FLAG_UNCHANGED_REFCOUNT, NULL, &h); break;
 	case CLIB_HANDLE_DLL:
@@ -249,11 +260,12 @@ static void *clib_getsym(CLibrary *cl, const char *name)
 	  GetModuleHandleExA(GET_MODULE_HANDLE_EX_FLAG_FROM_ADDRESS|GET_MODULE_HANDLE_EX_FLAG_UNCHANGED_REFCOUNT,
 			     (const char *)&_fmode, &h);
 	  break;
-	case CLIB_HANDLE_KERNEL32: h = LoadLibraryExA("kernel32.dll", NULL, 0); break;
-	case CLIB_HANDLE_USER32: h = LoadLibraryExA("user32.dll", NULL, 0); break;
-	case CLIB_HANDLE_GDI32: h = LoadLibraryExA("gdi32.dll", NULL, 0); break;
+	case CLIB_HANDLE_KERNEL32: h = LJ_WIN_LOADLIBA("kernel32.dll"); break;
+	case CLIB_HANDLE_USER32: h = LJ_WIN_LOADLIBA("user32.dll"); break;
+	case CLIB_HANDLE_GDI32: h = LJ_WIN_LOADLIBA("gdi32.dll"); break;
 	}
 	if (!h) continue;
+#endif
 	clib_def_handle[i] = (void *)h;
       }
       p = (void *)GetProcAddress(h, name);
diff --git a/src/lj_mcode.c b/src/lj_mcode.c
index c6361018..10db4457 100644
--- a/src/lj_mcode.c
+++ b/src/lj_mcode.c
@@ -66,8 +66,8 @@ void lj_mcode_sync(void *start, void *end)
 
 static void *mcode_alloc_at(jit_State *J, uintptr_t hint, size_t sz, DWORD prot)
 {
-  void *p = VirtualAlloc((void *)hint, sz,
-			 MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN, prot);
+  void *p = LJ_WIN_VALLOC((void *)hint, sz,
+			  MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN, prot);
   if (!p && !hint)
     lj_trace_err(J, LJ_TRERR_MCODEAL);
   return p;
@@ -82,7 +82,7 @@ static void mcode_free(jit_State *J, void *p, size_t sz)
 static int mcode_setprot(void *p, size_t sz, DWORD prot)
 {
   DWORD oprot;
-  return !VirtualProtect(p, sz, prot, &oprot);
+  return !LJ_WIN_VPROTECT(p, sz, prot, &oprot);
 }
 
 #elif LJ_TARGET_POSIX
@@ -255,7 +255,7 @@ static void *mcode_alloc(jit_State *J, size_t sz)
 /* All memory addresses are reachable by relative jumps. */
 static void *mcode_alloc(jit_State *J, size_t sz)
 {
-#ifdef __OpenBSD__
+#if defined(__OpenBSD__) || LJ_TARGET_UWP
   /* Allow better executable memory allocation for OpenBSD W^X mode. */
   void *p = mcode_alloc_at(J, 0, sz, MCPROT_RUN);
   if (p && mcode_setprot(p, sz, MCPROT_GEN)) {
diff --git a/src/lj_profile_timer.c b/src/lj_profile_timer.c
index 056fd1f7..0b859457 100644
--- a/src/lj_profile_timer.c
+++ b/src/lj_profile_timer.c
@@ -84,7 +84,7 @@ static DWORD WINAPI timer_thread(void *timerx)
 {
   lj_profile_timer *timer = (lj_profile_timer *)timerx;
   int interval = timer->opt.interval_msec;
-#if LJ_TARGET_WINDOWS
+#if LJ_TARGET_WINDOWS && !LJ_TARGET_UWP
   timer->wmm_tbp(interval);
 #endif
   while (1) {
@@ -92,7 +92,7 @@ static DWORD WINAPI timer_thread(void *timerx)
     if (timer->abort) break;
     timer->opt.handler();
   }
-#if LJ_TARGET_WINDOWS
+#if LJ_TARGET_WINDOWS && !LJ_TARGET_UWP
   timer->wmm_tep(interval);
 #endif
   return 0;
@@ -101,9 +101,9 @@ static DWORD WINAPI timer_thread(void *timerx)
 /* Start profiling timer thread. */
 void lj_profile_timer_start(lj_profile_timer *timer)
 {
-#if LJ_TARGET_WINDOWS
+#if LJ_TARGET_WINDOWS && !LJ_TARGET_UWP
   if (!timer->wmm) { /* Load WinMM library on-demand. */
-    timer->wmm = LoadLibraryExA("winmm.dll", NULL, 0);
+    timer->wmm = LJ_WIN_LOADLIBA("winmm.dll");
     if (timer->wmm) {
       timer->wmm_tbp =
 	(WMM_TPFUNC)GetProcAddress(timer->wmm, "timeBeginPeriod");
-- 
2.41.0