ICU-22787 Fix ClangCL cross-compilation on Windows

unicode-org · Jun 3, 2024 · 1343c73 · 1343c73
1 parent 81492ae
commit 1343c73
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 3 deletions.
diff --git a/icu4c/source/tools/genccode/genccode.c b/icu4c/source/tools/genccode/genccode.c
@@ -70,6 +70,7 @@ enum {
 #ifdef CAN_GENERATE_OBJECTS
   kOptObject,
   kOptMatchArch,
+  kOptCpuArch,
   kOptSkipDllExport,
 #endif
   kOptFilename,
@@ -86,6 +87,7 @@ static UOption options[]={
 #ifdef CAN_GENERATE_OBJECTS
 /*6*/UOPTION_DEF("object", 'o', UOPT_NO_ARG),
      UOPTION_DEF("match-arch", 'm', UOPT_REQUIRES_ARG),
+     UOPTION_DEF("cpu-arch", 'c', UOPT_REQUIRES_ARG),
      UOPTION_DEF("skip-dll-export", '\0', UOPT_NO_ARG),
 #endif
      UOPTION_DEF("filename", 'f', UOPT_REQUIRES_ARG),
@@ -131,6 +133,7 @@ main(int argc, char* argv[]) {
             "\t-o or --object      write a .obj file instead of .c\n"
             "\t-m or --match-arch file.o  match the architecture (CPU, 32/64 bits) of the specified .o\n"
             "\t                    ELF format defaults to i386. Windows defaults to the native platform.\n"
+            "\t-c or --cpu-arch    Specify a CPU architecture for which to write a .obj file for ClangCL on Windows\n"
             "\t--skip-dll-export   Don't export the ICU data entry point symbol (for use when statically linking)\n");
 #endif
         fprintf(stderr,
@@ -196,6 +199,7 @@ main(int argc, char* argv[]) {
                 writeObjectCode(filename, options[kOptDestDir].value,
                                 options[kOptEntryPoint].doesOccur ? options[kOptEntryPoint].value : NULL,
                                 options[kOptMatchArch].doesOccur ? options[kOptMatchArch].value : NULL,
+                                options[kOptCpuArch].doesOccur ? options[kOptCpuArch].value : NULL,
                                 options[kOptFilename].doesOccur ? options[kOptFilename].value : NULL,
                                 NULL,
                                 0,

diff --git a/icu4c/source/tools/pkgdata/pkgdata.cpp b/icu4c/source/tools/pkgdata/pkgdata.cpp
@@ -776,6 +776,7 @@ static int32_t pkg_executeOptions(UPKGOptions *o) {
                         o->entryName,
                         (optMatchArch[0] == 0 ? nullptr : optMatchArch),
                         nullptr,
+                        nullptr,
                         gencFilePath,
                         sizeof(gencFilePath),
                         true);

diff --git a/icu4c/source/tools/toolutil/pkg_genc.cpp b/icu4c/source/tools/toolutil/pkg_genc.cpp
@@ -799,7 +799,12 @@ getOutFilename(
 
 #ifdef CAN_GENERATE_OBJECTS
 static void
-getArchitecture(uint16_t *pCPU, uint16_t *pBits, UBool *pIsBigEndian, const char *optMatchArch) {
+getArchitecture(
+    uint16_t *pCPU,
+    uint16_t *pBits,
+    UBool *pIsBigEndian,
+    const char *optMatchArch,
+    [[maybe_unused]] const char *optCpuArch) {
     union {
         char        bytes[2048];
 #ifdef U_ELF
@@ -847,7 +852,24 @@ getArchitecture(uint16_t *pCPU, uint16_t *pBits, UBool *pIsBigEndian, const char
 #   if defined(_M_IX86)
         *pCPU = IMAGE_FILE_MACHINE_I386;
 #   else
-        *pCPU = IMAGE_FILE_MACHINE_UNKNOWN;
+        // Linker for ClangCL doesn't handle IMAGE_FILE_MACHINE_UNKNOWN the same as
+        // linker for MSVC. Because of this optCpuArch is used to define the CPU
+        // architecture in that case. While _M_AMD64 and _M_ARM64 could be used,
+        // this would potentially be problematic when cross-compiling as this code
+        // would most likely be ran on host machine to generate the .obj file for
+        // the target architecture.
+#       if defined(__clang__)
+            if (strcmp(optCpuArch, "x64") == 0) {
+                *pCPU = IMAGE_FILE_MACHINE_AMD64;
+            } else if (strcmp(optCpuArch, "arm64") == 0) {
+                *pCPU = IMAGE_FILE_MACHINE_ARM64;
+            } else {
+                // This should never happen.
+                *pCPU = IMAGE_FILE_MACHINE_UNKNOWN;
+            }
+#       else
+            *pCPU = IMAGE_FILE_MACHINE_UNKNOWN;
+#       endif
 #   endif
 #   if defined(_M_IA64) || defined(_M_AMD64) || defined (_M_ARM64)
         *pBits = 64; // Doesn't seem to be used for anything interesting though?
@@ -934,6 +956,7 @@ writeObjectCode(
         const char *destdir,
         const char *optEntryPoint,
         const char *optMatchArch,
+        const char *optCpuArch,
         const char *optFilename,
         char *outFilePath,
         size_t outFilePathCapacity,
@@ -1201,7 +1224,7 @@ writeObjectCode(
 #endif
 
     /* deal with options, files and the entry point name */
-    getArchitecture(&cpu, &bits, &makeBigEndian, optMatchArch);
+    getArchitecture(&cpu, &bits, &makeBigEndian, optMatchArch, optCpuArch);
     if (optMatchArch)
     {
         printf("genccode: --match-arch cpu=%hu bits=%hu big-endian=%d\n", cpu, bits, makeBigEndian);

diff --git a/icu4c/source/tools/toolutil/pkg_genc.h b/icu4c/source/tools/toolutil/pkg_genc.h
@@ -99,6 +99,7 @@ writeObjectCode(
     const char *destdir,
     const char *optEntryPoint,
     const char *optMatchArch,
+    const char *optCpuArch,
     const char *optFilename,
     char *outFilePath,
     size_t outFilePathCapacity,