macOS: Offer control over host architecture on Apple Silicon hosts

Since commit b6c60f14b6 (macOS: Default to arm64 architecture on Apple
Silicon hosts, 2020-09-28, v3.19.0-rc1~63^2) we use `sysctl` to detect
that we are running on Apple Silicon in a way that pierces Rosetta.
This always sets `CMAKE_HOST_SYSTEM_PROCESSOR` to be `arm64` on such
hosts.  However, macOS offers strong support for running processes under
an emulated `x86_64` architecture.

Teach CMake to select either `arm64` or `x86_64` as the host
architecture on Apple Silicon based on the architecture of its own
process.  When CMake is built as a universal binary, macOS will select
whichever slice (architecture) is appropriate under the user's shell,
and `CMAKE_HOST_SYSTEM_PROCESSOR` will match.

Also offer a `CMAKE_APPLE_SILICON_PROCESSOR` variable and environment
variable to provide users with explicit control over the host
architecture selection regardless of CMake's own architecture.

Finally, if `CMAKE_OSX_ARCHITECTURES` is not set, pass explicit flags to
the toolchain to use selected host architecture instead of letting the
toolchain pick.

Fixes: #21554

2 files changed, 41 insertions, 13 deletions

diff --git a/Modules/CMakeDetermineSystem.cmake b/Modules/CMakeDetermineSystem.cmake
index cb4421a..bae270d 100644
--- a/Modules/CMakeDetermineSystem.cmake
+++ b/Modules/CMakeDetermineSystem.cmake
@@ -43,25 +43,44 @@ if(CMAKE_HOST_UNIX)
     else()
       exec_program(${CMAKE_UNAME} ARGS -r OUTPUT_VARIABLE CMAKE_HOST_SYSTEM_VERSION)
     endif()
-    if(CMAKE_HOST_SYSTEM_NAME MATCHES "Linux|CYGWIN.*|Darwin|^GNU$|Android")
+    if(CMAKE_HOST_SYSTEM_NAME MATCHES "Linux|CYGWIN.*|^GNU$|Android")
       exec_program(${CMAKE_UNAME} ARGS -m OUTPUT_VARIABLE CMAKE_HOST_SYSTEM_PROCESSOR
         RETURN_VALUE val)
-      if(CMAKE_HOST_SYSTEM_NAME STREQUAL "Darwin")
-        if(CMAKE_HOST_SYSTEM_PROCESSOR STREQUAL "x86_64")
-          # Check whether we are running under Rosetta on arm64 hardware.
+    elseif(CMAKE_HOST_SYSTEM_NAME MATCHES "Darwin")
+      # If we are running on Apple Silicon, honor CMAKE_APPLE_SILICON_PROCESSOR.
+      if(DEFINED CMAKE_APPLE_SILICON_PROCESSOR)
+        set(_CMAKE_APPLE_SILICON_PROCESSOR "${CMAKE_APPLE_SILICON_PROCESSOR}")
+      elseif(DEFINED ENV{CMAKE_APPLE_SILICON_PROCESSOR})
+        set(_CMAKE_APPLE_SILICON_PROCESSOR "$ENV{CMAKE_APPLE_SILICON_PROCESSOR}")
+      else()
+        set(_CMAKE_APPLE_SILICON_PROCESSOR "")
+      endif()
+      if(_CMAKE_APPLE_SILICON_PROCESSOR)
+        if(";${_CMAKE_APPLE_SILICON_PROCESSOR};" MATCHES "^;(arm64|x86_64);$")
           execute_process(COMMAND sysctl -q hw.optional.arm64
             OUTPUT_VARIABLE _sysctl_stdout
             ERROR_VARIABLE _sysctl_stderr
             RESULT_VARIABLE _sysctl_result
             )
-          if(_sysctl_result EQUAL 0 AND _sysctl_stdout MATCHES "hw.optional.arm64: 1")
-            set(CMAKE_HOST_SYSTEM_PROCESSOR "arm64")
+          if(NOT _sysctl_result EQUAL 0 OR NOT _sysctl_stdout MATCHES "hw.optional.arm64: 1")
+            set(_CMAKE_APPLE_SILICON_PROCESSOR "")
           endif()
-        elseif(CMAKE_HOST_SYSTEM_PROCESSOR STREQUAL "Power Macintosh")
-          # OS X ppc 'uname -m' may report 'Power Macintosh' instead of 'powerpc'
-          set(CMAKE_HOST_SYSTEM_PROCESSOR "powerpc")
+          unset(_sysctl_result)
+          unset(_sysctl_stderr)
+          unset(_sysctl_stdout)
         endif()
       endif()
+      if(_CMAKE_APPLE_SILICON_PROCESSOR)
+        set(CMAKE_HOST_SYSTEM_PROCESSOR "${_CMAKE_APPLE_SILICON_PROCESSOR}")
+      else()
+        exec_program(${CMAKE_UNAME} ARGS -m OUTPUT_VARIABLE CMAKE_HOST_SYSTEM_PROCESSOR
+          RETURN_VALUE val)
+      endif()
+      unset(_CMAKE_APPLE_SILICON_PROCESSOR)
+      if(CMAKE_HOST_SYSTEM_PROCESSOR STREQUAL "Power Macintosh")
+        # OS X ppc 'uname -m' may report 'Power Macintosh' instead of 'powerpc'
+        set(CMAKE_HOST_SYSTEM_PROCESSOR "powerpc")
+      endif()
     elseif(CMAKE_HOST_SYSTEM_NAME MATCHES "OpenBSD")
       exec_program(arch ARGS -s OUTPUT_VARIABLE CMAKE_HOST_SYSTEM_PROCESSOR
         RETURN_VALUE val)
diff --git a/Modules/Platform/Darwin-Initialize.cmake b/Modules/Platform/Darwin-Initialize.cmake
index 213f71b..c2f1851 100644
--- a/Modules/Platform/Darwin-Initialize.cmake
+++ b/Modules/Platform/Darwin-Initialize.cmake
@@ -22,13 +22,22 @@ set(CMAKE_OSX_ARCHITECTURES "$ENV{CMAKE_OSX_ARCHITECTURES}" CACHE STRING
 
 if(NOT CMAKE_CROSSCOMPILING AND
    CMAKE_SYSTEM_NAME STREQUAL "Darwin" AND
-   CMAKE_HOST_SYSTEM_PROCESSOR STREQUAL "arm64" AND
-   CMAKE_SYSTEM_PROCESSOR STREQUAL "arm64")
-  # When building on Apple Silicon (arm64), we need to explicitly specify
+   CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "^(arm64|x86_64)$")
+  execute_process(COMMAND sysctl -q hw.optional.arm64
+    OUTPUT_VARIABLE _sysctl_stdout
+    ERROR_VARIABLE _sysctl_stderr
+    RESULT_VARIABLE _sysctl_result
+    )
+  # When building on an Apple Silicon host, we need to explicitly specify
   # the architecture to the toolchain since it will otherwise guess the
   # architecture based on that of the build system tool.
   # Set an *internal variable* to tell the generators to do this.
-  set(_CMAKE_APPLE_ARCHS_DEFAULT "arm64")
+  if(_sysctl_result EQUAL 0 AND _sysctl_stdout MATCHES "hw.optional.arm64: 1")
+    set(_CMAKE_APPLE_ARCHS_DEFAULT "${CMAKE_HOST_SYSTEM_PROCESSOR}")
+  endif()
+  unset(_sysctl_result)
+  unset(_sysctl_stderr)
+  unset(_sysctl_stdout)
 endif()
 
 # macOS, iOS, tvOS, and watchOS should lookup compilers from