[libc] Simplify integration tests by eliminating the artificial sysroot.

[sivachandra]

Summary

The test binaries are built like any other executable but with two
additional linker options -static and -nostdlib.

[jhuber6]

libc/cmake/modules/LLVMLibCTestRules.cmake

506–511

Should we use -nostdinc as well? Or do we still expect to pick up some system libraries.

[sivachandra]

libc/cmake/modules/LLVMLibCTestRules.cmake

506–511

Our libc does not [yet] provide the free standing headers like stddef.h and stdint.h. Using -nostdinc eliminates the paths to the compiler's freestanding headers also. So, we cannot [yet] use -nostdinc.

[jhuber6]

libc/cmake/modules/LLVMLibCTestRules.cmake

506–511

Alright, we can update this when libc is fully self supported.

[sivachandra]

• Improve the formatting of the code.
• Collect all deps in to a static archive which gets linked to the final binary.

[jhuber6]

libc/cmake/modules/LLVMLibCTestRules.cmake

450

Is it possible to make these dependencies transitive on the start implementation? Since presumably these are only required to implement the corresponding crt1.o and friends. For the GPU we wouldn't use any of these.

[sivachandra]

libc/cmake/modules/LLVMLibCTestRules.cmake

450

Yes, that can be done. I can do that separately.

libc/cmake/modules/LLVMLibCTestRules.cmake

function(add_integration_test test_name)
   endif()
   if(NOT INTEGRATION_TEST_SRCS)
     message(FATAL_ERROR "The SRCS list for add_integration_test is missing.")
   endif()
 
   get_fq_target_name(${test_name}.libc fq_libc_target_name)
 
   get_fq_deps_list(fq_deps_list ${INTEGRATION_TEST_DEPENDS})
+  list(APPEND fq_deps_list
       # All integration tests setup TLS area and the main thread's self object.
       # So, we need to link in the threads implementation. Likewise, the startup
       # code also has to run init_array callbacks which potentially register
       # their own atexit callbacks. So, link in exit and atexit also with all
       # integration tests.
-  list(
-      APPEND fq_deps_list
       libc.src.__support.threads.thread
       libc.src.stdlib.atexit
       libc.src.stdlib.exit
       libc.src.unistd.environ
-      libc.test.IntegrationTest.test)
+  )
+  list(APPEND memory_functions
+      libc.src.string.bcmp
+      libc.src.string.bzero
+      libc.src.string.memcmp
+      libc.src.string.memcpy
+      libc.src.string.memmove
+      libc.src.string.memset
+  )
+  # We remove the memory function deps because we want to explicitly add the
+  # object files which include the public symbols of the memory functions.
+  list(REMOVE_ITEM fq_deps_list ${memory_functions})
   list(REMOVE_DUPLICATES fq_deps_list)
 
   # TODO: Instead of gathering internal object files from entrypoints,
   # collect the object files with public names of entrypoints.
   get_object_files_for_test(
       link_object_files skipped_entrypoints_list ${fq_deps_list})
-  if(skipped_entrypoints_list)
-    message(STATUS "Skipping ${fq_target_name} as it has skipped deps.")
-    return()
-  endif()
-
-  # Create a sysroot structure
-  set(sysroot ${CMAKE_CURRENT_BINARY_DIR}/${test_name}/sysroot)
-  file(MAKE_DIRECTORY ${sysroot})
-  file(MAKE_DIRECTORY ${sysroot}/include)
-  set(sysroot_lib ${sysroot}/lib)
-  file(MAKE_DIRECTORY ${sysroot_lib})
-  set(startup_object_file $<TARGET_OBJECTS:${INTEGRATION_TEST_STARTUP}>)
-  set(crti_object_file $<TARGET_OBJECTS:libc.startup.linux.crti>)
-  set(crtn_object_file $<TARGET_OBJECTS:libc.startup.linux.crtn>)
-  set(dummy_archive $<TARGET_PROPERTY:libc_integration_test_dummy,ARCHIVE_OUTPUT_DIRECTORY>/lib$<TARGET_PROPERTY:libc_integration_test_dummy,ARCHIVE_OUTPUT_NAME>.a)
-  # TODO: Copy the startup files to the correct target-triple directory instead
-  # of to a partly hard-coded directory.
-  set(startup_dst ${sysroot_lib}/${LIBC_TARGET_ARCHITECTURE}-linux-gnu)
-  add_custom_command(
-    OUTPUT ${startup_dst} ${sysroot}/lib/crti.o ${sysroot}/lib/crtn.o ${sysroot}/lib/libm.a ${sysroot}/lib/libc++.a
-    COMMAND cmake -E copy ${startup_object_file} ${startup_dst}/$<TARGET_PROPERTY:${INTEGRATION_TEST_STARTUP},OUTPUT_NAME>
-    COMMAND cmake -E copy ${crti_object_file} ${sysroot_lib}/$<TARGET_PROPERTY:libc.startup.linux.crti,OUTPUT_NAME>
-    COMMAND cmake -E copy ${crtn_object_file} ${sysroot_lib}/$<TARGET_PROPERTY:libc.startup.linux.crtn,OUTPUT_NAME>
-    # We copy the dummy archive as libm.a and libc++.a as the compiler drivers expect them.
-    COMMAND cmake -E copy ${dummy_archive} ${sysroot_lib}/libm.a
-    COMMAND cmake -E copy ${dummy_archive} ${sysroot_lib}/libc++.a
-    DEPENDS ${INTEGRATION_TEST_STARTUP} libc.startup.linux.crti libc.startup.linux.crtn libc_integration_test_dummy
-  )
-  add_custom_target(
-    ${fq_target_name}.__copy_startup__
-    DEPENDS ${startup_dst}
-  )
-
-  add_library(
-    ${fq_libc_target_name}
-    STATIC
-    ${link_object_files}
-    # We add the memory functions objects explicitly. Note that we
-    # are adding objects of the targets which contain the public
-    # C symbols. This is because compiler codegen can emit calls to
-    # the C memory functions.
-    $<TARGET_OBJECTS:libc.src.string.bcmp>
-    $<TARGET_OBJECTS:libc.src.string.bzero>
-    $<TARGET_OBJECTS:libc.src.string.memcmp>
-    $<TARGET_OBJECTS:libc.src.string.memcpy>
-    $<TARGET_OBJECTS:libc.src.string.memmove>
-    $<TARGET_OBJECTS:libc.src.string.memset>
+  foreach(func IN LISTS memory_functions)
+    list(APPEND link_object_files $<TARGET_OBJECTS:${func}>)
+  endforeach()
+  list(REMOVE_DUPLICATES link_object_files)
+
+  # Make a library of all deps
+  add_library(
+    ${fq_target_name}.__libc__
+    STATIC
+    EXCLUDE_FROM_ALL
+    ${link_object_files}
   )
-  set_target_properties(${fq_libc_target_name} PROPERTIES ARCHIVE_OUTPUT_NAME c)
-  set_target_properties(${fq_libc_target_name} PROPERTIES ARCHIVE_OUTPUT_DIRECTORY ${sysroot_lib})
+  set_target_properties(${fq_target_name}.__libc__
+      PROPERTIES ARCHIVE_OUTPUT_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})
+  set_target_properties(${fq_target_name}.__libc__
+      PROPERTIES ARCHIVE_OUTPUT_NAME ${fq_target_name}.libc)
 
   set(fq_build_target_name ${fq_target_name}.__build__)
   add_executable(
     ${fq_build_target_name}
     EXCLUDE_FROM_ALL
     ${INTEGRATION_TEST_SRCS}
     ${INTEGRATION_TEST_HDRS}
   )
   set_target_properties(${fq_build_target_name}
       PROPERTIES RUNTIME_OUTPUT_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})
   target_include_directories(
     ${fq_build_target_name}
     PRIVATE
       ${LIBC_SOURCE_DIR}
       ${LIBC_BUILD_DIR}
       ${LIBC_BUILD_DIR}/include
   )
-  target_compile_options(${fq_build_target_name} PRIVATE -ffreestanding ${INTEGRATION_TEST_COMPILE_OPTIONS})
-  # We set a number of link options to prevent picking up system libc binaries.
-  # Also, we restrict the integration tests to fully static executables. The
-  # rtlib is set to compiler-rt to make the compiler drivers pick up the compiler
-  # runtime binaries using full paths. Otherwise, files like crtbegin.o are passed
-  # as is (and not as paths like /usr/lib/.../crtbegin.o).
-  target_link_options(${fq_build_target_name} PRIVATE --sysroot=${sysroot} -static -stdlib=libc++ --rtlib=compiler-rt)
+  target_compile_options(${fq_build_target_name}
+                         PRIVATE -ffreestanding ${INTEGRATION_TEST_COMPILE_OPTIONS})
+  target_link_options(${fq_build_target_name} PRIVATE -nostdlib -static)
+  target_link_libraries(${fq_build_target_name}
+                        ${INTEGRATION_TEST_STARTUP} ${fq_target_name}.__libc__
+                        libc.test.IntegrationTest.test)
   add_dependencies(${fq_build_target_name}
-                   ${fq_target_name}.__copy_startup__
-                   ${fq_libc_target_name}
                    libc.test.IntegrationTest.test
                    ${INTEGRATION_TEST_DEPENDS})
 
   add_custom_target(
     ${fq_target_name}
     COMMAND ${INTEGRATION_TEST_ENV} $<TARGET_FILE:${fq_build_target_name}> ${INTEGRATION_TEST_ARGS}
     COMMENT "Running integration test ${fq_target_name}"
   )
-
   add_dependencies(${INTEGRATION_TEST_SUITE} ${fq_target_name})
 endfunction(add_integration_test)

libc/startup/linux/aarch64/start.cpp

 #include <linux/auxvec.h>
 #include <linux/elf.h>
 #include <stdint.h>
 #include <sys/mman.h>
 #include <sys/syscall.h>
 #include <unistd.h>
 
 extern "C" int main(int, char **, char **);
+// The BFD linker requires a reference to __dso_handle to trigger creating
+// a symbol for it when -nostdlib is used..
+extern "C" void *__dso_handle = nullptr;
 
 // Source documentation:
 // https://github.com/ARM-software/abi-aa/tree/main/sysvabi64
 
 namespace __llvm_libc {
 
 #ifdef SYS_mmap2
 static constexpr long MMAP_SYSCALL_NUMBER = SYS_mmap2;

libc/startup/linux/x86_64/start.cpp

 #include <linux/auxvec.h>
 #include <linux/elf.h>
 #include <stdint.h>
 #include <sys/mman.h>
 #include <sys/syscall.h>
 #include <unistd.h>
 
 extern "C" int main(int, char **, char **);
+// The BFD linker requires a reference to __dso_handle to trigger creating
+// a symbol for it when -nostdlib is used..
+extern "C" void *__dso_handle = nullptr;
 
 namespace __llvm_libc {
 
 #ifdef SYS_mmap2
 static constexpr long mmapSyscallNumber = SYS_mmap2;
 #elif SYS_mmap
 static constexpr long mmapSyscallNumber = SYS_mmap;
 #else