maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/lld/test/pecoff/merge-largest.test

25 lines
838 B
Plaintext
Raw Normal View History

[PECOFF] Support yet another new type of weak symbol. COMDAT_SELECT_LARGEST is a COMDAT type that make linker to choose the largest definition from among all of the definition of a symbol. If the size is the same, the choice is arbitrary. Differential Revision: http://llvm-reviews.chandlerc.com/D3011 llvm-svn: 204172
2014-03-19 03:37:50 +08:00
# RUN: yaml2obj %p/Inputs/merge-largest1.obj.yaml > %t1.obj
# RUN: yaml2obj %p/Inputs/merge-largest2.obj.yaml > %t2.obj
#
# RUN: lld -flavor link /out:%t.exe /subsystem:console /opt:noref /force \
# RUN: -- %t1.obj %t2.obj 2>&1 > %t.log
#
# FileCheck complains if the input files is empty, so add a dummy line.
# RUN: echo foo >> %t.log
# RUN: FileCheck -check-prefix=STDERR %s < %t.log
#
# RUN: llvm-readobj -sections %t.exe | FileCheck -check-prefix=READOBJ %s
STDERR-NOT: duplicate symbol error
READOBJ: Format: COFF-i386
READOBJ-NEXT: Arch: i386
READOBJ-NEXT: AddressSize: 32bit
READOBJ-NEXT: Sections [
READOBJ-NEXT: Section {
READOBJ-NEXT: Number: 1
READOBJ-NEXT: Name: .text (2E 74 65 78 74 00 00 00)
READOBJ-NEXT: VirtualSize: 0x8
READOBJ-NEXT: VirtualAddress: 0x1000
[PECOFF] Fix section header. The PE/COFF spec says that SizeOfRawData field in the section header must be a multiple of FileAlignment from the optional header. LLD emits 512 as FileAlignment, so it must have been a multiple of 512. LLD did not follow that. It emitted the actual section size without the last padding as the SizeOfRawData. Although it's not correct as per the spec, the Windows loader doesn't seem to actually bother to check that. Executables created by LLD worked fine. However, tools dealing with executalbe files may expect it to be the correct value, and one instance of it is mt.exe tool distributed as a part of Windows SDK. If CMake is invoked with "-E vs_link_exe" option, it silently run mt.exe to embed a resource file to the resulting file. And mt.exe sometimes breaks an input file if it's section header does not follow the standard. That caused a misterous error that CMake with Ninja occasionally produces a broken executable. This patch fixes the section header to make mt.exe and other tools happy. llvm-svn: 214453
2014-08-01 06:40:35 +08:00
READOBJ-NEXT: RawDataSize: 512