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

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

25 lines
1.0 KiB
Plaintext
Raw Normal View History

[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
# REQUIRES: x86
[test] Replace `yaml2obj >` with `yaml2obj -o` and remove unneeded input redirection
2020-08-21 06:00:25 +08:00
# RUN: yaml2obj %p/Inputs/hello32.yaml -o %t.obj
[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
#
[COFF] Implement /safeseh:no and check @feat.00 flags by default Summary: Fixes PR41828. Before this, LLD always emitted SafeSEH chunks and defined __safe_se_handler_table & size. Now, /safeseh:no leaves those undefined. Additionally, we were checking for the safeseh @feat.00 flag in two places: once to emit errors, and once during safeseh table construction. The error was set up to be off by default, but safeseh is supposed to be on by default. I combined the two checks, so now LLD emits an error if an input object lacks @feat.00 and safeseh is enabled. This caused the majority of 32-bit LLD tests to fail, since many test input object files lack @feat.00 symbols. I explicitly added -safeseh:no to those tests to preserve behavior. Finally, LLD no longer sets IMAGE_DLL_CHARACTERISTICS_NO_SEH if any input file wasn't compiled for safeseh. Reviewers: mstorsjo, ruiu, thakis Reviewed By: ruiu, thakis Subscribers: llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63570 llvm-svn: 366238
2019-07-17 02:17:33 +08:00
# RUN: lld-link -safeseh:no %t.obj /fixed %p/Inputs/std32.lib /subsystem:console \
[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
# RUN: /entry:main@0 /debug /out:%t.fixed.exe
[test] Change llvm-readobj -long-option to --long-option or well-known short options. NFC Also change some options that have different semantics (cause confusion) in llvm-readelf mode: -s => -S -t => --symbols -sd => --section-data llvm-svn: 359651
2019-05-01 13:49:01 +08:00
# RUN: llvm-readobj --file-headers %t.fixed.exe | \
[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
# RUN: FileCheck -check-prefix=EXEFIXED %s
#
[COFF] Implement /safeseh:no and check @feat.00 flags by default Summary: Fixes PR41828. Before this, LLD always emitted SafeSEH chunks and defined __safe_se_handler_table & size. Now, /safeseh:no leaves those undefined. Additionally, we were checking for the safeseh @feat.00 flag in two places: once to emit errors, and once during safeseh table construction. The error was set up to be off by default, but safeseh is supposed to be on by default. I combined the two checks, so now LLD emits an error if an input object lacks @feat.00 and safeseh is enabled. This caused the majority of 32-bit LLD tests to fail, since many test input object files lack @feat.00 symbols. I explicitly added -safeseh:no to those tests to preserve behavior. Finally, LLD no longer sets IMAGE_DLL_CHARACTERISTICS_NO_SEH if any input file wasn't compiled for safeseh. Reviewers: mstorsjo, ruiu, thakis Reviewed By: ruiu, thakis Subscribers: llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63570 llvm-svn: 366238
2019-07-17 02:17:33 +08:00
# RUN: lld-link -safeseh:no %t.obj %p/Inputs/std32.lib /subsystem:console \
[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
# RUN: /entry:main@0 /debug /out:%t.exe
[test] Change llvm-readobj -long-option to --long-option or well-known short options. NFC Also change some options that have different semantics (cause confusion) in llvm-readelf mode: -s => -S -t => --symbols -sd => --section-data llvm-svn: 359651
2019-05-01 13:49:01 +08:00
# RUN: llvm-readobj --file-headers %t.exe | FileCheck -check-prefix=EXEREL %s
[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
#
[test] Replace `yaml2obj >` with `yaml2obj -o` and remove unneeded input redirection
2020-08-21 06:00:25 +08:00
# RUN: yaml2obj %p/Inputs/export.yaml -o %t.obj
[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
#
[COFF] Implement /safeseh:no and check @feat.00 flags by default Summary: Fixes PR41828. Before this, LLD always emitted SafeSEH chunks and defined __safe_se_handler_table & size. Now, /safeseh:no leaves those undefined. Additionally, we were checking for the safeseh @feat.00 flag in two places: once to emit errors, and once during safeseh table construction. The error was set up to be off by default, but safeseh is supposed to be on by default. I combined the two checks, so now LLD emits an error if an input object lacks @feat.00 and safeseh is enabled. This caused the majority of 32-bit LLD tests to fail, since many test input object files lack @feat.00 symbols. I explicitly added -safeseh:no to those tests to preserve behavior. Finally, LLD no longer sets IMAGE_DLL_CHARACTERISTICS_NO_SEH if any input file wasn't compiled for safeseh. Reviewers: mstorsjo, ruiu, thakis Reviewed By: ruiu, thakis Subscribers: llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63570 llvm-svn: 366238
2019-07-17 02:17:33 +08:00
# RUN: lld-link -safeseh:no %t.obj /dll /fixed /debug /out:%t.fixed.dll
[test] Change llvm-readobj -long-option to --long-option or well-known short options. NFC Also change some options that have different semantics (cause confusion) in llvm-readelf mode: -s => -S -t => --symbols -sd => --section-data llvm-svn: 359651
2019-05-01 13:49:01 +08:00
# RUN: llvm-readobj --file-headers %t.fixed.dll | FileCheck -check-prefix=DLLFIXED %s
[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
#
[COFF] Implement /safeseh:no and check @feat.00 flags by default Summary: Fixes PR41828. Before this, LLD always emitted SafeSEH chunks and defined __safe_se_handler_table & size. Now, /safeseh:no leaves those undefined. Additionally, we were checking for the safeseh @feat.00 flag in two places: once to emit errors, and once during safeseh table construction. The error was set up to be off by default, but safeseh is supposed to be on by default. I combined the two checks, so now LLD emits an error if an input object lacks @feat.00 and safeseh is enabled. This caused the majority of 32-bit LLD tests to fail, since many test input object files lack @feat.00 symbols. I explicitly added -safeseh:no to those tests to preserve behavior. Finally, LLD no longer sets IMAGE_DLL_CHARACTERISTICS_NO_SEH if any input file wasn't compiled for safeseh. Reviewers: mstorsjo, ruiu, thakis Reviewed By: ruiu, thakis Subscribers: llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63570 llvm-svn: 366238
2019-07-17 02:17:33 +08:00
# RUN: lld-link -safeseh:no %t.obj /dll /debug /out:%t.dll
[test] Change llvm-readobj -long-option to --long-option or well-known short options. NFC Also change some options that have different semantics (cause confusion) in llvm-readelf mode: -s => -S -t => --symbols -sd => --section-data llvm-svn: 359651
2019-05-01 13:49:01 +08:00
# RUN: llvm-readobj --file-headers %t.dll | FileCheck -check-prefix=DLLREL %s
[lld-link] Add comment explaining that /FIXED behavior is correct despite contradicting MSDN. Also add a test for /FIXED. https://reviews.llvm.org/D45087 llvm-svn: 328879
2018-03-31 01:17:04 +08:00
EXEFIXED-NOT: IMAGE_DLL_CHARACTERISTICS_DYNAMIC_BASE
DLLFIXED-NOT: IMAGE_DLL_CHARACTERISTICS_DYNAMIC_BASE
EXEREL: IMAGE_DLL_CHARACTERISTICS_DYNAMIC_BASE
DLLREL: IMAGE_DLL_CHARACTERISTICS_DYNAMIC_BASE