maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/lld/test/mach-o/arm64-reloc-negDelta32-fixu...

125 lines
4.6 KiB
YAML
Raw Normal View History

Fix negDelta32 relocatable fixups for arm64 in mach-o. negDelta32 is only ever implicitly generated as the FDE->CIE reference. We therefore don't emit a relocation for it in the object file in -r mode. The value we write in to the FDE location therefore needs to point to the final target address of the CIE, and not the inAtomAddress as it was currently doing. llvm-svn: 255835
2015-12-17 06:50:16 +08:00
# RUN: lld -flavor darwin -arch arm64 -r %s -o %t
# RUN: lld -flavor darwin -arch arm64 -r %t -o %t2
# RUN: llvm-objdump -s -section="__eh_frame" %t | FileCheck %s
# RUN: llvm-objdump -s -section="__eh_frame" %t2 | FileCheck %s
# The reference from FDE->CIE is implicitly created as a negDelta32.
# We don't emit these in to the binary as relocations, so we need to
# make sure that the offset in the FDE to the CIE is the correct value.
Sort sections in relocatable files. The final section order in relocatable files was just a side effect of the atom sorter. This meant that sections like __data were before __text because __data has RW permissions and __text RX and RW was less than RX in our enum. Final linked images had an actual section/segment sorter. There was no reason for the difference, so simplify a bunch of code and just use the same sorted for everything. Reviewed by Lang Hames. http://reviews.llvm.org/D15868 llvm-svn: 256786
2016-01-05 06:29:36 +08:00
# CHECK: {{[0-9abcdef]*}} 10000000 00000000 017a5200 01781e01
Fix offset in test case. NFC It wasn't actually pointing to the function at the start of the text section, and so the offset in the binary differed when we passed the file through a second time. The __eh_frame section uses implicit relocations and when reducing this test case from explicit to implicit, I got the offset wrong. This makes sure it is correct. llvm-svn: 257101
2016-01-08 05:12:30 +08:00
# CHECK: {{[0-9abcdef]*}} 100c1f00 20000000 18000000 b8ffffff
Fix test case comment after r256786. NFC. The comment spacing was meant to show the interesting bytes in the prior line, but the prior line moved slightly. llvm-svn: 256800
2016-01-05 08:47:22 +08:00
# Note, this one that matters ^~~~~~~~
Fix negDelta32 relocatable fixups for arm64 in mach-o. negDelta32 is only ever implicitly generated as the FDE->CIE reference. We therefore don't emit a relocation for it in the object file in -r mode. The value we write in to the FDE location therefore needs to point to the final target address of the CIE, and not the inAtomAddress as it was currently doing. llvm-svn: 255835
2015-12-17 06:50:16 +08:00
# It needs to be 0x18 as that is the offset back to 0 where the CIE is.
Sort sections in relocatable files. The final section order in relocatable files was just a side effect of the atom sorter. This meant that sections like __data were before __text because __data has RW permissions and __text RX and RW was less than RX in our enum. Final linked images had an actual section/segment sorter. There was no reason for the difference, so simplify a bunch of code and just use the same sorted for everything. Reviewed by Lang Hames. http://reviews.llvm.org/D15868 llvm-svn: 256786
2016-01-05 06:29:36 +08:00
# CHECK: {{[0-9abcdef]*}} ffffffff 20000000 00000000 00480e10
# CHECK: {{[0-9abcdef]*}} 9e019d02 00000000
Fix negDelta32 relocatable fixups for arm64 in mach-o. negDelta32 is only ever implicitly generated as the FDE->CIE reference. We therefore don't emit a relocation for it in the object file in -r mode. The value we write in to the FDE location therefore needs to point to the final target address of the CIE, and not the inAtomAddress as it was currently doing. llvm-svn: 255835
2015-12-17 06:50:16 +08:00
--- !mach-o
arch: arm64
file-type: MH_OBJECT
flags: [ MH_SUBSECTIONS_VIA_SYMBOLS ]
compat-version: 0.0
current-version: 0.0
has-UUID: false
OS: unknown
sections:
- segment: __TEXT
section: __text
type: S_REGULAR
attributes: [ S_ATTR_PURE_INSTRUCTIONS, S_ATTR_SOME_INSTRUCTIONS ]
alignment: 4
address: 0x0000000000000000
content: [ 0xFD, 0x7B, 0xBF, 0xA9, 0xFD, 0x03, 0x00, 0x91,
0x00, 0x00, 0x00, 0x90, 0x00, 0x00, 0x00, 0x91,
0x00, 0x00, 0x00, 0x94, 0x00, 0x00, 0x80, 0x52,
0xFD, 0x7B, 0xC1, 0xA8, 0xC0, 0x03, 0x5F, 0xD6 ]
relocations:
- offset: 0x00000010
type: ARM64_RELOC_BRANCH26
length: 2
pc-rel: true
extern: true
symbol: 6
- offset: 0x0000000C
type: ARM64_RELOC_PAGEOFF12
length: 2
pc-rel: false
extern: true
symbol: 1
- offset: 0x00000008
type: ARM64_RELOC_PAGE21
length: 2
pc-rel: true
extern: true
symbol: 1
- segment: __TEXT
section: __cstring
type: S_CSTRING_LITERALS
attributes: [ ]
address: 0x0000000000000020
content: [ 0x48, 0x65, 0x6C, 0x6C, 0x6F, 0x20, 0x77, 0x6F,
0x72, 0x6C, 0x64, 0x00 ]
- segment: __LD
section: __compact_unwind
type: S_REGULAR
attributes: [ ]
alignment: 8
address: 0x0000000000000030
content: [ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x20, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 ]
relocations:
- offset: 0x00000000
type: ARM64_RELOC_UNSIGNED
length: 3
pc-rel: false
extern: false
symbol: 1
- segment: __TEXT
section: __eh_frame
type: S_COALESCED
attributes: [ ]
alignment: 8
address: 0x0000000000000050
content: [ 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x01, 0x7A, 0x52, 0x00, 0x01, 0x78, 0x1E, 0x01,
0x10, 0x0C, 0x1F, 0x00, 0x20, 0x00, 0x00, 0x00,
Fix offset in test case. NFC It wasn't actually pointing to the function at the start of the text section, and so the offset in the binary differed when we passed the file through a second time. The __eh_frame section uses implicit relocations and when reducing this test case from explicit to implicit, I got the offset wrong. This makes sure it is correct. llvm-svn: 257101
2016-01-08 05:12:30 +08:00
0x18, 0x00, 0x00, 0x00, 0x94, 0xFF, 0xFF, 0xFF,
Fix negDelta32 relocatable fixups for arm64 in mach-o. negDelta32 is only ever implicitly generated as the FDE->CIE reference. We therefore don't emit a relocation for it in the object file in -r mode. The value we write in to the FDE location therefore needs to point to the final target address of the CIE, and not the inAtomAddress as it was currently doing. llvm-svn: 255835
2015-12-17 06:50:16 +08:00
0xFF, 0xFF, 0xFF, 0xFF, 0x20, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x48, 0x0E, 0x10,
0x9E, 0x01, 0x9D, 0x02, 0x00, 0x00, 0x00, 0x00 ]
local-symbols:
- name: ltmp0
type: N_SECT
sect: 1
value: 0x0000000000000000
- name: L_str
type: N_SECT
sect: 2
value: 0x0000000000000020
- name: ltmp1
type: N_SECT
sect: 2
value: 0x0000000000000020
- name: ltmp2
type: N_SECT
sect: 3
value: 0x0000000000000030
- name: ltmp3
type: N_SECT
sect: 4
value: 0x0000000000000050
global-symbols:
- name: __Z3fooi
type: N_SECT
scope: [ N_EXT ]
sect: 1
value: 0x0000000000000000
undefined-symbols:
- name: _puts
type: N_UNDF
scope: [ N_EXT ]
value: 0x0000000000000000
page-size: 0x00000000
...