llvm-project/lld/test/MachO/arm64-reloc-got-load.s

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

51 lines
1.7 KiB
ArmAsm
Raw Normal View History

# REQUIRES: aarch64
[lld-macho] Fix semantics & add tests for ARM64 GOT/TLV relocs I've adjusted the RelocAttrBits to better fit the semantics of the relocations. In particular: 1. *_UNSIGNED relocations are no longer marked with the `TLV` bit, even though they can occur within TLV sections. Instead the `TLV` bit is reserved for relocations that can reference thread-local symbols, and *_UNSIGNED relocations have their own `UNSIGNED` bit. The previous implementation caused TLV and regular UNSIGNED semantics to be conflated, resulting in rebase opcodes being incorrectly emitted for TLV relocations. 2. I've added a new `POINTER` bit to denote non-relaxable GOT relocations. This distinction isn't important on x86 -- the GOT relocations there are either relaxable or non-relaxable loads -- but arm64 has `GOT_LOAD_PAGE21` which loads the page that the referent symbol is in (regardless of whether the symbol ends up in the GOT). This relocation must reference a GOT symbol (so must have the `GOT` bit set) but isn't itself relaxable (so must not have the `LOAD` bit). The `POINTER` bit is used for relocations that *must* reference a GOT slot. 3. A similar situation occurs for TLV relocations. 4. ld64 supports both a pcrel and an absolute version of ARM64_RELOC_POINTER_TO_GOT. But the semantics of the absolute version are pretty weird -- it results in the value of the GOT slot being written, rather than the address. (That means a reference to a dynamically-bound slot will result in zeroes being written.) The programs I've tried linking don't use this form of the relocation, so I've dropped our partial support for it by removing the relevant RelocAttrBits. Reviewed By: alexshap Differential Revision: https://reviews.llvm.org/D97031
2021-02-24 10:41:54 +08:00
# RUN: rm -rf %t; split-file %s %t
# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %t/main.s -o %t/main.o
# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %t/foobar.s -o %t/foobar.o
# RUN: %lld -lSystem -arch arm64 -o %t/static %t/main.o %t/foobar.o
# RUN: llvm-objdump --macho -d --no-show-raw-insn --syms %t/static | FileCheck %s --check-prefix=STATIC
# RUN: %lld -lSystem -arch arm64 -dylib -o %t/libfoo.dylib %t/foobar.o
# RUN: %lld -lSystem -arch arm64 -o %t/main %t/main.o %t/libfoo.dylib
# RUN: llvm-objdump --macho -d --no-show-raw-insn --section-headers %t/main | FileCheck %s --check-prefix=DYLIB
# STATIC-LABEL: _main:
# STATIC-NEXT: adrp x8, [[#]] ; 0x[[#%x,PAGE:]]
# STATIC-NEXT: add x8, x8, #[[#%u,FOO_OFF:]]
# STATIC-NEXT: adrp x8, [[#]] ; 0x[[#PAGE]]
# STATIC-NEXT: add x8, x8, #[[#%u,BAR_OFF:]]
[lld-macho] Fix semantics & add tests for ARM64 GOT/TLV relocs I've adjusted the RelocAttrBits to better fit the semantics of the relocations. In particular: 1. *_UNSIGNED relocations are no longer marked with the `TLV` bit, even though they can occur within TLV sections. Instead the `TLV` bit is reserved for relocations that can reference thread-local symbols, and *_UNSIGNED relocations have their own `UNSIGNED` bit. The previous implementation caused TLV and regular UNSIGNED semantics to be conflated, resulting in rebase opcodes being incorrectly emitted for TLV relocations. 2. I've added a new `POINTER` bit to denote non-relaxable GOT relocations. This distinction isn't important on x86 -- the GOT relocations there are either relaxable or non-relaxable loads -- but arm64 has `GOT_LOAD_PAGE21` which loads the page that the referent symbol is in (regardless of whether the symbol ends up in the GOT). This relocation must reference a GOT symbol (so must have the `GOT` bit set) but isn't itself relaxable (so must not have the `LOAD` bit). The `POINTER` bit is used for relocations that *must* reference a GOT slot. 3. A similar situation occurs for TLV relocations. 4. ld64 supports both a pcrel and an absolute version of ARM64_RELOC_POINTER_TO_GOT. But the semantics of the absolute version are pretty weird -- it results in the value of the GOT slot being written, rather than the address. (That means a reference to a dynamically-bound slot will result in zeroes being written.) The programs I've tried linking don't use this form of the relocation, so I've dropped our partial support for it by removing the relevant RelocAttrBits. Reviewed By: alexshap Differential Revision: https://reviews.llvm.org/D97031
2021-02-24 10:41:54 +08:00
# STATIC-NEXT: ret
# STATIC-LABEL: SYMBOL TABLE:
# STATIC-DAG: {{0*}}[[#%x,PAGE+FOO_OFF]] g F __TEXT,__text _foo
# STATIC-DAG: {{0*}}[[#%x,PAGE+BAR_OFF]] g F __TEXT,__text _bar
# DYLIB-LABEL: _main:
# DYLIB-NEXT: adrp x8, [[#]] ; 0x[[#%x,GOT:]]
# DYLIB-NEXT: ldr x8, [x8, #8] ; literal pool symbol address: _foo
# DYLIB-NEXT: adrp x8, [[#]] ; 0x[[#GOT]]
# DYLIB-NEXT: ldr x8, [x8] ; literal pool symbol address: _bar
[lld-macho] Fix semantics & add tests for ARM64 GOT/TLV relocs I've adjusted the RelocAttrBits to better fit the semantics of the relocations. In particular: 1. *_UNSIGNED relocations are no longer marked with the `TLV` bit, even though they can occur within TLV sections. Instead the `TLV` bit is reserved for relocations that can reference thread-local symbols, and *_UNSIGNED relocations have their own `UNSIGNED` bit. The previous implementation caused TLV and regular UNSIGNED semantics to be conflated, resulting in rebase opcodes being incorrectly emitted for TLV relocations. 2. I've added a new `POINTER` bit to denote non-relaxable GOT relocations. This distinction isn't important on x86 -- the GOT relocations there are either relaxable or non-relaxable loads -- but arm64 has `GOT_LOAD_PAGE21` which loads the page that the referent symbol is in (regardless of whether the symbol ends up in the GOT). This relocation must reference a GOT symbol (so must have the `GOT` bit set) but isn't itself relaxable (so must not have the `LOAD` bit). The `POINTER` bit is used for relocations that *must* reference a GOT slot. 3. A similar situation occurs for TLV relocations. 4. ld64 supports both a pcrel and an absolute version of ARM64_RELOC_POINTER_TO_GOT. But the semantics of the absolute version are pretty weird -- it results in the value of the GOT slot being written, rather than the address. (That means a reference to a dynamically-bound slot will result in zeroes being written.) The programs I've tried linking don't use this form of the relocation, so I've dropped our partial support for it by removing the relevant RelocAttrBits. Reviewed By: alexshap Differential Revision: https://reviews.llvm.org/D97031
2021-02-24 10:41:54 +08:00
# DYLIB-NEXT: ret
# DYLIB-NEXT: Sections:
# DYLIB-NEXT: Idx Name Size VMA Type
# DYLIB: [[#]] __got 00000010 {{0*}}[[#GOT]] DATA
#--- main.s
.globl _main, _foo, _bar
.p2align 2
_main:
adrp x8, _foo@GOTPAGE
ldr x8, [x8, _foo@GOTPAGEOFF]
adrp x8, _bar@GOTPAGE
ldr x8, [x8, _bar@GOTPAGEOFF]
[lld-macho] Fix semantics & add tests for ARM64 GOT/TLV relocs I've adjusted the RelocAttrBits to better fit the semantics of the relocations. In particular: 1. *_UNSIGNED relocations are no longer marked with the `TLV` bit, even though they can occur within TLV sections. Instead the `TLV` bit is reserved for relocations that can reference thread-local symbols, and *_UNSIGNED relocations have their own `UNSIGNED` bit. The previous implementation caused TLV and regular UNSIGNED semantics to be conflated, resulting in rebase opcodes being incorrectly emitted for TLV relocations. 2. I've added a new `POINTER` bit to denote non-relaxable GOT relocations. This distinction isn't important on x86 -- the GOT relocations there are either relaxable or non-relaxable loads -- but arm64 has `GOT_LOAD_PAGE21` which loads the page that the referent symbol is in (regardless of whether the symbol ends up in the GOT). This relocation must reference a GOT symbol (so must have the `GOT` bit set) but isn't itself relaxable (so must not have the `LOAD` bit). The `POINTER` bit is used for relocations that *must* reference a GOT slot. 3. A similar situation occurs for TLV relocations. 4. ld64 supports both a pcrel and an absolute version of ARM64_RELOC_POINTER_TO_GOT. But the semantics of the absolute version are pretty weird -- it results in the value of the GOT slot being written, rather than the address. (That means a reference to a dynamically-bound slot will result in zeroes being written.) The programs I've tried linking don't use this form of the relocation, so I've dropped our partial support for it by removing the relevant RelocAttrBits. Reviewed By: alexshap Differential Revision: https://reviews.llvm.org/D97031
2021-02-24 10:41:54 +08:00
ret
#--- foobar.s
.globl _foo, _bar
_foo:
.space 0
_bar:
.space 0