maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/lld/test/ELF/arm-thumb2-ldrlit-err.s

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

31 lines
748 B
ArmAsm
Raw Normal View History

[ELF][LLD][ARM] Add missing REQUIRES: arm to tests Fix buildbots that don't build ARM backend.
2020-02-28 19:44:32 +08:00
// REQUIRES: arm
[LLD][ELF][ARM] use .reloc directive for Thumb assembler tests In the near future llvm-mc will resolve the fixups that generate R_ARM_THUMB_PC8 and R_ARM_THUMB_PC12 at assembly time (see comments in D72892), and forbid inter-section references. Change the LLD tests for these relocations to use .inst and .reloc to avoid LLD tests failing when this happens. The tests generate the same instructions, relocations and symbols. I will need to make equivalent changes for D75349 Arm equivalent relocations, but this is still in review so these don't need changing before llvm-mc. Differential Revision: https://reviews.llvm.org/D77200
2020-03-30 22:04:26 +08:00
// RUN: llvm-mc --triple=thumbv7m-none-eabi --arm-add-build-attributes -filetype=obj -o %t.o %s
[LLD][ELF][ARM] Implement Thumb pc-relative relocations for adr and ldr MC will now output the R_ARM_THM_PC8, R_ARM_THM_PC12 and R_ARM_THM_PREL_11_0 relocations. These are short-ranged relocations that are used to implement the adr rd, literal and ldr rd, literal pseudo instructions. The instructions use a new RelExpr called R_ARM_PCA in order to calculate the required S + A - Pa expression, where Pa is AlignDown(P, 4) as the instructions add their immediate to AlignDown(PC, 4). We also do not want these relocations to generate or resolve against a PLT entry as the range of these relocations is so short they would never reach. The R_ARM_THM_PC8 has a special encoding convention for the relocation addend, the immediate field is unsigned, yet the addend must be -4 to account for the Thumb PC bias. The ABI (not the architecture) uses the convention that the 8-byte immediate of 0xff represents -4. Differential Revision: https://reviews.llvm.org/D75042
2020-02-24 03:46:46 +08:00
// RUN: not ld.lld %t.o -o /dev/null 2>&1 | FileCheck %s
.section .text.0, "ax", %progbits
.thumb_func
.balign 4
low:
bx lr
nop
nop
.section .text.1, "ax", %progbits
.global _start
.thumb_func
_start:
[LLD][ELF][ARM] use .reloc directive for Thumb assembler tests In the near future llvm-mc will resolve the fixups that generate R_ARM_THUMB_PC8 and R_ARM_THUMB_PC12 at assembly time (see comments in D72892), and forbid inter-section references. Change the LLD tests for these relocations to use .inst and .reloc to avoid LLD tests failing when this happens. The tests generate the same instructions, relocations and symbols. I will need to make equivalent changes for D75349 Arm equivalent relocations, but this is still in review so these don't need changing before llvm-mc. Differential Revision: https://reviews.llvm.org/D77200
2020-03-30 22:04:26 +08:00
// CHECK: {{.*}}.s.tmp.o:(.text.1+0x0): relocation R_ARM_THM_PC12 out of range: 4098 is not in [0, 4095]
/// ldr.w r0, low - 4091
.inst.w 0xf85f0fff
.reloc 0, R_ARM_THM_PC12, low
// CHECK: {{.*}}.s.tmp.o:(.text.1+0x4): relocation R_ARM_THM_PC12 out of range: 4096 is not in [0, 4095]
/// ldr.w r0, high + 4091
.inst.w 0xf8df0ff7
.reloc 4, R_ARM_THM_PC12, high
[LLD][ELF][ARM] Implement Thumb pc-relative relocations for adr and ldr MC will now output the R_ARM_THM_PC8, R_ARM_THM_PC12 and R_ARM_THM_PREL_11_0 relocations. These are short-ranged relocations that are used to implement the adr rd, literal and ldr rd, literal pseudo instructions. The instructions use a new RelExpr called R_ARM_PCA in order to calculate the required S + A - Pa expression, where Pa is AlignDown(P, 4) as the instructions add their immediate to AlignDown(PC, 4). We also do not want these relocations to generate or resolve against a PLT entry as the range of these relocations is so short they would never reach. The R_ARM_THM_PC8 has a special encoding convention for the relocation addend, the immediate field is unsigned, yet the addend must be -4 to account for the Thumb PC bias. The ABI (not the architecture) uses the convention that the 8-byte immediate of 0xff represents -4. Differential Revision: https://reviews.llvm.org/D75042
2020-02-24 03:46:46 +08:00
.section .text.2
.thumb_func
.balign 4
high:
bx lr