maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/MC/MachO/debug_frame.s

59 lines
1.8 KiB
ArmAsm
Raw Normal View History

[MC] Convert other MachO tests from macho-dump to llvm-readobj. This commit accomplish two goals: 1) it's a step forward to deprecate macho-dump, now less than 40 tests rely on it. 2) It tests all the MachO specific features introduced in llvm-readobj in the following commits: r246789, r246665, r246474. While the conversion is mostly mechanical (I double-checked all the tests output one by one, but still), a post-commit review is greatly appreciated. llvm-svn: 246904
2015-09-05 09:02:05 +08:00
// RUN: llvm-mc -triple i386-apple-darwin %s -filetype=obj -o - | llvm-readobj -s -sd -r | FileCheck %s
On MachO, unlike ELF, there should be no relocation to produce the CIE pointer. llvm-svn: 131149
2011-05-11 04:59:42 +08:00
Some autoconf tests use module level inline asm to test compiler's handling of .cfi_startproc. e.g. libffi: $ cat confopt.c asm (".cfi_startproc\n\t.cfi_endproc"); int main () { return 0; } Teach MC / dwarf emission to handle these cfi directives which essentially create an empty frame. rdar://10017184 llvm-svn: 138504
2011-08-25 06:31:37 +08:00
// Make sure MC can handle file level .cfi_startproc and .cfi_endproc that creates
// an empty frame.
// rdar://10017184
[MC] Emit an error if cfi_startproc is used before a symbol is defined. Currently, we bind those directives with the last symbol, so if none has been defined, this would lead to a crash of the compiler. <rdar://problem/15939159> llvm-svn: 206236
2014-04-15 09:17:45 +08:00
_proc:
Some autoconf tests use module level inline asm to test compiler's handling of .cfi_startproc. e.g. libffi: $ cat confopt.c asm (".cfi_startproc\n\t.cfi_endproc"); int main () { return 0; } Teach MC / dwarf emission to handle these cfi directives which essentially create an empty frame. rdar://10017184 llvm-svn: 138504
2011-08-25 06:31:37 +08:00
.cfi_startproc
.cfi_endproc
On MachO, unlike ELF, there should be no relocation to produce the CIE pointer. llvm-svn: 131149
2011-05-11 04:59:42 +08:00
// Check that we don't produce a relocation for the CIE pointer and therefore
// we have only one relocation in __debug_frame.
.section __TEXT,__text,regular,pure_instructions
.globl _f
.align 4, 0x90
_f: ## @f
Ltmp0:
.cfi_startproc
## BB#0: ## %entry
movl $42, %eax
ret
Ltmp1:
.cfi_endproc
Leh_func_end0:
.cfi_sections .debug_frame
Ltext_end:
[MC] Convert other MachO tests from macho-dump to llvm-readobj. This commit accomplish two goals: 1) it's a step forward to deprecate macho-dump, now less than 40 tests rely on it. 2) It tests all the MachO specific features introduced in llvm-readobj in the following commits: r246789, r246665, r246474. While the conversion is mostly mechanical (I double-checked all the tests output one by one, but still), a post-commit review is greatly appreciated. llvm-svn: 246904
2015-09-05 09:02:05 +08:00
// CHECK: Section {
// CHECK: Index: 1
// CHECK: Name: __debug_frame (5F 5F 64 65 62 75 67 5F 66 72 61 6D 65 00 00 00)
// CHECK: Segment: __DWARF (5F 5F 44 57 41 52 46 00 00 00 00 00 00 00 00 00)
// CHECK: Address: 0x8
// CHECK: Size: 0x34
// CHECK: Offset: 332
// CHECK: Alignment: 2
// CHECK: RelocationOffset: 0x180
// CHECK: RelocationCount: 2
// CHECK: Type: 0x0
// CHECK: Attributes [ (0x20000)
// CHECK: Debug (0x20000)
// CHECK: ]
// CHECK: Reserved1: 0x0
// CHECK: Reserved2: 0x0
// CHECK: SectionData (
// CHECK: 0000: 10000000 FFFFFFFF 04000400 017C080C |.............|..|
// CHECK: 0010: 04048801 0C000000 00000000 00000000 |................|
// CHECK: 0020: 00000000 0C000000 00000000 00000000 |................|
// CHECK: 0030: 06000000 |....|
// CHECK: )
// CHECK: }
// CHECK: ]
// CHECK: Relocations [
// CHECK: Section __debug_frame {
// CHECK: 0x2C 0 2 0 GENERIC_RELOC_VANILLA 0 __text
// CHECK: 0x1C 0 2 0 GENERIC_RELOC_VANILLA 0 __text
// CHECK: }
// CHECK: ]