ELF/AMDGPU: Add support for R_AMDGPU_ABS32

[• tstellarAMD]

test/ELF/amdgpu-relocs-abs32.s

23

Is the full kernel_code_t definition required for this test?

[kzhuravl]

Rebase and update test

[ruiu]

ELF/Target.cpp

1425–1427

Sort alphabetically.

[• rafael]

we don't use llc to test elf lld.

[kzhuravl]

Feedback + update test

[ruiu]

Verifying an entire dwarf file to test ABS32 relocations seems a bit overkill. Why don't you add a few lines to test/ELF/amdgpu-relocs.s?

[kzhuravl]

R_AMDGPU_ABS32 relocations are only generated for dwarf

[ruiu]

The fact that ABS32 is generated only for DWARF does not necessarily mean that you need to create a DWARF to verify the behavior of the relocation. I was trying to say was that the test is too big compared to the size of the feature that is testing; it mostly verifies the structure of DWARF rather than the relocation. A test for ABS32 can be written in a few lines.

[kzhuravl]

Update test

[ruiu]

Don't you want to verify the contents of .data section?

[kzhuravl]

Update test

[ruiu]

LGTM

ELF/Target.cpp

 
 void AMDGPUTargetInfo::relocateOne(uint8_t *Loc, uint32_t Type,
                                    uint64_t Val) const {
-  assert(Type == R_AMDGPU_REL32);
-  write32le(Loc, Val);
+  switch (Type) {
+  default:
+    llvm_unreachable("unsupported relocation type");
+  case R_AMDGPU_ABS32:
+  case R_AMDGPU_REL32:
+    write32le(Loc, Val);
+    break;
+  }
 }
 
 RelExpr AMDGPUTargetInfo::getRelExpr(uint32_t Type, const SymbolBody &S) const {
-  if (Type != R_AMDGPU_REL32)
-    error("do not know how to handle relocation");
-  return R_PC;
+  switch (Type) {
+  default:
+    llvm_unreachable("unsupported relocation type");
+  case R_AMDGPU_ABS32:
+    return R_ABS;
+  case R_AMDGPU_REL32:
+    return R_PC;
+  }
 }
 
 ARMTargetInfo::ARMTargetInfo() {

test/ELF/amdgpu-relocs-abs32.s

+; RUN: llvm-mc -filetype=obj -triple=amdgcn--amdhsa -mcpu=fiji %s -o %t.o
+; RUN: llvm-dwarfdump -debug-dump=info %t.o | FileCheck %s
+
+; CHECK: DW_AT_producer [DW_FORM_strp]     ( .debug_str[0x00000000] = "clang version 3.9.0 (trunk 273560)")
+; CHECK: DW_AT_name [DW_FORM_strp] ( .debug_str[0x00000023] = "relocs.cl")
+; CHECK: DW_AT_comp_dir [DW_FORM_strp]     ( .debug_str[0x0000002d] = "/home/kzhuravl/Lightning/test")
+; CHECK: DW_AT_name [DW_FORM_strp]     ( .debug_str[0x00000052] = "A")
+; CHECK: DW_AT_name [DW_FORM_strp]       ( .debug_str[0x00000054] = "int")
+
+  .text
+  .hsa_code_object_version 2,0
+  .hsa_code_object_isa 8,0,3,"AMD","AMDGPU"
+  .section  .AMDGPU.config
+  .text
+  .globl  relocs
+  .p2align  8
+  .type relocs,@function
+  .amdgpu_hsa_kernel relocs
+relocs:                                 ; @relocs
+.Lfunc_begin0:
+  .file 1 "relocs.cl"
+  .loc  1 1 0                   ; relocs.cl:1:0
+  .amd_kernel_code_t
+    kernel_code_version_major = 1
+    kernel_code_version_minor = 0
+    machine_kind = 1
+    machine_version_major = 8
+    machine_version_minor = 0
+    machine_version_stepping = 3
+    kernel_code_entry_byte_offset = 256
+    kernel_code_prefetch_byte_size = 0
+    max_scratch_backing_memory_byte_size = 0
+    compute_pgm_rsrc1_vgprs = 0
+    compute_pgm_rsrc1_sgprs = 1
+    compute_pgm_rsrc1_priority = 0
+    compute_pgm_rsrc1_float_mode = 192
+    compute_pgm_rsrc1_priv = 0
+    compute_pgm_rsrc1_dx10_clamp = 1
+    compute_pgm_rsrc1_debug_mode = 0
+    compute_pgm_rsrc1_ieee_mode = 0
+    compute_pgm_rsrc2_scratch_en = 0
+    compute_pgm_rsrc2_user_sgpr = 6
+    compute_pgm_rsrc2_tgid_x_en = 1
+    compute_pgm_rsrc2_tgid_y_en = 0
+    compute_pgm_rsrc2_tgid_z_en = 0
+    compute_pgm_rsrc2_tg_size_en = 0
+    compute_pgm_rsrc2_tidig_comp_cnt = 0
+    compute_pgm_rsrc2_excp_en_msb = 0
+    compute_pgm_rsrc2_lds_size = 0
+    compute_pgm_rsrc2_excp_en = 0
+    enable_sgpr_private_segment_buffer = 1
+    enable_sgpr_dispatch_ptr = 0
+    enable_sgpr_queue_ptr = 0
+    enable_sgpr_kernarg_segment_ptr = 1
+    enable_sgpr_dispatch_id = 0
+    enable_sgpr_flat_scratch_init = 0
+    enable_sgpr_private_segment_size = 0
+    enable_sgpr_grid_workgroup_count_x = 0
+    enable_sgpr_grid_workgroup_count_y = 0
+    enable_sgpr_grid_workgroup_count_z = 0
+    enable_ordered_append_gds = 0
+    private_element_size = 1
+    is_ptr64 = 1
+    is_dynamic_callstack = 0
+    is_debug_enabled = 0
+    is_xnack_enabled = 0
+    workitem_private_segment_byte_size = 0
+    workgroup_group_segment_byte_size = 0
+    gds_segment_byte_size = 0
+    kernarg_segment_byte_size = 8
+    workgroup_fbarrier_count = 0
+    wavefront_sgpr_count = 12
+    workitem_vgpr_count = 3
+    reserved_vgpr_first = 0
+    reserved_vgpr_count = 0
+    reserved_sgpr_first = 0
+    reserved_sgpr_count = 0
+    debug_wavefront_private_segment_offset_sgpr = 0
+    debug_private_segment_buffer_sgpr = 0
+    kernarg_segment_alignment = 4
+    group_segment_alignment = 4
+    private_segment_alignment = 4
+    wavefront_size = 6
+    call_convention = 0
+    runtime_loader_kernel_symbol = 0
+  .end_amd_kernel_code_t
+; BB#0:                                 ; %entry
+  s_load_dwordx2 s[0:1], s[4:5], 0x0
+.Ltmp0:
+  .loc  1 2 6 prologue_end      ; relocs.cl:2:6
+  v_mov_b32_e32 v2, 0x7b
+  s_waitcnt lgkmcnt(0)
+  v_mov_b32_e32 v0, s0
+  v_mov_b32_e32 v1, s1
+  flat_store_dword v[0:1], v2
+  .loc  1 3 1                   ; relocs.cl:3:1
+  s_endpgm
+.Ltmp1:
+.Lfunc_end0:
+  .size relocs, .Lfunc_end0-relocs
+
+  .section  .AMDGPU.csdata
+; Kernel info:
+; codeLenInByte = 36
+; NumSgprs: 12
+; NumVgprs: 3
+; FloatMode: 192
+; IeeeMode: 0
+; ScratchSize: 0
+; LDSByteSize: 0 bytes/workgroup (compile time only)
+; ReservedVGPRFirst: 0
+; ReservedVGPRCount: 0
+; COMPUTE_PGM_RSRC2:USER_SGPR: 6
+; COMPUTE_PGM_RSRC2:TGID_X_EN: 1
+; COMPUTE_PGM_RSRC2:TGID_Y_EN: 0
+; COMPUTE_PGM_RSRC2:TGID_Z_EN: 0
+; COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
+  .section  .debug_str,"MS",@progbits,1
+.Linfo_string0:
+  .asciz  "clang version 3.9.0 (trunk 273560)" ; string offset=0
+.Linfo_string1:
+  .asciz  "relocs.cl"             ; string offset=35
+.Linfo_string2:
+  .asciz  "/home/kzhuravl/Lightning/test" ; string offset=45
+.Linfo_string3:
+  .asciz  "relocs"                ; string offset=75
+.Linfo_string4:
+  .asciz  "A"                     ; string offset=82
+.Linfo_string5:
+  .asciz  "int"                   ; string offset=84
+  .section  .debug_loc
+  .section  .debug_abbrev
+.Lsection_abbrev:
+  .byte 1                       ; Abbreviation Code
+  .byte 17                      ; DW_TAG_compile_unit
+  .byte 1                       ; DW_CHILDREN_yes
+  .byte 37                      ; DW_AT_producer
+  .byte 14                      ; DW_FORM_strp
+  .byte 19                      ; DW_AT_language
+  .byte 5                       ; DW_FORM_data2
+  .byte 3                       ; DW_AT_name
+  .byte 14                      ; DW_FORM_strp
+  .byte 16                      ; DW_AT_stmt_list
+  .byte 6                       ; DW_FORM_data4
+  .byte 27                      ; DW_AT_comp_dir
+  .byte 14                      ; DW_FORM_strp
+  .byte 17                      ; DW_AT_low_pc
+  .byte 1                       ; DW_FORM_addr
+  .byte 18                      ; DW_AT_high_pc
+  .byte 1                       ; DW_FORM_addr
+  .byte 0                       ; EOM(1)
+  .byte 0                       ; EOM(2)
+  .byte 2                       ; Abbreviation Code
+  .byte 46                      ; DW_TAG_subprogram
+  .byte 1                       ; DW_CHILDREN_yes
+  .byte 17                      ; DW_AT_low_pc
+  .byte 1                       ; DW_FORM_addr
+  .byte 18                      ; DW_AT_high_pc
+  .byte 1                       ; DW_FORM_addr
+  .byte 3                       ; DW_AT_name
+  .byte 14                      ; DW_FORM_strp
+  .byte 58                      ; DW_AT_decl_file
+  .byte 11                      ; DW_FORM_data1
+  .byte 59                      ; DW_AT_decl_line
+  .byte 11                      ; DW_FORM_data1
+  .byte 39                      ; DW_AT_prototyped
+  .byte 12                      ; DW_FORM_flag
+  .byte 63                      ; DW_AT_external
+  .byte 12                      ; DW_FORM_flag
+  .byte 0                       ; EOM(1)
+  .byte 0                       ; EOM(2)
+  .byte 3                       ; Abbreviation Code
+  .byte 5                       ; DW_TAG_formal_parameter
+  .byte 0                       ; DW_CHILDREN_no
+  .byte 3                       ; DW_AT_name
+  .byte 14                      ; DW_FORM_strp
+  .byte 58                      ; DW_AT_decl_file
+  .byte 11                      ; DW_FORM_data1
+  .byte 59                      ; DW_AT_decl_line
+  .byte 11                      ; DW_FORM_data1
+  .byte 73                      ; DW_AT_type
+  .byte 19                      ; DW_FORM_ref4
+  .byte 0                       ; EOM(1)
+  .byte 0                       ; EOM(2)
+  .byte 4                       ; Abbreviation Code
+  .byte 15                      ; DW_TAG_pointer_type
+  .byte 0                       ; DW_CHILDREN_no
+  .byte 73                      ; DW_AT_type
+  .byte 19                      ; DW_FORM_ref4
+  .byte 0                       ; EOM(1)
+  .byte 0                       ; EOM(2)
+  .byte 5                       ; Abbreviation Code
+  .byte 36                      ; DW_TAG_base_type
+  .byte 0                       ; DW_CHILDREN_no
+  .byte 3                       ; DW_AT_name
+  .byte 14                      ; DW_FORM_strp
+  .byte 62                      ; DW_AT_encoding
+  .byte 11                      ; DW_FORM_data1
+  .byte 11                      ; DW_AT_byte_size
+  .byte 11                      ; DW_FORM_data1
+  .byte 0                       ; EOM(1)
+  .byte 0                       ; EOM(2)
+  .byte 0                       ; EOM(3)
+  .section  .debug_info
+.Lsection_info:
+.Lcu_begin0:
+  .long 76                      ; Length of Unit
+  .short  2                       ; DWARF version number
+  .long .Lsection_abbrev        ; Offset Into Abbrev. Section
+  .byte 4                       ; Address Size (in bytes)
+  .byte 1                       ; Abbrev [1] 0xb:0x45 DW_TAG_compile_unit
+  .long .Linfo_string0          ; DW_AT_producer
+  .short  12                      ; DW_AT_language
+  .long .Linfo_string1          ; DW_AT_name
+  .long .Lline_table_start0     ; DW_AT_stmt_list
+  .long .Linfo_string2          ; DW_AT_comp_dir
+  .long .Lfunc_begin0           ; DW_AT_low_pc
+  .long .Lfunc_end0             ; DW_AT_high_pc
+  .byte 2                       ; Abbrev [2] 0x26:0x1d DW_TAG_subprogram
+  .long .Lfunc_begin0           ; DW_AT_low_pc
+  .long .Lfunc_end0             ; DW_AT_high_pc
+  .long .Linfo_string3          ; DW_AT_name
+  .byte 1                       ; DW_AT_decl_file
+  .byte 1                       ; DW_AT_decl_line
+  .byte 1                       ; DW_AT_prototyped
+  .byte 1                       ; DW_AT_external
+  .byte 3                       ; Abbrev [3] 0x37:0xb DW_TAG_formal_parameter
+  .long .Linfo_string4          ; DW_AT_name
+  .byte 1                       ; DW_AT_decl_file
+  .byte 1                       ; DW_AT_decl_line
+  .long 67                      ; DW_AT_type
+  .byte 0                       ; End Of Children Mark
+  .byte 4                       ; Abbrev [4] 0x43:0x5 DW_TAG_pointer_type
+  .long 72                      ; DW_AT_type
+  .byte 5                       ; Abbrev [5] 0x48:0x7 DW_TAG_base_type
+  .long .Linfo_string5          ; DW_AT_name
+  .byte 5                       ; DW_AT_encoding
+  .byte 4                       ; DW_AT_byte_size
+  .byte 0                       ; End Of Children Mark
+  .section  .debug_ranges
+.Ldebug_range:
+  .section  .debug_macinfo
+.Ldebug_macinfo:
+.Lcu_macro_begin0:
+  .byte 0                       ; End Of Macro List Mark
+  .section  .debug_pubnames
+  .long .LpubNames_end0-.LpubNames_begin0 ; Length of Public Names Info
+.LpubNames_begin0:
+  .short  2                       ; DWARF Version
+  .long .Lcu_begin0             ; Offset of Compilation Unit Info
+  .long 80                      ; Compilation Unit Length
+  .long 38                      ; DIE offset
+  .asciz  "relocs"                ; External Name
+  .long 0                       ; End Mark
+.LpubNames_end0:
+  .section  .debug_pubtypes
+  .long .LpubTypes_end0-.LpubTypes_begin0 ; Length of Public Types Info
+.LpubTypes_begin0:
+  .short  2                       ; DWARF Version
+  .long .Lcu_begin0             ; Offset of Compilation Unit Info
+  .long 80                      ; Compilation Unit Length
+  .long 72                      ; DIE offset
+  .asciz  "int"                   ; External Name
+  .long 0                       ; End Mark
+.LpubTypes_end0:
+
+  .ident  "clang version 3.9.0 (trunk 273560)"
+  .section  ".note.GNU-stack"
+  .section  .debug_line
+.Lline_table_start0: