[DebugInfo][llvm-symbolizer]Add some tests for edge cases when symbolizing

[jhenderson]

Summary

This patch adds half a dozen new tests that test various edge cases in the behaviour of the symbolizer and DWARF data parsing. All of them test the current behaviour.

[jdoerfert]

I think this caused some test failures (ignore if you are aware):
http://lab.llvm.org:8011/builders/sanitizer-x86_64-linux-fast/builds/34096/steps/check-llvm%20ubsan/logs/stdio

[jhenderson]

In D57741#1615890, @jdoerfert wrote:

I think this caused some test failures (ignore if you are aware):
http://lab.llvm.org:8011/builders/sanitizer-x86_64-linux-fast/builds/34096/steps/check-llvm%20ubsan/logs/stdio

The commit landed back in February, so it certainly wasn't caused by this change (what made you think it was?). The tests just showed up the failure introduced by rL367926, which was in turn fixed by rL367959.

llvm/trunk/test/DebugInfo/Inputs/symbolize-64bit-addr.c

+int _start() {
+    return 0;
+}
+
+// Compile with "clang --target=x86_64-pc-linux -c -g symbolize-64bit-addr.c".
+// Link with "ld.lld -Ttext=0xffffffff00000000 symbolize-64bit-addr.o -o symbolize-64bit-addr.elf.x86_64".

llvm/trunk/test/DebugInfo/symbolize-64bit-address.test

+RUN: llvm-symbolizer 0xffffffff00000000 -a --obj=%p/Inputs/symbolize-64bit-addr.elf.x86_64 \
+RUN:   | FileCheck %s
+
+CHECK:      0xffffffff00000000
+CHECK-NEXT: _start
+CHECK-NEXT: symbolize-64bit-addr.c:1:0

llvm/trunk/test/DebugInfo/symbolize-absolute-path-in-debug-line.s

+# Create .debug_line containing absolute path in filename. Show that the path is sensibly printed/found/etc.
+# REQUIRES: x86-registered-target
+
+# RUN: sed s!FILEPATH!%/s! %s > %t.s
+# RUN: llvm-mc --filetype=obj --triple=x86_64-pc-linux %t.s -o %t.o
+# RUN: llvm-symbolizer --obj=%t.o 0 | FileCheck %s -DPATH=%/s
+
+# CHECK: {{^}}[[PATH]]:1:0
+
+.type _start,@function
+_start:
+.Lfunc_begin0:
+    ret
+.Lfunc_end0:
+
+.section .debug_str,"MS",@progbits,1
+.Linfo_string1:
+    .asciz "test.c"
+.Linfo_string2:
+    .asciz "/some/dir"
+.Linfo_string3:
+    .asciz "_start"
+
+.section    .debug_abbrev,"",@progbits
+    .byte   1                       # Abbreviation Code
+    .byte   17                      # DW_TAG_compile_unit
+    .byte   1                       # DW_CHILDREN_yes
+    .byte   3                       # DW_AT_name
+    .byte   14                      # DW_FORM_strp
+    .byte   16                      # DW_AT_stmt_list
+    .byte   23                      # DW_FORM_sec_offset
+    .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   6                       # DW_FORM_data4
+    .byte   0                       # EOM(1)
+    .byte   0                       # EOM(2)
+    .byte   2                       # Abbreviation Code
+    .byte   46                      # DW_TAG_subprogram
+    .byte   0                       # DW_CHILDREN_no
+    .byte   17                      # DW_AT_low_pc
+    .byte   1                       # DW_FORM_addr
+    .byte   18                      # DW_AT_high_pc
+    .byte   6                       # DW_FORM_data4
+    .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   63                      # DW_AT_external
+    .byte   25                      # DW_FORM_flag_present
+    .byte   0                       # EOM(1)
+    .byte   0                       # EOM(2)
+    .byte   0                       # EOM(3)
+    .section    .debug_info,"",@progbits
+    .long   .Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+    .short  4                       # DWARF version number
+    .long   .debug_abbrev           # Offset Into Abbrev. Section
+    .byte   8                       # Address Size (in bytes)
+    .byte   1                       # Abbrev [1] 0xb:0x35 DW_TAG_compile_unit
+    .long   .Linfo_string1          # DW_AT_name
+    .long   .Lline_table_start0     # DW_AT_stmt_list
+    .long   .Linfo_string2          # DW_AT_comp_dir
+    .quad   .Lfunc_begin0           # DW_AT_low_pc
+    .long   .Lfunc_end0-.Lfunc_begin0 # DW_AT_high_pc
+    .byte   2                       # Abbrev [2] 0x2a:0x15 DW_TAG_subprogram
+    .quad   .Lfunc_begin0           # DW_AT_low_pc
+    .long   .Lfunc_end0-.Lfunc_begin0 # DW_AT_high_pc
+    .long   .Linfo_string3          # DW_AT_name
+    .byte   1                       # DW_AT_decl_file
+    .byte   1                       # DW_AT_decl_line
+                                        # DW_AT_external
+    .byte   0                       # End Of Children Mark
+.Ldebug_info_end0:
+
+# Hand-written .debug_line to allow replacing in the absolute path
+# into the filename table at runtime.
+.section .debug_line,"",@progbits
+.Lline_table_start0:
+    .long .Ltable_end - .Ltable_start   # unit length
+.Ltable_start:
+    .short 4                            # version
+    .long .Lheader_end - .Lheader_start # header length
+.Lheader_start:
+    .byte 1                             # min instruction length
+    .byte 1                             # max ops per instruction
+    .byte 1                             # default is_stmt
+    .byte -5                            # line base
+    .byte 14                            # line range
+    .byte 13                            # opcode base
+    .byte 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1 # standard opcode lengths
+    .byte 0                             # directory table
+    .asciz "FILEPATH"                   # filename table
+    .byte 0, 0, 0
+    .byte 0
+.Lheader_end:
+    .byte 0, 9, 2                       # DW_LNE_set_address
+    .quad .Lfunc_begin0
+    .byte 1                             # DW_LNS_copy
+    .byte 33                            # +1 address, +1 line
+    .byte 0, 1, 1                       # DW_LNE_end_sequence
+.Ltable_end:

llvm/trunk/test/DebugInfo/symbolize-no-debug-str.test

+RUN: llvm-objcopy -R .debug_str %p/Inputs/llvm-symbolizer-test.elf-x86-64 %t.elf
+RUN: llvm-symbolizer --functions=linkage --obj=%t.elf 0x401140 | FileCheck %s --check-prefix=LINKAGE
+RUN: llvm-symbolizer --functions=short --obj=%t.elf 0x401140 | FileCheck %s --check-prefix=SHORT
+
+LINKAGE:      main
+LINKAGE-NEXT: {{^}}llvm-symbolizer-test.c:10:0
+
+SHORT:        ??
+SHORT-NEXT:   {{^}}llvm-symbolizer-test.c:10:0

llvm/trunk/test/DebugInfo/symbolize-shared-abbrev.s

+# Show that multiple CUs can have a single common .debug_abbrev table. This can
+# occur due to e.g. LTO.
+
+# REQUIRES: x86-registered-target
+
+# RUN: llvm-mc --filetype=obj --triple=x86_64-pc-linux %s -o %t.o
+# RUN: llvm-symbolizer --obj=%t.o 0 16 --functions=short | FileCheck %s
+
+# CHECK:      foo
+# CHECK-NEXT: foo.c:1:0
+
+# CHECK:      bar
+# CHECK-NEXT: bar.c:2:0
+
+.global foo
+.type foo,@function
+foo:
+.Lfunc_begin0:
+    .file   1 "." "foo.c"
+    .loc    1 1 0
+    ret
+.Lfunc_end0:
+
+.global bar
+.p2align 4, 0x90
+.type bar,@function
+bar:
+.Lfunc_begin1:
+    .file   2 "." "bar.c"
+    .loc    2 2 0
+    ret
+.Lfunc_end1:
+
+    .section    .debug_str,"MS",@progbits,1
+.Linfo_string1:
+    .asciz  "foo.c"
+.Linfo_string2:
+    .asciz  "."
+.Linfo_string3:
+    .asciz  "foo"
+.Linfo_string4:
+    .asciz  "bar.c"
+.Linfo_string5:
+    .asciz  "bar"
+
+    # Regular .debug_abbrev section with CU and subprogram, but duplicated, with second
+    # half reordered slightly, to show that the correct abbrev is being referenced.
+    .section    .debug_abbrev,"",@progbits
+    .byte   1                       # Abbreviation Code
+    .byte   17                      # DW_TAG_compile_unit
+    .byte   1                       # DW_CHILDREN_yes
+    .byte   3                       # DW_AT_name
+    .byte   14                      # DW_FORM_strp
+    .byte   16                      # DW_AT_stmt_list
+    .byte   23                      # DW_FORM_sec_offset
+    .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   6                       # DW_FORM_data4
+    .byte   0                       # EOM(1)
+    .byte   0                       # EOM(2)
+    .byte   2                       # Abbreviation Code
+    .byte   46                      # DW_TAG_subprogram
+    .byte   0                       # DW_CHILDREN_no
+    .byte   17                      # DW_AT_low_pc
+    .byte   1                       # DW_FORM_addr
+    .byte   18                      # DW_AT_high_pc
+    .byte   6                       # DW_FORM_data4
+    .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   63                      # DW_AT_external
+    .byte   25                      # DW_FORM_flag_present
+    .byte   0                       # EOM(1)
+    .byte   0                       # EOM(2)
+    # Second-half starts here.
+    .byte   3                       # Abbreviation Code
+    .byte   17                      # DW_TAG_compile_unit
+    .byte   1                       # DW_CHILDREN_yes
+    .byte   16                      # DW_AT_stmt_list
+    .byte   23                      # DW_FORM_sec_offset
+    .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   6                       # DW_FORM_data4
+    .byte   3                       # DW_AT_name
+    .byte   14                      # DW_FORM_strp
+    .byte   0                       # EOM(1)
+    .byte   0                       # EOM(2)
+    .byte   4                       # Abbreviation Code
+    .byte   46                      # DW_TAG_subprogram
+    .byte   0                       # DW_CHILDREN_no
+    .byte   17                      # DW_AT_low_pc
+    .byte   1                       # DW_FORM_addr
+    .byte   18                      # DW_AT_high_pc
+    .byte   6                       # DW_FORM_data4
+    .byte   58                      # DW_AT_decl_file
+    .byte   11                      # DW_FORM_data1
+    .byte   59                      # DW_AT_decl_line
+    .byte   11                      # DW_FORM_data1
+    .byte   63                      # DW_AT_external
+    .byte   25                      # DW_FORM_flag_present
+    .byte   3                       # DW_AT_name
+    .byte   14                      # DW_FORM_strp
+    .byte   0                       # EOM(1)
+    .byte   0                       # EOM(2)
+    .byte   0                       # EOM(3)
+
+    .section    .debug_info,"",@progbits
+    # First CU table.
+    .long   .Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+    .short  4                       # DWARF version number
+    .long   .debug_abbrev           # Offset Into Abbrev. Section
+    .byte   8                       # Address Size (in bytes)
+    .byte   1                       # Abbrev [1] 0xb:0x35 DW_TAG_compile_unit
+    .long   .Linfo_string1          # DW_AT_name
+    .long   .Lline_table_start0     # DW_AT_stmt_list
+    .long   .Linfo_string2          # DW_AT_comp_dir
+    .quad   .Lfunc_begin0           # DW_AT_low_pc
+    .long   .Lfunc_end0-.Lfunc_begin0 # DW_AT_high_pc
+    .byte   2                       # Abbrev [2] 0x2a:0x15 DW_TAG_subprogram
+    .quad   .Lfunc_begin0           # DW_AT_low_pc
+    .long   .Lfunc_end0-.Lfunc_begin0 # DW_AT_high_pc
+    .long   .Linfo_string3          # DW_AT_name
+    .byte   1                       # DW_AT_decl_file
+    .byte   1                       # DW_AT_decl_line
+                                        # DW_AT_external
+    .byte   0                       # End Of Children Mark
+.Ldebug_info_end0:
+
+    # Second CU table.
+    .long   .Ldebug_info_end1-.Ldebug_info_start1 # Length of Unit
+.Ldebug_info_start1:
+    .short  4                       # DWARF version number
+    .long   .debug_abbrev           # Offset Into Abbrev. Section
+    .byte   8                       # Address Size (in bytes)
+    .byte   3                       # Abbrev [1] 0xb:0x35 DW_TAG_compile_unit
+    .long   .Lline_table_start0     # DW_AT_stmt_list
+    .long   .Linfo_string2          # DW_AT_comp_dir
+    .quad   .Lfunc_begin1           # DW_AT_low_pc
+    .long   .Lfunc_end1-.Lfunc_begin1 # DW_AT_high_pc
+    .long   .Linfo_string4          # DW_AT_name
+    .byte   4                       # Abbrev [2] 0x2a:0x15 DW_TAG_subprogram
+    .quad   .Lfunc_begin1           # DW_AT_low_pc
+    .long   .Lfunc_end1-.Lfunc_begin1 # DW_AT_high_pc
+    .byte   1                       # DW_AT_decl_file
+    .byte   1                       # DW_AT_decl_line
+                                        # DW_AT_external
+    .long   .Linfo_string5          # DW_AT_name
+    .byte   0                       # End Of Children Mark
+.Ldebug_info_end1:
+
+    .section    .debug_line,"",@progbits
+.Lline_table_start0:

llvm/trunk/test/DebugInfo/symbolize-stripped-sections.test

+RUN: llvm-symbolizer --obj=%p/Inputs/llvm-symbolizer-test.elf-x86-64 0x401140 \
+RUN:   | FileCheck %s --check-prefix=UNSTRIPPED
+
+RUN: llvm-objcopy --strip-sections %p/Inputs/llvm-symbolizer-test.elf-x86-64 %t.elf
+RUN: llvm-symbolizer --obj=%t.elf 0x401140 | FileCheck %s --check-prefix=STRIPPED
+
+UNSTRIPPED:      main
+UNSTRIPPED-NEXT: llvm-symbolizer-test.c:10:0
+
+STRIPPED:        ??
+STRIPPED-NEXT:   ??:0:0

llvm/trunk/test/tools/llvm-symbolizer/invalid-input-address.test

+# Use address that can't fit in a 64-bit number. Show that llvm-symbolizer
+# simply echoes it as per other malformed input addresses.
+RUN: llvm-symbolizer --obj=addr.exe 0x10000000000000000 | FileCheck %s
+
+CHECK-NOT: {{.}}
+CHECK:     0x10000000000000000
+CHECK-NOT: {{.}}