[WebAssembly] Fix crash when relocation synbol is not live

[sbc100]

Summary

When a symbol is GC'd it can still be referenced by relocations
in the debug sections, but such symbols are not assigned virtual
addresses.

This change adds a new global data symbol which gets gc'd but
should still appears in the output debug info, albeit with a 0
address.

Fixes 37555

[yurydelendik]

Looks good. Thank you.

wasm/InputFiles.cpp

129 ↗

(On Diff #148137)

I'm not sure about code formatting here: do we need braces for outer if since it has a two line body now?

lld/trunk/test/wasm/Inputs/debuginfo1.ll

 ; ModuleID = 'hi.c'
 source_filename = "hi.c"
 target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
 target triple = "wasm32-unknown-unknown"
 
 ; // hi.c:
 ; extern void foo(int);
-;  
+;
 ; int test(int t) {
 ;   return t * t;
 ; }
 ;
 ; int _start() {
 ;   foo(test(10));
 ;   return 0;
 ; }

lld/trunk/test/wasm/Inputs/debuginfo2.ll

 ; ModuleID = 'hi_foo.c'
 source_filename = "hi_foo.c"
 target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
 target triple = "wasm32-unknown-unknown"
 
 ; // hi_foo.c:
 ; int y[2] = {23, 41};
-;  
+;
 ; void foo(int p) {
 ;   y[p & 1]++;
 ; }
+;
+; // Will be GCed, but remain visible in debug info
+; int z[2] = {1, 2};
 
 @y = hidden local_unnamed_addr global [2 x i32] [i32 23, i32 41], align 4, !dbg !0
+@z = hidden local_unnamed_addr global [2 x i32] [i32 1, i32 2], align 4, !dbg !6
 
 ; Function Attrs: nounwind
-define hidden void @foo(i32 %p) local_unnamed_addr #0 !dbg !14 {
+define hidden void @foo(i32 %p) local_unnamed_addr #0 !dbg !16 {
 entry:
-  call void @llvm.dbg.value(metadata i32 %p, metadata !18, metadata !DIExpression()), !dbg !19
-  %and = and i32 %p, 1, !dbg !20
-  %arrayidx = getelementptr inbounds [2 x i32], [2 x i32]* @y, i32 0, i32 %and, !dbg !21
-  %0 = load i32, i32* %arrayidx, align 4, !dbg !22, !tbaa !23
-  %inc = add nsw i32 %0, 1, !dbg !22
-  store i32 %inc, i32* %arrayidx, align 4, !dbg !22, !tbaa !23
-  ret void, !dbg !27
+  call void @llvm.dbg.value(metadata i32 %p, metadata !20, metadata !DIExpression()), !dbg !21
+  %and = and i32 %p, 1, !dbg !22
+  %arrayidx = getelementptr inbounds [2 x i32], [2 x i32]* @y, i32 0, i32 %and, !dbg !23
+  %0 = load i32, i32* %arrayidx, align 4, !dbg !24, !tbaa !25
+  %inc = add nsw i32 %0, 1, !dbg !24
+  store i32 %inc, i32* %arrayidx, align 4, !dbg !24, !tbaa !25
+  ret void, !dbg !29
 }
 
 ; Function Attrs: nounwind readnone speculatable
 declare void @llvm.dbg.value(metadata, metadata, metadata) #1
 
 attributes #0 = { nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
 attributes #1 = { nounwind readnone speculatable }
 
 !llvm.dbg.cu = !{!2}
-!llvm.module.flags = !{!10, !11, !12}
-!llvm.ident = !{!13}
+!llvm.module.flags = !{!12, !13, !14}
+!llvm.ident = !{!15}
 
 !0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
-!1 = distinct !DIGlobalVariable(name: "y", scope: !2, file: !3, line: 1, type: !6, isLocal: false, isDefinition: true)
-!2 = distinct !DICompileUnit(language: DW_LANG_C99, file: !3, producer: "clang version 7.0.0 (trunk 331321)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5)
-!3 = !DIFile(filename: "hi_foo.c", directory: "/Users/yury/llvmwasm")
+!1 = distinct !DIGlobalVariable(name: "y", scope: !2, file: !3, line: 1, type: !8, isLocal: false, isDefinition: true)
+!2 = distinct !DICompileUnit(language: DW_LANG_C99, file: !3, producer: "clang version 7.0.0 (trunk 332913) (llvm/trunk 332919)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5)
+!3 = !DIFile(filename: "hi_foo.c", directory: "/usr/local/google/home/sbc/dev/wasm/llvm-build")
 !4 = !{}
-!5 = !{!0}
-!6 = !DICompositeType(tag: DW_TAG_array_type, baseType: !7, size: 64, elements: !8)
-!7 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
-!8 = !{!9}
-!9 = !DISubrange(count: 2)
-!10 = !{i32 2, !"Dwarf Version", i32 4}
-!11 = !{i32 2, !"Debug Info Version", i32 3}
-!12 = !{i32 1, !"wchar_size", i32 4}
-!13 = !{!"clang version 7.0.0 (trunk 331321)"}
-!14 = distinct !DISubprogram(name: "foo", scope: !3, file: !3, line: 3, type: !15, isLocal: false, isDefinition: true, scopeLine: 3, flags: DIFlagPrototyped, isOptimized: true, unit: !2, retainedNodes: !17)
-!15 = !DISubroutineType(types: !16)
-!16 = !{null, !7}
-!17 = !{!18}
-!18 = !DILocalVariable(name: "p", arg: 1, scope: !14, file: !3, line: 3, type: !7)
-!19 = !DILocation(line: 3, column: 14, scope: !14)
-!20 = !DILocation(line: 4, column: 7, scope: !14)
-!21 = !DILocation(line: 4, column: 3, scope: !14)
-!22 = !DILocation(line: 4, column: 11, scope: !14)
-!23 = !{!24, !24, i64 0}
-!24 = !{!"int", !25, i64 0}
-!25 = !{!"omnipotent char", !26, i64 0}
-!26 = !{!"Simple C/C++ TBAA"}
-!27 = !DILocation(line: 5, column: 1, scope: !14)
+!5 = !{!0, !6}
+!6 = !DIGlobalVariableExpression(var: !7, expr: !DIExpression())
+!7 = distinct !DIGlobalVariable(name: "z", scope: !2, file: !3, line: 8, type: !8, isLocal: false, isDefinition: true)
+!8 = !DICompositeType(tag: DW_TAG_array_type, baseType: !9, size: 64, elements: !10)
+!9 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!10 = !{!11}
+!11 = !DISubrange(count: 2)
+!12 = !{i32 2, !"Dwarf Version", i32 4}
+!13 = !{i32 2, !"Debug Info Version", i32 3}
+!14 = !{i32 1, !"wchar_size", i32 4}
+!15 = !{!"clang version 7.0.0 (trunk 332913) (llvm/trunk 332919)"}
+!16 = distinct !DISubprogram(name: "foo", scope: !3, file: !3, line: 3, type: !17, isLocal: false, isDefinition: true, scopeLine: 3, flags: DIFlagPrototyped, isOptimized: true, unit: !2, retainedNodes: !19)
+!17 = !DISubroutineType(types: !18)
+!18 = !{null, !9}
+!19 = !{!20}
+!20 = !DILocalVariable(name: "p", arg: 1, scope: !16, file: !3, line: 3, type: !9)
+!21 = !DILocation(line: 3, column: 14, scope: !16)
+!22 = !DILocation(line: 4, column: 7, scope: !16)
+!23 = !DILocation(line: 4, column: 3, scope: !16)
+!24 = !DILocation(line: 4, column: 11, scope: !16)
+!25 = !{!26, !26, i64 0}
+!26 = !{!"int", !27, i64 0}
+!27 = !{!"omnipotent char", !28, i64 0}
+!28 = !{!"Simple C/C++ TBAA"}
+!29 = !DILocation(line: 5, column: 1, scope: !16)

lld/trunk/test/wasm/debuginfo.test

 RUN: llc -filetype=obj %p/Inputs/debuginfo1.ll -o %t.debuginfo1.o
 RUN: llc -filetype=obj %p/Inputs/debuginfo2.ll -o %t.debuginfo2.o
-RUN: wasm-ld -r -o %t.wasm %t.debuginfo1.o %t.debuginfo2.o
+RUN: wasm-ld -o %t.wasm %t.debuginfo1.o %t.debuginfo2.o
 RUN: llvm-dwarfdump %t.wasm | FileCheck %s
 
 CHECK: file format WASM
 
 CHECK: .debug_info contents:
 CHECK: DW_TAG_compile_unit
-CHECK-NEXT:              DW_AT_producer ("clang version 7.0.0 (trunk 331321)")
+CHECK-NEXT:              DW_AT_producer ("clang version 7.0.0 (trunk {{.*}})")
 CHECK-NEXT:              DW_AT_language (DW_LANG_C99)
 CHECK-NEXT:              DW_AT_name ("hi.c")
 
 CHECK:   DW_TAG_subprogram
 CHECK-NEXT:                DW_AT_low_pc
 CHECK-NEXT:                DW_AT_high_pc
 CHECK-NEXT:                DW_AT_name ("test")
 CHECK-NEXT:                DW_AT_decl_file  ("/Users/yury/llvmwasm{{(/|\\)}}hi.c")

 CHECK-NEXT:                DW_AT_decl_line  (7)
 
 CHECK:   DW_TAG_base_type
 CHECK-NEXT:                DW_AT_name ("int")
 CHECK-NEXT:                DW_AT_encoding (DW_ATE_signed)
 CHECK-NEXT:                DW_AT_byte_size  (0x04)
 
 CHECK: DW_TAG_compile_unit
-CHECK-NEXT:              DW_AT_producer ("clang version 7.0.0 (trunk 331321)")
+CHECK-NEXT:              DW_AT_producer ("clang version 7.0.0 (trunk {{.*}})")
 CHECK-NEXT:              DW_AT_language (DW_LANG_C99)
 CHECK-NEXT:              DW_AT_name ("hi_foo.c")
 
 CHECK:   DW_TAG_variable
 CHECK-NEXT:                DW_AT_name ("y")
-CHECK-NEXT:                "int[]"
+CHECK-NEXT:                DW_AT_type (0x00000097 "int[]")
+CHECK-NEXT:                DW_AT_external (true)
+CHECK-NEXT:                DW_AT_decl_file  ("{{.*}}hi_foo.c")
+CHECK-NEXT:                DW_AT_decl_line  (1)
+CHECK:                     DW_AT_location (DW_OP_addr 0x400)
 
 CHECK:   DW_TAG_array_type
 
 CHECK:     DW_TAG_subrange_type
 
 CHECK:   DW_TAG_base_type
 CHECK-NEXT:                DW_AT_name ("int")
 CHECK-NEXT:                DW_AT_encoding (DW_ATE_signed)
 CHECK-NEXT:                DW_AT_byte_size  (0x04)
 
 CHECK:   DW_TAG_base_type
 CHECK-NEXT:                DW_AT_name ("__ARRAY_SIZE_TYPE__")
 CHECK-NEXT:                DW_AT_byte_size  (0x08)
 CHECK-NEXT:                DW_AT_encoding (DW_ATE_unsigned)
 
+CHECK:   DW_TAG_variable
+CHECK-NEXT:                DW_AT_name ("z")
+CHECK-NEXT:                DW_AT_type (0x00000097 "int[]")
+CHECK-NEXT:                DW_AT_external (true)
+CHECK-NEXT:                DW_AT_decl_file  ("{{.*}}hi_foo.c")
+CHECK-NEXT:                DW_AT_decl_line  (8)
+CHECK-NEXT:                DW_AT_location (DW_OP_addr 0x0)
+
 CHECK:   DW_TAG_subprogram
 CHECK-NEXT:                DW_AT_low_pc 
 CHECK-NEXT:                DW_AT_high_pc
 CHECK-NEXT:                DW_AT_name ("foo")
-CHECK-NEXT:                DW_AT_decl_file  ("/Users/yury/llvmwasm{{(/|\\)}}hi_foo.c")
+CHECK-NEXT:                DW_AT_decl_file  ("{{.*}}hi_foo.c")
 CHECK-NEXT:                DW_AT_decl_line  (3)
 
 CHECK:     DW_TAG_formal_parameter
 CHECK-NEXT:                  DW_AT_name ("p")
-CHECK-NEXT:                  DW_AT_decl_file  ("/Users/yury/llvmwasm{{(/|\\)}}hi_foo.c")
+CHECK-NEXT:                  DW_AT_decl_file  ("{{.*}}hi_foo.c")
 CHECK-NEXT:                  DW_AT_decl_line  (3)
 

lld/trunk/wasm/InputFiles.cpp

uint32_t ObjFile::calcNewValue(const WasmRelocation &Reloc) const {
   switch (Reloc.Type) {
   case R_WEBASSEMBLY_TABLE_INDEX_I32:
   case R_WEBASSEMBLY_TABLE_INDEX_SLEB:
     return getFunctionSymbol(Reloc.Index)->getTableIndex();
   case R_WEBASSEMBLY_MEMORY_ADDR_SLEB:
   case R_WEBASSEMBLY_MEMORY_ADDR_I32:
   case R_WEBASSEMBLY_MEMORY_ADDR_LEB:
     if (auto *Sym = dyn_cast<DefinedData>(getDataSymbol(Reloc.Index)))
+      if (Sym->isLive())
         return Sym->getVirtualAddress() + Reloc.Addend;
     return 0;
   case R_WEBASSEMBLY_TYPE_INDEX_LEB:
     return TypeMap[Reloc.Index];
   case R_WEBASSEMBLY_FUNCTION_INDEX_LEB:
     return getFunctionSymbol(Reloc.Index)->getFunctionIndex();
   case R_WEBASSEMBLY_GLOBAL_INDEX_LEB:
     return getGlobalSymbol(Reloc.Index)->getGlobalIndex();
   case R_WEBASSEMBLY_FUNCTION_OFFSET_I32: