[DebugInfo] Correctly handle salvaged casts and split fragments at ISel

Previously, LLVM had no functional way of performing casts inside of a
DIExpression(), which made salvaging cast instructions other than Noop
casts impossible. This patch enables the salvaging of casts by using the
DW_OP_LLVM_convert operator for SExt and Trunc instructions.

There is another issue which is exposed by this fix, in which fragment
DIExpressions (which are preserved more readily by this patch) for
values that must be split across registers in ISel trigger an assertion,
as the 'split' fragments extend beyond the bounds of the fragment
DIExpression causing an error. This patch also fixes this issue by
checking the fragment status of DIExpressions which are to be split, and
dropping fragments that are invalid.

11 files changed, 156 insertions, 19 deletions

diff --git a/llvm/include/llvm/IR/DebugInfoMetadata.h b/llvm/include/llvm/IR/DebugInfoMetadata.h
index 214003ad993..f5582d8f98c 100644
--- a/llvm/include/llvm/IR/DebugInfoMetadata.h
+++ b/llvm/include/llvm/IR/DebugInfoMetadata.h
@@ -2552,6 +2552,11 @@ public:
       return 0;
   }
 
+  using ExtOps = std::array<uint64_t, 6>;
+
+  /// Returns the ops for a zero- or sign-extension in a DIExpression.
+  static ExtOps getExtOps(unsigned FromSize, unsigned ToSize, bool Signed);
+
   /// Append a zero- or sign-extension to \p Expr. Converts the expression to a
   /// stack value if it isn't one already.
   static DIExpression *appendExt(const DIExpression *Expr, unsigned FromSize,
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 27ac489b35b..735ac67ebfc 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -5571,8 +5571,26 @@ bool SelectionDAGBuilder::EmitFuncArgumentDbgValue(
       = [&](ArrayRef<std::pair<unsigned, unsigned>> SplitRegs) {
       unsigned Offset = 0;
       for (auto RegAndSize : SplitRegs) {
+        // If the expression is already a fragment, the current register
+        // offset+size might extend beyond the fragment. In this case, only
+        // the register bits that are inside the fragment are relevant.
+        int RegFragmentSizeInBits = RegAndSize.second;
+        if (auto ExprFragmentInfo = Expr->getFragmentInfo()) {
+          uint64_t ExprFragmentSizeInBits = ExprFragmentInfo->SizeInBits;
+          // The register is entirely outside the expression fragment,
+          // so is irrelevant for debug info.
+          if (Offset >= ExprFragmentSizeInBits)
+            break;
+          // The register is partially outside the expression fragment, only
+          // the low bits within the fragment are relevant for debug info.
+          if (Offset + RegFragmentSizeInBits > ExprFragmentSizeInBits) {
+            RegFragmentSizeInBits = ExprFragmentSizeInBits - Offset;
+          }
+        }
+
         auto FragmentExpr = DIExpression::createFragmentExpression(
-          Expr, Offset, RegAndSize.second);
+            Expr, Offset, RegFragmentSizeInBits);
+        Offset += RegAndSize.second;
         // If a valid fragment expression cannot be created, the variable's
         // correct value cannot be determined and so it is set as Undef.
         if (!FragmentExpr) {
@@ -5585,7 +5603,6 @@ bool SelectionDAGBuilder::EmitFuncArgumentDbgValue(
         FuncInfo.ArgDbgValues.push_back(
           BuildMI(MF, DL, TII->get(TargetOpcode::DBG_VALUE), false,
                   RegAndSize.first, Variable, *FragmentExpr));
-        Offset += RegAndSize.second;
       }
     };
 
diff --git a/llvm/lib/IR/DebugInfoMetadata.cpp b/llvm/lib/IR/DebugInfoMetadata.cpp
index 9b42a5a0e1b..8970fc15576 100644
--- a/llvm/lib/IR/DebugInfoMetadata.cpp
+++ b/llvm/lib/IR/DebugInfoMetadata.cpp
@@ -1196,13 +1196,18 @@ bool DIExpression::isConstant() const {
   return true;
 }
 
+DIExpression::ExtOps DIExpression::getExtOps(unsigned FromSize, unsigned ToSize,
+                                             bool Signed) {
+  dwarf::TypeKind TK = Signed ? dwarf::DW_ATE_signed : dwarf::DW_ATE_unsigned;
+  DIExpression::ExtOps Ops({dwarf::DW_OP_LLVM_convert, FromSize, TK,
+                            dwarf::DW_OP_LLVM_convert, ToSize, TK});
+  return Ops;
+}
+
 DIExpression *DIExpression::appendExt(const DIExpression *Expr,
                                       unsigned FromSize, unsigned ToSize,
                                       bool Signed) {
-  dwarf::TypeKind TK = Signed ? dwarf::DW_ATE_signed : dwarf::DW_ATE_unsigned;
-  uint64_t Ops[] = {dwarf::DW_OP_LLVM_convert, FromSize, TK,
-                    dwarf::DW_OP_LLVM_convert, ToSize,   TK};
-  return appendToStack(Expr, Ops);
+  return appendToStack(Expr, getExtOps(FromSize, ToSize, Signed));
 }
 
 DIGlobalVariableExpression *
diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp
index d5690a04f53..b2d511c7c9a 100644
--- a/llvm/lib/Transforms/Utils/Local.cpp
+++ b/llvm/lib/Transforms/Utils/Local.cpp
@@ -1676,9 +1676,8 @@ DIExpression *llvm::salvageDebugInfoImpl(Instruction &I,
   };
 
   // initializer-list helper for applying operators to the source DIExpression.
-  auto applyOps =
-      [&](std::initializer_list<uint64_t> Opcodes) -> DIExpression * {
-    SmallVector<uint64_t, 8> Ops(Opcodes);
+  auto applyOps = [&](ArrayRef<uint64_t> Opcodes) -> DIExpression * {
+    SmallVector<uint64_t, 8> Ops(Opcodes.begin(), Opcodes.end());
     return doSalvage(Ops);
   };
 
@@ -1686,8 +1685,21 @@ DIExpression *llvm::salvageDebugInfoImpl(Instruction &I,
     // No-op casts and zexts are irrelevant for debug info.
     if (CI->isNoopCast(DL) || isa<ZExtInst>(&I))
       return SrcDIExpr;
-    return nullptr;
-  } else if (auto *GEP = dyn_cast<GetElementPtrInst>(&I)) {
+
+    Type *Type = CI->getType();
+    // Casts other than Trunc or SExt to scalar types cannot be salvaged.
+    if (Type->isVectorTy() || (!isa<TruncInst>(&I) && !isa<SExtInst>(&I)))
+      return nullptr;
+
+    Value *FromValue = CI->getOperand(0);
+    unsigned FromTypeBitSize = FromValue->getType()->getScalarSizeInBits();
+    unsigned ToTypeBitSize = Type->getScalarSizeInBits();
+
+    return applyOps(DIExpression::getExtOps(FromTypeBitSize, ToTypeBitSize,
+                                            isa<SExtInst>(&I)));
+  }
+
+  if (auto *GEP = dyn_cast<GetElementPtrInst>(&I)) {
     unsigned BitWidth =
         M.getDataLayout().getIndexSizeInBits(GEP->getPointerAddressSpace());
     // Rewrite a constant GEP into a DIExpression.
diff --git a/llvm/test/CodeGen/ARM/fragmented-args-multiple-regs.ll b/llvm/test/CodeGen/ARM/fragmented-args-multiple-regs.ll
new file mode 100644
index 00000000000..8c4822dfe15
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/fragmented-args-multiple-regs.ll
@@ -0,0 +1,72 @@
+; RUN: llc < %s -mtriple=armv7-linux-gnueabihf -O1 -stop-after=finalize-isel | FileCheck %s
+
+define dso_local i32 @h(i64 %j) local_unnamed_addr !dbg !8 {
+entry:
+  call void @llvm.dbg.value(metadata i64 %j, metadata !14, metadata !DIExpression()), !dbg !29
+  call void @llvm.dbg.value(metadata i64 %j, metadata !15, metadata !DIExpression(DW_OP_LLVM_convert, 64, DW_ATE_unsigned, DW_OP_LLVM_convert, 32, DW_ATE_unsigned, DW_OP_stack_value, DW_OP_LLVM_fragment, 0, 32)), !dbg !29
+  call void @llvm.dbg.value(metadata i64 %j, metadata !15, metadata !DIExpression(DW_OP_constu, 32, DW_OP_shr, DW_OP_LLVM_convert, 64, DW_ATE_unsigned, DW_OP_LLVM_convert, 32, DW_ATE_unsigned, DW_OP_stack_value, DW_OP_LLVM_fragment, 32, 32)), !dbg !29
+  %tobool = icmp ult i64 %j, 4294967296, !dbg !30
+  br i1 %tobool, label %cleanup, label %if.then, !dbg !31
+
+if.then:                                          ; preds = %entry
+  call void @llvm.dbg.value(metadata i64 %j, metadata !15, metadata !DIExpression(DW_OP_LLVM_convert, 64, DW_ATE_unsigned, DW_OP_LLVM_convert, 32, DW_ATE_unsigned, DW_OP_stack_value, DW_OP_LLVM_fragment, 0, 32)), !dbg !29
+  %conv = sitofp i64 %j to double, !dbg !32
+  %add = fadd double %conv, 0x43F0000000000000, !dbg !33
+  call void @llvm.dbg.value(metadata double %add, metadata !25, metadata !DIExpression()), !dbg !34
+  %conv2 = fptosi double %add to i32, !dbg !35
+  br label %cleanup
+
+cleanup:                                          ; preds = %entry, %if.then
+  %retval.0 = phi i32 [ %conv2, %if.then ], [ undef, %entry ]
+  ret i32 %retval.0, !dbg !36
+}
+
+; CHECK-LABEL: bb.0.entry:
+; CHECK: DBG_VALUE [[REG1:%[0-9]+]], $noreg, !14, !DIExpression(DW_OP_LLVM_fragment, 32, 32
+; CHECK: DBG_VALUE [[REG2:%[0-9]+]], $noreg, !14, !DIExpression(DW_OP_LLVM_fragment, 0, 32
+; CHECK: DBG_VALUE [[REG2]], $noreg, !15, !DIExpression({{.+}}DW_OP_LLVM_fragment, 0, 32
+; CHECK: DBG_VALUE $noreg, $noreg, !15, !DIExpression({{.+}}DW_OP_LLVM_fragment, 32, 32
+
+declare void @llvm.dbg.value(metadata, metadata, metadata)
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5, !6}
+!llvm.ident = !{!7}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 10.0.0 ", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, nameTableKind: None)
+!1 = !DIFile(filename: "tif_aux.c", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{i32 1, !"min_enum_size", i32 4}
+!7 = !{!"clang version 10.0.0 "}
+!8 = distinct !DISubprogram(name: "h", scope: !1, file: !1, line: 10, type: !9, scopeLine: 10, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !13)
+!9 = !DISubroutineType(types: !10)
+!10 = !{!11, !12}
+!11 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!12 = !DIBasicType(name: "long long int", size: 64, encoding: DW_ATE_signed)
+!13 = !{!14, !15, !25}
+!14 = !DILocalVariable(name: "j", arg: 1, scope: !8, file: !1, line: 10, type: !12)
+!15 = !DILocalVariable(name: "i", scope: !8, file: !1, line: 11, type: !16)
+!16 = !DIDerivedType(tag: DW_TAG_typedef, name: "g", file: !1, line: 8, baseType: !17)
+!17 = distinct !DICompositeType(tag: DW_TAG_union_type, file: !1, line: 5, size: 64, elements: !18)
+!18 = !{!19, !24}
+!19 = !DIDerivedType(tag: DW_TAG_member, name: "e", scope: !17, file: !1, line: 6, baseType: !20, size: 64)
+!20 = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "b", file: !1, line: 1, size: 64, elements: !21)
+!21 = !{!22, !23}
+!22 = !DIDerivedType(tag: DW_TAG_member, name: "c", scope: !20, file: !1, line: 2, baseType: !11, size: 32)
+!23 = !DIDerivedType(tag: DW_TAG_member, name: "d", scope: !20, file: !1, line: 2, baseType: !11, size: 32, offset: 32)
+!24 = !DIDerivedType(tag: DW_TAG_member, name: "f", scope: !17, file: !1, line: 7, baseType: !12, size: 64)
+!25 = !DILocalVariable(name: "a", scope: !26, file: !1, line: 14, type: !28)
+!26 = distinct !DILexicalBlock(scope: !27, file: !1, line: 13, column: 14)
+!27 = distinct !DILexicalBlock(scope: !8, file: !1, line: 13, column: 7)
+!28 = !DIBasicType(name: "double", size: 64, encoding: DW_ATE_float)
+!29 = !DILocation(line: 0, scope: !8)
+!30 = !DILocation(line: 13, column: 7, scope: !27)
+!31 = !DILocation(line: 13, column: 7, scope: !8)
+!32 = !DILocation(line: 14, column: 16, scope: !26)
+!33 = !DILocation(line: 14, column: 20, scope: !26)
+!34 = !DILocation(line: 0, scope: !26)
+!35 = !DILocation(line: 15, column: 12, scope: !26)
+!36 = !DILocation(line: 17, column: 1, scope: !8)
diff --git a/llvm/test/DebugInfo/X86/dbg-value-dropped-instcombine.ll b/llvm/test/DebugInfo/X86/dbg-value-dropped-instcombine.ll
index 18e51b6fabd..46f940e11c6 100644
--- a/llvm/test/DebugInfo/X86/dbg-value-dropped-instcombine.ll
+++ b/llvm/test/DebugInfo/X86/dbg-value-dropped-instcombine.ll
@@ -21,8 +21,8 @@
 ; }
 
 ; CHECK: define dso_local i64 @foo
-; CHECK: @llvm.dbg.value({{.*}}, metadata ![[BEE:[0-9]+]], metadata !DIExpression(DW_OP_LLVM_fragment, 0, 32)),
-; CHECK: @llvm.dbg.value(metadata i32 undef, metadata ![[BEE]], metadata !DIExpression(DW_OP_LLVM_fragment, 32, 32)),
+; CHECK: @llvm.dbg.value(metadata i64 {{.*}}, metadata ![[BEE:[0-9]+]], metadata !DIExpression(DW_OP_LLVM_fragment, 0, 32)),
+; CHECK: @llvm.dbg.value(metadata i64 {{.*}}, metadata ![[BEE]], metadata !DIExpression({{.*}}, DW_OP_LLVM_fragment, 32, 32)),
 
 target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-unknown"
diff --git a/llvm/test/DebugInfo/salvage-cast-debug-info.ll b/llvm/test/DebugInfo/salvage-cast-debug-info.ll
new file mode 100644
index 00000000000..f39ac46a66a
--- /dev/null
+++ b/llvm/test/DebugInfo/salvage-cast-debug-info.ll
@@ -0,0 +1,25 @@
+; RUN: opt %s -debugify -early-cse -S | FileCheck %s
+define i32 @foo(i64 %nose, i32 %more) {
+; CHECK-LABEL: @foo(
+; CHECK: call void @llvm.dbg.value(metadata i64 %nose, metadata [[V1:![0-9]+]], metadata !DIExpression(DW_OP_LLVM_convert, 64, DW_ATE_unsigned, DW_OP_LLVM_convert, 32, DW_ATE_unsigned
+; CHECK: call void @llvm.dbg.value(metadata i64 %nose.shift, metadata [[V2:![0-9]+]]
+; CHECK: call void @llvm.dbg.value(metadata i64 %nose.shift, metadata [[V3:![0-9]+]], metadata !DIExpression(DW_OP_LLVM_convert, 64, DW_ATE_unsigned, DW_OP_LLVM_convert, 32, DW_ATE_unsigned
+
+entry:
+  %nose.trunc = trunc i64 %nose to i32
+  %nose.shift = lshr i64 %nose, 32
+  %nose.trunc.2 = trunc i64 %nose.shift to i32
+  %add = add nsw i32 %more, 1
+  ret i32 %add
+}
+
+!llvm.module.flags = !{!0, !1}
+!llvm.ident = !{!2}
+
+!0 = !{i32 1, !"wchar_size", i32 2}
+!1 = !{i32 7, !"PIC Level", i32 2}
+!2 = !{!"clang version 10.0.0 "}
+
+; CHECK: [[V1]] = !DILocalVariable(
+; CHECK: [[V2]] = !DILocalVariable(
+; CHECK: [[V3]] = !DILocalVariable(
diff --git a/llvm/test/Transforms/EarlyCSE/debug-info-undef.ll b/llvm/test/Transforms/EarlyCSE/debug-info-undef.ll
index 4615aa264b6..b0fb8ff75ad 100644
--- a/llvm/test/Transforms/EarlyCSE/debug-info-undef.ll
+++ b/llvm/test/Transforms/EarlyCSE/debug-info-undef.ll
@@ -10,7 +10,7 @@ entry:
   %0 = load i8, i8* @a, align 1, !dbg !19, !tbaa !20
   %conv = sext i8 %0 to i16, !dbg !19
 
-; CHECK: call void @llvm.dbg.value(metadata i16 undef, metadata !17, metadata !DIExpression()), !dbg !18
+; CHECK: call void @llvm.dbg.value(metadata i8 %0, metadata !17, metadata !DIExpression(DW_OP_LLVM_convert, 8, DW_ATE_signed, DW_OP_LLVM_convert, 16, DW_ATE_signed, DW_OP_stack_value)), !dbg !18
 ; CHECK-NEXT:  call i32 (...) @optimize_me_not()
 
   call void @llvm.dbg.value(metadata i16 %conv, metadata !17, metadata !DIExpression()), !dbg !18
diff --git a/llvm/test/Transforms/InstCombine/cast-mul-select.ll b/llvm/test/Transforms/InstCombine/cast-mul-select.ll
index 5de3314b472..f82d2fd285f 100644
--- a/llvm/test/Transforms/InstCombine/cast-mul-select.ll
+++ b/llvm/test/Transforms/InstCombine/cast-mul-select.ll
@@ -13,8 +13,8 @@ define i32 @mul(i32 %x, i32 %y) {
 ; we preserve the debug information in the resulting
 ; instruction.
 ; DBGINFO-LABEL: @mul(
-; DBGINFO-NEXT:    call void @llvm.dbg.value(metadata i8 undef
-; DBGINFO-NEXT:    call void @llvm.dbg.value(metadata i8 undef
+; DBGINFO-NEXT:    call void @llvm.dbg.value(metadata i32 %x
+; DBGINFO-NEXT:    call void @llvm.dbg.value(metadata i32 %y
 ; DBGINFO-NEXT:    [[C:%.*]] = mul i32 {{.*}}
 ; DBGINFO-NEXT:    [[D:%.*]] = and i32 {{.*}}
 ; DBGINFO-NEXT:    call void @llvm.dbg.value(metadata i32 [[C]]
diff --git a/llvm/test/Transforms/InstCombine/pr43893.ll b/llvm/test/Transforms/InstCombine/pr43893.ll
index 0eb926b19a6..5eaae20fe74 100644
--- a/llvm/test/Transforms/InstCombine/pr43893.ll
+++ b/llvm/test/Transforms/InstCombine/pr43893.ll
@@ -13,9 +13,10 @@ entry:
 ;CHECK: call void @llvm.dbg.value(metadata i32 -8
 ;CHECK: call void @llvm.dbg.value(metadata i32 undef
   %conv = sext i8 %dec to i32, !dbg !17
-  call void @llvm.dbg.value(metadata i32 %conv, metadata !18, metadata !DIExpression()), !dbg !19
+  %udiv = udiv i32 %conv, 4, !dbg !17
+  call void @llvm.dbg.value(metadata i32 %udiv, metadata !18, metadata !DIExpression()), !dbg !19
   call void @llvm.dbg.value(metadata i32 -8, metadata !20, metadata !DIExpression()), !dbg !19
-  call void @llvm.dbg.value(metadata i32 %conv, metadata !20, metadata !DIExpression()), !dbg !19
+  call void @llvm.dbg.value(metadata i32 %udiv, metadata !20, metadata !DIExpression()), !dbg !19
   store i8 0, i8* @b, align 1, !dbg !21
   %cmp = icmp sgt i32 %conv, 0, !dbg !22
   %conv1 = zext i1 %cmp to i32, !dbg !22
diff --git a/llvm/test/Transforms/InstCombine/unavailable-debug.ll b/llvm/test/Transforms/InstCombine/unavailable-debug.ll
index 703c1c2898f..e3f0d7cf22d 100644
--- a/llvm/test/Transforms/InstCombine/unavailable-debug.ll
+++ b/llvm/test/Transforms/InstCombine/unavailable-debug.ll
@@ -2,7 +2,7 @@
 
 ; Make sure to update the debug value after dead code elimination.
 ; CHECK: %call = call signext i8 @b(i32 6), !dbg !39
-; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !30, metadata !DIExpression()), !dbg !38
+; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 %call, metadata !30, metadata !DIExpression(DW_OP_LLVM_convert, 8, DW_ATE_signed, DW_OP_LLVM_convert, 32, DW_ATE_signed, DW_OP_stack_value)), !dbg !38
 
 @e = common local_unnamed_addr global i8 0, align 1, !dbg !0
 @c = common local_unnamed_addr global i32 0, align 4, !dbg !6