[DebugInfo] Expand ability to load 2-byte addresses in dwarf sections

Some dwarf loaders in LLVM are hard-coded to only accept 4-byte and 8-byte address sizes. This patch generalizes acceptance into `DWARFContext::isAddressSizeSupported` and provides a common way to generate rejection errors.

The MSP430 target has been given new tests to cover dwarf loading cases that previously failed due to 2-byte addresses.

Reviewed By: dblaikie

Differential Revision: https://reviews.llvm.org/D111953

Author: jackoalan

llvm/include/llvm/DebugInfo/DWARF/DWARFContext.h

@@ -375,6 +375,23 @@ class DWARFContext : public DIContext {
   static bool isAddressSizeSupported(unsigned AddressSize) {
     return llvm::is_contained(getSupportedAddressSizes(), AddressSize);
   }
+  template <typename... Ts>
+  static Error checkAddressSizeSupported(unsigned AddressSize,
+                                         std::error_code EC, char const *Fmt,
+                                         const Ts &...Vals) {
+    if (isAddressSizeSupported(AddressSize))
+      return Error::success();
+    std::string Buffer;
+    raw_string_ostream Stream(Buffer);
+    Stream << format(Fmt, Vals...)
+           << " has unsupported address size: " << AddressSize
+           << " (supported are ";
+    ListSeparator LS;
+    for (unsigned Size : DWARFContext::getSupportedAddressSizes())
+      Stream << LS << Size;
+    Stream << ')';
+    return make_error<StringError>(Stream.str(), EC);
+  }
 
   std::shared_ptr<DWARFContext> getDWOContext(StringRef AbsolutePath);
 

llvm/include/llvm/DebugInfo/DWARF/DWARFDebugRangeList.h

@@ -49,12 +49,7 @@ class DWARFDebugRangeList {
     /// 2. An address, which defines the appropriate base address for
     /// use in interpreting the beginning and ending address offsets of
     /// subsequent entries of the location list.
-    bool isBaseAddressSelectionEntry(uint8_t AddressSize) const {
-      assert(AddressSize == 4 || AddressSize == 8);
-      if (AddressSize == 4)
-        return StartAddress == -1U;
-      return StartAddress == -1ULL;
-    }
+    bool isBaseAddressSelectionEntry(uint8_t AddressSize) const;
   };
 
 private:

llvm/lib/DebugInfo/DWARF/DWARFDebugAddr.cpp

@@ -8,7 +8,7 @@
 
 #include "llvm/DebugInfo/DWARF/DWARFDebugAddr.h"
 #include "llvm/BinaryFormat/Dwarf.h"
-#include "llvm/DebugInfo/DWARF/DWARFUnit.h"
+#include "llvm/DebugInfo/DWARF/DWARFContext.h"
 
 using namespace llvm;
 
@@ -18,12 +18,10 @@ Error DWARFDebugAddrTable::extractAddresses(const DWARFDataExtractor &Data,
   assert(EndOffset >= *OffsetPtr);
   uint64_t DataSize = EndOffset - *OffsetPtr;
   assert(Data.isValidOffsetForDataOfSize(*OffsetPtr, DataSize));
-  if (AddrSize != 4 && AddrSize != 8)
-    return createStringError(errc::not_supported,
-                             "address table at offset 0x%" PRIx64
-                             " has unsupported address size %" PRIu8
-                             " (4 and 8 are supported)",
-                             Offset, AddrSize);
+  if (Error SizeErr = DWARFContext::checkAddressSizeSupported(
+          AddrSize, errc::not_supported, "address table at offset 0x%" PRIx64,
+          Offset))
+    return SizeErr;
   if (DataSize % AddrSize != 0) {
     invalidateLength();
     return createStringError(errc::invalid_argument,
@@ -148,8 +146,20 @@ void DWARFDebugAddrTable::dump(raw_ostream &OS, DIDumpOptions DumpOpts) const {
   }
 
   if (Addrs.size() > 0) {
-    const char *AddrFmt =
-        (AddrSize == 4) ? "0x%8.8" PRIx64 "\n" : "0x%16.16" PRIx64 "\n";
+    const char *AddrFmt;
+    switch (AddrSize) {
+    case 2:
+      AddrFmt = "0x%4.4" PRIx64 "\n";
+      break;
+    case 4:
+      AddrFmt = "0x%8.8" PRIx64 "\n";
+      break;
+    case 8:
+      AddrFmt = "0x%16.16" PRIx64 "\n";
+      break;
+    default:
+      llvm_unreachable("unsupported address size");
+    }
     OS << "Addrs: [\n";
     for (uint64_t Addr : Addrs)
       OS << format(AddrFmt, Addr);

llvm/lib/DebugInfo/DWARF/DWARFDebugArangeSet.cpp

@@ -8,6 +8,7 @@
 
 #include "llvm/DebugInfo/DWARF/DWARFDebugArangeSet.h"
 #include "llvm/BinaryFormat/Dwarf.h"
+#include "llvm/DebugInfo/DWARF/DWARFContext.h"
 #include "llvm/DebugInfo/DWARF/DWARFFormValue.h"
 #include "llvm/Support/Errc.h"
 #include "llvm/Support/Format.h"
@@ -87,12 +88,10 @@ Error DWARFDebugArangeSet::extract(DWARFDataExtractor data,
                              "the length of address range table at offset "
                              "0x%" PRIx64 " exceeds section size",
                              Offset);
-  if (HeaderData.AddrSize != 4 && HeaderData.AddrSize != 8)
-    return createStringError(errc::invalid_argument,
-                             "address range table at offset 0x%" PRIx64
-                             " has unsupported address size: %d "
-                             "(4 and 8 supported)",
-                             Offset, HeaderData.AddrSize);
+  if (Error SizeErr = DWARFContext::checkAddressSizeSupported(
+          HeaderData.AddrSize, errc::invalid_argument,
+          "address range table at offset 0x%" PRIx64, Offset))
+    return SizeErr;
   if (HeaderData.SegSize != 0)
     return createStringError(errc::not_supported,
                              "non-zero segment selector size in address range "

llvm/lib/DebugInfo/DWARF/DWARFDebugRangeList.cpp

@@ -16,6 +16,12 @@
 
 using namespace llvm;
 
+bool DWARFDebugRangeList::RangeListEntry::isBaseAddressSelectionEntry(
+    uint8_t AddressSize) const {
+  assert(DWARFContext::isAddressSizeSupported(AddressSize));
+  return StartAddress == dwarf::computeTombstoneAddress(AddressSize);
+}
+
 void DWARFDebugRangeList::clear() {
   Offset = -1ULL;
   AddressSize = 0;
@@ -30,9 +36,10 @@ Error DWARFDebugRangeList::extract(const DWARFDataExtractor &data,
                        "invalid range list offset 0x%" PRIx64, *offset_ptr);
 
   AddressSize = data.getAddressSize();
-  if (AddressSize != 4 && AddressSize != 8)
-    return createStringError(errc::invalid_argument,
-                       "invalid address size: %" PRIu8, AddressSize);
+  if (Error SizeErr = DWARFContext::checkAddressSizeSupported(
+          AddressSize, errc::invalid_argument,
+          "range list at offset 0x%" PRIx64, *offset_ptr))
+    return SizeErr;
   Offset = *offset_ptr;
   while (true) {
     RangeListEntry Entry;
@@ -58,12 +65,22 @@ Error DWARFDebugRangeList::extract(const DWARFDataExtractor &data,
 }
 
 void DWARFDebugRangeList::dump(raw_ostream &OS) const {
-  for (const RangeListEntry &RLE : Entries) {
-    const char *format_str =
-        (AddressSize == 4 ? "%08" PRIx64 " %08" PRIx64 " %08" PRIx64 "\n"
-                          : "%08" PRIx64 " %016" PRIx64 " %016" PRIx64 "\n");
-    OS << format(format_str, Offset, RLE.StartAddress, RLE.EndAddress);
+  const char *AddrFmt;
+  switch (AddressSize) {
+  case 2:
+    AddrFmt = "%08" PRIx64 " %04" PRIx64 " %04" PRIx64 "\n";
+    break;
+  case 4:
+    AddrFmt = "%08" PRIx64 " %08" PRIx64 " %08" PRIx64 "\n";
+    break;
+  case 8:
+    AddrFmt = "%08" PRIx64 " %016" PRIx64 " %016" PRIx64 "\n";
+    break;
+  default:
+    llvm_unreachable("unsupported address size");
   }
+  for (const RangeListEntry &RLE : Entries)
+    OS << format(AddrFmt, Offset, RLE.StartAddress, RLE.EndAddress);
   OS << format("%08" PRIx64 " <End of list>\n", Offset);
 }
 

llvm/lib/DebugInfo/DWARF/DWARFListTable.cpp

@@ -8,6 +8,7 @@
 
 #include "llvm/DebugInfo/DWARF/DWARFListTable.h"
 #include "llvm/BinaryFormat/Dwarf.h"
+#include "llvm/DebugInfo/DWARF/DWARFContext.h"
 #include "llvm/Support/Errc.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/Format.h"
@@ -54,11 +55,10 @@ Error DWARFListTableHeader::extract(DWARFDataExtractor Data,
                        "unrecognised %s table version %" PRIu16
                        " in table at offset 0x%" PRIx64,
                        SectionName.data(), HeaderData.Version, HeaderOffset);
-  if (HeaderData.AddrSize != 4 && HeaderData.AddrSize != 8)
-    return createStringError(errc::not_supported,
-                       "%s table at offset 0x%" PRIx64
-                       " has unsupported address size %" PRIu8,
-                       SectionName.data(), HeaderOffset, HeaderData.AddrSize);
+  if (Error SizeErr = DWARFContext::checkAddressSizeSupported(
+          HeaderData.AddrSize, errc::not_supported,
+          "%s table at offset 0x%" PRIx64, SectionName.data(), HeaderOffset))
+    return SizeErr;
   if (HeaderData.SegSize != 0)
     return createStringError(errc::not_supported,
                        "%s table at offset 0x%" PRIx64

llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp

@@ -315,15 +315,10 @@ bool DWARFUnitHeader::extract(DWARFContext &Context,
     return false;
   }
 
-  if (!DWARFContext::isAddressSizeSupported(getAddressByteSize())) {
-    SmallVector<std::string, 3> Sizes;
-    for (auto Size : DWARFContext::getSupportedAddressSizes())
-      Sizes.push_back(std::to_string(Size));
-    Context.getWarningHandler()(createStringError(
-        errc::invalid_argument,
-        "DWARF unit at offset 0x%8.8" PRIx64 " "
-        "has unsupported address size %" PRIu8 ", supported are %s",
-        Offset, getAddressByteSize(), llvm::join(Sizes, ", ").c_str()));
+  if (Error SizeErr = DWARFContext::checkAddressSizeSupported(
+          getAddressByteSize(), errc::invalid_argument,
+          "DWARF unit at offset 0x%8.8" PRIx64, Offset)) {
+    Context.getWarningHandler()(std::move(SizeErr));
     return false;
   }
 

llvm/test/DebugInfo/MSP430/cu-ranges.ll

@@ -0,0 +1,72 @@
+; RUN: llc -O0 -mtriple=msp430 -filetype=obj %s -o %t
+; RUN: llvm-dwarfdump -v %t | FileCheck %s
+
+; Ported from generic test to cover 2-byte address size case
+
+; Check that we emit ranges for this which has a non-traditional section and a normal section.
+
+; CHECK: DW_TAG_compile_unit
+; CHECK: DW_AT_ranges
+; CHECK: DW_TAG_subprogram
+; CHECK: DW_AT_low_pc
+; CHECK: DW_AT_high_pc
+; CHECK: DW_TAG_subprogram
+; CHECK: DW_AT_low_pc
+; CHECK: DW_AT_high_pc
+
+; CHECK: .debug_ranges contents:
+; CHECK-NEXT: 00000000 0000 0030
+; CHECK-NEXT: 00000000 0000 0030
+; CHECK-NEXT: 00000000 <End of list>
+
+; Function Attrs: nounwind uwtable
+define i32 @foo(i32 %a) #0 section "__TEXT,__foo" !dbg !4 {
+entry:
+  %a.addr = alloca i32, align 4
+  store i32 %a, i32* %a.addr, align 4
+  call void @llvm.dbg.declare(metadata i32* %a.addr, metadata !13, metadata !DIExpression()), !dbg !14
+  %0 = load i32, i32* %a.addr, align 4, !dbg !15
+  %add = add nsw i32 %0, 5, !dbg !15
+  ret i32 %add, !dbg !15
+}
+
+; Function Attrs: nounwind readnone
+declare void @llvm.dbg.declare(metadata, metadata, metadata) #1
+
+; Function Attrs: nounwind uwtable
+define i32 @bar(i32 %a) #0 !dbg !9 {
+entry:
+  %a.addr = alloca i32, align 4
+  store i32 %a, i32* %a.addr, align 4
+  call void @llvm.dbg.declare(metadata i32* %a.addr, metadata !16, metadata !DIExpression()), !dbg !17
+  %0 = load i32, i32* %a.addr, align 4, !dbg !18
+  %add = add nsw i32 %0, 5, !dbg !18
+  ret i32 %add, !dbg !18
+}
+
+attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { nounwind readnone }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!10, !11}
+!llvm.ident = !{!12}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, producer: "clang version 3.5.0 (trunk 204164) (llvm/trunk 204183)", isOptimized: false, emissionKind: FullDebug, file: !1, enums: !2, retainedTypes: !2, globals: !2, imports: !2)
+!1 = !DIFile(filename: "foo.c", directory: "/usr/local/google/home/echristo")
+!2 = !{}
+!4 = distinct !DISubprogram(name: "foo", line: 1, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 1, file: !1, scope: !5, type: !6, retainedNodes: !2)
+!5 = !DIFile(filename: "foo.c", directory: "/usr/local/google/home/echristo")
+!6 = !DISubroutineType(types: !7)
+!7 = !{!8, !8}
+!8 = !DIBasicType(tag: DW_TAG_base_type, name: "int", size: 32, align: 32, encoding: DW_ATE_signed)
+!9 = distinct !DISubprogram(name: "bar", line: 5, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 5, file: !1, scope: !5, type: !6, retainedNodes: !2)
+!10 = !{i32 2, !"Dwarf Version", i32 4}
+!11 = !{i32 1, !"Debug Info Version", i32 3}
+!12 = !{!"clang version 3.5.0 (trunk 204164) (llvm/trunk 204183)"}
+!13 = !DILocalVariable(name: "a", line: 1, arg: 1, scope: !4, file: !5, type: !8)
+!14 = !DILocation(line: 1, scope: !4)
+!15 = !DILocation(line: 2, scope: !4)
+!16 = !DILocalVariable(name: "a", line: 5, arg: 1, scope: !9, file: !5, type: !8)
+!17 = !DILocation(line: 5, scope: !9)
+!18 = !DILocation(line: 6, scope: !9)
+