DWARF support for multiple line tables (#2557)

Multiple tables appear to be emitted when linking files
together. This fixes our support for that, which did not
update their size properly. This required patching the
YAML emitting code from LLVM in order to measure
the size and then emit it, as that code is apparently
not designed to handle changes in line table
contents.

Other minor fixes:

* Set the flags for our dwarfdump command to emit
  the same as llvm-dwarfdump does with -v -all.
* Add support for a few more opcodes,
  set_discriminator, set_basic_block, fixed_advance_pc,
  set_isa.
* Handle a compile unit without abbreviations in the
  YAML code (again, apparently not something this
  LLVM code was intended to do).
*  Handle a compile unit with zero entries in the
  YAML code (ditto).
* Properly set the AddressSize - we use the
  DWARFContext in a different way than LLVM expects,
  apparently.

With this the emscripten test suite passes with
-gforce_dwarf without crashing.

My overall impression so from the the YAML code is
that it probably isn't a long-term solution for us. Perhaps
it may end up being scaffolding, that is, we can
replace it with our own code eventually that is based
on it, and remove most of the LLVM code. Before
deciding that we should get everything working first,
and this seems like the quickest path there.

Author: kripken

src/wasm/wasm-debug.cpp

@@ -61,7 +61,8 @@ struct BinaryenDWARFInfo {
     }
     // Parse debug sections.
     uint8_t addrSize = 4;
-    context = llvm::DWARFContext::create(sections, addrSize);
+    bool isLittleEndian = true;
+    context = llvm::DWARFContext::create(sections, addrSize, isLittleEndian);
   }
 };
 
@@ -76,6 +77,8 @@ void dumpDWARF(const Module& wasm) {
     }
   }
   llvm::DIDumpOptions options;
+  options.DumpType = llvm::DIDT_All;
+  options.ShowChildren = true;
   options.Verbose = true;
   info.context->dump(llvm::outs(), options);
 }
@@ -111,8 +114,8 @@ struct LineState {
   uint32_t line = 1;
   uint32_t col = 0;
   uint32_t file = 1;
-  // TODO uint32_t isa = 0;
-  // TODO Discriminator = 0;
+  uint32_t isa = 0;
+  uint32_t discriminator = 0;
   bool isStmt;
   bool basicBlock = false;
   // XXX these two should be just prologue, epilogue?
@@ -139,9 +142,17 @@ struct LineState {
           case llvm::dwarf::DW_LNE_end_sequence: {
             return true;
           }
+          case llvm::dwarf::DW_LNE_set_discriminator: {
+            discriminator = opcode.Data;
+            break;
+          }
+          case llvm::dwarf::DW_LNE_define_file: {
+            Fatal() << "TODO: DW_LNE_define_file";
+          }
           default: {
-            Fatal() << "unknown debug line sub-opcode: " << std::hex
-                    << opcode.SubOpcode;
+            // An unknown opcode, ignore.
+            std::cerr << "warning: unknown subopcopde " << opcode.SubOpcode
+                      << '\n';
           }
         }
         break;
@@ -174,13 +185,25 @@ struct LineState {
         isStmt = !isStmt;
         break;
       }
+      case llvm::dwarf::DW_LNS_set_basic_block: {
+        basicBlock = true;
+        break;
+      }
       case llvm::dwarf::DW_LNS_const_add_pc: {
         uint8_t AdjustOpcode = 255 - table.OpcodeBase;
         uint64_t AddrOffset =
           (AdjustOpcode / table.LineRange) * table.MinInstLength;
         addr += AddrOffset;
         break;
       }
+      case llvm::dwarf::DW_LNS_fixed_advance_pc: {
+        addr += opcode.Data;
+        break;
+      }
+      case llvm::dwarf::DW_LNS_set_isa: {
+        isa = opcode.Data;
+        break;
+      }
       default: {
         if (opcode.Opcode >= table.OpcodeBase) {
           // Special opcode: adjust line and addr, using some math.
@@ -239,11 +262,23 @@ struct LineState {
       item.Data = file;
       newOpcodes.push_back(item);
     }
+    if (isa != old.isa) {
+      auto item = makeItem(llvm::dwarf::DW_LNS_set_isa);
+      item.Data = isa;
+      newOpcodes.push_back(item);
+    }
+    if (discriminator != old.discriminator) {
+      // len = 1 (subopcode) + 4 (wasm32 address)
+      auto item = makeItem(llvm::dwarf::DW_LNE_set_discriminator, 5);
+      item.Data = discriminator;
+      newOpcodes.push_back(item);
+    }
     if (isStmt != old.isStmt) {
       newOpcodes.push_back(makeItem(llvm::dwarf::DW_LNS_negate_stmt));
     }
     if (basicBlock != old.basicBlock) {
-      Fatal() << "bb";
+      assert(basicBlock);
+      newOpcodes.push_back(makeItem(llvm::dwarf::DW_LNS_set_basic_block));
     }
     if (prologueEnd != old.prologueEnd) {
       assert(prologueEnd);
@@ -382,21 +417,6 @@ static void updateDebugLines(const Module& wasm,
   }
 }
 
-static void fixEmittedSection(const std::string& name,
-                              std::vector<char>& data) {
-  if (name == ".debug_line") {
-    // The YAML code does not update the line section size. However, it is
-    // trivial to do so after the fact, as the wasm section's additional size is
-    // easy to compute: it is the emitted size - the 4 bytes of the size itself.
-    uint32_t size = data.size() - 4;
-    BufferWithRandomAccess buf;
-    buf << size;
-    for (int i = 0; i < 4; i++) {
-      data[i] = buf[i];
-    }
-  }
-}
-
 void writeDWARFSections(Module& wasm, const BinaryLocationsMap& newLocations) {
   BinaryenDWARFInfo info(wasm);
 
@@ -411,7 +431,8 @@ void writeDWARFSections(Module& wasm, const BinaryLocationsMap& newLocations) {
   // TODO: Actually update, and remove sections we don't know how to update yet?
 
   // Convert to binary sections.
-  auto newSections = EmitDebugSections(data, true);
+  auto newSections =
+    EmitDebugSections(data, false /* EmitFixups for debug_info */);
 
   // Update the custom sections in the wasm.
   // TODO: efficiency
@@ -422,7 +443,6 @@ void writeDWARFSections(Module& wasm, const BinaryLocationsMap& newLocations) {
         auto llvmData = newSections[llvmName]->getBuffer();
         section.data.resize(llvmData.size());
         std::copy(llvmData.begin(), llvmData.end(), section.data.data());
-        fixEmittedSection(section.name, section.data);
       }
     }
   }

test/passes/dwarfdump.bin.txt

@@ -39,6 +39,17 @@ Abbrev table for offset: 0x00000000
               DW_AT_low_pc [DW_FORM_addr]	(0x0000000000000005)
               DW_AT_high_pc [DW_FORM_data4]	(0x00000002)
 
+0x00000026:   DW_TAG_subprogram [2]  
+                DW_AT_low_pc [DW_FORM_addr]	(0x0000000000000005)
+                DW_AT_high_pc [DW_FORM_data4]	(0x00000002)
+                DW_AT_linkage_name [DW_FORM_strp]	( .debug_str[0x000000c8] = "_Z3foov")
+                DW_AT_name [DW_FORM_strp]	( .debug_str[0x000000d0] = "foo")
+                DW_AT_decl_file [DW_FORM_data1]	("/usr/local/google/home/azakai/Dev/emscripten/a.cpp")
+                DW_AT_decl_line [DW_FORM_data1]	(3)
+                DW_AT_external [DW_FORM_flag_present]	(true)
+
+0x00000039:   NULL
+
 .debug_line contents:
 debug_line[0x00000000]
 Line table prologue:

test/passes/dwarfdump_roundtrip_dwarfdump.bin.txt

@@ -39,6 +39,17 @@ Abbrev table for offset: 0x00000000
               DW_AT_low_pc [DW_FORM_addr]	(0x0000000000000005)
               DW_AT_high_pc [DW_FORM_data4]	(0x00000002)
 
+0x00000026:   DW_TAG_subprogram [2]  
+                DW_AT_low_pc [DW_FORM_addr]	(0x0000000000000005)
+                DW_AT_high_pc [DW_FORM_data4]	(0x00000002)
+                DW_AT_linkage_name [DW_FORM_strp]	( .debug_str[0x000000c8] = "_Z3foov")
+                DW_AT_name [DW_FORM_strp]	( .debug_str[0x000000d0] = "foo")
+                DW_AT_decl_file [DW_FORM_data1]	("/usr/local/google/home/azakai/Dev/emscripten/a.cpp")
+                DW_AT_decl_line [DW_FORM_data1]	(3)
+                DW_AT_external [DW_FORM_flag_present]	(true)
+
+0x00000039:   NULL
+
 .debug_line contents:
 debug_line[0x00000000]
 Line table prologue:
@@ -129,6 +140,17 @@ Abbrev table for offset: 0x00000000
               DW_AT_low_pc [DW_FORM_addr]	(0x0000000000000005)
               DW_AT_high_pc [DW_FORM_data4]	(0x00000002)
 
+0x00000026:   DW_TAG_subprogram [2]  
+                DW_AT_low_pc [DW_FORM_addr]	(0x0000000000000005)
+                DW_AT_high_pc [DW_FORM_data4]	(0x00000002)
+                DW_AT_linkage_name [DW_FORM_strp]	( .debug_str[0x000000c8] = "_Z3foov")
+                DW_AT_name [DW_FORM_strp]	( .debug_str[0x000000d0] = "foo")
+                DW_AT_decl_file [DW_FORM_data1]	("/usr/local/google/home/azakai/Dev/emscripten/a.cpp")
+                DW_AT_decl_line [DW_FORM_data1]	(3)
+                DW_AT_external [DW_FORM_flag_present]	(true)
+
+0x00000039:   NULL
+
 .debug_line contents:
 debug_line[0x00000000]
 Line table prologue: