[llvm-cov][WebAssembly] Read __llvm_prf_names from data segments

On WebAssembly, most coverage metadata contents read by llvm-cov (like
`__llvm_covmap` and `__llvm_covfun`) are stored in custom sections
because they are not referenced at runtime. However, `__llvm_prf_names`
is referenced at runtime by the profile runtime library and is read
by llvm-cov post-processing tools, so it needs to be stored in a data
segment, which is allocatable at runtime and accessible by tools as long
as "name" section is present in the binary.

This patch changes the way llvm-cov reads `__llvm_prf_names` on
WebAssembly. Instead of looking for a section, it looks for a data
segment with the same name.

Author: kateinoigakukun

llvm/lib/ProfileData/Coverage/CoverageMappingReader.cpp

@@ -18,12 +18,14 @@
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/BinaryFormat/Wasm.h"
 #include "llvm/Object/Archive.h"
 #include "llvm/Object/Binary.h"
 #include "llvm/Object/COFF.h"
 #include "llvm/Object/Error.h"
 #include "llvm/Object/MachOUniversal.h"
 #include "llvm/Object/ObjectFile.h"
+#include "llvm/Object/Wasm.h"
 #include "llvm/ProfileData/InstrProf.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/Compression.h"
@@ -1075,6 +1077,53 @@ lookupSections(ObjectFile &OF, InstrProfSectKind IPSK) {
   return Sections;
 }
 
+/// Find a section that matches \p Name and is allocatable at runtime.
+///
+/// Returns the contents of the section and its start offset in the object file.
+static Expected<std::pair<StringRef, uint64_t>>
+lookupAllocatableSection(ObjectFile &OF, InstrProfSectKind IPSK) {
+  // On Wasm, allocatable sections can live only in data segments.
+  if (auto *WOF = dyn_cast<WasmObjectFile>(&OF)) {
+    std::vector<const WasmSegment *> Segments;
+    auto ObjFormat = OF.getTripleObjectFormat();
+    auto Name =
+        getInstrProfSectionName(IPSK, ObjFormat, /*AddSegmentInfo=*/false);
+    for (const auto &DebugName : WOF->debugNames()) {
+      if (DebugName.Type != wasm::NameType::DATA_SEGMENT ||
+          DebugName.Name != Name)
+        continue;
+      if (DebugName.Index >= WOF->dataSegments().size())
+        return make_error<CoverageMapError>(coveragemap_error::malformed);
+      auto &Segment = WOF->dataSegments()[DebugName.Index];
+      Segments.push_back(&Segment);
+    }
+    if (Segments.empty())
+      return make_error<CoverageMapError>(coveragemap_error::no_data_found);
+    if (Segments.size() != 1)
+      return make_error<CoverageMapError>(coveragemap_error::malformed);
+
+    const auto &Segment = *Segments.front();
+    auto &Data = Segment.Data;
+    StringRef Content(reinterpret_cast<const char *>(Data.Content.data()),
+                      Data.Content.size());
+    return std::make_pair(Content, Segment.SectionOffset);
+  }
+
+  // On other object file types, delegate to lookupSections to find the section.
+  auto Sections = lookupSections(OF, IPSK);
+  if (!Sections)
+    return Sections.takeError();
+  if (Sections->size() != 1)
+    return make_error<CoverageMapError>(
+        coveragemap_error::malformed,
+        "the size of coverage mapping section is not one");
+  auto &Section = Sections->front();
+  auto ContentsOrErr = Section.getContents();
+  if (!ContentsOrErr)
+    return ContentsOrErr.takeError();
+  return std::make_pair(*ContentsOrErr, Section.getAddress());
+}
+
 static Expected<std::unique_ptr<BinaryCoverageReader>>
 loadBinaryFormat(std::unique_ptr<Binary> Bin, StringRef Arch,
                  StringRef CompilationDir = "",
@@ -1105,23 +1154,20 @@ loadBinaryFormat(std::unique_ptr<Binary> Bin, StringRef Arch,
 
   // Look for the sections that we are interested in.
   auto ProfileNames = std::make_unique<InstrProfSymtab>();
-  std::vector<SectionRef> NamesSectionRefs;
   // If IPSK_name is not found, fallback to search for IPK_covname, which is
   // used when binary correlation is enabled.
-  auto NamesSection = lookupSections(*OF, IPSK_name);
+  auto NamesSection = lookupAllocatableSection(*OF, IPSK_name);
   if (auto E = NamesSection.takeError()) {
     consumeError(std::move(E));
-    NamesSection = lookupSections(*OF, IPSK_covname);
+    NamesSection = lookupAllocatableSection(*OF, IPSK_covname);
     if (auto E = NamesSection.takeError())
       return std::move(E);
   }
-  NamesSectionRefs = *NamesSection;
 
-  if (NamesSectionRefs.size() != 1)
-    return make_error<CoverageMapError>(
-        coveragemap_error::malformed,
-        "the size of coverage mapping section is not one");
-  if (Error E = ProfileNames->create(NamesSectionRefs.back()))
+  uint64_t NamesAddress;
+  StringRef NamesContent;
+  std::tie(NamesContent, NamesAddress) = *NamesSection;
+  if (Error E = ProfileNames->create(NamesContent, NamesAddress))
     return std::move(E);
 
   auto CoverageSection = lookupSections(*OF, IPSK_covmap);

llvm/test/tools/llvm-cov/Inputs/binary-formats.v6.wasm32

@@ -0,0 +1,4 @@
+__main_argc_argv
+0x0
+1
+100

llvm/test/tools/llvm-cov/Inputs/binary-formats.wasm.proftext

@@ -10,4 +10,10 @@ int main(int argc, const char *argv[]) {}
 // RUN: llvm-cov show %S/Inputs/binary-formats.v3.macho64l -instr-profile %t.profdata -path-equivalence=/tmp,%S %s | FileCheck %s
 // RUN: llvm-cov show %S/Inputs/binary-formats.v6.linux64l -instr-profile %t.profdata -path-equivalence=/tmp,%S %s | FileCheck %s
 
+// RUN: llvm-profdata merge %S/Inputs/binary-formats.wasm.proftext -o %t.wasm.profdata
+// NOTE: The wasm binary is built with the following command:
+//   clang -target wasm32-unknown-wasi %s -o %S/Inputs/binary-formats.v6.wasm32 \
+//     -fprofile-instr-generate -fcoverage-mapping -lwasi-emulated-getpid -lwasi-emulated-mman
+// RUN: llvm-cov show %S/Inputs/binary-formats.v6.wasm32 -instr-profile %t.wasm.profdata -path-equivalence=/tmp,%S %s | FileCheck %s
+
 // RUN: llvm-cov export %S/Inputs/binary-formats.macho64l -instr-profile %t.profdata | FileCheck %S/Inputs/binary-formats.canonical.json