[PDB] Finish and simplify TPI hashing

Summary:
This removes the CVTypeVisitor updater and verifier classes. They were
made dead by the minimal type dumping refactoring. Replace them with a
single function that takes a type record and produces a hash. Call this
from the minimal type dumper and compare the hash.

I also noticed that the microsoft-pdb reference repository uses a basic
CRC32 for records that aren't special. We already have an implementation
of that CRC ready to use, because it's used in COFF for ICF.

I'll make LLD call this hashing utility in a follow-up change. We might
also consider using this same hash in type stream merging, so that we
don't have to hash our records twice.

Reviewers: inglorion, ruiu

Subscribers: llvm-commits, hiraditya

Differential Revision: https://reviews.llvm.org/D35515

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@308240 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 19 insertions, 6 deletions

diff --git a/tools/llvm-pdbutil/DumpOutputStyle.cpp b/tools/llvm-pdbutil/DumpOutputStyle.cpp
index 0642d841fd9f..01c7481c3086 100644
--- a/tools/llvm-pdbutil/DumpOutputStyle.cpp
+++ b/tools/llvm-pdbutil/DumpOutputStyle.cpp
@@ -654,7 +654,7 @@ static void dumpFullTypeStream(LinePrinter &Printer,
       NumDigits(TypeIndex::FirstNonSimpleIndex + Stream.getNumTypeRecords());
 
   MinimalTypeDumpVisitor V(Printer, Width + 2, Bytes, Extras, Types,
-                           Stream.getHashValues());
+                           Stream.getNumHashBuckets(), Stream.getHashValues());
 
   if (auto EC = codeview::visitTypeStream(Types, V)) {
     Printer.formatLine("An error occurred dumping type records: {0}",
@@ -670,7 +670,7 @@ static void dumpPartialTypeStream(LinePrinter &Printer,
       NumDigits(TypeIndex::FirstNonSimpleIndex + Stream.getNumTypeRecords());
 
   MinimalTypeDumpVisitor V(Printer, Width + 2, Bytes, Extras, Types,
-                           Stream.getHashValues());
+                           Stream.getNumHashBuckets(), Stream.getHashValues());
 
   if (opts::dump::DumpTypeDependents) {
     // If we need to dump all dependents, then iterate each index and find
diff --git a/tools/llvm-pdbutil/MinimalTypeDumper.cpp b/tools/llvm-pdbutil/MinimalTypeDumper.cpp
index fc54a72be236..0079b9e7eaa4 100644
--- a/tools/llvm-pdbutil/MinimalTypeDumper.cpp
+++ b/tools/llvm-pdbutil/MinimalTypeDumper.cpp
@@ -18,6 +18,7 @@
 #include "llvm/DebugInfo/CodeView/Formatters.h"
 #include "llvm/DebugInfo/CodeView/LazyRandomTypeCollection.h"
 #include "llvm/DebugInfo/CodeView/TypeRecord.h"
+#include "llvm/DebugInfo/PDB/Native/TpiHashing.h"
 #include "llvm/Support/FormatVariadic.h"
 #include "llvm/Support/MathExtras.h"
 
@@ -214,10 +215,20 @@ Error MinimalTypeDumpVisitor::visitTypeBegin(CVType &Record, TypeIndex Index) {
                  getLeafTypeName(Record.Type), Record.length());
   } else {
     std::string H;
-    if (Index.toArrayIndex() >= HashValues.size())
+    if (Index.toArrayIndex() >= HashValues.size()) {
       H = "(not present)";
-    else
-      H = utostr(HashValues[Index.toArrayIndex()]);
+    } else {
+      uint32_t Hash = HashValues[Index.toArrayIndex()];
+      Expected<uint32_t> MaybeHash = hashTypeRecord(Record);
+      if (!MaybeHash)
+        return MaybeHash.takeError();
+      uint32_t OurHash = *MaybeHash;
+      OurHash %= NumHashBuckets;
+      if (Hash == OurHash)
+        H = "0x" + utohexstr(Hash);
+      else
+        H = "0x" + utohexstr(Hash) + ", our hash = 0x" + utohexstr(OurHash);
+    }
     P.formatLine("{0} | {1} [size = {2}, hash = {3}]",
                  fmt_align(Index, AlignStyle::Right, Width),
                  getLeafTypeName(Record.Type), Record.length(), H);
diff --git a/tools/llvm-pdbutil/MinimalTypeDumper.h b/tools/llvm-pdbutil/MinimalTypeDumper.h
index 42882b4b4060..4227688f0f71 100644
--- a/tools/llvm-pdbutil/MinimalTypeDumper.h
+++ b/tools/llvm-pdbutil/MinimalTypeDumper.h
@@ -25,9 +25,10 @@ class MinimalTypeDumpVisitor : public codeview::TypeVisitorCallbacks {
 public:
   MinimalTypeDumpVisitor(LinePrinter &P, uint32_t Width, bool RecordBytes,
                          bool Hashes, codeview::LazyRandomTypeCollection &Types,
+                         uint32_t NumHashBuckets,
                          FixedStreamArray<support::ulittle32_t> HashValues)
       : P(P), Width(Width), RecordBytes(RecordBytes), Hashes(Hashes),
-        Types(Types), HashValues(HashValues) {}
+        Types(Types), NumHashBuckets(NumHashBuckets), HashValues(HashValues) {}
 
   Error visitTypeBegin(codeview::CVType &Record,
                        codeview::TypeIndex Index) override;
@@ -53,6 +54,7 @@ private:
   bool RecordBytes = false;
   bool Hashes = false;
   codeview::LazyRandomTypeCollection &Types;
+  uint32_t NumHashBuckets;
   FixedStreamArray<support::ulittle32_t> HashValues;
 };
 } // namespace pdb