[PDB] Increase TPI hash bucket count.

PDBs contain several serialized hash tables. In the microsoft-pdb
repo published to support LLVM implementing PDB support, the
provided initializes the bucket count for the TPI and IPI streams
to the maximum size. This occurs in tpi.cpp L33 and tpi.cpp L398.
In the LLVM code for generating PDBs, these streams are created with
minimum number of buckets. This difference makes LLVM generated
PDBs slower for when used for debugging.

Patch by C.J. Hebert
Differential Revision: https://reviews.llvm.org/D56942

llvm-svn: 352117

diff --git a/lld/test/COFF/pdb-tpi-hash-size.test b/lld/test/COFF/pdb-tpi-hash-size.test
new file mode 100644 (file)
index 0000000..3635a5c
--- /dev/null
+++ b/lld/test/COFF/pdb-tpi-hash-size.test
@@ -0,0 +1,10 @@
+# RUN: yaml2obj < %p/Inputs/pdb1.yaml > %t1.obj
+# RUN: yaml2obj < %p/Inputs/pdb2.yaml > %t2.obj
+# RUN: rm -f %t.dll %t.pdb
+# RUN: lld-link /debug /pdb:%t.pdb /dll /out:%t.dll \
+# RUN:   /entry:main /nodefaultlib %t1.obj %t2.obj
+
+# RUN: llvm-pdbutil dump -types -type-extras %t.pdb | FileCheck %s
+
+CHECK:      Hash Key Size: 4
+CHECK-NEXT: Num Hash Buckets: 262143

diff --git a/lld/test/COFF/pdb.test b/lld/test/COFF/pdb.test
index 5788b51..745000c 100644 (file)
--- a/lld/test/COFF/pdb.test
+++ b/lld/test/COFF/pdb.test
@@ -142,40 +142,40 @@ RAW-NEXT:              pdb file ni: 1 `{{.*pdb.test.tmp.pdb}}`, src file ni: 0 `
 RAW:                          Types (TPI Stream)
 RAW-NEXT: ============================================================
 RAW-NEXT:   Showing 5 records
-RAW-NEXT:   0x1000 | LF_ARGLIST [size = 8, hash = 0xEC0]
-RAW-NEXT:   0x1001 | LF_PROCEDURE [size = 16, hash = 0x7BC]
+RAW-NEXT:   0x1000 | LF_ARGLIST [size = 8, hash = 0x32484]
+RAW-NEXT:   0x1001 | LF_PROCEDURE [size = 16, hash = 0x27EE9]
 RAW-NEXT:            return type = 0x0074 (int), # args = 0, param list = 0x1000
 RAW-NEXT:            calling conv = cdecl, options = None
-RAW-NEXT:   0x1002 | LF_POINTER [size = 12, hash = 0x884]
+RAW-NEXT:   0x1002 | LF_POINTER [size = 12, hash = 0x39732]
 RAW-NEXT:            referent = 0x1001, mode = pointer, opts = None, kind = ptr64
-RAW-NEXT:   0x1003 | LF_ARGLIST [size = 12, hash = 0x936]
+RAW-NEXT:   0x1003 | LF_ARGLIST [size = 12, hash = 0x1FC10]
 RAW-NEXT:            <no type>: ``
-RAW-NEXT:   0x1004 | LF_PROCEDURE [size = 16, hash = 0x852]
+RAW-NEXT:   0x1004 | LF_PROCEDURE [size = 16, hash = 0x1BD3]
 RAW-NEXT:            return type = 0x0074 (int), # args = 0, param list = 0x1003
 RAW-NEXT:            calling conv = cdecl, options = None
 RAW:                          Types (IPI Stream)
 RAW-NEXT: ============================================================
 RAW-NEXT:   Showing 12 records
-RAW-NEXT:   0x1000 | LF_FUNC_ID [size = 20, hash = 0x330]
+RAW-NEXT:   0x1000 | LF_FUNC_ID [size = 20, hash = 0x38E5A]
 RAW-NEXT:            name = main, type = 0x1004, parent scope = <no type>
-RAW-NEXT:   0x1001 | LF_FUNC_ID [size = 16, hash = 0x120]
+RAW-NEXT:   0x1001 | LF_FUNC_ID [size = 16, hash = 0xD08E]
 RAW-NEXT:            name = foo, type = 0x1001, parent scope = <no type>
-RAW-NEXT:   0x1002 | LF_STRING_ID [size = 16, hash = 0x757] ID: <no type>, String: D:\b
-RAW-NEXT:   0x1003 | LF_STRING_ID [size = 36, hash = 0xC3A] ID: <no type>, String: C:\vs14\VC\BIN\amd64\cl.exe
-RAW-NEXT:   0x1004 | LF_STRING_ID [size = 260, hash = 0x433] ID: <no type>, String: -Z7 -c -MT -IC:\vs14\VC\INCLUDE -IC:\vs14\VC\ATLMFC\INCLUDE -I"C:\Program Files (x86)\Windows Kits\10\include\10.0.10150.0\ucrt" -I"C:\Program Files (x86)\Windows Kits\NETFXSDK\4.6\include\um" -I"C:\Program Files (x86)\Windows Kits\8.1\include\shared"
-RAW-NEXT:   0x1005 | LF_SUBSTR_LIST [size = 12, hash = 0x759]
+RAW-NEXT:   0x1002 | LF_STRING_ID [size = 16, hash = 0x3EBD9] ID: <no type>, String: D:\b
+RAW-NEXT:   0x1003 | LF_STRING_ID [size = 36, hash = 0xD327] ID: <no type>, String: C:\vs14\VC\BIN\amd64\cl.exe
+RAW-NEXT:   0x1004 | LF_STRING_ID [size = 260, hash = 0x2FA6A]  ID: <no type>, String: -Z7 -c -MT -IC:\vs14\VC\INCLUDE -IC:\vs14\VC\ATLMFC\INCLUDE -I"C:\Program Files (x86)\Windows Kits\10\include\10.0.10150.0\ucrt" -I"C:\Program Files (x86)\Windows Kits\NETFXSDK\4.6\include\um" -I"C:\Program Files (x86)\Windows Kits\8.1\include\shared"
+RAW-NEXT:   0x1005 | LF_SUBSTR_LIST [size = 12, hash = 0x6053]
 RAW-NEXT:            0x1004: `-Z7 -c -MT -IC:\vs14\VC\INCLUDE -IC:\vs14\VC\ATLMFC\INCLUDE -I"C:\Program Files (x86)\Windows Kits\10\include\10.0.10150.0\ucrt" -I"C:\Program Files (x86)\Windows Kits\NETFXSDK\4.6\include\um" -I"C:\Program Files (x86)\Windows Kits\8.1\include\shared"`
-RAW-NEXT:   0x1006 | LF_STRING_ID [size = 132, hash = 0xF57] ID: 0x1005, String:  -I"C:\Program Files (x86)\Windows Kits\8.1\include\um" -I"C:\Program Files (x86)\Windows Kits\8.1\include\winrt" -TC -X
-RAW-NEXT:   0x1007 | LF_STRING_ID [size = 24, hash = 0x2D1] ID: <no type>, String: ret42-main.c
-RAW-NEXT:   0x1008 | LF_STRING_ID [size = 24, hash = 0xB8B] ID: <no type>, String: D:\b\vc140.pdb
-RAW-NEXT:   0x1009 | LF_BUILDINFO [size = 28, hash = 0xA8C]
+RAW-NEXT:   0x1006 | LF_STRING_ID [size = 132, hash = 0xCAC7] ID: 0x1005, String:  -I"C:\Program Files (x86)\Windows Kits\8.1\include\um" -I"C:\Program Files (x86)\Windows Kits\8.1\include\winrt" -TC -X
+RAW-NEXT:   0x1007 | LF_STRING_ID [size = 24, hash = 0x21783] ID: <no type>, String: ret42-main.c
+RAW-NEXT:   0x1008 | LF_STRING_ID [size = 24, hash = 0x1DB87] ID: <no type>, String: D:\b\vc140.pdb
+RAW-NEXT:   0x1009 | LF_BUILDINFO [size = 28, hash = 0x5E91]
 RAW-NEXT:            0x1002: `D:\b`
 RAW-NEXT:            0x1003: `C:\vs14\VC\BIN\amd64\cl.exe`
 RAW-NEXT:            0x1007: `ret42-main.c`
 RAW-NEXT:            0x1008: `D:\b\vc140.pdb`
 RAW-NEXT:            0x1006: ` -I"C:\Program Files (x86)\Windows Kits\8.1\include\um" -I"C:\Program Files (x86)\Windows Kits\8.1\include\winrt" -TC -X`
-RAW-NEXT:   0x100A | LF_STRING_ID [size = 20, hash = 0x39C] ID: <no type>, String: ret42-sub.c
-RAW-NEXT:   0x100B | LF_BUILDINFO [size = 28, hash = 0xAD7]
+RAW-NEXT:   0x100A | LF_STRING_ID [size = 20, hash = 0x7C68] ID: <no type>, String: ret42-sub.c
+RAW-NEXT:   0x100B | LF_BUILDINFO [size = 28, hash = 0x254D2]
 RAW-NEXT:            0x1002: `D:\b`
 RAW-NEXT:            0x1003: `C:\vs14\VC\BIN\amd64\cl.exe`
 RAW-NEXT:            0x100A: `ret42-sub.c`

diff --git a/llvm/lib/DebugInfo/PDB/Native/TpiStreamBuilder.cpp b/llvm/lib/DebugInfo/PDB/Native/TpiStreamBuilder.cpp
index 36f02e5..f2a5dcb 100644 (file)
--- a/llvm/lib/DebugInfo/PDB/Native/TpiStreamBuilder.cpp
+++ b/llvm/lib/DebugInfo/PDB/Native/TpiStreamBuilder.cpp
@@ -76,7 +76,7 @@ Error TpiStreamBuilder::finalize() {
   H->HashStreamIndex = HashStreamIndex;
   H->HashAuxStreamIndex = kInvalidStreamIndex;
   H->HashKeySize = sizeof(ulittle32_t);
-  H->NumHashBuckets = MinTpiHashBuckets;
+  H->NumHashBuckets = MaxTpiHashBuckets - 1;
 
   // Recall that hash values go into a completely different stream identified by
   // the `HashStreamIndex` field of the `TpiStreamHeader`.  Therefore, the data
@@ -129,7 +129,7 @@ Error TpiStreamBuilder::finalizeMsfLayout() {
     ulittle32_t *H = Allocator.Allocate<ulittle32_t>(TypeHashes.size());
     MutableArrayRef<ulittle32_t> HashBuffer(H, TypeHashes.size());
     for (uint32_t I = 0; I < TypeHashes.size(); ++I) {
-      HashBuffer[I] = TypeHashes[I] % MinTpiHashBuckets;
+      HashBuffer[I] = TypeHashes[I] % (MaxTpiHashBuckets - 1);
     }
     ArrayRef<uint8_t> Bytes(
         reinterpret_cast<const uint8_t *>(HashBuffer.data()),

diff --git a/llvm/tools/llvm-pdbutil/DumpOutputStyle.cpp b/llvm/tools/llvm-pdbutil/DumpOutputStyle.cpp
index 89b0043..2c3a7b5 100644 (file)
--- a/llvm/tools/llvm-pdbutil/DumpOutputStyle.cpp
+++ b/llvm/tools/llvm-pdbutil/DumpOutputStyle.cpp
@@ -1412,6 +1412,21 @@ Error DumpOutputStyle::dumpTpiStream(uint32_t StreamIdx) {
 
   if (DumpExtras) {
     P.NewLine();
+    support::ulittle32_t Version;
+
+    support::ulittle16_t HashStreamIndex;
+    support::ulittle16_t HashAuxStreamIndex;
+    support::ulittle32_t HashKeySize;
+    support::ulittle32_t NumHashBuckets;
+
+    P.formatLine("Header Version: {0}",
+                 static_cast<uint32_t>(Stream.getTpiVersion()));
+    P.formatLine("Hash Stream Index: {0}", Stream.getTypeHashStreamIndex());
+    P.formatLine("Aux Hash Stream Index: {0}",
+                 Stream.getTypeHashStreamAuxIndex());
+    P.formatLine("Hash Key Size: {0}", Stream.getHashKeySize());
+    P.formatLine("Num Hash Buckets: {0}", Stream.getNumHashBuckets());
+
     auto IndexOffsets = Stream.getTypeIndexOffsets();
     P.formatLine("Type Index Offsets:");
     for (const auto &IO : IndexOffsets) {