Bitcode: Add a string table to the bitcode format.

Add a top-level STRTAB block containing a string table blob, and start storing
strings for module codes FUNCTION, GLOBALVAR, ALIAS, IFUNC and COMDAT in
the string table.

This change allows us to share names between globals and comdats as well
as between modules, and improves the efficiency of loading bitcode files by
no longer using a bit encoding for symbol names. Once we start writing the
irsymtab to the bitcode file we will also be able to share strings between
it and the module.

On my machine, link time for Chromium for Linux with ThinLTO decreases by
about 7% for no-op incremental builds or about 1% for full builds. Total
bitcode file size decreases by about 3%.

As discussed on llvm-dev:
http://lists.llvm.org/pipermail/llvm-dev/2017-April/111732.html

Differential Revision: https://reviews.llvm.org/D31838

llvm-svn: 300464

llvm/docs/BitCodeFormat.rst

@@ -550,6 +550,8 @@ LLVM IR is defined with the following blocks:
 
 * 17 --- `TYPE_BLOCK`_ --- This describes all of the types in the module.
 
+* 23 --- `STRTAB_BLOCK`_ --- The bitcode file's string table.
+
 .. _MODULE_BLOCK:
 
 MODULE_BLOCK Contents
@@ -577,7 +579,7 @@ MODULE_CODE_VERSION Record
 ``[VERSION, version#]``
 
 The ``VERSION`` record (code 1) contains a single value indicating the format
-version. Versions 0 and 1 are supported at this time. The difference between
+version. Versions 0, 1 and 2 are supported at this time. The difference between
 version 0 and 1 is in the encoding of instruction operands in
 each `FUNCTION_BLOCK`_.
 
@@ -620,6 +622,12 @@ as unsigned VBRs. However, forward references are rare, except in the
 case of phi instructions. For phi instructions, operands are encoded as
 `Signed VBRs`_ to deal with forward references.
 
+In version 2, the meaning of module records ``FUNCTION``, ``GLOBALVAR``,
+``ALIAS``, ``IFUNC`` and ``COMDAT`` change such that the first two operands
+specify an offset and size of a string in a string table (see `STRTAB_BLOCK
+Contents`_), the function name is removed from the ``FNENTRY`` record in the
+value symbol table, and the top-level ``VALUE_SYMTAB_BLOCK`` may only contain
+``FNENTRY`` records.
 
 MODULE_CODE_TRIPLE Record
 ^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -673,11 +681,14 @@ for each library name referenced.
 MODULE_CODE_GLOBALVAR Record
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-``[GLOBALVAR, pointer type, isconst, initid, linkage, alignment, section, visibility, threadlocal, unnamed_addr, externally_initialized, dllstorageclass, comdat]``
+``[GLOBALVAR, strtab offset, strtab size, pointer type, isconst, initid, linkage, alignment, section, visibility, threadlocal, unnamed_addr, externally_initialized, dllstorageclass, comdat]``
 
 The ``GLOBALVAR`` record (code 7) marks the declaration or definition of a
 global variable. The operand fields are:
 
+* *strtab offset*, *strtab size*: Specifies the name of the global variable.
+  See `STRTAB_BLOCK Contents`_.
+
 * *pointer type*: The type index of the pointer type used to point to this
   global variable
 
@@ -755,11 +766,14 @@ global variable. The operand fields are:
 MODULE_CODE_FUNCTION Record
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-``[FUNCTION, type, callingconv, isproto, linkage, paramattr, alignment, section, visibility, gc, prologuedata, dllstorageclass, comdat, prefixdata, personalityfn]``
+``[FUNCTION, strtab offset, strtab size, type, callingconv, isproto, linkage, paramattr, alignment, section, visibility, gc, prologuedata, dllstorageclass, comdat, prefixdata, personalityfn]``
 
 The ``FUNCTION`` record (code 8) marks the declaration or definition of a
 function. The operand fields are:
 
+* *strtab offset*, *strtab size*: Specifies the name of the function.
+  See `STRTAB_BLOCK Contents`_.
+
 * *type*: The type index of the function type describing this function
 
 * *callingconv*: The calling convention number:
@@ -817,11 +831,14 @@ function. The operand fields are:
 MODULE_CODE_ALIAS Record
 ^^^^^^^^^^^^^^^^^^^^^^^^
 
-``[ALIAS, alias type, aliasee val#, linkage, visibility, dllstorageclass, threadlocal, unnamed_addr]``
+``[ALIAS, strtab offset, strtab size, alias type, aliasee val#, linkage, visibility, dllstorageclass, threadlocal, unnamed_addr]``
 
 The ``ALIAS`` record (code 9) marks the definition of an alias. The operand
 fields are
 
+* *strtab offset*, *strtab size*: Specifies the name of the alias.
+  See `STRTAB_BLOCK Contents`_.
+
 * *alias type*: The type index of the alias
 
 * *aliasee val#*: The value index of the aliased value
@@ -1300,3 +1317,20 @@ METADATA_ATTACHMENT Contents
 ----------------------------
 
 The ``METADATA_ATTACHMENT`` block (id 16) ...
+
+.. _STRTAB_BLOCK:
+
+STRTAB_BLOCK Contents
+---------------------
+
+The ``STRTAB`` block (id 23) contains a single record (``STRTAB_BLOB``, id 1)
+with a single blob operand containing the bitcode file's string table.
+
+Strings in the string table are not null terminated. A record's *strtab
+offset* and *strtab size* operands specify the byte offset and size of a
+string within the string table.
+
+The string table is used by all preceding blocks in the bitcode file that are
+not succeeded by another intervening ``STRTAB`` block. Normally a bitcode
+file will have a single string table, but it may have more than one if it
+was created by binary concatenation of multiple bitcode files.

llvm/include/llvm/Bitcode/BitcodeReader.h

@@ -46,6 +46,9 @@ namespace llvm {
     ArrayRef<uint8_t> Buffer;
     StringRef ModuleIdentifier;
 
+    // The string table used to interpret this module.
+    StringRef Strtab;
+
     // The bitstream location of the IDENTIFICATION_BLOCK.
     uint64_t IdentificationBit;
 
@@ -70,6 +73,7 @@ namespace llvm {
     StringRef getBuffer() const {
       return StringRef((const char *)Buffer.begin(), Buffer.size());
     }
+    StringRef getStrtab() const { return Strtab; }
 
     StringRef getModuleIdentifier() const { return ModuleIdentifier; }
 

llvm/include/llvm/Bitcode/BitcodeWriter.h

@@ -15,6 +15,7 @@
 #define LLVM_BITCODE_BITCODEWRITER_H
 
 #include "llvm/IR/ModuleSummaryIndex.h"
+#include "llvm/MC/StringTableBuilder.h"
 #include <string>
 
 namespace llvm {
@@ -26,12 +27,25 @@ namespace llvm {
     SmallVectorImpl<char> &Buffer;
     std::unique_ptr<BitstreamWriter> Stream;
 
+    StringTableBuilder StrtabBuilder{StringTableBuilder::RAW};
+    bool WroteStrtab = false;
+
+    void writeBlob(unsigned Block, unsigned Record, StringRef Blob);
+
    public:
     /// Create a BitcodeWriter that writes to Buffer.
     BitcodeWriter(SmallVectorImpl<char> &Buffer);
 
     ~BitcodeWriter();
 
+    /// Write the bitcode file's string table. This must be called exactly once
+    /// after all modules have been written.
+    void writeStrtab();
+
+    /// Copy the string table for another module into this bitcode file. This
+    /// should be called after copying the module itself into the bitcode file.
+    void copyStrtab(StringRef Strtab);
+
     /// Write the specified module to the buffer specified at construction time.
     ///
     /// If \c ShouldPreserveUseListOrder, encode the use-list order for each \a

llvm/include/llvm/Bitcode/LLVMBitCodes.h

@@ -22,7 +22,7 @@
 
 namespace llvm {
 namespace bitc {
-// The only top-level block type defined is for a module.
+// The only top-level block types are MODULE, IDENTIFICATION and STRTAB.
 enum BlockIDs {
   // Blocks
   MODULE_BLOCK_ID = FIRST_APPLICATION_BLOCKID,
@@ -52,7 +52,9 @@ enum BlockIDs {
 
   OPERAND_BUNDLE_TAGS_BLOCK_ID,
 
-  METADATA_KIND_BLOCK_ID
+  METADATA_KIND_BLOCK_ID,
+
+  STRTAB_BLOCK_ID,
 };
 
 /// Identification block contains a string that describes the producer details,
@@ -232,6 +234,10 @@ enum GlobalValueSummarySymtabCodes {
   // llvm.type.checked.load intrinsic with all constant integer arguments.
   // [typeid, offset, n x arg]
   FS_TYPE_CHECKED_LOAD_CONST_VCALL = 15,
+  // Assigns a GUID to a value ID. This normally appears only in combined
+  // summaries, but it can also appear in per-module summaries for PGO data.
+  // [valueid, guid]
+  FS_VALUE_GUID = 16,
 };
 
 enum MetadataCodes {
@@ -550,6 +556,10 @@ enum ComdatSelectionKindCodes {
   COMDAT_SELECTION_KIND_SAME_SIZE = 5,
 };
 
+enum StrtabCodes {
+  STRTAB_BLOB = 1,
+};
+
 } // End bitc namespace
 } // End llvm namespace