[lld] A Unified LTO Bitcode Frontend

The unified LTO pipeline creates a single LTO bitcode structure that can
be used by Thin or Full LTO. This means that the LTO mode can be chosen
at link time and that all LTO bitcode produced by the pipeline is
compatible, from an optimization perspective. This makes the behavior of
LTO a bit more predictable by normalizing the set of LTO features
supported by each LTO bitcode file.

Example usage:

clang -flto -funified-lto -fuse-ld=lld foo.c

clang -flto=thin -funified-lto -fuse-ld=lld foo.c

clang -c -flto -funified-lto foo.c  # -flto={full,thin} are identical in
terms of compilation actions
clang -flto=thin -fuse-ld=lld foo.o # pass --lto=thin to ld.lld

clang -c -flto -funified-lto foo.c clang -flto -fuse-ld=lld foo.o

The RFC discussing the details and rational for this change is here:
https://discourse.llvm.org/t/rfc-a-unified-lto-bitcode-frontend/61774

Differential Revision: https://reviews.llvm.org/D123805

lld/ELF/Config.h

@@ -96,6 +96,9 @@ enum class SeparateSegmentKind { None, Code, Loadable };
 // For -z *stack
 enum class GnuStackKind { None, Exec, NoExec };
 
+// For --lto=
+enum LtoKind : uint8_t {UnifiedThin, UnifiedRegular, Default};
+
 struct SymbolVersion {
   llvm::StringRef name;
   bool isExternCpp;
@@ -415,6 +418,9 @@ struct Config {
   // not supported on Android 11 & 12.
   bool androidMemtagStack;
 
+  // When using a unified pre-link LTO pipeline, specify the backend LTO mode.
+  LtoKind ltoKind = LtoKind::Default;
+
   unsigned threadCount;
 
   // If an input file equals a key, remap it to the value.

lld/ELF/Driver.cpp

@@ -1489,6 +1489,19 @@ static void readConfigs(opt::InputArgList &args) {
     config->mllvmOpts.emplace_back(arg->getValue());
   }
 
+  config->ltoKind = LtoKind::Default;
+  if (auto *arg = args.getLastArg(OPT_lto)) {
+    StringRef s = arg->getValue();
+    if (s == "thin")
+      config->ltoKind = LtoKind::UnifiedThin;
+    else if (s == "full")
+      config->ltoKind = LtoKind::UnifiedRegular;
+    else if (s == "default")
+      config->ltoKind = LtoKind::Default;
+    else
+      error("unknown LTO mode: " + s);
+  }
+
   // --threads= takes a positive integer and provides the default value for
   // --thinlto-jobs=. If unspecified, cap the number of threads since
   // overhead outweighs optimization for used parallel algorithms for the

lld/ELF/LTO.cpp

@@ -206,8 +206,13 @@ BitcodeCompiler::BitcodeCompiler() {
         config->thinLTOEmitImportsFiles);
   }
 
-  ltoObj = std::make_unique<lto::LTO>(createConfig(), backend,
-                                       config->ltoPartitions);
+  constexpr llvm::lto::LTO::LTOKind ltoModes[3] =
+    {llvm::lto::LTO::LTOKind::LTOK_UnifiedThin,
+     llvm::lto::LTO::LTOKind::LTOK_UnifiedRegular,
+     llvm::lto::LTO::LTOKind::LTOK_Default};
+  ltoObj = std::make_unique<lto::LTO>(
+      createConfig(), backend, config->ltoPartitions,
+      ltoModes[config->ltoKind]);
 
   // Initialize usedStartStop.
   if (ctx.bitcodeFiles.empty())

lld/ELF/Options.td

@@ -577,6 +577,9 @@ def: JoinedOrSeparate<["-"], "u">, Alias<undefined>, HelpText<"Alias for --undef
 def: Flag<["-"], "V">, Alias<v>, HelpText<"Alias for -v">;
 
 // LTO-related options.
+
+def lto: JJ<"lto=">, HelpText<"Set LTO backend">,
+                 MetaVarName<"[full,thin]">;
 def lto_aa_pipeline: JJ<"lto-aa-pipeline=">,
   HelpText<"AA pipeline to run during LTO. Used in conjunction with -lto-newpm-passes">;
 def lto_debug_pass_manager: FF<"lto-debug-pass-manager">,

lld/test/ELF/lto/unified-lto.ll

@@ -0,0 +1,35 @@
+; REQUIRES: x86
+; RUN: opt -thinlto-bc -thinlto-split-lto-unit -unified-lto %s -o %t0.o
+; RUN: opt -thinlto-bc -thinlto-split-lto-unit %s -o %t1.o
+; RUN: ld.lld --lto=full %t0.o -o %t0
+; RUN: llvm-readelf -s %t0 | FileCheck %s --check-prefix=FULL
+; RUN: ld.lld --lto=thin %t0.o -o %t0
+; RUN: llvm-readelf -s %t0 | FileCheck %s --check-prefix=THIN
+; RUN: ld.lld --lto=default %t0.o -o %t0
+; RUN: llvm-readelf -s %t0 | FileCheck %s --check-prefix=THIN
+; RUN: ld.lld --lto=default %t1.o -o %t1
+; RUN: llvm-readelf -s %t1 | FileCheck %s --check-prefix=THIN
+; RUN: ld.lld %t0.o -o %t0 2>&1 | count 0
+; RUN: llvm-readelf -s %t0 | FileCheck %s --check-prefix=THIN
+; RUN: not ld.lld --lto=unknown %t1.o -o /dev/null 2>&1 | \
+; RUN:   FileCheck --implicit-check-not=error: --check-prefix=ERR %s
+; ERR: error: unknown LTO mode: unknown
+
+; FULL:      Symbol table '.symtab' contains 3 entries:
+; FULL-NEXT: Num:    Value          Size Type    Bind   Vis       Ndx Name
+; FULL-NEXT: 0: 0000000000000000     0 NOTYPE  LOCAL  DEFAULT   UND
+; FULL-NEXT: 1: 0000000000000000     0 FILE    LOCAL  DEFAULT   ABS ld-temp.o
+; FULL-NEXT: 2: 0000000000201120     1 FUNC    GLOBAL DEFAULT     1 _start
+
+; THIN:      Symbol table '.symtab' contains 3 entries:
+; THIN-NEXT: Num:    Value          Size Type    Bind   Vis       Ndx Name
+; THIN-NEXT: 0: 0000000000000000     0 NOTYPE  LOCAL  DEFAULT   UND
+; THIN-NEXT: 1: 0000000000000000     0 FILE    LOCAL  DEFAULT   ABS unified-lto.ll
+; THIN-NEXT: 2: 0000000000201120     1 FUNC    GLOBAL DEFAULT     1 _start
+
+target triple = "x86_64-unknown-linux-gnu"
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+
+define void @_start() {
+  ret void
+}