[ThinLTO] Serialize WithGlobalValueDeadStripping index flag for distributed backends

[tejohnson]

Summary

A recent fix to drop dead symbols (r323633) did not work for ThinLTO
distributed backends because we lose the WithGlobalValueDeadStripping
set on the index during the thin link. This patch adds a new flags
record to the bitcode format for the index, and serializes this flag
for the combined index (it would always be 0 for the per-module index
generated by the compile step, so no need to serialize the new flags
record there until/unless we add another flag that applies to the
per-module indexes).

Generally this flag should always be set for the distributed backends,
which are necessarily performed after the thin link. However, if we were
to simply set this flag on the index applied to the distributed backends
(invoked via clang), we would lose the ability to disable dead stripping
via -compute-dead=false for debugging purposes.

[grimar]

Patch looks good and correct to me (with minor comment/suggestion).
I am newbie in LTO though, so I think somebody else should
give a final approval.

lib/Bitcode/Reader/BitcodeReader.cpp

5145 ↗

(On Diff #132404)

I would make it a bit shorter:

uint64_t Flags = Record[0];
// Scan flags (set only on the combined index).
assert(Flags <= 1 && "Unexpected bits in flag");

// 1 bit: WithGlobalValueDeadStripping flag.
if (Flags & 0x1)
  TheIndex.setWithGlobalValueDeadStripping();

[tejohnson]

Address comments

[tejohnson]

In D42799#995066, @grimar wrote:

Patch looks good and correct to me (with minor comment/suggestion).
I am newbie in LTO though, so I think somebody else should
give a final approval.

@pcc can you take a look?

[tejohnson]

ping - @pcc any objections?

[pcc]

LGTM

llvm/trunk/include/llvm/Bitcode/LLVMBitCodes.h

enum GlobalValueSummarySymtabCodes {
   // strings in strtab.
   // [n * name]
   FS_CFI_FUNCTION_DECLS = 18,
   // Per-module summary that also adds relative block frequency to callee info.
   // PERMODULE_RELBF: [valueid, flags, instcount, numrefs,
   //                   numrefs x valueid,
   //                   n x (valueid, relblockfreq)]
   FS_PERMODULE_RELBF = 19,
+  // Index-wide flags
+  FS_FLAGS = 20,
 };
 
 enum MetadataCodes {
   METADATA_STRING_OLD = 1,     // MDSTRING:      [values]
   METADATA_VALUE = 2,          // VALUE:         [type num, value num]
   METADATA_NODE = 3,           // NODE:          [n x md num]
   METADATA_NAME = 4,           // STRING:        [values]
   METADATA_DISTINCT_NODE = 5,  // DISTINCT_NODE: [n x md num]

llvm/trunk/lib/Bitcode/Reader/BitcodeReader.cpp

while (true) {
     // via the bitcode offset of the summary records (which were saved
     // in the combined index VST entries). The records also contain
     // information used for ThinLTO renaming and importing.
     Record.clear();
     auto BitCode = Stream.readRecord(Entry.ID, Record);
     switch (BitCode) {
     default: // Default behavior: ignore.
       break;
+    case bitc::FS_FLAGS: {  // [flags]
+      uint64_t Flags = Record[0];
+      // Scan flags (set only on the combined index).
+      assert(Flags <= 1 && "Unexpected bits in flag");
+
+      // 1 bit: WithGlobalValueDeadStripping flag.
+      if (Flags & 0x1)
+        TheIndex.setWithGlobalValueDeadStripping();
+      break;
+    }
     case bitc::FS_VALUE_GUID: { // [valueid, refguid]
       uint64_t ValueID = Record[0];
       GlobalValue::GUID RefGUID = Record[1];
       ValueIdToValueInfoMap[ValueID] =
           std::make_pair(TheIndex.getOrInsertValueInfo(RefGUID), RefGUID);
       break;
     }
     // FS_PERMODULE: [valueid, flags, instcount, fflags, numrefs,

llvm/trunk/lib/Bitcode/Writer/BitcodeWriter.cpp

void ModuleBitcodeWriterBase::writePerModuleGlobalValueSummary() {
   Stream.ExitBlock();
 }
 
 /// Emit the combined summary section into the combined index file.
 void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
   Stream.EnterSubblock(bitc::GLOBALVAL_SUMMARY_BLOCK_ID, 3);
   Stream.EmitRecord(bitc::FS_VERSION, ArrayRef<uint64_t>{INDEX_VERSION});
 
+  // Write the index flags. Currently we only write a single flag, the value of
+  // withGlobalValueDeadStripping, which only applies to the combined index.
+  Stream.EmitRecord(bitc::FS_FLAGS,
+                    ArrayRef<uint64_t>{Index.withGlobalValueDeadStripping()});
+
   for (const auto &GVI : valueIds()) {
     Stream.EmitRecord(bitc::FS_VALUE_GUID,
                       ArrayRef<uint64_t>{GVI.second, GVI.first});
   }
 
   // Abbrev for FS_COMBINED.
   auto Abbv = std::make_shared<BitCodeAbbrev>();
   Abbv->Add(BitCodeAbbrevOp(bitc::FS_COMBINED));

llvm/trunk/test/Bitcode/thinlto-alias.ll

 ; CHECK-NEXT:    <PERMODULE {{.*}} op5=1/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'mainanalias{{.*}}'
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
+; COMBINED-NEXT:    <FLAGS
 ; See if the call to analias is registered, using the expected value id.
 ; COMBINED-NEXT:    <VALUE_GUID op0=[[ALIASID:[0-9]+]] op1=-5751648690987223394/>
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID op0=[[ALIASEEID:[0-9]+]] op1=-1039159065113703048/>
 ; COMBINED-NEXT:    <COMBINED {{.*}} op6=[[ALIASID]]/>
 ; COMBINED-NEXT:    <COMBINED {{.*}}
 ; COMBINED-NEXT:    <COMBINED_ALIAS  {{.*}} op3=[[ALIASEEID]]
 ; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK

llvm/trunk/test/Bitcode/thinlto-deadstrip-flag.ll

+; REQUIRES: x86-registered-target
+; RUN: opt -module-summary %s -o %t.o
+
+; Ensure dead stripping performed flag is set on distributed index
+; RUN: llvm-lto2 run %t.o -o %t.out -thinlto-distributed-indexes \
+; RUN:    -r %t.o,glob,plx
+; RUN: llvm-bcanalyzer -dump %t.o.thinlto.bc | FileCheck %s --check-prefix=WITHDEAD
+; WITHDEAD: <FLAGS op0=1/>
+
+; Ensure dead stripping performed flag is not set on distributed index
+; when option used to disable dead stripping computation.
+; RUN: llvm-lto2 run %t.o -o %t.out -thinlto-distributed-indexes \
+; RUN:    -r %t.o,glob,plx -compute-dead=false
+; RUN: llvm-bcanalyzer -dump %t.o.thinlto.bc | FileCheck %s --check-prefix=NODEAD
+; NODEAD: <FLAGS op0=0/>
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@glob = global i32 0

llvm/trunk/test/Bitcode/thinlto-function-summary-callgraph-pgo.ll

 ; See if the call to func is registered, using the expected hotness type.
 ; CHECK-NEXT:    <PERMODULE_PROFILE {{.*}} op5=1 op6=2/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'mainfunc{{.*}}'
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
+; COMBINED-NEXT:    <FLAGS
 ; COMBINED-NEXT:    <VALUE_GUID op0=[[FUNCID:[0-9]+]] op1=7289175272376759421/>
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <COMBINED
 ; See if the call to func is registered, using the expected hotness type.
 ; op6=2 which is hotnessType::None.
 ; COMBINED-NEXT:    <COMBINED_PROFILE {{.*}} op6=[[FUNCID]] op7=2/>
 ; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 

llvm/trunk/test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll

 ; CHECK-NEXT:    <PERMODULE_PROFILE {{.*}} op5=1 op6=3 op7=5 op8=1 op9=2 op10=3 op11=4 op12=1 op13=6 op14=2 op15=3 op16=3 op17=7 op18=2 op19=8 op20=2 op21=25 op22=4/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'hot_functionhot1hot2hot3hot4coldnone1none2none3{{.*}}'
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
+; COMBINED-NEXT:    <FLAGS
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID

llvm/trunk/test/Bitcode/thinlto-function-summary-callgraph-sample-profile-summary.ll

 ; CHECK-NEXT:    <PERMODULE_PROFILE {{.*}} op5=7 op6=0 op7=1 op8=3 op9=4 op10=1 op11=8 op12=0 op13=2 op14=3 op15=5 op16=1 op17=9 op18=0 op19=3 op20=3 op21=6 op22=1 op23=26 op24=4/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'hot_functionhot1hot2hot3cold1cold2cold3none1none2none3{{.*}}'
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
+; COMBINED-NEXT:    <FLAGS
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID

llvm/trunk/test/Bitcode/thinlto-function-summary-callgraph.ll

 ; CHECK-NEXT:    <PERMODULE {{.*}} op4=1
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'undefinedglobmainfunc{{.*}}'
 
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
+; COMBINED-NEXT:    <FLAGS
 ; Only 2 VALUE_GUID since reference to undefinedglob should not be included in
 ; combined index.
 ; COMBINED-NEXT:    <VALUE_GUID op0=[[FUNCID:[0-9]+]] op1=7289175272376759421/>
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <COMBINED
 ; See if the call to func is registered.
 ; COMBINED-NEXT:    <COMBINED {{.*}} op6=[[FUNCID]]/>
 ; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>

llvm/trunk/test/Bitcode/thinlto-function-summary-originalnames.ll

 ; Test to check the callgraph in summary
 ; RUN: opt -module-summary %s -o %t.o
 ; RUN: llvm-lto -thinlto-action=thinlink -o %t.index.bc %t.o
 ; RUN: llvm-bcanalyzer -dump %t.index.bc | FileCheck %s --check-prefix=COMBINED
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
+; COMBINED-NEXT:    <FLAGS
 ; COMBINED-NEXT:    <VALUE_GUID {{.*}} op1=4947176790635855146/>
 ; COMBINED-NEXT:    <VALUE_GUID {{.*}} op1=-6591587165810580810/>
 ; COMBINED-NEXT:    <VALUE_GUID {{.*}} op1=-4377693495213223786/>
 ; COMBINED-DAG:    <COMBINED
 ; COMBINED-DAG:    <COMBINED_ORIGINAL_NAME op0=6699318081062747564/>
 ; COMBINED-DAG:    <COMBINED_GLOBALVAR_INIT_REFS
 ; COMBINED-DAG:    <COMBINED_ORIGINAL_NAME op0=-2012135647395072713/>
 ; COMBINED-DAG:    <COMBINED_ALIAS

llvm/trunk/test/tools/gold/X86/thinlto.ll

 ; The backend index for this module contains summaries from itself and
 ; Inputs/thinlto.ll, as it imports from the latter.
 ; BACKEND1: <MODULE_STRTAB_BLOCK
 ; BACKEND1-NEXT: <ENTRY {{.*}} record string = '{{.*}}/test/tools/gold/X86/Output/thinlto.ll.tmp{{.*}}.o'
 ; BACKEND1-NEXT: <ENTRY {{.*}} record string = '{{.*}}/test/tools/gold/X86/Output/thinlto.ll.tmp{{.*}}.o'
 ; BACKEND1-NEXT: </MODULE_STRTAB_BLOCK
 ; BACKEND1-NEXT: <GLOBALVAL_SUMMARY_BLOCK
 ; BACKEND1-NEXT: <VERSION
+; BACKEND1-NEXT: <FLAGS
 ; BACKEND1-NEXT: <VALUE_GUID op0={{1|2}} op1={{-3706093650706652785|-5300342847281564238}}
 ; BACKEND1-NEXT: <VALUE_GUID op0={{1|2}} op1={{-3706093650706652785|-5300342847281564238}}
 ; BACKEND1-NEXT: <COMBINED
 ; BACKEND1-NEXT: <COMBINED
 ; BACKEND1-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 ; The backend index for Input/thinlto.ll contains summaries from itself only,
 ; as it does not import anything.
 ; BACKEND2: <MODULE_STRTAB_BLOCK
 ; BACKEND2-NEXT: <ENTRY {{.*}} record string = '{{.*}}/test/tools/gold/X86/Output/thinlto.ll.tmp2.o'
 ; BACKEND2-NEXT: </MODULE_STRTAB_BLOCK
 ; BACKEND2-NEXT: <GLOBALVAL_SUMMARY_BLOCK
 ; BACKEND2-NEXT: <VERSION
+; BACKEND2-NEXT: <FLAGS
 ; BACKEND2-NEXT: <VALUE_GUID op0=1 op1=-5300342847281564238
 ; BACKEND2-NEXT: <COMBINED
 ; BACKEND2-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 ; COMBINED: <MODULE_STRTAB_BLOCK
 ; COMBINED-NEXT: <ENTRY {{.*}} record string = '{{.*}}/test/tools/gold/X86/Output/thinlto.ll.tmp{{.*}}.o'
 ; COMBINED-NEXT: <ENTRY {{.*}} record string = '{{.*}}/test/tools/gold/X86/Output/thinlto.ll.tmp{{.*}}.o'
 ; COMBINED-NEXT: </MODULE_STRTAB_BLOCK
 ; COMBINED-NEXT: <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT: <VERSION
+; COMBINED-NEXT: <FLAGS
 ; COMBINED-NEXT: <VALUE_GUID op0={{1|2}} op1={{-3706093650706652785|-5300342847281564238}}
 ; COMBINED-NEXT: <VALUE_GUID op0={{1|2}} op1={{-3706093650706652785|-5300342847281564238}}
 ; COMBINED-NEXT: <COMBINED
 ; COMBINED-NEXT: <COMBINED
 ; COMBINED-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 declare void @g(...)
 
 define void @f() {
 entry:
   call void (...) @g()
   ret void
 }

llvm/trunk/test/tools/llvm-lto/thinlto.ll

 ; Test combined function index generation for ThinLTO via llvm-lto.
 ; RUN: opt -module-summary %s -o %t.o
 ; RUN: opt -module-summary %p/Inputs/thinlto.ll -o %t2.o
 ; RUN: llvm-lto -thinlto -o %t3 %t.o %t2.o
 ; RUN: llvm-bcanalyzer -dump %t3.thinlto.bc | FileCheck %s --check-prefix=COMBINED
 ; RUN: not test -e %t3
 
 ; COMBINED: <MODULE_STRTAB_BLOCK
 ; COMBINED-NEXT: <ENTRY {{.*}} record string = '{{.*}}thinlto.ll.tmp{{.*}}.o'
 ; COMBINED-NEXT: <ENTRY {{.*}} record string = '{{.*}}thinlto.ll.tmp{{.*}}.o'
 ; COMBINED-NEXT: </MODULE_STRTAB_BLOCK
 ; COMBINED-NEXT: <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT: <VERSION
+; COMBINED-NEXT: <FLAGS
 ; COMBINED-NEXT: <VALUE_GUID op0={{1|2}} op1={{-3706093650706652785|-5300342847281564238}}
 ; COMBINED-NEXT: <VALUE_GUID op0={{1|2}} op1={{-3706093650706652785|-5300342847281564238}}
 ; COMBINED-NEXT: <COMBINED
 ; COMBINED-NEXT: <COMBINED
 ; COMBINED-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 define void @f() {
 entry:
   ret void
 }

llvm/trunk/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp

default:
       STRINGIFY_CODE(FS, PERMODULE_GLOBALVAR_INIT_REFS)
       STRINGIFY_CODE(FS, COMBINED)
       STRINGIFY_CODE(FS, COMBINED_PROFILE)
       STRINGIFY_CODE(FS, COMBINED_GLOBALVAR_INIT_REFS)
       STRINGIFY_CODE(FS, ALIAS)
       STRINGIFY_CODE(FS, COMBINED_ALIAS)
       STRINGIFY_CODE(FS, COMBINED_ORIGINAL_NAME)
       STRINGIFY_CODE(FS, VERSION)
+      STRINGIFY_CODE(FS, FLAGS)
       STRINGIFY_CODE(FS, TYPE_TESTS)
       STRINGIFY_CODE(FS, TYPE_TEST_ASSUME_VCALLS)
       STRINGIFY_CODE(FS, TYPE_CHECKED_LOAD_VCALLS)
       STRINGIFY_CODE(FS, TYPE_TEST_ASSUME_CONST_VCALL)
       STRINGIFY_CODE(FS, TYPE_CHECKED_LOAD_CONST_VCALL)
       STRINGIFY_CODE(FS, VALUE_GUID)
       STRINGIFY_CODE(FS, CFI_FUNCTION_DEFS)
       STRINGIFY_CODE(FS, CFI_FUNCTION_DECLS)