[llvm] [BOLT] Refactor undefined symbols handling. NFCI (PR #167075)

[Maksim Panchenko via llvm-commits]

https://github.com/maksfb created https://github.com/llvm/llvm-project/pull/167075

Remove internal undefined symbol tracking and instead rely on the emission state of `MCSymbol` while processing data-to-code relocations.

Note that `CleanMCState` pass resets the state of all `MCSymbol`s prior to code emission.

>From 7bba3fc97b9b2ce8352e3fcd92e51fa539b2e07e Mon Sep 17 00:00:00 2001
From: Maksim Panchenko <maks at fb.com>
Date: Fri, 7 Nov 2025 16:31:59 -0800
Subject: [PATCH] [BOLT] Refactor undefined symbols handling. NFCI

Remove internal undefined symbol tracking and instead rely on the
emission state of MCSymbol while processing data-to-code relocations.

Note that CleanMCState pass resets the state of all MCSymbols prior to
code emission.
---
 bolt/include/bolt/Core/BinaryContext.h |  3 ---
 bolt/lib/Core/BinaryFunction.cpp       | 18 ------------------
 bolt/lib/Core/BinarySection.cpp        |  6 ++++--
 3 files changed, 4 insertions(+), 23 deletions(-)

diff --git a/bolt/include/bolt/Core/BinaryContext.h b/bolt/include/bolt/Core/BinaryContext.h
index 085c0265de3ed..57d4515bf8325 100644
--- a/bolt/include/bolt/Core/BinaryContext.h
+++ b/bolt/include/bolt/Core/BinaryContext.h
@@ -354,9 +354,6 @@ class BinaryContext {
   /// Newly created segments.
   std::vector<SegmentInfo> NewSegments;
 
-  /// Symbols that are expected to be undefined in MCContext during emission.
-  std::unordered_set<MCSymbol *> UndefinedSymbols;
-
   /// [name] -> [BinaryData*] map used for global symbol resolution.
   using SymbolMapType = StringMap<BinaryData *>;
   SymbolMapType GlobalSymbols;
diff --git a/bolt/lib/Core/BinaryFunction.cpp b/bolt/lib/Core/BinaryFunction.cpp
index ddaad6eef6140..2fd1ab13008b7 100644
--- a/bolt/lib/Core/BinaryFunction.cpp
+++ b/bolt/lib/Core/BinaryFunction.cpp
@@ -1896,16 +1896,6 @@ bool BinaryFunction::scanExternalRefs() {
     }
   }
 
-  // Inform BinaryContext that this function symbols will not be defined and
-  // relocations should not be created against them.
-  if (BC.HasRelocations) {
-    for (std::pair<const uint32_t, MCSymbol *> &LI : Labels)
-      BC.UndefinedSymbols.insert(LI.second);
-    for (MCSymbol *const EndLabel : FunctionEndLabels)
-      if (EndLabel)
-        BC.UndefinedSymbols.insert(EndLabel);
-  }
-
   clearList(Relocations);
   clearList(ExternallyReferencedOffsets);
 
@@ -3234,14 +3224,6 @@ void BinaryFunction::clearDisasmState() {
   clearList(Instructions);
   clearList(IgnoredBranches);
   clearList(TakenBranches);
-
-  if (BC.HasRelocations) {
-    for (std::pair<const uint32_t, MCSymbol *> &LI : Labels)
-      BC.UndefinedSymbols.insert(LI.second);
-    for (MCSymbol *const EndLabel : FunctionEndLabels)
-      if (EndLabel)
-        BC.UndefinedSymbols.insert(EndLabel);
-  }
 }
 
 void BinaryFunction::setTrapOnEntry() {
diff --git a/bolt/lib/Core/BinarySection.cpp b/bolt/lib/Core/BinarySection.cpp
index 6f07017c26060..e803d17021f8b 100644
--- a/bolt/lib/Core/BinarySection.cpp
+++ b/bolt/lib/Core/BinarySection.cpp
@@ -112,8 +112,10 @@ void BinarySection::emitAsData(MCStreamer &Streamer,
       RI = ROE;
 
       // Skip undefined symbols.
-      auto HasUndefSym = [this](const auto &Relocation) {
-        return BC.UndefinedSymbols.count(Relocation.Symbol);
+      auto HasUndefSym = [](const auto &Relocation) {
+        return Relocation.Symbol && Relocation.Symbol->isTemporary() &&
+               Relocation.Symbol->isUndefined() &&
+               !Relocation.Symbol->isRegistered();
       };
 
       if (std::any_of(ROI, ROE, HasUndefSym))