[llvm] Reduce llvm-gsymutil memory usage (lambda-free, and less locking) (PR #97640)

[Kevin Frei via llvm-commits]

https://github.com/kevinfrei updated https://github.com/llvm/llvm-project/pull/97640

>From b6a8e2fb8865c356db58eff165ca35b58c4b6098 Mon Sep 17 00:00:00 2001
From: Kevin Frei <kevinfrei at users.noreply.github.com>
Date: Tue, 2 Jul 2024 10:14:26 -0700
Subject: [PATCH] Reduce llvm-gsymutil memory usage (#91023)

llvm-gsymutil eats a lot of RAM. On some large binaries, it causes OOM's on smaller hardware, consuming well over 64GB of RAM.
This change frees line tables once we're done with them, and frees DWARFUnits's DIE's when we finish processing each DU, though
they may get reconstituted if there are references from other DU's during processing. Once the conversion is complete, all DIE's
are freed. The reduction in peak memory usage from these changes showed between 7-12% in my tests.

There is a recursive mutex necessary to prevent accidental freeing of the DIE arrays while they're being extraced. It needs
to be recursive as there's a recursive path through the final section of the code (determineStringOffsetsTableContribution) that
may result in a call to this function.
---
 llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h |  9 ++++++---
 llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp        | 10 ++++++++++
 llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp  | 15 ++++++++++++++-
 3 files changed, 30 insertions(+), 4 deletions(-)

diff --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
index 80c27aea89312..be3c4fe7c4b19 100644
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
@@ -27,6 +27,7 @@
 #include <cstdint>
 #include <map>
 #include <memory>
+#include <mutex>
 #include <set>
 #include <utility>
 #include <vector>
@@ -257,6 +258,8 @@ class DWARFUnit {
 
   std::shared_ptr<DWARFUnit> DWO;
 
+  mutable std::recursive_mutex FreeDIEsMutex;
+
 protected:
   friend dwarf_linker::parallel::CompileUnit;
 
@@ -566,6 +569,9 @@ class DWARFUnit {
 
   Error tryExtractDIEsIfNeeded(bool CUDieOnly);
 
+  /// clearDIEs - Clear parsed DIEs to keep memory usage low.
+  void clearDIEs(bool KeepCUDie);
+
 private:
   /// Size in bytes of the .debug_info data associated with this compile unit.
   size_t getDebugInfoSize() const {
@@ -581,9 +587,6 @@ class DWARFUnit {
   void extractDIEsToVector(bool AppendCUDie, bool AppendNonCUDIEs,
                            std::vector<DWARFDebugInfoEntry> &DIEs) const;
 
-  /// clearDIEs - Clear parsed DIEs to keep memory usage low.
-  void clearDIEs(bool KeepCUDie);
-
   /// parseDWO - Parses .dwo file for current compile unit. Returns true if
   /// it was actually constructed.
   /// The \p AlternativeLocation specifies an alternative location to get
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp b/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
index bdd04b00f557b..0449d4a7b078a 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
@@ -496,6 +496,12 @@ void DWARFUnit::extractDIEsIfNeeded(bool CUDieOnly) {
 }
 
 Error DWARFUnit::tryExtractDIEsIfNeeded(bool CUDieOnly) {
+  // Acquire the FreeDIEsMutex recursive lock to prevent a different thread
+  // from freeing the DIE arrays while they're being extracted. It needs to
+  // be recursive, as there is a potentially recursive path through
+  // determineStringOffsetsTableContribution.
+  std::lock_guard<std::recursive_mutex> FreeLock(FreeDIEsMutex);
+
   if ((CUDieOnly && !DieArray.empty()) ||
       DieArray.size() > 1)
     return Error::success(); // Already parsed.
@@ -653,6 +659,10 @@ bool DWARFUnit::parseDWO(StringRef DWOAlternativeLocation) {
 }
 
 void DWARFUnit::clearDIEs(bool KeepCUDie) {
+  // We need to acquire the FreeDIEsMutex lock in write-mode, because we are
+  // going to free the DIEs, when other threads might be trying to create them.
+  std::lock_guard<std::recursive_mutex> FreeLock(FreeDIEsMutex);
+
   // Do not use resize() + shrink_to_fit() to free memory occupied by dies.
   // shrink_to_fit() is a *non-binding* request to reduce capacity() to size().
   // It depends on the implementation whether the request is fulfilled.
diff --git a/llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp b/llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp
index 601686fdd3dd5..e1b30648b6a77 100644
--- a/llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp
+++ b/llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp
@@ -587,6 +587,11 @@ Error DwarfTransformer::convert(uint32_t NumThreads, OutputAggregator &Out) {
       DWARFDie Die = getDie(*CU);
       CUInfo CUI(DICtx, dyn_cast<DWARFCompileUnit>(CU.get()));
       handleDie(Out, CUI, Die);
+      // Release the line table, once we're done.
+      DICtx.clearLineTableForUnit(CU.get());
+      // Free any DIEs that were allocated by the DWARF parser.
+      // If/when they're needed by other CU's, they'll be recreated.
+      CU->clearDIEs(/*KeepCUDie=*/false);
     }
   } else {
     // LLVM Dwarf parser is not thread-safe and we need to parse all DWARF up
@@ -612,11 +617,16 @@ Error DwarfTransformer::convert(uint32_t NumThreads, OutputAggregator &Out) {
       DWARFDie Die = getDie(*CU);
       if (Die) {
         CUInfo CUI(DICtx, dyn_cast<DWARFCompileUnit>(CU.get()));
-        pool.async([this, CUI, &LogMutex, &Out, Die]() mutable {
+        pool.async([this, CUI, &CU, &LogMutex, &Out, Die]() mutable {
           std::string storage;
           raw_string_ostream StrStream(storage);
           OutputAggregator ThreadOut(Out.GetOS() ? &StrStream : nullptr);
           handleDie(ThreadOut, CUI, Die);
+          // Release the line table once we're done.
+          DICtx.clearLineTableForUnit(CU.get());
+          // Free any DIEs that were allocated by the DWARF parser.
+          // If/when they're needed by other CU's, they'll be recreated.
+          CU->clearDIEs(/*KeepCUDie=*/false);
           // Print ThreadLogStorage lines into an actual stream under a lock
           std::lock_guard<std::mutex> guard(LogMutex);
           if (Out.GetOS()) {
@@ -629,6 +639,9 @@ Error DwarfTransformer::convert(uint32_t NumThreads, OutputAggregator &Out) {
     }
     pool.wait();
   }
+  // Now get rid of all the DIEs that may have been recreated
+  for (const auto &CU : DICtx.compile_units())
+    CU->clearDIEs(/*KeepCUDie=*/false);
   size_t FunctionsAddedCount = Gsym.getNumFunctionInfos() - NumBefore;
   Out << "Loaded " << FunctionsAddedCount << " functions from DWARF.\n";
   return Error::success();