Restore "[MemProf] Refactor memory profile matching into MemProfiler (NFC)"

This restores commit 29252fd, reverted
in 3498cf5 because it was thought to
cause a bot failure, which ended up being unrelated to this patch set.

Differential Revision: https://reviews.llvm.org/D154872

Author: teresajohnson

llvm/include/llvm/Transforms/Instrumentation/MemProfiler.h

@@ -43,6 +43,13 @@ class ModuleMemProfilerPass : public PassInfoMixin<ModuleMemProfilerPass> {
   static bool isRequired() { return true; }
 };
 
+// TODO: Remove this declaration and make readMemprof static once the matching
+// is moved into its own pass.
+class IndexedInstrProfReader;
+class TargetLibraryInfo;
+void readMemprof(Module &M, Function &F, IndexedInstrProfReader *MemProfReader,
+                 const TargetLibraryInfo &TLI);
+
 } // namespace llvm
 
 #endif

llvm/lib/Transforms/Instrumentation/MemProfiler.cpp

@@ -18,9 +18,12 @@
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/Analysis/MemoryBuiltins.h"
+#include "llvm/Analysis/MemoryProfileInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/Constant.h"
 #include "llvm/IR/DataLayout.h"
+#include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GlobalValue.h"
 #include "llvm/IR/IRBuilder.h"
@@ -30,16 +33,28 @@
 #include "llvm/IR/Type.h"
 #include "llvm/IR/Value.h"
 #include "llvm/ProfileData/InstrProf.h"
+#include "llvm/ProfileData/InstrProfReader.h"
+#include "llvm/Support/BLAKE3.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
+#include "llvm/Support/HashBuilder.h"
 #include "llvm/TargetParser/Triple.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 #include "llvm/Transforms/Utils/ModuleUtils.h"
+#include <map>
+#include <set>
 
 using namespace llvm;
+using namespace llvm::memprof;
 
 #define DEBUG_TYPE "memprof"
 
+namespace llvm {
+extern cl::opt<bool> PGOWarnMissing;
+extern cl::opt<bool> NoPGOWarnMismatch;
+extern cl::opt<bool> NoPGOWarnMismatchComdatWeak;
+} // namespace llvm
+
 constexpr int LLVM_MEM_PROFILER_VERSION = 1;
 
 // Size of memory mapped to a single shadow location.
@@ -128,6 +143,7 @@ STATISTIC(NumInstrumentedReads, "Number of instrumented reads");
 STATISTIC(NumInstrumentedWrites, "Number of instrumented writes");
 STATISTIC(NumSkippedStackReads, "Number of non-instrumented stack reads");
 STATISTIC(NumSkippedStackWrites, "Number of non-instrumented stack writes");
+STATISTIC(NumOfMemProfMissing, "Number of functions without memory profile.");
 
 namespace {
 
@@ -601,3 +617,251 @@ bool MemProfiler::instrumentFunction(Function &F) {
 
   return FunctionModified;
 }
+
+static void addCallsiteMetadata(Instruction &I,
+                                std::vector<uint64_t> &InlinedCallStack,
+                                LLVMContext &Ctx) {
+  I.setMetadata(LLVMContext::MD_callsite,
+                buildCallstackMetadata(InlinedCallStack, Ctx));
+}
+
+static uint64_t computeStackId(GlobalValue::GUID Function, uint32_t LineOffset,
+                               uint32_t Column) {
+  llvm::HashBuilder<llvm::TruncatedBLAKE3<8>, llvm::support::endianness::little>
+      HashBuilder;
+  HashBuilder.add(Function, LineOffset, Column);
+  llvm::BLAKE3Result<8> Hash = HashBuilder.final();
+  uint64_t Id;
+  std::memcpy(&Id, Hash.data(), sizeof(Hash));
+  return Id;
+}
+
+static uint64_t computeStackId(const memprof::Frame &Frame) {
+  return computeStackId(Frame.Function, Frame.LineOffset, Frame.Column);
+}
+
+static void addCallStack(CallStackTrie &AllocTrie,
+                         const AllocationInfo *AllocInfo) {
+  SmallVector<uint64_t> StackIds;
+  for (const auto &StackFrame : AllocInfo->CallStack)
+    StackIds.push_back(computeStackId(StackFrame));
+  auto AllocType = getAllocType(AllocInfo->Info.getTotalLifetimeAccessDensity(),
+                                AllocInfo->Info.getAllocCount(),
+                                AllocInfo->Info.getTotalLifetime());
+  AllocTrie.addCallStack(AllocType, StackIds);
+}
+
+// Helper to compare the InlinedCallStack computed from an instruction's debug
+// info to a list of Frames from profile data (either the allocation data or a
+// callsite). For callsites, the StartIndex to use in the Frame array may be
+// non-zero.
+static bool
+stackFrameIncludesInlinedCallStack(ArrayRef<Frame> ProfileCallStack,
+                                   ArrayRef<uint64_t> InlinedCallStack,
+                                   unsigned StartIndex = 0) {
+  auto StackFrame = ProfileCallStack.begin() + StartIndex;
+  auto InlCallStackIter = InlinedCallStack.begin();
+  for (; StackFrame != ProfileCallStack.end() &&
+         InlCallStackIter != InlinedCallStack.end();
+       ++StackFrame, ++InlCallStackIter) {
+    uint64_t StackId = computeStackId(*StackFrame);
+    if (StackId != *InlCallStackIter)
+      return false;
+  }
+  // Return true if we found and matched all stack ids from the call
+  // instruction.
+  return InlCallStackIter == InlinedCallStack.end();
+}
+
+void llvm::readMemprof(Module &M, Function &F,
+                       IndexedInstrProfReader *MemProfReader,
+                       const TargetLibraryInfo &TLI) {
+  auto &Ctx = M.getContext();
+
+  auto FuncName = getPGOFuncName(F);
+  auto FuncGUID = Function::getGUID(FuncName);
+  Expected<memprof::MemProfRecord> MemProfResult =
+      MemProfReader->getMemProfRecord(FuncGUID);
+  if (Error E = MemProfResult.takeError()) {
+    handleAllErrors(std::move(E), [&](const InstrProfError &IPE) {
+      auto Err = IPE.get();
+      bool SkipWarning = false;
+      LLVM_DEBUG(dbgs() << "Error in reading profile for Func " << FuncName
+                        << ": ");
+      if (Err == instrprof_error::unknown_function) {
+        NumOfMemProfMissing++;
+        SkipWarning = !PGOWarnMissing;
+        LLVM_DEBUG(dbgs() << "unknown function");
+      } else if (Err == instrprof_error::hash_mismatch) {
+        SkipWarning =
+            NoPGOWarnMismatch ||
+            (NoPGOWarnMismatchComdatWeak &&
+             (F.hasComdat() ||
+              F.getLinkage() == GlobalValue::AvailableExternallyLinkage));
+        LLVM_DEBUG(dbgs() << "hash mismatch (skip=" << SkipWarning << ")");
+      }
+
+      if (SkipWarning)
+        return;
+
+      std::string Msg = (IPE.message() + Twine(" ") + F.getName().str() +
+                         Twine(" Hash = ") + std::to_string(FuncGUID))
+                            .str();
+
+      Ctx.diagnose(
+          DiagnosticInfoPGOProfile(M.getName().data(), Msg, DS_Warning));
+    });
+    return;
+  }
+
+  // Build maps of the location hash to all profile data with that leaf location
+  // (allocation info and the callsites).
+  std::map<uint64_t, std::set<const AllocationInfo *>> LocHashToAllocInfo;
+  // For the callsites we need to record the index of the associated frame in
+  // the frame array (see comments below where the map entries are added).
+  std::map<uint64_t, std::set<std::pair<const SmallVector<Frame> *, unsigned>>>
+      LocHashToCallSites;
+  const auto MemProfRec = std::move(MemProfResult.get());
+  for (auto &AI : MemProfRec.AllocSites) {
+    // Associate the allocation info with the leaf frame. The later matching
+    // code will match any inlined call sequences in the IR with a longer prefix
+    // of call stack frames.
+    uint64_t StackId = computeStackId(AI.CallStack[0]);
+    LocHashToAllocInfo[StackId].insert(&AI);
+  }
+  for (auto &CS : MemProfRec.CallSites) {
+    // Need to record all frames from leaf up to and including this function,
+    // as any of these may or may not have been inlined at this point.
+    unsigned Idx = 0;
+    for (auto &StackFrame : CS) {
+      uint64_t StackId = computeStackId(StackFrame);
+      LocHashToCallSites[StackId].insert(std::make_pair(&CS, Idx++));
+      // Once we find this function, we can stop recording.
+      if (StackFrame.Function == FuncGUID)
+        break;
+    }
+    assert(Idx <= CS.size() && CS[Idx - 1].Function == FuncGUID);
+  }
+
+  auto GetOffset = [](const DILocation *DIL) {
+    return (DIL->getLine() - DIL->getScope()->getSubprogram()->getLine()) &
+           0xffff;
+  };
+
+  // Now walk the instructions, looking up the associated profile data using
+  // dbug locations.
+  for (auto &BB : F) {
+    for (auto &I : BB) {
+      if (I.isDebugOrPseudoInst())
+        continue;
+      // We are only interested in calls (allocation or interior call stack
+      // context calls).
+      auto *CI = dyn_cast<CallBase>(&I);
+      if (!CI)
+        continue;
+      auto *CalledFunction = CI->getCalledFunction();
+      if (CalledFunction && CalledFunction->isIntrinsic())
+        continue;
+      // List of call stack ids computed from the location hashes on debug
+      // locations (leaf to inlined at root).
+      std::vector<uint64_t> InlinedCallStack;
+      // Was the leaf location found in one of the profile maps?
+      bool LeafFound = false;
+      // If leaf was found in a map, iterators pointing to its location in both
+      // of the maps. It might exist in neither, one, or both (the latter case
+      // can happen because we don't currently have discriminators to
+      // distinguish the case when a single line/col maps to both an allocation
+      // and another callsite).
+      std::map<uint64_t, std::set<const AllocationInfo *>>::iterator
+          AllocInfoIter;
+      std::map<uint64_t, std::set<std::pair<const SmallVector<Frame> *,
+                                            unsigned>>>::iterator CallSitesIter;
+      for (const DILocation *DIL = I.getDebugLoc(); DIL != nullptr;
+           DIL = DIL->getInlinedAt()) {
+        // Use C++ linkage name if possible. Need to compile with
+        // -fdebug-info-for-profiling to get linkage name.
+        StringRef Name = DIL->getScope()->getSubprogram()->getLinkageName();
+        if (Name.empty())
+          Name = DIL->getScope()->getSubprogram()->getName();
+        auto CalleeGUID = Function::getGUID(Name);
+        auto StackId =
+            computeStackId(CalleeGUID, GetOffset(DIL), DIL->getColumn());
+        // LeafFound will only be false on the first iteration, since we either
+        // set it true or break out of the loop below.
+        if (!LeafFound) {
+          AllocInfoIter = LocHashToAllocInfo.find(StackId);
+          CallSitesIter = LocHashToCallSites.find(StackId);
+          // Check if the leaf is in one of the maps. If not, no need to look
+          // further at this call.
+          if (AllocInfoIter == LocHashToAllocInfo.end() &&
+              CallSitesIter == LocHashToCallSites.end())
+            break;
+          LeafFound = true;
+        }
+        InlinedCallStack.push_back(StackId);
+      }
+      // If leaf not in either of the maps, skip inst.
+      if (!LeafFound)
+        continue;
+
+      // First add !memprof metadata from allocation info, if we found the
+      // instruction's leaf location in that map, and if the rest of the
+      // instruction's locations match the prefix Frame locations on an
+      // allocation context with the same leaf.
+      if (AllocInfoIter != LocHashToAllocInfo.end()) {
+        // Only consider allocations via new, to reduce unnecessary metadata,
+        // since those are the only allocations that will be targeted initially.
+        if (!isNewLikeFn(CI, &TLI))
+          continue;
+        // We may match this instruction's location list to multiple MIB
+        // contexts. Add them to a Trie specialized for trimming the contexts to
+        // the minimal needed to disambiguate contexts with unique behavior.
+        CallStackTrie AllocTrie;
+        for (auto *AllocInfo : AllocInfoIter->second) {
+          // Check the full inlined call stack against this one.
+          // If we found and thus matched all frames on the call, include
+          // this MIB.
+          if (stackFrameIncludesInlinedCallStack(AllocInfo->CallStack,
+                                                 InlinedCallStack))
+            addCallStack(AllocTrie, AllocInfo);
+        }
+        // We might not have matched any to the full inlined call stack.
+        // But if we did, create and attach metadata, or a function attribute if
+        // all contexts have identical profiled behavior.
+        if (!AllocTrie.empty()) {
+          // MemprofMDAttached will be false if a function attribute was
+          // attached.
+          bool MemprofMDAttached = AllocTrie.buildAndAttachMIBMetadata(CI);
+          assert(MemprofMDAttached == I.hasMetadata(LLVMContext::MD_memprof));
+          if (MemprofMDAttached) {
+            // Add callsite metadata for the instruction's location list so that
+            // it simpler later on to identify which part of the MIB contexts
+            // are from this particular instruction (including during inlining,
+            // when the callsite metdata will be updated appropriately).
+            // FIXME: can this be changed to strip out the matching stack
+            // context ids from the MIB contexts and not add any callsite
+            // metadata here to save space?
+            addCallsiteMetadata(I, InlinedCallStack, Ctx);
+          }
+        }
+        continue;
+      }
+
+      // Otherwise, add callsite metadata. If we reach here then we found the
+      // instruction's leaf location in the callsites map and not the allocation
+      // map.
+      assert(CallSitesIter != LocHashToCallSites.end());
+      for (auto CallStackIdx : CallSitesIter->second) {
+        // If we found and thus matched all frames on the call, create and
+        // attach call stack metadata.
+        if (stackFrameIncludesInlinedCallStack(
+                *CallStackIdx.first, InlinedCallStack, CallStackIdx.second)) {
+          addCallsiteMetadata(I, InlinedCallStack, Ctx);
+          // Only need to find one with a matching call stack and add a single
+          // callsite metadata.
+          break;
+        }
+      }
+    }
+  }
+}