From 9a81a4ef79cf283fcf55a25a0bea67ba34dc0d53 Mon Sep 17 00:00:00 2001
From: Sriraman Tallam <tmsriram@google.com>
Date: Fri, 29 Jan 2021 12:52:59 -0800
Subject: [PATCH] Emit metadata when instr. profiles hash mismatch occurs.

This patch emits "instr_prof_hash_mismatch" function annotation metadata if
there is a hash mismatch while applying instrumented profiles.

During the PGO optimized build using instrumented profiles, if the CFG of
the function has changed since generating the profile, a hash mismatch is
encountered. This patch emits this information as annotation metadata. We
plan to use this with Propeller which is done at the machine IR level.
Propeller is usually applied on top of PGO and a hash mismatch during
PGO could be used to detect source drift.

Differential Revision: https://reviews.llvm.org/D95495
---
 .../Instrumentation/PGOInstrumentation.cpp         | 24 ++++++++++++++++++++++
 .../Inputs/hash_mismatch_metadata.proftext         | 17 +++++++++++++++
 .../PGOProfile/hash_mismatch_metadata.ll           | 18 ++++++++++++++++
 3 files changed, 59 insertions(+)
 create mode 100644 llvm/test/Transforms/PGOProfile/Inputs/hash_mismatch_metadata.proftext
 create mode 100644 llvm/test/Transforms/PGOProfile/hash_mismatch_metadata.ll

diff --git a/llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp b/llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp
index be6c8c6..46e5b75 100644
--- a/llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp
+++ b/llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp
@@ -1245,6 +1245,28 @@ void PGOUseFunc::setEdgeCount(DirectEdges &Edges, uint64_t Value) {
   llvm_unreachable("Cannot find the unknown count edge");
 }
 
+// Emit function metadata indicating PGO profile mismatch.
+static void annotateFunctionWithHashMismatch(Function &F,
+                                             LLVMContext &ctx) {
+  const char MetadataName[] = "instr_prof_hash_mismatch";
+  SmallVector<Metadata *, 2> Names;
+  // If this metadata already exists, ignore.
+  auto *Existing = F.getMetadata(LLVMContext::MD_annotation);
+  if (Existing) {
+    MDTuple *Tuple = cast<MDTuple>(Existing);
+    for (auto &N : Tuple->operands()) {
+      if (cast<MDString>(N.get())->getString() ==  MetadataName)
+        return;
+      Names.push_back(N.get());
+    }
+  }
+
+  MDBuilder MDB(ctx);
+  Names.push_back(MDB.createString(MetadataName));
+  MDNode *MD = MDTuple::get(ctx, Names);
+  F.setMetadata(LLVMContext::MD_annotation, MD);
+}
+
 // Read the profile from ProfileFileName and assign the value to the
 // instrumented BB and the edges. This function also updates ProgramMaxCount.
 // Return true if the profile are successfully read, and false on errors.
@@ -1272,6 +1294,8 @@ bool PGOUseFunc::readCounters(IndexedInstrProfReader *PGOReader, bool &AllZeros,
              (F.hasComdat() ||
               F.getLinkage() == GlobalValue::AvailableExternallyLinkage));
         LLVM_DEBUG(dbgs() << "hash mismatch (skip=" << SkipWarning << ")");
+        // Emit function metadata indicating PGO profile mismatch.
+        annotateFunctionWithHashMismatch(F, M->getContext());
       }
 
       LLVM_DEBUG(dbgs() << " IsCS=" << IsCS << "\n");
diff --git a/llvm/test/Transforms/PGOProfile/Inputs/hash_mismatch_metadata.proftext b/llvm/test/Transforms/PGOProfile/Inputs/hash_mismatch_metadata.proftext
new file mode 100644
index 0000000..f2e6f4d
--- /dev/null
+++ b/llvm/test/Transforms/PGOProfile/Inputs/hash_mismatch_metadata.proftext
@@ -0,0 +1,17 @@
+:ir
+:entry_first
+foo
+# Func Hash:
+11111
+# Num Counters:
+1
+# Counter Values:
+100
+
+bar
+# Func Hash:
+11111
+# Num Counters:
+1
+# Counter Values:
+100
diff --git a/llvm/test/Transforms/PGOProfile/hash_mismatch_metadata.ll b/llvm/test/Transforms/PGOProfile/hash_mismatch_metadata.ll
new file mode 100644
index 0000000..561865c
--- /dev/null
+++ b/llvm/test/Transforms/PGOProfile/hash_mismatch_metadata.ll
@@ -0,0 +1,18 @@
+; RUN: llvm-profdata merge %S/Inputs/hash_mismatch_metadata.proftext -o %t.profdata
+; RUN: opt < %s -mtriple=x86_64-linux-gnu -passes=pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s
+
+define void @foo() !annotation !1 {
+entry:
+   ret void
+}
+
+define void @bar() !annotation !2 {
+entry:
+   ret void
+}
+
+!1 = !{!"fake_metadata"}
+!2 = !{!"instr_prof_hash_mismatch"}
+
+; CHECK-DAG: !{{[0-9]+}} = !{!"fake_metadata", !"instr_prof_hash_mismatch"}
+; CHECK-DAG: !{{[0-9]+}} = !{!"instr_prof_hash_mismatch"}
-- 
2.7.4