[pgo] add means to specify "unknown" MD_prof (#145578)

This PR is part of https://discourse.llvm.org/t/rfc-profile-information-propagation-unittesting/73595

In a slight departure from the RFC, instead of a brand-new `MD_prof_unknown` kind, this adds a first operand to `MD_prof` metadata. This makes it easy to replace with valid metadata (only one `MD_prof`), otherwise sites inserting valid `MD_prof` would also have to check to remove the `unknown` one.

The patch just introduces the notion and fixes the verifier accordingly. Existing APIs working (esp. reading) `MD_prof` will be updated subsequently.

1 files changed, 39 insertions, 17 deletions

diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index 853f3b4..227afe2b 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -2527,6 +2527,12 @@ void Verifier::verifyFunctionMetadata(
   for (const auto &Pair : MDs) {
     if (Pair.first == LLVMContext::MD_prof) {
       MDNode *MD = Pair.second;
+      if (isExplicitlyUnknownBranchWeightsMetadata(*MD)) {
+        CheckFailed("'unknown' !prof metadata should appear only on "
+                    "instructions supporting the 'branch_weights' metadata",
+                    MD);
+        continue;
+      }
       Check(MD->getNumOperands() >= 2,
             "!prof annotations should have no less than 2 operands", MD);
 
@@ -4989,9 +4995,24 @@ void Verifier::visitDereferenceableMetadata(Instruction& I, MDNode* MD) {
 }
 
 void Verifier::visitProfMetadata(Instruction &I, MDNode *MD) {
-  Check(MD->getNumOperands() >= 2,
-        "!prof annotations should have no less than 2 operands", MD);
-
+  auto GetBranchingTerminatorNumOperands = [&]() {
+    unsigned ExpectedNumOperands = 0;
+    if (BranchInst *BI = dyn_cast<BranchInst>(&I))
+      ExpectedNumOperands = BI->getNumSuccessors();
+    else if (SwitchInst *SI = dyn_cast<SwitchInst>(&I))
+      ExpectedNumOperands = SI->getNumSuccessors();
+    else if (isa<CallInst>(&I))
+      ExpectedNumOperands = 1;
+    else if (IndirectBrInst *IBI = dyn_cast<IndirectBrInst>(&I))
+      ExpectedNumOperands = IBI->getNumDestinations();
+    else if (isa<SelectInst>(&I))
+      ExpectedNumOperands = 2;
+    else if (CallBrInst *CI = dyn_cast<CallBrInst>(&I))
+      ExpectedNumOperands = CI->getNumSuccessors();
+    return ExpectedNumOperands;
+  };
+  Check(MD->getNumOperands() >= 1,
+        "!prof annotations should have at least 1 operand", MD);
   // Check first operand.
   Check(MD->getOperand(0) != nullptr, "first operand should not be null", MD);
   Check(isa<MDString>(MD->getOperand(0)),
@@ -4999,6 +5020,19 @@ void Verifier::visitProfMetadata(Instruction &I, MDNode *MD) {
   MDString *MDS = cast<MDString>(MD->getOperand(0));
   StringRef ProfName = MDS->getString();
 
+  if (ProfName == MDProfLabels::UnknownBranchWeightsMarker) {
+    Check(GetBranchingTerminatorNumOperands() != 0 || isa<InvokeInst>(I),
+          "'unknown' !prof should only appear on instructions on which "
+          "'branch_weights' would",
+          MD);
+    Check(MD->getNumOperands() == 1,
+          "'unknown' !prof should have no additional operands", MD);
+    return;
+  }
+
+  Check(MD->getNumOperands() >= 2,
+        "!prof annotations should have no less than 2 operands", MD);
+
   // Check consistency of !prof branch_weights metadata.
   if (ProfName == MDProfLabels::BranchWeights) {
     unsigned NumBranchWeights = getNumBranchWeights(*MD);
@@ -5006,20 +5040,8 @@ void Verifier::visitProfMetadata(Instruction &I, MDNode *MD) {
       Check(NumBranchWeights == 1 || NumBranchWeights == 2,
             "Wrong number of InvokeInst branch_weights operands", MD);
     } else {
-      unsigned ExpectedNumOperands = 0;
-      if (BranchInst *BI = dyn_cast<BranchInst>(&I))
-        ExpectedNumOperands = BI->getNumSuccessors();
-      else if (SwitchInst *SI = dyn_cast<SwitchInst>(&I))
-        ExpectedNumOperands = SI->getNumSuccessors();
-      else if (isa<CallInst>(&I))
-        ExpectedNumOperands = 1;
-      else if (IndirectBrInst *IBI = dyn_cast<IndirectBrInst>(&I))
-        ExpectedNumOperands = IBI->getNumDestinations();
-      else if (isa<SelectInst>(&I))
-        ExpectedNumOperands = 2;
-      else if (CallBrInst *CI = dyn_cast<CallBrInst>(&I))
-        ExpectedNumOperands = CI->getNumSuccessors();
-      else
+      const unsigned ExpectedNumOperands = GetBranchingTerminatorNumOperands();
+      if (ExpectedNumOperands == 0)
         CheckFailed("!prof branch_weights are not allowed for this instruction",
                     MD);