Verifier: check prof branch_weights

[yrouban]

Summary

There are constraints on !pro branch_weights metadata
https://llvm.org/docs/BranchWeightMetadata.html
It needs to be fixed. As I found in the tests, two more instructions may have !prof branch_weights: Invoke and Select. I'm not sure who should fix the documentation.

This patch is to check some of those constraints.
Several patches are needed to land this patch. See D62122, D62123, D62126.

[reames]

LGTM w/a caveat. I fully expect that landing this would expose lots of existing breakage and would break the build bots. In practice, I don't think you should land this until fixing any issues you've already found. Once that's done, land, but expect to revert and fix found issues for a few cycles.

llvm/trunk/lib/IR/Verifier.cpp

private:
   void visitModuleFlag(const MDNode *Op,
                        DenseMap<const MDString *, const MDNode *> &SeenIDs,
                        SmallVectorImpl<const MDNode *> &Requirements);
   void visitModuleFlagCGProfileEntry(const MDOperand &MDO);
   void visitFunction(const Function &F);
   void visitBasicBlock(BasicBlock &BB);
   void visitRangeMetadata(Instruction &I, MDNode *Range, Type *Ty);
   void visitDereferenceableMetadata(Instruction &I, MDNode *MD);
+  void visitProfMetadata(Instruction &I, MDNode *MD);
 
   template <class Ty> bool isValidMetadataArray(const MDTuple &N);
 #define HANDLE_SPECIALIZED_MDNODE_LEAF(CLASS) void visit##CLASS(const CLASS &N);
 #include "llvm/IR/Metadata.def"
   void visitDIScope(const DIScope &N);
   void visitDIVariable(const DIVariable &N);
   void visitDILexicalBlockBase(const DILexicalBlockBase &N);
   void visitDITemplateParameter(const DITemplateParameter &N);
Assert((isa<LoadInst>(I) || isa<IntToPtrInst>(I)),
          " and inttoptr instructions, use attributes for calls or invokes", &I);
   Assert(MD->getNumOperands() == 1, "dereferenceable, dereferenceable_or_null "
          "take one operand!", &I);
   ConstantInt *CI = mdconst::dyn_extract<ConstantInt>(MD->getOperand(0));
   Assert(CI && CI->getType()->isIntegerTy(64), "dereferenceable, "
          "dereferenceable_or_null metadata value must be an i64!", &I);
 }
 
+void Verifier::visitProfMetadata(Instruction &I, MDNode *MD) {
+  Assert(MD->getNumOperands() >= 2,
+         "!prof annotations should have no less than 2 operands", MD);
+
+  // Check first operand.
+  Assert(MD->getOperand(0) != nullptr, "first operand should not be null", MD);
+  Assert(isa<MDString>(MD->getOperand(0)),
+         "expected string with name of the !prof annotation", MD);
+  MDString *MDS = cast<MDString>(MD->getOperand(0));
+  StringRef ProfName = MDS->getString();
+
+  // Check consistency of !prof branch_weights metadata.
+  if (ProfName.equals("branch_weights")) {
+    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) || isa<InvokeInst>(&I))
+      ExpectedNumOperands = 1;
+    else if (IndirectBrInst *IBI = dyn_cast<IndirectBrInst>(&I))
+      ExpectedNumOperands = IBI->getNumDestinations();
+    else if (isa<SelectInst>(&I))
+      ExpectedNumOperands = 2;
+    else
+      CheckFailed("!prof branch_weights are not allowed for this instruction",
+                  MD);
+
+    Assert(MD->getNumOperands() == 1 + ExpectedNumOperands,
+           "Wrong number of operands", MD);
+    for (unsigned i = 1; i < MD->getNumOperands(); ++i) {
+      auto &MDO = MD->getOperand(i);
+      Assert(MDO, "second operand should not be null", MD);
+      Assert(mdconst::dyn_extract<ConstantInt>(MDO),
+             "!prof brunch_weights operand is not a const int");
+    }
+  }
+}
+
 /// verifyInstruction - Verify that an instruction is well formed.
 ///
 void Verifier::visitInstruction(Instruction &I) {
   BasicBlock *BB = I.getParent();
   Assert(BB, "Instruction not embedded in basic block!", &I);
 
   if (!isa<PHINode>(I)) {   // Check that non-phi nodes are not self referential
     for (User *U : I.users()) {
Assert(CI && CI->getType()->isIntegerTy(64),
            "align metadata value must be an i64!", &I);
     uint64_t Align = CI->getZExtValue();
     Assert(isPowerOf2_64(Align),
            "align metadata value must be a power of 2!", &I);
     Assert(Align <= Value::MaximumAlignment,
            "alignment is larger that implementation defined limit", &I);
   }
 
+  if (MDNode *MD = I.getMetadata(LLVMContext::MD_prof))
+    visitProfMetadata(I, MD);
+
   if (MDNode *N = I.getDebugLoc().getAsMDNode()) {
     AssertDI(isa<DILocation>(N), "invalid !dbg metadata attachment", &I, N);
     visitMDNode(*N);
   }
 
   if (auto *DII = dyn_cast<DbgVariableIntrinsic>(&I))
     verifyFragmentExpression(*DII);