Move the complex address expression out of DIVariable and into an extra

argument of the llvm.dbg.declare/llvm.dbg.value intrinsics.

Previously, DIVariable was a variable-length field that has an optional
reference to a Metadata array consisting of a variable number of
complex address expressions. In the case of OpPiece expressions this is
wasting a lot of storage in IR, because when an aggregate type is, e.g.,
SROA'd into all of its n individual members, the IR will contain n copies
of the DIVariable, all alike, only differing in the complex address
reference at the end.

By making the complex address into an extra argument of the
dbg.value/dbg.declare intrinsics, all of the pieces can reference the
same variable and the complex address expressions can be uniqued across
the CU, too.
Down the road, this will allow us to move other flags, such as
"indirection" out of the DIVariable, too.

The new intrinsics look like this:
declare void @llvm.dbg.declare(metadata %storage, metadata %var, metadata %expr)
declare void @llvm.dbg.value(metadata %storage, i64 %offset, metadata %var, metadata %expr)

This patch adds a new LLVM-local tag to DIExpressions, so we can detect
and pretty-print DIExpression metadata nodes.

What this patch doesn't do:

This patch does not touch the "Indirect" field in DIVariable; but moving
that into the expression would be a natural next step.

http://reviews.llvm.org/D4919
rdar://problem/17994491

Thanks to dblaikie and dexonsmith for reviewing this patch!

Note: I accidentally committed a bogus older version of this patch previously.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218787 91177308-0d34-0410-b5e6-96231b3b80d8

lib/IR/AutoUpgrade.cpp

@@ -17,6 +17,7 @@
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DebugInfo.h"
 #include "llvm/IR/DiagnosticInfo.h"
+#include "llvm/IR/DIBuilder.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instruction.h"
@@ -106,6 +107,20 @@ static bool UpgradeIntrinsicFunction1(Function *F, Function *&NewFn) {
     }
     break;
   }
+  case 'd': {
+    if (Name.startswith("dbg.declare") && F->arg_size() == 2) {
+      F->setName(Name + ".old");
+      NewFn = Intrinsic::getDeclaration(F->getParent(), Intrinsic::dbg_declare);
+      return true;
+    }
+    if (Name.startswith("dbg.value") && F->arg_size() == 3) {
+      F->setName(Name + ".old");
+      NewFn = Intrinsic::getDeclaration(F->getParent(), Intrinsic::dbg_value);
+      return true;
+    }
+    break;
+  }
+
   case 'o':
     // We only need to change the name to match the mangling including the
     // address space.
@@ -239,6 +254,22 @@ bool llvm::UpgradeGlobalVariable(GlobalVariable *GV) {
   return false;
 }
 
+static MDNode *getNodeField(const MDNode *DbgNode, unsigned Elt) {
+  if (!DbgNode || Elt >= DbgNode->getNumOperands())
+    return nullptr;
+  return dyn_cast_or_null<MDNode>(DbgNode->getOperand(Elt));
+}
+
+static DIExpression getExpression(Value *VarOperand, Function *F) {
+  // Old-style DIVariables have an optional expression as the 8th element.
+  DIExpression Expr(getNodeField(cast<MDNode>(VarOperand), 8));
+  if (!Expr) {
+    DIBuilder DIB(*F->getParent());
+    Expr = DIB.createExpression();
+  }
+  return Expr;
+}
+
 // UpgradeIntrinsicCall - Upgrade a call to an old intrinsic to be a call the
 // upgraded intrinsic. All argument and return casting must be provided in
 // order to seamlessly integrate with existing context.
@@ -402,12 +433,32 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) {
   }
 
   std::string Name = CI->getName().str();
-  CI->setName(Name + ".old");
+  if (!Name.empty())
+    CI->setName(Name + ".old");
 
   switch (NewFn->getIntrinsicID()) {
   default:
     llvm_unreachable("Unknown function for CallInst upgrade.");
 
+  // Upgrade debug intrinsics to use an additional DIExpression argument.
+  case Intrinsic::dbg_declare: {
+    auto NewCI =
+        Builder.CreateCall3(NewFn, CI->getArgOperand(0), CI->getArgOperand(1),
+                            getExpression(CI->getArgOperand(1), F), Name);
+    NewCI->setDebugLoc(CI->getDebugLoc());
+    CI->replaceAllUsesWith(NewCI);
+    CI->eraseFromParent();
+    return;
+  }
+  case Intrinsic::dbg_value: {
+    auto NewCI = Builder.CreateCall4(
+        NewFn, CI->getArgOperand(0), CI->getArgOperand(1), CI->getArgOperand(2),
+        getExpression(CI->getArgOperand(2), F), Name);
+    NewCI->setDebugLoc(CI->getDebugLoc());
+    CI->replaceAllUsesWith(NewCI);
+    CI->eraseFromParent();
+    return;
+  }
   case Intrinsic::ctlz:
   case Intrinsic::cttz:
     assert(CI->getNumArgOperands() == 1 &&