[TableGen] Better error checking for TIED_TO constraints.

There are quite strong constraints on how you can use the TIED_TO
constraint between MC operands, many of which are currently not
checked until compiler run time.

MachineVerifier enforces that operands can only be tied together in
pairs (no three-way ties), and MachineInstr::tieOperands enforces that
one of the tied operands must be an output operand (def) and the other
must be an input operand (use).

Now we check these at TableGen time, so that if you violate any of
them in a new instruction definition, you find out immediately,
instead of having to wait until you compile something that makes code
generation hit one of those assertions.

Also in this commit, all the error reports in ParseConstraint now
include the name and source location of the def where the problem
happened, so that if you do trigger any of these errors, it's easier
to find the part of your TableGen input where you made the mistake.

The trunk sources already build successfully with this additional
error check, so I think no in-tree target has any of these problems.

Reviewers: fhahn, lhames, nhaehnle, MatzeB

Reviewed By: MatzeB

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D53815

llvm-svn: 347743

test/TableGen/ConstraintChecking.inc

@@ -0,0 +1,33 @@
+include "llvm/Target/Target.td"
+
+def TestTarget : Target;
+
+class Encoding : Instruction {
+  field bits<8> Inst;
+}
+
+class TestReg<string name, bits<1> enc> : Register<name, []> {
+    let HWEncoding{15-1} = 0;
+    let HWEncoding{0} = enc;
+}
+
+def R0 : TestReg<"R0", 0>;
+def R1 : TestReg<"R1", 1>;
+def Reg : RegisterClass<"TestTarget", [i32], 32, (sequence "R%d", 0, 1)>;
+
+class TestInstructionWithConstraints<string cstr> : Encoding {
+  dag OutOperandList = (outs Reg:$dest1, Reg:$dest2);
+  dag InOperandList = (ins Reg:$src1, Reg:$src2);
+  string AsmString = "mnemonic $dest1, $dest2, $src1, $src2";
+  string AsmVariantName = "";
+  let Constraints = cstr;
+  field bits<1> dest1;
+  field bits<1> dest2;
+  field bits<1> src1;
+  field bits<1> src2;
+  let Inst{7-4} = 0b1010;
+  let Inst{3} = dest1{0};
+  let Inst{2} = dest2{0};
+  let Inst{1} = src1{0};
+  let Inst{0} = src2{0};
+}

test/TableGen/ConstraintChecking1.td

@@ -0,0 +1,6 @@
+// RUN: not llvm-tblgen -gen-asm-writer -I %p -I %p/../../include %s 2>&1 | FileCheck %s -DFILE=%s
+
+include "ConstraintChecking.inc"
+
+// CHECK: [[FILE]]:[[@LINE+1]]:1: error: Unrecognized constraint '$dest1 ~ $src2' in 'Foo'
+def Foo : TestInstructionWithConstraints<"$dest1 ~ $src2">;

test/TableGen/ConstraintChecking2.td

@@ -0,0 +1,6 @@
+// RUN: not llvm-tblgen -gen-asm-writer -I %p -I %p/../../include %s 2>&1 | FileCheck %s -DFILE=%s
+
+include "ConstraintChecking.inc"
+
+// CHECK: [[FILE]]:[[@LINE+1]]:1: error: Illegal format for @earlyclobber constraint in 'Foo'
+def Foo : TestInstructionWithConstraints<"@earlyclobber ">;

test/TableGen/ConstraintChecking3.td

@@ -0,0 +1,8 @@
+// RUN: not llvm-tblgen -gen-asm-writer -I %p -I %p/../../include %s 2>&1 | FileCheck %s -DFILE=%s
+
+include "ConstraintChecking.inc"
+
+// (This is illegal because the '=' has to be surrounded by whitespace)
+
+// CHECK: [[FILE]]:[[@LINE+1]]:1: error: Illegal format for tied-to constraint in 'Foo'
+def Foo : TestInstructionWithConstraints<"$dest1=$dest2">;

test/TableGen/ConstraintChecking4.td

@@ -0,0 +1,6 @@
+// RUN: not llvm-tblgen -gen-asm-writer -I %p -I %p/../../include %s 2>&1 | FileCheck %s -DFILE=%s
+
+include "ConstraintChecking.inc"
+
+// CHECK: [[FILE]]:[[@LINE+1]]:1: error: Output operands '$dest1' and '$dest2' of 'Foo' cannot be tied!
+def Foo : TestInstructionWithConstraints<"$dest1 = $dest2">;

test/TableGen/ConstraintChecking5.td

@@ -0,0 +1,6 @@
+// RUN: not llvm-tblgen -gen-asm-writer -I %p -I %p/../../include %s 2>&1 | FileCheck %s -DFILE=%s
+
+include "ConstraintChecking.inc"
+
+// CHECK: [[FILE]]:[[@LINE+1]]:1: error: Input operands '$src1' and '$src2' of 'Foo' cannot be tied!
+def Foo : TestInstructionWithConstraints<"$src1 = $src2">;

test/TableGen/ConstraintChecking6.td

@@ -0,0 +1,6 @@
+// RUN: not llvm-tblgen -gen-asm-writer -I %p -I %p/../../include %s 2>&1 | FileCheck %s -DFILE=%s
+
+include "ConstraintChecking.inc"
+
+// CHECK: [[FILE]]:[[@LINE+1]]:1: error: Operand '$dest1' of 'Foo' cannot have multiple operands tied to it!
+def Foo : TestInstructionWithConstraints<"$dest1 = $src1, $dest1 = $src2">;

test/TableGen/ConstraintChecking7.td

@@ -0,0 +1,6 @@
+// RUN: not llvm-tblgen -gen-asm-writer -I %p -I %p/../../include %s 2>&1 | FileCheck %s -DFILE=%s
+
+include "ConstraintChecking.inc"
+
+// CHECK: [[FILE]]:[[@LINE+1]]:1: error: Operand '$src1' of 'Foo' cannot have multiple constraints!
+def Foo : TestInstructionWithConstraints<"$dest1 = $src1, $dest2 = $src1">;

utils/TableGen/CodeGenInstruction.cpp

@@ -202,7 +202,8 @@ CGIOperandList::ParseOperandName(const std::string &Op, bool AllowWholeOp) {
   return std::make_pair(0U, 0U);
 }
 
-static void ParseConstraint(const std::string &CStr, CGIOperandList &Ops) {
+static void ParseConstraint(const std::string &CStr, CGIOperandList &Ops,
+                            Record *Rec) {
   // EARLY_CLOBBER: @early $reg
   std::string::size_type wpos = CStr.find_first_of(" \t");
   std::string::size_type start = CStr.find_first_not_of(" \t");
@@ -211,13 +212,17 @@ static void ParseConstraint(const std::string &CStr, CGIOperandList &Ops) {
     std::string Name = CStr.substr(wpos+1);
     wpos = Name.find_first_not_of(" \t");
     if (wpos == std::string::npos)
-      PrintFatalError("Illegal format for @earlyclobber constraint: '" + CStr + "'");
+      PrintFatalError(
+        Rec->getLoc(), "Illegal format for @earlyclobber constraint in '" +
+        Rec->getName() + "': '" + CStr + "'");
     Name = Name.substr(wpos);
     std::pair<unsigned,unsigned> Op = Ops.ParseOperandName(Name, false);
 
     // Build the string for the operand
     if (!Ops[Op.first].Constraints[Op.second].isNone())
-      PrintFatalError("Operand '" + Name + "' cannot have multiple constraints!");
+      PrintFatalError(
+        Rec->getLoc(), "Operand '" + Name + "' of '" + Rec->getName() +
+        "' cannot have multiple constraints!");
     Ops[Op.first].Constraints[Op.second] =
     CGIOperandList::ConstraintInfo::getEarlyClobber();
     return;
@@ -225,39 +230,73 @@ static void ParseConstraint(const std::string &CStr, CGIOperandList &Ops) {
 
   // Only other constraint is "TIED_TO" for now.
   std::string::size_type pos = CStr.find_first_of('=');
-  assert(pos != std::string::npos && "Unrecognized constraint");
+  if (pos == std::string::npos)
+    PrintFatalError(
+      Rec->getLoc(), "Unrecognized constraint '" + CStr +
+      "' in '" + Rec->getName() + "'");
   start = CStr.find_first_not_of(" \t");
-  std::string Name = CStr.substr(start, pos - start);
 
   // TIED_TO: $src1 = $dst
-  wpos = Name.find_first_of(" \t");
-  if (wpos == std::string::npos)
-    PrintFatalError("Illegal format for tied-to constraint: '" + CStr + "'");
-  std::string DestOpName = Name.substr(0, wpos);
-  std::pair<unsigned,unsigned> DestOp = Ops.ParseOperandName(DestOpName, false);
+  wpos = CStr.find_first_of(" \t", start);
+  if (wpos == std::string::npos || wpos > pos)
+    PrintFatalError(
+      Rec->getLoc(), "Illegal format for tied-to constraint in '" +
+      Rec->getName() + "': '" + CStr + "'");
+  std::string LHSOpName = StringRef(CStr).substr(start, wpos - start);
+  std::pair<unsigned,unsigned> LHSOp = Ops.ParseOperandName(LHSOpName, false);
 
-  Name = CStr.substr(pos+1);
-  wpos = Name.find_first_not_of(" \t");
+  wpos = CStr.find_first_not_of(" \t", pos + 1);
   if (wpos == std::string::npos)
-    PrintFatalError("Illegal format for tied-to constraint: '" + CStr + "'");
+    PrintFatalError(
+      Rec->getLoc(), "Illegal format for tied-to constraint: '" + CStr + "'");
 
-  std::string SrcOpName = Name.substr(wpos);
-  std::pair<unsigned,unsigned> SrcOp = Ops.ParseOperandName(SrcOpName, false);
-  if (SrcOp > DestOp) {
-    std::swap(SrcOp, DestOp);
-    std::swap(SrcOpName, DestOpName);
+  std::string RHSOpName = StringRef(CStr).substr(wpos);
+  std::pair<unsigned,unsigned> RHSOp = Ops.ParseOperandName(RHSOpName, false);
+
+  // Sort the operands into order, which should put the output one
+  // first. But keep the original order, for use in diagnostics.
+  bool FirstIsDest = (LHSOp < RHSOp);
+  std::pair<unsigned,unsigned> DestOp = (FirstIsDest ? LHSOp : RHSOp);
+  StringRef DestOpName = (FirstIsDest ? LHSOpName : RHSOpName);
+  std::pair<unsigned,unsigned> SrcOp = (FirstIsDest ? RHSOp : LHSOp);
+  StringRef SrcOpName = (FirstIsDest ? RHSOpName : LHSOpName);
+
+  // Ensure one operand is a def and the other is a use.
+  if (DestOp.first >= Ops.NumDefs)
+    PrintFatalError(
+      Rec->getLoc(), "Input operands '" + LHSOpName + "' and '" + RHSOpName +
+      "' of '" + Rec->getName() + "' cannot be tied!");
+  if (SrcOp.first < Ops.NumDefs)
+    PrintFatalError(
+      Rec->getLoc(), "Output operands '" + LHSOpName + "' and '" + RHSOpName +
+      "' of '" + Rec->getName() + "' cannot be tied!");
+
+  // The constraint has to go on the operand with higher index, i.e.
+  // the source one. Check there isn't another constraint there
+  // already.
+  if (!Ops[SrcOp.first].Constraints[SrcOp.second].isNone())
+    PrintFatalError(
+      Rec->getLoc(), "Operand '" + SrcOpName + "' of '" + Rec->getName() +
+      "' cannot have multiple constraints!");
+
+  unsigned DestFlatOpNo = Ops.getFlattenedOperandNumber(DestOp);
+  auto NewConstraint = CGIOperandList::ConstraintInfo::getTied(DestFlatOpNo);
+
+  // Check that the earlier operand is not the target of another tie
+  // before making it the target of this one.
+  for (const CGIOperandList::OperandInfo &Op : Ops) {
+    for (unsigned i = 0; i < Op.MINumOperands; i++)
+      if (Op.Constraints[i] == NewConstraint)
+        PrintFatalError(
+          Rec->getLoc(), "Operand '" + DestOpName + "' of '" + Rec->getName() +
+          "' cannot have multiple operands tied to it!");
   }
 
-  unsigned FlatOpNo = Ops.getFlattenedOperandNumber(SrcOp);
-
-  if (!Ops[DestOp.first].Constraints[DestOp.second].isNone())
-    PrintFatalError("Operand '" + DestOpName +
-      "' cannot have multiple constraints!");
-  Ops[DestOp.first].Constraints[DestOp.second] =
-    CGIOperandList::ConstraintInfo::getTied(FlatOpNo);
+  Ops[SrcOp.first].Constraints[SrcOp.second] = NewConstraint;
 }
 
-static void ParseConstraints(const std::string &CStr, CGIOperandList &Ops) {
+static void ParseConstraints(const std::string &CStr, CGIOperandList &Ops,
+                             Record *Rec) {
   if (CStr.empty()) return;
 
   const std::string delims(",");
@@ -269,7 +308,7 @@ static void ParseConstraints(const std::string &CStr, CGIOperandList &Ops) {
     if (eidx == std::string::npos)
       eidx = CStr.length();
 
-    ParseConstraint(CStr.substr(bidx, eidx - bidx), Ops);
+    ParseConstraint(CStr.substr(bidx, eidx - bidx), Ops, Rec);
     bidx = CStr.find_first_not_of(delims, eidx);
   }
 }
@@ -353,7 +392,7 @@ CodeGenInstruction::CodeGenInstruction(Record *R)
   hasChain_Inferred = false;
 
   // Parse Constraints.
-  ParseConstraints(R->getValueAsString("Constraints"), Operands);
+  ParseConstraints(R->getValueAsString("Constraints"), Operands, R);
 
   // Parse the DisableEncoding field.
   Operands.ProcessDisableEncoding(R->getValueAsString("DisableEncoding"));

utils/TableGen/CodeGenInstruction.h

@@ -57,6 +57,15 @@ template <typename T> class ArrayRef;
         assert(isTied());
         return OtherTiedOperand;
       }
+
+      bool operator==(const ConstraintInfo &RHS) const {
+        if (Kind != RHS.Kind)
+          return false;
+        if (Kind == Tied && OtherTiedOperand != RHS.OtherTiedOperand)
+          return false;
+        return true;
+      }
+      bool operator!=(const ConstraintInfo &RHS) const { return *this != RHS; }
     };
 
     /// OperandInfo - The information we keep track of for each operand in the