[TableGen] Fix non-standard escape warnings for braces in InstAlias

Summary:
TableGen interprets braces ('{}') in the asm string of instruction aliases as
variants but when defining aliases with literal braces they have to be escaped
to prevent them being removed.

Braces are escaped with '\\', for example:

  def FooBraces : InstAlias<"foo \\{$imm\\}", (foo IntOperand:$imm)>;

Although when TableGen is emitting the assembly writer (-gen-asm-writer)
the AsmString that gets emitted is:

  AsmString = "foo \{$\x01\}";

In c/c++ braces don't need to be escaped which causes compilation
warnings:

  warning: use of non-standard escape character '\{' [-Wpedantic]

This patch fixes the issue by unescaping the flattened alias asm string
in the asm writer, by replacing '\{\}' with '{}'.

Reviewed By: hfinkel

Differential Revision: https://reviews.llvm.org/D79991

diff --git a/llvm/test/TableGen/AliasAsmString.td b/llvm/test/TableGen/AliasAsmString.td
new file mode 100644 (file)
index 0000000..dedcc4b
--- /dev/null
+++ b/llvm/test/TableGen/AliasAsmString.td
@@ -0,0 +1,28 @@
+// RUN: llvm-tblgen -gen-asm-writer -I %p/../../include %s | FileCheck %s
+
+include "llvm/Target/Target.td"
+
+def ArchInstrInfo : InstrInfo { }
+
+def Arch : Target {
+  let InstructionSet = ArchInstrInfo;
+}
+
+def Reg : Register<"reg">;
+
+def RegClass : RegisterClass<"foo", [i32], 0, (add Reg)>;
+
+def IntOperand: Operand<i32>;
+
+def foo : Instruction {
+  let Size = 2;
+  let OutOperandList = (outs);
+  let InOperandList = (ins IntOperand:$imm);
+  let AsmString = "foo $imm";
+  let Namespace = "Arch";
+}
+
+def FooBraces : InstAlias<"foo \\{$imm\\}", (foo IntOperand:$imm)>;
+
+// CHECK: static const char AsmStrings[] =
+// CHECK-NEXT: /* 0 */ "foo {$\x01}\0"

diff --git a/llvm/utils/TableGen/AsmWriterEmitter.cpp b/llvm/utils/TableGen/AsmWriterEmitter.cpp
index 72c7baa139a9d621014b19d807850e81acb06f81..d10ea71e97e3f155307208e64047a23d9a57b4fe 100644 (file)
--- a/llvm/utils/TableGen/AsmWriterEmitter.cpp
+++ b/llvm/utils/TableGen/AsmWriterEmitter.cpp
@@ -267,6 +267,27 @@ static void UnescapeString(std::string &Str) {
   }
 }
 
+/// UnescapeAliasString - Supports literal braces in InstAlias asm string which
+/// are escaped with '\\' to avoid being interpreted as variants. Braces must
+/// be unescaped before c++ code is generated as (e.g.):
+///
+///   AsmString = "foo \{$\x01\}";
+///
+/// causes non-standard escape character warnings.
+static void UnescapeAliasString(std::string &Str) {
+  for (unsigned i = 0; i != Str.size(); ++i) {
+    if (Str[i] == '\\' && i != Str.size()-1) {
+      switch (Str[i+1]) {
+      default: continue;  // Don't execute the code after the switch.
+      case '{': Str[i] = '{'; break;
+      case '}': Str[i] = '}'; break;
+      }
+      // Nuke the second character.
+      Str.erase(Str.begin()+i+1);
+    }
+  }
+}
+
 /// EmitPrintInstruction - Generate the code for the "printInstruction" method
 /// implementation. Destroys all instances of AsmWriterInst information, by
 /// clearing the Instructions vector.
@@ -803,6 +824,7 @@ void AsmWriterEmitter::EmitPrintAliasInstruction(raw_ostream &O) {
 
       std::string FlatAliasAsmString =
           CodeGenInstruction::FlattenAsmStringVariants(CGA.AsmString, Variant);
+      UnescapeAliasString(FlatAliasAsmString);
 
       // Don't emit the alias if it has more operands than what it's aliasing.
       if (NumResultOps < CountNumOperands(FlatAliasAsmString, Variant))