[llvm] r192758 - MC: Better handling of tricky symbol and section names
Hans Wennborg
hans at hanshq.net
Tue Oct 15 18:20:40 PDT 2013
Author: hans
Date: Tue Oct 15 20:20:40 2013
New Revision: 192758
URL: http://llvm.org/viewvc/llvm-project?rev=192758&view=rev
Log:
MC: Better handling of tricky symbol and section names
Because of win32 mangling, we produce symbol and section names with
funny characters in them, most notably @ characters.
MC would choke on trying to parse its own assembly output. This patch addresses
that by:
- Making @ trigger quoting of symbol names
- Also quote section names in the same way
- Just parse section names like other identifiers (to allow for quotes)
- Don't assume @ signifies a symbol variant if it is in a string.
Differential Revision: http://llvm-reviews.chandlerc.com/D1945
Added:
llvm/trunk/test/MC/COFF/quoted-names.ll
Modified:
llvm/trunk/lib/MC/MCParser/AsmParser.cpp
llvm/trunk/lib/MC/MCParser/COFFAsmParser.cpp
llvm/trunk/lib/MC/MCSectionCOFF.cpp
llvm/trunk/lib/MC/MCSymbol.cpp
llvm/trunk/test/CodeGen/X86/coff-feat00.ll
llvm/trunk/test/CodeGen/X86/fastcall-correct-mangling.ll
llvm/trunk/test/CodeGen/X86/stdcall.ll
Modified: llvm/trunk/lib/MC/MCParser/AsmParser.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/MC/MCParser/AsmParser.cpp?rev=192758&r1=192757&r2=192758&view=diff
==============================================================================
--- llvm/trunk/lib/MC/MCParser/AsmParser.cpp (original)
+++ llvm/trunk/lib/MC/MCParser/AsmParser.cpp Tue Oct 15 20:20:40 2013
@@ -792,19 +792,25 @@ bool AsmParser::parsePrimaryExpr(const M
EndLoc = SMLoc::getFromPointer(Identifier.end());
// This is a symbol reference.
+ StringRef SymbolName = Identifier;
+ MCSymbolRefExpr::VariantKind Variant = MCSymbolRefExpr::VK_None;
std::pair<StringRef, StringRef> Split = Identifier.split('@');
- MCSymbol *Sym = getContext().GetOrCreateSymbol(Split.first);
+
+ if (Split.first.size() != Identifier.size() &&
+ FirstTokenKind != AsmToken::String) {
+ SymbolName = Split.first;
+ StringRef VariantName = Split.second;
- // Lookup the symbol variant if used.
- MCSymbolRefExpr::VariantKind Variant = MCSymbolRefExpr::VK_None;
- if (Split.first.size() != Identifier.size()) {
- Variant = MCSymbolRefExpr::getVariantKindForName(Split.second);
+ // Lookup the symbol variant.
+ Variant = MCSymbolRefExpr::getVariantKindForName(VariantName);
if (Variant == MCSymbolRefExpr::VK_Invalid) {
Variant = MCSymbolRefExpr::VK_None;
- return TokError("invalid variant '" + Split.second + "'");
+ return TokError("invalid variant '" + VariantName + "'");
}
}
+ MCSymbol *Sym = getContext().GetOrCreateSymbol(SymbolName);
+
// If this is an absolute variable reference, substitute it now to preserve
// semantics in the face of reassignment.
if (Sym->isVariable() && isa<MCConstantExpr>(Sym->getVariableValue())) {
Modified: llvm/trunk/lib/MC/MCParser/COFFAsmParser.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/MC/MCParser/COFFAsmParser.cpp?rev=192758&r1=192757&r2=192758&view=diff
==============================================================================
--- llvm/trunk/lib/MC/MCParser/COFFAsmParser.cpp (original)
+++ llvm/trunk/lib/MC/MCParser/COFFAsmParser.cpp Tue Oct 15 20:20:40 2013
@@ -295,12 +295,7 @@ bool COFFAsmParser::ParseSectionSwitch(S
}
bool COFFAsmParser::ParseSectionName(StringRef &SectionName) {
- if (!getLexer().is(AsmToken::Identifier))
- return true;
-
- SectionName = getTok().getIdentifier();
- Lex();
- return false;
+ return getParser().parseIdentifier(SectionName);
}
// .section name [, "flags"]
Modified: llvm/trunk/lib/MC/MCSectionCOFF.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/MC/MCSectionCOFF.cpp?rev=192758&r1=192757&r2=192758&view=diff
==============================================================================
--- llvm/trunk/lib/MC/MCSectionCOFF.cpp (original)
+++ llvm/trunk/lib/MC/MCSectionCOFF.cpp Tue Oct 15 20:20:40 2013
@@ -39,6 +39,22 @@ void MCSectionCOFF::setSelection(int Sel
Characteristics |= COFF::IMAGE_SCN_LNK_COMDAT;
}
+static bool isAcceptableSectionNameChar(char C) {
+ return (C >= 'a' && C <= 'z') ||
+ (C >= 'A' && C <= 'Z') ||
+ (C >= '0' && C <= '9') ||
+ C == '_' || C == '$' || C == '.';
+}
+
+/// NameNeedsQuoting - Return true if the identifier \p Str needs quotes to be
+/// syntactically correct.
+static bool sectionNameNeedsQuoting(StringRef Name) {
+ for (unsigned i = 0, e = Name.size(); i != e; ++i)
+ if (!isAcceptableSectionNameChar(Name[i]))
+ return true;
+ return false;
+}
+
void MCSectionCOFF::PrintSwitchToSection(const MCAsmInfo &MAI,
raw_ostream &OS,
const MCExpr *Subsection) const {
@@ -49,7 +65,10 @@ void MCSectionCOFF::PrintSwitchToSection
return;
}
- OS << "\t.section\t" << getSectionName() << ",\"";
+ if (sectionNameNeedsQuoting(getSectionName()))
+ OS << "\t.section\t" << '"' << getSectionName() << '"' << ",\"";
+ else
+ OS << "\t.section\t" << getSectionName() << ",\"";
if (getKind().isText())
OS << 'x';
if (getKind().isWriteable())
Modified: llvm/trunk/lib/MC/MCSymbol.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/MC/MCSymbol.cpp?rev=192758&r1=192757&r2=192758&view=diff
==============================================================================
--- llvm/trunk/lib/MC/MCSymbol.cpp (original)
+++ llvm/trunk/lib/MC/MCSymbol.cpp Tue Oct 15 20:20:40 2013
@@ -18,12 +18,10 @@ const MCSection *MCSymbol::AbsolutePseud
reinterpret_cast<const MCSection *>(1);
static bool isAcceptableChar(char C) {
- if ((C < 'a' || C > 'z') &&
- (C < 'A' || C > 'Z') &&
- (C < '0' || C > '9') &&
- C != '_' && C != '$' && C != '.' && C != '@')
- return false;
- return true;
+ return (C >= 'a' && C <= 'z') ||
+ (C >= 'A' && C <= 'Z') ||
+ (C >= '0' && C <= '9') ||
+ C == '_' || C == '$' || C == '.';
}
/// NameNeedsQuoting - Return true if the identifier \p Str needs quotes to be
Modified: llvm/trunk/test/CodeGen/X86/coff-feat00.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/coff-feat00.ll?rev=192758&r1=192757&r2=192758&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/coff-feat00.ll (original)
+++ llvm/trunk/test/CodeGen/X86/coff-feat00.ll Tue Oct 15 20:20:40 2013
@@ -4,4 +4,4 @@ define i32 @foo() {
ret i32 0
}
-; CHECK: @feat.00 = 1
+; CHECK: "@feat.00" = 1
Modified: llvm/trunk/test/CodeGen/X86/fastcall-correct-mangling.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/fastcall-correct-mangling.ll?rev=192758&r1=192757&r2=192758&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/fastcall-correct-mangling.ll (original)
+++ llvm/trunk/test/CodeGen/X86/fastcall-correct-mangling.ll Tue Oct 15 20:20:40 2013
@@ -3,7 +3,7 @@
; Check that a fastcall function gets correct mangling
define x86_fastcallcc void @func(i64 %X, i8 %Y, i8 %G, i16 %Z) {
-; CHECK: @func at 20:
+; CHECK: "@func at 20":
ret void
}
Modified: llvm/trunk/test/CodeGen/X86/stdcall.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/stdcall.ll?rev=192758&r1=192757&r2=192758&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/stdcall.ll (original)
+++ llvm/trunk/test/CodeGen/X86/stdcall.ll Tue Oct 15 20:20:40 2013
@@ -5,7 +5,7 @@
define internal x86_stdcallcc void @MyFunc() nounwind {
entry:
-; CHECK: MyFunc at 0:
+; CHECK: "_MyFunc at 0":
; CHECK: ret
ret void
}
@@ -20,5 +20,5 @@ entry:
@B = global %0 { void (...)* bitcast (void ()* @MyFunc to void (...)*) }, align 4
; CHECK: _B:
-; CHECK: .long _MyFunc at 0
+; CHECK: .long "_MyFunc at 0"
Added: llvm/trunk/test/MC/COFF/quoted-names.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/MC/COFF/quoted-names.ll?rev=192758&view=auto
==============================================================================
--- llvm/trunk/test/MC/COFF/quoted-names.ll (added)
+++ llvm/trunk/test/MC/COFF/quoted-names.ll Tue Oct 15 20:20:40 2013
@@ -0,0 +1,20 @@
+; Check that certain symbol and section names are quoted in the asm output.
+; RUN: llc -mtriple=i686-pc-win32 %s -o - | FileCheck %s
+
+; Check that the symbol and section names can round-trip through the assembler.
+; RUN: llc -mtriple=i686-pc-win32 %s -o - | llvm-mc -triple i686-pc-win32 -filetype=obj | llvm-readobj -s -section-symbols | FileCheck %s --check-prefix=READOBJ
+
+@"\01??__E_Generic_object@?$_Error_objects at H@std@@YAXXZ" = global i32 0
+
+define weak i32 @"\01??_B?$num_put at _WV?$back_insert_iterator at V?$basic_string at _WU?$char_traits at _W@std@@V?$allocator at _W@2@@std@@@std@@@std@@51"() section ".text" {
+ %res = load i32* @"\01??__E_Generic_object@?$_Error_objects at H@std@@YAXXZ"
+ ret i32 %res
+}
+
+; CHECK: .section ".text$??_B?$num_put at _WV?$back_insert_iterator at V?$basic_string at _WU?$char_traits at _W@std@@V?$allocator at _W@2@@std@@@std@@@std@@51","xr"
+; CHECK: .globl "??_B?$num_put at _WV?$back_insert_iterator at V?$basic_string at _WU?$char_traits at _W@std@@V?$allocator at _W@2@@std@@@std@@@std@@51"
+; CHECK: "??_B?$num_put at _WV?$back_insert_iterator at V?$basic_string at _WU?$char_traits at _W@std@@V?$allocator at _W@2@@std@@@std@@@std@@51"
+
+; READOBJ: Symbol
+; READOBJ: Name: ??_B?$num_put at _WV?$back_insert_iterator at V?$basic_string at _WU?$char_traits at _W@std@@V?$allocator at _W@2@@std@@@std@@@std@@51
+; READOBJ: Section: .text$??_B?$num_put at _WV?$back_insert_iterator at V?$basic_string at _WU?$char_traits at _W@std@@V?$allocator at _W@2@@std@@@std@@@std@@51
More information about the llvm-commits
mailing list