maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/MC/MCExpr.cpp

705 lines
24 KiB
C++
Raw Normal View History

llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
//===- MCExpr.cpp - Assembly Level Expression Implementation --------------===//
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
MC: Sprinkle in some more interesting statistics. llvm-svn: 99350
2010-03-24 07:47:14 +08:00
#define DEBUG_TYPE "mcexpr"
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
#include "llvm/MC/MCExpr.h"
MC: Sprinkle in some more interesting statistics. llvm-svn: 99350
2010-03-24 07:47:14 +08:00
#include "llvm/ADT/Statistic.h"
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
#include "llvm/ADT/StringSwitch.h"
MC/Mach-O: Implement "absolutizing" semantics of .set, by evaluating the assembly time value of variables. llvm-svn: 98241
2010-03-11 13:53:37 +08:00
#include "llvm/MC/MCAsmLayout.h"
#include "llvm/MC/MCAssembler.h"
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
#include "llvm/MC/MCContext.h"
Prune some includes and forward declarations. llvm-svn: 153429
2012-03-26 14:58:25 +08:00
#include "llvm/MC/MCObjectWriter.h"
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
#include "llvm/MC/MCSymbol.h"
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
#include "llvm/MC/MCValue.h"
Change errs() to dbgs(). llvm-svn: 92630
2010-01-05 09:28:07 +08:00
#include "llvm/Support/Debug.h"
Add 'llvm_unreachable' to passify GCC's understanding of the constraints of several newly un-defaulted switches. This also helps optimizers (including LLVM's) recognize that every case is covered, and we should assume as much. llvm-svn: 147861
2012-01-11 02:08:01 +08:00
#include "llvm/Support/ErrorHandling.h"
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
#include "llvm/Support/raw_ostream.h"
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
using namespace llvm;
MC: Sprinkle in some more interesting statistics. llvm-svn: 99350
2010-03-24 07:47:14 +08:00
namespace {
namespace stats {
STATISTIC(MCExprEvaluate, "Number of MCExpr evaluations");
}
}
remove the MAI argument to MCExpr::print and switch overthing to use << when printing them. llvm-svn: 93699
2010-01-18 08:37:40 +08:00
void MCExpr::print(raw_ostream &OS) const {
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
switch (getKind()) {
add scaffolding for target-specific MCExprs. llvm-svn: 95559
2010-02-09 03:41:07 +08:00
case MCExpr::Target:
return cast<MCTargetExpr>(this)->PrintImpl(OS);
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
case MCExpr::Constant:
OS << cast<MCConstantExpr>(*this).getValue();
return;
parenthesize symbol names that start with $, fixing X86/dollar-name.ll with the new asmprinter. llvm-svn: 81269
2009-09-09 07:20:50 +08:00
case MCExpr::SymbolRef: {
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
const MCSymbolRefExpr &SRE = cast<MCSymbolRefExpr>(*this);
const MCSymbol &Sym = SRE.getSymbol();
add targetoperand flags for jump tables, constant pool and block address nodes to indicate when ha16/lo16 modifiers should be used. This lets us pass PowerPC/indirectbr.ll. The one annoying thing about this patch is that the MCSymbolExpr isn't expressive enough to represent ha16(label1-label2) which we need on PowerPC. I have a terrible hack in the meantime, but this will have to be revisited at some point. Last major conversion item left is global variable references. llvm-svn: 119105
2010-11-15 10:46:57 +08:00
// Parenthesize names that start with $ so that they don't look like
// absolute names.
bool UseParens = Sym.getName()[0] == '$';
if (UseParens)
now that MCSymbol::print doesn't use it's MAI argument, we can remove it and change all the code that prints MCSymbols to use << instead, which is much simpler and cleaner. llvm-svn: 93695
2010-01-18 05:43:43 +08:00
OS << '(' << Sym << ')';
else
OS << Sym;
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
Add ARM NONE and PREL31 relocation types. Add R_ARM_NONE and R_ARM_PREL31 relocation types to MCExpr. Both of them will be used while generating .ARM.extab and .ARM.exidx sections. llvm-svn: 169965
2012-12-12 15:14:46 +08:00
if (SRE.getKind() == MCSymbolRefExpr::VK_ARM_NONE ||
SRE.getKind() == MCSymbolRefExpr::VK_ARM_PLT ||
Update ARMConstantPoolValue to not use a modifier string. Use an explicit VariantKind marker to indicate the additional information necessary. Update MC to handle the new Kinds. rdar://8647623 llvm-svn: 118671
2010-11-10 11:26:07 +08:00
SRE.getKind() == MCSymbolRefExpr::VK_ARM_TLSGD ||
SRE.getKind() == MCSymbolRefExpr::VK_ARM_GOT ||
SRE.getKind() == MCSymbolRefExpr::VK_ARM_GOTOFF ||
SRE.getKind() == MCSymbolRefExpr::VK_ARM_TPOFF ||
Add support for the R_ARM_TARGET1 relocation, which should be given to relocations applied to all C++ constructors and destructors. This enables the linker to match concrete relocation types (absolute or relative) with whatever library or C++ support code is being linked against. llvm-svn: 149057
2012-01-26 17:25:43 +08:00
SRE.getKind() == MCSymbolRefExpr::VK_ARM_GOTTPOFF ||
Add ARM TARGET2 relocation. The testcase will follow with actualy use-case. Based on the patch by Logan Chien! llvm-svn: 167633
2012-11-10 04:20:12 +08:00
SRE.getKind() == MCSymbolRefExpr::VK_ARM_TARGET1 ||
Add ARM NONE and PREL31 relocation types. Add R_ARM_NONE and R_ARM_PREL31 relocation types to MCExpr. Both of them will be used while generating .ARM.extab and .ARM.exidx sections. llvm-svn: 169965
2012-12-12 15:14:46 +08:00
SRE.getKind() == MCSymbolRefExpr::VK_ARM_TARGET2 ||
SRE.getKind() == MCSymbolRefExpr::VK_ARM_PREL31)
Add support for ELF PLT references for ARM MC asm printing. Adding a new VariantKind to the MCSymbolExpr seems like overkill, but I'm not sure there's a more straightforward way to get the printing difference captured. (i.e., x86 uses @PLT, ARM uses (PLT)). llvm-svn: 114613
2010-09-23 07:27:36 +08:00
OS << MCSymbolRefExpr::getVariantKindName(SRE.getKind());
[PowerPC] Clean up generation of ha16() / lo16() markers When targeting the Darwin assembler, we need to generate markers ha16() and lo16() to designate the high and low parts of a (symbolic) immediate. This is necessary not just for plain symbols, but also for certain symbolic expression, typically along the lines of ha16(A - B). The latter doesn't work when simply using VariantKind flags on the symbol reference. This is why the current back-end uses hacks (explicitly called out as such via multiple FIXMEs) in the symbolLo/symbolHi print methods. This patch uses target-defined MCExpr codes to represent the Darwin ha16/lo16 constructs, following along the lines of the equivalent solution used by the ARM back end to handle their :upper16: / :lower16: markers. This allows us to get rid of special handling both in the symbolLo/symbolHi print method and in the common code MCExpr::print routine. Instead, the ha16 / lo16 markers are printed simply in a custom print routine for the target MCExpr types. (As a result, the symbolLo/symbolHi print methods can now replaced by a single printS16ImmOperand routine that also handles symbolic operands.) The patch also provides a EvaluateAsRelocatableImpl routine to handle ha16/lo16 constructs. This is not actually used at the moment by any in-tree code, but is provided as it makes merging into David Fang's out-of-tree Mach-O object writer simpler. Since there is no longer any need to treat VK_PPC_GAS_HA16 and VK_PPC_DARWIN_HA16 differently, they are merged into a single VK_PPC_ADDR16_HA (and likewise for the _LO16 types). llvm-svn: 182616
2013-05-24 06:26:41 +08:00
else if (SRE.getKind() != MCSymbolRefExpr::VK_None)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
OS << '@' << MCSymbolRefExpr::getVariantKindName(SRE.getKind());
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
return;
parenthesize symbol names that start with $, fixing X86/dollar-name.ll with the new asmprinter. llvm-svn: 81269
2009-09-09 07:20:50 +08:00
}
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
case MCExpr::Unary: {
const MCUnaryExpr &UE = cast<MCUnaryExpr>(*this);
switch (UE.getOpcode()) {
case MCUnaryExpr::LNot: OS << '!'; break;
case MCUnaryExpr::Minus: OS << '-'; break;
case MCUnaryExpr::Not: OS << '~'; break;
case MCUnaryExpr::Plus: OS << '+'; break;
}
remove the MAI argument to MCExpr::print and switch overthing to use << when printing them. llvm-svn: 93699
2010-01-18 08:37:40 +08:00
OS << *UE.getSubExpr();
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
return;
}
case MCExpr::Binary: {
const MCBinaryExpr &BE = cast<MCBinaryExpr>(*this);
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
make formatting of expressions more closely match the existing asmprinter. llvm-svn: 81202
2009-09-08 14:34:07 +08:00
// Only print parens around the LHS if it is non-trivial.
if (isa<MCConstantExpr>(BE.getLHS()) || isa<MCSymbolRefExpr>(BE.getLHS())) {
remove the MAI argument to MCExpr::print and switch overthing to use << when printing them. llvm-svn: 93699
2010-01-18 08:37:40 +08:00
OS << *BE.getLHS();
make formatting of expressions more closely match the existing asmprinter. llvm-svn: 81202
2009-09-08 14:34:07 +08:00
} else {
remove the MAI argument to MCExpr::print and switch overthing to use << when printing them. llvm-svn: 93699
2010-01-18 08:37:40 +08:00
OS << '(' << *BE.getLHS() << ')';
make formatting of expressions more closely match the existing asmprinter. llvm-svn: 81202
2009-09-08 14:34:07 +08:00
}
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
switch (BE.getOpcode()) {
Print "X-42" instead of "X+-42". llvm-svn: 81203
2009-09-08 14:37:35 +08:00
case MCBinaryExpr::Add:
// Print "X-42" instead of "X+-42".
if (const MCConstantExpr *RHSC = dyn_cast<MCConstantExpr>(BE.getRHS())) {
if (RHSC->getValue() < 0) {
OS << RHSC->getValue();
return;
}
}
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
Print "X-42" instead of "X+-42". llvm-svn: 81203
2009-09-08 14:37:35 +08:00
OS << '+';
break;
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
case MCBinaryExpr::And: OS << '&'; break;
case MCBinaryExpr::Div: OS << '/'; break;
case MCBinaryExpr::EQ: OS << "=="; break;
case MCBinaryExpr::GT: OS << '>'; break;
case MCBinaryExpr::GTE: OS << ">="; break;
case MCBinaryExpr::LAnd: OS << "&&"; break;
case MCBinaryExpr::LOr: OS << "||"; break;
case MCBinaryExpr::LT: OS << '<'; break;
case MCBinaryExpr::LTE: OS << "<="; break;
case MCBinaryExpr::Mod: OS << '%'; break;
case MCBinaryExpr::Mul: OS << '*'; break;
case MCBinaryExpr::NE: OS << "!="; break;
case MCBinaryExpr::Or: OS << '|'; break;
case MCBinaryExpr::Shl: OS << "<<"; break;
case MCBinaryExpr::Shr: OS << ">>"; break;
case MCBinaryExpr::Sub: OS << '-'; break;
case MCBinaryExpr::Xor: OS << '^'; break;
}
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
make formatting of expressions more closely match the existing asmprinter. llvm-svn: 81202
2009-09-08 14:34:07 +08:00
// Only print parens around the LHS if it is non-trivial.
if (isa<MCConstantExpr>(BE.getRHS()) || isa<MCSymbolRefExpr>(BE.getRHS())) {
remove the MAI argument to MCExpr::print and switch overthing to use << when printing them. llvm-svn: 93699
2010-01-18 08:37:40 +08:00
OS << *BE.getRHS();
make formatting of expressions more closely match the existing asmprinter. llvm-svn: 81202
2009-09-08 14:34:07 +08:00
} else {
remove the MAI argument to MCExpr::print and switch overthing to use << when printing them. llvm-svn: 93699
2010-01-18 08:37:40 +08:00
OS << '(' << *BE.getRHS() << ')';
make formatting of expressions more closely match the existing asmprinter. llvm-svn: 81202
2009-09-08 14:34:07 +08:00
}
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
return;
}
}
Convert assert(0) to llvm_unreachable llvm-svn: 149967
2012-02-07 13:05:23 +08:00
llvm_unreachable("Invalid expression kind!");
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
}
Release build: guard dump functions with "#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)" No functional change. Update r163344. llvm-svn: 163679
2012-09-12 13:06:18 +08:00
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
void MCExpr::dump() const {
remove the MAI argument to MCExpr::print and switch overthing to use << when printing them. llvm-svn: 93699
2010-01-18 08:37:40 +08:00
print(dbgs());
Change errs() to dbgs(). llvm-svn: 92630
2010-01-05 09:28:07 +08:00
dbgs() << '\n';
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
}
Release build: guard dump functions with "ifndef NDEBUG" No functional change. llvm-svn: 163344
2012-09-07 03:55:56 +08:00
#endif
llvm-mc: Add MCExpr::{dump,print}. llvm-svn: 80570
2009-08-31 16:07:33 +08:00
/* *** */
tidy whitespace. llvm-svn: 81201
2009-09-08 14:27:48 +08:00
const MCBinaryExpr *MCBinaryExpr::Create(Opcode Opc, const MCExpr *LHS,
const MCExpr *RHS, MCContext &Ctx) {
llvm-mc: Switch MCExpr construction to using static member functions, and taking the MCContext (which now owns all MCExprs). llvm-svn: 80569
2009-08-31 16:07:22 +08:00
return new (Ctx) MCBinaryExpr(Opc, LHS, RHS);
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
}
tidy whitespace. llvm-svn: 81201
2009-09-08 14:27:48 +08:00
const MCUnaryExpr *MCUnaryExpr::Create(Opcode Opc, const MCExpr *Expr,
MCContext &Ctx) {
llvm-mc: Switch MCExpr construction to using static member functions, and taking the MCContext (which now owns all MCExprs). llvm-svn: 80569
2009-08-31 16:07:22 +08:00
return new (Ctx) MCUnaryExpr(Opc, Expr);
}
const MCConstantExpr *MCConstantExpr::Create(int64_t Value, MCContext &Ctx) {
return new (Ctx) MCConstantExpr(Value);
}
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
/* *** */
llvm-mc: Switch MCExpr construction to using static member functions, and taking the MCContext (which now owns all MCExprs). llvm-svn: 80569
2009-08-31 16:07:22 +08:00
const MCSymbolRefExpr *MCSymbolRefExpr::Create(const MCSymbol *Sym,
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
VariantKind Kind,
llvm-mc: Switch MCExpr construction to using static member functions, and taking the MCContext (which now owns all MCExprs). llvm-svn: 80569
2009-08-31 16:07:22 +08:00
MCContext &Ctx) {
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
return new (Ctx) MCSymbolRefExpr(Sym, Kind);
llvm-mc: Switch MCExpr construction to using static member functions, and taking the MCContext (which now owns all MCExprs). llvm-svn: 80569
2009-08-31 16:07:22 +08:00
}
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
const MCSymbolRefExpr *MCSymbolRefExpr::Create(StringRef Name, VariantKind Kind,
MCContext &Ctx) {
return Create(Ctx.GetOrCreateSymbol(Name), Kind, Ctx);
add a helper method for creating MCSymbol and MCSymbolRefExpr at the same time. llvm-svn: 81984
2009-09-16 09:26:31 +08:00
}
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
StringRef MCSymbolRefExpr::getVariantKindName(VariantKind Kind) {
switch (Kind) {
case VK_Invalid: return "<<invalid>>";
case VK_None: return "<<none>>";
case VK_GOT: return "GOT";
case VK_GOTOFF: return "GOTOFF";
case VK_GOTPCREL: return "GOTPCREL";
case VK_GOTTPOFF: return "GOTTPOFF";
case VK_INDNTPOFF: return "INDNTPOFF";
case VK_NTPOFF: return "NTPOFF";
Implement VK_GOTNTPOFF and switch RelocNeedsGOT to use VariantKind. llvm-svn: 117543
2010-10-28 22:22:44 +08:00
case VK_GOTNTPOFF: return "GOTNTPOFF";
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
case VK_PLT: return "PLT";
case VK_TLSGD: return "TLSGD";
Implement TLSLD. llvm-svn: 117547
2010-10-28 23:02:40 +08:00
case VK_TLSLD: return "TLSLD";
Implement TLSLDM. llvm-svn: 117544
2010-10-28 22:37:09 +08:00
case VK_TLSLDM: return "TLSLDM";
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
case VK_TPOFF: return "TPOFF";
Implement DTPOFF. llvm-svn: 117546
2010-10-28 22:48:59 +08:00
case VK_DTPOFF: return "DTPOFF";
reimplement ppc asmprinter "toc" handling to use a VariantKind on the operand, required for .o file writing and fixing the PowerPC/mult-alt-generic-powerpc64.ll failure with the new instprinter. llvm-svn: 119087
2010-11-15 06:22:59 +08:00
case VK_TLVP: return "TLVP";
Change '@SECREL' suffix to GAS-compatible '@SECREL32'. '@SECREL' is what is used by the Microsoft assembler, but GNU as expects '@SECREL32'. With the patch, the MC-generated code works fine in combination with a recent GNU as (2.23.51.20120920 here). Patch by David Nadlinger! Differential Revision: http://llvm-reviews.chandlerc.com/D429 llvm-svn: 178427
2013-03-31 00:21:50 +08:00
case VK_SECREL: return "SECREL32";
Add ARM NONE and PREL31 relocation types. Add R_ARM_NONE and R_ARM_PREL31 relocation types to MCExpr. Both of them will be used while generating .ARM.extab and .ARM.exidx sections. llvm-svn: 169965
2012-12-12 15:14:46 +08:00
case VK_ARM_NONE: return "(NONE)";
Add support for ELF PLT references for ARM MC asm printing. Adding a new VariantKind to the MCSymbolExpr seems like overkill, but I'm not sure there's a more straightforward way to get the printing difference captured. (i.e., x86 uses @PLT, ARM uses (PLT)). llvm-svn: 114613
2010-09-23 07:27:36 +08:00
case VK_ARM_PLT: return "(PLT)";
Update ARMConstantPoolValue to not use a modifier string. Use an explicit VariantKind marker to indicate the additional information necessary. Update MC to handle the new Kinds. rdar://8647623 llvm-svn: 118671
2010-11-10 11:26:07 +08:00
case VK_ARM_GOT: return "(GOT)";
case VK_ARM_GOTOFF: return "(GOTOFF)";
case VK_ARM_TPOFF: return "(tpoff)";
case VK_ARM_GOTTPOFF: return "(gottpoff)";
Fix typo. llvm-svn: 119542
2010-11-18 03:30:11 +08:00
case VK_ARM_TLSGD: return "(tlsgd)";
Add support for the R_ARM_TARGET1 relocation, which should be given to relocations applied to all C++ constructors and destructors. This enables the linker to match concrete relocation types (absolute or relative) with whatever library or C++ support code is being linked against. llvm-svn: 149057
2012-01-26 17:25:43 +08:00
case VK_ARM_TARGET1: return "(target1)";
Add ARM TARGET2 relocation. The testcase will follow with actualy use-case. Based on the patch by Logan Chien! llvm-svn: 167633
2012-11-10 04:20:12 +08:00
case VK_ARM_TARGET2: return "(target2)";
Add ARM NONE and PREL31 relocation types. Add R_ARM_NONE and R_ARM_PREL31 relocation types to MCExpr. Both of them will be used while generating .ARM.extab and .ARM.exidx sections. llvm-svn: 169965
2012-12-12 15:14:46 +08:00
case VK_ARM_PREL31: return "(prel31)";
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
case VK_PPC_LO: return "l";
[PowerPC] Support @h modifier This adds necessary infrastructure to support the @h modifier. Note that all required relocation types were already present (and unused). This patch provides support for using @h in the assembler; it would also be possible to now use this feature in code generated by the compiler, but this is not done yet. llvm-svn: 184548
2013-06-21 22:42:49 +08:00
case VK_PPC_HI: return "h";
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
case VK_PPC_HA: return "ha";
[PowerPC] Support @higher et.al. modifiers This adds support for the @higher, @highera, @highest, and @highesta modifers, including some missing relocation types. llvm-svn: 184550
2013-06-21 22:43:42 +08:00
case VK_PPC_HIGHER: return "higher";
case VK_PPC_HIGHERA: return "highera";
case VK_PPC_HIGHEST: return "highest";
case VK_PPC_HIGHESTA: return "highesta";
[PowerPC] Clean up VK_PPC_TOC... names This is another minor cleanup; to bring enum names in line with the corresponding @modifier names, this renames: VK_PPC_TOC -> VK_PPC_TOCBASE VK_PPC_TOC_ENTRY -> VK_PPC_TOC16 No code change intended. llvm-svn: 184491
2013-06-21 06:39:42 +08:00
case VK_PPC_TOCBASE: return "tocbase";
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
case VK_PPC_TOC: return "toc";
case VK_PPC_TOC_LO: return "toc@l";
[PowerPC] Support @toc@h modifier This adds the relocation type and other necessary infrastructure to use the @toc@h modifier in the assembler. llvm-svn: 184549
2013-06-21 22:43:10 +08:00
case VK_PPC_TOC_HI: return "toc@h";
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
case VK_PPC_TOC_HA: return "toc@ha";
case VK_PPC_TPREL_LO: return "tprel@l";
case VK_PPC_TPREL_HA: return "tprel@ha";
case VK_PPC_DTPREL_LO: return "dtprel@l";
case VK_PPC_DTPREL_HA: return "dtprel@ha";
case VK_PPC_GOT_TPREL_LO: return "got@tprel@l";
case VK_PPC_GOT_TPREL_HA: return "got@tprel@ha";
This patch introduces initial-exec model support for thread-local storage on 64-bit PowerPC ELF. The patch includes code to handle external assembly and MC output with the integrated assembler. It intentionally does not support the "old" JIT. For the initial-exec TLS model, the ABI requires the following to calculate the address of external thread-local variable x: Code sequence Relocation Symbol ld 9,x@got@tprel(2) R_PPC64_GOT_TPREL16_DS x add 9,9,x@tls R_PPC64_TLS x The register 9 is arbitrary here. The linker will replace x@got@tprel with the offset relative to the thread pointer to the generated GOT entry for symbol x. It will replace x@tls with the thread-pointer register (13). The two test cases verify correct assembly output and relocation output as just described. PowerPC-specific selection node variants are added for the two instructions above: LD_GOT_TPREL and ADD_TLS. These are inserted when an initial-exec global variable is encountered by PPCTargetLowering::LowerGlobalTLSAddress(), and later lowered to machine instructions LDgotTPREL and ADD8TLS. LDgotTPREL is a pseudo that uses the same LDrs support added for medium code model's LDtocL, with a different relocation type. The rest of the processing is straightforward. llvm-svn: 169281
2012-12-05 00:18:08 +08:00
case VK_PPC_TLS: return "tls";
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
case VK_PPC_GOT_TLSGD_LO: return "got@tlsgd@l";
case VK_PPC_GOT_TLSGD_HA: return "got@tlsgd@ha";
This patch implements the general dynamic TLS model for 64-bit PowerPC. Given a thread-local symbol x with global-dynamic access, the generated code to obtain x's address is: Instruction Relocation Symbol addis ra,r2,x@got@tlsgd@ha R_PPC64_GOT_TLSGD16_HA x addi r3,ra,x@got@tlsgd@l R_PPC64_GOT_TLSGD16_L x bl __tls_get_addr(x@tlsgd) R_PPC64_TLSGD x R_PPC64_REL24 __tls_get_addr nop <use address in r3> The implementation borrows from the medium code model work for introducing special forms of ADDIS and ADDI into the DAG representation. This is made slightly more complicated by having to introduce a call to the external function __tls_get_addr. Using the full call machinery is overkill and, more importantly, makes it difficult to add a special relocation. So I've introduced another opcode GET_TLS_ADDR to represent the function call, and surrounded it with register copies to set up the parameter and return value. Most of the code is pretty straightforward. I ran into one peculiarity when I introduced a new PPC opcode BL8_NOP_ELF_TLSGD, which is just like BL8_NOP_ELF except that it takes another parameter to represent the symbol ("x" above) that requires a relocation on the call. Something in the TblGen machinery causes BL8_NOP_ELF and BL8_NOP_ELF_TLSGD to be treated identically during the emit phase, so this second operand was never visited to generate relocations. This is the reason for the slightly messy workaround in PPCMCCodeEmitter.cpp:getDirectBrEncoding(). Two new tests are included to demonstrate correct external assembly and correct generation of relocations using the integrated assembler. Comments welcome! Thanks, Bill llvm-svn: 169910
2012-12-12 04:30:11 +08:00
case VK_PPC_TLSGD: return "tlsgd";
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
case VK_PPC_GOT_TLSLD_LO: return "got@tlsld@l";
case VK_PPC_GOT_TLSLD_HA: return "got@tlsld@ha";
This patch implements local-dynamic TLS model support for the 64-bit PowerPC target. This is the last of the four models, so we now have full TLS support. This is mostly a straightforward extension of the general dynamic model. I had to use an additional Chain operand to tie ADDIS_DTPREL_HA to the register copy following ADDI_TLSLD_L; otherwise everything above the ADDIS_DTPREL_HA appeared dead and was removed. As before, there are new test cases to test the assembly generation, and the relocations output during integrated assembly. The expected code gen sequence can be read in test/CodeGen/PowerPC/tls-ld.ll. There are a couple of things I think can be done more efficiently in the overall TLS code, so there will likely be a clean-up patch forthcoming; but for now I want to be sure the functionality is in place. Bill llvm-svn: 170003
2012-12-13 03:29:35 +08:00
case VK_PPC_TLSLD: return "tlsld";
Local dynamic TLS model for direct object output. Create the correct TLS MIPS ELF relocations. Patch by Jack Carter. llvm-svn: 147118
2011-12-22 09:05:17 +08:00
case VK_Mips_GPREL: return "GPREL";
case VK_Mips_GOT_CALL: return "GOT_CALL";
case VK_Mips_GOT16: return "GOT16";
case VK_Mips_GOT: return "GOT";
case VK_Mips_ABS_HI: return "ABS_HI";
case VK_Mips_ABS_LO: return "ABS_LO";
case VK_Mips_TLSGD: return "TLSGD";
case VK_Mips_TLSLDM: return "TLSLDM";
case VK_Mips_DTPREL_HI: return "DTPREL_HI";
case VK_Mips_DTPREL_LO: return "DTPREL_LO";
case VK_Mips_GOTTPREL: return "GOTTPREL";
case VK_Mips_TPREL_HI: return "TPREL_HI";
case VK_Mips_TPREL_LO: return "TPREL_LO";
case VK_Mips_GPOFF_HI: return "GPOFF_HI";
case VK_Mips_GPOFF_LO: return "GPOFF_LO";
case VK_Mips_GOT_DISP: return "GOT_DISP";
case VK_Mips_GOT_PAGE: return "GOT_PAGE";
case VK_Mips_GOT_OFST: return "GOT_OFST";
Add VK_Mips_HIGHER and VK_Mips_HIGHEST to MCSymbolRefExpr::VariantKind. Test case will be added later when long branch patch is checked in. llvm-svn: 160597
2012-07-21 10:15:19 +08:00
case VK_Mips_HIGHER: return "HIGHER";
case VK_Mips_HIGHEST: return "HIGHEST";
Add relocations used for mips big GOT. llvm-svn: 168448
2012-11-22 03:50:22 +08:00
case VK_Mips_GOT_HI16: return "GOT_HI16";
case VK_Mips_GOT_LO16: return "GOT_LO16";
case VK_Mips_CALL_HI16: return "CALL_HI16";
case VK_Mips_CALL_LO16: return "CALL_LO16";
MC: Support COFF image-relative MCSymbolRefs Add support for the COFF relocation types IMAGE_REL_I386_DIR32NB and IMAGE_REL_AMD64_ADDR32NB for 32- and 64-bit respectively. These are similar to normal 4-byte relocations except that they do not include the base address of the image. Image-relative relocations are used for debug information (32-bit) and SEH unwind tables (64-bit). A new MCSymbolRef variant called 'VK_COFF_IMGREL32' is introduced to specify such relocations. For AT&T assembly, this variant can be accessed using the symbol suffix '@imgrel'. llvm-svn: 179240
2013-04-11 07:28:17 +08:00
case VK_COFF_IMGREL32: return "IMGREL32";
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
}
Add 'llvm_unreachable' to passify GCC's understanding of the constraints of several newly un-defaulted switches. This also helps optimizers (including LLVM's) recognize that every case is covered, and we should assume as much. llvm-svn: 147861
2012-01-11 02:08:01 +08:00
llvm_unreachable("Invalid variant kind");
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
}
MCSymbolRefExpr::VariantKind
MCSymbolRefExpr::getVariantKindForName(StringRef Name) {
return StringSwitch<VariantKind>(Name)
.Case("GOT", VK_GOT)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("got", VK_GOT)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Case("GOTOFF", VK_GOTOFF)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("gotoff", VK_GOTOFF)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Case("GOTPCREL", VK_GOTPCREL)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("gotpcrel", VK_GOTPCREL)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Case("GOTTPOFF", VK_GOTTPOFF)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("gottpoff", VK_GOTTPOFF)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Case("INDNTPOFF", VK_INDNTPOFF)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("indntpoff", VK_INDNTPOFF)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Case("NTPOFF", VK_NTPOFF)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("ntpoff", VK_NTPOFF)
Implement VK_GOTNTPOFF and switch RelocNeedsGOT to use VariantKind. llvm-svn: 117543
2010-10-28 22:22:44 +08:00
.Case("GOTNTPOFF", VK_GOTNTPOFF)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("gotntpoff", VK_GOTNTPOFF)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Case("PLT", VK_PLT)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("plt", VK_PLT)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Case("TLSGD", VK_TLSGD)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("tlsgd", VK_TLSGD)
Implement TLSLD. llvm-svn: 117547
2010-10-28 23:02:40 +08:00
.Case("TLSLD", VK_TLSLD)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("tlsld", VK_TLSLD)
Implement TLSLDM. llvm-svn: 117544
2010-10-28 22:37:09 +08:00
.Case("TLSLDM", VK_TLSLDM)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("tlsldm", VK_TLSLDM)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Case("TPOFF", VK_TPOFF)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("tpoff", VK_TPOFF)
Implement DTPOFF. llvm-svn: 117546
2010-10-28 22:48:59 +08:00
.Case("DTPOFF", VK_DTPOFF)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("dtpoff", VK_DTPOFF)
Start adding mach-o tls reloc support. llvm-svn: 104651
2010-05-26 08:02:12 +08:00
.Case("TLVP", VK_TLVP)
Add support for lowercase variants. llvm-svn: 124071
2011-01-24 00:11:25 +08:00
.Case("tlvp", VK_TLVP)
MC: Support COFF image-relative MCSymbolRefs Add support for the COFF relocation types IMAGE_REL_I386_DIR32NB and IMAGE_REL_AMD64_ADDR32NB for 32- and 64-bit respectively. These are similar to normal 4-byte relocations except that they do not include the base address of the image. Image-relative relocations are used for debug information (32-bit) and SEH unwind tables (64-bit). A new MCSymbolRef variant called 'VK_COFF_IMGREL32' is introduced to specify such relocations. For AT&T assembly, this variant can be accessed using the symbol suffix '@imgrel'. llvm-svn: 179240
2013-04-11 07:28:17 +08:00
.Case("IMGREL", VK_COFF_IMGREL32)
.Case("imgrel", VK_COFF_IMGREL32)
Fix section relocation for SECTIONREL32 with immediate offset. Patch by Kai Nacke. This matches the gnu as output. llvm-svn: 180568
2013-04-26 03:27:05 +08:00
.Case("SECREL32", VK_SECREL)
.Case("secrel32", VK_SECREL)
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
.Case("L", VK_PPC_LO)
.Case("l", VK_PPC_LO)
[PowerPC] Support @h modifier This adds necessary infrastructure to support the @h modifier. Note that all required relocation types were already present (and unused). This patch provides support for using @h in the assembler; it would also be possible to now use this feature in code generated by the compiler, but this is not done yet. llvm-svn: 184548
2013-06-21 22:42:49 +08:00
.Case("H", VK_PPC_HI)
.Case("h", VK_PPC_HI)
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
.Case("HA", VK_PPC_HA)
.Case("ha", VK_PPC_HA)
[PowerPC] Support @higher et.al. modifiers This adds support for the @higher, @highera, @highest, and @highesta modifers, including some missing relocation types. llvm-svn: 184550
2013-06-21 22:43:42 +08:00
.Case("HIGHER", VK_PPC_HIGHER)
.Case("higher", VK_PPC_HIGHER)
.Case("HIGHERA", VK_PPC_HIGHERA)
.Case("highera", VK_PPC_HIGHERA)
.Case("HIGHEST", VK_PPC_HIGHEST)
.Case("highest", VK_PPC_HIGHEST)
.Case("HIGHESTA", VK_PPC_HIGHESTA)
.Case("highesta", VK_PPC_HIGHESTA)
[PowerPC] Clean up VK_PPC_TOC... names This is another minor cleanup; to bring enum names in line with the corresponding @modifier names, this renames: VK_PPC_TOC -> VK_PPC_TOCBASE VK_PPC_TOC_ENTRY -> VK_PPC_TOC16 No code change intended. llvm-svn: 184491
2013-06-21 06:39:42 +08:00
.Case("TOCBASE", VK_PPC_TOCBASE)
.Case("tocbase", VK_PPC_TOCBASE)
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
.Case("TOC", VK_PPC_TOC)
.Case("toc", VK_PPC_TOC)
.Case("TOC@L", VK_PPC_TOC_LO)
.Case("toc@l", VK_PPC_TOC_LO)
[PowerPC] Support @toc@h modifier This adds the relocation type and other necessary infrastructure to use the @toc@h modifier in the assembler. llvm-svn: 184549
2013-06-21 22:43:10 +08:00
.Case("TOC@H", VK_PPC_TOC_HI)
.Case("toc@h", VK_PPC_TOC_HI)
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
.Case("TOC@HA", VK_PPC_TOC_HA)
.Case("toc@ha", VK_PPC_TOC_HA)
[PowerPC] Parse platform-specifc variant kinds in AsmParser This patch adds support for PowerPC platform-specific variant kinds in MCSymbolRefExpr::getVariantKindForName, and also adds a test case to verify they are translated to the appropriate fixup type. llvm-svn: 181053
2013-05-04 03:52:35 +08:00
.Case("TLS", VK_PPC_TLS)
.Case("tls", VK_PPC_TLS)
[PowerPC] Rename some more VK_PPC_ enums This renames more VK_PPC_ enums, to make them more closely reflect the @modifier string they represent. This also prepares for adding a bunch of new VK_PPC_ enums in upcoming patches. For consistency, some MO_ flags related to VK_PPC_ enums are likewise renamed. No change in behaviour. llvm-svn: 184547
2013-06-21 22:42:20 +08:00
.Case("TPREL@L", VK_PPC_TPREL_LO)
.Case("tprel@l", VK_PPC_TPREL_LO)
.Case("TPREL@HA", VK_PPC_TPREL_HA)
.Case("tprel@ha", VK_PPC_TPREL_HA)
.Case("DTPREL@L", VK_PPC_DTPREL_LO)
.Case("dtprel@l", VK_PPC_DTPREL_LO)
.Case("DTPREL@HA", VK_PPC_DTPREL_HA)
.Case("dtprel@ha", VK_PPC_DTPREL_HA)
.Case("GOT@TPREL@L", VK_PPC_GOT_TPREL_LO)
.Case("got@tprel@l", VK_PPC_GOT_TPREL_LO)
.Case("GOT@TPREL@HA", VK_PPC_GOT_TPREL_HA)
.Case("got@tprel@ha", VK_PPC_GOT_TPREL_HA)
.Case("GOT@TLSGD@L", VK_PPC_GOT_TLSGD_LO)
.Case("got@tlsgd@l", VK_PPC_GOT_TLSGD_LO)
.Case("GOT@TLSGD@HA", VK_PPC_GOT_TLSGD_HA)
.Case("got@tlsgd@ha", VK_PPC_GOT_TLSGD_HA)
.Case("GOT@TLSLD@L", VK_PPC_GOT_TLSLD_LO)
.Case("got@tlsld@l", VK_PPC_GOT_TLSLD_LO)
.Case("GOT@TLSLD@HA", VK_PPC_GOT_TLSLD_HA)
.Case("got@tlsld@ha", VK_PPC_GOT_TLSLD_HA)
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
.Default(VK_Invalid);
set the temporary bit on MCSymbols correctly. llvm-svn: 98124
2010-03-10 10:25:11 +08:00
}
MC: Allow modifiers in MCSymbolRefExpr, and eliminate X86MCTargetExpr. - Although it would be nice to allow this decoupling, the assembler needs to be able to reason about MCSymbolRefExprs in too many places to make this viable. We can use a target specific encoding of the variant if this becomes an issue. - This patch also extends llvm-mc to support parsing of the modifiers, as opposed to lumping them in with the symbol. llvm-svn: 98592
2010-03-16 07:51:06 +08:00
/* *** */
Rename virtual table anchors from Anchor() to anchor() for consistency with the rest of the tree. llvm-svn: 164666
2012-09-26 14:36:36 +08:00
void MCTargetExpr::anchor() {}
add a helper method for creating MCSymbol and MCSymbolRefExpr at the same time. llvm-svn: 81984
2009-09-16 09:26:31 +08:00
llvm-mc: Switch MCExpr construction to using static member functions, and taking the MCContext (which now owns all MCExprs). llvm-svn: 80569
2009-08-31 16:07:22 +08:00
/* *** */
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
bool MCExpr::EvaluateAsAbsolute(int64_t &Res) const {
return EvaluateAsAbsolute(Res, 0, 0, 0);
}
bool MCExpr::EvaluateAsAbsolute(int64_t &Res,
const MCAsmLayout &Layout) const {
return EvaluateAsAbsolute(Res, &Layout.getAssembler(), &Layout, 0);
}
bool MCExpr::EvaluateAsAbsolute(int64_t &Res,
const MCAsmLayout &Layout,
const SectionAddrMap &Addrs) const {
return EvaluateAsAbsolute(Res, &Layout.getAssembler(), &Layout, &Addrs);
}
bool MCExpr::EvaluateAsAbsolute(int64_t &Res, const MCAssembler &Asm) const {
return EvaluateAsAbsolute(Res, &Asm, 0, 0);
}
bool MCExpr::EvaluateAsAbsolute(int64_t &Res, const MCAssembler *Asm,
const MCAsmLayout *Layout,
Sorry for such a large commit. The summary is that only MachO cares about the actuall addresses in a .o file, so it is better to let the MachO writer compute it. This is good for two reasons. First, areas that shouldn't care about addresses now don't have access to it. Second, the layout of each section is independent. I should use this in a subsequent commit to speed it up. Most of the patch is just removing the section address computation. The two interesting parts are the change on how we handle padding in the end of sections and how MachO can get the address of a-b when a and b are in different sections. Since now the expression evaluation normally doesn't know the section address, it will think that a-b needs relocation and let the MachO writer know. Once it has computed the section addresses, it calls back the expression evaluation with the section addresses to resolve these expressions. The remaining problem is the handling of padding. Currently it will create a special alignment fragment at the end. Since that fragment doesn't update the alignment of the section, it needs the real address to be computed. Since now the layout will not compute a-b with a and b in different sections, the only effect that the special alignment fragment has is update the address size of the section. This can also be done by the MachO writer. llvm-svn: 121076
2010-12-07 08:27:36 +08:00
const SectionAddrMap *Addrs) const {
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
MCValue Value;
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
llvm-mc: Fast path EvaluateAbsolute of constants. llvm-svn: 99348
2010-03-24 07:47:07 +08:00
// Fast path constants.
if (const MCConstantExpr *CE = dyn_cast<MCConstantExpr>(this)) {
Res = CE->getValue();
return true;
}
Add a FIXME and explain a hack. llvm-svn: 122144
2010-12-18 12:19:20 +08:00
// FIXME: The use if InSet = Addrs is a hack. Setting InSet causes us
// absolutize differences across sections and that is what the MachO writer
// uses Addrs for.
Add r122359 back now that the bug in MCDwarfLineAddrFragment fragment has been fixed. llvm-svn: 122448
2010-12-23 06:16:24 +08:00
bool IsRelocatable =
EvaluateAsRelocatableImpl(Value, Asm, Layout, Addrs, /*InSet*/ Addrs);
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
Add r122359 back now that the bug in MCDwarfLineAddrFragment fragment has been fixed. llvm-svn: 122448
2010-12-23 06:16:24 +08:00
// Record the current value.
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
Res = Value.getConstant();
Add r122359 back now that the bug in MCDwarfLineAddrFragment fragment has been fixed. llvm-svn: 122448
2010-12-23 06:16:24 +08:00
return IsRelocatable && Value.isAbsolute();
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
}
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
/// \brief Helper method for \see EvaluateSymbolAdd().
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
static void AttemptToFoldSymbolOffsetDifference(const MCAssembler *Asm,
const MCAsmLayout *Layout,
const SectionAddrMap *Addrs,
bool InSet,
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
const MCSymbolRefExpr *&A,
const MCSymbolRefExpr *&B,
int64_t &Addend) {
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
if (!A || !B)
return;
const MCSymbol &SA = A->getSymbol();
const MCSymbol &SB = B->getSymbol();
if (SA.isUndefined() || SB.isUndefined())
return;
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
if (!Asm->getWriter().IsSymbolRefDifferenceFullyResolved(*Asm, A, B, InSet))
return;
MCSymbolData &AD = Asm->getSymbolData(SA);
MCSymbolData &BD = Asm->getSymbolData(SB);
if (AD.getFragment() == BD.getFragment()) {
Addend += (AD.getOffset() - BD.getOffset());
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
Add support for Thumb interworking addresses for symbol offsets that get constant folded very early. This fixes SPASS with -integrated-as. <rdar://problem/9165399> llvm-svn: 128037
2011-03-22 07:13:43 +08:00
// Pointers to Thumb symbols need to have their low-bit set to allow
// for interworking.
if (Asm->isThumbFunc(&SA))
Addend |= 1;
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
// Clear the symbol expr pointers to indicate we have folded these
// operands.
A = B = 0;
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
return;
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
}
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
if (!Layout)
return;
const MCSectionData &SecA = *AD.getFragment()->getParent();
const MCSectionData &SecB = *BD.getFragment()->getParent();
if ((&SecA != &SecB) && !Addrs)
return;
// Eagerly evaluate.
Addend += (Layout->getSymbolOffset(&Asm->getSymbolData(A->getSymbol())) -
Layout->getSymbolOffset(&Asm->getSymbolData(B->getSymbol())));
if (Addrs && (&SecA != &SecB))
Addend += (Addrs->lookup(&SecA) - Addrs->lookup(&SecB));
ARM Thumb symbol references in assembly need the low bit set. Add support for a missed case when the symbols in a difference expression are in the same section but not the same fragment. rdar://10924681 llvm-svn: 151345
2012-02-24 13:12:18 +08:00
// Pointers to Thumb symbols need to have their low-bit set to allow
// for interworking.
if (Asm->isThumbFunc(&SA))
Addend |= 1;
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
// Clear the symbol expr pointers to indicate we have folded these
// operands.
A = B = 0;
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
}
MC/Expr: Add a doxyment. llvm-svn: 121988
2010-12-17 02:36:25 +08:00
/// \brief Evaluate the result of an add between (conceptually) two MCValues.
///
/// This routine conceptually attempts to construct an MCValue:
/// Result = (Result_A - Result_B + Result_Cst)
/// from two MCValue's LHS and RHS where
/// Result = LHS + RHS
/// and
/// Result = (LHS_A - LHS_B + LHS_Cst) + (RHS_A - RHS_B + RHS_Cst).
///
/// This routine attempts to aggresively fold the operands such that the result
/// is representable in an MCValue, but may not always succeed.
///
/// \returns True on success, false if the result is not representable in an
/// MCValue.
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
/// NOTE: It is really important to have both the Asm and Layout arguments.
/// They might look redundant, but this function can be used before layout
/// is done (see the object streamer for example) and having the Asm argument
Fix the note. llvm-svn: 122139
2010-12-18 12:01:45 +08:00
/// lets us avoid relaxations early.
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
static bool EvaluateSymbolicAdd(const MCAssembler *Asm,
const MCAsmLayout *Layout,
Sorry for such a large commit. The summary is that only MachO cares about the actuall addresses in a .o file, so it is better to let the MachO writer compute it. This is good for two reasons. First, areas that shouldn't care about addresses now don't have access to it. Second, the layout of each section is independent. I should use this in a subsequent commit to speed it up. Most of the patch is just removing the section address computation. The two interesting parts are the change on how we handle padding in the end of sections and how MachO can get the address of a-b when a and b are in different sections. Since now the expression evaluation normally doesn't know the section address, it will think that a-b needs relocation and let the MachO writer know. Once it has computed the section addresses, it calls back the expression evaluation with the section addresses to resolve these expressions. The remaining problem is the handling of padding. Currently it will create a special alignment fragment at the end. Since that fragment doesn't update the alignment of the section, it needs the real address to be computed. Since now the layout will not compute a-b with a and b in different sections, the only effect that the special alignment fragment has is update the address size of the section. This can also be done by the MachO writer. llvm-svn: 121076
2010-12-07 08:27:36 +08:00
const SectionAddrMap *Addrs,
Try to resolve symbol differences early, and if successful create a plain data fragment. This reduces the time to assemble the test in 8711 from 60s to 54s. llvm-svn: 120767
2010-12-03 08:55:40 +08:00
bool InSet,
Add a MCObjectFormat class so that code common to all targets that use a single object format can be shared. This also adds support for mov zed+(bar-foo), %eax on ELF and COFF targets. llvm-svn: 116675
2010-10-17 02:23:53 +08:00
const MCValue &LHS,const MCSymbolRefExpr *RHS_A,
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
const MCSymbolRefExpr *RHS_B, int64_t RHS_Cst,
llvm-mc: Rewrite binary subtraction for relocatable expressions, we can't always legally negate an MCValue. llvm-svn: 74497
2009-06-30 10:08:27 +08:00
MCValue &Res) {
MC/Expr: Simplify (and add a FIXME). llvm-svn: 122008
2010-12-17 09:07:20 +08:00
// FIXME: This routine (and other evaluation parts) are *incredibly* sloppy
// about dealing with modifiers. This will ultimately bite us, one day.
const MCSymbolRefExpr *LHS_A = LHS.getSymA();
const MCSymbolRefExpr *LHS_B = LHS.getSymB();
int64_t LHS_Cst = LHS.getConstant();
// Fold the result constant immediately.
int64_t Result_Cst = LHS_Cst + RHS_Cst;
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
assert((!Layout || Asm) &&
"Must have an assembler object if layout is given!");
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
// If we have a layout, we can fold resolved differences.
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
if (Asm) {
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
// First, fold out any differences which are fully resolved. By
// reassociating terms in
// Result = (LHS_A - LHS_B + LHS_Cst) + (RHS_A - RHS_B + RHS_Cst).
// we have the four possible differences:
// (LHS_A - LHS_B),
// (LHS_A - RHS_B),
// (RHS_A - LHS_B),
// (RHS_A - RHS_B).
Fix a ton of comment typos found by codespell. Patch by Luis Felipe Strano Moraes! llvm-svn: 129558
2011-04-15 13:18:47 +08:00
// Since we are attempting to be as aggressive as possible about folding, we
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
// attempt to evaluate each possible alternative.
Fixed version of 122160 (the previous one would fold undefined symbols). llvm-svn: 122167
2010-12-19 12:18:56 +08:00
AttemptToFoldSymbolOffsetDifference(Asm, Layout, Addrs, InSet, LHS_A, LHS_B,
Result_Cst);
AttemptToFoldSymbolOffsetDifference(Asm, Layout, Addrs, InSet, LHS_A, RHS_B,
Result_Cst);
AttemptToFoldSymbolOffsetDifference(Asm, Layout, Addrs, InSet, RHS_A, LHS_B,
Result_Cst);
AttemptToFoldSymbolOffsetDifference(Asm, Layout, Addrs, InSet, RHS_A, RHS_B,
Result_Cst);
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
}
MC/Expr: Simplify (and add a FIXME). llvm-svn: 122008
2010-12-17 09:07:20 +08:00
// We can't represent the addition or subtraction of two symbols.
if ((LHS_A && RHS_A) || (LHS_B && RHS_B))
llvm-mc: Rewrite binary subtraction for relocatable expressions, we can't always legally negate an MCValue. llvm-svn: 74497
2009-06-30 10:08:27 +08:00
return false;
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
// At this point, we have at most one additive symbol and one subtractive
// symbol -- find them.
MC/Expr: Simplify (and add a FIXME). llvm-svn: 122008
2010-12-17 09:07:20 +08:00
const MCSymbolRefExpr *A = LHS_A ? LHS_A : RHS_A;
const MCSymbolRefExpr *B = LHS_B ? LHS_B : RHS_B;
MC/Expr: Implemnt more aggressive folding during symbol evaluation using IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away something like: -- _a: ... L0: ... L1: ... .long (L1 - L0) / 2 -- llvm-svn: 122043
2010-12-17 13:50:33 +08:00
// If we have a negated symbol, then we must have also have a non-negated
// symbol in order to encode the expression.
if (B && !A)
return false;
Add a MCObjectFormat class so that code common to all targets that use a single object format can be shared. This also adds support for mov zed+(bar-foo), %eax on ELF and COFF targets. llvm-svn: 116675
2010-10-17 02:23:53 +08:00
MC/Expr: Simplify (and add a FIXME). llvm-svn: 122008
2010-12-17 09:07:20 +08:00
Res = MCValue::get(A, B, Result_Cst);
llvm-mc: Rewrite binary subtraction for relocatable expressions, we can't always legally negate an MCValue. llvm-svn: 74497
2009-06-30 10:08:27 +08:00
return true;
}
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
bool MCExpr::EvaluateAsRelocatable(MCValue &Res,
Use references and simplify. llvm-svn: 122405
2010-12-23 00:11:57 +08:00
const MCAsmLayout &Layout) const {
return EvaluateAsRelocatableImpl(Res, &Layout.getAssembler(), &Layout,
0, false);
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
}
Add a MCObjectFormat class so that code common to all targets that use a single object format can be shared. This also adds support for mov zed+(bar-foo), %eax on ELF and COFF targets. llvm-svn: 116675
2010-10-17 02:23:53 +08:00
bool MCExpr::EvaluateAsRelocatableImpl(MCValue &Res,
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
const MCAssembler *Asm,
Add a MCObjectFormat class so that code common to all targets that use a single object format can be shared. This also adds support for mov zed+(bar-foo), %eax on ELF and COFF targets. llvm-svn: 116675
2010-10-17 02:23:53 +08:00
const MCAsmLayout *Layout,
Sorry for such a large commit. The summary is that only MachO cares about the actuall addresses in a .o file, so it is better to let the MachO writer compute it. This is good for two reasons. First, areas that shouldn't care about addresses now don't have access to it. Second, the layout of each section is independent. I should use this in a subsequent commit to speed it up. Most of the patch is just removing the section address computation. The two interesting parts are the change on how we handle padding in the end of sections and how MachO can get the address of a-b when a and b are in different sections. Since now the expression evaluation normally doesn't know the section address, it will think that a-b needs relocation and let the MachO writer know. Once it has computed the section addresses, it calls back the expression evaluation with the section addresses to resolve these expressions. The remaining problem is the handling of padding. Currently it will create a special alignment fragment at the end. Since that fragment doesn't update the alignment of the section, it needs the real address to be computed. Since now the layout will not compute a-b with a and b in different sections, the only effect that the special alignment fragment has is update the address size of the section. This can also be done by the MachO writer. llvm-svn: 121076
2010-12-07 08:27:36 +08:00
const SectionAddrMap *Addrs,
Add a MCObjectFormat class so that code common to all targets that use a single object format can be shared. This also adds support for mov zed+(bar-foo), %eax on ELF and COFF targets. llvm-svn: 116675
2010-10-17 02:23:53 +08:00
bool InSet) const {
MC: Sprinkle in some more interesting statistics. llvm-svn: 99350
2010-03-24 07:47:14 +08:00
++stats::MCExprEvaluate;
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
switch (getKind()) {
add scaffolding for target-specific MCExprs. llvm-svn: 95559
2010-02-09 03:41:07 +08:00
case Target:
MC: Sketch initial MCAsmLayout class, which encapsulates the current layout of an assembly file. The MCAsmLayout is also available for use by MCExpr::EvaluateAs{Absolute,Relocatable}, to allow target specific hooks and "absolutizing" of symbols. llvm-svn: 98227
2010-03-11 10:28:59 +08:00
return cast<MCTargetExpr>(this)->EvaluateAsRelocatableImpl(Res, Layout);
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
case Constant:
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
Res = MCValue::get(cast<MCConstantExpr>(this)->getValue());
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
return true;
case SymbolRef: {
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
const MCSymbolRefExpr *SRE = cast<MCSymbolRefExpr>(this);
const MCSymbol &Sym = SRE->getSymbol();
MC: Move assembler variable values from MCContext to MCSymbol. llvm-svn: 84229
2009-10-16 09:33:57 +08:00
// Evaluate recursively if this is a variable.
Change MCExpr::EvaluateAsRelocatableImpl of variables to return the original variable if recursing fails to simplify it. Factor AliasedSymbol to be a method of MCSymbol. Update MCAssembler::EvaluateFixup to match the change in EvaluateAsRelocatableImpl. Remove the WeakRefExpr hack, as the object writer now sees the weakref with no extra effort needed. Nothing else is using MCTargetExpr, but keep it for now. Now that the ELF writer sees relocations with aliases, handle .weak foo2 foo2: .weak bar2 .set bar2,foo2 .quad bar2 the same way gas does and produce a relocation with bar2. llvm-svn: 119152
2010-11-16 00:33:49 +08:00
if (Sym.isVariable() && SRE->getKind() == MCSymbolRefExpr::VK_None) {
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
bool Ret = Sym.getVariableValue()->EvaluateAsRelocatableImpl(Res, Asm,
Layout,
Addrs,
true);
Change MCExpr::EvaluateAsRelocatableImpl of variables to return the original variable if recursing fails to simplify it. Factor AliasedSymbol to be a method of MCSymbol. Update MCAssembler::EvaluateFixup to match the change in EvaluateAsRelocatableImpl. Remove the WeakRefExpr hack, as the object writer now sees the weakref with no extra effort needed. Nothing else is using MCTargetExpr, but keep it for now. Now that the ELF writer sees relocations with aliases, handle .weak foo2 foo2: .weak bar2 .set bar2,foo2 .quad bar2 the same way gas does and produce a relocation with bar2. llvm-svn: 119152
2010-11-16 00:33:49 +08:00
// If we failed to simplify this to a constant, let the target
// handle it.
if (Ret && !Res.getSymA() && !Res.getSymB())
return true;
}
MC: Move assembler variable values from MCContext to MCSymbol. llvm-svn: 84229
2009-10-16 09:33:57 +08:00
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
Res = MCValue::get(SRE, 0, 0);
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
return true;
}
case Unary: {
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
const MCUnaryExpr *AUE = cast<MCUnaryExpr>(this);
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
MCValue Value;
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
if (!AUE->getSubExpr()->EvaluateAsRelocatableImpl(Value, Asm, Layout,
Sorry for such a large commit. The summary is that only MachO cares about the actuall addresses in a .o file, so it is better to let the MachO writer compute it. This is good for two reasons. First, areas that shouldn't care about addresses now don't have access to it. Second, the layout of each section is independent. I should use this in a subsequent commit to speed it up. Most of the patch is just removing the section address computation. The two interesting parts are the change on how we handle padding in the end of sections and how MachO can get the address of a-b when a and b are in different sections. Since now the expression evaluation normally doesn't know the section address, it will think that a-b needs relocation and let the MachO writer know. Once it has computed the section addresses, it calls back the expression evaluation with the section addresses to resolve these expressions. The remaining problem is the handling of padding. Currently it will create a special alignment fragment at the end. Since that fragment doesn't update the alignment of the section, it needs the real address to be computed. Since now the layout will not compute a-b with a and b in different sections, the only effect that the special alignment fragment has is update the address size of the section. This can also be done by the MachO writer. llvm-svn: 121076
2010-12-07 08:27:36 +08:00
Addrs, InSet))
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
return false;
switch (AUE->getOpcode()) {
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
case MCUnaryExpr::LNot:
Rename MCValue::isConstant to isAbsolute. llvm-svn: 74596
2009-07-01 14:48:00 +08:00
if (!Value.isAbsolute())
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
return false;
Res = MCValue::get(!Value.getConstant());
break;
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
case MCUnaryExpr::Minus:
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
/// -(a - b + const) ==> (b - a - const)
llvm-mc: Fix a crash on invalid due to a typo in relocatable expression evaluation. llvm-svn: 78692
2009-08-12 01:47:52 +08:00
if (Value.getSymA() && !Value.getSymB())
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
return false;
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
Res = MCValue::get(Value.getSymB(), Value.getSymA(),
-Value.getConstant());
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
break;
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
case MCUnaryExpr::Not:
Rename MCValue::isConstant to isAbsolute. llvm-svn: 74596
2009-07-01 14:48:00 +08:00
if (!Value.isAbsolute())
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
return false;
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
Res = MCValue::get(~Value.getConstant());
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
break;
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
case MCUnaryExpr::Plus:
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
Res = Value;
break;
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
}
return true;
}
case Binary: {
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
const MCBinaryExpr *ABE = cast<MCBinaryExpr>(this);
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
MCValue LHSValue, RHSValue;
MCValue: Change to holding MCSymbolRefExprs instead of MCSymbols, we will need this for accessing to symbol modifiers. llvm-svn: 98791
2010-03-18 08:59:10 +08:00
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
if (!ABE->getLHS()->EvaluateAsRelocatableImpl(LHSValue, Asm, Layout,
Sorry for such a large commit. The summary is that only MachO cares about the actuall addresses in a .o file, so it is better to let the MachO writer compute it. This is good for two reasons. First, areas that shouldn't care about addresses now don't have access to it. Second, the layout of each section is independent. I should use this in a subsequent commit to speed it up. Most of the patch is just removing the section address computation. The two interesting parts are the change on how we handle padding in the end of sections and how MachO can get the address of a-b when a and b are in different sections. Since now the expression evaluation normally doesn't know the section address, it will think that a-b needs relocation and let the MachO writer know. Once it has computed the section addresses, it calls back the expression evaluation with the section addresses to resolve these expressions. The remaining problem is the handling of padding. Currently it will create a special alignment fragment at the end. Since that fragment doesn't update the alignment of the section, it needs the real address to be computed. Since now the layout will not compute a-b with a and b in different sections, the only effect that the special alignment fragment has is update the address size of the section. This can also be done by the MachO writer. llvm-svn: 121076
2010-12-07 08:27:36 +08:00
Addrs, InSet) ||
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
!ABE->getRHS()->EvaluateAsRelocatableImpl(RHSValue, Asm, Layout,
Sorry for such a large commit. The summary is that only MachO cares about the actuall addresses in a .o file, so it is better to let the MachO writer compute it. This is good for two reasons. First, areas that shouldn't care about addresses now don't have access to it. Second, the layout of each section is independent. I should use this in a subsequent commit to speed it up. Most of the patch is just removing the section address computation. The two interesting parts are the change on how we handle padding in the end of sections and how MachO can get the address of a-b when a and b are in different sections. Since now the expression evaluation normally doesn't know the section address, it will think that a-b needs relocation and let the MachO writer know. Once it has computed the section addresses, it calls back the expression evaluation with the section addresses to resolve these expressions. The remaining problem is the handling of padding. Currently it will create a special alignment fragment at the end. Since that fragment doesn't update the alignment of the section, it needs the real address to be computed. Since now the layout will not compute a-b with a and b in different sections, the only effect that the special alignment fragment has is update the address size of the section. This can also be done by the MachO writer. llvm-svn: 121076
2010-12-07 08:27:36 +08:00
Addrs, InSet))
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
return false;
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
// We only support a few operations on non-constant expressions, handle
// those first.
Rename MCValue::isConstant to isAbsolute. llvm-svn: 74596
2009-07-01 14:48:00 +08:00
if (!LHSValue.isAbsolute() || !RHSValue.isAbsolute()) {
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
switch (ABE->getOpcode()) {
default:
return false;
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
case MCBinaryExpr::Sub:
llvm-mc: Rewrite binary subtraction for relocatable expressions, we can't always legally negate an MCValue. llvm-svn: 74497
2009-06-30 10:08:27 +08:00
// Negate RHS and add.
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
return EvaluateSymbolicAdd(Asm, Layout, Addrs, InSet, LHSValue,
llvm-mc: Rewrite binary subtraction for relocatable expressions, we can't always legally negate an MCValue. llvm-svn: 74497
2009-06-30 10:08:27 +08:00
RHSValue.getSymB(), RHSValue.getSymA(),
-RHSValue.getConstant(),
Res);
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
case MCBinaryExpr::Add:
Revert 122011, 122012, 122013, 122023 adding back an important optimization. I added a note, but suggestions on how to add a test are really welcome. llvm-svn: 122138
2010-12-18 11:57:21 +08:00
return EvaluateSymbolicAdd(Asm, Layout, Addrs, InSet, LHSValue,
llvm-mc: Rewrite binary subtraction for relocatable expressions, we can't always legally negate an MCValue. llvm-svn: 74497
2009-06-30 10:08:27 +08:00
RHSValue.getSymA(), RHSValue.getSymB(),
RHSValue.getConstant(),
Res);
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
}
}
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
// FIXME: We need target hooks for the evaluation. It may be limited in
Document that MCExpr::Mod is actually remainder. Document that MCExpr::Div, Mod, and the comparison operators are all signed operators. Document that the comparison operators' results are target-dependent. Document that the behavior of shr is target-dependent. llvm-svn: 95619
2010-02-09 07:58:47 +08:00
// width, and gas defines the result of comparisons and right shifts
// differently from Apple as.
Suppress may-be-used-uninitialized warning. llvm-svn: 74529
2009-07-01 00:02:47 +08:00
int64_t LHS = LHSValue.getConstant(), RHS = RHSValue.getConstant();
int64_t Result = 0;
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
switch (ABE->getOpcode()) {
llvm-mc: Move AsmExpr into MC lib (as MCExpr). llvm-svn: 80567
2009-08-31 16:06:59 +08:00
case MCBinaryExpr::Add: Result = LHS + RHS; break;
case MCBinaryExpr::And: Result = LHS & RHS; break;
case MCBinaryExpr::Div: Result = LHS / RHS; break;
case MCBinaryExpr::EQ: Result = LHS == RHS; break;
case MCBinaryExpr::GT: Result = LHS > RHS; break;
case MCBinaryExpr::GTE: Result = LHS >= RHS; break;
case MCBinaryExpr::LAnd: Result = LHS && RHS; break;
case MCBinaryExpr::LOr: Result = LHS || RHS; break;
case MCBinaryExpr::LT: Result = LHS < RHS; break;
case MCBinaryExpr::LTE: Result = LHS <= RHS; break;
case MCBinaryExpr::Mod: Result = LHS % RHS; break;
case MCBinaryExpr::Mul: Result = LHS * RHS; break;
case MCBinaryExpr::NE: Result = LHS != RHS; break;
case MCBinaryExpr::Or: Result = LHS | RHS; break;
case MCBinaryExpr::Shl: Result = LHS << RHS; break;
case MCBinaryExpr::Shr: Result = LHS >> RHS; break;
case MCBinaryExpr::Sub: Result = LHS - RHS; break;
case MCBinaryExpr::Xor: Result = LHS ^ RHS; break;
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
}
llvm-mc: Evaluation for relocatable expressions. llvm-svn: 74496
2009-06-30 09:49:52 +08:00
Res = MCValue::get(Result);
MC: Improve expression parsing and implement evaluation of absolute expressions (missed files). llvm-svn: 74450
2009-06-30 04:40:36 +08:00
return true;
}
}
Convert assert(0) to llvm_unreachable llvm-svn: 149967
2012-02-07 13:05:23 +08:00
llvm_unreachable("Invalid assembly expression kind!");
llvm-mc: Switch MCExpr construction to using static member functions, and taking the MCContext (which now owns all MCExprs). llvm-svn: 80569
2009-08-31 16:07:22 +08:00
}
MCExpr: Add FindAssociatedSection, which attempts to mirror the 'as' semantics that associate sections with expressions. llvm-svn: 130517
2011-04-30 02:00:03 +08:00
const MCSection *MCExpr::FindAssociatedSection() const {
switch (getKind()) {
case Target:
// We never look through target specific expressions.
return cast<MCTargetExpr>(this)->FindAssociatedSection();
case Constant:
return MCSymbol::AbsolutePseudoSection;
case SymbolRef: {
const MCSymbolRefExpr *SRE = cast<MCSymbolRefExpr>(this);
const MCSymbol &Sym = SRE->getSymbol();
if (Sym.isDefined())
return &Sym.getSection();
return 0;
}
case Unary:
return cast<MCUnaryExpr>(this)->getSubExpr()->FindAssociatedSection();
case Binary: {
const MCBinaryExpr *BE = cast<MCBinaryExpr>(this);
const MCSection *LHS_S = BE->getLHS()->FindAssociatedSection();
const MCSection *RHS_S = BE->getRHS()->FindAssociatedSection();
// If either section is absolute, return the other.
if (LHS_S == MCSymbol::AbsolutePseudoSection)
return RHS_S;
if (RHS_S == MCSymbol::AbsolutePseudoSection)
return LHS_S;
// Otherwise, return the first non-null section.
return LHS_S ? LHS_S : RHS_S;
}
}
Convert assert(0) to llvm_unreachable llvm-svn: 149967
2012-02-07 13:05:23 +08:00
llvm_unreachable("Invalid assembly expression kind!");
MCExpr: Add FindAssociatedSection, which attempts to mirror the 'as' semantics that associate sections with expressions. llvm-svn: 130517
2011-04-30 02:00:03 +08:00
}