RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-12-02 16:36:40 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

This option allows selecting the TLS size in the local exec TLS model,

Browse Source 
which is the default TLS model for non-PIC objects. This allows large/
many thread local variables or a compact/fast code in an executable.

Specification is same as that of GCC. For example, the code model
option precedes the TLS size option.

TLS access models other than local-exec are not changed. It means
supoort of the large code model is only in the local exec TLS model.

Patch By KAWASHIMA Takahiro (kawashima-fj <t-kawashima@fujitsu.com>)
Reviewers: dmgreen, mstorsjo, t.p.northover, peter.smith, ostannard
Reviewd By: peter.smith
Committed by: peter.smith

Differential Revision: https://reviews.llvm.org/D71688
This commit is contained in:
KAWASHIMA Takahiro 2020-01-13 09:28:02 +00:00 committed by Peter Smith
parent 4897d2be46
commit 78130ba3e6
7 changed files with 231 additions and 71 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
include/llvm/CodeGen/CommandFlags.inc
View File

@ -238,6 +238,10 @@ static cl::opt<bool>
cl::desc("Emit functions into separate sections"),
cl::init(false));
static cl::opt<unsigned> TLSSize("tls-size",
cl::desc("Bit size of immediate TLS offsets"),
cl::init(0));
static cl::opt<bool> EmulatedTLS("emulated-tls",
cl::desc("Use emulated TLS model"),
cl::init(false));
@ -305,6 +309,7 @@ static TargetOptions InitTargetOptionsFromCodeGenFlags() {
Options.DataSections = DataSections;
Options.FunctionSections = FunctionSections;
Options.UniqueSectionNames = UniqueSectionNames;
Options.TLSSize = TLSSize;
Options.EmulatedTLS = EmulatedTLS;
Options.ExplicitEmulatedTLS = EmulatedTLS.getNumOccurrences() > 0;
Options.ExceptionModel = ExceptionModel;

3
include/llvm/Target/TargetOptions.h
View File

@ -231,6 +231,9 @@ namespace llvm {
/// noreturn calls, even if TrapUnreachable is true.
unsigned NoTrapAfterNoreturn : 1;
/// Bit size of immediate TLS offsets (0 == use the default).
unsigned TLSSize : 8;
/// EmulatedTLS - This flag enables emulated TLS model, using emutls
/// function in the runtime library..
unsigned EmulatedTLS : 1;

130
lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -4591,6 +4591,97 @@ AArch64TargetLowering::LowerDarwinGlobalTLSAddress(SDValue Op,
return DAG.getCopyFromReg(Chain, DL, AArch64::X0, PtrVT, Chain.getValue(1));
}
/// Convert a thread-local variable reference into a sequence of instructions to
/// compute the variable's address for the local exec TLS model of ELF targets.
/// The sequence depends on the maximum TLS area size.
SDValue AArch64TargetLowering::LowerELFTLSLocalExec(const GlobalValue *GV,
SDValue ThreadBase,
const SDLoc &DL,
SelectionDAG &DAG) const {
EVT PtrVT = getPointerTy(DAG.getDataLayout());
SDValue TPOff, Addr;
switch (DAG.getTarget().Options.TLSSize) {
default:
llvm_unreachable("Unexpected TLS size");
case 12: {
// mrs x0, TPIDR_EL0
// add x0, x0, :tprel_lo12:a
SDValue Var = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0, AArch64II::MO_TLS | AArch64II::MO_PAGEOFF);
return SDValue(DAG.getMachineNode(AArch64::ADDXri, DL, PtrVT, ThreadBase,
Var,
DAG.getTargetConstant(0, DL, MVT::i32)),
0);
}
case 24: {
// mrs x0, TPIDR_EL0
// add x0, x0, :tprel_hi12:a
// add x0, x0, :tprel_lo12_nc:a
SDValue HiVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0, AArch64II::MO_TLS | AArch64II::MO_HI12);
SDValue LoVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0,
AArch64II::MO_TLS | AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
Addr = SDValue(DAG.getMachineNode(AArch64::ADDXri, DL, PtrVT, ThreadBase,
HiVar,
DAG.getTargetConstant(0, DL, MVT::i32)),
0);
return SDValue(DAG.getMachineNode(AArch64::ADDXri, DL, PtrVT, Addr,
LoVar,
DAG.getTargetConstant(0, DL, MVT::i32)),
0);
}
case 32: {
// mrs x1, TPIDR_EL0
// movz x0, #:tprel_g1:a
// movk x0, #:tprel_g0_nc:a
// add x0, x1, x0
SDValue HiVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0, AArch64II::MO_TLS | AArch64II::MO_G1);
SDValue LoVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0,
AArch64II::MO_TLS | AArch64II::MO_G0 | AArch64II::MO_NC);
TPOff = SDValue(DAG.getMachineNode(AArch64::MOVZXi, DL, PtrVT, HiVar,
DAG.getTargetConstant(16, DL, MVT::i32)),
0);
TPOff = SDValue(DAG.getMachineNode(AArch64::MOVKXi, DL, PtrVT, TPOff, LoVar,
DAG.getTargetConstant(0, DL, MVT::i32)),
0);
return DAG.getNode(ISD::ADD, DL, PtrVT, ThreadBase, TPOff);
}
case 48: {
// mrs x1, TPIDR_EL0
// movz x0, #:tprel_g2:a
// movk x0, #:tprel_g1_nc:a
// movk x0, #:tprel_g0_nc:a
// add x0, x1, x0
SDValue HiVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0, AArch64II::MO_TLS | AArch64II::MO_G2);
SDValue MiVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0,
AArch64II::MO_TLS | AArch64II::MO_G1 | AArch64II::MO_NC);
SDValue LoVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0,
AArch64II::MO_TLS | AArch64II::MO_G0 | AArch64II::MO_NC);
TPOff = SDValue(DAG.getMachineNode(AArch64::MOVZXi, DL, PtrVT, HiVar,
DAG.getTargetConstant(32, DL, MVT::i32)),
0);
TPOff = SDValue(DAG.getMachineNode(AArch64::MOVKXi, DL, PtrVT, TPOff, MiVar,
DAG.getTargetConstant(16, DL, MVT::i32)),
0);
TPOff = SDValue(DAG.getMachineNode(AArch64::MOVKXi, DL, PtrVT, TPOff, LoVar,
DAG.getTargetConstant(0, DL, MVT::i32)),
0);
return DAG.getNode(ISD::ADD, DL, PtrVT, ThreadBase, TPOff);
}
}
}
/// When accessing thread-local variables under either the general-dynamic or
/// local-dynamic system, we make a "TLS-descriptor" call. The variable will
/// have a descriptor, accessible via a PC-relative ADRP, and whose first entry
@ -4628,15 +4719,7 @@ SDValue
AArch64TargetLowering::LowerELFGlobalTLSAddress(SDValue Op,
SelectionDAG &DAG) const {
assert(Subtarget->isTargetELF() && "This function expects an ELF target");
if (getTargetMachine().getCodeModel() == CodeModel::Large)
report_fatal_error("ELF TLS only supported in small memory model");
// Different choices can be made for the maximum size of the TLS area for a
// module. For the small address model, the default TLS size is 16MiB and the
// maximum TLS size is 4GiB.
// FIXME: add -mtls-size command line option and make it control the 16MiB
// vs. 4GiB code sequence generation.
// FIXME: add tiny codemodel support. We currently generate the same code as
// small, which may be larger than needed.
const GlobalAddressSDNode *GA = cast<GlobalAddressSDNode>(Op);
TLSModel::Model Model = getTargetMachine().getTLSModel(GA->getGlobal());
@ -4646,6 +4729,17 @@ AArch64TargetLowering::LowerELFGlobalTLSAddress(SDValue Op,
Model = TLSModel::GeneralDynamic;
}
if (getTargetMachine().getCodeModel() == CodeModel::Large &&
Model != TLSModel::LocalExec)
report_fatal_error("ELF TLS only supported in small memory model or "
"in local exec TLS model");
// Different choices can be made for the maximum size of the TLS area for a
// module. For the small address model, the default TLS size is 16MiB and the
// maximum TLS size is 4GiB.
// FIXME: add tiny and large code model support for TLS access models other
// than local exec. We currently generate the same code as small for tiny,
// which may be larger than needed.
SDValue TPOff;
EVT PtrVT = getPointerTy(DAG.getDataLayout());
SDLoc DL(Op);
@ -4654,23 +4748,7 @@ AArch64TargetLowering::LowerELFGlobalTLSAddress(SDValue Op,
SDValue ThreadBase = DAG.getNode(AArch64ISD::THREAD_POINTER, DL, PtrVT);
if (Model == TLSModel::LocalExec) {
SDValue HiVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0, AArch64II::MO_TLS | AArch64II::MO_HI12);
SDValue LoVar = DAG.getTargetGlobalAddress(
GV, DL, PtrVT, 0,
AArch64II::MO_TLS | AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
SDValue TPWithOff_lo =
SDValue(DAG.getMachineNode(AArch64::ADDXri, DL, PtrVT, ThreadBase,
HiVar,
DAG.getTargetConstant(0, DL, MVT::i32)),
0);
SDValue TPWithOff =
SDValue(DAG.getMachineNode(AArch64::ADDXri, DL, PtrVT, TPWithOff_lo,
LoVar,
DAG.getTargetConstant(0, DL, MVT::i32)),
0);
return TPWithOff;
return LowerELFTLSLocalExec(GV, ThreadBase, DL, DAG);
} else if (Model == TLSModel::InitialExec) {
TPOff = DAG.getTargetGlobalAddress(GV, DL, PtrVT, 0, AArch64II::MO_TLS);
TPOff = DAG.getNode(AArch64ISD::LOADgot, DL, PtrVT, TPOff);

2
lib/Target/AArch64/AArch64ISelLowering.h
View File

@ -696,6 +696,8 @@ private:
SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerDarwinGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerELFGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerELFTLSLocalExec(const GlobalValue *GV, SDValue ThreadBase,
const SDLoc &DL, SelectionDAG &DAG) const;
SDValue LowerELFTLSDescCallSeq(SDValue SymAddr, const SDLoc &DL,
SelectionDAG &DAG) const;
SDValue LowerWindowsGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;

11
lib/Target/AArch64/AArch64TargetMachine.cpp
View File

@ -288,6 +288,17 @@ AArch64TargetMachine::AArch64TargetMachine(const Target &T, const Triple &TT,
this->Options.TrapUnreachable = true;
}
if (this->Options.TLSSize == 0) // default
this->Options.TLSSize = 24;
if ((getCodeModel() == CodeModel::Small ||
getCodeModel() == CodeModel::Kernel) &&
this->Options.TLSSize > 32)
// for the small (and kernel) code model, the maximum TLS size is 4GiB
this->Options.TLSSize = 32;
else if (getCodeModel() == CodeModel::Tiny && this->Options.TLSSize > 24)
// for the tiny code model, the maximum TLS size is 1MiB (< 16MiB)
this->Options.TLSSize = 24;
// Enable GlobalISel at or below EnableGlobalISelAt0, unless this is
// MachO/CodeModel::Large, which GlobalISel does not support.
if (getOptLevel() <= EnableGlobalISelAtO &&

45
test/CodeGen/AArch64/arm64-tls-execs.ll → test/CodeGen/AArch64/arm64-tls-initial-exec.ll
View File

@ -49,48 +49,3 @@ define i32* @test_initial_exec_addr() {
; CHECK-TINY-RELOC: R_AARCH64_TLSIE_LD_GOTTPREL_PREL19
}
@local_exec_var = thread_local(localexec) global i32 0
define i32 @test_local_exec() {
; CHECK-LABEL: test_local_exec:
%val = load i32, i32* @local_exec_var
; CHECK: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK: add x[[R2:[0-9]+]], x[[R1]], :tprel_hi12:local_exec_var
; CHECK: add x[[R3:[0-9]+]], x[[R2]], :tprel_lo12_nc:local_exec_var
; CHECK: ldr w0, [x[[R3]]]
; CHECK-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
; CHECK-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
; CHECK-TINY: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-TINY: add x[[R2:[0-9]+]], x[[R1]], :tprel_hi12:local_exec_var
; CHECK-TINY: add x[[R3:[0-9]+]], x[[R2]], :tprel_lo12_nc:local_exec_var
; CHECK-TINY: ldr w0, [x[[R3]]]
; CHECK-TINY-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
; CHECK-TINY-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
ret i32 %val
}
define i32* @test_local_exec_addr() {
; CHECK-LABEL: test_local_exec_addr:
ret i32* @local_exec_var
; CHECK: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK: add x[[R2:[0-9]+]], x[[R1]], :tprel_hi12:local_exec_var
; CHECK: add x0, x[[R2]], :tprel_lo12_nc:local_exec_var
; CHECK: ret
; CHECK-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
; CHECK-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
; CHECK-TINY: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-TINY: add x[[R2:[0-9]+]], x[[R1]], :tprel_hi12:local_exec_var
; CHECK-TINY: add x0, x[[R2]], :tprel_lo12_nc:local_exec_var
; CHECK-TINY: ret
; CHECK-TINY-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
; CHECK-TINY-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
}

106
test/CodeGen/AArch64/arm64-tls-local-exec.ll Normal file
View File

@ -0,0 +1,106 @@
; Test each TLS size option
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -tls-size=12 < %s | FileCheck %s --check-prefix=CHECK-12
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -tls-size=12 | llvm-objdump -r - | FileCheck --check-prefix=CHECK-12-RELOC %s
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=tiny -tls-size=24 < %s | FileCheck %s --check-prefix=CHECK-24
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=tiny -tls-size=24 | llvm-objdump -r - | FileCheck --check-prefix=CHECK-24-RELOC %s
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=small -tls-size=32 < %s | FileCheck %s --check-prefix=CHECK-32
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=small -tls-size=32 | llvm-objdump -r - | FileCheck --check-prefix=CHECK-32-RELOC %s
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=large -tls-size=48 < %s | FileCheck %s --check-prefix=CHECK-48
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=large -tls-size=48 | llvm-objdump -r - | FileCheck --check-prefix=CHECK-48-RELOC %s
;
; Test the maximum TLS size for each code model (fallback to a smaller size from the specified size)
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -tls-size=32 < %s | FileCheck %s --check-prefix=CHECK-32
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -tls-size=32 | llvm-objdump -r - | FileCheck --check-prefix=CHECK-32-RELOC %s
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=tiny -tls-size=32 < %s | FileCheck %s --check-prefix=CHECK-24
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=tiny -tls-size=32 | llvm-objdump -r - | FileCheck --check-prefix=CHECK-24-RELOC %s
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=small -tls-size=48 < %s | FileCheck %s --check-prefix=CHECK-32
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=small -tls-size=48 | llvm-objdump -r - | FileCheck --check-prefix=CHECK-32-RELOC %s
;
; Test the default TLS size for each code model
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding < %s | FileCheck --check-prefix=CHECK-24 %s
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s | llvm-objdump -r - | FileCheck --check-prefix=CHECK-24-RELOC %s
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=tiny < %s | FileCheck %s --check-prefix=CHECK-24
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=tiny | llvm-objdump -r - | FileCheck --check-prefix=CHECK-24-RELOC %s
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=small < %s | FileCheck %s --check-prefix=CHECK-24
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=small | llvm-objdump -r - | FileCheck --check-prefix=CHECK-24-RELOC %s
; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=large < %s | FileCheck %s --check-prefix=CHECK-24
; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=large | llvm-objdump -r - | FileCheck --check-prefix=CHECK-24-RELOC %s
@local_exec_var = thread_local(localexec) global i32 0
define i32 @test_local_exec() {
; CHECK-LABEL: test_local_exec:
%val = load i32, i32* @local_exec_var
; CHECK-12: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-12: add x[[R2:[0-9]+]], x[[R1]], :tprel_lo12:local_exec_var
; CHECK-12: ldr w0, [x[[R2]]]
; CHECK-12-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12
; CHECK-24: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-24: add x[[R2:[0-9]+]], x[[R1]], :tprel_hi12:local_exec_var
; CHECK-24: add x[[R3:[0-9]+]], x[[R2]], :tprel_lo12_nc:local_exec_var
; CHECK-24: ldr w0, [x[[R3]]]
; CHECK-24-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
; CHECK-24-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
; CHECK-32: movz x[[R2:[0-9]+]], #:tprel_g1:local_exec_var
; CHECK-32: movk x[[R2]], #:tprel_g0_nc:local_exec_var
; CHECK-32: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-32: ldr w0, [x[[R1]], x[[R2]]]
; CHECK-32-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G1
; CHECK-32-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G0_NC
; CHECK-48: movz x[[R2:[0-9]+]], #:tprel_g2:local_exec_var
; CHECK-48: movk x[[R2]], #:tprel_g1_nc:local_exec_var
; CHECK-48: movk x[[R2]], #:tprel_g0_nc:local_exec_var
; CHECK-48: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-48: ldr w0, [x[[R1]], x[[R2]]]
; CHECK-48-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G2
; CHECK-48-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G1_NC
; CHECK-48-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G0_NC
ret i32 %val
}
define i32* @test_local_exec_addr() {
; CHECK-LABEL: test_local_exec_addr:
ret i32* @local_exec_var
; CHECK-12: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-12: add x0, x[[R1]], :tprel_lo12:local_exec_var
; CHECK-12: ret
; CHECK-12-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12
; CHECK-24: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-24: add x[[R2:[0-9]+]], x[[R1]], :tprel_hi12:local_exec_var
; CHECK-24: add x0, x[[R2]], :tprel_lo12_nc:local_exec_var
; CHECK-24: ret
; CHECK-24-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
; CHECK-24-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
; CHECK-32: movz x[[R2:[0-9]+]], #:tprel_g1:local_exec_var
; CHECK-32: movk x[[R2]], #:tprel_g0_nc:local_exec_var
; CHECK-32: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-32: add x0, x[[R1]], x[[R2]]
; CHECK-32: ret
; CHECK-32-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G1
; CHECK-32-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G0_NC
; CHECK-48: movz x[[R2:[0-9]+]], #:tprel_g2:local_exec_var
; CHECK-48: movk x[[R2]], #:tprel_g1_nc:local_exec_var
; CHECK-48: movk x[[R2]], #:tprel_g0_nc:local_exec_var
; CHECK-48: mrs x[[R1:[0-9]+]], TPIDR_EL0
; CHECK-48: add x0, x[[R1]], x[[R2]]
; CHECK-48: ret
; CHECK-48-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G2
; CHECK-48-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G1_NC
; CHECK-48-RELOC: R_AARCH64_TLSLE_MOVW_TPREL_G0_NC
}