[clang] 2d739f9 - [ARM] Allocatable Global Register Variables for ARM
Anna Welker via cfe-commits
cfe-commits at lists.llvm.org
Mon Nov 18 02:08:17 PST 2019
Author: Anna Welker
Date: 2019-11-18T10:07:37Z
New Revision: 2d739f98d8a53e38bf9faa88cdb6b0c2a363fb77
URL: https://github.com/llvm/llvm-project/commit/2d739f98d8a53e38bf9faa88cdb6b0c2a363fb77
DIFF: https://github.com/llvm/llvm-project/commit/2d739f98d8a53e38bf9faa88cdb6b0c2a363fb77.diff
LOG: [ARM] Allocatable Global Register Variables for ARM
Provides support for using r6-r11 as globally scoped
register variables. This requires a -ffixed-rN flag
in order to reserve rN against general allocation.
If for a given GRV declaration the corresponding flag
is not found, or the the register in question is the
target's FP, we fail with a diagnostic.
Differential Revision: https://reviews.llvm.org/D68862
Added:
clang/test/Driver/arm-reserved-reg-options.c
clang/test/Sema/arm-global-regs.c
llvm/test/CodeGen/ARM/reg-alloc-fixed-r6-vla.ll
llvm/test/CodeGen/ARM/reg-alloc-with-fixed-reg-r6-modified.ll
llvm/test/CodeGen/ARM/reg-alloc-with-fixed-reg-r6.ll
llvm/test/CodeGen/ARM/reg-alloc-wout-fixed-regs.ll
llvm/test/CodeGen/Thumb/callee_save_reserved.ll
llvm/test/Feature/reserve_global_reg.ll
Modified:
clang/docs/ClangCommandLineReference.rst
clang/include/clang/Basic/DiagnosticDriverKinds.td
clang/include/clang/Basic/DiagnosticGroups.td
clang/include/clang/Basic/DiagnosticSemaKinds.td
clang/include/clang/Basic/TargetInfo.h
clang/include/clang/Driver/Options.td
clang/lib/Basic/Targets/ARM.cpp
clang/lib/Basic/Targets/ARM.h
clang/lib/Driver/ToolChains/Arch/ARM.cpp
clang/lib/Sema/SemaDecl.cpp
llvm/lib/Target/ARM/ARM.td
llvm/lib/Target/ARM/ARMAsmPrinter.cpp
llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp
llvm/lib/Target/ARM/ARMFrameLowering.cpp
llvm/lib/Target/ARM/ARMISelLowering.cpp
llvm/lib/Target/ARM/ARMSubtarget.cpp
llvm/lib/Target/ARM/ARMSubtarget.h
llvm/lib/Target/ARM/ARMTargetTransformInfo.h
Removed:
################################################################################
diff --git a/clang/docs/ClangCommandLineReference.rst b/clang/docs/ClangCommandLineReference.rst
index e8d561fae956..492eec71f2e4 100644
--- a/clang/docs/ClangCommandLineReference.rst
+++ b/clang/docs/ClangCommandLineReference.rst
@@ -2430,10 +2430,31 @@ Enable XNACK (AMDGPU only)
ARM
---
+
+.. option:: -ffixed-r6
+
+Reserve the r6 register (ARM only)
+
+.. option:: -ffixed-r7
+
+Reserve the r7 register (ARM only)
+
+.. option:: -ffixed-r8
+
+Reserve the r8 register (ARM only)
+
.. option:: -ffixed-r9
Reserve the r9 register (ARM only)
+.. option:: -ffixed-r10
+
+Reserve the r10 register (ARM only)
+
+.. option:: -ffixed-r11
+
+Reserve the r11 register (ARM only)
+
.. option:: -mexecute-only, -mno-execute-only, -mpure-code
Disallow generation of data access to code sections (ARM only)
diff --git a/clang/include/clang/Basic/DiagnosticDriverKinds.td b/clang/include/clang/Basic/DiagnosticDriverKinds.td
index 5ff03e133563..0e309909030e 100644
--- a/clang/include/clang/Basic/DiagnosticDriverKinds.td
+++ b/clang/include/clang/Basic/DiagnosticDriverKinds.td
@@ -464,6 +464,10 @@ def warn_drv_msp430_hwmult_no_device : Warning<"no MCU device specified, but "
"specify a MSP430 device, or -mhwmult to set hardware multiply type "
"explicitly.">, InGroup<InvalidCommandLineArgument>;
+// Frame pointer reservation.
+def err_reserved_frame_pointer : Error<
+ "'%0' has been specified but '%1' is used as the frame pointer for this target">;
+
def warn_drv_libstdcxx_not_found : Warning<
"include path for libstdc++ headers not found; pass '-stdlib=libc++' on the "
"command line to use the libc++ standard library instead">,
diff --git a/clang/include/clang/Basic/DiagnosticGroups.td b/clang/include/clang/Basic/DiagnosticGroups.td
index bc66a8253074..6b83bf59ea89 100644
--- a/clang/include/clang/Basic/DiagnosticGroups.td
+++ b/clang/include/clang/Basic/DiagnosticGroups.td
@@ -1115,3 +1115,6 @@ def CrossTU : DiagGroup<"ctu">;
def CTADMaybeUnsupported : DiagGroup<"ctad-maybe-unsupported">;
def FortifySource : DiagGroup<"fortify-source">;
+
+// Register reservation.
+def FixedRegs : DiagGroup<"fixed-registers">;
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
index beb25c5a0892..49ad7c7cc462 100644
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -7716,6 +7716,8 @@ let CategoryName = "Inline Assembly Issue" in {
def err_asm_unknown_register_name : Error<"unknown register name '%0' in asm">;
def err_asm_invalid_global_var_reg : Error<"register '%0' unsuitable for "
"global register variables on this target">;
+ def err_asm_missing_fixed_reg_opt : Error<"-ffixed-%0 is required for "
+ "global named register variable declaration">;
def err_asm_register_size_mismatch : Error<"size of register '%0' does not "
"match variable size">;
def err_asm_bad_register_type : Error<"bad type for named register variable">;
diff --git a/clang/include/clang/Basic/TargetInfo.h b/clang/include/clang/Basic/TargetInfo.h
index 33cecdadc686..cc83f4c34c14 100644
--- a/clang/include/clang/Basic/TargetInfo.h
+++ b/clang/include/clang/Basic/TargetInfo.h
@@ -938,6 +938,12 @@ class TargetInfo : public virtual TransferrableTargetInfo,
return true;
}
+ /// Check if the register is reserved globally
+ ///
+ /// This function returns true if the register passed in RegName is reserved
+ /// using the corresponding -ffixed-RegName option.
+ virtual bool isRegisterReservedGlobally(StringRef) const { return true; }
+
// validateOutputConstraint, validateInputConstraint - Checks that
// a constraint is valid and provides information about it.
// FIXME: These should return a real error instead of just true/false.
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 6087b13228dc..3fca181b8784 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -2266,8 +2266,9 @@ def mrestrict_it: Flag<["-"], "mrestrict-it">, Group<m_arm_Features_Group>,
def mno_restrict_it: Flag<["-"], "mno-restrict-it">, Group<m_arm_Features_Group>,
HelpText<"Allow generation of deprecated IT blocks for ARMv8. It is off by default for ARMv8 Thumb mode">;
def marm : Flag<["-"], "marm">, Alias<mno_thumb>;
-def ffixed_r9 : Flag<["-"], "ffixed-r9">, Group<m_arm_Features_Group>,
- HelpText<"Reserve the r9 register (ARM only)">;
+foreach i = {6-11} in
+ def ffixed_r#i : Flag<["-"], "ffixed-r"#i>, Group<m_arm_Features_Group>,
+ HelpText<"Reserve the r"#i#" register (ARM only)">;
def mno_movt : Flag<["-"], "mno-movt">, Group<m_arm_Features_Group>,
HelpText<"Disallow use of movt/movw pairs (ARM only)">;
def mcrc : Flag<["-"], "mcrc">, Group<m_Group>,
diff --git a/clang/lib/Basic/Targets/ARM.cpp b/clang/lib/Basic/Targets/ARM.cpp
index 437a77afdc99..92e5e26eba3c 100644
--- a/clang/lib/Basic/Targets/ARM.cpp
+++ b/clang/lib/Basic/Targets/ARM.cpp
@@ -879,6 +879,38 @@ ArrayRef<TargetInfo::GCCRegAlias> ARMTargetInfo::getGCCRegAliases() const {
return llvm::makeArrayRef(GCCRegAliases);
}
+bool ARMTargetInfo::validateGlobalRegisterVariable(
+ StringRef RegName, unsigned RegSize, bool &HasSizeMismatch) const {
+ bool isValid = llvm::StringSwitch<bool>(RegName)
+ .Case("r6", true)
+ .Case("r7", true)
+ .Case("r8", true)
+ .Case("r9", true)
+ .Case("r10", true)
+ .Case("r11", true)
+ .Case("sp", true)
+ .Default(false);
+ HasSizeMismatch = false;
+ return isValid;
+}
+
+bool ARMTargetInfo::isRegisterReservedGlobally(StringRef RegName) const {
+ // The "sp" register does not have a -ffixed-sp option,
+ // so reserve it unconditionally.
+ if (RegName.equals("sp"))
+ return true;
+
+ // reserve rN (N:6-11) registers only if the corresponding
+ // +reserve-rN feature is found
+ const std::vector<std::string> &Features = getTargetOpts().Features;
+ const std::string SearchFeature = "+reserve-" + RegName.str();
+ for (const std::string &Feature : Features) {
+ if (Feature.compare(SearchFeature) == 0)
+ return true;
+ }
+ return false;
+}
+
bool ARMTargetInfo::validateAsmConstraint(
const char *&Name, TargetInfo::ConstraintInfo &Info) const {
switch (*Name) {
diff --git a/clang/lib/Basic/Targets/ARM.h b/clang/lib/Basic/Targets/ARM.h
index ce87a6265934..90fb20f8f7a5 100644
--- a/clang/lib/Basic/Targets/ARM.h
+++ b/clang/lib/Basic/Targets/ARM.h
@@ -161,6 +161,9 @@ class LLVM_LIBRARY_VISIBILITY ARMTargetInfo : public TargetInfo {
ArrayRef<const char *> getGCCRegNames() const override;
ArrayRef<TargetInfo::GCCRegAlias> getGCCRegAliases() const override;
+ bool validateGlobalRegisterVariable(StringRef RegName, unsigned RegSize,
+ bool &HasSizeMismatch) const override;
+ bool isRegisterReservedGlobally(StringRef RegName) const override;
bool validateAsmConstraint(const char *&Name,
TargetInfo::ConstraintInfo &Info) const override;
std::string convertConstraint(const char *&Constraint) const override;
diff --git a/clang/lib/Driver/ToolChains/Arch/ARM.cpp b/clang/lib/Driver/ToolChains/Arch/ARM.cpp
index 68a57310ad40..cca47722c204 100644
--- a/clang/lib/Driver/ToolChains/Arch/ARM.cpp
+++ b/clang/lib/Driver/ToolChains/Arch/ARM.cpp
@@ -592,11 +592,39 @@ void arm::getARMTargetFeatures(const ToolChain &TC,
Features.push_back("+strict-align");
}
- // llvm does not support reserving registers in general. There is support
- // for reserving r9 on ARM though (defined as a platform-specific register
- // in ARM EABI).
- if (Args.hasArg(options::OPT_ffixed_r9))
- Features.push_back("+reserve-r9");
+ // Do not allow r9 reservation with -frwpi.
+ if (Args.hasArg(options::OPT_ffixed_r9) && Args.hasArg(options::OPT_frwpi)) {
+ Arg *A = Args.getLastArg(options::OPT_ffixed_r9);
+ Arg *B = Args.getLastArg(options::OPT_frwpi);
+ D.Diag(diag::err_opt_not_valid_with_opt)
+ << A->getAsString(Args) << B->getAsString(Args);
+ }
+
+ // The compiler can still use a FP in certain circumstances,
+ // even when frame pointer elimination is enabled. Thus we should
+ // not allow to reserve a target's FP register.
+ const llvm::opt::OptSpecifier RestrictFPOpt =
+ (Triple.isOSDarwin() || (!Triple.isOSWindows() && Triple.isThumb()))
+ ? options::OPT_ffixed_r7
+ : options::OPT_ffixed_r11;
+ if (Args.hasArg(RestrictFPOpt)) {
+ const std::string OptStr =
+ Args.getLastArg(RestrictFPOpt)->getAsString(Args);
+ const unsigned int SubStrIndex = strlen("ffixed-r");
+ D.Diag(diag::err_reserved_frame_pointer)
+ << OptStr << OptStr.substr(SubStrIndex);
+ }
+
+// Reservation of general purpose registers.
+#define HANDLE_FFIXED_R(n) \
+ if (Args.hasArg(options::OPT_ffixed_r##n)) \
+ Features.push_back("+reserve-r" #n)
+ HANDLE_FFIXED_R(6);
+ HANDLE_FFIXED_R(7);
+ HANDLE_FFIXED_R(8);
+ HANDLE_FFIXED_R(9);
+ HANDLE_FFIXED_R(10);
+ HANDLE_FFIXED_R(11);
// The kext linker doesn't know how to deal with movw/movt.
if (KernelOrKext || Args.hasArg(options::OPT_mno_movt))
diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp
index aba7049b0a51..b469217108ce 100644
--- a/clang/lib/Sema/SemaDecl.cpp
+++ b/clang/lib/Sema/SemaDecl.cpp
@@ -7009,6 +7009,8 @@ NamedDecl *Sema::ActOnVariableDeclarator(
Diag(E->getExprLoc(), diag::err_asm_invalid_global_var_reg) << Label;
else if (HasSizeMismatch)
Diag(E->getExprLoc(), diag::err_asm_register_size_mismatch) << Label;
+ else if (!TI.isRegisterReservedGlobally(Label))
+ Diag(E->getExprLoc(), diag::err_asm_missing_fixed_reg_opt) << Label;
}
if (!R->isIntegralType(Context) && !R->isPointerType()) {
diff --git a/clang/test/Driver/arm-reserved-reg-options.c b/clang/test/Driver/arm-reserved-reg-options.c
new file mode 100644
index 000000000000..e97c717d7e7e
--- /dev/null
+++ b/clang/test/Driver/arm-reserved-reg-options.c
@@ -0,0 +1,35 @@
+// ## FP ARM + Thumb
+// RUN: %clang -target arm-arm-none-eabi -### -ffixed-r11 -c %s 2>&1 | FileCheck -check-prefix=CHECK-ERROR-R11 %s
+// RUN: %clang -target arm-arm-none-eabi -### -ffixed-r7 -c %s 2>&1 | FileCheck -check-prefix=CHECK-NO-ERROR %s
+
+// RUN: %clang -target arm-arm-none-eabi -### -ffixed-r7 -mthumb -c %s 2>&1 | FileCheck -check-prefix=CHECK-ERROR-R7 %s
+// RUN: %clang -target arm-arm-none-eabi -### -ffixed-r11 -mthumb -c %s 2>&1 | FileCheck -check-prefix=CHECK-NO-ERROR %s
+
+// RUN: %clang -target thumbv6m-none-eabi -### -ffixed-r7 -c %s 2>&1 | FileCheck -check-prefix=CHECK-ERROR-R7 %s
+// RUN: %clang -target thumbv6m-none-eabi -### -ffixed-r11 -c %s 2>&1 | FileCheck -check-prefix=CHECK-NO-ERROR %s
+
+// ## FP Darwin (R7)
+// RUN: %clang -target armv6-apple-darwin9 -### -ffixed-r7 -c %s 2>&1 | FileCheck -check-prefix=CHECK-ERROR-R7 %s
+// RUN: %clang -target armv6-apple-darwin9 -### -ffixed-r11 -c %s 2>&1 | FileCheck -check-prefix=CHECK-NO-ERROR %s
+
+// RUN: %clang -target armv6-apple-ios3 -### -ffixed-r7 -c %s 2>&1 | FileCheck -check-prefix=CHECK-ERROR-R7 %s
+// RUN: %clang -target armv6-apple-ios3 -### -ffixed-r11 -c %s 2>&1 | FileCheck -check-prefix=CHECK-NO-ERROR %s
+
+// RUN: %clang -target armv7s-apple-darwin10 -### -ffixed-r7 -c %s 2>&1 | FileCheck -check-prefix=CHECK-ERROR-R7 %s
+// RUN: %clang -target armv7s-apple-darwin10 -### -ffixed-r11 -c %s 2>&1 | FileCheck -check-prefix=CHECK-NO-ERROR %s
+
+// ## FP Windows (R11)
+// RUN: %clang -target armv7-windows -### -ffixed-r11 -c %s 2>&1 | FileCheck -check-prefix=CHECK-ERROR-R11 %s
+// RUN: %clang -target armv7-windows -### -ffixed-r7 -c %s 2>&1 | FileCheck -check-prefix=CHECK-NO-ERROR %s
+
+// ## FRWPI (R9)
+// RUN: %clang -target arm-arm-none-eabi -### -frwpi -ffixed-r9 -c %s 2>&1 | FileCheck -check-prefix=CHECK-RESERVED-FRWPI-CONFLICT %s
+// RUN: %clang -target arm-arm-none-eabi -### -ffixed-r9 -c %s 2>&1 | FileCheck -check-prefix=CHECK-RESERVED-FRWPI-VALID %s
+// RUN: %clang -target arm-arm-none-eabi -### -frwpi -c %s 2>&1 | FileCheck -check-prefix=CHECK-RESERVED-FRWPI-VALID %s
+
+// CHECK-ERROR-R11: error: '-ffixed-r11' has been specified but 'r11' is used as the frame pointer for this target
+// CHECK-ERROR-R7: error: '-ffixed-r7' has been specified but 'r7' is used as the frame pointer for this target
+// CHECK-NO-ERROR-NOT: may still be used as a frame pointer
+
+// CHECK-RESERVED-FRWPI-CONFLICT: option '-ffixed-r9' cannot be specified with '-frwpi'
+// CHECK-RESERVED-FRWPI-VALID-NOT: option '-ffixed-r9' cannot be specified with '-frwpi'
diff --git a/clang/test/Sema/arm-global-regs.c b/clang/test/Sema/arm-global-regs.c
new file mode 100644
index 000000000000..753cb60e6838
--- /dev/null
+++ b/clang/test/Sema/arm-global-regs.c
@@ -0,0 +1,20 @@
+// RUN: %clang_cc1 -ffreestanding -fsyntax-only -target-feature +reserve-r9 -verify -triple arm-arm-none-eabi %s
+
+// Check a small subset of valid and invalid global register variable declarations.
+// Also check that for global register variables without -ffixed-reg options it throws an error.
+
+register unsigned arm_r3 __asm("r3"); //expected-error {{register 'r3' unsuitable for global register variables on this target}}
+
+register unsigned arm_r12 __asm("r12"); //expected-error {{register 'r12' unsuitable for global register variables on this target}}
+
+register unsigned arm_r5 __asm("r5"); //expected-error {{register 'r5' unsuitable for global register variables on this target}}
+
+register unsigned arm_r9 __asm("r9");
+
+register unsigned arm_r6 __asm("r6"); //expected-error {{-ffixed-r6 is required for global named register variable declaration}}
+
+register unsigned arm_r7 __asm("r7"); //expected-error {{-ffixed-r7 is required for global named register variable declaration}}
+
+register unsigned *parm_r7 __asm("r7"); //expected-error {{-ffixed-r7 is required for global named register variable declaration}}
+
+register unsigned arm_sp __asm("sp");
diff --git a/llvm/lib/Target/ARM/ARM.td b/llvm/lib/Target/ARM/ARM.td
index 66bfd4c82e25..285dad1cf29a 100644
--- a/llvm/lib/Target/ARM/ARM.td
+++ b/llvm/lib/Target/ARM/ARM.td
@@ -391,9 +391,11 @@ def FeatureExecuteOnly : SubtargetFeature<"execute-only",
"Enable the generation of "
"execute only code.">;
-def FeatureReserveR9 : SubtargetFeature<"reserve-r9", "ReserveR9", "true",
- "Reserve R9, making it unavailable"
- " as GPR">;
+foreach i = {6-11} in
+ def FeatureReserveR#i : SubtargetFeature<"reserve-r"#i,
+ "ReservedGPRegisters["#i#"]", "true",
+ "Reserve R"#i#", making it "
+ "unavailable as a GPR">;
def FeatureNoMovt : SubtargetFeature<"no-movt", "NoMovt", "true",
"Don't use movt/movw pairs for "
diff --git a/llvm/lib/Target/ARM/ARMAsmPrinter.cpp b/llvm/lib/Target/ARM/ARMAsmPrinter.cpp
index ed0969fa625b..10153dd2e395 100644
--- a/llvm/lib/Target/ARM/ARMAsmPrinter.cpp
+++ b/llvm/lib/Target/ARM/ARMAsmPrinter.cpp
@@ -752,7 +752,7 @@ void ARMAsmPrinter::emitAttributes() {
if (STI.isRWPI())
ATS.emitAttribute(ARMBuildAttrs::ABI_PCS_R9_use,
ARMBuildAttrs::R9IsSB);
- else if (STI.isR9Reserved())
+ else if (STI.isGPRegisterReserved(9))
ATS.emitAttribute(ARMBuildAttrs::ABI_PCS_R9_use,
ARMBuildAttrs::R9Reserved);
else
diff --git a/llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp b/llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp
index 4ace52b32e9f..afcdb648cbc8 100644
--- a/llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp
@@ -198,9 +198,11 @@ getReservedRegs(const MachineFunction &MF) const {
markSuperRegs(Reserved, getFramePointerReg(STI));
if (hasBasePointer(MF))
markSuperRegs(Reserved, BasePtr);
- // Some targets reserve R9.
- if (STI.isR9Reserved())
- markSuperRegs(Reserved, ARM::R9);
+ for (size_t R = 0; R < ARM::GPRRegClass.getNumRegs(); ++R) {
+ if (STI.isGPRegisterReserved(R)) {
+ markSuperRegs(Reserved, ARM::R0 + R);
+ }
+ }
// Reserve D16-D31 if the subtarget doesn't support them.
if (!STI.hasD32()) {
static_assert(ARM::D31 == ARM::D16 + 15, "Register list not consecutive!");
@@ -280,7 +282,7 @@ ARMBaseRegisterInfo::getRegPressureLimit(const TargetRegisterClass *RC,
case ARM::GPRRegClassID: {
bool HasFP = MF.getFrameInfo().isMaxCallFrameSizeComputed()
? TFI->hasFP(MF) : true;
- return 10 - HasFP - (STI.isR9Reserved() ? 1 : 0);
+ return 10 - HasFP - STI.getNumGPRegistersReserved();
}
case ARM::SPRRegClassID: // Currently not used as 'rep' register class.
case ARM::DPRRegClassID:
@@ -380,6 +382,11 @@ bool ARMBaseRegisterInfo::hasBasePointer(const MachineFunction &MF) const {
const MachineFrameInfo &MFI = MF.getFrameInfo();
const ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
const ARMFrameLowering *TFI = getFrameLowering(MF);
+ const ARMSubtarget &STI = MF.getSubtarget<ARMSubtarget>();
+
+ // Disable base pointer R6 if -ffixed-r6 is used.
+ if (STI.isGPRegisterReserved(BasePtr - ARM::R0))
+ return false;
// If we have stack realignment and VLAs, we have no pointer to use to
// access the stack. If we have stack realignment, and a large call frame,
@@ -416,6 +423,7 @@ bool ARMBaseRegisterInfo::hasBasePointer(const MachineFunction &MF) const {
bool ARMBaseRegisterInfo::canRealignStack(const MachineFunction &MF) const {
const MachineRegisterInfo *MRI = &MF.getRegInfo();
const ARMFrameLowering *TFI = getFrameLowering(MF);
+ const ARMSubtarget &STI = MF.getSubtarget<ARMSubtarget>();
// We can't realign the stack if:
// 1. Dynamic stack realignment is explicitly disabled,
// 2. There are VLAs in the function and the base pointer is disabled.
@@ -425,6 +433,9 @@ bool ARMBaseRegisterInfo::canRealignStack(const MachineFunction &MF) const {
// register allocation with frame pointer elimination, it is too late now.
if (!MRI->canReserveReg(getFramePointerReg(MF.getSubtarget<ARMSubtarget>())))
return false;
+ // Disable base pointer R6 if -ffixed-r6 is used.
+ if (STI.isGPRegisterReserved(BasePtr - ARM::R0))
+ return false;
// We may also need a base pointer if there are dynamic allocas or stack
// pointer adjustments around calls.
if (TFI->hasReservedCallFrame(MF))
diff --git a/llvm/lib/Target/ARM/ARMFrameLowering.cpp b/llvm/lib/Target/ARM/ARMFrameLowering.cpp
index 5428bd6c94b3..106894e28f03 100644
--- a/llvm/lib/Target/ARM/ARMFrameLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMFrameLowering.cpp
@@ -1704,6 +1704,19 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF,
const MCPhysReg *CSRegs = RegInfo->getCalleeSavedRegs(&MF);
for (unsigned i = 0; CSRegs[i]; ++i) {
unsigned Reg = CSRegs[i];
+ if (STI.isRWPI() && Reg == ARM::R9) {
+ // Paranoid check for use of R9 with RWPI. Clobbering R9 with -frwpi will
+ // emit warnings about undefined behaviour but maybe theres's a valid use
+ // case so on that basis allow it to be pushed/popped in the
+ // prologue/epilogue.
+ } else if (Reg > ARM::R0 && ARM::GPRRegClass.contains(Reg) &&
+ STI.isGPRegisterReserved(Reg - ARM::R0)) {
+ LLVM_DEBUG(dbgs() << printReg(Reg, TRI) << " has been reserved and"
+ << " should not be allocatable"
+ << " or spillable.\n");
+ SavedRegs.reset(Reg);
+ continue;
+ }
bool Spilled = false;
if (SavedRegs.test(Reg)) {
Spilled = true;
@@ -1948,7 +1961,7 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF,
LLVM_DEBUG(dbgs() << printReg(Reg, TRI)
<< " is saved low register, RegDeficit = "
<< RegDeficit << "\n");
- } else {
+ } else if (!STI.isGPRegisterReserved(Reg - ARM::R0)) {
AvailableRegs.push_back(Reg);
LLVM_DEBUG(
dbgs()
@@ -1963,7 +1976,7 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF,
--RegDeficit;
LLVM_DEBUG(dbgs() << "%r7 is saved low register, RegDeficit = "
<< RegDeficit << "\n");
- } else {
+ } else if (!STI.isGPRegisterReserved(7)) {
AvailableRegs.push_back(ARM::R7);
LLVM_DEBUG(
dbgs()
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index c395a4feea70..b1d1d4fd5fc9 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -5572,9 +5572,15 @@ SDValue ARMTargetLowering::LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const {
Register ARMTargetLowering::getRegisterByName(const char* RegName, EVT VT,
const MachineFunction &MF) const {
Register Reg = StringSwitch<unsigned>(RegName)
- .Case("sp", ARM::SP)
- .Default(0);
- if (Reg)
+ .Case("r6", ARM::R6)
+ .Case("r7", ARM::R7)
+ .Case("r8", ARM::R8)
+ .Case("r9", ARM::R9)
+ .Case("r10", ARM::R10)
+ .Case("r11", ARM::R11)
+ .Case("sp", ARM::SP)
+ .Default(ARM::NoRegister);
+ if (Reg != ARM::NoRegister)
return Reg;
report_fatal_error(Twine("Invalid register name \""
+ StringRef(RegName) + "\"."));
diff --git a/llvm/lib/Target/ARM/ARMSubtarget.cpp b/llvm/lib/Target/ARM/ARMSubtarget.cpp
index eb4d39b01cbb..7a57376a6895 100644
--- a/llvm/lib/Target/ARM/ARMSubtarget.cpp
+++ b/llvm/lib/Target/ARM/ARMSubtarget.cpp
@@ -98,8 +98,9 @@ ARMSubtarget::ARMSubtarget(const Triple &TT, const std::string &CPU,
const ARMBaseTargetMachine &TM, bool IsLittle,
bool MinSize)
: ARMGenSubtargetInfo(TT, CPU, FS), UseMulOps(UseFusedMulOps),
- CPUString(CPU), OptMinSize(MinSize), IsLittle(IsLittle),
- TargetTriple(TT), Options(TM.Options), TM(TM),
+ ReservedGPRegisters(ARM::GPRRegClass.getNumRegs()), CPUString(CPU),
+ OptMinSize(MinSize), IsLittle(IsLittle), TargetTriple(TT),
+ Options(TM.Options), TM(TM),
FrameLowering(initializeFrameLowering(CPU, FS)),
// At this point initializeSubtargetDependencies has been called so
// we can query directly.
@@ -253,8 +254,18 @@ void ARMSubtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
(Options.UnsafeFPMath || isTargetDarwin()))
UseNEONForSinglePrecisionFP = true;
- if (isRWPI())
- ReserveR9 = true;
+ if (isRWPI() || (isTargetMachO() && !HasV6Ops))
+ ReservedGPRegisters.set(9);
+
+ // Throw an error when trying to reserve a target's FP register. It may
+ // be used by the compiler even when frame pointer elimination is enabled.
+ // FIXME: Throw this error if -frame-pointer=none is not set; otherwise
+ // only emit a warning.
+ const int restFP = (useR7AsFramePointer()) ? 7 : 11;
+ if (isGPRegisterReserved(restFP))
+ report_fatal_error(
+ "Register r" + std::to_string(restFP) +
+ " has been specified but is used as the frame pointer for this target.");
// If MVEVectorCostFactor is still 0 (has not been set to anything else), default it to 2
if (MVEVectorCostFactor == 0)
diff --git a/llvm/lib/Target/ARM/ARMSubtarget.h b/llvm/lib/Target/ARM/ARMSubtarget.h
index f582a92f6563..c5836a3eca7b 100644
--- a/llvm/lib/Target/ARM/ARMSubtarget.h
+++ b/llvm/lib/Target/ARM/ARMSubtarget.h
@@ -229,8 +229,8 @@ class ARMSubtarget : public ARMGenSubtargetInfo {
/// NoARM - True if subtarget does not support ARM mode execution.
bool NoARM = false;
- /// ReserveR9 - True if R9 is not available as a general purpose register.
- bool ReserveR9 = false;
+ // ReservedGPRegisters[i] - R#i is not available as a general purpose register
+ BitVector ReservedGPRegisters;
/// NoMovt - True if MOVT / MOVW pairs are not used for materialization of
/// 32-bit imms (including global addresses).
@@ -763,8 +763,9 @@ class ARMSubtarget : public ARMGenSubtargetInfo {
bool isAClass() const { return ARMProcClass == AClass; }
bool isReadTPHard() const { return ReadTPHard; }
- bool isR9Reserved() const {
- return isTargetMachO() ? (ReserveR9 || !HasV6Ops) : ReserveR9;
+ bool isGPRegisterReserved(size_t i) const { return ReservedGPRegisters[i]; }
+ unsigned getNumGPRegistersReserved() const {
+ return ReservedGPRegisters.count();
}
bool useR7AsFramePointer() const {
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
index 5bb3bcaf10e7..c1fd01d2df9d 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
@@ -76,7 +76,9 @@ class ARMTTIImpl : public BasicTTIImplBase<ARMTTIImpl> {
ARM::FeatureDSP, ARM::FeatureMP, ARM::FeatureVirtualization,
ARM::FeatureMClass, ARM::FeatureRClass, ARM::FeatureAClass,
ARM::FeatureNaClTrap, ARM::FeatureStrictAlign, ARM::FeatureLongCalls,
- ARM::FeatureExecuteOnly, ARM::FeatureReserveR9, ARM::FeatureNoMovt,
+ ARM::FeatureExecuteOnly, ARM::FeatureReserveR6, ARM::FeatureReserveR7,
+ ARM::FeatureReserveR8, ARM::FeatureReserveR9, ARM::FeatureReserveR10,
+ ARM::FeatureReserveR11, ARM::FeatureNoMovt,
ARM::FeatureNoNegativeImmediates
};
diff --git a/llvm/test/CodeGen/ARM/reg-alloc-fixed-r6-vla.ll b/llvm/test/CodeGen/ARM/reg-alloc-fixed-r6-vla.ll
new file mode 100644
index 000000000000..0b6fd7443af2
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/reg-alloc-fixed-r6-vla.ll
@@ -0,0 +1,44 @@
+; Using VLAs(Variable Length Arrays) in a function will use R6 to keep track
+; of the stack frame, and also spill/restore R6 to the stack.
+; This tests that using -ffixed-r6 (-mattr=+reserve-r6) will stop R6
+; being used and also stop it being spilled/restored to the stack.
+; RUN: llc < %s -mcpu=cortex-m0 -mtriple=thumbv7-arm-none-eabi | FileCheck %s --check-prefix=CHECK-STATIC --check-prefix=CHECK-R6
+; RUN: llc < %s -mcpu=cortex-m0 -mtriple=thumbv7-arm-none-eabi -mattr=+reserve-r6 | FileCheck %s --check-prefix=CHECK-STATIC --check-prefix=CHECK-NO-R6
+
+define void @f() #0 {
+entry:
+ %i = alloca i32, align 4
+ store i32 0, i32* %i, align 4
+
+ %saved_stack = alloca i8*, align 4
+ %0 = call i8* @llvm.stacksave()
+ store i8* %0, i8** %saved_stack, align 4
+
+ %__vla_expr0 = alloca i32, align 4
+ %1 = load i32, i32* %i, align 4
+ %vla = alloca double, i32 %1, align 8
+ store i32 %1, i32* %__vla_expr0, align 4
+
+ %2 = load i8*, i8** %saved_stack, align 4
+ call void @llvm.stackrestore(i8* %2)
+
+ ret void
+}
+
+declare i8* @llvm.stacksave() #1
+declare void @llvm.stackrestore(i8* %ptr) #1
+
+attributes #0 = { noinline nounwind "stackrealign" }
+attributes #1 = { nounwind }
+
+; CHECK-STATIC: push {r4,
+; CHECK-R6: r6
+; CHECK-NO-R6-NOT: r6
+; CHECK-STATIC: lr}
+; CHECK-R6: r6
+; CHECK-NO-R6-NOT: r6
+; CHECK-STATIC: pop {r4,
+; CHECK-R6: r6
+; CHECK-NO-R6-NOT: r6
+; CHECK-STATIC: pc}
+
diff --git a/llvm/test/CodeGen/ARM/reg-alloc-with-fixed-reg-r6-modified.ll b/llvm/test/CodeGen/ARM/reg-alloc-with-fixed-reg-r6-modified.ll
new file mode 100644
index 000000000000..e2a4af87dde7
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/reg-alloc-with-fixed-reg-r6-modified.ll
@@ -0,0 +1,63 @@
+; RUN: llc < %s -mattr=+reserve-r6 -mtriple=arm-linux-gnueabi -O0 -filetype=asm --regalloc=fast 2>&1 | FileCheck %s
+;
+; Equivalent C source code
+; register unsigned r6 asm("r6");
+; void bar(unsigned int i,
+; unsigned int j,
+; unsigned int k,
+; unsigned int l,
+; unsigned int m,
+; unsigned int n,
+; unsigned int o,
+; unsigned int p)
+; {
+; r6 = 10;
+; unsigned int result = i + j + k + l + m + n + o + p;
+; }
+declare void @llvm.write_register.i32(metadata, i32) nounwind
+
+define void @bar(i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p) nounwind {
+entry:
+; CHECK-NOT: push {{{.*}}r6,{{.*}}}
+; CHECK: {{.*}}mov{{.*}}r6,{{.*}}
+; CHECK-NOT: {{.*}}r6{{.*}}
+ %i.addr = alloca i32, align 4
+ %j.addr = alloca i32, align 4
+ %k.addr = alloca i32, align 4
+ %l.addr = alloca i32, align 4
+ %m.addr = alloca i32, align 4
+ %n.addr = alloca i32, align 4
+ %o.addr = alloca i32, align 4
+ %p.addr = alloca i32, align 4
+ %result = alloca i32, align 4
+ store i32 %i, i32* %i.addr, align 4
+ store i32 %j, i32* %j.addr, align 4
+ store i32 %k, i32* %k.addr, align 4
+ store i32 %l, i32* %l.addr, align 4
+ store i32 %m, i32* %m.addr, align 4
+ store i32 %n, i32* %n.addr, align 4
+ store i32 %o, i32* %o.addr, align 4
+ store i32 %p, i32* %p.addr, align 4
+ call void @llvm.write_register.i32(metadata !0, i32 10)
+ %0 = load i32, i32* %i.addr, align 4
+ %1 = load i32, i32* %j.addr, align 4
+ %add = add i32 %0, %1
+ %2 = load i32, i32* %k.addr, align 4
+ %add1 = add i32 %add, %2
+ %3 = load i32, i32* %l.addr, align 4
+ %add2 = add i32 %add1, %3
+ %4 = load i32, i32* %m.addr, align 4
+ %add3 = add i32 %add2, %4
+ %5 = load i32, i32* %n.addr, align 4
+ %add4 = add i32 %add3, %5
+ %6 = load i32, i32* %o.addr, align 4
+ %add5 = add i32 %add4, %6
+ %7 = load i32, i32* %p.addr, align 4
+ %add6 = add i32 %add5, %7
+ store i32 %add6, i32* %result, align 4
+ ret void
+}
+
+!llvm.named.register.r6 = !{!0}
+!0 = !{!"r6"}
+
diff --git a/llvm/test/CodeGen/ARM/reg-alloc-with-fixed-reg-r6.ll b/llvm/test/CodeGen/ARM/reg-alloc-with-fixed-reg-r6.ll
new file mode 100644
index 000000000000..3647c0701a7c
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/reg-alloc-with-fixed-reg-r6.ll
@@ -0,0 +1,57 @@
+; RUN: llc < %s -mattr=+reserve-r6 -mtriple=arm-linux-gnueabi -O0 -filetype=asm --regalloc=fast 2>&1 | FileCheck %s
+;
+; Equivalent C source code
+; void bar(unsigned int i,
+; unsigned int j,
+; unsigned int k,
+; unsigned int l,
+; unsigned int m,
+; unsigned int n,
+; unsigned int o,
+; unsigned int p)
+; {
+; unsigned int result = i + j + k + l + m + n + o + p;
+; }
+
+define void @bar(i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p) nounwind {
+entry:
+; CHECK-NOT: push {{{.*}}r6,{{.*}}}
+ %i.addr = alloca i32, align 4
+ %j.addr = alloca i32, align 4
+ %k.addr = alloca i32, align 4
+ %l.addr = alloca i32, align 4
+ %m.addr = alloca i32, align 4
+ %n.addr = alloca i32, align 4
+ %o.addr = alloca i32, align 4
+ %p.addr = alloca i32, align 4
+ %result = alloca i32, align 4
+ store i32 %i, i32* %i.addr, align 4
+ store i32 %j, i32* %j.addr, align 4
+ store i32 %k, i32* %k.addr, align 4
+ store i32 %l, i32* %l.addr, align 4
+ store i32 %m, i32* %m.addr, align 4
+ store i32 %n, i32* %n.addr, align 4
+ store i32 %o, i32* %o.addr, align 4
+ store i32 %p, i32* %p.addr, align 4
+ %0 = load i32, i32* %i.addr, align 4
+ %1 = load i32, i32* %j.addr, align 4
+ %add = add i32 %0, %1
+ %2 = load i32, i32* %k.addr, align 4
+ %add1 = add i32 %add, %2
+ %3 = load i32, i32* %l.addr, align 4
+ %add2 = add i32 %add1, %3
+ %4 = load i32, i32* %m.addr, align 4
+ %add3 = add i32 %add2, %4
+ %5 = load i32, i32* %n.addr, align 4
+ %add4 = add i32 %add3, %5
+ %6 = load i32, i32* %o.addr, align 4
+ %add5 = add i32 %add4, %6
+ %7 = load i32, i32* %p.addr, align 4
+ %add6 = add i32 %add5, %7
+ store i32 %add6, i32* %result, align 4
+; CHECK: {{.*}}r5{{.*}}
+; CHECK-NOT: {{.*}}r6{{.*}}
+ ret void
+; CHECK-NOT: pop {{{.*}}r6,{{.*}}}
+}
+
diff --git a/llvm/test/CodeGen/ARM/reg-alloc-wout-fixed-regs.ll b/llvm/test/CodeGen/ARM/reg-alloc-wout-fixed-regs.ll
new file mode 100644
index 000000000000..d1f020936a3d
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/reg-alloc-wout-fixed-regs.ll
@@ -0,0 +1,58 @@
+; RUN: llc < %s -mtriple=arm-linux-gnueabi -O0 -filetype=asm --regalloc=fast 2>&1 | FileCheck %s
+;
+; Equivalent C source code
+; void bar(unsigned int i,
+; unsigned int j,
+; unsigned int k,
+; unsigned int l,
+; unsigned int m,
+; unsigned int n,
+; unsigned int o,
+; unsigned int p)
+; {
+; unsigned int result = i + j + k + l + m + n + o + p;
+; }
+
+define void @bar(i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p) nounwind {
+entry:
+; CHECK: push {{{.*}}r4, r5{{.*}}}
+ %i.addr = alloca i32, align 4
+ %j.addr = alloca i32, align 4
+ %k.addr = alloca i32, align 4
+ %l.addr = alloca i32, align 4
+ %m.addr = alloca i32, align 4
+ %n.addr = alloca i32, align 4
+ %o.addr = alloca i32, align 4
+ %p.addr = alloca i32, align 4
+ %result = alloca i32, align 4
+ store i32 %i, i32* %i.addr, align 4
+ store i32 %j, i32* %j.addr, align 4
+ store i32 %k, i32* %k.addr, align 4
+ store i32 %l, i32* %l.addr, align 4
+ store i32 %m, i32* %m.addr, align 4
+ store i32 %n, i32* %n.addr, align 4
+ store i32 %o, i32* %o.addr, align 4
+ store i32 %p, i32* %p.addr, align 4
+ %0 = load i32, i32* %i.addr, align 4
+ %1 = load i32, i32* %j.addr, align 4
+ %add = add i32 %0, %1
+ %2 = load i32, i32* %k.addr, align 4
+ %add1 = add i32 %add, %2
+ %3 = load i32, i32* %l.addr, align 4
+ %add2 = add i32 %add1, %3
+ %4 = load i32, i32* %m.addr, align 4
+ %add3 = add i32 %add2, %4
+ %5 = load i32, i32* %n.addr, align 4
+ %add4 = add i32 %add3, %5
+ %6 = load i32, i32* %o.addr, align 4
+ %add5 = add i32 %add4, %6
+ %7 = load i32, i32* %p.addr, align 4
+ %add6 = add i32 %add5, %7
+ store i32 %add6, i32* %result, align 4
+; CHECK: {{.*}}r4{{.*}}
+; CHECK: {{.*}}r5{{.*}}
+
+; CHECK: pop {{{.*}}r4, r5{{.*}}}
+ ret void
+}
+
diff --git a/llvm/test/CodeGen/Thumb/callee_save_reserved.ll b/llvm/test/CodeGen/Thumb/callee_save_reserved.ll
new file mode 100644
index 000000000000..0329d7886a2a
--- /dev/null
+++ b/llvm/test/CodeGen/Thumb/callee_save_reserved.ll
@@ -0,0 +1,15 @@
+; RUN: llc < %s -mtriple=thumbv6m-none-eabi -verify-machineinstrs -frame-pointer=none -mattr=+reserve-r6,+reserve-r8 \
+; RUN: -asm-verbose=false | FileCheck --check-prefix=CHECK-INVALID %s
+
+; Reserved low registers should not be used to correct reg deficit.
+define <4 x i32> @four_high_four_return_reserved() {
+entry:
+ ; CHECK-INVALID-NOT: r{{6|8}}
+ tail call void asm sideeffect "", "~{r8},~{r9}"()
+ %vecinit = insertelement <4 x i32> undef, i32 1, i32 0
+ %vecinit11 = insertelement <4 x i32> %vecinit, i32 2, i32 1
+ %vecinit12 = insertelement <4 x i32> %vecinit11, i32 3, i32 2
+ %vecinit13 = insertelement <4 x i32> %vecinit12, i32 4, i32 3
+ ret <4 x i32> %vecinit13
+}
+
diff --git a/llvm/test/Feature/reserve_global_reg.ll b/llvm/test/Feature/reserve_global_reg.ll
new file mode 100644
index 000000000000..06081cae1fb2
--- /dev/null
+++ b/llvm/test/Feature/reserve_global_reg.ll
@@ -0,0 +1,29 @@
+; RUN: not llc < %s -mtriple=thumbv7-apple-darwin -mattr=+reserve-r7 -o - 2>&1 | FileCheck -check-prefix=CHECK-RESERVE-FP7 %s
+; RUN: not llc < %s -mtriple=armv7-windows-msvc -mattr=+reserve-r11 -o - 2>&1 | FileCheck -check-prefix=CHECK-RESERVE-FP11 %s
+; RUN: not llc < %s -mtriple=thumbv7-windows -mattr=+reserve-r11 -o - 2>&1 | FileCheck -check-prefix=CHECK-RESERVE-FP11-2 %s
+
+; int test(int a, int b, int c) {
+; return a + b + c;
+; }
+
+; Function Attrs: noinline nounwind optnone
+define hidden i32 @_Z4testiii(i32 %a, i32 %b, i32 %c) #0 {
+entry:
+ %a.addr = alloca i32, align 4
+ %b.addr = alloca i32, align 4
+ %c.addr = alloca i32, align 4
+ store i32 %a, i32* %a.addr, align 4
+ store i32 %b, i32* %b.addr, align 4
+ store i32 %c, i32* %c.addr, align 4
+ %0 = load i32, i32* %a.addr, align 4
+ %1 = load i32, i32* %b.addr, align 4
+ %add = add nsw i32 %0, %1
+ %2 = load i32, i32* %c.addr, align 4
+ %add1 = add nsw i32 %add, %2
+ ret i32 %add1
+}
+
+; CHECK-RESERVE-FP7: Register r7 has been specified but is used as the frame pointer for this target.
+; CHECK-RESERVE-FP11: Register r11 has been specified but is used as the frame pointer for this target.
+; CHECK-RESERVE-FP11-2: Register r11 has been specified but is used as the frame pointer for this target.
+
More information about the cfe-commits
mailing list