[AArch64][SME] Resume streaming-mode on entry to exception handlers

llvm/include/llvm/CodeGen/TargetLowering.h

@@ -4686,6 +4686,13 @@ class LLVM_ABI TargetLowering : public TargetLoweringBase {
     llvm_unreachable("Not Implemented");
   }
 
+  /// Optional target hook to add target-specific actions when entering EH pad
+  /// blocks. The implementation should return the resulting token chain value.
+  virtual SDValue lowerEHPadEntry(SDValue Chain, const SDLoc &DL,
+                                  SelectionDAG &DAG) const {
+    return SDValue();
+  }
+
   virtual void markLibCallAttributes(MachineFunction *MF, unsigned CC,
                                      ArgListTy &Args) const {}
 

llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp

@@ -1729,10 +1729,18 @@ void SelectionDAGISel::SelectAllBasicBlocks(const Function &Fn) {
     // Setup an EH landing-pad block.
     FuncInfo->ExceptionPointerVirtReg = Register();
     FuncInfo->ExceptionSelectorVirtReg = Register();
-    if (LLVMBB->isEHPad())
+    if (LLVMBB->isEHPad()) {
       if (!PrepareEHLandingPad())
         continue;
 
+      if (!FastIS) {
+        SDValue NewRoot = TLI->lowerEHPadEntry(CurDAG->getRoot(),
+                                               SDB->getCurSDLoc(), *CurDAG);
+        if (NewRoot && NewRoot != CurDAG->getRoot())
+          CurDAG->setRoot(NewRoot);
+      }
+    }
+
     // Before doing SelectionDAG ISel, see if FastISel has been requested.
     if (FastIS) {
       if (LLVMBB != &Fn.getEntryBlock())

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -7908,6 +7908,39 @@ static bool isPassedInFPR(EVT VT) {
          (VT.isFloatingPoint() && !VT.isScalableVector());
 }
 
+SDValue AArch64TargetLowering::lowerEHPadEntry(SDValue Chain, SDLoc const &DL,
+                                               SelectionDAG &DAG) const {
+  assert(Chain.getOpcode() == ISD::EntryToken && "Unexpected Chain value");
+  SDValue Glue = Chain.getValue(1);
+
+  MachineFunction &MF = DAG.getMachineFunction();
+  SMEAttrs SMEFnAttrs = MF.getInfo<AArch64FunctionInfo>()->getSMEFnAttrs();
+
+  // Exception handlers are entered with:
+  // - PSTATE.SM is 0.
+  // - PSTATE.ZA is 0.
+  // - TPIDR2_EL0 is null.
+  // See:
+  // https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#exceptions
+  //
+  // Therefore, if the function that contains this exception handler is a
+  // streaming[-compatible] function, we must re-enable streaming mode.
+  //
+  // These mode changes are usually optimized away in catch blocks as they
+  // occur before the __cxa_begin_catch (which is a non-streaming function),
+  // but are necessary in some cases (such as for cleanups).
+
+  if (SMEFnAttrs.hasStreamingInterfaceOrBody())
+    return changeStreamingMode(DAG, DL, /*Enable=*/true, Chain,
+                               /*Glue*/ Glue, AArch64SME::Always);
+
+  if (SMEFnAttrs.hasStreamingCompatibleInterface())
+    return changeStreamingMode(DAG, DL, /*Enable=*/true, Chain, Glue,
+                               AArch64SME::IfCallerIsStreaming);
+
+  return Chain;
+}
+
 SDValue AArch64TargetLowering::LowerFormalArguments(
     SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
     const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &DL,

llvm/lib/Target/AArch64/AArch64ISelLowering.h

@@ -575,6 +575,9 @@ class AArch64TargetLowering : public TargetLowering {
 
   bool shouldExpandBuildVectorWithShuffles(EVT, unsigned) const override;
 
+  SDValue lowerEHPadEntry(SDValue Chain, SDLoc const &DL,
+                          SelectionDAG &DAG) const override;
+
   SDValue LowerFormalArguments(SDValue Chain, CallingConv::ID CallConv,
                                bool isVarArg,
                                const SmallVectorImpl<ISD::InputArg> &Ins,

llvm/test/CodeGen/AArch64/sme-streaming-mode-landingpads.ll

@@ -0,0 +1,198 @@
+; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=aarch64 -aarch64-streaming-hazard-size=0 -mattr=+sme,+sve -stop-before=finalize-isel -verify-machineinstrs < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+declare void @"StreamingCleanup::~StreamingCleanup"(ptr %this) nounwind "aarch64_pstate_sm_enabled"
+declare void @"StreamingCompatCleanup::~StreamingCompatCleanup"(ptr %this) nounwind "aarch64_pstate_sm_compatible"
+
+declare void @may_throw() "aarch64_pstate_sm_compatible"
+
+; This test models the kind of IR clang would emit for the following C++:
+;
+; struct StreamingCleanup {
+;     ~StreamingCleanup() __arm_streaming
+; };
+;
+; void may_throw() __arm_streaming_compatible;
+;
+; void streaming_with_cleanup() __arm_streaming {
+;     StreamingCleanup cleanup;
+;     may_throw();
+; }
+;
+; This is a streaming function and all callees of this function are streaming[-compatible]
+; functions (including the StreamingCleanup destructor). This means call lowering will not
+; insert any streaming mode switches. However, if "may_throw" throws an exception, the
+; unwinder can re-enter this function (in %unwind_cleanup) to run the "StreamingCleanup"
+; destructor. The unwinder will always re-enter functions with streaming-mode disabled, so
+; we must ensure streaming-mode is enabled on entry to exception handlers.
+define void @streaming_with_cleanup() "aarch64_pstate_sm_enabled" personality ptr @__gxx_personality_v0 {
+  ; CHECK-LABEL: name: streaming_with_cleanup
+  ; CHECK: bb.0 (%ir-block.0):
+  ; CHECK-NEXT:   successors: %bb.1(0x7ffff800), %bb.2(0x00000800)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   BL @may_throw, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   B %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1.normal_return:
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   [[ADDXri:%[0-9]+]]:gpr64sp = ADDXri %stack.0.cleanup, 0, 0
+  ; CHECK-NEXT:   $x0 = COPY [[ADDXri]]
+  ; CHECK-NEXT:   BL @"StreamingCleanup::~StreamingCleanup", csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   RET_ReallyLR
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2.unwind_cleanup (landing-pad):
+  ; CHECK-NEXT:   liveins: $x0, $x1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64all = COPY killed $x1
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:gpr64all = COPY killed $x0
+  ; CHECK-NEXT:   MSRpstatesvcrImm1 1, 1, csr_aarch64_smstartstop, implicit-def dead $nzcv, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   [[ADDXri1:%[0-9]+]]:gpr64sp = ADDXri %stack.0.cleanup, 0, 0
+  ; CHECK-NEXT:   $x0 = COPY [[ADDXri1]]
+  ; CHECK-NEXT:   BL @"StreamingCleanup::~StreamingCleanup", csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   MSRpstatesvcrImm1 1, 0, csr_aarch64_smstartstop, implicit-def dead $nzcv, implicit-def $sp, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  ; CHECK-NEXT:   $x0 = COPY [[COPY1]]
+  ; CHECK-NEXT:   BL @_Unwind_Resume, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   MSRpstatesvcrImm1 1, 1, csr_aarch64_smstartstop, implicit-def dead $nzcv, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  %cleanup = alloca i8, align 1
+  invoke void @may_throw()
+          to label %normal_return unwind label %unwind_cleanup
+
+normal_return:
+  call void @"StreamingCleanup::~StreamingCleanup"(ptr %cleanup)
+  ret void
+
+unwind_cleanup:
+  %eh_info = landingpad { ptr, i32 }
+          cleanup
+  call void @"StreamingCleanup::~StreamingCleanup"(ptr %cleanup)
+  resume { ptr, i32 } %eh_info
+}
+
+; This test is the same as "streaming_with_cleanup", but now the function and destructor
+; are streaming-compatible functions. In this case, when we enter the exception handler,
+; we must switch to streaming-mode "streaming_compatible_with_cleanup" was entered with
+; during normal execution (i.e., EntryPStateSM).
+define void @streaming_compatible_with_cleanup() "aarch64_pstate_sm_compatible" personality ptr @__gxx_personality_v0 {
+  ; CHECK-LABEL: name: streaming_compatible_with_cleanup
+  ; CHECK: bb.0 (%ir-block.0):
+  ; CHECK-NEXT:   successors: %bb.1(0x7ffff800), %bb.2(0x00000800)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[EntryPStateSM:%[0-9]+]]:gpr64 = EntryPStateSM
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   BL @may_throw, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   B %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1.normal_return:
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   [[ADDXri:%[0-9]+]]:gpr64sp = ADDXri %stack.0.cleanup, 0, 0
+  ; CHECK-NEXT:   $x0 = COPY [[ADDXri]]
+  ; CHECK-NEXT:   BL @"StreamingCompatCleanup::~StreamingCompatCleanup", csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   RET_ReallyLR
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2.unwind_cleanup (landing-pad):
+  ; CHECK-NEXT:   liveins: $x0, $x1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64all = COPY killed $x1
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:gpr64all = COPY killed $x0
+  ; CHECK-NEXT:   MSRpstatePseudo 1, 1, 1, [[EntryPStateSM]], csr_aarch64_smstartstop, implicit-def dead $vg, implicit $vg, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   [[ADDXri1:%[0-9]+]]:gpr64sp = ADDXri %stack.0.cleanup, 0, 0
+  ; CHECK-NEXT:   $x0 = COPY [[ADDXri1]]
+  ; CHECK-NEXT:   BL @"StreamingCompatCleanup::~StreamingCompatCleanup", csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   MSRpstatePseudo 1, 0, 1, [[EntryPStateSM]], csr_aarch64_smstartstop, implicit-def $vg, implicit $vg, implicit-def $sp, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  ; CHECK-NEXT:   $x0 = COPY [[COPY1]]
+  ; CHECK-NEXT:   BL @_Unwind_Resume, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $vg
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   MSRpstatePseudo 1, 1, 1, [[EntryPStateSM]], csr_aarch64_smstartstop, implicit-def dead $vg, implicit $vg, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  %cleanup = alloca i8, align 1
+  invoke void @may_throw()
+          to label %normal_return unwind label %unwind_cleanup
+
+normal_return:
+  call void @"StreamingCompatCleanup::~StreamingCompatCleanup"(ptr %cleanup)
+  ret void
+
+unwind_cleanup:
+  %eh_info = landingpad { ptr, i32 }
+          cleanup
+  call void @"StreamingCompatCleanup::~StreamingCompatCleanup"(ptr %cleanup)
+  resume { ptr, i32 } %eh_info
+}
+
+; This is the same as "streaming_with_cleanup" but for a locally streaming function.
+; The lowering of "unwind_cleanup" is expected to match "streaming_with_cleanup".
+define void @locally_streaming_with_cleanup() "aarch64_pstate_sm_body" personality ptr @__gxx_personality_v0 {
+  ; CHECK-LABEL: name: locally_streaming_with_cleanup
+  ; CHECK: bb.0 (%ir-block.0):
+  ; CHECK-NEXT:   successors: %bb.1(0x7ffff800), %bb.2(0x00000800)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   MSRpstatesvcrImm1 1, 1, csr_aarch64_smstartstop, implicit-def dead $nzcv, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   BL @may_throw, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   B %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1.normal_return:
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   [[ADDXri:%[0-9]+]]:gpr64sp = ADDXri %stack.0.cleanup, 0, 0
+  ; CHECK-NEXT:   $x0 = COPY [[ADDXri]]
+  ; CHECK-NEXT:   BL @"StreamingCleanup::~StreamingCleanup", csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   MSRpstatesvcrImm1 1, 0, csr_aarch64_smstartstop, implicit-def dead $nzcv, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  ; CHECK-NEXT:   RET_ReallyLR
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2.unwind_cleanup (landing-pad):
+  ; CHECK-NEXT:   liveins: $x0, $x1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   EH_LABEL <mcsymbol >
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64all = COPY killed $x1
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:gpr64all = COPY killed $x0
+  ; CHECK-NEXT:   MSRpstatesvcrImm1 1, 1, csr_aarch64_smstartstop, implicit-def dead $nzcv, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   [[ADDXri1:%[0-9]+]]:gpr64sp = ADDXri %stack.0.cleanup, 0, 0
+  ; CHECK-NEXT:   $x0 = COPY [[ADDXri1]]
+  ; CHECK-NEXT:   BL @"StreamingCleanup::~StreamingCleanup", csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   MSRpstatesvcrImm1 1, 0, csr_aarch64_smstartstop, implicit-def dead $nzcv, implicit-def $sp, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  ; CHECK-NEXT:   $x0 = COPY [[COPY1]]
+  ; CHECK-NEXT:   BL @_Unwind_Resume, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+  ; CHECK-NEXT:   MSRpstatesvcrImm1 1, 1, csr_aarch64_smstartstop, implicit-def dead $nzcv, implicit $vg, implicit-def $vg, implicit-def $fpmr
+  %cleanup = alloca i8, align 1
+  invoke void @may_throw()
+          to label %normal_return unwind label %unwind_cleanup
+
+normal_return:
+  call void @"StreamingCleanup::~StreamingCleanup"(ptr %cleanup)
+  ret void
+
+unwind_cleanup:
+  %eh_info = landingpad { ptr, i32 }
+          cleanup
+  call void @"StreamingCleanup::~StreamingCleanup"(ptr %cleanup)
+  resume { ptr, i32 } %eh_info
+}
+
+declare i32 @__gxx_personality_v0(...)