[ARM][Thumb2] Mark BTI-clearing instructions as scheduling region boundaries

vhscampos · vhscampos · commit e628563ad7e6 · 2024-01-23T17:22:59.000Z
Following #68313 this patch extends the idea to M-profile PACBTI. The Machine Scheduler can reorder instructions within a scheduling region depending on the scheduling policy set. If a BTI-clearing instruction happens to partake in one such region, it might be moved around, therefore ending up where it shouldn't. The solution is to mark all BTI-clearing instructions as scheduling region boundaries. This essentially means that they must not be part of any scheduling region, and as consequence never get moved: - PAC - PACBTI - BTI - SG - CALL_BTI (pseudo-instruction for setjmp + bti) Note that PAC isn't BTI-clearing, but it's replaced by PACBTI late in the compilation pipeline. As far as I know, currently it isn't possible to organically obtain code that's susceptible to the bug: - Instructions that write to SP are region boundaries. PAC seems to always be followed by the pushing of r12 to the stack, so essentially PAC is always by itself in a scheduling region. - CALL_BTI is expanded into a machine instruction bundle. Bundles are unpacked only after the last machine scheduler run. Thus setjmp and BTI can be separated only if someone deliberately run the scheduler once more. - The BTI insertion pass is run late in the pipeline, only after the last machine scheduling has run. So once again it can be reordered only if someone deliberately runs the scheduler again. Nevertheless, one can reasonably argue that we should prevent the bug in spite of the compiler not being able to produce the required conditions for it. If things change, the compiler will be robust against this issue. The tests written for this are contrived: bogus MIR instructions have been added adjacent to the BTI-clearing instructions in order to have them inside non-trivial scheduling regions.
diff --git a/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp b/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -2088,7 +2088,7 @@ bool ARMBaseInstrInfo::isSchedulingBoundary(const MachineInstr &MI,
   if (!MI.isCall() && MI.definesRegister(ARM::SP))
     return true;
 
-  return false;
+  return TargetInstrInfo::isSchedulingBoundary(MI, MBB, MF);
 }
 
 bool ARMBaseInstrInfo::
diff --git a/llvm/lib/Target/ARM/Thumb2InstrInfo.cpp b/llvm/lib/Target/ARM/Thumb2InstrInfo.cpp
@@ -286,6 +286,26 @@ MachineInstr *Thumb2InstrInfo::commuteInstructionImpl(MachineInstr &MI,
   return ARMBaseInstrInfo::commuteInstructionImpl(MI, NewMI, OpIdx1, OpIdx2);
 }
 
+bool Thumb2InstrInfo::isSchedulingBoundary(const MachineInstr &MI,
+                                           const MachineBasicBlock *MBB,
+                                           const MachineFunction &MF) const {
+  // BTI clearing instructions shall not take part in scheduling regions as
+  // they must stay in their intended place. Although PAC isn't BTI clearing,
+  // it can be transformed into PACBTI after the pre-RA Machine Scheduling
+  // has taken place, so its movement must also be restricted.
+  switch (MI.getOpcode()) {
+  case ARM::t2BTI:
+  case ARM::t2PAC:
+  case ARM::t2PACBTI:
+  case ARM::t2CALL_BTI:
+  case ARM::t2SG:
+    return true;
+  default:
+    break;
+  }
+  return ARMBaseInstrInfo::isSchedulingBoundary(MI, MBB, MF);
+}
+
 void llvm::emitT2RegPlusImmediate(MachineBasicBlock &MBB,
                                   MachineBasicBlock::iterator &MBBI,
                                   const DebugLoc &dl, Register DestReg,
diff --git a/llvm/lib/Target/ARM/Thumb2InstrInfo.h b/llvm/lib/Target/ARM/Thumb2InstrInfo.h
@@ -68,6 +68,10 @@ class Thumb2InstrInfo : public ARMBaseInstrInfo {
                                        unsigned OpIdx1,
                                        unsigned OpIdx2) const override;
 
+  bool isSchedulingBoundary(const MachineInstr &MI,
+                            const MachineBasicBlock *MBB,
+                            const MachineFunction &MF) const override;
+
 private:
   void expandLoadStackGuard(MachineBasicBlock::iterator MI) const override;
 };
diff --git a/llvm/test/CodeGen/ARM/misched-branch-targets.mir b/llvm/test/CodeGen/ARM/misched-branch-targets.mir
@@ -0,0 +1,181 @@
+# RUN: llc -o - -run-pass=machine-scheduler -misched=shuffle %s | FileCheck %s
+# RUN: llc -o - -run-pass=postmisched %s | FileCheck %s
+
+--- |
+  target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
+  target triple = "thumbv8.1m.main-arm-none-eabi"
+
+  define dso_local i32 @foo_bti(i32 noundef %a) local_unnamed_addr #7 {
+  entry:
+    %add = add nsw i32 %a, 1
+    ret i32 %add
+  }
+
+    define dso_local i32 @foo_pacbti(i32 noundef %a) local_unnamed_addr #7 {
+  entry:
+    %add = add nsw i32 %a, 1
+    ret i32 %add
+  }
+
+    define dso_local noundef i32 @foo_setjmp() local_unnamed_addr #0 {
+  entry:
+    %buf = alloca [20 x i64], align 8
+    call void @llvm.lifetime.start.p0(i64 160, ptr nonnull %buf) #4
+    %call = call i32 @setjmp(ptr noundef nonnull %buf) #5
+    %tobool.not = icmp eq i32 %call, 0
+    br i1 %tobool.not, label %if.else, label %if.then
+  
+  if.then:                                          ; preds = %entry
+    call void @longjmp(ptr noundef nonnull %buf, i32 noundef 1) #6
+    unreachable
+  
+  if.else:                                          ; preds = %entry
+    call void @llvm.lifetime.end.p0(i64 160, ptr nonnull %buf) #4
+    ret i32 0
+  }
+  
+  declare void @llvm.lifetime.start.p0(i64 immarg, ptr nocapture) #1
+  declare dso_local i32 @setjmp(ptr noundef) local_unnamed_addr #2
+  declare dso_local void @longjmp(ptr noundef, i32 noundef) local_unnamed_addr #3
+  declare void @llvm.lifetime.end.p0(i64 immarg, ptr nocapture) #1
+  
+  attributes #0 = { nounwind "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="cortex-m55" "target-features"="+armv8.1-m.main,+dsp,+fp-armv8d16,+fp-armv8d16sp,+fp16,+fp64,+fullfp16,+hwdiv,+lob,+mve,+mve.fp,+ras,+strict-align,+thumb-mode,+vfp2,+vfp2sp,+vfp3d16,+vfp3d16sp,+vfp4d16,+vfp4d16sp,-aes,-bf16,-cdecp0,-cdecp1,-cdecp2,-cdecp3,-cdecp4,-cdecp5,-cdecp6,-cdecp7,-crc,-crypto,-d32,-dotprod,-fp-armv8,-fp-armv8sp,-fp16fml,-hwdiv-arm,-i8mm,-neon,-pacbti,-sb,-sha2,-vfp3,-vfp3sp,-vfp4,-vfp4sp" }
+  attributes #1 = { nocallback nofree nosync nounwind willreturn memory(argmem: readwrite) }
+  attributes #2 = { nounwind returns_twice "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="cortex-m55" "target-features"="+armv8.1-m.main,+dsp,+fp-armv8d16,+fp-armv8d16sp,+fp16,+fp64,+fullfp16,+hwdiv,+lob,+mve,+mve.fp,+ras,+strict-align,+thumb-mode,+vfp2,+vfp2sp,+vfp3d16,+vfp3d16sp,+vfp4d16,+vfp4d16sp,-aes,-bf16,-cdecp0,-cdecp1,-cdecp2,-cdecp3,-cdecp4,-cdecp5,-cdecp6,-cdecp7,-crc,-crypto,-d32,-dotprod,-fp-armv8,-fp-armv8sp,-fp16fml,-hwdiv-arm,-i8mm,-neon,-pacbti,-sb,-sha2,-vfp3,-vfp3sp,-vfp4,-vfp4sp" }
+  attributes #3 = { noreturn nounwind "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="cortex-m55" "target-features"="+armv8.1-m.main,+dsp,+fp-armv8d16,+fp-armv8d16sp,+fp16,+fp64,+fullfp16,+hwdiv,+lob,+mve,+mve.fp,+ras,+strict-align,+thumb-mode,+vfp2,+vfp2sp,+vfp3d16,+vfp3d16sp,+vfp4d16,+vfp4d16sp,-aes,-bf16,-cdecp0,-cdecp1,-cdecp2,-cdecp3,-cdecp4,-cdecp5,-cdecp6,-cdecp7,-crc,-crypto,-d32,-dotprod,-fp-armv8,-fp-armv8sp,-fp16fml,-hwdiv-arm,-i8mm,-neon,-pacbti,-sb,-sha2,-vfp3,-vfp3sp,-vfp4,-vfp4sp" }
+  attributes #4 = { nounwind }
+  attributes #5 = { nounwind returns_twice }
+  attributes #6 = { noreturn nounwind }
+  attributes #7 = { mustprogress nofree norecurse nosync nounwind willreturn memory(none) "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="cortex-m55" "target-features"="+armv8.1-m.main,+dsp,+fp-armv8d16,+fp-armv8d16sp,+fp16,+fp64,+fullfp16,+hwdiv,+lob,+mve,+mve.fp,+ras,+strict-align,+thumb-mode,+vfp2,+vfp2sp,+vfp3d16,+vfp3d16sp,+vfp4d16,+vfp4d16sp,-aes,-bf16,-cdecp0,-cdecp1,-cdecp2,-cdecp3,-cdecp4,-cdecp5,-cdecp6,-cdecp7,-crc,-crypto,-d32,-dotprod,-fp-armv8,-fp-armv8sp,-fp16fml,-hwdiv-arm,-i8mm,-neon,-pacbti,-sb,-sha2,-vfp3,-vfp3sp,-vfp4,-vfp4sp" }
+
+...
+---
+name:            foo_bti
+alignment:       4
+tracksRegLiveness: true
+tracksDebugUserValues: true
+liveins:
+  - { reg: '$r0' }
+frameInfo:
+  maxAlignment:    1
+  maxCallFrameSize: 0
+machineFunctionInfo:
+  isLRSpilled:     false
+body:             |
+  bb.0.entry:
+    liveins: $r0
+
+    t2BTI
+    renamable $r0, dead $cpsr = nsw tADDi8 killed renamable $r0, 1, 14 /* CC::al */, $noreg
+    tBX_RET 14 /* CC::al */, $noreg, implicit killed $r0
+
+...
+
+# CHECK-LABEL: name:            foo_bti
+# CHECK:       body:
+# CHECK-NEXT:   bb.0.entry:
+# CHECK-NEXT:     liveins: $r0
+# CHECK-NEXT:     {{^ +$}}
+# CHECK-NEXT:     t2BTI
+
+---
+name:            foo_pacbti
+alignment:       4
+tracksRegLiveness: true
+tracksDebugUserValues: true
+liveins:
+  - { reg: '$r0' }
+frameInfo:
+  stackSize:       12
+  offsetAdjustment: -4
+  maxAlignment:    4
+  maxCallFrameSize: 0
+stack:
+  - { id: 0, type: spill-slot, offset: -4, size: 4, alignment: 4, callee-saved-register: '$lr' }
+  - { id: 1, type: spill-slot, offset: -8, size: 4, alignment: 4, callee-saved-register: '$r7' }
+  - { id: 2, type: spill-slot, offset: -12, size: 4, alignment: 4, callee-saved-register: '$r12' }
+machineFunctionInfo:
+  isLRSpilled:     true
+body:             |
+  bb.0.entry:
+    liveins: $r0, $lr, $r12
+
+    frame-setup t2PAC implicit-def $r12, implicit $lr, implicit $sp
+    renamable $r2 = nsw t2ADDri $r0, 3, 14 /* CC::al */, $noreg, $noreg
+    $sp = frame-setup t2STMDB_UPD $sp, 14 /* CC::al */, $noreg, killed $r7, killed $lr
+    frame-setup CFI_INSTRUCTION def_cfa_offset 8
+    frame-setup CFI_INSTRUCTION offset $lr, -4
+    frame-setup CFI_INSTRUCTION offset $r7, -8
+    $r7 = frame-setup tMOVr killed $sp, 14 /* CC::al */, $noreg
+    frame-setup CFI_INSTRUCTION def_cfa_register $r7
+    early-clobber $sp = frame-setup t2STR_PRE killed $r12, $sp, -4, 14 /* CC::al */, $noreg
+    frame-setup CFI_INSTRUCTION offset $ra_auth_code, -12
+    renamable $r0 = nsw t2ADDri killed renamable $r0, 1, 14 /* CC::al */, $noreg, $noreg
+    $r12, $sp = frame-destroy t2LDR_POST $sp, 4, 14 /* CC::al */, $noreg
+    $sp = frame-destroy t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r7, def $lr
+    t2AUT implicit $r12, implicit $lr, implicit $sp
+    tBX_RET 14 /* CC::al */, $noreg, implicit $r0
+
+...
+
+# CHECK-LABEL: name:            foo_pacbti
+# CHECK:       body:
+# CHECK-NEXT:    bb.0.entry:
+# CHECK-NEXT:      liveins: $r0, $lr, $r12
+# CHECK-NEXT:      {{^ +$}}
+# CHECK-NEXT:      frame-setup t2PAC implicit-def $r12, implicit $lr, implicit $sp
+
+---
+name:            foo_setjmp
+alignment:       4
+exposesReturnsTwice: true
+tracksRegLiveness: true
+tracksDebugUserValues: true
+frameInfo:
+  stackSize:       168
+  offsetAdjustment: -160
+  maxAlignment:    8
+  adjustsStack:    true
+  hasCalls:        true
+  maxCallFrameSize: 0
+  localFrameSize:  160
+stack:
+  - { id: 0, name: buf, offset: -168, size: 160, alignment: 8, local-offset: -160 }
+  - { id: 1, type: spill-slot, offset: -4, size: 4, alignment: 4, callee-saved-register: '$lr', 
+      callee-saved-restored: false }
+  - { id: 2, type: spill-slot, offset: -8, size: 4, alignment: 4, callee-saved-register: '$r7' }
+machineFunctionInfo:
+  isLRSpilled:     true
+body:             |
+  bb.0.entry:
+    successors: %bb.1
+    liveins: $lr
+  
+    frame-setup tPUSH 14 /* CC::al */, $noreg, $r7, killed $lr, implicit-def $sp, implicit $sp
+    frame-setup CFI_INSTRUCTION def_cfa_offset 8
+    frame-setup CFI_INSTRUCTION offset $lr, -4
+    frame-setup CFI_INSTRUCTION offset $r7, -8
+    $r7 = frame-setup tMOVr $sp, 14 /* CC::al */, $noreg
+    frame-setup CFI_INSTRUCTION def_cfa_register $r7
+    $sp = frame-setup tSUBspi $sp, 40, 14 /* CC::al */, $noreg
+    renamable $r0 = tMOVr $sp, 14 /* CC::al */, $noreg
+    tBL 14 /* CC::al */, $noreg, @setjmp, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit-def $sp, implicit-def $r0
+    t2BTI
+    renamable $r2 = nsw t2ADDri $r0, 3, 14 /* CC::al */, $noreg, $noreg
+    tCMPi8 killed renamable $r0, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
+    t2IT 0, 2, implicit-def $itstate
+    renamable $r0 = tMOVi8 $noreg, 0, 0 /* CC::eq */, $cpsr, implicit $itstate
+    $sp = frame-destroy tADDspi $sp, 40, 0 /* CC::eq */, $cpsr, implicit $itstate
+    frame-destroy tPOP_RET 0 /* CC::eq */, killed $cpsr, def $r7, def $pc, implicit killed $r0, implicit $sp, implicit killed $itstate
+  
+  bb.1.if.then:
+    renamable $r0 = tMOVr $sp, 14 /* CC::al */, $noreg
+    renamable $r1, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
+    tBL 14 /* CC::al */, $noreg, @longjmp, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit killed $r1, implicit-def $sp
+
+...
+
+# CHECK-LABEL: name:            foo_setjmp
+# CHECK:       body:
+# CHECK:         tBL 14 /* CC::al */, $noreg, @setjmp, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit-def $sp, implicit-def $r0
+# CHECK-NEXT:    t2BTI

Original file line number	Diff line number	Diff line change
`@@ -2088,7 +2088,7 @@ bool ARMBaseInstrInfo::isSchedulingBoundary(const MachineInstr &MI,`
`2088`	`2088`	`if (!MI.isCall() && MI.definesRegister(ARM::SP))`
`2089`	`2089`	`return true;`
`2090`	`2090`
`2091`		`- return false;`
	`2091`	`+ return TargetInstrInfo::isSchedulingBoundary(MI, MBB, MF);`
`2092`	`2092`	`}`
`2093`	`2093`
`2094`	`2094`	`bool ARMBaseInstrInfo::`