[SEH] [ARM64] Retrieve the frame pointer from SEH funclets

[ssijaric]

Summary

The Windows ARM64 runtime passes the establisher frame to funclets as the first argument. This change just copies x1 to fp in that case.

The test case depends on https://reviews.llvm.org/D53540, which lowers the localaddr intrinsic.

[efriedma]

lib/Target/AArch64/AArch64FrameLowering.cpp

927

The casting/stripPointerCasts/hasPersonalityFn is unnecessary here, I think; llvm::classifyEHPersonality will do it for you.

Checking the personality here seems a little awkward, but I guess it works.

[ssijaric]

Cleanup per Eli's comments. Checking for the personality function is probably not necessary. I could add an assert instead of the check?

[efriedma]

lib/Target/AArch64/AArch64FrameLowering.cpp

923

Do we need to do anything special to recover the base pointer in SEH funclets? (If not, probably worth adding an explicit comment.)

[ssijaric]

Clarify the comment. By looking at cl.exe generated code, it looks like only the frame pointer is passed in x1. The base pointer, if needed, is used directly (e.g. x19). I will verify with a more complicated test case.

[efriedma]

LGTM

test/CodeGen/AArch64/seh_funclet_x1.ll

119

You could probably clean up this testcase a bit (remove the unnecessary attributes, maybe run mem2reg).

[ssijaric]

Committed under https://reviews.llvm.org/rL351404. Forgot to add a Different Revision line.

lib/Target/AArch64/AArch64FrameLowering.cpp

void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
 
   // The code below is not applicable to funclets. We have emitted all the SEH
   // opcodes that we needed to emit.  The FP and BP belong to the containing
   // function.
   if (IsFunclet) {
     if (NeedsWinCFI)
       BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_PrologEnd))
           .setMIFlag(MachineInstr::FrameSetup);
+
+    // SEH funclets are passed the frame pointer in X1.
+    if (F.hasPersonalityFn()) {
+      EHPersonality Per = classifyEHPersonality(F.getPersonalityFn());
+      if (isAsynchronousEHPersonality(Per))
+        BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::COPY), AArch64::FP)
+            .addReg(AArch64::X1).setMIFlag(MachineInstr::FrameSetup);
+    }
+
     return;
   }
 
   if (HasFP) {
     // Only set up FP if we actually need to. Frame pointer is fp =
     // sp - fixedobject - 16.
     int FPOffset = AFI->getCalleeSavedStackSize() - 16;
     if (CombineSPBump)

test/CodeGen/AArch64/seh_funclet_x1.ll

+; RUN: llc -o - %s -mtriple=aarch64-windows | FileCheck %s
+
+; Windows runtime passes the establisher frame as the second argument to the
+; termination handler.  Check that we copy it into fp.
+
+; CHECK:      ?dtor$3@?0?main@4HA":
+; CHECK:      .seh_proc "?dtor$3@?0?main@4HA"
+; CHECK:      stp     x29, x30, [sp, #-16]!   ; 16-byte Folded Spill
+; CHECK-NEXT: mov     x29, x1
+
+target datalayout = "e-m:w-p:64:64-i32:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-unknown-windows-msvc19.15.26732"
+
+; Function Attrs: noinline nounwind optnone uwtable
+define dso_local i32 @main() #0 personality i8* bitcast (i32 (...)* @__C_specific_handler to i8*) {
+entry:
+  %retval = alloca i32, align 4
+  %Counter = alloca i32, align 4
+  %__exception_code = alloca i32, align 4
+  call void (...) @llvm.localescape(i32* %Counter)
+  store i32 0, i32* %retval, align 4
+  store i32 0, i32* %Counter, align 4
+  %call = invoke i32 bitcast (i32 (...)* @RaiseStatus to i32 (i32)*)(i32 -1073741675) #5
+          to label %invoke.cont unwind label %ehcleanup
+
+invoke.cont:                                      ; preds = %entry
+  %0 = call i8* @llvm.localaddress()
+  invoke void @"?fin$0@0@main@@"(i8 0, i8* %0) #5
+          to label %invoke.cont1 unwind label %catch.dispatch
+
+invoke.cont1:                                     ; preds = %invoke.cont
+  br label %__try.cont
+
+ehcleanup:                                        ; preds = %entry
+  %1 = cleanuppad within none []
+  %2 = call i8* @llvm.localaddress()
+  invoke void @"?fin$0@0@main@@"(i8 1, i8* %2) #5 [ "funclet"(token %1) ]
+          to label %invoke.cont2 unwind label %catch.dispatch
+
+invoke.cont2:                                     ; preds = %ehcleanup
+  cleanupret from %1 unwind label %catch.dispatch
+
+catch.dispatch:                                   ; preds = %invoke.cont2, %ehcleanup, %invoke.cont
+  %3 = catchswitch within none [label %__except] unwind to caller
+
+__except:                                         ; preds = %catch.dispatch
+  %4 = catchpad within %3 [i8* null]
+  catchret from %4 to label %__except3
+
+__except3:                                        ; preds = %__except
+  %5 = call i32 @llvm.eh.exceptioncode(token %4)
+  store i32 %5, i32* %__exception_code, align 4
+  %6 = load i32, i32* %Counter, align 4
+  %add = add nsw i32 %6, 5
+  store i32 %add, i32* %Counter, align 4
+  br label %__try.cont
+
+__try.cont:                                       ; preds = %__except3, %invoke.cont1
+  %7 = load i32, i32* %retval, align 4
+  ret i32 %7
+}
+
+define internal void @"?fin$0@0@main@@"(i8 %abnormal_termination, i8* %frame_pointer) #1 {
+entry:
+  %frame_pointer.addr = alloca i8*, align 8
+  %abnormal_termination.addr = alloca i8, align 1
+  %0 = call i8* @llvm.localrecover(i8* bitcast (i32 ()* @main to i8*), i8* %frame_pointer, i32 0)
+  %Counter = bitcast i8* %0 to i32*
+  store i8* %frame_pointer, i8** %frame_pointer.addr, align 8
+  store i8 %abnormal_termination, i8* %abnormal_termination.addr, align 1
+  store i32 3, i32* %Counter, align 4
+  call void @"?fin$1@0@main@@"(i8 0, i8* %frame_pointer)
+  %1 = load i32, i32* %Counter, align 4
+  %add = add nsw i32 %1, 2
+  store i32 %add, i32* %Counter, align 4
+  %call = call i32 bitcast (i32 (...)* @RaiseStatus to i32 (i32)*)(i32 -1073741675)
+  ret void
+}
+
+; Function Attrs: nounwind readnone
+declare i8* @llvm.localrecover(i8*, i8*, i32) #2
+
+define internal void @"?fin$1@0@main@@"(i8 %abnormal_termination, i8* %frame_pointer) #1 {
+entry:
+  %frame_pointer.addr = alloca i8*, align 8
+  %abnormal_termination.addr = alloca i8, align 1
+  %0 = call i8* @llvm.localrecover(i8* bitcast (i32 ()* @main to i8*), i8* %frame_pointer, i32 0)
+  %Counter = bitcast i8* %0 to i32*
+  store i8* %frame_pointer, i8** %frame_pointer.addr, align 8
+  store i8 %abnormal_termination, i8* %abnormal_termination.addr, align 1
+  %1 = load i32, i32* %Counter, align 4
+  %cmp = icmp eq i32 %1, 3
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:                                          ; preds = %entry
+  %2 = load i32, i32* %Counter, align 4
+  %add = add nsw i32 %2, 1
+  store i32 %add, i32* %Counter, align 4
+  br label %if.end
+
+if.end:                                           ; preds = %if.then, %entry
+  ret void
+}
+
+declare dso_local i32 @RaiseStatus(...) #3
+
+declare dso_local i32 @__C_specific_handler(...)
+
+; Function Attrs: nounwind readnone
+declare i8* @llvm.localaddress() #2
+
+; Function Attrs: nounwind readnone
+declare i32 @llvm.eh.exceptioncode(token) #2
+
+; Function Attrs: nounwind
+declare void @llvm.localescape(...) #4
+
+attributes #0 = { noinline nounwind optnone uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #2 = { nounwind readnone }
+attributes #3 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #4 = { nounwind }
+attributes #5 = { noinline }