[AArch64][SME] Disable outlining for functions with streaming-mode changes (#95132)

2 files changed, 85 insertions, 0 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
index a5135b7..1a795b5 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
@@ -8701,6 +8701,13 @@ bool AArch64InstrInfo::isFunctionSafeToOutlineFrom(
   if (!AFI || AFI->hasRedZone().value_or(true))
     return false;
 
+  // FIXME: Determine whether it is safe to outline from functions which contain
+  // streaming-mode changes. We may need to ensure any smstart/smstop pairs are
+  // outlined together and ensure it is safe to outline with async unwind info,
+  // required for saving & restoring VG around calls.
+  if (AFI->hasStreamingModeChanges())
+    return false;
+
   // FIXME: Teach the outliner to generate/handle Windows unwind info.
   if (MF.getTarget().getMCAsmInfo()->usesWindowsCFI())
     return false;
diff --git a/llvm/test/CodeGen/AArch64/outlining-with-streaming-mode-changes.ll b/llvm/test/CodeGen/AArch64/outlining-with-streaming-mode-changes.ll
new file mode 100644
index 0000000..44d47a0
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/outlining-with-streaming-mode-changes.ll
@@ -0,0 +1,78 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=+sme2 -enable-machine-outliner -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=+sme2 -enable-machine-outliner -verify-machineinstrs < %s | FileCheck %s -check-prefix=OUTLINER
+
+declare void @callee();
+
+define void @streaming_mode_change1() #0 {
+; CHECK-LABEL: streaming_mode_change1:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp d15, d14, [sp, #-80]! // 16-byte Folded Spill
+; CHECK-NEXT:    stp d13, d12, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d11, d10, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d9, d8, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    str x30, [sp, #64] // 8-byte Folded Spill
+; CHECK-NEXT:    smstop sm
+; CHECK-NEXT:    bl callee
+; CHECK-NEXT:    smstart sm
+; CHECK-NEXT:    ldp d9, d8, [sp, #48] // 16-byte Folded Reload
+; CHECK-NEXT:    ldr x30, [sp, #64] // 8-byte Folded Reload
+; CHECK-NEXT:    ldp d11, d10, [sp, #32] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d13, d12, [sp, #16] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d15, d14, [sp], #80 // 16-byte Folded Reload
+; CHECK-NEXT:    ret
+;
+; OUTLINER-LABEL: streaming_mode_change1:
+; OUTLINER-NOT: OUTLINED_FUNCTION_
+  call void @callee();
+  ret void;
+}
+
+define void @streaming_mode_change2() #0 {
+; CHECK-LABEL: streaming_mode_change2:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp d15, d14, [sp, #-80]! // 16-byte Folded Spill
+; CHECK-NEXT:    stp d13, d12, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d11, d10, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d9, d8, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    str x30, [sp, #64] // 8-byte Folded Spill
+; CHECK-NEXT:    smstop sm
+; CHECK-NEXT:    bl callee
+; CHECK-NEXT:    smstart sm
+; CHECK-NEXT:    ldp d9, d8, [sp, #48] // 16-byte Folded Reload
+; CHECK-NEXT:    ldr x30, [sp, #64] // 8-byte Folded Reload
+; CHECK-NEXT:    ldp d11, d10, [sp, #32] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d13, d12, [sp, #16] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d15, d14, [sp], #80 // 16-byte Folded Reload
+; CHECK-NEXT:    ret
+;
+; OUTLINER-LABEL: streaming_mode_change2:
+; OUTLINER-NOT: OUTLINED_FUNCTION_
+  call void @callee();
+  ret void;
+}
+
+define void @streaming_mode_change3() #0 {
+; CHECK-LABEL: streaming_mode_change3:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp d15, d14, [sp, #-80]! // 16-byte Folded Spill
+; CHECK-NEXT:    stp d13, d12, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d11, d10, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d9, d8, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    str x30, [sp, #64] // 8-byte Folded Spill
+; CHECK-NEXT:    smstop sm
+; CHECK-NEXT:    bl callee
+; CHECK-NEXT:    smstart sm
+; CHECK-NEXT:    ldp d9, d8, [sp, #48] // 16-byte Folded Reload
+; CHECK-NEXT:    ldr x30, [sp, #64] // 8-byte Folded Reload
+; CHECK-NEXT:    ldp d11, d10, [sp, #32] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d13, d12, [sp, #16] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d15, d14, [sp], #80 // 16-byte Folded Reload
+; CHECK-NEXT:    ret
+;
+; OUTLINER-LABEL: streaming_mode_change3:
+; OUTLINER-NOT: OUTLINED_FUNCTION_
+  call void @callee();
+  ret void;
+}
+
+attributes #0 = { "aarch64_pstate_sm_enabled" nounwind }