[llvm] [AArch64][SME] Disable tail-call optimization for __arm_locally_streaming functions. (PR #65258)

[via llvm-commits]

https://github.com/sdesmalen-arm created https://github.com/llvm/llvm-project/pull/65258:

When calling e.g. a streaming-compatible function (which requires no streaming-mode change), LLVM would otherwise emit:

  // function prologue
  smstart
  b streaming_compatible_function   // tail call
  // never an smstop

>From 3a45f9cdd76e14c8f9a3977328a9a5a179daeae8 Mon Sep 17 00:00:00 2001
From: Sander de Smalen <sander.desmalen at arm.com>
Date: Mon, 4 Sep 2023 11:45:39 +0100
Subject: [PATCH] [AArch64][SME] Disable tail-call optimization for
 __arm_locally_streaming functions.

When calling e.g. a streaming-compatible function (which requires no streaming-mode change),
LLVM would otherwise emit:

  // function prologue
  smstart
  b streaming_compatible_function   // tail call
  // never an smstop
---
 .../Target/AArch64/AArch64ISelLowering.cpp    |  3 ++-
 .../CodeGen/AArch64/sme-streaming-body.ll     | 21 +++++++++++++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 0c8432daeb8c56c..d82575dd978088c 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -6977,7 +6977,8 @@ bool AArch64TargetLowering::isEligibleForTailCallOptimization(
   SMEAttrs CallerAttrs(MF.getFunction());
   auto CalleeAttrs = CLI.CB ? SMEAttrs(*CLI.CB) : SMEAttrs(SMEAttrs::Normal);
   if (CallerAttrs.requiresSMChange(CalleeAttrs) ||
-      CallerAttrs.requiresLazySave(CalleeAttrs))
+      CallerAttrs.requiresLazySave(CalleeAttrs) ||
+      CallerAttrs.hasStreamingBody())
     return false;
 
   // Functions using the C or Fast calling convention that have an SVE signature
diff --git a/llvm/test/CodeGen/AArch64/sme-streaming-body.ll b/llvm/test/CodeGen/AArch64/sme-streaming-body.ll
index ff23ed9dfe5a2d5..1aaef90e9eed867 100644
--- a/llvm/test/CodeGen/AArch64/sme-streaming-body.ll
+++ b/llvm/test/CodeGen/AArch64/sme-streaming-body.ll
@@ -306,3 +306,24 @@ for.cond.cleanup:
   ret float %add
 
 }
+
+define void @disable_tailcallopt() "aarch64_pstate_sm_body" nounwind {
+; CHECK-LABEL: disable_tailcallopt:
+; 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:    smstart sm
+; CHECK-NEXT:    bl streaming_compatible_callee
+; CHECK-NEXT:    smstop 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
+  tail call void @streaming_compatible_callee();
+  ret void;
+}