[AArch64] Fix wrong condition in canUseAsPrologue

[momchil-velikov]

Inline stack probing code may need a scratch register, hence basic blocks where such register is not available cannot be used as prologues.

Checking for an available scratch regidster was incorrectly skipped when the function uses stack probing.

[llvmbot]

@llvm/pr-subscribers-backend-aarch64

Author: Momchil Velikov (momchil-velikov)

Changes

Inline stack probing code may need a scratch register, hence basic blocks where such register is not available cannot be used as prologues.

Checking for an available scratch regidster was incorrectly skipped when the function uses stack probing.

---

Full diff: https://github.com/llvm/llvm-project/pull/81878.diff

2 Files Affected:

• (modified) llvm/lib/Target/AArch64/AArch64FrameLowering.cpp (+1-1)
• (added) llvm/test/CodeGen/AArch64/stack-probing-no-scratch-reg.mir (+105)

diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index 2d0ca6e6d0d3fc..315e013103c3ac 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -1060,7 +1060,7 @@ bool AArch64FrameLowering::canUseAsPrologue(
 
   // Don't need a scratch register if we're not going to re-align the stack or
   // emit stack probes.
-  if (!RegInfo->hasStackRealignment(*MF) && TLI->hasInlineStackProbe(*MF))
+  if (!RegInfo->hasStackRealignment(*MF) && !TLI->hasInlineStackProbe(*MF))
     return true;
   // Otherwise, we can use any block as long as it has a scratch register
   // available.
diff --git a/llvm/test/CodeGen/AArch64/stack-probing-no-scratch-reg.mir b/llvm/test/CodeGen/AArch64/stack-probing-no-scratch-reg.mir
new file mode 100644
index 00000000000000..f50bd9ab4b8a1b
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/stack-probing-no-scratch-reg.mir
@@ -0,0 +1,105 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 4
+# RUN: llc %s --start-before=shrink-wrap -stop-after=prologepilog -o - | FileCheck %s
+--- |
+  target triple = "aarch64-linux"
+
+  define void @f(i32 %n) #0 {
+  entry:
+    %a = alloca i8, i32 150000, align 8
+    %c0 = icmp sle i32 %n, 1
+    br i1 %c0, label %if.then1, label %exit
+
+  if.then1:
+    call void @g(ptr %a)
+    br label %exit
+
+  exit:
+    ret void
+  }
+
+  declare void @g(...)
+
+  attributes #0 = { nounwind "probe-stack"="inline-asm" "stack-probe-size"="4096" }
+
+...
+---
+name:            f
+alignment:       4
+tracksRegLiveness: true
+liveins:
+  - { reg: '$w0', virtual-reg: '' }
+frameInfo:
+  localFrameSize:  150000
+stack:
+  - { id: 0, name: a, type: default, offset: 0, size: 150000, alignment: 8,
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+      local-offset: -150000, debug-info-variable: '', debug-info-expression: '',
+      debug-info-location: '' }
+entry_values:    []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: f
+  ; CHECK: bb.0.entry:
+  ; CHECK-NEXT:   successors: %bb.3(0x80000000)
+  ; CHECK-NEXT:   liveins: $w0, $lr
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -2 :: (store (s64) into %stack.2), (store (s64) into %stack.1)
+  ; CHECK-NEXT:   $x9 = frame-setup SUBXri $sp, 36, 12
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.3.entry:
+  ; CHECK-NEXT:   successors: %bb.4(0x40000000), %bb.3(0x40000000)
+  ; CHECK-NEXT:   liveins: $x0, $x1, $x2, $x3, $x4, $x5, $x6, $x7, $x8, $x9, $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17, $x18, $x19, $x20, $x21, $x22, $x23, $x25, $x27, $x28
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $sp = frame-setup SUBXri $sp, 1, 12
+  ; CHECK-NEXT:   frame-setup STRXui $xzr, $sp, 0
+  ; CHECK-NEXT:   $xzr = frame-setup SUBSXrx64 $sp, $x9, 24, implicit-def $nzcv
+  ; CHECK-NEXT:   frame-setup Bcc 1, %bb.3, implicit $nzcv
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.4.entry:
+  ; CHECK-NEXT:   successors: %bb.1(0x40000000), %bb.2(0x40000000)
+  ; CHECK-NEXT:   liveins: $x0, $x1, $x2, $x3, $x4, $x5, $x6, $x7, $x8, $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17, $x18, $x19, $x20, $x21, $x22, $x23, $x25, $x27, $x28
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $sp = frame-setup SUBXri $sp, 2544, 0
+  ; CHECK-NEXT:   frame-setup STRXui $xzr, $sp, 0
+  ; CHECK-NEXT:   $x9 = IMPLICIT_DEF
+  ; CHECK-NEXT:   dead $wzr = SUBSWri killed renamable $w0, 1, 0, implicit-def $nzcv
+  ; CHECK-NEXT:   Bcc 12, %bb.2, implicit $nzcv
+  ; CHECK-NEXT:   B %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1.if.then1:
+  ; CHECK-NEXT:   successors: %bb.2(0x80000000)
+  ; CHECK-NEXT:   liveins: $x0, $x1, $x2, $x3, $x4, $x5, $x6, $x7, $x8, $x9, $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17, $x18, $x19, $x20, $x21, $x22, $x23, $x23, $x25, $x25, $x27, $x28
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $x0 = ADDXri $sp, 0, 0
+  ; CHECK-NEXT:   BL @g, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2.exit:
+  ; CHECK-NEXT:   $sp = frame-destroy ADDXri $sp, 36, 12
+  ; CHECK-NEXT:   $sp = frame-destroy ADDXri $sp, 2544, 0
+  ; CHECK-NEXT:   early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 2 :: (load (s64) from %stack.2), (load (s64) from %stack.1)
+  ; CHECK-NEXT:   RET_ReallyLR
+  bb.0.entry:
+    successors: %bb.1(0x40000000), %bb.2(0x40000000)
+    liveins: $w0
+
+    $x9 = IMPLICIT_DEF
+    dead $wzr = SUBSWri killed renamable $w0, 1, 0, implicit-def $nzcv
+    Bcc 12, %bb.2, implicit $nzcv
+    B %bb.1
+
+  bb.1.if.then1:
+    successors: %bb.2(0x80000000)
+    liveins: $x0, $x1, $x2, $x3, $x4, $x5, $x6, $x7, $x8, $x9, $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17, $x18, $x19, $x20, $x21, $x22, $x23, $x23, $x25, $x25, $x27, $x28
+
+    ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+    $x0 = ADDXri %stack.0.a, 0, 0
+    BL @g, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
+    ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+
+  bb.2.exit:
+    RET_ReallyLR
+
+...

[efriedma-quic]

LGTM