; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 -aarch64-streaming-hazard-size=0 -mattr=+sve -mattr=+sme < %s | FileCheck %s --check-prefixes=CHECK-COMMON,CHECK
; RUN: llc -mtriple=aarch64 -aarch64-streaming-hazard-size=0 -mattr=+sve -mattr=+sme -aarch64-new-sme-abi < %s | FileCheck %s --check-prefixes=CHECK-COMMON,CHECK-NEWLOWERING

declare void @private_za_callee()
declare void @shared_za_callee() "aarch64_inout_za"
declare void @preserves_za_callee() "aarch64_preserves_za"

declare float @llvm.cos.f32(float)

; Test lazy-save mechanism for a single callee.
define void @test_lazy_save_1_callee() nounwind "aarch64_inout_za" {
; CHECK-COMMON-LABEL: test_lazy_save_1_callee:
; CHECK-COMMON:       // %bb.0:
; CHECK-COMMON-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-COMMON-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-COMMON-NEXT:    mov x29, sp
; CHECK-COMMON-NEXT:    sub sp, sp, #16
; CHECK-COMMON-NEXT:    rdsvl x8, #1
; CHECK-COMMON-NEXT:    mov x9, sp
; CHECK-COMMON-NEXT:    msub x9, x8, x8, x9
; CHECK-COMMON-NEXT:    mov sp, x9
; CHECK-COMMON-NEXT:    sub x10, x29, #16
; CHECK-COMMON-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-COMMON-NEXT:    msr TPIDR2_EL0, x10
; CHECK-COMMON-NEXT:    bl private_za_callee
; CHECK-COMMON-NEXT:    smstart za
; CHECK-COMMON-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-COMMON-NEXT:    sub x0, x29, #16
; CHECK-COMMON-NEXT:    cbnz x8, .LBB0_2
; CHECK-COMMON-NEXT:  // %bb.1:
; CHECK-COMMON-NEXT:    bl __arm_tpidr2_restore
; CHECK-COMMON-NEXT:  .LBB0_2:
; CHECK-COMMON-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-COMMON-NEXT:    mov sp, x29
; CHECK-COMMON-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-COMMON-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-COMMON-NEXT:    ret
  call void @private_za_callee()
  ret void
}

; Test lazy-save mechanism for multiple callees.
define void @test_lazy_save_2_callees() nounwind "aarch64_inout_za" {
; CHECK-LABEL: test_lazy_save_2_callees:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT:    mov x29, sp
; CHECK-NEXT:    sub sp, sp, #16
; CHECK-NEXT:    rdsvl x8, #1
; CHECK-NEXT:    mov x9, sp
; CHECK-NEXT:    msub x9, x8, x8, x9
; CHECK-NEXT:    mov sp, x9
; CHECK-NEXT:    sub x20, x29, #16
; CHECK-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB1_2
; CHECK-NEXT:  // %bb.1:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB1_2:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB1_4
; CHECK-NEXT:  // %bb.3:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB1_4:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    mov sp, x29
; CHECK-NEXT:    ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-NEXT:    ret
;
; CHECK-NEWLOWERING-LABEL: test_lazy_save_2_callees:
; CHECK-NEWLOWERING:       // %bb.0:
; CHECK-NEWLOWERING-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-NEWLOWERING-NEXT:    mov x29, sp
; CHECK-NEWLOWERING-NEXT:    sub sp, sp, #16
; CHECK-NEWLOWERING-NEXT:    rdsvl x8, #1
; CHECK-NEWLOWERING-NEXT:    mov x9, sp
; CHECK-NEWLOWERING-NEXT:    msub x9, x8, x8, x9
; CHECK-NEWLOWERING-NEXT:    mov sp, x9
; CHECK-NEWLOWERING-NEXT:    sub x10, x29, #16
; CHECK-NEWLOWERING-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, x10
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    smstart za
; CHECK-NEWLOWERING-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEWLOWERING-NEXT:    sub x0, x29, #16
; CHECK-NEWLOWERING-NEXT:    cbnz x8, .LBB1_2
; CHECK-NEWLOWERING-NEXT:  // %bb.1:
; CHECK-NEWLOWERING-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEWLOWERING-NEXT:  .LBB1_2:
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEWLOWERING-NEXT:    mov sp, x29
; CHECK-NEWLOWERING-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-NEWLOWERING-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ret
  call void @private_za_callee()
  call void @private_za_callee()
  ret void
}

; Test a call of an intrinsic that gets expanded to a library call.
define float @test_lazy_save_expanded_intrinsic(float %a) nounwind "aarch64_inout_za" {
; CHECK-COMMON-LABEL: test_lazy_save_expanded_intrinsic:
; CHECK-COMMON:       // %bb.0:
; CHECK-COMMON-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-COMMON-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-COMMON-NEXT:    mov x29, sp
; CHECK-COMMON-NEXT:    sub sp, sp, #16
; CHECK-COMMON-NEXT:    rdsvl x8, #1
; CHECK-COMMON-NEXT:    mov x9, sp
; CHECK-COMMON-NEXT:    msub x9, x8, x8, x9
; CHECK-COMMON-NEXT:    mov sp, x9
; CHECK-COMMON-NEXT:    sub x10, x29, #16
; CHECK-COMMON-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-COMMON-NEXT:    msr TPIDR2_EL0, x10
; CHECK-COMMON-NEXT:    bl cosf
; CHECK-COMMON-NEXT:    smstart za
; CHECK-COMMON-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-COMMON-NEXT:    sub x0, x29, #16
; CHECK-COMMON-NEXT:    cbnz x8, .LBB2_2
; CHECK-COMMON-NEXT:  // %bb.1:
; CHECK-COMMON-NEXT:    bl __arm_tpidr2_restore
; CHECK-COMMON-NEXT:  .LBB2_2:
; CHECK-COMMON-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-COMMON-NEXT:    mov sp, x29
; CHECK-COMMON-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-COMMON-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-COMMON-NEXT:    ret
  %res = call float @llvm.cos.f32(float %a)
  ret float %res
}

; Test a combination of streaming-compatible -> normal call with lazy-save.
define void @test_lazy_save_and_conditional_smstart() nounwind "aarch64_inout_za" "aarch64_pstate_sm_compatible" {
; CHECK-LABEL: test_lazy_save_and_conditional_smstart:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp d15, d14, [sp, #-96]! // 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:    stp x29, x30, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT:    add x29, sp, #64
; CHECK-NEXT:    stp x20, x19, [sp, #80] // 16-byte Folded Spill
; CHECK-NEXT:    sub sp, sp, #16
; CHECK-NEXT:    rdsvl x8, #1
; CHECK-NEXT:    mov x9, sp
; CHECK-NEXT:    mrs x20, SVCR
; CHECK-NEXT:    msub x9, x8, x8, x9
; CHECK-NEXT:    mov sp, x9
; CHECK-NEXT:    sub x10, x29, #80
; CHECK-NEXT:    stp x9, x8, [x29, #-80]
; CHECK-NEXT:    msr TPIDR2_EL0, x10
; CHECK-NEXT:    tbz w20, #0, .LBB3_2
; CHECK-NEXT:  // %bb.1:
; CHECK-NEXT:    smstop sm
; CHECK-NEXT:  .LBB3_2:
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    tbz w20, #0, .LBB3_4
; CHECK-NEXT:  // %bb.3:
; CHECK-NEXT:    smstart sm
; CHECK-NEXT:  .LBB3_4:
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #80
; CHECK-NEXT:    cbnz x8, .LBB3_6
; CHECK-NEXT:  // %bb.5:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB3_6:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    sub sp, x29, #64
; CHECK-NEXT:    ldp x20, x19, [sp, #80] // 16-byte Folded Reload
; CHECK-NEXT:    ldp x29, x30, [sp, #64] // 16-byte Folded Reload
; CHECK-NEXT:    ldp d9, d8, [sp, #48] // 16-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], #96 // 16-byte Folded Reload
; CHECK-NEXT:    ret
;
; CHECK-NEWLOWERING-LABEL: test_lazy_save_and_conditional_smstart:
; CHECK-NEWLOWERING:       // %bb.0:
; CHECK-NEWLOWERING-NEXT:    stp d15, d14, [sp, #-96]! // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    stp d13, d12, [sp, #16] // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    stp d11, d10, [sp, #32] // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    stp d9, d8, [sp, #48] // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    stp x29, x30, [sp, #64] // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    add x29, sp, #64
; CHECK-NEWLOWERING-NEXT:    stp x20, x19, [sp, #80] // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    sub sp, sp, #16
; CHECK-NEWLOWERING-NEXT:    rdsvl x8, #1
; CHECK-NEWLOWERING-NEXT:    mov x9, sp
; CHECK-NEWLOWERING-NEXT:    msub x9, x8, x8, x9
; CHECK-NEWLOWERING-NEXT:    mov sp, x9
; CHECK-NEWLOWERING-NEXT:    stp x9, x8, [x29, #-80]
; CHECK-NEWLOWERING-NEXT:    mrs x20, SVCR
; CHECK-NEWLOWERING-NEXT:    sub x8, x29, #80
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, x8
; CHECK-NEWLOWERING-NEXT:    tbz w20, #0, .LBB3_2
; CHECK-NEWLOWERING-NEXT:  // %bb.1:
; CHECK-NEWLOWERING-NEXT:    smstop sm
; CHECK-NEWLOWERING-NEXT:  .LBB3_2:
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    tbz w20, #0, .LBB3_4
; CHECK-NEWLOWERING-NEXT:  // %bb.3:
; CHECK-NEWLOWERING-NEXT:    smstart sm
; CHECK-NEWLOWERING-NEXT:  .LBB3_4:
; CHECK-NEWLOWERING-NEXT:    smstart za
; CHECK-NEWLOWERING-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEWLOWERING-NEXT:    sub x0, x29, #80
; CHECK-NEWLOWERING-NEXT:    cbnz x8, .LBB3_6
; CHECK-NEWLOWERING-NEXT:  // %bb.5:
; CHECK-NEWLOWERING-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEWLOWERING-NEXT:  .LBB3_6:
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEWLOWERING-NEXT:    sub sp, x29, #64
; CHECK-NEWLOWERING-NEXT:    ldp x20, x19, [sp, #80] // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ldp x29, x30, [sp, #64] // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ldp d9, d8, [sp, #48] // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ldp d11, d10, [sp, #32] // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ldp d13, d12, [sp, #16] // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ldp d15, d14, [sp], #96 // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ret
  call void @private_za_callee()
  ret void
}

; Note: For the final @private_za_callee() we setup a lazy save then don't
; restore from it (since ZA is off on return). We could improve this case
; by turning ZA off before the final private ZA call.
define void @test_lazy_save_mixed_shared_and_private_callees() "aarch64_new_za"
; CHECK-LABEL: test_lazy_save_mixed_shared_and_private_callees:
; CHECK:       // %bb.0: // %prelude
; CHECK-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT:    mov x29, sp
; CHECK-NEXT:    sub sp, sp, #16
; CHECK-NEXT:    .cfi_def_cfa w29, 32
; CHECK-NEXT:    .cfi_offset w19, -8
; CHECK-NEXT:    .cfi_offset w20, -16
; CHECK-NEXT:    .cfi_offset w30, -24
; CHECK-NEXT:    .cfi_offset w29, -32
; CHECK-NEXT:    rdsvl x8, #1
; CHECK-NEXT:    mov x9, sp
; CHECK-NEXT:    msub x9, x8, x8, x9
; CHECK-NEXT:    mov sp, x9
; CHECK-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    cbz x8, .LBB4_2
; CHECK-NEXT:  // %bb.1: // %save.za
; CHECK-NEXT:    bl __arm_tpidr2_save
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:  .LBB4_2:
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    sub x20, x29, #16
; CHECK-NEXT:    zero {za}
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB4_4
; CHECK-NEXT:  // %bb.3:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB4_4:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    bl shared_za_callee
; CHECK-NEXT:    bl preserves_za_callee
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB4_6
; CHECK-NEXT:  // %bb.5:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB4_6:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    smstop za
; CHECK-NEXT:    mov sp, x29
; CHECK-NEXT:    ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-NEXT:    ret
;
; CHECK-NEWLOWERING-LABEL: test_lazy_save_mixed_shared_and_private_callees:
; CHECK-NEWLOWERING:       // %bb.0:
; CHECK-NEWLOWERING-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-NEWLOWERING-NEXT:    mov x29, sp
; CHECK-NEWLOWERING-NEXT:    sub sp, sp, #16
; CHECK-NEWLOWERING-NEXT:    .cfi_def_cfa w29, 32
; CHECK-NEWLOWERING-NEXT:    .cfi_offset w19, -16
; CHECK-NEWLOWERING-NEXT:    .cfi_offset w30, -24
; CHECK-NEWLOWERING-NEXT:    .cfi_offset w29, -32
; CHECK-NEWLOWERING-NEXT:    rdsvl x8, #1
; CHECK-NEWLOWERING-NEXT:    mov x9, sp
; CHECK-NEWLOWERING-NEXT:    msub x9, x8, x8, x9
; CHECK-NEWLOWERING-NEXT:    mov sp, x9
; CHECK-NEWLOWERING-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-NEWLOWERING-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEWLOWERING-NEXT:    cbz x8, .LBB4_2
; CHECK-NEWLOWERING-NEXT:  // %bb.1:
; CHECK-NEWLOWERING-NEXT:    bl __arm_tpidr2_save
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEWLOWERING-NEXT:    zero {za}
; CHECK-NEWLOWERING-NEXT:  .LBB4_2:
; CHECK-NEWLOWERING-NEXT:    smstart za
; CHECK-NEWLOWERING-NEXT:    sub x8, x29, #16
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, x8
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    smstart za
; CHECK-NEWLOWERING-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEWLOWERING-NEXT:    sub x0, x29, #16
; CHECK-NEWLOWERING-NEXT:    cbnz x8, .LBB4_4
; CHECK-NEWLOWERING-NEXT:  // %bb.3:
; CHECK-NEWLOWERING-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEWLOWERING-NEXT:  .LBB4_4:
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEWLOWERING-NEXT:    bl shared_za_callee
; CHECK-NEWLOWERING-NEXT:    bl preserves_za_callee
; CHECK-NEWLOWERING-NEXT:    sub x8, x29, #16
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, x8
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEWLOWERING-NEXT:    smstop za
; CHECK-NEWLOWERING-NEXT:    mov sp, x29
; CHECK-NEWLOWERING-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-NEWLOWERING-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ret
{
  call void @private_za_callee()
  call void @shared_za_callee()
  call void @preserves_za_callee()
  call void @private_za_callee()
  ret void
}

define void @test_many_back2back_private_za_calls() "aarch64_inout_za" {
; CHECK-LABEL: test_many_back2back_private_za_calls:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT:    mov x29, sp
; CHECK-NEXT:    sub sp, sp, #16
; CHECK-NEXT:    .cfi_def_cfa w29, 32
; CHECK-NEXT:    .cfi_offset w19, -8
; CHECK-NEXT:    .cfi_offset w20, -16
; CHECK-NEXT:    .cfi_offset w30, -24
; CHECK-NEXT:    .cfi_offset w29, -32
; CHECK-NEXT:    rdsvl x8, #1
; CHECK-NEXT:    mov x9, sp
; CHECK-NEXT:    msub x9, x8, x8, x9
; CHECK-NEXT:    mov sp, x9
; CHECK-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-NEXT:    bl shared_za_callee
; CHECK-NEXT:    sub x20, x29, #16
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB5_2
; CHECK-NEXT:  // %bb.1:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB5_2:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB5_4
; CHECK-NEXT:  // %bb.3:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB5_4:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB5_6
; CHECK-NEXT:  // %bb.5:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB5_6:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB5_8
; CHECK-NEXT:  // %bb.7:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB5_8:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB5_10
; CHECK-NEXT:  // %bb.9:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB5_10:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    msr TPIDR2_EL0, x20
; CHECK-NEXT:    bl private_za_callee
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB5_12
; CHECK-NEXT:  // %bb.11:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB5_12:
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    bl shared_za_callee
; CHECK-NEXT:    mov sp, x29
; CHECK-NEXT:    ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-NEXT:    ret
;
; CHECK-NEWLOWERING-LABEL: test_many_back2back_private_za_calls:
; CHECK-NEWLOWERING:       // %bb.0:
; CHECK-NEWLOWERING-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-NEWLOWERING-NEXT:    mov x29, sp
; CHECK-NEWLOWERING-NEXT:    sub sp, sp, #16
; CHECK-NEWLOWERING-NEXT:    .cfi_def_cfa w29, 32
; CHECK-NEWLOWERING-NEXT:    .cfi_offset w19, -16
; CHECK-NEWLOWERING-NEXT:    .cfi_offset w30, -24
; CHECK-NEWLOWERING-NEXT:    .cfi_offset w29, -32
; CHECK-NEWLOWERING-NEXT:    rdsvl x8, #1
; CHECK-NEWLOWERING-NEXT:    mov x9, sp
; CHECK-NEWLOWERING-NEXT:    msub x9, x8, x8, x9
; CHECK-NEWLOWERING-NEXT:    mov sp, x9
; CHECK-NEWLOWERING-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-NEWLOWERING-NEXT:    bl shared_za_callee
; CHECK-NEWLOWERING-NEXT:    sub x8, x29, #16
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, x8
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    bl private_za_callee
; CHECK-NEWLOWERING-NEXT:    smstart za
; CHECK-NEWLOWERING-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEWLOWERING-NEXT:    sub x0, x29, #16
; CHECK-NEWLOWERING-NEXT:    cbnz x8, .LBB5_2
; CHECK-NEWLOWERING-NEXT:  // %bb.1:
; CHECK-NEWLOWERING-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEWLOWERING-NEXT:  .LBB5_2:
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEWLOWERING-NEXT:    bl shared_za_callee
; CHECK-NEWLOWERING-NEXT:    mov sp, x29
; CHECK-NEWLOWERING-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-NEWLOWERING-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ret
  call void @shared_za_callee()
  call void @private_za_callee()
  call void @private_za_callee()
  call void @private_za_callee()
  call void @private_za_callee()
  call void @private_za_callee()
  call void @private_za_callee()
  call void @shared_za_callee()
  ret void
}

define void @test_shared_private_shared() nounwind "aarch64_inout_za" {
; CHECK-COMMON-LABEL: test_shared_private_shared:
; CHECK-COMMON:       // %bb.0:
; CHECK-COMMON-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-COMMON-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-COMMON-NEXT:    mov x29, sp
; CHECK-COMMON-NEXT:    sub sp, sp, #16
; CHECK-COMMON-NEXT:    rdsvl x8, #1
; CHECK-COMMON-NEXT:    mov x9, sp
; CHECK-COMMON-NEXT:    msub x9, x8, x8, x9
; CHECK-COMMON-NEXT:    mov sp, x9
; CHECK-COMMON-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-COMMON-NEXT:    bl shared_za_callee
; CHECK-COMMON-NEXT:    sub x8, x29, #16
; CHECK-COMMON-NEXT:    msr TPIDR2_EL0, x8
; CHECK-COMMON-NEXT:    bl private_za_callee
; CHECK-COMMON-NEXT:    smstart za
; CHECK-COMMON-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-COMMON-NEXT:    sub x0, x29, #16
; CHECK-COMMON-NEXT:    cbnz x8, .LBB6_2
; CHECK-COMMON-NEXT:  // %bb.1:
; CHECK-COMMON-NEXT:    bl __arm_tpidr2_restore
; CHECK-COMMON-NEXT:  .LBB6_2:
; CHECK-COMMON-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-COMMON-NEXT:    bl shared_za_callee
; CHECK-COMMON-NEXT:    mov sp, x29
; CHECK-COMMON-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-COMMON-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-COMMON-NEXT:    ret
  call void @shared_za_callee()
  call void @private_za_callee()
  call void @shared_za_callee()
  ret void
}

define void @test_only_shared_za() nounwind "aarch64_inout_za" {
; CHECK-COMMON-LABEL: test_only_shared_za:
; CHECK-COMMON:       // %bb.0:
; CHECK-COMMON-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-COMMON-NEXT:    bl shared_za_callee
; CHECK-COMMON-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-COMMON-NEXT:    ret
  call void @shared_za_callee()
  ret void
}

declare i64 @shared_za_callee_i64(i64) "aarch64_inout_za"
declare i64 @private_za_callee_i64(i64)

define i64 @test_shared_private_shared_i64(i64 %x) nounwind "aarch64_inout_za" {
; CHECK-COMMON-LABEL: test_shared_private_shared_i64:
; CHECK-COMMON:       // %bb.0:
; CHECK-COMMON-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-COMMON-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-COMMON-NEXT:    mov x29, sp
; CHECK-COMMON-NEXT:    sub sp, sp, #16
; CHECK-COMMON-NEXT:    rdsvl x8, #1
; CHECK-COMMON-NEXT:    mov x9, sp
; CHECK-COMMON-NEXT:    msub x9, x8, x8, x9
; CHECK-COMMON-NEXT:    mov sp, x9
; CHECK-COMMON-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-COMMON-NEXT:    bl shared_za_callee_i64
; CHECK-COMMON-NEXT:    sub x8, x29, #16
; CHECK-COMMON-NEXT:    msr TPIDR2_EL0, x8
; CHECK-COMMON-NEXT:    bl private_za_callee_i64
; CHECK-COMMON-NEXT:    mov x1, x0
; CHECK-COMMON-NEXT:    smstart za
; CHECK-COMMON-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-COMMON-NEXT:    sub x0, x29, #16
; CHECK-COMMON-NEXT:    cbnz x8, .LBB8_2
; CHECK-COMMON-NEXT:  // %bb.1:
; CHECK-COMMON-NEXT:    bl __arm_tpidr2_restore
; CHECK-COMMON-NEXT:  .LBB8_2:
; CHECK-COMMON-NEXT:    mov x0, x1
; CHECK-COMMON-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-COMMON-NEXT:    bl shared_za_callee_i64
; CHECK-COMMON-NEXT:    mov sp, x29
; CHECK-COMMON-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-COMMON-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-COMMON-NEXT:    ret
  %a = call i64 @shared_za_callee_i64(i64 %x)
  %b = call i64 @private_za_callee_i64(i64 %a)
  %c = call i64 @shared_za_callee_i64(i64 %b)
  ret i64 %c
}

declare i64 @many_args_private_za_callee(
  i64, i64, i64, i64, i64, i64, i64, i64, i64, i64)

; In this example some arguments are passed on the stack, which decrements the
; stack pointer before the call -- in this test the lazy save should be setup
; before the stack decrement.
define i64  @test_many_callee_arguments(
; CHECK-LABEL: test_many_callee_arguments:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-NEXT:    mov x29, sp
; CHECK-NEXT:    sub sp, sp, #16
; CHECK-NEXT:    mov x8, sp
; CHECK-NEXT:    rdsvl x9, #1
; CHECK-NEXT:    msub x8, x9, x9, x8
; CHECK-NEXT:    mov sp, x8
; CHECK-NEXT:    ldp x10, x11, [x29, #32]
; CHECK-NEXT:    sub x12, x29, #16
; CHECK-NEXT:    stp x8, x9, [x29, #-16]
; CHECK-NEXT:    msr TPIDR2_EL0, x12
; CHECK-NEXT:    stp x10, x11, [sp, #-16]!
; CHECK-NEXT:    bl many_args_private_za_callee
; CHECK-NEXT:    add sp, sp, #16
; CHECK-NEXT:    mov x1, x0
; CHECK-NEXT:    smstart za
; CHECK-NEXT:    mrs x8, TPIDR2_EL0
; CHECK-NEXT:    sub x0, x29, #16
; CHECK-NEXT:    cbnz x8, .LBB9_2
; CHECK-NEXT:  // %bb.1:
; CHECK-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEXT:  .LBB9_2:
; CHECK-NEXT:    mov x0, x1
; CHECK-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEXT:    mov sp, x29
; CHECK-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-NEXT:    ret
;
; CHECK-NEWLOWERING-LABEL: test_many_callee_arguments:
; CHECK-NEWLOWERING:       // %bb.0:
; CHECK-NEWLOWERING-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEWLOWERING-NEXT:    str x19, [sp, #16] // 8-byte Spill
; CHECK-NEWLOWERING-NEXT:    mov x29, sp
; CHECK-NEWLOWERING-NEXT:    sub sp, sp, #16
; CHECK-NEWLOWERING-NEXT:    rdsvl x8, #1
; CHECK-NEWLOWERING-NEXT:    mov x9, sp
; CHECK-NEWLOWERING-NEXT:    msub x9, x8, x8, x9
; CHECK-NEWLOWERING-NEXT:    mov sp, x9
; CHECK-NEWLOWERING-NEXT:    ldp x10, x11, [x29, #32]
; CHECK-NEWLOWERING-NEXT:    sub x12, x29, #16
; CHECK-NEWLOWERING-NEXT:    stp x9, x8, [x29, #-16]
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, x12
; CHECK-NEWLOWERING-NEXT:    stp x10, x11, [sp, #-16]!
; CHECK-NEWLOWERING-NEXT:    bl many_args_private_za_callee
; CHECK-NEWLOWERING-NEXT:    add sp, sp, #16
; CHECK-NEWLOWERING-NEXT:    mov x8, x0
; CHECK-NEWLOWERING-NEXT:    smstart za
; CHECK-NEWLOWERING-NEXT:    mrs x9, TPIDR2_EL0
; CHECK-NEWLOWERING-NEXT:    sub x0, x29, #16
; CHECK-NEWLOWERING-NEXT:    cbnz x9, .LBB9_2
; CHECK-NEWLOWERING-NEXT:  // %bb.1:
; CHECK-NEWLOWERING-NEXT:    bl __arm_tpidr2_restore
; CHECK-NEWLOWERING-NEXT:  .LBB9_2:
; CHECK-NEWLOWERING-NEXT:    mov x0, x8
; CHECK-NEWLOWERING-NEXT:    msr TPIDR2_EL0, xzr
; CHECK-NEWLOWERING-NEXT:    mov sp, x29
; CHECK-NEWLOWERING-NEXT:    ldr x19, [sp, #16] // 8-byte Reload
; CHECK-NEWLOWERING-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
; CHECK-NEWLOWERING-NEXT:    ret
  i64 %0, i64 %1, i64 %2, i64 %3, i64 %4, i64 %5, i64 %6, i64 %7, i64 %8, i64 %9
) nounwind "aarch64_inout_za" {
  %ret = call i64 @many_args_private_za_callee(
    i64 %0, i64 %1, i64 %2, i64 %3, i64 %4, i64 %5, i64 %6, i64 %7, i64 %8, i64 %9)
  ret i64 %ret
}