; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple riscv32-unknown-linux-gnu -o - %s | FileCheck %s
; RUN: llc -mtriple riscv32-unknown-linux-gnu -mattr=experimental-zicfilp \
; RUN:   -code-model=large -o - %s \
; RUN:   | FileCheck %s -check-prefix=CHECK-LARGE-ZICFILP
; RUN: llc -mtriple riscv32-unknown-elf       -o - %s | FileCheck %s

; Perform tail call optimization for global address.
declare i32 @callee_tail(i32 %i)
define i32 @caller_tail(i32 %i) nounwind {
; CHECK-LABEL: caller_tail:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    tail callee_tail
;
; CHECK-LARGE-ZICFILP-LABEL: caller_tail:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi0:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a1, %pcrel_hi(.LCPI0_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi0)(a1)
; CHECK-LARGE-ZICFILP-NEXT:    jr t2
entry:
  %r = tail call i32 @callee_tail(i32 %i)
  ret i32 %r
}

; Perform tail call optimization for external symbol.
@dest = global [2 x i8] zeroinitializer
declare void @llvm.memcpy.p0.p0.i32(ptr, ptr, i32, i1)
define void @caller_extern(ptr %src) optsize {
; CHECK-LABEL: caller_extern:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    lui a1, %hi(dest)
; CHECK-NEXT:    addi a1, a1, %lo(dest)
; CHECK-NEXT:    li a2, 7
; CHECK-NEXT:    mv a3, a0
; CHECK-NEXT:    mv a0, a1
; CHECK-NEXT:    mv a1, a3
; CHECK-NEXT:    tail memcpy
;
; CHECK-LARGE-ZICFILP-LABEL: caller_extern:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi1:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a1, %pcrel_hi(.LCPI1_0)
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi2:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a2, %pcrel_hi(.LCPI1_1)
; CHECK-LARGE-ZICFILP-NEXT:    lw a1, %pcrel_lo(.Lpcrel_hi1)(a1)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi2)(a2)
; CHECK-LARGE-ZICFILP-NEXT:    li a2, 7
; CHECK-LARGE-ZICFILP-NEXT:    mv a3, a0
; CHECK-LARGE-ZICFILP-NEXT:    mv a0, a1
; CHECK-LARGE-ZICFILP-NEXT:    mv a1, a3
; CHECK-LARGE-ZICFILP-NEXT:    jr t2
entry:
  tail call void @llvm.memcpy.p0.p0.i32(ptr @dest, ptr %src, i32 7, i1 false)
  ret void
}

; Perform tail call optimization for external symbol.
@dest_pgso = global [2 x i8] zeroinitializer
define void @caller_extern_pgso(ptr %src) !prof !14 {
; CHECK-LABEL: caller_extern_pgso:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    lui a1, %hi(dest_pgso)
; CHECK-NEXT:    addi a1, a1, %lo(dest_pgso)
; CHECK-NEXT:    li a2, 7
; CHECK-NEXT:    mv a3, a0
; CHECK-NEXT:    mv a0, a1
; CHECK-NEXT:    mv a1, a3
; CHECK-NEXT:    tail memcpy
;
; CHECK-LARGE-ZICFILP-LABEL: caller_extern_pgso:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi3:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a1, %pcrel_hi(.LCPI2_0)
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi4:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a2, %pcrel_hi(.LCPI2_1)
; CHECK-LARGE-ZICFILP-NEXT:    lw a1, %pcrel_lo(.Lpcrel_hi3)(a1)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi4)(a2)
; CHECK-LARGE-ZICFILP-NEXT:    li a2, 7
; CHECK-LARGE-ZICFILP-NEXT:    mv a3, a0
; CHECK-LARGE-ZICFILP-NEXT:    mv a0, a1
; CHECK-LARGE-ZICFILP-NEXT:    mv a1, a3
; CHECK-LARGE-ZICFILP-NEXT:    jr t2
entry:
  tail call void @llvm.memcpy.p0.p0.i32(ptr @dest_pgso, ptr %src, i32 7, i1 false)
  ret void
}

; Perform indirect tail call optimization (for function pointer call).
declare void @callee_indirect1()
declare void @callee_indirect2()
define void @caller_indirect_tail(i32 %a) nounwind {
; CHECK-LABEL: caller_indirect_tail:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    beqz a0, .LBB3_2
; CHECK-NEXT:  # %bb.1: # %entry
; CHECK-NEXT:    lui t1, %hi(callee_indirect2)
; CHECK-NEXT:    addi t1, t1, %lo(callee_indirect2)
; CHECK-NEXT:    jr t1
; CHECK-NEXT:  .LBB3_2:
; CHECK-NEXT:    lui t1, %hi(callee_indirect1)
; CHECK-NEXT:    addi t1, t1, %lo(callee_indirect1)
; CHECK-NEXT:    jr t1
;
; CHECK-LARGE-ZICFILP-LABEL: caller_indirect_tail:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    beqz a0, .LBB3_2
; CHECK-LARGE-ZICFILP-NEXT:  # %bb.1: # %entry
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi6:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI3_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t1, %pcrel_lo(.Lpcrel_hi6)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jr t1
; CHECK-LARGE-ZICFILP-NEXT:  .LBB3_2:
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi5:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI3_1)
; CHECK-LARGE-ZICFILP-NEXT:    lw t1, %pcrel_lo(.Lpcrel_hi5)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jr t1
entry:
  %tobool = icmp eq i32 %a, 0
  %callee = select i1 %tobool, ptr @callee_indirect1, ptr @callee_indirect2
  tail call void %callee()
  ret void
}

; Make sure we don't use t0 as the source for jr as that is a hint to pop the
; return address stack on some microarchitectures.
define i32 @caller_indirect_no_t0(ptr %0, i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i32 %6, i32 %7) {
; CHECK-LABEL: caller_indirect_no_t0:
; CHECK:       # %bb.0:
; CHECK-NEXT:    mv t1, a0
; CHECK-NEXT:    mv a0, a1
; CHECK-NEXT:    mv a1, a2
; CHECK-NEXT:    mv a2, a3
; CHECK-NEXT:    mv a3, a4
; CHECK-NEXT:    mv a4, a5
; CHECK-NEXT:    mv a5, a6
; CHECK-NEXT:    mv a6, a7
; CHECK-NEXT:    jr t1
;
; CHECK-LARGE-ZICFILP-LABEL: caller_indirect_no_t0:
; CHECK-LARGE-ZICFILP:       # %bb.0:
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    mv t1, a0
; CHECK-LARGE-ZICFILP-NEXT:    mv a0, a1
; CHECK-LARGE-ZICFILP-NEXT:    mv a1, a2
; CHECK-LARGE-ZICFILP-NEXT:    mv a2, a3
; CHECK-LARGE-ZICFILP-NEXT:    mv a3, a4
; CHECK-LARGE-ZICFILP-NEXT:    mv a4, a5
; CHECK-LARGE-ZICFILP-NEXT:    mv a5, a6
; CHECK-LARGE-ZICFILP-NEXT:    mv a6, a7
; CHECK-LARGE-ZICFILP-NEXT:    jr t1
  %9 = tail call i32 %0(i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i32 %6, i32 %7)
  ret i32 %9
}

; Do not tail call optimize functions with varargs passed by stack.
declare i32 @callee_varargs(i32, ...)
define void @caller_varargs(i32 %a, i32 %b) nounwind {
; CHECK-LABEL: caller_varargs:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a0, 0(sp)
; CHECK-NEXT:    mv a2, a1
; CHECK-NEXT:    mv a3, a0
; CHECK-NEXT:    mv a4, a0
; CHECK-NEXT:    mv a5, a1
; CHECK-NEXT:    mv a6, a1
; CHECK-NEXT:    mv a7, a0
; CHECK-NEXT:    call callee_varargs
; CHECK-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    ret
;
; CHECK-LARGE-ZICFILP-LABEL: caller_varargs:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, -16
; CHECK-LARGE-ZICFILP-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi7:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a2, %pcrel_hi(.LCPI5_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi7)(a2)
; CHECK-LARGE-ZICFILP-NEXT:    sw a0, 0(sp)
; CHECK-LARGE-ZICFILP-NEXT:    mv a2, a1
; CHECK-LARGE-ZICFILP-NEXT:    mv a3, a0
; CHECK-LARGE-ZICFILP-NEXT:    mv a4, a0
; CHECK-LARGE-ZICFILP-NEXT:    mv a5, a1
; CHECK-LARGE-ZICFILP-NEXT:    mv a6, a1
; CHECK-LARGE-ZICFILP-NEXT:    mv a7, a0
; CHECK-LARGE-ZICFILP-NEXT:    jalr t2
; CHECK-LARGE-ZICFILP-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, 16
; CHECK-LARGE-ZICFILP-NEXT:    ret
entry:
  %call = tail call i32 (i32, ...) @callee_varargs(i32 %a, i32 %b, i32 %b, i32 %a, i32 %a, i32 %b, i32 %b, i32 %a, i32 %a)
  ret void
}

; Do not tail call optimize if stack is used to pass parameters.
declare i32 @callee_args(i32 %a, i32 %b, i32 %c, i32 %dd, i32 %e, i32 %ff, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n)
define i32 @caller_args(i32 %a, i32 %b, i32 %c, i32 %dd, i32 %e, i32 %ff, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n) nounwind {
; CHECK-LABEL: caller_args:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -32
; CHECK-NEXT:    sw ra, 28(sp) # 4-byte Folded Spill
; CHECK-NEXT:    lw t0, 32(sp)
; CHECK-NEXT:    lw t1, 36(sp)
; CHECK-NEXT:    lw t2, 40(sp)
; CHECK-NEXT:    lw t3, 44(sp)
; CHECK-NEXT:    lw t4, 48(sp)
; CHECK-NEXT:    lw t5, 52(sp)
; CHECK-NEXT:    sw t4, 16(sp)
; CHECK-NEXT:    sw t5, 20(sp)
; CHECK-NEXT:    sw t0, 0(sp)
; CHECK-NEXT:    sw t1, 4(sp)
; CHECK-NEXT:    sw t2, 8(sp)
; CHECK-NEXT:    sw t3, 12(sp)
; CHECK-NEXT:    call callee_args
; CHECK-NEXT:    lw ra, 28(sp) # 4-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 32
; CHECK-NEXT:    ret
;
; CHECK-LARGE-ZICFILP-LABEL: caller_args:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, -32
; CHECK-LARGE-ZICFILP-NEXT:    sw ra, 28(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    lw t0, 32(sp)
; CHECK-LARGE-ZICFILP-NEXT:    lw t1, 36(sp)
; CHECK-LARGE-ZICFILP-NEXT:    lw t3, 40(sp)
; CHECK-LARGE-ZICFILP-NEXT:    lw t4, 44(sp)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, 48(sp)
; CHECK-LARGE-ZICFILP-NEXT:    lw t5, 52(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw t2, 16(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw t5, 20(sp)
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi8:
; CHECK-LARGE-ZICFILP-NEXT:    auipc t2, %pcrel_hi(.LCPI6_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi8)(t2)
; CHECK-LARGE-ZICFILP-NEXT:    sw t0, 0(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw t1, 4(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw t3, 8(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw t4, 12(sp)
; CHECK-LARGE-ZICFILP-NEXT:    jalr t2
; CHECK-LARGE-ZICFILP-NEXT:    lw ra, 28(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, 32
; CHECK-LARGE-ZICFILP-NEXT:    ret
entry:
  %r = tail call i32 @callee_args(i32 %a, i32 %b, i32 %c, i32 %dd, i32 %e, i32 %ff, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n)
  ret i32 %r
}

; Do not tail call optimize if parameters need to be passed indirectly.
declare i32 @callee_indirect_args(fp128 %a)
define void @caller_indirect_args() nounwind {
; CHECK-LABEL: caller_indirect_args:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -32
; CHECK-NEXT:    sw ra, 28(sp) # 4-byte Folded Spill
; CHECK-NEXT:    lui a1, 262128
; CHECK-NEXT:    mv a0, sp
; CHECK-NEXT:    sw zero, 0(sp)
; CHECK-NEXT:    sw zero, 4(sp)
; CHECK-NEXT:    sw zero, 8(sp)
; CHECK-NEXT:    sw a1, 12(sp)
; CHECK-NEXT:    call callee_indirect_args
; CHECK-NEXT:    lw ra, 28(sp) # 4-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 32
; CHECK-NEXT:    ret
;
; CHECK-LARGE-ZICFILP-LABEL: caller_indirect_args:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, -32
; CHECK-LARGE-ZICFILP-NEXT:    sw ra, 28(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    lui a1, 262128
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi9:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI7_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi9)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    mv a0, sp
; CHECK-LARGE-ZICFILP-NEXT:    sw zero, 0(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw zero, 4(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw zero, 8(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw a1, 12(sp)
; CHECK-LARGE-ZICFILP-NEXT:    jalr t2
; CHECK-LARGE-ZICFILP-NEXT:    lw ra, 28(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, 32
; CHECK-LARGE-ZICFILP-NEXT:    ret
entry:
  %call = tail call i32 @callee_indirect_args(fp128 0xL00000000000000003FFF000000000000)
  ret void
}

; Perform tail call optimization for external weak symbol.
declare extern_weak void @callee_weak()
define void @caller_weak() nounwind {
; CHECK-LABEL: caller_weak:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    tail callee_weak
;
; CHECK-LARGE-ZICFILP-LABEL: caller_weak:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi10:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI8_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi10)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jr t2
entry:
  tail call void @callee_weak()
  ret void
}

; Exception-handling functions need a special set of instructions to indicate a
; return to the hardware. Tail-calling another function would probably break
; this.
declare void @callee_irq()
define void @caller_irq() nounwind "interrupt"="machine" {
; CHECK-LABEL: caller_irq:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -64
; CHECK-NEXT:    sw ra, 60(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw t0, 56(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw t1, 52(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw t2, 48(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a0, 44(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a1, 40(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a2, 36(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a3, 32(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a4, 28(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a5, 24(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a6, 20(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw a7, 16(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw t3, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw t4, 8(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw t5, 4(sp) # 4-byte Folded Spill
; CHECK-NEXT:    sw t6, 0(sp) # 4-byte Folded Spill
; CHECK-NEXT:    call callee_irq
; CHECK-NEXT:    lw ra, 60(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw t0, 56(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw t1, 52(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw t2, 48(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw a0, 44(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw a1, 40(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw a2, 36(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw a3, 32(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw a4, 28(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw a5, 24(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw a6, 20(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw a7, 16(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw t3, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw t4, 8(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw t5, 4(sp) # 4-byte Folded Reload
; CHECK-NEXT:    lw t6, 0(sp) # 4-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 64
; CHECK-NEXT:    mret
;
; CHECK-LARGE-ZICFILP-LABEL: caller_irq:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, -64
; CHECK-LARGE-ZICFILP-NEXT:    sw ra, 60(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw t0, 56(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw t1, 52(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw t2, 48(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw a0, 44(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw a1, 40(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw a2, 36(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw a3, 32(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw a4, 28(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw a5, 24(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw a6, 20(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw a7, 16(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw t3, 12(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw t4, 8(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw t5, 4(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    sw t6, 0(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi11:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI9_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi11)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jalr t2
; CHECK-LARGE-ZICFILP-NEXT:    lw ra, 60(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw t0, 56(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw t1, 52(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, 48(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw a0, 44(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw a1, 40(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw a2, 36(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw a3, 32(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw a4, 28(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw a5, 24(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw a6, 20(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw a7, 16(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw t3, 12(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw t4, 8(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw t5, 4(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    lw t6, 0(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, 64
; CHECK-LARGE-ZICFILP-NEXT:    mret
entry:
  tail call void @callee_irq()
  ret void
}

; Byval parameters hand the function a pointer directly into the stack area
; we want to reuse during a tail call. Do not tail call optimize functions with
; byval parameters.
declare i32 @callee_byval(ptr byval(ptr) %a)
define i32 @caller_byval() nounwind {
; CHECK-LABEL: caller_byval:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT:    lw a0, 8(sp)
; CHECK-NEXT:    sw a0, 4(sp)
; CHECK-NEXT:    addi a0, sp, 4
; CHECK-NEXT:    call callee_byval
; CHECK-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    ret
;
; CHECK-LARGE-ZICFILP-LABEL: caller_byval:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, -16
; CHECK-LARGE-ZICFILP-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:    lw a0, 8(sp)
; CHECK-LARGE-ZICFILP-NEXT:    sw a0, 4(sp)
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi12:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI10_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi12)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    addi a0, sp, 4
; CHECK-LARGE-ZICFILP-NEXT:    jalr t2
; CHECK-LARGE-ZICFILP-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, 16
; CHECK-LARGE-ZICFILP-NEXT:    ret
entry:
  %a = alloca ptr
  %r = tail call i32 @callee_byval(ptr byval(ptr) %a)
  ret i32 %r
}

; Do not tail call optimize if callee uses structret semantics.
%struct.A = type { i32 }
@a = global %struct.A zeroinitializer

declare void @callee_struct(ptr sret(%struct.A) %a)
define void @caller_nostruct() nounwind {
; CHECK-LABEL: caller_nostruct:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT:    lui a0, %hi(a)
; CHECK-NEXT:    addi a0, a0, %lo(a)
; CHECK-NEXT:    call callee_struct
; CHECK-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    ret
;
; CHECK-LARGE-ZICFILP-LABEL: caller_nostruct:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, -16
; CHECK-LARGE-ZICFILP-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi13:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI11_0)
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi14:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a1, %pcrel_hi(.LCPI11_1)
; CHECK-LARGE-ZICFILP-NEXT:    lw a0, %pcrel_lo(.Lpcrel_hi13)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi14)(a1)
; CHECK-LARGE-ZICFILP-NEXT:    jalr t2
; CHECK-LARGE-ZICFILP-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, 16
; CHECK-LARGE-ZICFILP-NEXT:    ret
entry:
  tail call void @callee_struct(ptr sret(%struct.A) @a)
  ret void
}

; Do not tail call optimize if caller uses structret semantics.
declare void @callee_nostruct()
define void @caller_struct(ptr sret(%struct.A) %a) nounwind {
; CHECK-LABEL: caller_struct:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT:    call callee_nostruct
; CHECK-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    ret
;
; CHECK-LARGE-ZICFILP-LABEL: caller_struct:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, -16
; CHECK-LARGE-ZICFILP-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi15:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI12_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi15)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jalr t2
; CHECK-LARGE-ZICFILP-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, 16
; CHECK-LARGE-ZICFILP-NEXT:    ret
entry:
  tail call void @callee_nostruct()
  ret void
}

; Do not tail call optimize if disabled.
define i32 @disable_tail_calls(i32 %i) nounwind "disable-tail-calls"="true" {
; CHECK-LABEL: disable_tail_calls:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT:    call callee_tail
; CHECK-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    ret
;
; CHECK-LARGE-ZICFILP-LABEL: disable_tail_calls:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, -16
; CHECK-LARGE-ZICFILP-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi16:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a1, %pcrel_hi(.LCPI13_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi16)(a1)
; CHECK-LARGE-ZICFILP-NEXT:    jalr t2
; CHECK-LARGE-ZICFILP-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-LARGE-ZICFILP-NEXT:    addi sp, sp, 16
; CHECK-LARGE-ZICFILP-NEXT:    ret
entry:
  %rv = tail call i32 @callee_tail(i32 %i)
  ret i32 %rv
}

; Duplicate returns to enable tail call optimizations.
declare i32 @test()
declare i32 @test1()
declare i32 @test2()
declare i32 @test3()
define i32 @duplicate_returns(i32 %a, i32 %b) nounwind {
; CHECK-LABEL: duplicate_returns:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    beqz a0, .LBB14_4
; CHECK-NEXT:  # %bb.1: # %if.else
; CHECK-NEXT:    beqz a1, .LBB14_5
; CHECK-NEXT:  # %bb.2: # %if.else4
; CHECK-NEXT:    bge a1, a0, .LBB14_6
; CHECK-NEXT:  # %bb.3: # %if.then6
; CHECK-NEXT:    tail test2
; CHECK-NEXT:  .LBB14_4: # %if.then
; CHECK-NEXT:    tail test
; CHECK-NEXT:  .LBB14_5: # %if.then2
; CHECK-NEXT:    tail test1
; CHECK-NEXT:  .LBB14_6: # %if.else8
; CHECK-NEXT:    tail test3
;
; CHECK-LARGE-ZICFILP-LABEL: duplicate_returns:
; CHECK-LARGE-ZICFILP:       # %bb.0: # %entry
; CHECK-LARGE-ZICFILP-NEXT:    lpad 0
; CHECK-LARGE-ZICFILP-NEXT:    beqz a0, .LBB14_4
; CHECK-LARGE-ZICFILP-NEXT:  # %bb.1: # %if.else
; CHECK-LARGE-ZICFILP-NEXT:    beqz a1, .LBB14_5
; CHECK-LARGE-ZICFILP-NEXT:  # %bb.2: # %if.else4
; CHECK-LARGE-ZICFILP-NEXT:    bge a1, a0, .LBB14_6
; CHECK-LARGE-ZICFILP-NEXT:  # %bb.3: # %if.then6
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi19:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI14_1)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi19)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jr t2
; CHECK-LARGE-ZICFILP-NEXT:  .LBB14_4: # %if.then
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi17:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI14_3)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi17)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jr t2
; CHECK-LARGE-ZICFILP-NEXT:  .LBB14_5: # %if.then2
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi18:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI14_2)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi18)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jr t2
; CHECK-LARGE-ZICFILP-NEXT:  .LBB14_6: # %if.else8
; CHECK-LARGE-ZICFILP-NEXT:  .Lpcrel_hi20:
; CHECK-LARGE-ZICFILP-NEXT:    auipc a0, %pcrel_hi(.LCPI14_0)
; CHECK-LARGE-ZICFILP-NEXT:    lw t2, %pcrel_lo(.Lpcrel_hi20)(a0)
; CHECK-LARGE-ZICFILP-NEXT:    jr t2
entry:
  %cmp = icmp eq i32 %a, 0
  br i1 %cmp, label %if.then, label %if.else

if.then:                                          ; preds = %entry
  %call = tail call i32 @test()
  br label %return

if.else:                                          ; preds = %entry
  %cmp1 = icmp eq i32 %b, 0
  br i1 %cmp1, label %if.then2, label %if.else4

if.then2:                                         ; preds = %if.else
  %call3 = tail call i32 @test1()
  br label %return

if.else4:                                         ; preds = %if.else
  %cmp5 = icmp sgt i32 %a, %b
  br i1 %cmp5, label %if.then6, label %if.else8

if.then6:                                         ; preds = %if.else4
  %call7 = tail call i32 @test2()
  br label %return

if.else8:                                         ; preds = %if.else4
  %call9 = tail call i32 @test3()
  br label %return

return:                                           ; preds = %if.else8, %if.then6, %if.then2, %if.then
  %retval = phi i32 [ %call, %if.then ], [ %call3, %if.then2 ], [ %call7, %if.then6 ], [ %call9, %if.else8 ]
  ret i32 %retval
}

!llvm.module.flags = !{!0}
!0 = !{i32 1, !"ProfileSummary", !1}
!1 = !{!2, !3, !4, !5, !6, !7, !8, !9}
!2 = !{!"ProfileFormat", !"InstrProf"}
!3 = !{!"TotalCount", i64 10000}
!4 = !{!"MaxCount", i64 10}
!5 = !{!"MaxInternalCount", i64 1}
!6 = !{!"MaxFunctionCount", i64 1000}
!7 = !{!"NumCounts", i64 3}
!8 = !{!"NumFunctions", i64 3}
!9 = !{!"DetailedSummary", !10}
!10 = !{!11, !12, !13}
!11 = !{i32 10000, i64 100, i32 1}
!12 = !{i32 999000, i64 100, i32 1}
!13 = !{i32 999999, i64 1, i32 2}
!14 = !{!"function_entry_count", i64 0}