I wrote a stack implementation using a singly linked list in x86_64 assembly. This stack supports the usual push/pop operations as well as first/next for iterating over each element.

I'm looking for general feedback.

Here are the stack subroutines.

; Stack Structure
;   Pointer Head
;   Pointer Current

; Stack Node
;   Pointer Next
;   Pointer Value

; input
;   void
; output
;   stack or 0 on error
StackCreate:
  mov rdi, 24
  call malloc
  test rax,rax
  jz StackCreate_end
  xor rdi, rdi
  mov [rax], rdi
  mov [rax+8], rdi
  ret
StackCreate_end:
  add rsp, 8
  ret

; input
;   stack
; output
;   void
StackDestroy:
  call free
  ret

; input
;   stack
;   value
; output
;   0 on error
StackPush:
  push rdi
  push rsi
  mov rdi, 16
  call malloc
  test rax,rax
  jz StackPush_end
  pop rsi
  pop rdi
  mov rdx, [rdi]
  mov [rax], rdx
  mov [rax+8], rsi
  mov [rdi], rax
  ret
StackPush_end:
  add rsp, 16
  ret

; input
;   stack
; output
;   value or 0 if empty
StackPop:
  mov rsi, rdi
  mov rdi, [rdi]
  test rdi, rdi
  jz StackPop_end
  mov rax, [rdi]
  mov [rsi], rax
  mov rax, [rdi+8]
  push rax
  call free
  pop rax
  ret
StackPop_end:
  xor rax, rax
  ret
  nop;e

; input
;   stack
; output
;   value or 0 if empty
StackFirst:
  mov rax, [rdi]
  test rax, rax
  jz StackFirst_end
  mov rsi, [rax]
  mov [rdi+8], rsi
  mov rax, [rax+8]
StackFirst_end:
  ret

; input
;   stack
; output
;   value or 0 if end
StackNext:
  mov rsi, [rdi+8]
  test rsi, rsi
  jz StackNext_end
  mov rax, [rsi]
  mov [rdi+8], rax
  mov rax, [rsi+8]
  ret
StackNext_end:
  xor rax, rax
  ret

Here is a driver.

[extern puts]
[extern malloc]
[extern free]

[SECTION .data]

arguments:
  db "Incorrect arguments.",10,"Expected: stackme <string1> <string2> ...",0

[SECTION .text]
BITS 64
global main

wrong_arguments:
  mov rdi, arguments
  call puts
  jmp main_end

main:
  cmp rdi, 1
  jle wrong_arguments

  lea r12, [rsi+8]
  lea r13, [rdi-1]

  call StackCreate
  test rax, rax
  jz main_end
  mov r14, rax

pushing_loop:
  test r13, r13
  jz pushing_done
  mov rdi, r14
  mov rsi, [r12]
  call StackPush
  add r12, 8
  dec r13
  jmp pushing_loop
pushing_done:

  mov rdi, r14
  call StackFirst
print_loop:
  test rax, rax
  jz print_done
  mov rdi, rax
  call puts
  mov rdi, r14
  call StackNext
  jmp print_loop
print_done:

stack_delete:
  mov rdi, r14
  call StackPop
  test rax, rax
  jnz stack_delete
stack_delete_done:
  mov rdi, r14
  call StackDestroy

main_end:
  xor eax, eax
  ret

Assembling/Linking

nasm -f elf64 -l stackme.lst stackme.asm
gcc -o stackme stackme.o