Why does the assembly after my sys_clone call affect the cloned process?

Question

I'm attempting to write a compiler in x86 Intel noprefix assembly, but I've come across an issue while implementing threads. If I run the following, the new thread runs correctly, albeit with a seg_fault.

    call create_thread_stack
    push rax                            # Push f onto new stack, followed by thread_wrapper
    pop rsi                             # New thread should start in thread_wrapper when cloned
    sub rsi, 8
    lea rdi, [rip + f]
    push rdi
    pop [rsi]
    sub rsi, 8
    lea rdi, [rip + thread_wrapper]
    push rdi
    pop [rsi]
    mov rdi, -2147479808    # CLONE_VM | CLONE_FS | CLONE_FILES | CLONE_SIGHAND | CLONE_IO
    mov rax, 56             # Sys_clone
    syscall

But nothing runs in the new thread if I follow the above with this:

    sub rsp, 4
    mov dword ptr [rsp], eax
    mov eax, dword ptr [rsp]
    add rsp, 4
    mov dword ptr [rbp + -4], eax
    mov rax, 0
    mov rsp, rbp
    pop rbp
    ret

I'm unsure about what I can do to fix this, and would really appreciate any help. I'm not that familiar with X86, so I'm almost certainly missing something. I've put the file contents below here. Thank you!

.intel_syntax noprefix 
.globl main 
.section .rodata 
.text
f:                        # prints 1 and returns 0
    push rbp
    mov rbp, rsp
    mov eax, 1
    sub rsp, 4
    mov dword ptr [rsp], eax
    mov edi, dword ptr [rsp]
    add rsp, 4
    movsx rdi, edi
    call _printi
    mov eax, 0
    sub rsp, 4
    mov dword ptr [rsp], eax
    mov eax, dword ptr [rsp]
    add rsp, 4
    movsx rax, eax
    mov rsp, rbp
    pop rbp
    ret
main: 
    push rbp
    mov rbp, rsp
    sub rsp, 4
    mov dword ptr [rsp], eax
    call create_thread_stack
    push rax                            # Push f onto new stack, followed by thread_wrapper
    pop rsi                             # New thread should start in thread_wrapper when cloned
    sub rsi, 8
    lea rdi, [rip + f]
    push rdi
    pop [rsi]
    sub rsi, 8
    lea rdi, [rip + thread_wrapper]
    push rdi
    pop [rsi]
    mov rdi, -2147479808    # CLONE_VM | CLONE_FS | CLONE_FILES | CLONE_SIGHAND | CLONE_IO
    mov rax, 56             # Sys_clone
    syscall
    sub rsp, 4
    mov dword ptr [rsp], eax
    mov eax, dword ptr [rsp]
    add rsp, 4
    mov dword ptr [rbp + -4], eax
    mov rax, 0
    mov rsp, rbp
    pop rbp
    ret
.section .rodata
    .int 2
.L._printi_str0: 
    .asciz "%d"
.text
_printi: 
    push rbp
    mov rbp, rsp
    and rsp, -16
    mov esi, edi
    lea rdi, [rip + .L._printi_str0]
    mov al, 0
    call printf@plt
    mov rdi, 0
    call fflush@plt
    mov rsp, rbp
    pop rbp
    ret
create_thread_stack:           # Creates stack for new thread
    mov rdi, 0
    mov rsi, 4194304
    mov rdx, 3
    mov r10, 290
    mov r9, 0
    mov r8, -1
    mov rax, 9
    syscall
    lea rax, [rax + 4194304]
    ret
thread_exit: 
    mov rdi, 0
    mov rax, 60
    syscall
thread_wrapper:                # Runs label below thread_wrapper on the new stack
    pop rax
    call rax
    call thread_exit