// The body of kern_ap_stub (kernel.c, "asynchronous preemption"), included once per register width with AP_NAME the
// function's name, AP_VMOV and AP_V the move and the register prefix that save the vector registers, and AP_VZEROUPPER
// the instruction that ends the use of the upper halves (or nothing). No include guard: kernel.c includes it twice.
#ifdef _WIN32
__asm__(".text\n"
        ".globl " AP_NAME "\n"
        ".def " AP_NAME "; .scl 2; .type 32; .endef\n"
        ".p2align 4\n"
        AP_NAME ":\n"
        ".seh_proc " AP_NAME "\n"
        "    leaq -8(%rsp), %rsp\n"   // not sub: the flags are still the interrupted code's until pushfq
        ".seh_stackalloc 8\n"
        "    pushfq\n"
        ".seh_stackalloc 8\n"
        "    pushq %rax\n"
        ".seh_pushreg %rax\n"
        "    pushq %rcx\n"
        ".seh_pushreg %rcx\n"
        "    pushq %rdx\n"
        ".seh_pushreg %rdx\n"
        "    pushq %r8\n"
        ".seh_pushreg %r8\n"
        "    pushq %r9\n"
        ".seh_pushreg %r9\n"
        "    pushq %r10\n"
        ".seh_pushreg %r10\n"
        "    pushq %r11\n"
        ".seh_pushreg %r11\n"
        "    pushq %rbp\n"
        ".seh_pushreg %rbp\n"
        "    movq %rsp, %rbp\n"
        ".seh_setframe %rbp, 0\n"
        ".seh_endprologue\n"
        "    andq $-32, %rsp\n"
        "    subq $576, %rsp\n"   // 0: shadow space, 32: MXCSR saved, 36: MXCSR default, 64: YMM0-15 (XMM0-15 without AVX)
        "    " AP_VMOV " " AP_V "0, 64(%rsp)\n"
        "    " AP_VMOV " " AP_V "1, 96(%rsp)\n"
        "    " AP_VMOV " " AP_V "2, 128(%rsp)\n"
        "    " AP_VMOV " " AP_V "3, 160(%rsp)\n"
        "    " AP_VMOV " " AP_V "4, 192(%rsp)\n"
        "    " AP_VMOV " " AP_V "5, 224(%rsp)\n"
        "    " AP_VMOV " " AP_V "6, 256(%rsp)\n"
        "    " AP_VMOV " " AP_V "7, 288(%rsp)\n"
        "    " AP_VMOV " " AP_V "8, 320(%rsp)\n"
        "    " AP_VMOV " " AP_V "9, 352(%rsp)\n"
        "    " AP_VMOV " " AP_V "10, 384(%rsp)\n"
        "    " AP_VMOV " " AP_V "11, 416(%rsp)\n"
        "    " AP_VMOV " " AP_V "12, 448(%rsp)\n"
        "    " AP_VMOV " " AP_V "13, 480(%rsp)\n"
        "    " AP_VMOV " " AP_V "14, 512(%rsp)\n"
        "    " AP_VMOV " " AP_V "15, 544(%rsp)\n"
        "    stmxcsr 32(%rsp)\n"
        "    movl $0x1f80, 36(%rsp)\n"
        "    ldmxcsr 36(%rsp)\n"
        "    cld\n"
        AP_VZEROUPPER
        "    call kern_ap_rip\n"
        "    movq %rax, 72(%rbp)\n"   // the return slot: rbp + 8 pushes + pushfq
        "    call kern_ap_yield\n"
        "    ldmxcsr 32(%rsp)\n"
        "    " AP_VMOV " 64(%rsp), " AP_V "0\n"
        "    " AP_VMOV " 96(%rsp), " AP_V "1\n"
        "    " AP_VMOV " 128(%rsp), " AP_V "2\n"
        "    " AP_VMOV " 160(%rsp), " AP_V "3\n"
        "    " AP_VMOV " 192(%rsp), " AP_V "4\n"
        "    " AP_VMOV " 224(%rsp), " AP_V "5\n"
        "    " AP_VMOV " 256(%rsp), " AP_V "6\n"
        "    " AP_VMOV " 288(%rsp), " AP_V "7\n"
        "    " AP_VMOV " 320(%rsp), " AP_V "8\n"
        "    " AP_VMOV " 352(%rsp), " AP_V "9\n"
        "    " AP_VMOV " 384(%rsp), " AP_V "10\n"
        "    " AP_VMOV " 416(%rsp), " AP_V "11\n"
        "    " AP_VMOV " 448(%rsp), " AP_V "12\n"
        "    " AP_VMOV " 480(%rsp), " AP_V "13\n"
        "    " AP_VMOV " 512(%rsp), " AP_V "14\n"
        "    " AP_VMOV " 544(%rsp), " AP_V "15\n"
        "    movq %rbp, %rsp\n"
        "    popq %rbp\n"
        "    popq %r11\n"
        "    popq %r10\n"
        "    popq %r9\n"
        "    popq %r8\n"
        "    popq %rdx\n"
        "    popq %rcx\n"
        "    popq %rax\n"
        "    popfq\n"
        "    leaq 8(%rsp), %rsp\n"
        "    jmpq *-8(%rsp)\n"
        ".seh_endproc\n");
#else
// The System V version: rsi and rdi are volatile there too, and the interrupted code may keep data in the 128 bytes
// below its stack pointer (the red zone), so the return slot and the saves go below that. Without a red zone in the
// way the slot is at entry - 136; the exit restores rsp to the entry value and jumps through the slot.
__asm__(".text\n"
        ".globl " AP_NAME "\n"
        ".type " AP_NAME ", @function\n"
        ".p2align 4\n"
        AP_NAME ":\n"
        "    .cfi_startproc\n"
        "    leaq -136(%rsp), %rsp\n"   // not sub: the flags are still the interrupted code's until pushfq
        "    pushfq\n"
        "    pushq %rax\n"
        "    pushq %rcx\n"
        "    pushq %rdx\n"
        "    pushq %rsi\n"
        "    pushq %rdi\n"
        "    pushq %r8\n"
        "    pushq %r9\n"
        "    pushq %r10\n"
        "    pushq %r11\n"
        "    pushq %rbp\n"
        "    movq %rsp, %rbp\n"
        "    andq $-32, %rsp\n"
        "    subq $576, %rsp\n"   // 32: MXCSR saved, 36: MXCSR default, 64: YMM0-15 (XMM0-15 without AVX)
        "    " AP_VMOV " " AP_V "0, 64(%rsp)\n"
        "    " AP_VMOV " " AP_V "1, 96(%rsp)\n"
        "    " AP_VMOV " " AP_V "2, 128(%rsp)\n"
        "    " AP_VMOV " " AP_V "3, 160(%rsp)\n"
        "    " AP_VMOV " " AP_V "4, 192(%rsp)\n"
        "    " AP_VMOV " " AP_V "5, 224(%rsp)\n"
        "    " AP_VMOV " " AP_V "6, 256(%rsp)\n"
        "    " AP_VMOV " " AP_V "7, 288(%rsp)\n"
        "    " AP_VMOV " " AP_V "8, 320(%rsp)\n"
        "    " AP_VMOV " " AP_V "9, 352(%rsp)\n"
        "    " AP_VMOV " " AP_V "10, 384(%rsp)\n"
        "    " AP_VMOV " " AP_V "11, 416(%rsp)\n"
        "    " AP_VMOV " " AP_V "12, 448(%rsp)\n"
        "    " AP_VMOV " " AP_V "13, 480(%rsp)\n"
        "    " AP_VMOV " " AP_V "14, 512(%rsp)\n"
        "    " AP_VMOV " " AP_V "15, 544(%rsp)\n"
        "    stmxcsr 32(%rsp)\n"
        "    movl $0x1f80, 36(%rsp)\n"
        "    ldmxcsr 36(%rsp)\n"
        "    cld\n"
        AP_VZEROUPPER
        "    call kern_ap_rip\n"
        "    movq %rax, 88(%rbp)\n"   // the return slot: rbp + 10 pushes + pushfq
        "    call kern_ap_yield\n"
        "    ldmxcsr 32(%rsp)\n"
        "    " AP_VMOV " 64(%rsp), " AP_V "0\n"
        "    " AP_VMOV " 96(%rsp), " AP_V "1\n"
        "    " AP_VMOV " 128(%rsp), " AP_V "2\n"
        "    " AP_VMOV " 160(%rsp), " AP_V "3\n"
        "    " AP_VMOV " 192(%rsp), " AP_V "4\n"
        "    " AP_VMOV " 224(%rsp), " AP_V "5\n"
        "    " AP_VMOV " 256(%rsp), " AP_V "6\n"
        "    " AP_VMOV " 288(%rsp), " AP_V "7\n"
        "    " AP_VMOV " 320(%rsp), " AP_V "8\n"
        "    " AP_VMOV " 352(%rsp), " AP_V "9\n"
        "    " AP_VMOV " 384(%rsp), " AP_V "10\n"
        "    " AP_VMOV " 416(%rsp), " AP_V "11\n"
        "    " AP_VMOV " 448(%rsp), " AP_V "12\n"
        "    " AP_VMOV " 480(%rsp), " AP_V "13\n"
        "    " AP_VMOV " 512(%rsp), " AP_V "14\n"
        "    " AP_VMOV " 544(%rsp), " AP_V "15\n"
        "    movq %rbp, %rsp\n"
        "    popq %rbp\n"
        "    popq %r11\n"
        "    popq %r10\n"
        "    popq %r9\n"
        "    popq %r8\n"
        "    popq %rdi\n"
        "    popq %rsi\n"
        "    popq %rdx\n"
        "    popq %rcx\n"
        "    popq %rax\n"
        "    popfq\n"
        "    leaq 136(%rsp), %rsp\n"
        "    jmpq *-136(%rsp)\n"
        "    .cfi_endproc\n"
        ".size " AP_NAME ", .-" AP_NAME "\n");
#endif