[Bug target/110184] [x86] Missed optimisation: atomic operations should use PF, ZF and SF

["securesneakers at gmail dot com" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110184

Ivan Bodrov <securesneakers at gmail dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |securesneakers at gmail dot com

--- Comment #2 from Ivan Bodrov <securesneakers at gmail dot com> ---
This seem to have been implemented, at least for __atomic_fetch_and, but the
optimization is very fragile and fails when "lock and" value and mask used
during checking come from separate literals:

    $ cat fragile-fetch-and.c
    void slowpath(unsigned long *p);
    void func_bad(unsigned long *p)
    {
        if (__atomic_fetch_and(p, ~1UL, __ATOMIC_RELAXED) & ~1UL)
            slowpath(p);
    }
    void func_good(unsigned long *p)
    {
        unsigned long mask = ~1UL;
        if (__atomic_fetch_and(p, mask, __ATOMIC_RELAXED) & mask)
            slowpath(p);
    }

Compiling this we can see that even though functions are the same, the first
one wasn't optimized:

    $ gcc --version
    gcc (GCC) 13.2.1 20230801
    Copyright (C) 2023 Free Software Foundation, Inc.
    This is free software; see the source for copying conditions.  There is NO
    warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

    $ uname -s -m
    Linux x86_64
    $ gcc -O2 -c fragile-fetch-and.c 
    $ objdump -d fragile-fetch-and.o

    fragile-fetch-and.o:     file format elf64-x86-64


    Disassembly of section .text:

    0000000000000000 <func_bad>:
       0:   48 8b 07                mov    (%rdi),%rax
       3:   48 89 c1                mov    %rax,%rcx
       6:   48 89 c2                mov    %rax,%rdx
       9:   48 83 e1 fe             and    $0xfffffffffffffffe,%rcx
       d:   f0 48 0f b1 0f          lock cmpxchg %rcx,(%rdi)
      12:   75 ef                   jne    3 <func_bad+0x3>
      14:   48 83 fa 01             cmp    $0x1,%rdx
      18:   77 06                   ja     20 <func_bad+0x20>
      1a:   c3                      ret
      1b:   0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
      20:   e9 00 00 00 00          jmp    25 <func_bad+0x25>
      25:   66 66 2e 0f 1f 84 00    data16 cs nopw 0x0(%rax,%rax,1)
      2c:   00 00 00 00 

    0000000000000030 <func_good>:
      30:   f0 48 83 27 fe          lock andq $0xfffffffffffffffe,(%rdi)
      35:   75 09                   jne    40 <func_good+0x10>
      37:   c3                      ret
      38:   0f 1f 84 00 00 00 00    nopl   0x0(%rax,%rax,1)
      3f:   00 
      40:   e9 00 00 00 00          jmp    45 <func_good+0x15>