I was running the trace_event benchmark and noticed that the times
to record a trace_event was all over the place. I looked at the assembly
of the ring_buffer_lock_reserver() and saw this:

 <ring_buffer_lock_reserve>:
       31 c0                   xor    %eax,%eax
       48 83 3d 76 47 bd 00    cmpq   $0x1,0xbd4776(%rip)        # ffffffff81d10d60 <ring_buffer_flags>
       01
       55                      push   %rbp
       48 89 e5                mov    %rsp,%rbp
       75 1d                   jne    ffffffff8113c60d <ring_buffer_lock_reserve+0x2d>
       65 ff 05 69 e3 ec 7e    incl   %gs:0x7eece369(%rip)        # a960 <__preempt_count>
       8b 47 08                mov    0x8(%rdi),%eax
       85 c0                   test   %eax,%eax
 +---- 74 12                   je     ffffffff8113c610 <ring_buffer_lock_reserve+0x30>
 |     65 ff 0d 5b e3 ec 7e    decl   %gs:0x7eece35b(%rip)        # a960 <__preempt_count>
 |     0f 84 85 00 00 00       je     ffffffff8113c690 <ring_buffer_lock_reserve+0xb0>
 |     31 c0                   xor    %eax,%eax
 |     5d                      pop    %rbp
 |     c3                      retq
 |     90                      nop
 +---> 65 44 8b 05 48 e3 ec    mov    %gs:0x7eece348(%rip),%r8d        # a960 <__preempt_count>
       7e
       41 81 e0 ff ff ff 7f    and    $0x7fffffff,%r8d
       b0 08                   mov    $0x8,%al
       65 8b 0d 58 36 ed 7e    mov    %gs:0x7eed3658(%rip),%ecx        # fc80 <current_context>
       41 f7 c0 00 ff 1f 00    test   $0x1fff00,%r8d
       74 1e                   je     ffffffff8113c64f <ring_buffer_lock_reserve+0x6f>
       41 f7 c0 00 00 10 00    test   $0x100000,%r8d
       b0 01                   mov    $0x1,%al
       75 13                   jne    ffffffff8113c64f <ring_buffer_lock_reserve+0x6f>
       41 81 e0 00 00 0f 00    and    $0xf0000,%r8d
       49 83 f8 01             cmp    $0x1,%r8
       19 c0                   sbb    %eax,%eax
       83 e0 02                and    $0x2,%eax
       83 c0 02                add    $0x2,%eax
       85 c8                   test   %ecx,%eax
       75 ab                   jne    ffffffff8113c5fe <ring_buffer_lock_reserve+0x1e>
       09 c8                   or     %ecx,%eax
       65 89 05 24 36 ed 7e    mov    %eax,%gs:0x7eed3624(%rip)        # fc80 <current_context>

The arrow is the fast path.

After adding the unlikely's, the fast path looks a bit better:

 <ring_buffer_lock_reserve>:
       31 c0                   xor    %eax,%eax
       48 83 3d 76 47 bd 00    cmpq   $0x1,0xbd4776(%rip)        # ffffffff81d10d60 <ring_buffer_flags>
       01
       55                      push   %rbp
       48 89 e5                mov    %rsp,%rbp
       75 7b                   jne    ffffffff8113c66b <ring_buffer_lock_reserve+0x8b>
       65 ff 05 69 e3 ec 7e    incl   %gs:0x7eece369(%rip)        # a960 <__preempt_count>
       8b 47 08                mov    0x8(%rdi),%eax
       85 c0                   test   %eax,%eax
       0f 85 9f 00 00 00       jne    ffffffff8113c6a1 <ring_buffer_lock_reserve+0xc1>
       65 8b 0d 57 e3 ec 7e    mov    %gs:0x7eece357(%rip),%ecx        # a960 <__preempt_count>
       81 e1 ff ff ff 7f       and    $0x7fffffff,%ecx
       b0 08                   mov    $0x8,%al
       65 8b 15 68 36 ed 7e    mov    %gs:0x7eed3668(%rip),%edx        # fc80 <current_context>
       f7 c1 00 ff 1f 00       test   $0x1fff00,%ecx
       75 50                   jne    ffffffff8113c670 <ring_buffer_lock_reserve+0x90>
       85 d0                   test   %edx,%eax
       75 7d                   jne    ffffffff8113c6a1 <ring_buffer_lock_reserve+0xc1>
       09 d0                   or     %edx,%eax
       65 89 05 53 36 ed 7e    mov    %eax,%gs:0x7eed3653(%rip)        # fc80 <current_context>
       65 8b 05 fc da ec 7e    mov    %gs:0x7eecdafc(%rip),%eax        # a130 <cpu_number>
       89 c2                   mov    %eax,%edx

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>