Re: [PATCH] trace: adjust code layout in get_recursion_context

[Jesper Dangaard Brouer <brouer@redhat.com>]

On Tue, 22 Aug 2017 19:00:39 +0200
Jesper Dangaard Brouer <brouer@redhat.com> wrote:

> On Tue, 22 Aug 2017 17:20:25 +0200
> Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > On Tue, Aug 22, 2017 at 05:14:10PM +0200, Peter Zijlstra wrote:  
> > > On Tue, Aug 22, 2017 at 04:40:24PM +0200, Jesper Dangaard Brouer wrote:    
> > > > In an XDP redirect applications using tracepoint xdp:xdp_redirect to
> > > > diagnose TX overrun, I noticed perf_swevent_get_recursion_context()
> > > > was consuming 2% CPU. This was reduced to 1.6% with this simple
> > > > change.    
> > > 
> > > It is also incorrect. What do you suppose it now returns when the NMI
> > > hits a hard IRQ which hit during a Soft IRQ?    
> > 
> > Does this help any? I can imagine the compiler could struggle to CSE
> > preempt_count() seeing how its an asm thing.  
> 
> Nope, it does not help (see assembly below, with perf percentages).
> 
> But I think I can achieve that I want by a simple unlikely(in_nmi()) annotation.

Like:

diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 486fd78eb8d5..e1a7ac7bd686 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -208,7 +208,7 @@ static inline int get_recursion_context(int *recursion)
 {
        int rctx;
 
-       if (in_nmi())
+       if (unlikely(in_nmi()))
                rctx = 3;
        else if (in_irq())
                rctx = 2;

Testing this show I get the expected result. Although, the 2% is
reduced to 1.85% (and not 1.6% as before).  


perf_swevent_get_recursion_context  /proc/kcore
       │
       │    Disassembly of section load0:
       │
       │    ffffffff811465c0 <load0>:
  4.94 │      push   %rbp
  2.56 │      mov    $0x14d20,%rax
 14.81 │      mov    %rsp,%rbp
  3.47 │      add    %gs:0x7eec3b5d(%rip),%rax
  0.91 │      lea    0x34(%rax),%rdx
  1.46 │      mov    %gs:0x7eec5db2(%rip),%eax
  8.04 │      test   $0x100000,%eax
       │    ↓ jne    59
  3.11 │      test   $0xf0000,%eax
       │    ↓ jne    4d
  0.37 │      test   $0xff,%ah
  1.83 │      setne  %cl
  9.87 │      movzbl %cl,%eax
  2.01 │      movzbl %cl,%ecx
  1.65 │      shl    $0x2,%rcx
  4.39 │3c:   add    %rcx,%rdx
 29.62 │      mov    (%rdx),%ecx
  2.93 │      test   %ecx,%ecx
       │    ↓ jne    65
  0.55 │      movl   $0x1,(%rdx)
  2.56 │      pop    %rbp
  4.94 │    ← retq
       │4d:   mov    $0x8,%ecx
       │      mov    $0x2,%eax
       │    ↑ jmp    3c
       │59:   mov    $0xc,%ecx
       │      mov    $0x3,%eax
       │    ↑ jmp    3c
       │65:   mov    $0xffffffff,%eax
       │      pop    %rbp
       │    ← retq



> > ---
> >  kernel/events/internal.h | 7 ++++---
> >  1 file changed, 4 insertions(+), 3 deletions(-)
> > 
> > diff --git a/kernel/events/internal.h b/kernel/events/internal.h
> > index 486fd78eb8d5..e0b5b8fa83a2 100644
> > --- a/kernel/events/internal.h
> > +++ b/kernel/events/internal.h
> > @@ -206,13 +206,14 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs);
> >  
> >  static inline int get_recursion_context(int *recursion)
> >  {
> > +	unsigned int pc = preempt_count();
> >  	int rctx;
> >  
> > -	if (in_nmi())
> > +	if (pc & NMI_MASK)
> >  		rctx = 3;
> > -	else if (in_irq())
> > +	else if (pc & HARDIRQ_MASK)
> >  		rctx = 2;
> > -	else if (in_softirq())
> > +	else if (pc & SOFTIRQ_OFFSET)  
> 
> Hmmm... shouldn't this be SOFTIRQ_MASK?
> 
> >  		rctx = 1;
> >  	else
> >  		rctx = 0;  
> 
> perf_swevent_get_recursion_context  /proc/kcore
>        │
>        │
>        │    Disassembly of section load0:
>        │
>        │    ffffffff811465c0 <load0>:
>  13.32 │      push   %rbp
>   1.43 │      mov    $0x14d20,%rax
>   5.12 │      mov    %rsp,%rbp
>   6.56 │      add    %gs:0x7eec3b5d(%rip),%rax
>   0.72 │      lea    0x34(%rax),%rdx
>   0.31 │      mov    %gs:0x7eec5db2(%rip),%eax
>   2.46 │      mov    %eax,%ecx
>   6.86 │      and    $0x7fffffff,%ecx
>   0.72 │      test   $0x100000,%eax
>        │    ↓ jne    40
>        │      test   $0xf0000,%eax
>   0.41 │    ↓ je     5b
>        │      mov    $0x8,%ecx
>        │      mov    $0x2,%eax
>        │    ↓ jmp    4a
>        │40:   mov    $0xc,%ecx
>        │      mov    $0x3,%eax
>   2.05 │4a:   add    %rcx,%rdx
>  16.60 │      mov    (%rdx),%ecx
>   2.66 │      test   %ecx,%ecx
>        │    ↓ jne    6d
>   1.33 │      movl   $0x1,(%rdx)
>   1.54 │      pop    %rbp
>   4.51 │    ← retq
>   3.89 │5b:   shr    $0x8,%ecx
>   9.53 │      and    $0x1,%ecx
>   0.61 │      movzbl %cl,%eax
>   0.92 │      movzbl %cl,%ecx
>   4.30 │      shl    $0x2,%rcx
>  14.14 │    ↑ jmp    4a
>        │6d:   mov    $0xffffffff,%eax
>        │      pop    %rbp
>        │    ← retq
>        │      xchg   %ax,%ax
> 
> 
> 



-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer