Re: [PATCH] tracing: Cleanup the convoluted softirq tracepoints

["H. Peter Anvin" <hpa@zytor.com>]

On 10/19/2010 03:23 PM, Steven Rostedt wrote:
> On Tue, 2010-10-19 at 14:48 -0700, H. Peter Anvin wrote:
>> On 10/19/2010 02:23 PM, Steven Rostedt wrote:
>>>
>>> But it seemed that gcc for you inlined the code in the wrong spot.
>>> Perhaps it's not a good idea to have the something like h - softirq_vec
>>> in the parameter of the tracepoint. Not saying that your change is not
>>> worth it. It is, because h - softirq_vec is used by others now too.
>>>
>>
>> OK, first of all, there are some serious WTFs here:
>>
>> # define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
>>
>> A jump instruction is one of the worst possible NOPs.  Why are we doing
>> this?
> 
> Good question. Safety?  Jason?
> 
> This is the initial jumps and are converted on boot up to a better nop.
> 

But it makes absolutely no sense to insert an instruction that
suboptimal and then convert it.  Start out with a reasonable,
universally acceptable, instruction, e.g. LEA on 32 bits and NOPL on 64
bits.

>>
>> The second thing that I found when implementing static_cpu_has() was
>> that it is actually better to encapsulate the asm goto in a small inline
>> which returns bool (true/false) -- gcc will happily optimize out the
>> variable and only see it as a flow of control thing.  I would be very
>> curious if that wouldn't make gcc generate better code in cases like that.
>>
>> gcc 4.5.0 has a bug in that there must be a flowthrough case in the asm
>> goto (you can't have it unconditionally branch one way or the other), so
>> that should be the likely case and accordingly it should be annotated
>> likely() so that gcc doesn't reorder.  I suspect in the end one ends up
>> with code like this:
>>
>> static __always_inline __pure bool __switch_point(...)
>> {
>> 	asm goto("1: " JUMP_LABEL_INITIAL_NOP
>> 		 /* ... patching stuff */
>> 		: : : : t_jump);
>> 	return false;
>> t_jump:
>> 	return true;
>> }
>>
>> #define SWITCH_POINT(x) unlikely(__switch_point(x))
>>
>> I *suspect* this will resolve the need for hot/cold labels just fine.
> 
> Interesting, we could try this.
> 

It of course also have the nice property that it syntactically looks
exactly like any other C conditional.

	-hpa