Re: [RFC][PATCH][kprobe] enabling booster on the preemptible kernel, take 2

["bibo,mao" <bibo_mao at linux dot intel dot com>]

Masami Hiramatsu wrote:
> Hi bibo,
>
> Thank you for your review!
>
> bibo,mao wrote:
> > This patch will boost kprobe on preemptible kernel, I think
> > it is deserved to waster some memory for better performance
> > by deferring memory free after freeze_processes.
>
> I think it doesn't waste memory so much, because it tries
> to reuse garbage memories before the kernel allocates an
> additional page.
>
> [...]
> > > +static int __kprobes collect_garbage_slots(void)
> > > +{
> > > +       struct kprobe_insn_page *kip;
> > > +       struct hlist_node *pos, *next;
> > > +       int ret = -1;
> > > +
> > > +#if defined(CONFIG_PREEMPT) && defined(CONFIG_PM)
> > > +       /* Ensure no-one is preepmted on the garbages */
> > > +       if (freeze_processes() != 0)
> > I do not know whether there exists non-freezeable and preemptive kernel
> > thread, if there exist then this thread will not be frozen.
>
> In that case, freeze_processes() returns the positive value which
> means how many processes are not frozen. If freeze_processes()
> returns non-zero, this function aborts the garbage collection.
But from the code, return value of freeze_processes() represents how many
processes can be frozen but are not frozen. I grep the kernel code, there
still exists many processes which flag is PF_NOFREEZE.
I think if current probed thread is PF_NOFREEZE, then kprobe_handler need 
skip the bootser.

thanks
bibo,mao