Re: [LSF/MM/BPF TOPIC] faster uprobes

[Oleg Nesterov <oleg@redhat.com>]

On 03/11, Jiri Olsa wrote:
>
> On Mon, Mar 11, 2024 at 04:06:59PM +0100, Oleg Nesterov wrote:
> > I forgot everything about the low-level x86_64 code, but...
> >
> > On 03/11, Jiri Olsa wrote:
> > >
> > >  #ifdef CONFIG_X86_64
> > > +
> > > +asm (
> > > +       ".pushsection .rodata\n"
> > > +       ".global uretprobe_syscall_entry\n"
> > > +       "uretprobe_syscall_entry:\n"
> > > +       "push %rax\n"
> > > +       "mov $462, %rax\n"
> > > +       "syscall\n"
> >
> > Hmm... I think you need to save/restore more registers clobbered by
> > syscall/entry_SYSCALL_64 ?
>
> hum, so the call happens on the function call return, so I thought
> we should just preserve callee saved registers which seems to be
> taken care of by the entry_SYSCALL_64 path..

Yes, but we do not know if the (ret)probed function obeys the C-calling
convention, perhaps it is low level asm code or not a C function.

> I will double check

but I won't insist if you think we do not care.

> > > +
> > > +	regs->ax = ax;
> >
> > probably not strictly needed, we are going to return ax...
>
> it needs to be there for the bpf program to read proper return
> value from regs

OK, I see, thanks.

Oleg.