All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Daniel Bristot de Oliveira <bristot@redhat.com>,
	LKML <linux-kernel@vger.kernel.org>, X86 ML <x86@kernel.org>,
	Nadav Amit <nadav.amit@gmail.com>,
	Andy Lutomirski <luto@kernel.org>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Song Liu <songliubraving@fb.com>,
	Masami Hiramatsu <mhiramat@kernel.org>
Subject: Re: [PATCH 3/3] x86/ftrace: Use text_poke()
Date: Tue, 22 Oct 2019 19:21:32 -0400	[thread overview]
Message-ID: <20191022192132.22cc15b5@gandalf.local.home> (raw)
In-Reply-To: <7364B113-DD65-423D-BED3-FF90C4DF8334@amacapital.net>

On Tue, 22 Oct 2019 15:45:26 -0700
Andy Lutomirski <luto@amacapital.net> wrote:

> >> On Oct 22, 2019, at 2:58 PM, Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote:
> >> 
> >> On Tue, Oct 22, 2019 at 05:04:30PM -0400, Steven Rostedt wrote:
> >> I gave a solution for this. And that is to add another flag to allow
> >> for just the minimum to change the ip. And we can even add another flag
> >> to allow for changing the stack if needed (to emulate a call with the
> >> same parameters).  
> > 
> > your solution is to reduce the overhead.
> > my solution is to remove it competely. See the difference?
> >   
> >> By doing this work, live kernel patching will also benefit. Because it
> >> is also dealing with the unnecessary overhead of saving regs.
> >> And we could possibly even have kprobes benefit from this if a kprobe
> >> doesn't need full regs.  
> > 
> > Neither of two statements are true. The per-function generated trampoline
> > I'm talking about is bpf specific. For a function with two arguments it's just:
> > push rbp 
> > mov rbp, rsp
> > push rdi
> > push rsi
> > lea  rdi,[rbp-0x10]
> > call jited_bpf_prog
> > pop rsi
> > pop rdi
> > leave
> > ret  
> 
> Why are you saving rsi?  You said upthread that you’re saving the
> args, but rsi is already available in rsi.

The above is for two parameters, and is being called before the
function with those two parameters. The jited_bpf_prog will be called
with those two parameters as well, but it may also clobber them. Then
we need to restore those two parameters before calling the original
function.

> 
> Just how custom is this bpf program?  It seems to clobber no regs
> (except args), and it doesn’t return anything. Is it entirely
> specific to the probed function?  If so, why not just call it
> directly?

It's injecting the jited_bpf_prog to be called when the probed function
is called, with the same parameters as the probed function.

my_probed_function
  call trampoline


trampoline
  save parameters
  call jited_bpf_prog (with same parameters)
  restore paremeters
  ret

Jumps back to the my_probed_function, where my_probed_function is
clueless it was just interrupted.

No need to save any clobbered registers but the parameters, as the
jited_bpf_prog needs to save any registers that it clobbers just like
the my_probed_function saves its.

-- Steve

  reply	other threads:[~2019-10-22 23:21 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-27 18:06 [PATCH 0/3] Rewrite x86/ftrace to use text_poke() Peter Zijlstra
2019-08-27 18:06 ` [PATCH 1/3] x86/alternatives: Teach text_poke_bp() to emulate instructions Peter Zijlstra
2019-10-03  5:00   ` Masami Hiramatsu
2019-10-03  8:27     ` Peter Zijlstra
2019-10-03 11:01       ` Peter Zijlstra
2019-10-03 12:32         ` Peter Zijlstra
2019-10-04 13:45         ` Masami Hiramatsu
2019-10-07  8:05           ` Peter Zijlstra
2019-10-09 13:07           ` x86/kprobes bug? (was: [PATCH 1/3] x86/alternatives: Teach text_poke_bp() to emulate instructions) Peter Zijlstra
2019-10-09 13:26             ` Peter Zijlstra
2019-10-09 13:28               ` Peter Zijlstra
2019-10-09 14:26             ` Mathieu Desnoyers
2019-10-17 19:59               ` Peter Zijlstra
2019-10-03 13:05       ` [PATCH 1/3] x86/alternatives: Teach text_poke_bp() to emulate instructions Peter Zijlstra
2019-08-27 18:06 ` [PATCH 2/3] x86/alternatives,jump_label: Provide better text_poke() batching interface Peter Zijlstra
2019-10-02 16:34   ` Daniel Bristot de Oliveira
2019-10-03  5:50   ` Masami Hiramatsu
2019-08-27 18:06 ` [PATCH 3/3] x86/ftrace: Use text_poke() Peter Zijlstra
2019-10-02 16:35   ` Daniel Bristot de Oliveira
2019-10-02 18:21     ` Peter Zijlstra
2019-10-03 22:10       ` Steven Rostedt
2019-10-04  8:10         ` Daniel Bristot de Oliveira
2019-10-04 13:40           ` Steven Rostedt
2019-10-04 14:44             ` Daniel Bristot de Oliveira
2019-10-04 15:13               ` Steven Rostedt
2019-10-07  8:08           ` Peter Zijlstra
2019-10-11  7:01           ` Peter Zijlstra
2019-10-11  7:37             ` Daniel Bristot de Oliveira
2019-10-11 10:57               ` Peter Zijlstra
2019-10-11 13:11               ` Steven Rostedt
2019-10-04 11:22         ` Peter Zijlstra
2019-10-04 13:42           ` Steven Rostedt
2019-10-22  0:36             ` Alexei Starovoitov
2019-10-22  0:43               ` Steven Rostedt
2019-10-22  3:10                 ` Alexei Starovoitov
2019-10-22  3:16                   ` Steven Rostedt
2019-10-22  3:19                     ` Steven Rostedt
2019-10-22  4:05                       ` Alexei Starovoitov
2019-10-22 11:19                         ` Steven Rostedt
2019-10-22 13:44                           ` Steven Rostedt
2019-10-22 17:50                             ` Alexei Starovoitov
2019-10-22 18:10                               ` Steven Rostedt
2019-10-22 20:46                                 ` Alexei Starovoitov
2019-10-22 21:04                                   ` Steven Rostedt
2019-10-22 21:58                                     ` Alexei Starovoitov
2019-10-22 22:17                                       ` Steven Rostedt
2019-10-23  2:02                                         ` Steven Rostedt
2019-10-22 22:45                                       ` Andy Lutomirski
2019-10-22 23:21                                         ` Steven Rostedt [this message]
2019-10-22 23:49                                         ` Alexei Starovoitov
2019-10-23  4:20                                           ` Andy Lutomirski
2019-10-23  9:02                                             ` Peter Zijlstra
2019-10-23 16:23                                       ` Steven Rostedt
2019-10-23 17:42                                         ` Steven Rostedt
2019-10-23 19:34                                         ` Alexei Starovoitov
2019-10-23 20:08                                           ` Steven Rostedt
2019-10-23 22:36                                             ` Alexei Starovoitov
2019-10-22  3:55                     ` Alexei Starovoitov
2019-10-03  5:52     ` Masami Hiramatsu
2019-08-28  7:22 ` [PATCH 0/3] Rewrite x86/ftrace to use text_poke() Song Liu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191022192132.22cc15b5@gandalf.local.home \
    --to=rostedt@goodmis.org \
    --cc=alexei.starovoitov@gmail.com \
    --cc=bristot@redhat.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=luto@kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=nadav.amit@gmail.com \
    --cc=peterz@infradead.org \
    --cc=songliubraving@fb.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.