LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Josh Poimboeuf <jpoimboe@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Kairui Song <kasong@redhat.com>, Alexei Starovoitov <ast@fb.com>,
	Song Liu <songliubraving@fb.com>,
	lkml <linux-kernel@vger.kernel.org>,
	Kernel Team <Kernel-team@fb.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	"bpf@vger.kernel.org" <bpf@vger.kernel.org>,
	Steven Rostedt <rostedt@goodmis.org>
Subject: Re: Getting empty callchain from perf_callchain_kernel()
Date: Wed, 12 Jun 2019 09:50:08 -0500	[thread overview]
Message-ID: <20190612145008.3l5iguuwk2termi4@treble> (raw)
In-Reply-To: <20190612085423.GE3436@hirez.programming.kicks-ass.net>

On Wed, Jun 12, 2019 at 10:54:23AM +0200, Peter Zijlstra wrote:
> On Tue, Jun 11, 2019 at 10:05:01PM -0500, Josh Poimboeuf wrote:
> > On Fri, May 24, 2019 at 10:53:19AM +0200, Peter Zijlstra wrote:
> > > > For ORC, I'm thinking we may be able to just require that all generated
> > > > code (BPF and others) always use frame pointers.  Then when ORC doesn't
> > > > recognize a code address, it could try using the frame pointer as a
> > > > fallback.
> > > 
> > > Yes, this seems like a sensible approach. We'd also have to audit the
> > > ftrace and kprobe trampolines, IIRC they only do framepointer setup for
> > > CONFIG_FRAME_POINTER currently, which should be easy to fix (after the
> > > patches I have to fix the FP generation in the first place:
> > > 
> > >   https://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git/log/?h=x86/wip
> > 
> > Right now, ftrace has a special hook in the ORC unwinder
> > (orc_ftrace_find).  It would be great if we could get rid of that in
> > favor of the "always use frame pointers" approach.  I'll hold off on
> > doing the kpatch/kprobe trampoline conversions in my patches since it
> > would conflict with yours.
> > 
> > Though, hm, because of pt_regs I guess ORC would need to be able to
> > decode an encoded frame pointer?  I was hoping we could leave those
> > encoded frame pointers behind in CONFIG_FRAME_POINTER-land forever...
> 
> Ah, I see.. could a similar approach work for the kprobe trampolines
> perhaps?

If you mean requiring that kprobes trampolines always use frame
pointers, I think it should work.

> > Here are my latest BPF unwinder patches in case anybody wants a sneak
> > peek:
> > 
> >   https://git.kernel.org/pub/scm/linux/kernel/git/jpoimboe/linux.git/log/?h=bpf-orc-fix
> 
> On a quick read-through, that looks good to me. A minor nit:
> 
> 			/* mov dst_reg, %r11 */
> 			EMIT_mov(dst_reg, AUX_REG);
> 
> The disparity between %r11 and AUX_REG is jarring. I understand the
> whole bpf register mapping thing, but it is just weird when reading
> this.

True, but there are several cases where the r11 is hard-coded in the
instruction encoding itself, like:

			/* mov imm32, %r11 */
			EMIT3_off32(0x49, 0xC7, 0xC3, imm32);

If the code were more decoupled, like if it had helpers where you could
always just pass AUX_REG, and the code never had to know what the value
of AUX_REG is, then using "AUX_REG" in the comments would make sense.

But since there are inconsistencies, with hard-coded register mapping
knowledge in many places, I find it easier to follow what's going on
when the specific register name is always shown in the comments.

> Other than that, the same note as before, the 32bit JIT still seems
> buggered, but I'm not sure you (or anybody else) cares enough about that
> to fix it though. It seems to use ebp as its own frame pointer, which
> completely defeats an unwinder.

I'm still trying to decide if I care about 32-bit.  It does indeed use
ebp everywhere.  But I'm not sure if I want to poke the beehive...  Also
factoring into the equation is the fact that I'll be on PTO next week
:-)  If I have time in the next couple days then I may take a look.

-- 
Josh

  reply	other threads:[~2019-06-12 14:50 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-16 23:51 Song Liu
2019-05-17  7:46 ` Peter Zijlstra
2019-05-17  8:10   ` Peter Zijlstra
2019-05-17  8:15     ` Kairui Song
2019-05-17  8:32       ` Kairui Song
2019-05-17 16:22         ` Song Liu
2019-05-17  9:10       ` Peter Zijlstra
2019-05-17 18:40         ` Song Liu
2019-05-17 21:06           ` Alexei Starovoitov
2019-05-17 21:48             ` Song Liu
2019-05-19 18:07               ` Kairui Song
2019-05-20 17:22                 ` Song Liu
2019-05-22 13:51                   ` Peter Zijlstra
2019-05-19 18:06         ` Kairui Song
2019-05-20 17:16           ` Song Liu
2019-05-20 17:19           ` Song Liu
2019-05-22 14:02           ` Peter Zijlstra
2019-05-22 14:49             ` Alexei Starovoitov
2019-05-22 17:45               ` Josh Poimboeuf
2019-05-22 23:46                 ` Josh Poimboeuf
2019-05-23  6:48                   ` Kairui Song
2019-05-23  8:27                     ` Song Liu
2019-05-23  9:11                       ` Kairui Song
2019-05-23 13:32                     ` Josh Poimboeuf
2019-05-23 14:50                       ` Kairui Song
2019-05-23 15:24                         ` Josh Poimboeuf
2019-05-23 16:41                           ` Kairui Song
2019-05-23 17:27                             ` Josh Poimboeuf
2019-05-24  2:20                               ` Kairui Song
2019-05-24 23:23                                 ` Josh Poimboeuf
2019-05-27 11:57                                   ` Kairui Song
2019-06-06 16:04                                     ` Song Liu
2019-06-06 23:58                                       ` Josh Poimboeuf
2019-06-11 21:03                                       ` Josh Poimboeuf
2019-05-24  8:53                           ` Peter Zijlstra
2019-05-24 13:05                             ` Josh Poimboeuf
2019-06-12  3:05                             ` Josh Poimboeuf
2019-06-12  8:54                               ` Peter Zijlstra
2019-06-12 14:50                                 ` Josh Poimboeuf [this message]
2019-06-13 20:26                                   ` Josh Poimboeuf
2019-06-12 13:10                               ` Steven Rostedt
2019-06-12 14:26                                 ` Josh Poimboeuf
2019-05-22 18:07       ` Josh Poimboeuf
2019-05-22 21:55         ` Alexei Starovoitov
2019-05-17 16:32     ` 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=20190612145008.3l5iguuwk2termi4@treble \
    --to=jpoimboe@redhat.com \
    --cc=Kernel-team@fb.com \
    --cc=ast@fb.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=kasong@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=songliubraving@fb.com \
    --subject='Re: Getting empty callchain from perf_callchain_kernel()' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).