linux-kernel - Re: [PATCH bpf-next 09/13] selftests/bpf: Use 5-byte nop for x86 usdt probes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <Z1_ll7ArngBWpx4N@krava>
Date: Mon, 16 Dec 2024 09:32:23 +0100
From: Jiri Olsa <olsajiri@...il.com>
To: Andrii Nakryiko <andrii.nakryiko@...il.com>
Cc: Oleg Nesterov <oleg@...hat.com>, Peter Zijlstra <peterz@...radead.org>,
	Andrii Nakryiko <andrii@...nel.org>, bpf@...r.kernel.org,
	Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
	John Fastabend <john.fastabend@...il.com>,
	Hao Luo <haoluo@...gle.com>, Steven Rostedt <rostedt@...dmis.org>,
	Masami Hiramatsu <mhiramat@...nel.org>,
	Alan Maguire <alan.maguire@...cle.com>,
	linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org
Subject: Re: [PATCH bpf-next 09/13] selftests/bpf: Use 5-byte nop for x86
 usdt probes

On Fri, Dec 13, 2024 at 01:58:33PM -0800, Andrii Nakryiko wrote:
> On Wed, Dec 11, 2024 at 5:35 AM Jiri Olsa <jolsa@...nel.org> wrote:
> >
> > Using 5-byte nop for x86 usdt probes so we can switch
> > to optimized uprobe them.
> >
> > Signed-off-by: Jiri Olsa <jolsa@...nel.org>
> > ---
> >  tools/testing/selftests/bpf/sdt.h | 9 ++++++++-
> >  1 file changed, 8 insertions(+), 1 deletion(-)
> >
> 
> This change will make it impossible to run latest selftests on older
> kernels. Let's do what we did with -DENABLE_ATOMICS_TESTS and allow to
> disable this through Makefile, ok?

ok, I wanted to start addressing this after this version

so the problem is using this macro with nop5 in application running
on older kernels that do not have nop5 emulation and uprobe syscall
optimization, because uprobe/usdt on top of nop5 (single-stepped)
will be slower than on top of current nop1 (emulated)

AFAICS selftests should still work, just bit slower due to nop5 emulation

one part of the solution would be to backport [1] to stable kernels
which is an easy fix (even though it needs changes now)

if that's not enough we'd need to come up with that nop1/nop5 macro
solution, where tooling (libbpf with extra data in usdt note) would
install uprobe on top of nop1 on older kernels and on top of nop5 on
new ones.. but that'd need more work of course

jirka


[1] patch#7 - uprobes/x86: Add support to emulate nop5 instruction


> 
> 
> > diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h
> > index ca0162b4dc57..7ac9291f45f1 100644
> > --- a/tools/testing/selftests/bpf/sdt.h
> > +++ b/tools/testing/selftests/bpf/sdt.h
> > @@ -234,6 +234,13 @@ __extension__ extern unsigned long long __sdt_unsp;
> >  #define _SDT_NOP       nop
> >  #endif
> >
> > +/* Use 5 byte nop for x86_64 to allow optimizing uprobes. */
> > +#if defined(__x86_64__)
> > +# define _SDT_DEF_NOP _SDT_ASM_5(990:  .byte 0x0f, 0x1f, 0x44, 0x00, 0x00)
> > +#else
> > +# define _SDT_DEF_NOP _SDT_ASM_1(990:  _SDT_NOP)
> > +#endif
> > +
> >  #define _SDT_NOTE_NAME "stapsdt"
> >  #define _SDT_NOTE_TYPE 3
> >
> > @@ -286,7 +293,7 @@ __extension__ extern unsigned long long __sdt_unsp;
> >
> >  #define _SDT_ASM_BODY(provider, name, pack_args, args, ...)                  \
> >    _SDT_DEF_MACROS                                                            \
> > -  _SDT_ASM_1(990:      _SDT_NOP)                                             \
> > +  _SDT_DEF_NOP                                                               \
> >    _SDT_ASM_3(          .pushsection .note.stapsdt,_SDT_ASM_AUTOGROUP,"note") \
> >    _SDT_ASM_1(          .balign 4)                                            \
> >    _SDT_ASM_3(          .4byte 992f-991f, 994f-993f, _SDT_NOTE_TYPE)          \
> > --
> > 2.47.0
> >