From: Masami Hiramatsu <mhiramat@redhat.com>
To: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>, LKML <linux-kernel@vger.kernel.org>,
Steven Rostedt <rostedt@goodmis.org>
Subject: Re: [GIT PULL] tracing/kprobes: Add dynamic tracepoints + instruction decoder
Date: Thu, 27 Aug 2009 11:00:38 -0400 [thread overview]
Message-ID: <4A969F96.2020107@redhat.com> (raw)
In-Reply-To: <1251340337-5640-1-git-send-email-fweisbec@gmail.com>
Frederic Weisbecker wrote:
> Ingo,
>
> This is the kprobes tracing pile of patches. I've tested it
> successfully by setting some kprobes through debugfs by hand.
>
> It brings no known regressions.
>
> However, the stress test provided by Masami have revealed some
> unstable points. Some symbols are unsafe to probe and raise
> probing recursion.
>
> I've added a tiny patch in the series that helps identifying the
> kprobe that has raised such situation.
> For example it has learned me today that it's unsafe to trace
> ret_from_exception() (obviously: it's on the int 3 handler path).
Thank you, Frederic.
I'm currently fixing those problems on x86-64 (on kvm).
I'll also check it on x86-32, and fix it.
Thanks
> Anyway, we have all the tools to debug that and easily find the
> fragile points to probe. It's then just a matter of investigation
> and stress tests now.
>
> And because the pile of patches becomes big enough, I've thought it
> could be time to do a pull request for -tip for it to have a
> private branch and get fixes over the time.
>
> Tell me if that's a problem and we can delay the pull request until
> we fix the recursive points problems.
>
> Thanks,
> Frederic.
>
> The following changes since commit 35dce1a99d010f3d738af4ce1b9b77302fdfe69c:
> Ingo Molnar (1):
> Merge branch 'tracing/core' of git://git.kernel.org/.../frederic/random-tracing into tracing/core
>
> are available in the git repository at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> tracing/kprobes
>
> Frederic Weisbecker (1):
> tracing/kprobes: Dump the culprit kprobe in case of kprobe recursion
>
> Masami Hiramatsu (17):
> x86: Instruction decoder API
> x86: X86 instruction decoder build-time selftest
> kprobes: Checks probe address is instruction boudary on x86
> kprobes: Cleanup fix_riprel() using insn decoder on x86
> x86: Add pt_regs register and stack access APIs
> tracing: Ftrace dynamic ftrace_event_call support
> tracing: Introduce TRACE_FIELD_ZERO() macro
> tracing: Add kprobe-based event tracer
> tracing: Add kprobe-based event tracer documentation
> tracing: Kprobe-tracer supports more than 6 arguments
> tracing: Generate names for each kprobe event automatically
> tracing: Kprobe tracer assigns new event ids for each event
> tracing: Add kprobes event profiling interface
> x86: Fix x86 instruction decoder selftest to check only .text
> x86: Check awk features before generating inat-tables.c
> tracing/kprobes: Fix format typo in trace_kprobes
> tracing/kprobes: Change trace_arg to probe_arg
>
> Documentation/trace/kprobetrace.txt | 148 ++++
> arch/x86/Kconfig.debug | 9 +
> arch/x86/Makefile | 3 +
> arch/x86/include/asm/inat.h | 188 ++++++
> arch/x86/include/asm/inat_types.h | 29 +
> arch/x86/include/asm/insn.h | 143 ++++
> arch/x86/include/asm/ptrace.h | 62 ++
> arch/x86/kernel/kprobes.c | 209 +++---
> arch/x86/kernel/ptrace.c | 112 +++
> arch/x86/lib/Makefile | 13 +
> arch/x86/lib/inat.c | 78 +++
> arch/x86/lib/insn.c | 464 +++++++++++++
> arch/x86/lib/x86-opcode-map.txt | 719 ++++++++++++++++++++
> arch/x86/tools/Makefile | 15 +
> arch/x86/tools/distill.awk | 42 ++
> arch/x86/tools/gen-insn-attr-x86.awk | 334 +++++++++
> arch/x86/tools/test_get_len.c | 113 ++++
> include/linux/ftrace_event.h | 19 +-
> include/linux/kprobes.h | 2 +
> include/linux/syscalls.h | 4 +-
> include/trace/ftrace.h | 16 +-
> include/trace/syscall.h | 11 +-
> kernel/kprobes.c | 7 +
> kernel/trace/Kconfig | 12 +
> kernel/trace/Makefile | 1 +
> kernel/trace/trace.h | 24 +
> kernel/trace/trace_event_types.h | 4 +-
> kernel/trace/trace_events.c | 121 +++-
> kernel/trace/trace_export.c | 34 +-
> kernel/trace/trace_kprobe.c | 1231 ++++++++++++++++++++++++++++++++++
> kernel/trace/trace_syscalls.c | 20 +-
> 31 files changed, 3991 insertions(+), 196 deletions(-)
> create mode 100644 Documentation/trace/kprobetrace.txt
> create mode 100644 arch/x86/include/asm/inat.h
> create mode 100644 arch/x86/include/asm/inat_types.h
> create mode 100644 arch/x86/include/asm/insn.h
> create mode 100644 arch/x86/lib/inat.c
> create mode 100644 arch/x86/lib/insn.c
> create mode 100644 arch/x86/lib/x86-opcode-map.txt
> create mode 100644 arch/x86/tools/Makefile
> create mode 100644 arch/x86/tools/distill.awk
> create mode 100644 arch/x86/tools/gen-insn-attr-x86.awk
> create mode 100644 arch/x86/tools/test_get_len.c
> create mode 100644 kernel/trace/trace_kprobe.c
--
Masami Hiramatsu
Software Engineer
Hitachi Computer Products (America), Inc.
Software Solutions Division
e-mail: mhiramat@redhat.com
next prev parent reply other threads:[~2009-08-27 14:57 UTC|newest]
Thread overview: 89+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-08-27 2:31 Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 01/18] x86: Instruction decoder API Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 02/18] x86: X86 instruction decoder build-time selftest Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 03/18] kprobes: Checks probe address is instruction boudary on x86 Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 04/18] kprobes: Cleanup fix_riprel() using insn decoder " Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 05/18] x86: Add pt_regs register and stack access APIs Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 06/18] tracing: Ftrace dynamic ftrace_event_call support Frederic Weisbecker
2009-08-27 2:47 ` Li Zefan
2009-08-27 2:56 ` Frederic Weisbecker
2009-08-27 15:07 ` Masami Hiramatsu
2009-08-27 2:32 ` [PATCH 07/18] tracing: Introduce TRACE_FIELD_ZERO() macro Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 08/18] tracing: Add kprobe-based event tracer Frederic Weisbecker
2009-08-27 7:31 ` Ingo Molnar
2009-08-27 13:48 ` Frederic Weisbecker
2009-08-27 15:38 ` Masami Hiramatsu
2009-08-27 2:32 ` [PATCH 09/18] tracing: Add kprobe-based event tracer documentation Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 10/18] tracing: Kprobe-tracer supports more than 6 arguments Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 11/18] tracing: Generate names for each kprobe event automatically Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 12/18] tracing: Kprobe tracer assigns new event ids for each event Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 13/18] tracing: Add kprobes event profiling interface Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 14/18] x86: Fix x86 instruction decoder selftest to check only .text Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 15/18] x86: Check awk features before generating inat-tables.c Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 16/18] tracing/kprobes: Fix format typo in trace_kprobes Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 17/18] tracing/kprobes: Change trace_arg to probe_arg Frederic Weisbecker
2009-08-27 2:32 ` [PATCH 18/18] tracing/kprobes: Dump the culprit kprobe in case of kprobe recursion Frederic Weisbecker
2009-08-27 15:30 ` Masami Hiramatsu
2009-08-27 15:34 ` Frederic Weisbecker
2009-08-27 15:52 ` Masami Hiramatsu
2009-08-27 16:30 ` Frederic Weisbecker
2009-08-27 16:45 ` Masami Hiramatsu
2009-08-27 16:45 ` Frederic Weisbecker
2009-08-27 3:34 ` [GIT PULL v2] tracing/kprobes: v1 + two fixes Frederic Weisbecker
2009-08-27 15:24 ` Ingo Molnar
2009-08-27 15:40 ` Frederic Weisbecker
2009-08-27 15:59 ` Frederic Weisbecker
2009-08-27 16:17 ` [PATCH] tracing: Undef TRACE_EVENT_FN between trace events headers inclusion Frederic Weisbecker
2009-08-27 16:36 ` [tip:tracing/core] " tip-bot for Frederic Weisbecker
2009-08-27 16:12 ` [GIT PULL v2] tracing/kprobes: v1 + two fixes Masami Hiramatsu
2009-08-27 16:35 ` Ingo Molnar
2009-08-27 16:52 ` Masami Hiramatsu
2009-08-29 11:02 ` Ingo Molnar
2009-08-28 22:13 ` [PATCH -tip tracing/kprobes 1/2] x86: Allow x86-32 instruction decoder selftest on x86-64 Masami Hiramatsu
2009-08-30 1:35 ` Frederic Weisbecker
2009-10-17 9:58 ` [tip:perf/probes] " tip-bot for Masami Hiramatsu
2009-08-28 22:13 ` [PATCH -tip tracing/kprobes 2/2] x86: Remove unused config macros from instruction decoder selftest Masami Hiramatsu
2009-10-17 9:58 ` [tip:perf/probes] " tip-bot for Masami Hiramatsu
2009-08-27 15:26 ` [GIT PULL v2] tracing/kprobes: v1 + two fixes Ingo Molnar
2009-09-16 5:30 ` Frederic Weisbecker
2009-08-27 3:34 ` [PATCH 19/18] tracing: Restore the const qualifier for field names and types definition Frederic Weisbecker
2009-08-27 15:07 ` Masami Hiramatsu
2009-08-27 3:34 ` [PATCH 20/18] tracing: Remove unneeded pointer casts Frederic Weisbecker
2009-08-27 15:08 ` Masami Hiramatsu
2009-08-27 15:00 ` Masami Hiramatsu [this message]
2009-08-27 15:25 ` [GIT PULL] tracing/kprobes: Add dynamic tracepoints + instruction decoder Frederic Weisbecker
2009-08-27 17:22 ` [PATCH -tip tracing/kprobes 1/6] kprobes/x86: Call BUG() when reentering probe into KPROBES_HIT_SS Masami Hiramatsu
2009-08-28 4:38 ` Ananth N Mavinakayanahalli
2009-08-30 1:25 ` Frederic Weisbecker
2009-10-17 9:56 ` [tip:perf/probes] " tip-bot for Masami Hiramatsu
2009-08-27 17:23 ` [PATCH -tip tracing/kprobes 2/6] kprobes/x86-64: Allow to reenter probe on post_handler Masami Hiramatsu
2009-08-28 4:39 ` Ananth N Mavinakayanahalli
2009-10-17 9:57 ` [tip:perf/probes] " tip-bot for Masami Hiramatsu
2009-08-27 17:23 ` [PATCH -tip tracing/kprobes 3/6] kprobes/x86: Fix to add __kprobes to in-kernel fault handing functions Masami Hiramatsu
2009-08-28 4:40 ` Ananth N Mavinakayanahalli
2009-08-30 0:50 ` Frederic Weisbecker
2009-08-30 2:43 ` Masami Hiramatsu
2009-08-30 0:53 ` Frederic Weisbecker
2009-08-30 2:49 ` Masami Hiramatsu
2009-08-30 16:09 ` Frederic Weisbecker
2009-08-31 4:00 ` Masami Hiramatsu
2009-09-01 20:09 ` Masami Hiramatsu
2009-09-02 12:58 ` Masami Hiramatsu
2009-09-03 5:46 ` Frederic Weisbecker
2009-09-04 19:06 ` Frederic Weisbecker
2009-09-04 22:29 ` Masami Hiramatsu
2009-09-08 16:32 ` [PATCH tracing/kprobes] x86: Add MMX support for instruction decoder Masami Hiramatsu
2009-09-10 22:57 ` Frederic Weisbecker
2009-10-17 9:58 ` [tip:perf/probes] " tip-bot for Masami Hiramatsu
2009-09-08 16:54 ` [RFC PATCH tracing/kprobes] kprobes: Call vmalloc_sync_all() for avoiding in-kernel paging on kprobes Masami Hiramatsu
[not found] ` <20090908165438.24437.40931.stgit@dhcp-100-2-132.bos.redhat .com>
2009-09-08 17:03 ` system hang - I suspect a sata problem - 2.6.30.5 debug kernel jeffunit
2009-10-17 9:57 ` [tip:perf/probes] kprobes/x86: Fix to add __kprobes to in-kernel fault handing functions tip-bot for Masami Hiramatsu
2009-08-27 17:23 ` [PATCH -tip tracing/kprobes 4/6] kprobes: Fix to add __kprobes to notify_die Masami Hiramatsu
2009-08-28 4:41 ` Ananth N Mavinakayanahalli
2009-10-17 9:57 ` [tip:perf/probes] " tip-bot for Masami Hiramatsu
2009-08-27 17:23 ` [PATCH -tip tracing/kprobes 5/6] kprobes/x86-64: Fix to move common_interrupt to .kprobes.text Masami Hiramatsu
2009-10-17 9:57 ` [tip:perf/probes] " tip-bot for Masami Hiramatsu
2009-08-27 17:23 ` [PATCH -tip tracing/kprobes 6/6] kprobes: Prohibit to probe native_get_debugreg Masami Hiramatsu
2009-08-28 4:41 ` Ananth N Mavinakayanahalli
2009-10-17 9:57 ` [tip:perf/probes] " tip-bot for Masami Hiramatsu
2009-08-27 17:32 ` [GIT PULL] tracing/kprobes: Add dynamic tracepoints + instruction decoder Masami Hiramatsu
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=4A969F96.2020107@redhat.com \
--to=mhiramat@redhat.com \
--cc=fweisbec@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rostedt@goodmis.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome