linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Masami Hiramatsu <mhiramat@kernel.org>
To: Jeff Xie <xiehuan09@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	mingo@redhat.com, Tom Zanussi <zanussi@kernel.org>,
	linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH v6 0/5] trace: Introduce objtrace trigger to trace the kernel object
Date: Mon, 13 Dec 2021 19:16:47 +0900	[thread overview]
Message-ID: <20211213191647.36d6016fb08420fbc6d55b1b@kernel.org> (raw)
In-Reply-To: <CAEr6+EDZ5vZyTkA3XCO3u76sY7SpZEV2nhLiY4MPL_BuFQDi0A@mail.gmail.com>

Hi Jeff,

On Sat, 11 Dec 2021 00:55:31 +0800
Jeff Xie <xiehuan09@gmail.com> wrote:

> hi Steve and Masami,
> 
> I really don't know what else I can do to enhance this patchset, if
> this idea is really valuable and
> can play its role, it may need the help of you or other developers ;-)

Thanks for ping me. Let me review it this week.

Thank you!

> 
> On Tue, Nov 30, 2021 at 12:50 AM Jeff Xie <xiehuan09@gmail.com> wrote:
> >
> > Introduce a method based on function tracer to trace any object and get
> > the value of the object dynamically. the object can be obtained from the
> > dynamic event (kprobe_event/uprobe_event) or the static event(tracepoint).
> >
> > Usage:
> > When using the kprobe event, only need to set the objtrace(a new trigger),
> > we can get the value of the object. The object is from the setting of the
> > kprobe event.
> >
> > For example:
> > For the function bio_add_page():
> >
> > int bio_add_page(struct bio *bio, struct page *page,
> >         unsigned int len, unsigned int offset)
> >
> > Firstly, we can set the base of the object, thus the first string "arg1"
> > stands for the value of the first parameter of this function bio_add_gage(),
> >
> > # echo 'p bio_add_page arg1=$arg1' >> ./kprobe_events
> >
> > Secondly, we can get the value dynamically base the above object.
> >
> > find the offset of the bi_size in struct bio:
> > $ gdb vmlinux
> > (gdb) p &(((struct bio *)0)->bi_iter.bi_size)
> > $1 = (unsigned int *) 0x28
> >
> > # echo 'objtrace:add:arg1,0x28:u32:1 if comm == "cat"' > ./events/kprobes/ \
> >         p_bio_add_page_0/trigger
> >
> > The best way to use this is that we can set the entrance event and exit
> > event, for example, the following example is to set the read_papes as
> > the entrance event, and set the __blk_account_io_start as the exit event.
> >
> > # cd /sys/kernel/debug/tracing/
> > # echo 0 > ./tracing_on
> > # echo 'p read_pages' >> ./kprobe_events
> > # echo 'p __blk_account_io_start' >> ./kprobe_events
> > # echo 'traceon if comm == "cat"' > ./events/kprobes/p_read_pages_0/trigger
> > # echo 'traceoff if comm == "cat"' > ./events/kprobes/p___blk_account_io_start_0/trigger
> > # echo 'p bio_add_page arg1=$arg1' >> ./kprobe_events
> > # echo 'objtrace:add:arg1,0x28:u32:1 if comm == "cat"' > ./events/kprobes/p_bio_add_page_0/trigger
> >
> > # du -sh /test.txt
> > 12.0K   /test.txt
> >
> > # cat  /test.txt > /dev/null
> > # cat ./trace
> >
> > # tracer: nop
> > #
> > # entries-in-buffer/entries-written: 50/50   #P:1
> > #
> > #                                _-----=> irqs-off
> > #                               / _----=> need-resched
> > #                              | / _---=> hardirq/softirq
> > #                              || / _--=> preempt-depth
> > #                              ||| / _-=> migrate-disable
> > #                              |||| /     delay
> > #           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
> > #              | |         |   |||||     |         |
> >              cat-95      [000] .....     1.412065: _raw_spin_unlock_irqrestore <-event_triggers_call object:0xffff888108af6328 value:0x0
> >              cat-95      [000] .....     1.412066: __bio_try_merge_page <-bio_add_page object:0xffff888108af6328 value:0x0
> >              cat-95      [000] .....     1.412066: __bio_add_page <-bio_add_page object:0xffff888108af6328 value:0x0
> >              cat-95      [000] .....     1.412066: rcu_read_unlock_strict <-xa_load object:0xffff888108af6328 value:0x1000
> >              cat-95      [000] .....     1.412066: bio_add_page <-ext4_mpage_readpages object:0xffff888108af6328 value:0x1000
> >              cat-95      [000] .....     1.412066: kprobe_ftrace_handler <-ftrace_ops_list_func object:0xffff888108af6328 value:0x1000
> >              cat-95      [000] .....     1.412067: get_kprobe <-kprobe_ftrace_handler object:0xffff888108af6328 value:0x1000
> >              cat-95      [000] .....     1.412067: __bio_try_merge_page <-bio_add_page object:0xffff888108af6328 value:0x1000
> >              cat-95      [000] .....     1.412067: __bio_add_page <-bio_add_page object:0xffff888108af6328 value:0x1000
> >              cat-95      [000] .....     1.412067: rcu_read_unlock_strict <-xa_load object:0xffff888108af6328 value:0x2000
> >              cat-95      [000] .....     1.412067: bio_add_page <-ext4_mpage_readpages object:0xffff888108af6328 value:0x2000
> >              cat-95      [000] .....     1.412067: kprobe_ftrace_handler <-ftrace_ops_list_func object:0xffff888108af6328 value:0x2000
> >              cat-95      [000] .....     1.412067: get_kprobe <-kprobe_ftrace_handler object:0xffff888108af6328 value:0x2000
> >              cat-95      [000] .....     1.412067: __bio_try_merge_page <-bio_add_page object:0xffff888108af6328 value:0x2000
> >              cat-95      [000] .....     1.412068: submit_bio <-ext4_mpage_readpages object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: submit_bio_noacct <-ext4_mpage_readpages object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: __submit_bio <-submit_bio_noacct object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: blk_try_enter_queue <-__submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: rcu_read_unlock_strict <-blk_try_enter_queue object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: rcu_read_unlock_strict <-blk_try_enter_queue object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: submit_bio_checks <-__submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: __cond_resched <-submit_bio_checks object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: rcu_all_qs <-__cond_resched object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412068: should_fail_bio <-submit_bio_checks object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412069: create_task_io_context <-submit_bio_checks object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412069: kmem_cache_alloc_node <-create_task_io_context object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412069: should_failslab <-kmem_cache_alloc_node object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412069: _raw_spin_lock <-create_task_io_context object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412069: blk_mq_submit_bio <-__submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412069: __blk_queue_split <-blk_mq_submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412069: bvec_split_segs <-__blk_queue_split object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412069: blk_attempt_plug_merge <-blk_mq_submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: __blk_mq_sched_bio_merge <-blk_mq_submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: dd_bio_merge <-blk_mq_submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: _raw_spin_lock <-dd_bio_merge object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: blk_mq_sched_try_merge <-dd_bio_merge object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: elv_merge <-blk_mq_sched_try_merge object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: elv_rqhash_find <-elv_merge object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: dd_request_merge <-blk_mq_sched_try_merge object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: elv_rb_find <-dd_request_merge object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412070: __blk_mq_alloc_request <-blk_mq_submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: dd_limit_depth <-__blk_mq_alloc_request object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: blk_mq_get_tag <-__blk_mq_alloc_request object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: __blk_mq_get_tag <-blk_mq_get_tag object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: blk_mq_rq_ctx_init.isra.0 <-blk_mq_submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: ktime_get <-blk_mq_rq_ctx_init.isra.0 object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: dd_prepare_request <-blk_mq_rq_ctx_init.isra.0 object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: __blk_account_io_start <-blk_mq_submit_bio object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: kprobe_ftrace_handler <-ftrace_ops_list_func object:0xffff888108af6328 value:0x3000
> >              cat-95      [000] .....     1.412071: get_kprobe <-kprobe_ftrace_handler object:0xffff888108af6328 value:0x3000
> >
> > Jeff Xie (5):
> >   trace: Add trace any kernel object
> >   trace/objtrace: get the value of the object
> >   trace/README: Document objtrace trigger syntax
> >   trace/objtrace: Add testcases for objtrace
> >   trace/objtrace: Add documentation for objtrace
> >
> >  Documentation/trace/events.rst                | 114 +++
> >  include/linux/trace_events.h                  |   1 +
> >  kernel/trace/Kconfig                          |  10 +
> >  kernel/trace/Makefile                         |   1 +
> >  kernel/trace/trace.c                          |   3 +
> >  kernel/trace/trace.h                          |   8 +
> >  kernel/trace/trace_entries.h                  |  18 +
> >  kernel/trace/trace_events_trigger.c           |   1 +
> >  kernel/trace/trace_object.c                   | 660 ++++++++++++++++++
> >  kernel/trace/trace_output.c                   |  40 ++
> >  .../ftrace/test.d/trigger/trigger-objtrace.tc |  39 ++
> >  11 files changed, 895 insertions(+)
> >  create mode 100644 kernel/trace/trace_object.c
> >  create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/trigger-objtrace.tc
> >
> > --
> > 2.25.1
> >
> 
> Thanks,
> ---
> JeffXie


-- 
Masami Hiramatsu <mhiramat@kernel.org>

  parent reply	other threads:[~2021-12-13 10:39 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-29 16:49 [RFC][PATCH v6 0/5] trace: Introduce objtrace trigger to trace the kernel object Jeff Xie
2021-11-29 16:49 ` [RFC][PATCH v6 1/5] trace: Add trace any " Jeff Xie
2021-12-17  4:51   ` Masami Hiramatsu
2021-12-17 16:32     ` Jeff Xie
2021-12-19  3:07       ` Masami Hiramatsu
2022-01-08  0:21         ` Steven Rostedt
2022-01-10  2:00           ` Jeff Xie
2021-12-21  7:36       ` Masami Hiramatsu
2021-12-21 10:29         ` Jeff Xie
2021-12-23 14:12           ` Jeff Xie
2021-11-29 16:49 ` [RFC][PATCH v6 2/5] trace/objtrace: get the value of the object Jeff Xie
2021-11-29 16:49 ` [RFC][PATCH v6 3/5] trace/README: Document objtrace trigger syntax Jeff Xie
2021-12-16 15:02   ` Masami Hiramatsu
2021-12-17  1:45     ` Jeff Xie
2021-11-29 16:49 ` [RFC][PATCH v6 4/5] trace/objtrace: Add testcases for objtrace Jeff Xie
2021-11-29 16:49 ` [RFC][PATCH v6 5/5] trace/objtrace: Add documentation " Jeff Xie
2021-12-10 16:55 ` [RFC][PATCH v6 0/5] trace: Introduce objtrace trigger to trace the kernel object Jeff Xie
2021-12-10 17:31   ` Steven Rostedt
2021-12-13 10:16   ` Masami Hiramatsu [this message]
2021-12-16 14:50 ` Masami Hiramatsu
2021-12-17  1:43   ` Jeff Xie

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=20211213191647.36d6016fb08420fbc6d55b1b@kernel.org \
    --to=mhiramat@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=xiehuan09@gmail.com \
    --cc=zanussi@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 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).