From: "Paul E. McKenney" <paulmck@kernel.org>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Steven Rostedt <rostedt@goodmis.org>,
Peter Zijlstra <peterz@infradead.org>,
LKML <linux-kernel@vger.kernel.org>, X86 ML <x86@kernel.org>,
Brian Gerst <brgerst@gmail.com>, Juergen Gross <JGross@suse.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Arnd Bergmann <arnd@arndb.de>
Subject: Re: [patch 4/8] x86/entry: Move irq tracing on syscall entry to C-code
Date: Sun, 1 Mar 2020 12:18:07 -0800 [thread overview]
Message-ID: <20200301201807.GZ2935@paulmck-ThinkPad-P72> (raw)
In-Reply-To: <5BCFDB36-26B6-4881-94D9-4AB0731F8DC5@amacapital.net>
On Sun, Mar 01, 2020 at 11:39:42AM -0800, Andy Lutomirski wrote:
>
>
> > On Mar 1, 2020, at 11:30 AM, Paul E. McKenney <paulmck@kernel.org> wrote:
> >
> > On Sun, Mar 01, 2020 at 10:54:23AM -0800, Andy Lutomirski wrote:
> >>> On Sun, Mar 1, 2020 at 10:26 AM Paul E. McKenney <paulmck@kernel.org> wrote:
> >>>
> >>> On Sun, Mar 01, 2020 at 07:12:25PM +0100, Thomas Gleixner wrote:
> >>>> Andy Lutomirski <luto@kernel.org> writes:
> >>>>> On Sun, Mar 1, 2020 at 7:21 AM Thomas Gleixner <tglx@linutronix.de> wrote:
> >>>>>> Andy Lutomirski <luto@amacapital.net> writes:
> >>>>>>>> On Mar 1, 2020, at 2:16 AM, Thomas Gleixner <tglx@linutronix.de> wrote:
> >>>>>>>> Ok, but for the time being anything before/after CONTEXT_KERNEL is unsafe
> >>>>>>>> except trace_hardirq_off/on() as those trace functions do not allow to
> >>>>>>>> attach anything AFAICT.
> >>>>>>>
> >>>>>>> Can you point to whatever makes those particular functions special? I
> >>>>>>> failed to follow the macro maze.
> >>>>>>
> >>>>>> Those are not tracepoints and not going through the macro maze. See
> >>>>>> kernel/trace/trace_preemptirq.c
> >>>>>
> >>>>> That has:
> >>>>>
> >>>>> void trace_hardirqs_on(void)
> >>>>> {
> >>>>> if (this_cpu_read(tracing_irq_cpu)) {
> >>>>> if (!in_nmi())
> >>>>> trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
> >>>>> tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
> >>>>> this_cpu_write(tracing_irq_cpu, 0);
> >>>>> }
> >>>>>
> >>>>> lockdep_hardirqs_on(CALLER_ADDR0);
> >>>>> }
> >>>>> EXPORT_SYMBOL(trace_hardirqs_on);
> >>>>> NOKPROBE_SYMBOL(trace_hardirqs_on);
> >>>>>
> >>>>> But this calls trace_irq_enable_rcuidle(), and that's the part of the
> >>>>> macro maze I got lost in. I found:
> >>>>>
> >>>>> #ifdef CONFIG_TRACE_IRQFLAGS
> >>>>> DEFINE_EVENT(preemptirq_template, irq_disable,
> >>>>> TP_PROTO(unsigned long ip, unsigned long parent_ip),
> >>>>> TP_ARGS(ip, parent_ip));
> >>>>>
> >>>>> DEFINE_EVENT(preemptirq_template, irq_enable,
> >>>>> TP_PROTO(unsigned long ip, unsigned long parent_ip),
> >>>>> TP_ARGS(ip, parent_ip));
> >>>>> #else
> >>>>> #define trace_irq_enable(...)
> >>>>> #define trace_irq_disable(...)
> >>>>> #define trace_irq_enable_rcuidle(...)
> >>>>> #define trace_irq_disable_rcuidle(...)
> >>>>> #endif
> >>>>>
> >>>>> But the DEFINE_EVENT doesn't have the "_rcuidle" part. And that's
> >>>>> where I got lost in the macro maze. I looked at the gcc asm output,
> >>>>> and there is, indeed:
> >>>>
> >>>> DEFINE_EVENT
> >>>> DECLARE_TRACE
> >>>> __DECLARE_TRACE
> >>>> __DECLARE_TRACE_RCU
> >>>> static inline void trace_##name##_rcuidle(proto)
> >>>> __DO_TRACE
> >>>> if (rcuidle)
> >>>> ....
> >>>>
> >>>>> But I also don't see why this is any different from any other tracepoint.
> >>>>
> >>>> Indeed. I took a wrong turn at some point in the macro jungle :)
> >>>>
> >>>> So tracing itself is fine, but then if you have probes or bpf programs
> >>>> attached to a tracepoint these use rcu_read_lock()/unlock() which is
> >>>> obviosly wrong in rcuidle context.
> >>>
> >>> Definitely, any such code needs to use tricks similar to that of the
> >>> tracing code. Or instead use something like SRCU, which is OK with
> >>> readers from idle. Or use something like Steve Rostedt's workqueue-based
> >>> approach, though please be very careful with this latter, lest the
> >>> battery-powered embedded guys come after you for waking up idle CPUs
> >>> too often. ;-)
> >>
> >> Are we okay if we somehow ensure that all the entry code before
> >> enter_from_user_mode() only does rcuidle tracing variants and has
> >> kprobes off? Including for BPF use cases?
> >
> > That would work, though if BPF used SRCU instead of RCU, this would
> > be unnecessary. Sadly, SRCU has full memory barriers in each of
> > srcu_read_lock() and srcu_read_unlock(), but we are working on it.
> > (As always, no promises!)
> >
> >> It would be *really* nice if we could statically verify this, as has
> >> been mentioned elsewhere in the thread. It would also probably be
> >> good enough if we could do it at runtime. Maybe with lockdep on, we
> >> verify rcu state in tracepoints even if the tracepoint isn't active?
> >> And we could plausibly have some widget that could inject something
> >> into *every* kprobeable function to check rcu state.
> >
> > Or just have at least one testing step that activates all tracepoints,
> > but with lockdep enabled?
>
> Also kprobe.
I didn't realize we could test all kprobe points easily, but yes,
that would also be good.
> I don’t suppose we could make notrace imply nokprobe. Then all kprobeable functions would also have entry/exit tracepoints, right?
On this, I must defer to the tracing and kprobes people.
Thanx, Paul
next prev parent reply other threads:[~2020-03-01 20:18 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-25 22:08 [patch 0/8] x86/entry: Consolidation - Part II Thomas Gleixner
2020-02-25 22:08 ` [patch 1/8] x86/entry/64: Trace irqflags unconditionally on when returing to user space Thomas Gleixner
2020-02-27 19:49 ` Borislav Petkov
2020-02-27 22:45 ` Frederic Weisbecker
2020-02-28 8:58 ` Alexandre Chartre
2020-02-25 22:08 ` [patch 2/8] x86/entry/common: Consolidate syscall entry code Thomas Gleixner
2020-02-27 19:57 ` Borislav Petkov
2020-02-27 22:52 ` Frederic Weisbecker
2020-02-28 8:59 ` Alexandre Chartre
2020-02-25 22:08 ` [patch 3/8] x86/entry/common: Mark syscall entry points notrace/nokprobe Thomas Gleixner
2020-02-27 23:15 ` Frederic Weisbecker
2020-02-28 8:59 ` Alexandre Chartre
2020-02-25 22:08 ` [patch 4/8] x86/entry: Move irq tracing on syscall entry to C-code Thomas Gleixner
2020-02-26 5:43 ` Andy Lutomirski
2020-02-26 8:17 ` Peter Zijlstra
2020-02-26 11:20 ` Andy Lutomirski
2020-02-26 19:51 ` Thomas Gleixner
2020-02-29 14:44 ` Thomas Gleixner
2020-02-29 19:25 ` Andy Lutomirski
2020-02-29 23:58 ` Steven Rostedt
2020-03-01 10:16 ` Thomas Gleixner
2020-03-01 14:37 ` Andy Lutomirski
2020-03-01 15:21 ` Thomas Gleixner
2020-03-01 16:00 ` Andy Lutomirski
2020-03-01 18:12 ` Thomas Gleixner
2020-03-01 18:26 ` Paul E. McKenney
2020-03-01 18:54 ` Andy Lutomirski
2020-03-01 19:30 ` Paul E. McKenney
2020-03-01 19:39 ` Andy Lutomirski
2020-03-01 20:18 ` Paul E. McKenney [this message]
2020-03-02 0:35 ` Steven Rostedt
2020-03-02 6:47 ` Masami Hiramatsu
2020-03-02 1:10 ` Joel Fernandes
2020-03-02 2:18 ` Andy Lutomirski
2020-03-02 2:36 ` Joel Fernandes
2020-03-02 5:40 ` Andy Lutomirski
2020-03-02 8:10 ` Thomas Gleixner
2020-03-01 18:23 ` Steven Rostedt
2020-03-01 18:20 ` Steven Rostedt
2020-02-27 23:11 ` Frederic Weisbecker
2020-02-28 9:00 ` Alexandre Chartre
2020-02-25 22:08 ` [patch 5/8] x86/entry/common: Provide trace/kprobe safe exit to user space functions Thomas Gleixner
2020-02-26 5:45 ` Andy Lutomirski
2020-02-26 8:15 ` Peter Zijlstra
2020-02-27 15:43 ` Alexandre Chartre
2020-02-27 15:53 ` Thomas Gleixner
2020-02-25 22:08 ` [patch 6/8] x86/entry: Move irq tracing to syscall_slow_exit_work Thomas Gleixner
2020-02-26 5:47 ` Andy Lutomirski
2020-02-27 16:12 ` Alexandre Chartre
2020-02-25 22:08 ` [patch 7/8] x86/entry: Move irq tracing to prepare_exit_to_user_mode() Thomas Gleixner
2020-02-26 5:50 ` Andy Lutomirski
2020-02-26 19:53 ` Thomas Gleixner
2020-02-26 20:07 ` Andy Lutomirski
2020-02-25 22:08 ` [patch 8/8] x86/entry: Move irqflags tracing to do_int80_syscall_32() Thomas Gleixner
2020-02-27 16:46 ` Alexandre Chartre
2020-02-28 13:49 ` Thomas Gleixner
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=20200301201807.GZ2935@paulmck-ThinkPad-P72 \
--to=paulmck@kernel.org \
--cc=JGross@suse.com \
--cc=arnd@arndb.de \
--cc=brgerst@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=luto@kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--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 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).