All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Andy Lutomirski <luto@amacapital.net>, X86 ML <x86@kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Willy Tarreau <w@1wt.eu>, Borislav Petkov <bp@alien8.de>,
	Thomas Gleixner <tglx@linutronix.de>,
	Brian Gerst <brgerst@gmail.com>
Subject: Re: Dealing with the NMI mess
Date: Fri, 24 Jul 2015 14:43:04 +0200	[thread overview]
Message-ID: <20150724124304.GH19282@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20150724075841.40f209f4@gandalf.local.home>

On Fri, Jul 24, 2015 at 07:58:41AM -0400, Steven Rostedt wrote:
> On Fri, 24 Jul 2015 10:13:26 +0200
> Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > On Thu, Jul 23, 2015 at 02:59:56PM -0700, Linus Torvalds wrote:
> > > Hmmm. I thought watchpoints were "before the instruction" too, but
> > > that's just because I haven't used them in ages, and I didn't remember
> > > the details. I just looked it up.
> > > 
> > > You're right - the memory watchpoints trigger after the instruction
> > > has executed, so RF isn't an issue. So yes, the only issue is
> > > instruction breakpoints, and those are the only ones we need to clear.
> > > 
> > > And that makes it really easy.
> > > 
> > > So yes, I agree. We only need to clear all kernel breakpoints.
> > 
> > But but but, we can access userspace with !IF, imagine someone doing:
> > 
> >   local_irq_disable();
> >   copy_from_user_inatomic();
> > 
> > and as luck would have it, there's a breakpoint on the user memory we
> > just touched. And we go and disable a user breakpoint.
> 
> Where does the kernel do that to user text? I would think that user
> data would only have watchpoints, and Andy and Linus said that those
> would not be disabled (I'm guessing because they don't have the RF flag
> set, and forward progress can proceed). If the kernel does the above to
> user code and there's a breakpoint there, would it even trigger?
> 
> I'm not too familiar with how to use hw breakpoints, but I'm guessing
> (correct me if I'm wrong) that breakpoints on code that trigger when
> executed, but watchpoints on data trigger when accessed. Then
> copy_from_user_inatomic() would only trigger on watchpoints (it's not
> executing that code, at least I hope it isn't!), and those wont bother
> us.

These things can be: RW, W, X.

Sure, hitting a user X watchpoint is going to be 'interesting', but its
fairly easy to hit a RW one.

Just watch an on-stack variable and get perf to copy a huge chunk of
stack (like it does for the dwarf stuff).


  reply	other threads:[~2015-07-24 12:43 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-23 20:21 Dealing with the NMI mess Andy Lutomirski
2015-07-23 20:38 ` Linus Torvalds
2015-07-23 20:49   ` Andy Lutomirski
2015-07-23 21:08     ` Linus Torvalds
2015-07-23 21:31       ` Steven Rostedt
2015-07-23 21:46         ` Willy Tarreau
2015-07-23 21:46           ` Andy Lutomirski
2015-07-23 21:50             ` Willy Tarreau
2015-07-23 21:48         ` Linus Torvalds
2015-07-23 21:50           ` Andy Lutomirski
2015-07-23 21:59             ` Linus Torvalds
2015-07-24  8:13               ` Peter Zijlstra
2015-07-24  9:02                 ` Willy Tarreau
2015-07-24 11:58                 ` Steven Rostedt
2015-07-24 12:43                   ` Peter Zijlstra [this message]
2015-07-24 13:03                     ` Steven Rostedt
2015-07-24 13:21                       ` Willy Tarreau
2015-07-24 13:30                         ` Peter Zijlstra
2015-07-24 13:33                           ` Peter Zijlstra
2015-07-24 14:31                         ` Steven Rostedt
2015-07-24 14:59                           ` Willy Tarreau
2015-07-24 15:16                             ` Steven Rostedt
2015-07-24 15:26                               ` Willy Tarreau
2015-07-24 15:30                                 ` Peter Zijlstra
2015-07-24 15:33                                   ` Willy Tarreau
2015-07-24 18:29                                   ` Linus Torvalds
2015-07-24 18:41                                     ` Linus Torvalds
2015-07-24 19:05                                       ` Steven Rostedt
2015-07-24 19:55                                     ` Peter Zijlstra
2015-07-24 20:22                                       ` Linus Torvalds
2015-07-24 20:51                                         ` Peter Zijlstra
2015-07-24 21:07                                           ` Steven Rostedt
2015-07-24 21:08                                           ` Andy Lutomirski
2015-07-30 15:41                                             ` Paolo Bonzini
2015-07-30 21:22                                               ` Andy Lutomirski
2015-07-30 21:58                                                 ` Brian Gerst
2015-07-30 22:59                                                 ` Thomas Gleixner
2015-07-31  4:22                                                 ` Borislav Petkov
2015-07-31  5:11                                                   ` Andy Lutomirski
2015-07-31  7:51                                                     ` Paolo Bonzini
2015-07-31  8:03                                                     ` Borislav Petkov
2015-07-31  9:27                                                       ` Paolo Bonzini
2015-07-31 10:25                                                         ` Borislav Petkov
2015-07-31 10:26                                                           ` Paolo Bonzini
2015-07-31 10:32                                                             ` Borislav Petkov
2015-09-07  5:39                                                       ` Maciej W. Rozycki
2015-09-07  7:42                                                         ` Ingo Molnar
2015-09-07  8:19                                                           ` Maciej W. Rozycki
2015-09-07 10:19                                                             ` Paolo Bonzini
2015-09-07 17:01                                                               ` Maciej W. Rozycki
2015-09-07 17:22                                                                 ` Andy Lutomirski
2015-09-07 19:30                                                                   ` Maciej W. Rozycki
2015-09-07 21:56                                                                     ` Andy Lutomirski
2015-09-08 16:21                                                                       ` Maciej W. Rozycki
2015-07-24 23:53                                           ` Linus Torvalds
2015-07-24 15:34                                 ` Steven Rostedt
2015-07-24 15:49                                   ` Willy Tarreau
2015-07-24 15:48                 ` Andy Lutomirski
2015-07-24 16:02                   ` Steven Rostedt
2015-07-24 16:08                     ` Willy Tarreau
2015-07-24 16:31                       ` Steven Rostedt
2015-07-24 16:06                   ` Steven Rostedt
2015-07-24 16:25                   ` Willy Tarreau
2015-07-24 17:21                     ` Andy Lutomirski
2015-07-24 17:10                   ` Willy Tarreau
2015-07-24 17:20                     ` Andy Lutomirski
2015-07-30 15:54                       ` Paolo Bonzini
2015-07-24 17:21                     ` Willy Tarreau
2015-07-23 20:52   ` Willy Tarreau
2015-07-23 20:53     ` Andy Lutomirski
2015-07-23 21:07       ` Willy Tarreau
2015-07-23 21:13     ` Linus Torvalds
2015-07-23 21:18       ` Willy Tarreau
2015-07-23 21:20   ` Peter Zijlstra
2015-07-23 21:35     ` Linus Torvalds
2015-07-23 21:45       ` Andy Lutomirski
2015-07-23 21:54         ` Linus Torvalds
2015-07-23 21:59           ` Andy Lutomirski
2015-07-23 22:03             ` Linus Torvalds
2015-07-24 10:28             ` Peter Zijlstra
2015-07-24 11:06           ` Peter Zijlstra
2015-07-23 21:17 ` Peter Zijlstra
2015-07-23 21:20 ` Steven Rostedt
2015-07-23 21:46   ` Andy Lutomirski
2015-07-24 16:33 ` Raymond Jennings

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=20150724124304.GH19282@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=w@1wt.eu \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.