From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Peter Zijlstra <peterz@infradead.org>,
Steven Rostedt <rostedt@goodmis.org>,
LKML <linux-kernel@vger.kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Ingo Molnar <mingo@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Thomas Gleixner <tglx@linutronix.de>,
Masami Hiramatsu <mhiramat@kernel.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Matthew Helsley <mhelsley@vmware.com>,
"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
David Woodhouse <dwmw2@infradead.org>,
Paolo Bonzini <pbonzini@redhat.com>,
Josh Poimboeuf <jpoimboe@redhat.com>,
Jason Baron <jbaron@akamai.com>, Jiri Kosina <jkosina@suse.cz>,
Andrew Lutomirski <luto@kernel.org>
Subject: Re: [POC][RFC][PATCH 1/2] jump_function: Addition of new feature "jump_function"
Date: Mon, 8 Oct 2018 19:30:23 +0200 [thread overview]
Message-ID: <CAKv+Gu-08i6QEahyYhBtCBmpOYNuxirgdsgGvRw+Y0DX3+DVNQ@mail.gmail.com> (raw)
In-Reply-To: <CALCETrWuGh=1n2bEE9B0eeyzvnaD4y_Sx6MB+r9B5aFXzg8qBw@mail.gmail.com>
On 8 October 2018 at 19:25, Andy Lutomirski <luto@amacapital.net> wrote:
> On Mon, Oct 8, 2018 at 9:40 AM Peter Zijlstra <peterz@infradead.org> wrote:
>>
>> On Mon, Oct 08, 2018 at 09:29:56AM -0700, Andy Lutomirski wrote:
>> >
>> >
>> > > On Oct 8, 2018, at 8:57 AM, Peter Zijlstra <peterz@infradead.org> wrote:
>> > >
>> > > On Mon, Oct 08, 2018 at 01:33:14AM -0700, Andy Lutomirski wrote:
>> > >>> Can't we hijack the relocation records for these functions before they
>> > >>> get thrown out in the (final) link pass or something?
>> > >>
>> > >> I could be talking out my arse here, but I thought we could do this,
>> > >> too, then changed my mind. The relocation records give us the
>> > >> location of the call or jump operand, but they don’t give the address
>> > >> of the beginning of the instruction.
>> > >
>> > > But that's like 1 byte before the operand, right? We could even double check
>> > > this by reading back that byte and ensuring it is in fact 0xE8 (CALL).
>> > >
>> > > AFAICT there is only the _1_ CALL encoding, and that is the 5 byte: E8 <PLT32>,
>> > > so if we have the PLT32 location, we also have the instruction location. Or am
>> > > I missing something?
>> >
>> > There’s also JMP and Jcc, any of which can be used for rail calls, but
>> > those are also one byte. I suppose GCC is unlikely to emit a prefixed
>> > form of any of these. So maybe we really can assume they’re all one
>> > byte.
>>
>> Oh, I had not considered tail calls..
>>
>> > But there is a nasty potential special case: anything that takes the
>> > function’s address. This includes jump tables, computed gotos, and
>> > plain old function pointers. And I suspect that any of these could
>> > have one of the rather large number of CALL/JMP/Jcc bytes before the
>> > relocation by coincidence.
>>
>> We can have objtool verify the CALL/JMP/Jcc only condition. So if
>> someone tries to take the address of a patchable function, it will error
>> out.
>
> I think we should just ignore the sites that take the address and
> maybe issue a warning. After all, GCC can create them all by itself.
> We'll always have a plain wrapper function, and I think we should just
> not patch code that takes its address. So we do, roughly:
>
> void default_foo(void);
>
> GLOBAL(foo)
> jmp *current_foo(%rip)
> ENDPROC(foo)
>
> And code that does:
>
> foo();
>
> as a call, a tail call, a conditional tail call, etc, gets discovered
> by objtool + relocation processing or whatever and gets patched. (And
> foo() itself gets patched, too, as a special case. But we patch foo
> itself at some point during boot to turn it into a direct JMP. Doing
> it this way means that the whole mechanism works from very early
> boot.)
Does that mean that architectures could opt out of doing the whole
objtool + relocation processing thing, and instead take the hit of
going through the trampoline for all calls?
> And anything awful like:
>
> switch(whatever) {
> case 0:
> foo();
> };
>
> that gets translated to a jump table and gets optimized such that it
> jumps straight to foo just gets left alone, since it still works.
> It's just a bit suboptimial. Similarly, code that does:
>
> void (*ptr)(void);
> ptr = foo;
>
> gets a bona fide pointer to foo(), and any calls through the pointer
> land on foo() and jump to the current selected foo with only a single
> indirect branch / retpoline.
>
> Does this seem reasonable? Is there a reason we should make it more
> restrictive?
next prev parent reply other threads:[~2018-10-08 17:30 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-06 1:51 [POC][RFC][PATCH 0/2] PROOF OF CONCEPT: Dynamic Functions (jump functions) Steven Rostedt
2018-10-06 1:51 ` [POC][RFC][PATCH 1/2] jump_function: Addition of new feature "jump_function" Steven Rostedt
2018-10-06 2:00 ` Steven Rostedt
2018-10-06 2:02 ` Steven Rostedt
2018-10-06 2:03 ` Steven Rostedt
2018-10-06 15:15 ` Steven Rostedt
2018-10-06 12:12 ` Peter Zijlstra
2018-10-06 13:39 ` Steven Rostedt
2018-10-06 15:13 ` Andy Lutomirski
2018-10-06 15:16 ` Steven Rostedt
2018-10-08 7:21 ` Peter Zijlstra
2018-10-08 8:33 ` Andy Lutomirski
2018-10-08 15:57 ` Peter Zijlstra
2018-10-08 16:29 ` Andy Lutomirski
2018-10-08 16:39 ` Steven Rostedt
2018-10-08 16:39 ` Peter Zijlstra
2018-10-08 17:25 ` Andy Lutomirski
2018-10-08 17:30 ` Ard Biesheuvel [this message]
2018-10-08 17:42 ` Andy Lutomirski
2018-10-08 17:44 ` Jiri Kosina
2018-10-08 17:45 ` Ard Biesheuvel
2018-10-08 17:47 ` Andy Lutomirski
2018-10-09 2:17 ` Josh Poimboeuf
2018-10-09 3:57 ` Steven Rostedt
2018-10-10 17:52 ` Josh Poimboeuf
2018-10-10 18:03 ` Andy Lutomirski
2018-10-10 18:16 ` Josh Poimboeuf
2018-10-10 18:17 ` Josh Poimboeuf
2018-10-10 21:13 ` Andy Lutomirski
2018-10-11 3:07 ` Josh Poimboeuf
2018-10-11 12:52 ` Josh Poimboeuf
2018-10-11 16:20 ` Andy Lutomirski
2018-10-10 18:33 ` Josh Poimboeuf
2018-10-10 18:56 ` Steven Rostedt
2018-10-10 20:16 ` Josh Poimboeuf
2018-10-10 20:57 ` Andy Lutomirski
2018-10-08 16:31 ` Steven Rostedt
2018-10-08 11:30 ` Ard Biesheuvel
2018-10-09 3:44 ` Masami Hiramatsu
2018-10-09 3:55 ` Steven Rostedt
2018-10-09 16:04 ` Masami Hiramatsu
2018-10-09 8:59 ` David Laight
2018-10-06 1:51 ` [POC][RFC][PATCH 2/2] tracepoints: Implement it with dynamic functions Steven Rostedt
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=CAKv+Gu-08i6QEahyYhBtCBmpOYNuxirgdsgGvRw+Y0DX3+DVNQ@mail.gmail.com \
--to=ard.biesheuvel@linaro.org \
--cc=akpm@linux-foundation.org \
--cc=dwmw2@infradead.org \
--cc=jbaron@akamai.com \
--cc=jkosina@suse.cz \
--cc=jpoimboe@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=luto@kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhelsley@vmware.com \
--cc=mhiramat@kernel.org \
--cc=mingo@kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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).