linux-kernel - BPF tracing trampoline synchronization between update/freeing and execution?

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAG48ez2gDDRtKaOcGdKLREd7RGtVzCypXiBMHBguOGSpxQFk3w@mail.gmail.com>
Date:   Mon, 6 Jan 2020 17:39:30 +0100
From:   Jann Horn <jannh@...gle.com>
To:     bpf@...r.kernel.org, live-patching@...r.kernel.org,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Steven Rostedt <rostedt@...dmis.org>
Cc:     KP Singh <kpsingh@...omium.org>,
        Andy Lutomirski <luto@...capital.net>,
        kernel list <linux-kernel@...r.kernel.org>,
        "the arch/x86 maintainers" <x86@...nel.org>,
        Josh Poimboeuf <jpoimboe@...hat.com>,
        Ingo Molnar <mingo@...hat.com>
Subject: BPF tracing trampoline synchronization between update/freeing and execution?

Hi!

I was chatting with kpsingh about BPF trampolines, and I noticed that
it looks like BPF trampolines (as of current bpf-next/master) seem to
be missing synchronization between trampoline code updates and
trampoline execution. Or maybe I'm missing something?

If I understand correctly, trampolines are executed directly from the
fentry placeholders at the start of arbitrary kernel functions, so
they can run without any locks held. So for example, if task A starts
executing a trampoline on entry to sys_open(), then gets preempted in
the middle of the trampoline, and then task B quickly calls
BPF_RAW_TRACEPOINT_OPEN twice, and then task A continues execution,
task A will end up executing the middle of newly-written machine code,
which can probably end up crashing the kernel somehow?

I think that at least to synchronize trampoline text freeing with
concurrent trampoline execution, it is necessary to do something
similar to what the livepatching code does with klp_check_stack(), and
then either use a callback from the scheduler to periodically re-check
tasks that were in the trampoline or let the trampoline tail-call into
a cleanup helper that is part of normal kernel text. And you'd
probably have to gate BPF trampolines on
CONFIG_HAVE_RELIABLE_STACKTRACE.

[Trampoline *updates* could probably be handled more easily if a
trampoline consisted of an immutable header that increments something
like a percpu refcount followed by a mutable body, but given that that
doesn't solve freeing trampolines, I'm not sure if it'd be worth the
effort. Unless you just never free trampoline memory, but that's
probably not a great idea.]