[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAG48ez2DkjrvmP57JvbC+4ee0qCXCEXEyYuA4YApWGX_k29y_w@mail.gmail.com>
Date: Tue, 28 Aug 2018 01:12:11 +0200
From: Jann Horn <jannh@...gle.com>
To: Andy Lutomirski <luto@...nel.org>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>
Cc: "the arch/x86 maintainers" <x86@...nel.org>,
Borislav Petkov <bp@...en8.de>,
Rik van Riel <riel@...riel.com>,
kernel list <linux-kernel@...r.kernel.org>,
stable@...r.kernel.org, Peter Zijlstra <peterz@...radead.org>,
Nadav Amit <nadav.amit@...il.com>
Subject: Re: [PATCH] x86/nmi: Fix some races in NMI uaccess
On Tue, Aug 28, 2018 at 1:04 AM Andy Lutomirski <luto@...nel.org> wrote:
>
> In NMI context, we might be in the middle of context switching or in
> the middle of switch_mm_irqs_off(). In either case, CR3 might not
> match current->mm, which could cause copy_from_user_nmi() and
> friends to read the wrong memory.
>
> Fix it by adding a new nmi_uaccess_okay() helper and checking it in
> copy_from_user_nmi() and in __copy_from_user_nmi()'s callers.
What about eBPF probes (which I think can be attached to kprobe points
/ tracepoints / perf events) that perform userspace reads / userspace
writes / kernel reads? Can those run in NMI context, and if so, do
they also need special handling?
Powered by blists - more mailing lists