linux-kernel - Re: [PATCH] s390: fix double free of GS and RI CBs on fork() failure

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

Message-ID: <YwXavKvCjHp9a84E@osiris>
Date:   Wed, 24 Aug 2022 10:01:00 +0200
From:   Heiko Carstens <hca@...ux.ibm.com>
To:     Brian Foster <bfoster@...hat.com>,
        Vasily Gorbik <gor@...ux.ibm.com>
Cc:     linux-s390@...r.kernel.org, linux-kernel@...r.kernel.org,
        geraldsc@...ibm.com
Subject: Re: [PATCH] s390: fix double free of GS and RI CBs on fork() failure

On Tue, Aug 16, 2022 at 11:54:07AM -0400, Brian Foster wrote:
> The pointers for guarded storage and runtime instrumentation control
> blocks are stored in the thread_struct of the associated task. These
> pointers are initially copied on fork() via arch_dup_task_struct()
> and then cleared via copy_thread() before fork() returns. If fork()
> happens to fail after the initial task dup and before copy_thread(),
> the newly allocated task and associated thread_struct memory are
> freed via free_task() -> arch_release_task_struct(). This results in
> a double free of the guarded storage and runtime info structs
> because the fields in the failed task still refer to memory
> associated with the source task.
> 
> This problem can manifest as a BUG_ON() in set_freepointer() (with
> CONFIG_SLAB_FREELIST_HARDENED enabled) or KASAN splat (if enabled)
> when running trinity syscall fuzz tests on s390x. To avoid this
> problem, clear the associated pointer fields in
> arch_dup_task_struct() immediately after the new task is copied.
> Note that the RI flag is still cleared in copy_thread() because it
> resides in thread stack memory and that is where stack info is
> copied.
> 
> Signed-off-by: Brian Foster <bfoster@...hat.com>
> ---
>  arch/s390/kernel/process.c | 22 ++++++++++++++++------
>  1 file changed, 16 insertions(+), 6 deletions(-)

Reviewed-by: Heiko Carstens <hca@...ux.ibm.com>

Thanks for debugging and fixing this!

Vasily, could you pick this one up, and also add the Fixes: and Cc:
stable tags as proposed by Gerald?
Thanks!