netdev - Re: [PATCH v4 bpf-next 1/9] bpf: introduce bpf_spin

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: <20190125083846.GJ17749@hirez.programming.kicks-ass.net>
Date:   Fri, 25 Jan 2019 09:38:46 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Alexei Starovoitov <alexei.starovoitov@...il.com>
Cc:     Eric Dumazet <eric.dumazet@...il.com>,
        Alexei Starovoitov <ast@...nel.org>, davem@...emloft.net,
        daniel@...earbox.net, jakub.kicinski@...ronome.com,
        netdev@...r.kernel.org, kernel-team@...com, mingo@...hat.com,
        will.deacon@....com, Paul McKenney <paulmck@...ux.vnet.ibm.com>,
        jannh@...gle.com
Subject: Re: [PATCH v4 bpf-next 1/9] bpf: introduce bpf_spin_lock

On Thu, Jan 24, 2019 at 06:57:00PM -0800, Alexei Starovoitov wrote:
> On Thu, Jan 24, 2019 at 06:44:20PM -0800, Eric Dumazet wrote:
> > Let see if we understood this well.
> > 
> > 1. create perf event PERF_TYPE_HARDWARE:PERF_COUNT_HW_CPU_CYCLES
> > 2. attach bpf probram to this event 
> > 3. since that's a hw event, the bpf program is executed in NMI context
> > 4. the bpf program calls bpf_get_stackid to record the trace in a bpf map
> > 5. bpf_get_stackid calls pcpu_freelist_pop and pcpu_freelist_push from NMI

How is this not a straight up bug? NMI code should not ever call code
that uses spinlocks.

> > 6. userspace calls sys_bpf(bpf_map_lookup_elem) which calls bpf_stackmap_copy which can call pcpu_freelist_push
> 
> argh. lookup cmd is missing __this_cpu_inc(bpf_prog_active); like update/delete do.
> Will fix.
> 
> > It seems pcpu_freelist_pop and pcpu_freelist_push are not NMI safe,
> > so what prevents bad things to happen ?
> 
> nmi checks for bpf_prog_active==0. See bpf_overflow_handler.

yuck yuck yuck.. That's horrific :-( That means the whole BPF crud is
unreliable and events can go randomly missing.