Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Fri, 9 Oct 2020 17:41:16 +0200
From:   Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To:     Juri Lelli <juri.lelli@redhat.com>
Cc:     tglx@linutronix.de, linux-rt-users@vger.kernel.org,
        linux-kernel@vger.kernel.org, bristot@redhat.com,
        williams@redhat.com, echaudro@redhat.com, atheurer@redhat.com
Subject: Re: [PATCH 5.9 RT] net: openvswitch: Fix using smp_processor_id() in
 preemptible code
Message-ID: <20201009154116.a4fcrrm7flxonidd@linutronix.de>
References: <20201009124759.592550-1-juri.lelli@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <20201009124759.592550-1-juri.lelli@redhat.com>
Precedence: bulk

On 2020-10-09 14:47:59 [+0200], Juri Lelli wrote:
> This happens because openvswitch/flow_table::flow_lookup() accesses
> per-cpu data while being preemptible (and migratable).
> 
> Fix it by adding get/put_cpu_light(), so that, even if preempted, the
> task executing this code is not migrated (operation is also guarded by
> ovs_mutex mutex).

This warning is not limited to PREEMPT_RT it also present upstream since
commit
   eac87c413bf97 ("net: openvswitch: reorder masks array based on usage")

You should be able to reproduce it there, too.
The path ovs_flow_tbl_lookup() -> flow_lookup() is guarded by ovs_lock()
I can't say that this true for
   ovs_vport_receive() -> ovs_dp_process_packet() ->
   ovs_flow_tbl_lookup_stats() -> flow_lookup()

(means I don't know but it looks like coming from NAPI).

Which means u64_stats_update_begin() could have two writers. This must
not happen.
There are two reader which do u64_stats_fetch_begin_irq(). Disabling
interrupts makes no sense since they perform cross-CPU access.

-> You need to ensure that there is only one writer at a time.

If mask_array gains a spinlock_t for writer protection then you can
acquire the lock prio grabbing ->masks_usage_cntr. But as of now there
is one `ma->syncp'.

Sebastian