Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Content-Type: text/plain;
        charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3731.200.110.1.12\))
Subject: Re: BUG: unable to handle kernel paging request in bpf_dispatcher_xdp
From:   Hao Sun <sunhao.th@gmail.com>
In-Reply-To: <Y5dDArARol3gfVNf@krava>
Date:   Tue, 13 Dec 2022 10:26:13 +0800
Cc:     Alexei Starovoitov <alexei.starovoitov@gmail.com>,
        Jakub Kicinski <kuba@kernel.org>,
        "Paul E. McKenney" <paulmck@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Yonghong Song <yhs@meta.com>, Song Liu <song@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        bpf <bpf@vger.kernel.org>, Alexei Starovoitov <ast@kernel.org>,
        John Fastabend <john.fastabend@gmail.com>,
        Andrii Nakryiko <andrii@kernel.org>,
        Martin KaFai Lau <martin.lau@linux.dev>,
        Yonghong Song <yhs@fb.com>, KP Singh <kpsingh@kernel.org>,
        Stanislav Fomichev <sdf@google.com>,
        Hao Luo <haoluo@google.com>,
        David Miller <davem@davemloft.net>,
        Jesper Dangaard Brouer <hawk@kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        netdev <netdev@vger.kernel.org>,
        Thorsten Leemhuis <regressions@leemhuis.info>
Content-Transfer-Encoding: quoted-printable
Message-Id: <0B62D35A-E695-4B7A-A0D4-774767544C1A@gmail.com>
References: <Y5NSStSi7h9Vdo/j@krava>
 <5c9d77bf-75f5-954a-c691-39869bb22127@meta.com> <Y5OuQNmkoIvcV6IL@krava>
 <ee2a087e-b8c5-fc3e-a114-232490a6c3be@iogearbox.net> <Y5O/yxcjQLq5oDAv@krava>
 <96b0d9d8-02a7-ce70-de1e-b275a01f5ff3@iogearbox.net>
 <20221209153445.22182ca5@kernel.org> <Y5PNeFYJrC6D4P9p@krava>
 <CAADnVQKr9NYektHFq2sUKMxxXJVFHcMPWh=pKa08b-yM9cgAAQ@mail.gmail.com>
 <Y5SFho7ZYXr9ifRn@krava> <Y5dDArARol3gfVNf@krava>
To:     Jiri Olsa <olsajiri@gmail.com>
Precedence: bulk


> On 12 Dec 2022, at 11:04 PM, Jiri Olsa <olsajiri@gmail.com> wrote:
>=20
> On Sat, Dec 10, 2022 at 02:11:34PM +0100, Jiri Olsa wrote:
>> On Fri, Dec 09, 2022 at 05:12:03PM -0800, Alexei Starovoitov wrote:
>>> On Fri, Dec 9, 2022 at 4:06 PM Jiri Olsa <olsajiri@gmail.com> wrote:
>>>>=20
>>>> On Fri, Dec 09, 2022 at 03:34:45PM -0800, Jakub Kicinski wrote:
>>>>> On Sat, 10 Dec 2022 00:32:07 +0100 Daniel Borkmann wrote:
>>>>>> fwiw, these should not be necessary, =
Documentation/RCU/checklist.rst :
>>>>>>=20
>>>>>>   [...] One example of non-obvious pairing is the XDP feature in =
networking,
>>>>>>   which calls BPF programs from network-driver NAPI (softirq) =
context. BPF
>>>>>>   relies heavily on RCU protection for its data structures, but =
because the
>>>>>>   BPF program invocation happens entirely within a single =
local_bh_disable()
>>>>>>   section in a NAPI poll cycle, this usage is safe. The reason =
that this usage
>>>>>>   is safe is that readers can use anything that disables BH when =
updaters use
>>>>>>   call_rcu() or synchronize_rcu(). [...]
>>>>>=20
>>>>> FWIW I sent a link to the thread to Paul and he confirmed
>>>>> the RCU will wait for just the BH.
>>>>=20
>>>> so IIUC we can omit the rcu_read_lock/unlock on bpf_prog_run_xdp =
side
>>>>=20
>>>> Paul,
>>>> any thoughts on what we can use in here to synchronize =
bpf_dispatcher_change_prog
>>>> with bpf_prog_run_xdp callers?
>>>>=20
>>>> with synchronize_rcu_tasks I'm getting splats like:
>>>>  =
https://lore.kernel.org/bpf/20221209153445.22182ca5@kernel.org/T/#m0a869f9=
3404a2744884d922bc96d497ffe8f579f
>>>>=20
>>>> synchronize_rcu_tasks_rude seems to work (patch below), but it also =
sounds special ;-)
>>>=20
>>> Jiri,
>>>=20
>>> I haven't tried to repro this yet, but I feel you're on
>>> the wrong path here. The splat has this:
>>> ? bpf_prog_run_xdp include/linux/filter.h:775 [inline]
>>> ? bpf_test_run+0x2ce/0x990 net/bpf/test_run.c:400
>>> that test_run logic takes rcu_read_lock.
>>> See bpf_test_timer_enter.
>>> I suspect the addition of synchronize_rcu_tasks_rude
>>> only slows down the race.
>>> The synchronize_rcu_tasks_trace also behaves like synchronize_rcu.
>>> See our new and fancy rcu_trace_implies_rcu_gp(),
>>> but I'm not sure it applies to synchronize_rcu_tasks_rude.
>>> Have you tried with just synchronize_rcu() ?
>>> If your theory about the race is correct then
>>> the vanila sync_rcu should help.
>>> If not, the issue is some place else.
>>=20
>> synchronize_rcu seems to work as well, I'll keep the test
>> running for some time
>=20
> looks good, Hao Sun, could you please test change below?

Hi,

Tested on a latest bpf-next build. The reproducer would trigger
the Oops in 5 mins without the patch. After applying the patch,
the reproducer cannot trigger any issue for more than 15 mins.
Seems working, tested on:

HEAD commit: ef3911a3e4d6 docs/bpf: Reword docs for =
BPF_MAP_TYPE_SK_STORAGE
git tree: bpf-next
kernel config: https://pastebin.com/raw/rZdWLcgK
C reproducer: https://pastebin.com/raw/GFfDn2Gk

>=20
> ---
> diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
> index c19719f48ce0..4b0fa5b98137 100644
> --- a/kernel/bpf/dispatcher.c
> +++ b/kernel/bpf/dispatcher.c
> @@ -124,6 +124,7 @@ static void bpf_dispatcher_update(struct =
bpf_dispatcher *d, int prev_num_progs)
> }
>=20
> __BPF_DISPATCHER_UPDATE(d, new ?: (void *)&bpf_dispatcher_nop_func);
> + synchronize_rcu();
>=20
> if (new)
> d->image_off =3D noff;