Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) client-ip=2620:137:e000::3:8;
Message-ID: <90de4882-7683-4c7b-95bc-a5eb363912a2@arista.com>
Date:   Mon, 27 Nov 2023 14:42:35 +0000
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v2 6/7] net/tcp: Add sne_lock to access SNEs
Content-Language: en-US
To:     Paolo Abeni <pabeni@redhat.com>
Cc:     linux-kernel@vger.kernel.org,
        Dmitry Safonov <0x7f454c46@gmail.com>,
        Francesco Ruggeri <fruggeri05@gmail.com>,
        Salam Noureddine <noureddine@arista.com>,
        Simon Horman <horms@kernel.org>, netdev@vger.kernel.org,
        David Ahern <dsahern@kernel.org>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        "David S. Miller" <davem@davemloft.net>
References: <20231124002720.102537-1-dima@arista.com>
 <20231124002720.102537-7-dima@arista.com>
 <1c769b1a72c5a7f6e19010dfccc78b2502484cf3.camel@redhat.com>
From:   Dmitry Safonov <dima@arista.com>
In-Reply-To: <1c769b1a72c5a7f6e19010dfccc78b2502484cf3.camel@redhat.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 11/27/23 11:41, Paolo Abeni wrote:
> On Fri, 2023-11-24 at 00:27 +0000, Dmitry Safonov wrote:
>> RFC 5925 (6.2):
>>> TCP-AO emulates a 64-bit sequence number space by inferring when to
>>> increment the high-order 32-bit portion (the SNE) based on
>>> transitions in the low-order portion (the TCP sequence number).
>>
>> snd_sne and rcv_sne are the upper 4 bytes of extended SEQ number.
>> Unfortunately, reading two 4-bytes pointers can't be performed
>> atomically (without synchronization).
>>
>> Let's keep it KISS and add an rwlock - that shouldn't create much
>> contention as SNE are updated every 4Gb of traffic and the atomic region
>> is quite small.
>>
>> Fixes: 64382c71a557 ("net/tcp: Add TCP-AO SNE support")
>> Signed-off-by: Dmitry Safonov <dima@arista.com>
>> ---
>>  include/net/tcp_ao.h |  2 +-
>>  net/ipv4/tcp_ao.c    | 34 +++++++++++++++++++++-------------
>>  net/ipv4/tcp_input.c | 16 ++++++++++++++--
>>  3 files changed, 36 insertions(+), 16 deletions(-)
>>
>> diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
>> index 647781080613..beea3e6b39e2 100644
>> --- a/include/net/tcp_ao.h
>> +++ b/include/net/tcp_ao.h
>> @@ -123,6 +123,7 @@ struct tcp_ao_info {
>>  	 */
>>  	u32			snd_sne;
>>  	u32			rcv_sne;
>> +	rwlock_t		sne_lock;
> 
> RW lock are problematic in the networking code, see commit
> dbca1596bbb08318f5e3b3b99f8ca0a0d3830a65.

Thanks, was not aware of this pitfall.

> I think you can use a plain spinlock here, as both read and write
> appears to be in the fastpath (?!?)

Yeah, I wanted to avoid to RX concurrency here as writing happens only
once in 4Gb. I'll take another attempt to prevent that in v3.

>> @@ -781,8 +780,10 @@ int tcp_ao_prepare_reset(const struct sock *sk, struct sk_buff *skb,
>>  		*traffic_key = snd_other_key(*key);
>>  		rnext_key = READ_ONCE(ao_info->rnext_key);
>>  		*keyid = rnext_key->rcvid;
>> -		*sne = tcp_ao_compute_sne(READ_ONCE(ao_info->snd_sne),
>> -					  snd_basis, seq);
>> +		read_lock_irqsave(&ao_info->sne_lock, flags);
>> +		*sne = tcp_ao_compute_sne(ao_info->snd_sne,
>> +					  READ_ONCE(*snd_basis), seq);
>> +		read_unlock_irqrestore(&ao_info->sne_lock, flags);
> 
> Why are you using the irqsave variant? bh should suffice.

It should, yes :)

> 
> Cheers,
> 
> Paolo
> 

Thanks,
             Dmitry