Received-SPF: pass (google.com: best guess record for domain of linux-crypto-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH v3] net: ipv4: move tcp_fastopen server side code to
 SipHash library
To:     Ard Biesheuvel <ard.biesheuvel@linaro.org>, netdev@vger.kernel.org
Cc:     linux-crypto@vger.kernel.org, herbert@gondor.apana.org.au,
        ebiggers@kernel.org, edumazet@google.com, davem@davemloft.net,
        kuznet@ms2.inr.ac.ru, yoshfuji@linux-ipv6.org, jbaron@akamai.com,
        cpaasch@apple.com, David.Laight@aculab.com, ycheng@google.com
References: <20190617080933.32152-1-ard.biesheuvel@linaro.org>
From:   Eric Dumazet <eric.dumazet@gmail.com>
Message-ID: <e1c4c9b6-3668-106a-69ef-7ef6c016a5f6@gmail.com>
Date:   Mon, 17 Jun 2019 10:00:28 -0700
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.7.0
MIME-Version: 1.0
In-Reply-To: <20190617080933.32152-1-ard.biesheuvel@linaro.org>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: linux-crypto-owner@vger.kernel.org
Precedence: bulk


On 6/17/19 1:09 AM, Ard Biesheuvel wrote:
> Using a bare block cipher in non-crypto code is almost always a bad idea,
> not only for security reasons (and we've seen some examples of this in
> the kernel in the past), but also for performance reasons.
> 
> In the TCP fastopen case, we call into the bare AES block cipher one or
> two times (depending on whether the connection is IPv4 or IPv6). On most
> systems, this results in a call chain such as
> 
>   crypto_cipher_encrypt_one(ctx, dst, src)
>     crypto_cipher_crt(tfm)->cit_encrypt_one(crypto_cipher_tfm(tfm), ...);
>       aesni_encrypt
>         kernel_fpu_begin();
>         aesni_enc(ctx, dst, src); // asm routine
>         kernel_fpu_end();
> 
> It is highly unlikely that the use of special AES instructions has a
> benefit in this case, especially since we are doing the above twice
> for IPv6 connections, instead of using a transform which can process
> the entire input in one go.
> 
> We could switch to the cbcmac(aes) shash, which would at least get
> rid of the duplicated overhead in *some* cases (i.e., today, only
> arm64 has an accelerated implementation of cbcmac(aes), while x86 will
> end up using the generic cbcmac template wrapping the AES-NI cipher,
> which basically ends up doing exactly the above). However, in the given
> context, it makes more sense to use a light-weight MAC algorithm that
> is more suitable for the purpose at hand, such as SipHash.
> 
> Since the output size of SipHash already matches our chosen value for
> TCP_FASTOPEN_COOKIE_SIZE, and given that it accepts arbitrary input
> sizes, this greatly simplifies the code as well.
> 
> NOTE: Server farms backing a single server IP for load balancing purposes
>       and sharing a single fastopen key will be adversely affected by
>       this change unless all systems in the pool receive their kernel
>       upgrades at the same time.
> 
> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> ---

All our fastopen packetdrill tests pass (after I changed all the cookie values in them)

Signed-off-by: Eric Dumazet <edumazet@google.com>