[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <255b4de132365501c6e1e97246c30d9729860546.camel@microchip.com>
Date: Thu, 15 Jun 2023 12:45:46 +0200
From: Steen Hegelund <steen.hegelund@...rochip.com>
To: Dmitry Safonov <dima@...sta.com>, David Ahern <dsahern@...nel.org>,
"Eric Dumazet" <edumazet@...gle.com>,
Paolo Abeni <pabeni@...hat.com>,
"Jakub Kicinski" <kuba@...nel.org>,
"David S. Miller" <davem@...emloft.net>
CC: <linux-kernel@...r.kernel.org>,
Andy Lutomirski <luto@...capital.net>,
"Ard Biesheuvel" <ardb@...nel.org>,
Bob Gilligan <gilligan@...sta.com>,
"Dan Carpenter" <error27@...il.com>,
David Laight <David.Laight@...lab.com>,
Dmitry Safonov <0x7f454c46@...il.com>,
Donald Cassidy <dcassidy@...hat.com>,
Eric Biggers <ebiggers@...nel.org>,
"Eric W. Biederman" <ebiederm@...ssion.com>,
Francesco Ruggeri <fruggeri05@...il.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
"Hideaki YOSHIFUJI" <yoshfuji@...ux-ipv6.org>,
Ivan Delalande <colona@...sta.com>,
Leonard Crestez <cdleonard@...il.com>,
Salam Noureddine <noureddine@...sta.com>,
<netdev@...r.kernel.org>
Subject: Re: [PATCH v7 01/22] net/tcp: Prepare tcp_md5sig_pool for TCP-AO
Hi Dmitry,
On Thu, 2023-06-15 at 00:09 +0100, Dmitry Safonov wrote:
> EXTERNAL EMAIL: Do not click links or open attachments unless you know the
> content is safe
>
> TCP-AO, similarly to TCP-MD5, needs to allocate tfms on a slow-path,
> which is setsockopt() and use crypto ahash requests on fast paths,
> which are RX/TX softirqs. Also, it needs a temporary/scratch buffer
> for preparing the hash.
>
> Rework tcp_md5sig_pool in order to support other hashing algorithms
> than MD5. It will make it possible to share pre-allocated crypto_ahash
> descriptors and scratch area between all TCP hash users.
>
> Internally tcp_sigpool calls crypto_clone_ahash() API over pre-allocated
> crypto ahash tfm. Kudos to Herbert, who provided this new crypto API.
>
> I was a little concerned over GFP_ATOMIC allocations of ahash and
> crypto_request in RX/TX (see tcp_sigpool_start()), so I benchmarked both
> "backends" with different algorithms, using patched version of iperf3[2].
> On my laptop with i7-7600U @ 2.80GHz:
>
... snip ...
> +/**
> + * tcp_sigpool_alloc_ahash - allocates pool for ahash requests
> + * @alg: name of async hash algorithm
> + * @scratch_size: reserve a tcp_sigpool::scratch buffer of this size
> + */
> +int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size)
> +{
> + int i, ret;
> +
> + /* slow-path */
> + mutex_lock(&cpool_mutex);
> + ret = sigpool_reserve_scratch(scratch_size);
> + if (ret)
> + goto out;
> + for (i = 0; i < cpool_populated; i++) {
> + if (!cpool[i].alg)
> + continue;
> + if (strcmp(cpool[i].alg, alg))
> + continue;
> +
> + if (kref_read(&cpool[i].kref) > 0)
> + kref_get(&cpool[i].kref);
> + else
> + kref_init(&cpool[i].kref);
> + ret = i;
> + goto out;
> + }
Here it looks to me like you will never get to this part of the code since you
always end up going to the out label in the previous loop.
> +
> + for (i = 0; i < cpool_populated; i++) {
> + if (!cpool[i].alg)
> + break;
> + }
> + if (i >= CPOOL_SIZE) {
> + ret = -ENOSPC;
> + goto out;
> + }
> +
> + ret = __cpool_alloc_ahash(&cpool[i], alg);
> + if (!ret) {
> + ret = i;
> + if (i == cpool_populated)
> + cpool_populated++;
> + }
> +out:
> + mutex_unlock(&cpool_mutex);
> + return ret;
> +}
> +EXPORT_SYMBOL_GPL(tcp_sigpool_alloc_ahash);
> +
... snip ...
> clear_hash:
> - tcp_put_md5sig_pool();
> -clear_hash_noput:
> + tcp_sigpool_end(&hp);
> +clear_hash_nostart:
> memset(md5_hash, 0, 16);
> return 1;
> }
> --
> 2.40.0
>
>
BR
Steen
Powered by blists - more mailing lists