DPDK patches and discussions
 help / color / mirror / Atom feed
From: Akhil Goyal <gakhil@marvell.com>
To: Kai Ji <kai.ji@intel.com>, "dev@dpdk.org" <dev@dpdk.org>,
	Stephen Hemminger <stephen@networkplumber.org>,
	"NBU-Contact-Thomas Monjalon (EXTERNAL)" <thomas@monjalon.net>,
	Bruce Richardson <bruce.richardson@intel.com>,
	David Marchand <david.marchand@redhat.com>
Cc: "stable@dpdk.org" <stable@dpdk.org>,
	Pablo de Lara <pablo.de.lara.guarch@intel.com>,
	Fan Zhang <fanzhang.oss@gmail.com>
Subject: RE: [EXTERNAL] [dpdk-dev v1] cryptodev: introduce constant-time memory comparison
Date: Thu, 25 Sep 2025 10:33:52 +0000	[thread overview]
Message-ID: <CO6PR18MB4484264974305D4A6B065A76D81FA@CO6PR18MB4484.namprd18.prod.outlook.com> (raw)
In-Reply-To: <20250925102223.145471-1-kai.ji@intel.com>

> Add rte_consttime_memcmp() to prevent timing attacks in cryptographic
> digest verification operations.
> 
> Replace memcmp() with rte_consttime_memcmp() in cryptographic
> authentication verification operations across multiple crypto drivers:
> 
> * ipsec_mb
> * scheduler
> 
> Note: OpenSSL crypto driver already uses CRYPTO_memcmp() which
> provides equivalent timing attack resistance and is left unchanged.
> 
> Bugzilla ID: 1773
> Cc: stable@dpdk.org
> 
> [0] https://bugs.dpdk.org/show_bug.cgi?id=1773
> 
> Signed-off-by: Kai Ji <kai.ji@intel.com>


> diff --git a/lib/cryptodev/rte_cryptodev.h b/lib/cryptodev/rte_cryptodev.h
> index eaf0e50d37..77f10fbf88 100644
> --- a/lib/cryptodev/rte_cryptodev.h
> +++ b/lib/cryptodev/rte_cryptodev.h
> @@ -78,6 +78,29 @@ extern int rte_cryptodev_logtype;
>  #define rte_crypto_op_ctophys_offset(c, o)	\
>  	(rte_iova_t)((c)->phys_addr + (o))
> 
> +/**
> + * Constant-time memory comparison for cryptographic use.
> + * Returns 0 if the memory regions are equal, nonzero otherwise.
> + * Runs in constant time with respect to the length to prevent timing attacks.
> + *
> + * @param a
> + *   Pointer to the first memory region.
> + * @param b
> + *   Pointer to the second memory region.
> + * @param n
> + *   Number of bytes to compare.
> + * @return
> + *   0 if memory regions are equal, nonzero otherwise.
> + */
> +#define rte_consttime_memcmp(a, b, n) __extension__ ({ \
> +	const volatile uint8_t *__pa = (const volatile uint8_t *)(a); \
> +	const volatile uint8_t *__pb = (const volatile uint8_t *)(b); \
> +	uint8_t __result = 0; \
> +	for (size_t __i = 0; __i < (n); __i++) \
> +		__result |= __pa[__i] ^ __pb[__i]; \
> +	__result; \
> +})
> +
>  /**
>   * Crypto parameters range description
>   */

I believe this is not the right place to add this define. It should be somewhere in common eal if it is already not there.

++ Thomas, Stephen, Bruce, David.

  reply	other threads:[~2025-09-25 10:33 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-25 10:22 Kai Ji
2025-09-25 10:33 ` Akhil Goyal [this message]
2025-09-25 20:47   ` [EXTERNAL] " Thomas Monjalon
2025-09-26  7:55     ` Bruce Richardson
2025-09-26  7:58       ` Bruce Richardson
2025-09-26 12:34       ` Morten Brørup
2025-09-26  8:13     ` Konstantin Ananyev
2025-09-26  8:16       ` Konstantin Ananyev
2025-09-26 15:49 ` [dpdk-dev v2 1/2] eal: Add rte_consttime_memsq() to prevent timing attacks memcmp Kai Ji
2025-09-26 15:49   ` [dpdk-dev v2 2/2] crypto/ipsec-mb: use constant-time memory comparison Kai Ji
2025-09-26 16:02   ` [dpdk-dev v3 1/2] eal: Add rte_consttime_memneq() to prevent timing attacks memcmp Kai Ji
2025-09-26 16:02     ` [dpdk-dev v3 2/2] crypto/ipsec-mb: use constant-time memory comparison Kai Ji
2025-09-26 18:12     ` [dpdk-dev v3 1/2] eal: Add rte_consttime_memneq() to prevent timing attacks memcmp Stephen Hemminger
2025-09-26 19:17     ` Morten Brørup
2025-09-26 20:15       ` Stephen Hemminger
2025-09-26 18:07   ` [dpdk-dev v2 1/2] eal: Add rte_consttime_memsq() " Stephen Hemminger

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CO6PR18MB4484264974305D4A6B065A76D81FA@CO6PR18MB4484.namprd18.prod.outlook.com \
    --to=gakhil@marvell.com \
    --cc=bruce.richardson@intel.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=fanzhang.oss@gmail.com \
    --cc=kai.ji@intel.com \
    --cc=pablo.de.lara.guarch@intel.com \
    --cc=stable@dpdk.org \
    --cc=stephen@networkplumber.org \
    --cc=thomas@monjalon.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).