linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Eric Biggers <ebiggers@kernel.org>
To: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: "open list:HARDWARE RANDOM NUMBER GENERATOR CORE" 
	<linux-crypto@vger.kernel.org>,
	linux-fscrypt@vger.kernel.org,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	Paul Crowley <paulcrowley@google.com>,
	Greg Kaiser <gkaiser@google.com>,
	Michael Halcrow <mhalcrow@google.com>,
	"Jason A . Donenfeld" <Jason@zx2c4.com>,
	Samuel Neves <samuel.c.p.neves@gmail.com>,
	Tomer Ashur <tomer.ashur@esat.kuleuven.be>
Subject: Re: [RFC PATCH v2 09/12] crypto: nhpoly1305 - add NHPoly1305 support
Date: Mon, 22 Oct 2018 11:42:37 -0700	[thread overview]
Message-ID: <20181022184236.GA59695@gmail.com> (raw)
In-Reply-To: <CAKv+Gu-A_EhMBXq_nqzBzpgN36foo6hA3Ba3=j+WVM-jph=mrw@mail.gmail.com>

On Sat, Oct 20, 2018 at 11:06:00PM +0800, Ard Biesheuvel wrote:
> >> > +
> >> > +#define NH_STRIDE(K0, K1, K2, K3)                              \
> >> > +({                                                             \
> >> > +       m_A = get_unaligned_le32(src); src += 4;                \
> >> > +       m_B = get_unaligned_le32(src); src += 4;                \
> >> > +       m_C = get_unaligned_le32(src); src += 4;                \
> >> > +       m_D = get_unaligned_le32(src); src += 4;                \
> >> > +       K3##_A = *key++;                                        \
> >> > +       K3##_B = *key++;                                        \
> >> > +       K3##_C = *key++;                                        \
> >> > +       K3##_D = *key++;                                        \
> >> > +       sum0 += (u64)(u32)(m_A + K0##_A) * (u32)(m_C + K0##_C); \
> >> > +       sum1 += (u64)(u32)(m_A + K1##_A) * (u32)(m_C + K1##_C); \
> >> > +       sum2 += (u64)(u32)(m_A + K2##_A) * (u32)(m_C + K2##_C); \
> >> > +       sum3 += (u64)(u32)(m_A + K3##_A) * (u32)(m_C + K3##_C); \
> >> > +       sum0 += (u64)(u32)(m_B + K0##_B) * (u32)(m_D + K0##_D); \
> >> > +       sum1 += (u64)(u32)(m_B + K1##_B) * (u32)(m_D + K1##_D); \
> >> > +       sum2 += (u64)(u32)(m_B + K2##_B) * (u32)(m_D + K2##_D); \
> >> > +       sum3 += (u64)(u32)(m_B + K3##_B) * (u32)(m_D + K3##_D); \
> >> > +})
> >> > +
> >> > +static void nh_generic(const u32 *key, const u8 *src, size_t srclen,
> >> > +                      __le64 hash[NH_NUM_PASSES])
> >> > +{
> >> > +       u64 sum0 = 0, sum1 = 0, sum2 = 0, sum3 = 0;
> >> > +       u32 k0_A = *key++;
> >> > +       u32 k0_B = *key++;
> >> > +       u32 k0_C = *key++;
> >> > +       u32 k0_D = *key++;
> >> > +       u32 k1_A = *key++;
> >> > +       u32 k1_B = *key++;
> >> > +       u32 k1_C = *key++;
> >> > +       u32 k1_D = *key++;
> >> > +       u32 k2_A = *key++;
> >> > +       u32 k2_B = *key++;
> >> > +       u32 k2_C = *key++;
> >> > +       u32 k2_D = *key++;
> >> > +       u32 k3_A, k3_B, k3_C, k3_D;
> >> > +       u32 m_A, m_B, m_C, m_D;
> >> > +       size_t n = srclen / NH_MESSAGE_UNIT;
> >> > +
> >> > +       BUILD_BUG_ON(NH_PAIR_STRIDE != 2);
> >> > +       BUILD_BUG_ON(NH_NUM_PASSES != 4);
> >> > +
> >> > +       while (n >= 4) {
> >> > +               NH_STRIDE(k0, k1, k2, k3);
> >> > +               NH_STRIDE(k1, k2, k3, k0);
> >> > +               NH_STRIDE(k2, k3, k0, k1);
> >> > +               NH_STRIDE(k3, k0, k1, k2);
> >> > +               n -= 4;
> >> > +       }
> >> > +       if (n) {
> >> > +               NH_STRIDE(k0, k1, k2, k3);
> >> > +               if (--n) {
> >> > +                       NH_STRIDE(k1, k2, k3, k0);
> >> > +                       if (--n)
> >> > +                               NH_STRIDE(k2, k3, k0, k1);
> >> > +               }
> >> > +       }
> >> > +
> >>
> >> This all looks a bit clunky to me, with the macro, the *key++s in the
> >> initializers and these conditionals.
> >>
> >> Was it written in this particular way to get GCC to optimize it in the
> >> right way?
> >
> > This does get compiled into something much faster than a naive version, which
> > you can find commented out at
> > https://github.com/google/adiantum/blob/master/benchmark/src/nh.c#L14.
> >
> > Though, I admit that I haven't put a ton of effort into this C implementation of
> > NH yet.  Right now it's actually somewhat of a translation of the NEON version.
> > I'll do some experiments and see if it can be made into something less ugly
> > without losing performance.
> >
> 
> No that's fine but please document it.
> 

Hmm, I'm actually leaning towards the following instead.  Unrolling multiple
strides to try to reduce loads of the keys doesn't seem worthwhile in the C
implementation; for one, it bloats the code size a lot
(412 => 2332 bytes on arm32).

static void nh_generic(const u32 *key, const u8 *message, size_t message_len,
		       __le64 hash[NH_NUM_PASSES])
{
	u64 sums[4] = { 0, 0, 0, 0 };

	BUILD_BUG_ON(NH_PAIR_STRIDE != 2);
	BUILD_BUG_ON(NH_NUM_PASSES != 4);

	while (message_len) {
		u32 m0 = get_unaligned_le32(message + 0);
		u32 m1 = get_unaligned_le32(message + 4);
		u32 m2 = get_unaligned_le32(message + 8);
		u32 m3 = get_unaligned_le32(message + 12);

		sums[0] += (u64)(u32)(m0 + key[ 0]) * (u32)(m2 + key[ 2]);
		sums[1] += (u64)(u32)(m0 + key[ 4]) * (u32)(m2 + key[ 6]);
		sums[2] += (u64)(u32)(m0 + key[ 8]) * (u32)(m2 + key[10]);
		sums[3] += (u64)(u32)(m0 + key[12]) * (u32)(m2 + key[14]);
		sums[0] += (u64)(u32)(m1 + key[ 1]) * (u32)(m3 + key[ 3]);
		sums[1] += (u64)(u32)(m1 + key[ 5]) * (u32)(m3 + key[ 7]);
		sums[2] += (u64)(u32)(m1 + key[ 9]) * (u32)(m3 + key[11]);
		sums[3] += (u64)(u32)(m1 + key[13]) * (u32)(m3 + key[15]);
		key += NH_MESSAGE_UNIT / sizeof(key[0]);
		message += NH_MESSAGE_UNIT;
		message_len -= NH_MESSAGE_UNIT;
	}

	hash[0] = cpu_to_le64(sums[0]);
	hash[1] = cpu_to_le64(sums[1]);
	hash[2] = cpu_to_le64(sums[2]);
	hash[3] = cpu_to_le64(sums[3]);
}

  reply	other threads:[~2018-10-22 18:42 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-15 17:54 [RFC PATCH v2 00/12] crypto: Adiantum support Eric Biggers
2018-10-15 17:54 ` [RFC PATCH v2 01/12] crypto: chacha20-generic - add HChaCha20 library function Eric Biggers
2018-10-19 14:13   ` Ard Biesheuvel
2018-10-15 17:54 ` [RFC PATCH v2 02/12] crypto: chacha20-generic - add XChaCha20 support Eric Biggers
2018-10-19 14:24   ` Ard Biesheuvel
2018-10-15 17:54 ` [RFC PATCH v2 03/12] crypto: chacha20-generic - refactor to allow varying number of rounds Eric Biggers
2018-10-19 14:25   ` Ard Biesheuvel
2018-10-15 17:54 ` [RFC PATCH v2 04/12] crypto: chacha - add XChaCha12 support Eric Biggers
2018-10-19 14:34   ` Ard Biesheuvel
2018-10-19 18:28     ` Eric Biggers
2018-10-15 17:54 ` [RFC PATCH v2 05/12] crypto: arm/chacha20 - add XChaCha20 support Eric Biggers
2018-10-20  2:29   ` Ard Biesheuvel
2018-10-15 17:54 ` [RFC PATCH v2 06/12] crypto: arm/chacha20 - refactor to allow varying number of rounds Eric Biggers
2018-10-20  3:35   ` Ard Biesheuvel
2018-10-20  5:26     ` Eric Biggers
2018-10-15 17:54 ` [RFC PATCH v2 07/12] crypto: arm/chacha - add XChaCha12 support Eric Biggers
2018-10-20  3:36   ` Ard Biesheuvel
2018-10-15 17:54 ` [RFC PATCH v2 08/12] crypto: poly1305 - add Poly1305 core API Eric Biggers
2018-10-20  3:45   ` Ard Biesheuvel
2018-10-15 17:54 ` [RFC PATCH v2 09/12] crypto: nhpoly1305 - add NHPoly1305 support Eric Biggers
2018-10-20  4:00   ` Ard Biesheuvel
2018-10-20  5:38     ` Eric Biggers
2018-10-20 15:06       ` Ard Biesheuvel
2018-10-22 18:42         ` Eric Biggers [this message]
2018-10-22 22:25           ` Ard Biesheuvel
2018-10-22 22:40             ` Eric Biggers
2018-10-22 22:43               ` Ard Biesheuvel
2018-10-15 17:54 ` [RFC PATCH v2 10/12] crypto: arm/nhpoly1305 - add NEON-accelerated NHPoly1305 Eric Biggers
2018-10-20  4:12   ` Ard Biesheuvel
2018-10-20  5:51     ` Eric Biggers
2018-10-20 15:00       ` Ard Biesheuvel
2018-10-15 17:54 ` [RFC PATCH v2 11/12] crypto: adiantum - add Adiantum support Eric Biggers
2018-10-20  4:17   ` Ard Biesheuvel
2018-10-20  7:12     ` Eric Biggers
2018-10-23 10:40       ` Ard Biesheuvel
2018-10-24 22:06         ` Eric Biggers
2018-10-30  8:17           ` Herbert Xu
2018-10-15 17:54 ` [RFC PATCH v2 12/12] fscrypt: " Eric Biggers
2018-10-19 15:58 ` [RFC PATCH v2 00/12] crypto: " Jason A. Donenfeld
2018-10-19 18:19   ` Paul Crowley
2018-10-20  3:24     ` Ard Biesheuvel
2018-10-20  5:22       ` Eric Biggers
     [not found]     ` <2395454e-a0dc-408f-4138-9d15ab5f20b8@esat.kuleuven.be>
2018-10-22 11:20       ` Tomer Ashur
2018-10-19 19:04   ` Eric Biggers
2018-10-20 10:26     ` Milan Broz
2018-10-20 13:47       ` Jason A. Donenfeld
2018-11-16 21:52       ` Eric Biggers
2018-11-17 10:29         ` Milan Broz
2018-11-19 19:28           ` Eric Biggers
2018-11-19 20:05             ` Milan Broz
2018-11-19 20:30               ` Jason A. Donenfeld
2018-10-21 22:23     ` Eric Biggers
2018-10-21 22:51       ` Jason A. Donenfeld
2018-10-22 17:17         ` Paul Crowley

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=20181022184236.GA59695@gmail.com \
    --to=ebiggers@kernel.org \
    --cc=Jason@zx2c4.com \
    --cc=ard.biesheuvel@linaro.org \
    --cc=gkaiser@google.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-fscrypt@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mhalcrow@google.com \
    --cc=paulcrowley@google.com \
    --cc=samuel.c.p.neves@gmail.com \
    --cc=tomer.ashur@esat.kuleuven.be \
    --subject='Re: [RFC PATCH v2 09/12] crypto: nhpoly1305 - add NHPoly1305 support' \
    /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

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).